42112 lines
1.1 MiB
42112 lines
1.1 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.0172910662824206,
|
|
"eval_steps": 3000,
|
|
"global_step": 21000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691994762420654,
|
|
"epoch": 0.0004803073967339097,
|
|
"grad_norm": 13.0,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8298,
|
|
"mean_token_accuracy": 0.00017574692610651256,
|
|
"num_tokens": 10855.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.692014980316163,
|
|
"epoch": 0.0009606147934678194,
|
|
"grad_norm": 11.875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7988,
|
|
"mean_token_accuracy": 6.361323175951838e-05,
|
|
"num_tokens": 24110.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.691526508331298,
|
|
"epoch": 0.001440922190201729,
|
|
"grad_norm": 9.0625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.5635,
|
|
"mean_token_accuracy": 0.009693572070682421,
|
|
"num_tokens": 35984.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.687669563293458,
|
|
"epoch": 0.0019212295869356388,
|
|
"grad_norm": 5.875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.2633,
|
|
"mean_token_accuracy": 0.03138538394123316,
|
|
"num_tokens": 48152.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.66963233947754,
|
|
"epoch": 0.0024015369836695487,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.9747,
|
|
"mean_token_accuracy": 0.03182830363512039,
|
|
"num_tokens": 59810.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.646976470947266,
|
|
"epoch": 0.002881844380403458,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.7996,
|
|
"mean_token_accuracy": 0.030580480955541132,
|
|
"num_tokens": 70852.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.643668174743652,
|
|
"epoch": 0.0033621517771373678,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.7121,
|
|
"mean_token_accuracy": 0.044353676959872246,
|
|
"num_tokens": 83378.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.629865646362305,
|
|
"epoch": 0.0038424591738712775,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.6969,
|
|
"mean_token_accuracy": 0.03739585131406784,
|
|
"num_tokens": 95505.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.624952030181884,
|
|
"epoch": 0.004322766570605188,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.644,
|
|
"mean_token_accuracy": 0.03773416038602591,
|
|
"num_tokens": 106812.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.627149295806884,
|
|
"epoch": 0.004803073967339097,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.6128,
|
|
"mean_token_accuracy": 0.04628298096358776,
|
|
"num_tokens": 118572.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.618532657623291,
|
|
"epoch": 0.005283381364073006,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.536,
|
|
"mean_token_accuracy": 0.04271497819572687,
|
|
"num_tokens": 130051.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.595185852050781,
|
|
"epoch": 0.005763688760806916,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.4554,
|
|
"mean_token_accuracy": 0.05276048481464386,
|
|
"num_tokens": 141920.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.418802833557129,
|
|
"epoch": 0.006243996157540826,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.2853,
|
|
"mean_token_accuracy": 0.06248371712863445,
|
|
"num_tokens": 152706.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.36757173538208,
|
|
"epoch": 0.0067243035542747355,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.233,
|
|
"mean_token_accuracy": 0.060585541650652885,
|
|
"num_tokens": 165253.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.45568037033081,
|
|
"epoch": 0.007204610951008645,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.0994,
|
|
"mean_token_accuracy": 0.06531122252345085,
|
|
"num_tokens": 176708.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.3664475440979,
|
|
"epoch": 0.007684918347742555,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.0522,
|
|
"mean_token_accuracy": 0.06962743550539016,
|
|
"num_tokens": 188240.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.326856517791748,
|
|
"epoch": 0.008165225744476465,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 8.8157,
|
|
"mean_token_accuracy": 0.07712479382753372,
|
|
"num_tokens": 198355.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.325936794281006,
|
|
"epoch": 0.008645533141210375,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.7825,
|
|
"mean_token_accuracy": 0.06999509334564209,
|
|
"num_tokens": 209497.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.277573776245116,
|
|
"epoch": 0.009125840537944284,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.7287,
|
|
"mean_token_accuracy": 0.07384132854640484,
|
|
"num_tokens": 220859.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.238515377044678,
|
|
"epoch": 0.009606147934678195,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.7114,
|
|
"mean_token_accuracy": 0.0710748840123415,
|
|
"num_tokens": 231550.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.141935634613038,
|
|
"epoch": 0.010086455331412104,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.5351,
|
|
"mean_token_accuracy": 0.07423771843314171,
|
|
"num_tokens": 244210.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.091501617431641,
|
|
"epoch": 0.010566762728146013,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.4067,
|
|
"mean_token_accuracy": 0.07901745364069938,
|
|
"num_tokens": 255745.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.973632621765137,
|
|
"epoch": 0.011047070124879923,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.34,
|
|
"mean_token_accuracy": 0.07736451774835587,
|
|
"num_tokens": 266180.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.920284843444824,
|
|
"epoch": 0.011527377521613832,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.2139,
|
|
"mean_token_accuracy": 0.08326469734311104,
|
|
"num_tokens": 277736.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.804916763305664,
|
|
"epoch": 0.012007684918347743,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.1262,
|
|
"mean_token_accuracy": 0.08335627838969231,
|
|
"num_tokens": 289069.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.654496765136718,
|
|
"epoch": 0.012487992315081652,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.982,
|
|
"mean_token_accuracy": 0.0891214020550251,
|
|
"num_tokens": 300240.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.51935634613037,
|
|
"epoch": 0.012968299711815562,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.9186,
|
|
"mean_token_accuracy": 0.08641641587018967,
|
|
"num_tokens": 311698.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.386024379730225,
|
|
"epoch": 0.013448607108549471,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.8071,
|
|
"mean_token_accuracy": 0.08323717042803765,
|
|
"num_tokens": 322844.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.19943733215332,
|
|
"epoch": 0.013928914505283382,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.7047,
|
|
"mean_token_accuracy": 0.08635102547705173,
|
|
"num_tokens": 335092.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.99285430908203,
|
|
"epoch": 0.01440922190201729,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.5836,
|
|
"mean_token_accuracy": 0.09075271785259247,
|
|
"num_tokens": 347033.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.85265007019043,
|
|
"epoch": 0.014889529298751201,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.5019,
|
|
"mean_token_accuracy": 0.09151116386055946,
|
|
"num_tokens": 358696.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.618675422668456,
|
|
"epoch": 0.01536983669548511,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.4649,
|
|
"mean_token_accuracy": 0.09147786870598792,
|
|
"num_tokens": 369390.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.480183792114257,
|
|
"epoch": 0.01585014409221902,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.3834,
|
|
"mean_token_accuracy": 0.09084892570972443,
|
|
"num_tokens": 380540.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.312250709533691,
|
|
"epoch": 0.01633045148895293,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.3613,
|
|
"mean_token_accuracy": 0.08976613730192184,
|
|
"num_tokens": 391243.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.24670467376709,
|
|
"epoch": 0.01681075888568684,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.3067,
|
|
"mean_token_accuracy": 0.09706953838467598,
|
|
"num_tokens": 403336.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.182134532928467,
|
|
"epoch": 0.01729106628242075,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.2322,
|
|
"mean_token_accuracy": 0.09516221880912781,
|
|
"num_tokens": 413886.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.060572624206543,
|
|
"epoch": 0.01777137367915466,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.2831,
|
|
"mean_token_accuracy": 0.0937311127781868,
|
|
"num_tokens": 425277.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.067521953582764,
|
|
"epoch": 0.01825168107588857,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.3469,
|
|
"mean_token_accuracy": 0.10086444318294525,
|
|
"num_tokens": 436868.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.983385992050171,
|
|
"epoch": 0.018731988472622477,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.1829,
|
|
"mean_token_accuracy": 0.0981162391602993,
|
|
"num_tokens": 448349.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.912872409820556,
|
|
"epoch": 0.01921229586935639,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.1809,
|
|
"mean_token_accuracy": 0.1006820909678936,
|
|
"num_tokens": 459447.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.837088775634766,
|
|
"epoch": 0.0196926032660903,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.1355,
|
|
"mean_token_accuracy": 0.10290173068642616,
|
|
"num_tokens": 470734.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.882002639770508,
|
|
"epoch": 0.020172910662824207,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.1962,
|
|
"mean_token_accuracy": 0.09575840085744858,
|
|
"num_tokens": 482015.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.781675577163696,
|
|
"epoch": 0.020653218059558116,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.135,
|
|
"mean_token_accuracy": 0.10343812555074691,
|
|
"num_tokens": 493339.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.7119114875793455,
|
|
"epoch": 0.021133525456292025,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.0748,
|
|
"mean_token_accuracy": 0.10489624291658402,
|
|
"num_tokens": 504924.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.732145166397094,
|
|
"epoch": 0.021613832853025938,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.0553,
|
|
"mean_token_accuracy": 0.10040180832147598,
|
|
"num_tokens": 516603.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.646589851379394,
|
|
"epoch": 0.022094140249759846,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.9788,
|
|
"mean_token_accuracy": 0.10746042132377624,
|
|
"num_tokens": 528347.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.625714540481567,
|
|
"epoch": 0.022574447646493755,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.066,
|
|
"mean_token_accuracy": 0.10943897366523743,
|
|
"num_tokens": 539328.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.685968589782715,
|
|
"epoch": 0.023054755043227664,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.0299,
|
|
"mean_token_accuracy": 0.1110406532883644,
|
|
"num_tokens": 549297.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.528189706802368,
|
|
"epoch": 0.023535062439961577,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.9969,
|
|
"mean_token_accuracy": 0.1060897670686245,
|
|
"num_tokens": 560306.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.643190383911133,
|
|
"epoch": 0.024015369836695485,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.0794,
|
|
"mean_token_accuracy": 0.1051125854253769,
|
|
"num_tokens": 571972.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.565358638763428,
|
|
"epoch": 0.024495677233429394,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.9495,
|
|
"mean_token_accuracy": 0.1124962568283081,
|
|
"num_tokens": 582962.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.412648057937622,
|
|
"epoch": 0.024975984630163303,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.9282,
|
|
"mean_token_accuracy": 0.10846399590373039,
|
|
"num_tokens": 597193.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.551580333709717,
|
|
"epoch": 0.025456292026897216,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.009,
|
|
"mean_token_accuracy": 0.10793014243245125,
|
|
"num_tokens": 608982.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.537101221084595,
|
|
"epoch": 0.025936599423631124,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.0458,
|
|
"mean_token_accuracy": 0.10489416942000389,
|
|
"num_tokens": 619953.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.462128353118897,
|
|
"epoch": 0.026416906820365033,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.0194,
|
|
"mean_token_accuracy": 0.10800884142518044,
|
|
"num_tokens": 631039.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.485836219787598,
|
|
"epoch": 0.026897214217098942,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.9934,
|
|
"mean_token_accuracy": 0.11202432513237,
|
|
"num_tokens": 642656.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.342169904708863,
|
|
"epoch": 0.027377521613832854,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.8649,
|
|
"mean_token_accuracy": 0.12204736247658729,
|
|
"num_tokens": 653748.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.397694301605225,
|
|
"epoch": 0.027857829010566763,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.8424,
|
|
"mean_token_accuracy": 0.11272634193301201,
|
|
"num_tokens": 665618.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.279082107543945,
|
|
"epoch": 0.028338136407300672,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.8628,
|
|
"mean_token_accuracy": 0.11514977887272834,
|
|
"num_tokens": 677329.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.362811470031739,
|
|
"epoch": 0.02881844380403458,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.8424,
|
|
"mean_token_accuracy": 0.11373096629977227,
|
|
"num_tokens": 688278.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.34859447479248,
|
|
"epoch": 0.029298751200768493,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.9076,
|
|
"mean_token_accuracy": 0.11521193608641625,
|
|
"num_tokens": 700739.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.254595613479614,
|
|
"epoch": 0.029779058597502402,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.8432,
|
|
"mean_token_accuracy": 0.11028756424784661,
|
|
"num_tokens": 712527.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.202204751968384,
|
|
"epoch": 0.03025936599423631,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.864,
|
|
"mean_token_accuracy": 0.11237984746694565,
|
|
"num_tokens": 724514.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.36283130645752,
|
|
"epoch": 0.03073967339097022,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.8167,
|
|
"mean_token_accuracy": 0.11994114443659783,
|
|
"num_tokens": 735679.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.1851198196411135,
|
|
"epoch": 0.03121998078770413,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.8088,
|
|
"mean_token_accuracy": 0.11908385753631592,
|
|
"num_tokens": 747896.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.289603328704834,
|
|
"epoch": 0.03170028818443804,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.8518,
|
|
"mean_token_accuracy": 0.11320118606090546,
|
|
"num_tokens": 759081.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.253341245651245,
|
|
"epoch": 0.03218059558117195,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.7882,
|
|
"mean_token_accuracy": 0.1182114154100418,
|
|
"num_tokens": 770459.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.093820095062256,
|
|
"epoch": 0.03266090297790586,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.771,
|
|
"mean_token_accuracy": 0.11635568663477898,
|
|
"num_tokens": 783960.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.230938196182251,
|
|
"epoch": 0.03314121037463977,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.8633,
|
|
"mean_token_accuracy": 0.11809436529874802,
|
|
"num_tokens": 795425.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.197586011886597,
|
|
"epoch": 0.03362151777137368,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.8226,
|
|
"mean_token_accuracy": 0.11154912114143371,
|
|
"num_tokens": 807536.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.180789470672607,
|
|
"epoch": 0.034101825168107586,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.8588,
|
|
"mean_token_accuracy": 0.10917665809392929,
|
|
"num_tokens": 818801.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.213369083404541,
|
|
"epoch": 0.0345821325648415,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.7306,
|
|
"mean_token_accuracy": 0.11763328164815903,
|
|
"num_tokens": 831497.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.144342565536499,
|
|
"epoch": 0.03506243996157541,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.6993,
|
|
"mean_token_accuracy": 0.11783419996500015,
|
|
"num_tokens": 842491.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.148865461349487,
|
|
"epoch": 0.03554274735830932,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.7629,
|
|
"mean_token_accuracy": 0.11268699765205384,
|
|
"num_tokens": 854560.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.070219230651856,
|
|
"epoch": 0.03602305475504323,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.6713,
|
|
"mean_token_accuracy": 0.12674204707145692,
|
|
"num_tokens": 866688.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.121457624435425,
|
|
"epoch": 0.03650336215177714,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8012,
|
|
"mean_token_accuracy": 0.1115094892680645,
|
|
"num_tokens": 879484.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.130339431762695,
|
|
"epoch": 0.036983669548511046,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.7764,
|
|
"mean_token_accuracy": 0.11798848286271095,
|
|
"num_tokens": 890807.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.105965280532837,
|
|
"epoch": 0.037463976945244955,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7144,
|
|
"mean_token_accuracy": 0.12049998492002487,
|
|
"num_tokens": 901759.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.977410364151001,
|
|
"epoch": 0.037944284341978864,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.6589,
|
|
"mean_token_accuracy": 0.12746476903557777,
|
|
"num_tokens": 912212.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.118232536315918,
|
|
"epoch": 0.03842459173871278,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7486,
|
|
"mean_token_accuracy": 0.11947299242019653,
|
|
"num_tokens": 923947.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.024134111404419,
|
|
"epoch": 0.03890489913544669,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.6862,
|
|
"mean_token_accuracy": 0.12633359655737877,
|
|
"num_tokens": 935732.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.993129873275757,
|
|
"epoch": 0.0393852065321806,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.6445,
|
|
"mean_token_accuracy": 0.12226018980145455,
|
|
"num_tokens": 948261.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.054693984985351,
|
|
"epoch": 0.039865513928914506,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7483,
|
|
"mean_token_accuracy": 0.12283496558666229,
|
|
"num_tokens": 959574.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.068386030197144,
|
|
"epoch": 0.040345821325648415,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.8132,
|
|
"mean_token_accuracy": 0.1177711933851242,
|
|
"num_tokens": 970329.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.12344765663147,
|
|
"epoch": 0.040826128722382324,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.6619,
|
|
"mean_token_accuracy": 0.12985703051090242,
|
|
"num_tokens": 982037.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.886354589462281,
|
|
"epoch": 0.04130643611911623,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.6427,
|
|
"mean_token_accuracy": 0.12207310572266579,
|
|
"num_tokens": 994612.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.98868842124939,
|
|
"epoch": 0.04178674351585014,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7539,
|
|
"mean_token_accuracy": 0.1252766214311123,
|
|
"num_tokens": 1005960.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.9740221977233885,
|
|
"epoch": 0.04226705091258405,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.6033,
|
|
"mean_token_accuracy": 0.12968871667981147,
|
|
"num_tokens": 1017618.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.922601890563965,
|
|
"epoch": 0.042747358309317966,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.6465,
|
|
"mean_token_accuracy": 0.12342445105314255,
|
|
"num_tokens": 1029307.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.9612586975097654,
|
|
"epoch": 0.043227665706051875,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.6732,
|
|
"mean_token_accuracy": 0.12270124480128289,
|
|
"num_tokens": 1042027.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.969175624847412,
|
|
"epoch": 0.043707973102785784,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6708,
|
|
"mean_token_accuracy": 0.12182219475507736,
|
|
"num_tokens": 1053125.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.936508846282959,
|
|
"epoch": 0.04418828049951969,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.665,
|
|
"mean_token_accuracy": 0.12442595884203911,
|
|
"num_tokens": 1064908.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.912284183502197,
|
|
"epoch": 0.0446685878962536,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.5303,
|
|
"mean_token_accuracy": 0.13149212673306465,
|
|
"num_tokens": 1076328.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.9709954261779785,
|
|
"epoch": 0.04514889529298751,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7529,
|
|
"mean_token_accuracy": 0.11909845769405365,
|
|
"num_tokens": 1088469.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.846514415740967,
|
|
"epoch": 0.04562920268972142,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.5585,
|
|
"mean_token_accuracy": 0.12500514462590218,
|
|
"num_tokens": 1099408.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.745689010620117,
|
|
"epoch": 0.04610951008645533,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.4979,
|
|
"mean_token_accuracy": 0.13311537280678748,
|
|
"num_tokens": 1111101.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.8271801471710205,
|
|
"epoch": 0.046589817483189244,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.5075,
|
|
"mean_token_accuracy": 0.13259562402963637,
|
|
"num_tokens": 1122877.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.848812913894653,
|
|
"epoch": 0.04707012487992315,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.6051,
|
|
"mean_token_accuracy": 0.11904392987489701,
|
|
"num_tokens": 1133956.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.778984117507934,
|
|
"epoch": 0.04755043227665706,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.5109,
|
|
"mean_token_accuracy": 0.12579242512583733,
|
|
"num_tokens": 1146101.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.885318088531494,
|
|
"epoch": 0.04803073967339097,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6045,
|
|
"mean_token_accuracy": 0.1354927733540535,
|
|
"num_tokens": 1157432.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.818215417861938,
|
|
"epoch": 0.04851104707012488,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6063,
|
|
"mean_token_accuracy": 0.1280461445450783,
|
|
"num_tokens": 1167601.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.870798349380493,
|
|
"epoch": 0.04899135446685879,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.4939,
|
|
"mean_token_accuracy": 0.1299281470477581,
|
|
"num_tokens": 1178818.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.9249014377594,
|
|
"epoch": 0.0494716618635927,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7383,
|
|
"mean_token_accuracy": 0.12631357237696647,
|
|
"num_tokens": 1189977.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.810466480255127,
|
|
"epoch": 0.049951969260326606,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.5705,
|
|
"mean_token_accuracy": 0.12949271276593208,
|
|
"num_tokens": 1201039.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.855518198013305,
|
|
"epoch": 0.05043227665706052,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.5834,
|
|
"mean_token_accuracy": 0.13200551122426987,
|
|
"num_tokens": 1212573.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.824741506576538,
|
|
"epoch": 0.05091258405379443,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.5354,
|
|
"mean_token_accuracy": 0.13781235069036485,
|
|
"num_tokens": 1223382.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.7808338642120365,
|
|
"epoch": 0.05139289145052834,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6058,
|
|
"mean_token_accuracy": 0.1346134640276432,
|
|
"num_tokens": 1236501.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.873517370223999,
|
|
"epoch": 0.05187319884726225,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6176,
|
|
"mean_token_accuracy": 0.1229935683310032,
|
|
"num_tokens": 1246798.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.770853757858276,
|
|
"epoch": 0.05235350624399616,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.5278,
|
|
"mean_token_accuracy": 0.131402201205492,
|
|
"num_tokens": 1258182.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.721636343002319,
|
|
"epoch": 0.052833813640730067,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.4956,
|
|
"mean_token_accuracy": 0.12394713386893272,
|
|
"num_tokens": 1270273.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.748588562011719,
|
|
"epoch": 0.053314121037463975,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.564,
|
|
"mean_token_accuracy": 0.12861081212759018,
|
|
"num_tokens": 1281136.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.822348165512085,
|
|
"epoch": 0.053794428434197884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.5332,
|
|
"mean_token_accuracy": 0.1262042038142681,
|
|
"num_tokens": 1294488.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.638409280776978,
|
|
"epoch": 0.05427473583093179,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.4427,
|
|
"mean_token_accuracy": 0.1283183604478836,
|
|
"num_tokens": 1304113.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.839196443557739,
|
|
"epoch": 0.05475504322766571,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.4978,
|
|
"mean_token_accuracy": 0.13207686319947243,
|
|
"num_tokens": 1315417.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.662651681900025,
|
|
"epoch": 0.05523535062439962,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.4716,
|
|
"mean_token_accuracy": 0.13050151988863945,
|
|
"num_tokens": 1328084.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.7578453540802,
|
|
"epoch": 0.05571565802113353,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6132,
|
|
"mean_token_accuracy": 0.13093195483088493,
|
|
"num_tokens": 1338696.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.7748335838317875,
|
|
"epoch": 0.056195965417867436,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.562,
|
|
"mean_token_accuracy": 0.12585949748754502,
|
|
"num_tokens": 1350240.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.783541250228882,
|
|
"epoch": 0.056676272814601344,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.4932,
|
|
"mean_token_accuracy": 0.12611313983798028,
|
|
"num_tokens": 1361720.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.612882852554321,
|
|
"epoch": 0.05715658021133525,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5042,
|
|
"mean_token_accuracy": 0.13373664170503616,
|
|
"num_tokens": 1373286.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.7925944328308105,
|
|
"epoch": 0.05763688760806916,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.4551,
|
|
"mean_token_accuracy": 0.1283906377851963,
|
|
"num_tokens": 1384274.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.585460376739502,
|
|
"epoch": 0.05811719500480307,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4981,
|
|
"mean_token_accuracy": 0.13031432554125785,
|
|
"num_tokens": 1395355.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.695233345031738,
|
|
"epoch": 0.05859750240153699,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.432,
|
|
"mean_token_accuracy": 0.13920981362462043,
|
|
"num_tokens": 1406664.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.800591993331909,
|
|
"epoch": 0.059077809798270896,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.5881,
|
|
"mean_token_accuracy": 0.1273250959813595,
|
|
"num_tokens": 1418450.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.617939186096192,
|
|
"epoch": 0.059558117195004805,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.4711,
|
|
"mean_token_accuracy": 0.12932650744915009,
|
|
"num_tokens": 1430048.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.8016432762146,
|
|
"epoch": 0.060038424591738714,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5198,
|
|
"mean_token_accuracy": 0.12878495454788208,
|
|
"num_tokens": 1441820.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.6186442375183105,
|
|
"epoch": 0.06051873198847262,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.3647,
|
|
"mean_token_accuracy": 0.13323647081851958,
|
|
"num_tokens": 1453209.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.574874639511108,
|
|
"epoch": 0.06099903938520653,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.3786,
|
|
"mean_token_accuracy": 0.13276926502585412,
|
|
"num_tokens": 1465423.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.555490970611572,
|
|
"epoch": 0.06147934678194044,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.3747,
|
|
"mean_token_accuracy": 0.13574829548597336,
|
|
"num_tokens": 1476575.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.587315893173217,
|
|
"epoch": 0.06195965417867435,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.3322,
|
|
"mean_token_accuracy": 0.1344550520181656,
|
|
"num_tokens": 1486932.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.613981676101685,
|
|
"epoch": 0.06243996157540826,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.3728,
|
|
"mean_token_accuracy": 0.13380691781640053,
|
|
"num_tokens": 1498494.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.618697786331177,
|
|
"epoch": 0.06292026897214217,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.4205,
|
|
"mean_token_accuracy": 0.12903504446148872,
|
|
"num_tokens": 1509937.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.636468410491943,
|
|
"epoch": 0.06340057636887608,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.4578,
|
|
"mean_token_accuracy": 0.13971399664878845,
|
|
"num_tokens": 1519823.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.600921487808227,
|
|
"epoch": 0.06388088376560999,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.4917,
|
|
"mean_token_accuracy": 0.13139465302228928,
|
|
"num_tokens": 1529943.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.552580738067627,
|
|
"epoch": 0.0643611911623439,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.3208,
|
|
"mean_token_accuracy": 0.13542892634868622,
|
|
"num_tokens": 1540618.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.590906476974487,
|
|
"epoch": 0.06484149855907781,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.4445,
|
|
"mean_token_accuracy": 0.12609068006277085,
|
|
"num_tokens": 1553208.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.6104003429412845,
|
|
"epoch": 0.06532180595581172,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.3976,
|
|
"mean_token_accuracy": 0.13887525647878646,
|
|
"num_tokens": 1563975.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.60408387184143,
|
|
"epoch": 0.06580211335254563,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.4545,
|
|
"mean_token_accuracy": 0.12825093641877175,
|
|
"num_tokens": 1575998.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.527513599395752,
|
|
"epoch": 0.06628242074927954,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.3405,
|
|
"mean_token_accuracy": 0.1409427411854267,
|
|
"num_tokens": 1586041.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.5415153980255125,
|
|
"epoch": 0.06676272814601344,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4212,
|
|
"mean_token_accuracy": 0.13314746618270873,
|
|
"num_tokens": 1597531.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.584891843795776,
|
|
"epoch": 0.06724303554274735,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.3945,
|
|
"mean_token_accuracy": 0.13237977102398873,
|
|
"num_tokens": 1609255.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.540241670608521,
|
|
"epoch": 0.06772334293948126,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.3882,
|
|
"mean_token_accuracy": 0.1362485833466053,
|
|
"num_tokens": 1621098.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.483046913146973,
|
|
"epoch": 0.06820365033621517,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.2802,
|
|
"mean_token_accuracy": 0.14179484769701958,
|
|
"num_tokens": 1631941.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.428355741500854,
|
|
"epoch": 0.0686839577329491,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.2949,
|
|
"mean_token_accuracy": 0.1408768616616726,
|
|
"num_tokens": 1643117.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.48242449760437,
|
|
"epoch": 0.069164265129683,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.3234,
|
|
"mean_token_accuracy": 0.13696753680706025,
|
|
"num_tokens": 1653595.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.584324550628662,
|
|
"epoch": 0.06964457252641691,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.3559,
|
|
"mean_token_accuracy": 0.1360025905072689,
|
|
"num_tokens": 1664495.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.441131734848023,
|
|
"epoch": 0.07012487992315082,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.3516,
|
|
"mean_token_accuracy": 0.1386575371026993,
|
|
"num_tokens": 1674923.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.524987745285034,
|
|
"epoch": 0.07060518731988473,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.14099352359771727,
|
|
"num_tokens": 1685904.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.478848505020141,
|
|
"epoch": 0.07108549471661864,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4734,
|
|
"mean_token_accuracy": 0.12722889482975006,
|
|
"num_tokens": 1699133.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.433591699600219,
|
|
"epoch": 0.07156580211335255,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.13473247811198236,
|
|
"num_tokens": 1711559.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.478820514678955,
|
|
"epoch": 0.07204610951008646,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.14430032372474672,
|
|
"num_tokens": 1722526.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.378771543502808,
|
|
"epoch": 0.07252641690682037,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.2721,
|
|
"mean_token_accuracy": 0.14127281457185745,
|
|
"num_tokens": 1734261.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.47073130607605,
|
|
"epoch": 0.07300672430355427,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.2562,
|
|
"mean_token_accuracy": 0.14478438049554826,
|
|
"num_tokens": 1745151.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.5499794483184814,
|
|
"epoch": 0.07348703170028818,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4066,
|
|
"mean_token_accuracy": 0.13729395270347594,
|
|
"num_tokens": 1755463.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.480459976196289,
|
|
"epoch": 0.07396733909702209,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3553,
|
|
"mean_token_accuracy": 0.13681658804416658,
|
|
"num_tokens": 1767717.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.337383556365967,
|
|
"epoch": 0.074447646493756,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.2254,
|
|
"mean_token_accuracy": 0.14543235525488854,
|
|
"num_tokens": 1779115.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.324974822998047,
|
|
"epoch": 0.07492795389048991,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.1411907806992531,
|
|
"num_tokens": 1789644.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.443322086334229,
|
|
"epoch": 0.07540826128722382,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.3874,
|
|
"mean_token_accuracy": 0.13707425221800804,
|
|
"num_tokens": 1800606.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.4391655921936035,
|
|
"epoch": 0.07588856868395773,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.3836,
|
|
"mean_token_accuracy": 0.13318542316555976,
|
|
"num_tokens": 1812168.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.557193803787231,
|
|
"epoch": 0.07636887608069164,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.3292,
|
|
"mean_token_accuracy": 0.1308665730059147,
|
|
"num_tokens": 1823830.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.370806503295898,
|
|
"epoch": 0.07684918347742556,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.3024,
|
|
"mean_token_accuracy": 0.14099160134792327,
|
|
"num_tokens": 1835611.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.4798859596252445,
|
|
"epoch": 0.07732949087415947,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.3725,
|
|
"mean_token_accuracy": 0.1324798546731472,
|
|
"num_tokens": 1847036.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.354656791687011,
|
|
"epoch": 0.07780979827089338,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3285,
|
|
"mean_token_accuracy": 0.13368458151817322,
|
|
"num_tokens": 1857476.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.486216354370117,
|
|
"epoch": 0.07829010566762729,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.34,
|
|
"mean_token_accuracy": 0.1375596970319748,
|
|
"num_tokens": 1869073.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.291975498199463,
|
|
"epoch": 0.0787704130643612,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.1451445624232292,
|
|
"num_tokens": 1880439.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.534289789199829,
|
|
"epoch": 0.0792507204610951,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3752,
|
|
"mean_token_accuracy": 0.13702573478221894,
|
|
"num_tokens": 1891600.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.388027858734131,
|
|
"epoch": 0.07973102785782901,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3387,
|
|
"mean_token_accuracy": 0.1376413509249687,
|
|
"num_tokens": 1903126.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.4992616176605225,
|
|
"epoch": 0.08021133525456292,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3019,
|
|
"mean_token_accuracy": 0.14277714490890503,
|
|
"num_tokens": 1913913.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.272941446304321,
|
|
"epoch": 0.08069164265129683,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.225,
|
|
"mean_token_accuracy": 0.13915303945541382,
|
|
"num_tokens": 1924961.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.446083831787109,
|
|
"epoch": 0.08117195004803074,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3065,
|
|
"mean_token_accuracy": 0.1305370144546032,
|
|
"num_tokens": 1936773.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.336392736434936,
|
|
"epoch": 0.08165225744476465,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2366,
|
|
"mean_token_accuracy": 0.1390191063284874,
|
|
"num_tokens": 1948190.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.204436302185059,
|
|
"epoch": 0.08213256484149856,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.2183,
|
|
"mean_token_accuracy": 0.1443942204117775,
|
|
"num_tokens": 1960038.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.534562492370606,
|
|
"epoch": 0.08261287223823247,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3142,
|
|
"mean_token_accuracy": 0.14003733769059182,
|
|
"num_tokens": 1970535.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.319477272033692,
|
|
"epoch": 0.08309317963496637,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.2778,
|
|
"mean_token_accuracy": 0.13469554260373115,
|
|
"num_tokens": 1981386.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.3450806617736815,
|
|
"epoch": 0.08357348703170028,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2155,
|
|
"mean_token_accuracy": 0.14487679153680802,
|
|
"num_tokens": 1993196.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.35351300239563,
|
|
"epoch": 0.08405379442843419,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.2328,
|
|
"mean_token_accuracy": 0.14924731850624084,
|
|
"num_tokens": 2004756.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.282998752593994,
|
|
"epoch": 0.0845341018251681,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2067,
|
|
"mean_token_accuracy": 0.14092259407043456,
|
|
"num_tokens": 2016020.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.280064392089844,
|
|
"epoch": 0.08501440922190202,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.2503,
|
|
"mean_token_accuracy": 0.1401905208826065,
|
|
"num_tokens": 2027747.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.42980260848999,
|
|
"epoch": 0.08549471661863593,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.2409,
|
|
"mean_token_accuracy": 0.1382843941450119,
|
|
"num_tokens": 2038841.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.32186861038208,
|
|
"epoch": 0.08597502401536984,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.2849,
|
|
"mean_token_accuracy": 0.13336346074938774,
|
|
"num_tokens": 2049905.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.393303108215332,
|
|
"epoch": 0.08645533141210375,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3592,
|
|
"mean_token_accuracy": 0.13393715322017669,
|
|
"num_tokens": 2062492.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.300298881530762,
|
|
"epoch": 0.08693563880883766,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2929,
|
|
"mean_token_accuracy": 0.13643542900681496,
|
|
"num_tokens": 2073840.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.314391565322876,
|
|
"epoch": 0.08741594620557157,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.1959,
|
|
"mean_token_accuracy": 0.14078257232904434,
|
|
"num_tokens": 2085720.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.303665971755981,
|
|
"epoch": 0.08789625360230548,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2748,
|
|
"mean_token_accuracy": 0.14021435827016832,
|
|
"num_tokens": 2096649.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.352846956253051,
|
|
"epoch": 0.08837656099903939,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.2732,
|
|
"mean_token_accuracy": 0.14132813215255738,
|
|
"num_tokens": 2109030.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.3393628120422365,
|
|
"epoch": 0.0888568683957733,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.1974,
|
|
"mean_token_accuracy": 0.14321812987327576,
|
|
"num_tokens": 2121384.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.2493661403656,
|
|
"epoch": 0.0893371757925072,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.14775265604257584,
|
|
"num_tokens": 2131377.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.321423816680908,
|
|
"epoch": 0.08981748318924111,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.3338,
|
|
"mean_token_accuracy": 0.13767930790781974,
|
|
"num_tokens": 2142364.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.346617650985718,
|
|
"epoch": 0.09029779058597502,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.2031,
|
|
"mean_token_accuracy": 0.14090971127152443,
|
|
"num_tokens": 2153040.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.218026161193848,
|
|
"epoch": 0.09077809798270893,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.2617,
|
|
"mean_token_accuracy": 0.14209684506058692,
|
|
"num_tokens": 2165571.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.29831714630127,
|
|
"epoch": 0.09125840537944284,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.13673647940158845,
|
|
"num_tokens": 2177241.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.3340067863464355,
|
|
"epoch": 0.09173871277617675,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.1352509543299675,
|
|
"num_tokens": 2187475.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.255965852737427,
|
|
"epoch": 0.09221902017291066,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2969,
|
|
"mean_token_accuracy": 0.1429886355996132,
|
|
"num_tokens": 2198185.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.263639736175537,
|
|
"epoch": 0.09269932756964457,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2189,
|
|
"mean_token_accuracy": 0.14560386911034584,
|
|
"num_tokens": 2210404.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.340889978408813,
|
|
"epoch": 0.09317963496637849,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.1988,
|
|
"mean_token_accuracy": 0.14268205910921097,
|
|
"num_tokens": 2222188.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.228783655166626,
|
|
"epoch": 0.0936599423631124,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.2665,
|
|
"mean_token_accuracy": 0.14132686331868172,
|
|
"num_tokens": 2233418.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.285604953765869,
|
|
"epoch": 0.0941402497598463,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2257,
|
|
"mean_token_accuracy": 0.14632130712270736,
|
|
"num_tokens": 2245053.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.280080986022949,
|
|
"epoch": 0.09462055715658022,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.14620544537901878,
|
|
"num_tokens": 2256375.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.203731918334961,
|
|
"epoch": 0.09510086455331412,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.14922656118869781,
|
|
"num_tokens": 2267074.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.126199769973755,
|
|
"epoch": 0.09558117195004803,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.1454,
|
|
"mean_token_accuracy": 0.14771648943424226,
|
|
"num_tokens": 2277168.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.2248108863830565,
|
|
"epoch": 0.09606147934678194,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.1255,
|
|
"mean_token_accuracy": 0.1431685522198677,
|
|
"num_tokens": 2288178.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.142765951156616,
|
|
"epoch": 0.09654178674351585,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999983283737,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.14583995565772057,
|
|
"num_tokens": 2299765.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.346807956695557,
|
|
"epoch": 0.09702209414024976,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999999915373924,
|
|
"loss": 6.2432,
|
|
"mean_token_accuracy": 0.13548499941825867,
|
|
"num_tokens": 2312047.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.25492000579834,
|
|
"epoch": 0.09750240153698367,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999999795225793,
|
|
"loss": 6.2417,
|
|
"mean_token_accuracy": 0.13594504818320274,
|
|
"num_tokens": 2324118.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.260981035232544,
|
|
"epoch": 0.09798270893371758,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999999622839347,
|
|
"loss": 6.2336,
|
|
"mean_token_accuracy": 0.14039840698242187,
|
|
"num_tokens": 2335171.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.23499436378479,
|
|
"epoch": 0.09846301633045149,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999999398214593,
|
|
"loss": 6.1352,
|
|
"mean_token_accuracy": 0.14257553666830064,
|
|
"num_tokens": 2346338.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.206463623046875,
|
|
"epoch": 0.0989433237271854,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999121351532,
|
|
"loss": 6.1719,
|
|
"mean_token_accuracy": 0.14637897461652755,
|
|
"num_tokens": 2357185.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.176500654220581,
|
|
"epoch": 0.0994236311239193,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999998792250173,
|
|
"loss": 6.1065,
|
|
"mean_token_accuracy": 0.15227214843034745,
|
|
"num_tokens": 2368494.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.258463287353516,
|
|
"epoch": 0.09990393852065321,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999998410910524,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.1299520067870617,
|
|
"num_tokens": 2380800.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.313528776168823,
|
|
"epoch": 0.10038424591738712,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999997977332592,
|
|
"loss": 6.2431,
|
|
"mean_token_accuracy": 0.14309075325727463,
|
|
"num_tokens": 2391753.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.099646091461182,
|
|
"epoch": 0.10086455331412104,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999997491516389,
|
|
"loss": 6.1271,
|
|
"mean_token_accuracy": 0.13740728944540023,
|
|
"num_tokens": 2403324.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.263489484786987,
|
|
"epoch": 0.10134486071085495,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999996953461925,
|
|
"loss": 6.2272,
|
|
"mean_token_accuracy": 0.13747475668787956,
|
|
"num_tokens": 2414873.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.0689709186553955,
|
|
"epoch": 0.10182516810758886,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999996363169212,
|
|
"loss": 6.0125,
|
|
"mean_token_accuracy": 0.1530752882361412,
|
|
"num_tokens": 2425308.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.09112696647644,
|
|
"epoch": 0.10230547550432277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999995720638266,
|
|
"loss": 6.0554,
|
|
"mean_token_accuracy": 0.15447276532649995,
|
|
"num_tokens": 2436835.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.165467739105225,
|
|
"epoch": 0.10278578290105668,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00049999950258691,
|
|
"loss": 6.1774,
|
|
"mean_token_accuracy": 0.1442865952849388,
|
|
"num_tokens": 2446798.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.124160242080689,
|
|
"epoch": 0.10326609029779059,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999994278861731,
|
|
"loss": 6.0595,
|
|
"mean_token_accuracy": 0.14578312933444976,
|
|
"num_tokens": 2457308.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.178969097137451,
|
|
"epoch": 0.1037463976945245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999993479616175,
|
|
"loss": 6.1251,
|
|
"mean_token_accuracy": 0.13860208466649054,
|
|
"num_tokens": 2468917.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.162839746475219,
|
|
"epoch": 0.1042267050912584,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999992628132451,
|
|
"loss": 6.1411,
|
|
"mean_token_accuracy": 0.13992882445454596,
|
|
"num_tokens": 2481363.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.167838716506958,
|
|
"epoch": 0.10470701248799232,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999991724410582,
|
|
"loss": 6.1495,
|
|
"mean_token_accuracy": 0.1436173811554909,
|
|
"num_tokens": 2493082.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.146947622299194,
|
|
"epoch": 0.10518731988472622,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999990768450583,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.14399811923503875,
|
|
"num_tokens": 2503849.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.146644163131714,
|
|
"epoch": 0.10566762728146013,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999989760252482,
|
|
"loss": 6.1399,
|
|
"mean_token_accuracy": 0.14404821395874023,
|
|
"num_tokens": 2514528.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.133210849761963,
|
|
"epoch": 0.10614793467819404,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999988699816299,
|
|
"loss": 6.1223,
|
|
"mean_token_accuracy": 0.1479478061199188,
|
|
"num_tokens": 2524971.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.089270114898682,
|
|
"epoch": 0.10662824207492795,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999987587142058,
|
|
"loss": 6.0441,
|
|
"mean_token_accuracy": 0.14856501221656798,
|
|
"num_tokens": 2535674.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.2527556896209715,
|
|
"epoch": 0.10710854947166186,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999986422229789,
|
|
"loss": 6.273,
|
|
"mean_token_accuracy": 0.13680738657712938,
|
|
"num_tokens": 2547108.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.12102518081665,
|
|
"epoch": 0.10758885686839577,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999985205079514,
|
|
"loss": 6.09,
|
|
"mean_token_accuracy": 0.1455679714679718,
|
|
"num_tokens": 2559474.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 5.961005830764771,
|
|
"epoch": 0.10806916426512968,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999983935691265,
|
|
"loss": 5.9472,
|
|
"mean_token_accuracy": 0.16263456791639327,
|
|
"num_tokens": 2571264.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.1322558403015135,
|
|
"epoch": 0.10854947166186359,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499998261406507,
|
|
"loss": 6.1162,
|
|
"mean_token_accuracy": 0.1466919831931591,
|
|
"num_tokens": 2583731.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.223382377624512,
|
|
"epoch": 0.10902977905859751,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999981240200958,
|
|
"loss": 6.159,
|
|
"mean_token_accuracy": 0.14457977414131165,
|
|
"num_tokens": 2595497.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.054231023788452,
|
|
"epoch": 0.10951008645533142,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999979814098966,
|
|
"loss": 6.1182,
|
|
"mean_token_accuracy": 0.14522254467010498,
|
|
"num_tokens": 2607358.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.160077381134033,
|
|
"epoch": 0.10999039385206533,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999978335759121,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.15187736079096795,
|
|
"num_tokens": 2618936.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.127855730056763,
|
|
"epoch": 0.11047070124879924,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999976805181461,
|
|
"loss": 6.1975,
|
|
"mean_token_accuracy": 0.138966653496027,
|
|
"num_tokens": 2631840.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.094377899169922,
|
|
"epoch": 0.11095100864553314,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499997522236602,
|
|
"loss": 6.1264,
|
|
"mean_token_accuracy": 0.1518709197640419,
|
|
"num_tokens": 2642412.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.152898597717285,
|
|
"epoch": 0.11143131604226705,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999973587312837,
|
|
"loss": 6.0987,
|
|
"mean_token_accuracy": 0.14559589624404906,
|
|
"num_tokens": 2653890.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.167875289916992,
|
|
"epoch": 0.11191162343900096,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999971900021947,
|
|
"loss": 6.1535,
|
|
"mean_token_accuracy": 0.15283165276050567,
|
|
"num_tokens": 2664888.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.071065759658813,
|
|
"epoch": 0.11239193083573487,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999970160493391,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.14622594192624092,
|
|
"num_tokens": 2675550.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.0063920497894285,
|
|
"epoch": 0.11287223823246878,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999968368727209,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.15350247249007226,
|
|
"num_tokens": 2688022.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.19563660621643,
|
|
"epoch": 0.11335254562920269,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999966524723442,
|
|
"loss": 6.0585,
|
|
"mean_token_accuracy": 0.14814461022615433,
|
|
"num_tokens": 2698737.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 5.993877696990967,
|
|
"epoch": 0.1138328530259366,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999964628482135,
|
|
"loss": 6.0264,
|
|
"mean_token_accuracy": 0.1589604675769806,
|
|
"num_tokens": 2709844.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.143397569656372,
|
|
"epoch": 0.1143131604226705,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999962680003328,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.15612745732069017,
|
|
"num_tokens": 2720273.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.110628890991211,
|
|
"epoch": 0.11479346781940442,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499996067928707,
|
|
"loss": 6.1046,
|
|
"mean_token_accuracy": 0.14770417958498,
|
|
"num_tokens": 2731354.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.056782531738281,
|
|
"epoch": 0.11527377521613832,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999958626333406,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.15016127973794938,
|
|
"num_tokens": 2742966.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.037007665634155,
|
|
"epoch": 0.11575408261287223,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999956521142383,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.15777237117290496,
|
|
"num_tokens": 2755010.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.1013503074646,
|
|
"epoch": 0.11623439000960614,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999954363714051,
|
|
"loss": 6.0362,
|
|
"mean_token_accuracy": 0.1465275302529335,
|
|
"num_tokens": 2766176.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.126735496520996,
|
|
"epoch": 0.11671469740634005,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999952154048459,
|
|
"loss": 6.1767,
|
|
"mean_token_accuracy": 0.1463685430586338,
|
|
"num_tokens": 2777861.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.039095830917359,
|
|
"epoch": 0.11719500480307397,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499994989214566,
|
|
"loss": 5.9973,
|
|
"mean_token_accuracy": 0.1520916223526001,
|
|
"num_tokens": 2788725.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 5.984258842468262,
|
|
"epoch": 0.11767531219980788,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999947578005705,
|
|
"loss": 6.0395,
|
|
"mean_token_accuracy": 0.15116385817527772,
|
|
"num_tokens": 2801613.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.119243383407593,
|
|
"epoch": 0.11815561959654179,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999945211628648,
|
|
"loss": 6.1088,
|
|
"mean_token_accuracy": 0.1472545124590397,
|
|
"num_tokens": 2812474.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 5.99455075263977,
|
|
"epoch": 0.1186359269932757,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999942793014544,
|
|
"loss": 6.0074,
|
|
"mean_token_accuracy": 0.15461577028036116,
|
|
"num_tokens": 2823178.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.0010467052459715,
|
|
"epoch": 0.11911623439000961,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499994032216345,
|
|
"loss": 6.0073,
|
|
"mean_token_accuracy": 0.15202462002635003,
|
|
"num_tokens": 2836486.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.10334792137146,
|
|
"epoch": 0.11959654178674352,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999937799075422,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.15411641150712968,
|
|
"num_tokens": 2847902.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 5.905390882492066,
|
|
"epoch": 0.12007684918347743,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499993522375052,
|
|
"loss": 5.9685,
|
|
"mean_token_accuracy": 0.15486289709806442,
|
|
"num_tokens": 2859991.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.18690938949585,
|
|
"epoch": 0.12055715658021134,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999932596188802,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.14711093232035638,
|
|
"num_tokens": 2870269.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.073237323760987,
|
|
"epoch": 0.12103746397694524,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999929916390331,
|
|
"loss": 6.0326,
|
|
"mean_token_accuracy": 0.14399343878030776,
|
|
"num_tokens": 2882191.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 5.968440008163452,
|
|
"epoch": 0.12151777137367915,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999927184355169,
|
|
"loss": 6.0411,
|
|
"mean_token_accuracy": 0.14858935698866843,
|
|
"num_tokens": 2892775.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.032851934432983,
|
|
"epoch": 0.12199807877041306,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999924400083377,
|
|
"loss": 6.0188,
|
|
"mean_token_accuracy": 0.15558268502354622,
|
|
"num_tokens": 2904750.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.158710575103759,
|
|
"epoch": 0.12247838616714697,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999921563575022,
|
|
"loss": 6.0977,
|
|
"mean_token_accuracy": 0.14594096317887306,
|
|
"num_tokens": 2916150.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.050063037872315,
|
|
"epoch": 0.12295869356388088,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999918674830169,
|
|
"loss": 6.0618,
|
|
"mean_token_accuracy": 0.14690043553709983,
|
|
"num_tokens": 2928452.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.043630933761596,
|
|
"epoch": 0.12343900096061479,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999915733848886,
|
|
"loss": 6.0461,
|
|
"mean_token_accuracy": 0.14408571869134904,
|
|
"num_tokens": 2940577.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 5.969705057144165,
|
|
"epoch": 0.1239193083573487,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499991274063124,
|
|
"loss": 6.0197,
|
|
"mean_token_accuracy": 0.1521909199655056,
|
|
"num_tokens": 2952302.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.062735939025879,
|
|
"epoch": 0.12439961575408261,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999909695177301,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.15105145871639253,
|
|
"num_tokens": 2964611.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.10636625289917,
|
|
"epoch": 0.12487992315081652,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499990659748714,
|
|
"loss": 6.0592,
|
|
"mean_token_accuracy": 0.14832675009965895,
|
|
"num_tokens": 2975668.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.1376677513122555,
|
|
"epoch": 0.12536023054755044,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999903447560828,
|
|
"loss": 6.117,
|
|
"mean_token_accuracy": 0.14772927314043044,
|
|
"num_tokens": 2987303.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.051840353012085,
|
|
"epoch": 0.12584053794428435,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999900245398439,
|
|
"loss": 6.0254,
|
|
"mean_token_accuracy": 0.15303617119789123,
|
|
"num_tokens": 3000400.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.011703777313232,
|
|
"epoch": 0.12632084534101826,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999896991000047,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.1523553252220154,
|
|
"num_tokens": 3012336.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.029785680770874,
|
|
"epoch": 0.12680115273775217,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999893684365729,
|
|
"loss": 6.0096,
|
|
"mean_token_accuracy": 0.15119000896811485,
|
|
"num_tokens": 3023004.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 5.994943571090698,
|
|
"epoch": 0.12728146013448607,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999890325495559,
|
|
"loss": 6.1015,
|
|
"mean_token_accuracy": 0.14477866813540458,
|
|
"num_tokens": 3035147.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.066337728500367,
|
|
"epoch": 0.12776176753121998,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999886914389617,
|
|
"loss": 5.9232,
|
|
"mean_token_accuracy": 0.1547378495335579,
|
|
"num_tokens": 3045611.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 5.912863159179688,
|
|
"epoch": 0.1282420749279539,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999883451047981,
|
|
"loss": 5.9387,
|
|
"mean_token_accuracy": 0.15571426451206208,
|
|
"num_tokens": 3056420.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 5.993097162246704,
|
|
"epoch": 0.1287223823246878,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999879935470733,
|
|
"loss": 5.9405,
|
|
"mean_token_accuracy": 0.1529444746673107,
|
|
"num_tokens": 3068770.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.023547983169555,
|
|
"epoch": 0.1292026897214217,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999876367657954,
|
|
"loss": 6.0563,
|
|
"mean_token_accuracy": 0.14409474655985832,
|
|
"num_tokens": 3080806.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.111025857925415,
|
|
"epoch": 0.12968299711815562,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999872747609725,
|
|
"loss": 6.0713,
|
|
"mean_token_accuracy": 0.14507278203964233,
|
|
"num_tokens": 3091769.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 5.956837129592896,
|
|
"epoch": 0.13016330451488953,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999869075326132,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.15012748390436173,
|
|
"num_tokens": 3103121.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.027207374572754,
|
|
"epoch": 0.13064361191162344,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499986535080726,
|
|
"loss": 5.9609,
|
|
"mean_token_accuracy": 0.15629629492759706,
|
|
"num_tokens": 3115606.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 5.960008859634399,
|
|
"epoch": 0.13112391930835735,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999861574053196,
|
|
"loss": 5.8764,
|
|
"mean_token_accuracy": 0.15644163638353348,
|
|
"num_tokens": 3127961.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 5.850315856933594,
|
|
"epoch": 0.13160422670509125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999857745064027,
|
|
"loss": 5.8877,
|
|
"mean_token_accuracy": 0.15920821577310562,
|
|
"num_tokens": 3138316.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 5.928855562210083,
|
|
"epoch": 0.13208453410182516,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499985386383984,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.15633490532636643,
|
|
"num_tokens": 3150818.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 5.971828317642212,
|
|
"epoch": 0.13256484149855907,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999849930380729,
|
|
"loss": 6.0293,
|
|
"mean_token_accuracy": 0.1495520919561386,
|
|
"num_tokens": 3162066.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 5.955291509628296,
|
|
"epoch": 0.13304514889529298,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999845944686781,
|
|
"loss": 5.9953,
|
|
"mean_token_accuracy": 0.1490943156182766,
|
|
"num_tokens": 3172209.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 5.91329345703125,
|
|
"epoch": 0.1335254562920269,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999841906758093,
|
|
"loss": 5.8221,
|
|
"mean_token_accuracy": 0.16563501954078674,
|
|
"num_tokens": 3183248.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.891427898406983,
|
|
"epoch": 0.1340057636887608,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999837816594757,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.15676223784685134,
|
|
"num_tokens": 3194748.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.952425384521485,
|
|
"epoch": 0.1344860710854947,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999833674196865,
|
|
"loss": 5.8884,
|
|
"mean_token_accuracy": 0.16636295914649962,
|
|
"num_tokens": 3205669.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 5.914532804489136,
|
|
"epoch": 0.13496637848222862,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999829479564518,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.14935347959399223,
|
|
"num_tokens": 3216035.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.010363340377808,
|
|
"epoch": 0.13544668587896252,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499982523269781,
|
|
"loss": 5.9699,
|
|
"mean_token_accuracy": 0.1579734966158867,
|
|
"num_tokens": 3227192.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 5.964124011993408,
|
|
"epoch": 0.13592699327569643,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999820933596842,
|
|
"loss": 5.9985,
|
|
"mean_token_accuracy": 0.15174955129623413,
|
|
"num_tokens": 3240237.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 5.98430118560791,
|
|
"epoch": 0.13640730067243034,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499981658226171,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.16217702850699425,
|
|
"num_tokens": 3251963.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 5.839476776123047,
|
|
"epoch": 0.13688760806916425,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499981217869252,
|
|
"loss": 5.9987,
|
|
"mean_token_accuracy": 0.15809622257947922,
|
|
"num_tokens": 3263101.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 5.9774946689605715,
|
|
"epoch": 0.1373679154658982,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499980772288937,
|
|
"loss": 5.8689,
|
|
"mean_token_accuracy": 0.16284565776586532,
|
|
"num_tokens": 3275100.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 5.925450658798217,
|
|
"epoch": 0.1378482228626321,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999803214852367,
|
|
"loss": 5.9703,
|
|
"mean_token_accuracy": 0.15639356076717376,
|
|
"num_tokens": 3287025.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.026112604141235,
|
|
"epoch": 0.138328530259366,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999798654581613,
|
|
"loss": 5.9803,
|
|
"mean_token_accuracy": 0.1564973570406437,
|
|
"num_tokens": 3299867.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 5.93130669593811,
|
|
"epoch": 0.13880883765609991,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999794042077214,
|
|
"loss": 5.9138,
|
|
"mean_token_accuracy": 0.15421272069215775,
|
|
"num_tokens": 3311183.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.9360240459442135,
|
|
"epoch": 0.13928914505283382,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999789377339279,
|
|
"loss": 5.9876,
|
|
"mean_token_accuracy": 0.1524989053606987,
|
|
"num_tokens": 3322247.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.935307788848877,
|
|
"epoch": 0.13976945244956773,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999784660367915,
|
|
"loss": 5.8929,
|
|
"mean_token_accuracy": 0.1573137417435646,
|
|
"num_tokens": 3333369.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 5.8698266506195065,
|
|
"epoch": 0.14024975984630164,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999779891163231,
|
|
"loss": 5.9246,
|
|
"mean_token_accuracy": 0.15648573487997056,
|
|
"num_tokens": 3345876.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 5.949500894546508,
|
|
"epoch": 0.14073006724303555,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999775069725339,
|
|
"loss": 5.8207,
|
|
"mean_token_accuracy": 0.1597806304693222,
|
|
"num_tokens": 3357323.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.861354398727417,
|
|
"epoch": 0.14121037463976946,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499977019605435,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.15788870602846145,
|
|
"num_tokens": 3367689.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.8307782173156735,
|
|
"epoch": 0.14169068203650337,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999765270150378,
|
|
"loss": 5.8743,
|
|
"mean_token_accuracy": 0.1602980002760887,
|
|
"num_tokens": 3379472.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.964514970779419,
|
|
"epoch": 0.14217098943323728,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999760292013536,
|
|
"loss": 5.9186,
|
|
"mean_token_accuracy": 0.15641037970781327,
|
|
"num_tokens": 3390929.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.022605943679809,
|
|
"epoch": 0.14265129682997119,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999755261643941,
|
|
"loss": 5.905,
|
|
"mean_token_accuracy": 0.1637382462620735,
|
|
"num_tokens": 3401242.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.793807697296143,
|
|
"epoch": 0.1431316042267051,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999750179041709,
|
|
"loss": 5.8881,
|
|
"mean_token_accuracy": 0.15650701224803926,
|
|
"num_tokens": 3411169.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.8970543384552006,
|
|
"epoch": 0.143611911623439,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999745044206959,
|
|
"loss": 5.7408,
|
|
"mean_token_accuracy": 0.16639568358659745,
|
|
"num_tokens": 3423265.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.791120100021362,
|
|
"epoch": 0.1440922190201729,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999739857139809,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.16577493995428086,
|
|
"num_tokens": 3434793.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 5.775409364700318,
|
|
"epoch": 0.14457252641690682,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499973461784038,
|
|
"loss": 5.7786,
|
|
"mean_token_accuracy": 0.17025359869003295,
|
|
"num_tokens": 3445732.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.93105673789978,
|
|
"epoch": 0.14505283381364073,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999729326308792,
|
|
"loss": 5.9634,
|
|
"mean_token_accuracy": 0.1571228712797165,
|
|
"num_tokens": 3457090.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.9968592643737795,
|
|
"epoch": 0.14553314121037464,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499972398254517,
|
|
"loss": 5.9388,
|
|
"mean_token_accuracy": 0.15059952139854432,
|
|
"num_tokens": 3468087.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.91447343826294,
|
|
"epoch": 0.14601344860710855,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499971858654964,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.15860198959708213,
|
|
"num_tokens": 3478820.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.818390035629273,
|
|
"epoch": 0.14649375600384246,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999713138322321,
|
|
"loss": 5.9116,
|
|
"mean_token_accuracy": 0.1562931038439274,
|
|
"num_tokens": 3489878.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.955449724197388,
|
|
"epoch": 0.14697406340057637,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999707637863346,
|
|
"loss": 5.8924,
|
|
"mean_token_accuracy": 0.15876611322164536,
|
|
"num_tokens": 3500944.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.860537052154541,
|
|
"epoch": 0.14745437079731027,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999702085172838,
|
|
"loss": 5.8845,
|
|
"mean_token_accuracy": 0.15949865728616713,
|
|
"num_tokens": 3511383.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.9207518100738525,
|
|
"epoch": 0.14793467819404418,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999696480250929,
|
|
"loss": 5.9694,
|
|
"mean_token_accuracy": 0.15462590605020524,
|
|
"num_tokens": 3523300.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.986819219589234,
|
|
"epoch": 0.1484149855907781,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999690823097747,
|
|
"loss": 5.8881,
|
|
"mean_token_accuracy": 0.1520873211324215,
|
|
"num_tokens": 3534371.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.836016654968262,
|
|
"epoch": 0.148895292987512,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999685113713426,
|
|
"loss": 5.8587,
|
|
"mean_token_accuracy": 0.15948065519332885,
|
|
"num_tokens": 3544847.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.924603080749511,
|
|
"epoch": 0.1493756003842459,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999679352098096,
|
|
"loss": 5.8315,
|
|
"mean_token_accuracy": 0.16097427457571029,
|
|
"num_tokens": 3555859.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.79734616279602,
|
|
"epoch": 0.14985590778097982,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999673538251891,
|
|
"loss": 5.8566,
|
|
"mean_token_accuracy": 0.16221377849578858,
|
|
"num_tokens": 3568283.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.874051904678344,
|
|
"epoch": 0.15033621517771373,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999667672174947,
|
|
"loss": 5.936,
|
|
"mean_token_accuracy": 0.15294544994831086,
|
|
"num_tokens": 3581442.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.990495872497559,
|
|
"epoch": 0.15081652257444764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049996617538674,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.152780419588089,
|
|
"num_tokens": 3594055.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.927357292175293,
|
|
"epoch": 0.15129682997118155,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999655783329386,
|
|
"loss": 5.9306,
|
|
"mean_token_accuracy": 0.15304084718227387,
|
|
"num_tokens": 3605952.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.955839014053344,
|
|
"epoch": 0.15177713736791545,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999649760561046,
|
|
"loss": 5.9639,
|
|
"mean_token_accuracy": 0.15580520704388617,
|
|
"num_tokens": 3618544.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.893008375167847,
|
|
"epoch": 0.15225744476464936,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999643685562519,
|
|
"loss": 5.9039,
|
|
"mean_token_accuracy": 0.16198357045650483,
|
|
"num_tokens": 3630445.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.909841632843017,
|
|
"epoch": 0.15273775216138327,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999637558333945,
|
|
"loss": 5.8977,
|
|
"mean_token_accuracy": 0.15822411477565765,
|
|
"num_tokens": 3642516.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.8553213596344,
|
|
"epoch": 0.15321805955811718,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999631378875467,
|
|
"loss": 5.8313,
|
|
"mean_token_accuracy": 0.16457842588424682,
|
|
"num_tokens": 3654425.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.782710266113281,
|
|
"epoch": 0.15369836695485112,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999625147187228,
|
|
"loss": 5.8311,
|
|
"mean_token_accuracy": 0.16059335172176362,
|
|
"num_tokens": 3666521.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.004714059829712,
|
|
"epoch": 0.15417867435158503,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999618863269373,
|
|
"loss": 5.8901,
|
|
"mean_token_accuracy": 0.1548692986369133,
|
|
"num_tokens": 3679121.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.864198493957519,
|
|
"epoch": 0.15465898174831894,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999612527122049,
|
|
"loss": 5.8955,
|
|
"mean_token_accuracy": 0.15978342294692993,
|
|
"num_tokens": 3691095.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.847317218780518,
|
|
"epoch": 0.15513928914505284,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999606138745402,
|
|
"loss": 5.8793,
|
|
"mean_token_accuracy": 0.16035235822200775,
|
|
"num_tokens": 3703426.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.953561687469483,
|
|
"epoch": 0.15561959654178675,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999599698139581,
|
|
"loss": 5.9444,
|
|
"mean_token_accuracy": 0.1594718113541603,
|
|
"num_tokens": 3715429.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.9446728229522705,
|
|
"epoch": 0.15609990393852066,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999593205304734,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.1545853793621063,
|
|
"num_tokens": 3726327.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.84681715965271,
|
|
"epoch": 0.15658021133525457,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999586660241012,
|
|
"loss": 5.8669,
|
|
"mean_token_accuracy": 0.1516711249947548,
|
|
"num_tokens": 3736818.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 5.9327000141143795,
|
|
"epoch": 0.15706051873198848,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999580062948569,
|
|
"loss": 5.8792,
|
|
"mean_token_accuracy": 0.1590345323085785,
|
|
"num_tokens": 3747776.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.772314119338989,
|
|
"epoch": 0.1575408261287224,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999573413427556,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.16504391878843308,
|
|
"num_tokens": 3758990.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.833576440811157,
|
|
"epoch": 0.1580211335254563,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999566711678128,
|
|
"loss": 5.8008,
|
|
"mean_token_accuracy": 0.1592164508998394,
|
|
"num_tokens": 3769686.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.878905963897705,
|
|
"epoch": 0.1585014409221902,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999559957700442,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.1629639074206352,
|
|
"num_tokens": 3781815.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.876691675186157,
|
|
"epoch": 0.15898174831892412,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999553151494653,
|
|
"loss": 5.9186,
|
|
"mean_token_accuracy": 0.15917147397994996,
|
|
"num_tokens": 3793392.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.906066942214966,
|
|
"epoch": 0.15946205571565802,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999546293060919,
|
|
"loss": 5.8438,
|
|
"mean_token_accuracy": 0.15719185918569564,
|
|
"num_tokens": 3804974.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.735585021972656,
|
|
"epoch": 0.15994236311239193,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00049995393823994,
|
|
"loss": 5.7178,
|
|
"mean_token_accuracy": 0.1695894032716751,
|
|
"num_tokens": 3817166.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.842826509475708,
|
|
"epoch": 0.16042267050912584,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999532419510255,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.1561794638633728,
|
|
"num_tokens": 3828151.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.824618721008301,
|
|
"epoch": 0.16090297790585975,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499952540439365,
|
|
"loss": 5.8509,
|
|
"mean_token_accuracy": 0.15955035239458085,
|
|
"num_tokens": 3839439.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.892849397659302,
|
|
"epoch": 0.16138328530259366,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999518337049743,
|
|
"loss": 5.8922,
|
|
"mean_token_accuracy": 0.15924266576766968,
|
|
"num_tokens": 3851694.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.856962966918945,
|
|
"epoch": 0.16186359269932757,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049995112174787,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.1590324103832245,
|
|
"num_tokens": 3863593.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.7850672721862795,
|
|
"epoch": 0.16234390009606148,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999504045680687,
|
|
"loss": 5.7881,
|
|
"mean_token_accuracy": 0.16856220066547395,
|
|
"num_tokens": 3874588.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.888552188873291,
|
|
"epoch": 0.1628242074927954,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999496821655869,
|
|
"loss": 5.8923,
|
|
"mean_token_accuracy": 0.15879060029983522,
|
|
"num_tokens": 3884662.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.994271564483642,
|
|
"epoch": 0.1633045148895293,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999489545404414,
|
|
"loss": 5.9752,
|
|
"mean_token_accuracy": 0.15433130860328675,
|
|
"num_tokens": 3896569.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.953902006149292,
|
|
"epoch": 0.1637848222862632,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999482216926493,
|
|
"loss": 5.8156,
|
|
"mean_token_accuracy": 0.16419725492596626,
|
|
"num_tokens": 3907691.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.858258485794067,
|
|
"epoch": 0.1642651296829971,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999474836222273,
|
|
"loss": 5.8577,
|
|
"mean_token_accuracy": 0.16659338772296906,
|
|
"num_tokens": 3918794.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.810220861434937,
|
|
"epoch": 0.16474543707973102,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999467403291928,
|
|
"loss": 5.8451,
|
|
"mean_token_accuracy": 0.170916186273098,
|
|
"num_tokens": 3929773.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.874481058120727,
|
|
"epoch": 0.16522574447646493,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999459918135628,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.15871367529034613,
|
|
"num_tokens": 3940264.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.773836088180542,
|
|
"epoch": 0.16570605187319884,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499945238075355,
|
|
"loss": 5.7441,
|
|
"mean_token_accuracy": 0.17102676779031753,
|
|
"num_tokens": 3951500.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.826447868347168,
|
|
"epoch": 0.16618635926993275,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999444791145865,
|
|
"loss": 5.8218,
|
|
"mean_token_accuracy": 0.16380431354045868,
|
|
"num_tokens": 3963580.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.825805950164795,
|
|
"epoch": 0.16666666666666666,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999437149312754,
|
|
"loss": 5.7672,
|
|
"mean_token_accuracy": 0.17581460922956466,
|
|
"num_tokens": 3975994.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.801591205596924,
|
|
"epoch": 0.16714697406340057,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499942945525439,
|
|
"loss": 5.776,
|
|
"mean_token_accuracy": 0.15901320427656174,
|
|
"num_tokens": 3987897.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.858685302734375,
|
|
"epoch": 0.16762728146013448,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999421708970954,
|
|
"loss": 5.9475,
|
|
"mean_token_accuracy": 0.15513574853539466,
|
|
"num_tokens": 3999829.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.771667766571045,
|
|
"epoch": 0.16810758885686838,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999413910462625,
|
|
"loss": 5.7651,
|
|
"mean_token_accuracy": 0.165543270111084,
|
|
"num_tokens": 4010882.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.86086745262146,
|
|
"epoch": 0.1685878962536023,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999406059729586,
|
|
"loss": 5.7506,
|
|
"mean_token_accuracy": 0.1660080999135971,
|
|
"num_tokens": 4021423.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.8848597526550295,
|
|
"epoch": 0.1690682036503362,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999398156772016,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.14788322001695633,
|
|
"num_tokens": 4033590.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.708123207092285,
|
|
"epoch": 0.16954851104707014,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049993902015901,
|
|
"loss": 5.76,
|
|
"mean_token_accuracy": 0.16511440128087998,
|
|
"num_tokens": 4043978.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.914384508132935,
|
|
"epoch": 0.17002881844380405,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999382194184023,
|
|
"loss": 5.8963,
|
|
"mean_token_accuracy": 0.16086647510528565,
|
|
"num_tokens": 4054513.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.877263736724854,
|
|
"epoch": 0.17050912584053796,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999374134553972,
|
|
"loss": 5.8334,
|
|
"mean_token_accuracy": 0.161749929189682,
|
|
"num_tokens": 4066019.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.784802484512329,
|
|
"epoch": 0.17098943323727187,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999366022700131,
|
|
"loss": 5.8089,
|
|
"mean_token_accuracy": 0.16527846902608873,
|
|
"num_tokens": 4077688.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.878071594238281,
|
|
"epoch": 0.17146974063400577,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999357858622691,
|
|
"loss": 5.8765,
|
|
"mean_token_accuracy": 0.16478312462568284,
|
|
"num_tokens": 4089803.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.798900747299195,
|
|
"epoch": 0.17195004803073968,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999349642321842,
|
|
"loss": 5.8299,
|
|
"mean_token_accuracy": 0.1660858377814293,
|
|
"num_tokens": 4101969.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.848860549926758,
|
|
"epoch": 0.1724303554274736,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999341373797772,
|
|
"loss": 5.8185,
|
|
"mean_token_accuracy": 0.15646317452192307,
|
|
"num_tokens": 4113567.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.768601655960083,
|
|
"epoch": 0.1729106628242075,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999333053050675,
|
|
"loss": 5.7615,
|
|
"mean_token_accuracy": 0.16766850799322128,
|
|
"num_tokens": 4125191.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.8816813945770265,
|
|
"epoch": 0.1733909702209414,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999324680080744,
|
|
"loss": 5.8026,
|
|
"mean_token_accuracy": 0.16495769172906877,
|
|
"num_tokens": 4135050.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.751550960540771,
|
|
"epoch": 0.17387127761767532,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999316254888172,
|
|
"loss": 5.8817,
|
|
"mean_token_accuracy": 0.16480684131383896,
|
|
"num_tokens": 4146874.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.83385910987854,
|
|
"epoch": 0.17435158501440923,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999307777473157,
|
|
"loss": 5.8112,
|
|
"mean_token_accuracy": 0.1625033974647522,
|
|
"num_tokens": 4158118.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.847680330276489,
|
|
"epoch": 0.17483189241114314,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999299247835893,
|
|
"loss": 5.7714,
|
|
"mean_token_accuracy": 0.17347559779882432,
|
|
"num_tokens": 4169035.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.711978626251221,
|
|
"epoch": 0.17531219980787704,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499929066597658,
|
|
"loss": 5.7653,
|
|
"mean_token_accuracy": 0.16850776970386505,
|
|
"num_tokens": 4180314.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.895935201644898,
|
|
"epoch": 0.17579250720461095,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999282031895418,
|
|
"loss": 5.8433,
|
|
"mean_token_accuracy": 0.16246981769800187,
|
|
"num_tokens": 4192238.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.767987537384033,
|
|
"epoch": 0.17627281460134486,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999273345592604,
|
|
"loss": 5.7592,
|
|
"mean_token_accuracy": 0.16418991535902022,
|
|
"num_tokens": 4203346.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.8496533870697025,
|
|
"epoch": 0.17675312199807877,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999264607068343,
|
|
"loss": 5.8291,
|
|
"mean_token_accuracy": 0.16989802122116088,
|
|
"num_tokens": 4213763.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.774960660934449,
|
|
"epoch": 0.17723342939481268,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999255816322837,
|
|
"loss": 5.7905,
|
|
"mean_token_accuracy": 0.16875854432582854,
|
|
"num_tokens": 4225553.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.843294954299926,
|
|
"epoch": 0.1777137367915466,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499924697335629,
|
|
"loss": 5.7029,
|
|
"mean_token_accuracy": 0.17008138149976731,
|
|
"num_tokens": 4236058.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.6908050060272215,
|
|
"epoch": 0.1781940441882805,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999238078168906,
|
|
"loss": 5.7919,
|
|
"mean_token_accuracy": 0.17022341936826707,
|
|
"num_tokens": 4248299.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.790624284744263,
|
|
"epoch": 0.1786743515850144,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999229130760894,
|
|
"loss": 5.7265,
|
|
"mean_token_accuracy": 0.16692683696746827,
|
|
"num_tokens": 4259704.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.719745206832886,
|
|
"epoch": 0.17915465898174832,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499922013113246,
|
|
"loss": 5.6039,
|
|
"mean_token_accuracy": 0.17842074930667878,
|
|
"num_tokens": 4270480.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.753391408920288,
|
|
"epoch": 0.17963496637848222,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999211079283814,
|
|
"loss": 5.863,
|
|
"mean_token_accuracy": 0.16482710540294648,
|
|
"num_tokens": 4282104.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.87967004776001,
|
|
"epoch": 0.18011527377521613,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999201975215164,
|
|
"loss": 5.8262,
|
|
"mean_token_accuracy": 0.15974476411938668,
|
|
"num_tokens": 4294251.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.736110019683838,
|
|
"epoch": 0.18059558117195004,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999192818926725,
|
|
"loss": 5.716,
|
|
"mean_token_accuracy": 0.16437824815511703,
|
|
"num_tokens": 4305569.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.875268745422363,
|
|
"epoch": 0.18107588856868395,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999183610418706,
|
|
"loss": 5.8513,
|
|
"mean_token_accuracy": 0.15760496482253075,
|
|
"num_tokens": 4317845.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.779155492782593,
|
|
"epoch": 0.18155619596541786,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999174349691322,
|
|
"loss": 5.7135,
|
|
"mean_token_accuracy": 0.1670348510146141,
|
|
"num_tokens": 4329987.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.700251865386963,
|
|
"epoch": 0.18203650336215177,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999165036744788,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.1668106958270073,
|
|
"num_tokens": 4341628.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.813083982467651,
|
|
"epoch": 0.18251681075888568,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999155671579322,
|
|
"loss": 5.8017,
|
|
"mean_token_accuracy": 0.16486806869506837,
|
|
"num_tokens": 4352379.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.670444774627685,
|
|
"epoch": 0.1829971181556196,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499914625419514,
|
|
"loss": 5.7558,
|
|
"mean_token_accuracy": 0.16672856360673904,
|
|
"num_tokens": 4364800.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.83980655670166,
|
|
"epoch": 0.1834774255523535,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999136784592459,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.16598723232746124,
|
|
"num_tokens": 4376048.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.711176252365112,
|
|
"epoch": 0.1839577329490874,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999127262771502,
|
|
"loss": 5.7516,
|
|
"mean_token_accuracy": 0.16420275270938872,
|
|
"num_tokens": 4388072.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.869711828231812,
|
|
"epoch": 0.1844380403458213,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999117688732487,
|
|
"loss": 5.8476,
|
|
"mean_token_accuracy": 0.1579664781689644,
|
|
"num_tokens": 4399843.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.777758169174194,
|
|
"epoch": 0.18491834774255522,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999108062475638,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.1702708438038826,
|
|
"num_tokens": 4411373.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.629845428466797,
|
|
"epoch": 0.18539865513928913,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499909838400118,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.16839613616466523,
|
|
"num_tokens": 4421857.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.868199729919434,
|
|
"epoch": 0.18587896253602307,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999088653309334,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.16982695311307908,
|
|
"num_tokens": 4432728.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.67154221534729,
|
|
"epoch": 0.18635926993275698,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999078870400329,
|
|
"loss": 5.7117,
|
|
"mean_token_accuracy": 0.17299556732177734,
|
|
"num_tokens": 4444683.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.840871000289917,
|
|
"epoch": 0.18683957732949089,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999069035274391,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.1611169919371605,
|
|
"num_tokens": 4456961.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.786156940460205,
|
|
"epoch": 0.1873198847262248,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999059147931747,
|
|
"loss": 5.6842,
|
|
"mean_token_accuracy": 0.1698920473456383,
|
|
"num_tokens": 4468424.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.754351711273193,
|
|
"epoch": 0.1878001921229587,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999049208372629,
|
|
"loss": 5.8806,
|
|
"mean_token_accuracy": 0.15270430967211723,
|
|
"num_tokens": 4479813.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.978194904327393,
|
|
"epoch": 0.1882804995196926,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999039216597267,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.16417741179466247,
|
|
"num_tokens": 4491172.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.761383438110352,
|
|
"epoch": 0.18876080691642652,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999029172605892,
|
|
"loss": 5.7583,
|
|
"mean_token_accuracy": 0.16918664872646333,
|
|
"num_tokens": 4503063.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.823719692230225,
|
|
"epoch": 0.18924111431316043,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999019076398738,
|
|
"loss": 5.8348,
|
|
"mean_token_accuracy": 0.1524723470211029,
|
|
"num_tokens": 4514188.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.849233388900757,
|
|
"epoch": 0.18972142170989434,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499900892797604,
|
|
"loss": 5.7518,
|
|
"mean_token_accuracy": 0.17084438353776932,
|
|
"num_tokens": 4525293.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.750137710571289,
|
|
"epoch": 0.19020172910662825,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998998727338031,
|
|
"loss": 5.8355,
|
|
"mean_token_accuracy": 0.16559164077043534,
|
|
"num_tokens": 4536589.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.72334475517273,
|
|
"epoch": 0.19068203650336216,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998988474484952,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.18548283725976944,
|
|
"num_tokens": 4547594.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.712575387954712,
|
|
"epoch": 0.19116234390009607,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998978169417038,
|
|
"loss": 5.8049,
|
|
"mean_token_accuracy": 0.17276343405246736,
|
|
"num_tokens": 4559850.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.752055835723877,
|
|
"epoch": 0.19164265129682997,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998967812134529,
|
|
"loss": 5.7435,
|
|
"mean_token_accuracy": 0.166203336417675,
|
|
"num_tokens": 4570727.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.661357784271241,
|
|
"epoch": 0.19212295869356388,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998957402637664,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.16516755968332292,
|
|
"num_tokens": 4582248.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.777338647842408,
|
|
"epoch": 0.1926032660902978,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998946940926687,
|
|
"loss": 5.6964,
|
|
"mean_token_accuracy": 0.1687027707695961,
|
|
"num_tokens": 4592604.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.725868988037109,
|
|
"epoch": 0.1930835734870317,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499893642700184,
|
|
"loss": 5.7282,
|
|
"mean_token_accuracy": 0.16577396988868714,
|
|
"num_tokens": 4604398.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.773129844665528,
|
|
"epoch": 0.1935638808837656,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998925860863368,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.16959393471479417,
|
|
"num_tokens": 4616434.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.8592376708984375,
|
|
"epoch": 0.19404418828049952,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998915242511516,
|
|
"loss": 5.7692,
|
|
"mean_token_accuracy": 0.17441897690296174,
|
|
"num_tokens": 4627577.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.786738777160645,
|
|
"epoch": 0.19452449567723343,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998904571946528,
|
|
"loss": 5.8282,
|
|
"mean_token_accuracy": 0.163761468231678,
|
|
"num_tokens": 4639698.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.795274019241333,
|
|
"epoch": 0.19500480307396734,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998893849168655,
|
|
"loss": 5.8307,
|
|
"mean_token_accuracy": 0.16407214850187302,
|
|
"num_tokens": 4650643.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.810069179534912,
|
|
"epoch": 0.19548511047070125,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998883074178144,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.16761939823627472,
|
|
"num_tokens": 4662897.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.7967664241790775,
|
|
"epoch": 0.19596541786743515,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998872246975247,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.1682201936841011,
|
|
"num_tokens": 4673701.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.908203554153443,
|
|
"epoch": 0.19644572526416906,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998861367560213,
|
|
"loss": 5.8056,
|
|
"mean_token_accuracy": 0.16590456962585448,
|
|
"num_tokens": 4685873.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.757840490341186,
|
|
"epoch": 0.19692603266090297,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998850435933296,
|
|
"loss": 5.6981,
|
|
"mean_token_accuracy": 0.16957563161849976,
|
|
"num_tokens": 4697179.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.743989706039429,
|
|
"epoch": 0.19740634005763688,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998839452094749,
|
|
"loss": 5.7245,
|
|
"mean_token_accuracy": 0.17266342043876648,
|
|
"num_tokens": 4707752.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.651218271255493,
|
|
"epoch": 0.1978866474543708,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998828416044829,
|
|
"loss": 5.5989,
|
|
"mean_token_accuracy": 0.17622617036104202,
|
|
"num_tokens": 4718413.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.691513156890869,
|
|
"epoch": 0.1983669548511047,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499881732778379,
|
|
"loss": 5.7996,
|
|
"mean_token_accuracy": 0.16042491793632507,
|
|
"num_tokens": 4730033.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.744086170196534,
|
|
"epoch": 0.1988472622478386,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499880618731189,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.17289423197507858,
|
|
"num_tokens": 4742084.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.77696385383606,
|
|
"epoch": 0.19932756964457252,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998794994629388,
|
|
"loss": 5.8756,
|
|
"mean_token_accuracy": 0.16191525459289552,
|
|
"num_tokens": 4753885.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.747893857955932,
|
|
"epoch": 0.19980787704130643,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998783749736545,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.16694570183753968,
|
|
"num_tokens": 4765686.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.786468601226806,
|
|
"epoch": 0.20028818443804033,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998772452633619,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.1651153862476349,
|
|
"num_tokens": 4777157.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.70054874420166,
|
|
"epoch": 0.20076849183477424,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998761103320876,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.17375380098819732,
|
|
"num_tokens": 4788583.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.848137521743775,
|
|
"epoch": 0.20124879923150815,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998749701798577,
|
|
"loss": 5.8217,
|
|
"mean_token_accuracy": 0.15967348739504814,
|
|
"num_tokens": 4800749.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.707665586471558,
|
|
"epoch": 0.2017291066282421,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998738248066986,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.17104323357343673,
|
|
"num_tokens": 4812488.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.780162286758423,
|
|
"epoch": 0.202209414024976,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998726742126372,
|
|
"loss": 5.6933,
|
|
"mean_token_accuracy": 0.17079969197511674,
|
|
"num_tokens": 4823495.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.70079460144043,
|
|
"epoch": 0.2026897214217099,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998715183976999,
|
|
"loss": 5.7506,
|
|
"mean_token_accuracy": 0.1680034041404724,
|
|
"num_tokens": 4834450.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.701813983917236,
|
|
"epoch": 0.20317002881844382,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998703573619137,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.1787526175379753,
|
|
"num_tokens": 4846826.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.863315725326538,
|
|
"epoch": 0.20365033621517772,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998691911053056,
|
|
"loss": 5.8482,
|
|
"mean_token_accuracy": 0.15404986143112182,
|
|
"num_tokens": 4859668.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.724852418899536,
|
|
"epoch": 0.20413064361191163,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998680196279026,
|
|
"loss": 5.744,
|
|
"mean_token_accuracy": 0.17037879824638366,
|
|
"num_tokens": 4871727.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.777047634124756,
|
|
"epoch": 0.20461095100864554,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998668429297319,
|
|
"loss": 5.7833,
|
|
"mean_token_accuracy": 0.1723802901804447,
|
|
"num_tokens": 4882191.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.799057054519653,
|
|
"epoch": 0.20509125840537945,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998656610108208,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.17028309404850006,
|
|
"num_tokens": 4892416.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.681277322769165,
|
|
"epoch": 0.20557156580211336,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998644738711969,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.16490518152713776,
|
|
"num_tokens": 4903572.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.86609845161438,
|
|
"epoch": 0.20605187319884727,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998632815108874,
|
|
"loss": 5.7848,
|
|
"mean_token_accuracy": 0.16344586461782457,
|
|
"num_tokens": 4915417.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.707794094085694,
|
|
"epoch": 0.20653218059558118,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998620839299203,
|
|
"loss": 5.6717,
|
|
"mean_token_accuracy": 0.16817740350961685,
|
|
"num_tokens": 4926943.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.663424491882324,
|
|
"epoch": 0.2070124879923151,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998608811283233,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.17493653148412705,
|
|
"num_tokens": 4937724.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.8030298233032225,
|
|
"epoch": 0.207492795389049,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998596731061244,
|
|
"loss": 5.7863,
|
|
"mean_token_accuracy": 0.15989046841859816,
|
|
"num_tokens": 4949970.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.811215448379516,
|
|
"epoch": 0.2079731027857829,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998584598633516,
|
|
"loss": 5.795,
|
|
"mean_token_accuracy": 0.16158758848905563,
|
|
"num_tokens": 4961389.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.815727233886719,
|
|
"epoch": 0.2084534101825168,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998572414000329,
|
|
"loss": 5.8331,
|
|
"mean_token_accuracy": 0.16089604347944259,
|
|
"num_tokens": 4973888.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.760948657989502,
|
|
"epoch": 0.20893371757925072,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998560177161969,
|
|
"loss": 5.7756,
|
|
"mean_token_accuracy": 0.1567353755235672,
|
|
"num_tokens": 4985423.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.727832221984864,
|
|
"epoch": 0.20941402497598463,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998547888118718,
|
|
"loss": 5.7413,
|
|
"mean_token_accuracy": 0.1611969456076622,
|
|
"num_tokens": 4997711.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.755141544342041,
|
|
"epoch": 0.20989433237271854,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998535546870862,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.1680392399430275,
|
|
"num_tokens": 5009633.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.778329706192016,
|
|
"epoch": 0.21037463976945245,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998523153418687,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.17196120470762252,
|
|
"num_tokens": 5021523.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.801051235198974,
|
|
"epoch": 0.21085494716618636,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998510707762481,
|
|
"loss": 5.798,
|
|
"mean_token_accuracy": 0.16583292111754416,
|
|
"num_tokens": 5033513.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.814651918411255,
|
|
"epoch": 0.21133525456292027,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998498209902533,
|
|
"loss": 5.802,
|
|
"mean_token_accuracy": 0.1642946258187294,
|
|
"num_tokens": 5047055.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.744992685317993,
|
|
"epoch": 0.21181556195965417,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998485659839134,
|
|
"loss": 5.6831,
|
|
"mean_token_accuracy": 0.17113134264945984,
|
|
"num_tokens": 5057613.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.7201080322265625,
|
|
"epoch": 0.21229586935638808,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998473057572575,
|
|
"loss": 5.7882,
|
|
"mean_token_accuracy": 0.16534605771303176,
|
|
"num_tokens": 5068886.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.771329689025879,
|
|
"epoch": 0.212776176753122,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998460403103146,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.1629289612174034,
|
|
"num_tokens": 5079978.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.7839549541473385,
|
|
"epoch": 0.2132564841498559,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998447696431146,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.16622460633516312,
|
|
"num_tokens": 5091021.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.6839478492736815,
|
|
"epoch": 0.2137367915465898,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998434937556865,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.1787912830710411,
|
|
"num_tokens": 5101483.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.740524005889893,
|
|
"epoch": 0.21421709894332372,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998422126480602,
|
|
"loss": 5.7645,
|
|
"mean_token_accuracy": 0.15988581329584123,
|
|
"num_tokens": 5113116.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.788122272491455,
|
|
"epoch": 0.21469740634005763,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998409263202653,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.16564781963825226,
|
|
"num_tokens": 5124824.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.643939590454101,
|
|
"epoch": 0.21517771373679154,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998396347723318,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.1620142638683319,
|
|
"num_tokens": 5137567.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.727840948104858,
|
|
"epoch": 0.21565802113352545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998383380042895,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.16364779621362685,
|
|
"num_tokens": 5149016.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.6396842956542965,
|
|
"epoch": 0.21613832853025935,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998370360161688,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.17202943414449692,
|
|
"num_tokens": 5160356.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.76469407081604,
|
|
"epoch": 0.21661863592699326,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998357288079996,
|
|
"loss": 5.7866,
|
|
"mean_token_accuracy": 0.15679443031549453,
|
|
"num_tokens": 5172100.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.7535566806793215,
|
|
"epoch": 0.21709894332372717,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998344163798125,
|
|
"loss": 5.7609,
|
|
"mean_token_accuracy": 0.16207664608955383,
|
|
"num_tokens": 5183984.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.754034566879272,
|
|
"epoch": 0.21757925072046108,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998330987316379,
|
|
"loss": 5.7302,
|
|
"mean_token_accuracy": 0.1636928603053093,
|
|
"num_tokens": 5195853.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.650364589691162,
|
|
"epoch": 0.21805955811719502,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998317758635062,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.17500120401382446,
|
|
"num_tokens": 5206995.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.553444576263428,
|
|
"epoch": 0.21853986551392893,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998304477754484,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.17451995462179185,
|
|
"num_tokens": 5219291.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.784403228759766,
|
|
"epoch": 0.21902017291066284,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998291144674952,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.17241026610136032,
|
|
"num_tokens": 5230856.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.624175596237182,
|
|
"epoch": 0.21950048030739674,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998277759396776,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.18255098909139633,
|
|
"num_tokens": 5242871.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.6208032131195065,
|
|
"epoch": 0.21998078770413065,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998264321920265,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.1755027338862419,
|
|
"num_tokens": 5253835.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.68435001373291,
|
|
"epoch": 0.22046109510086456,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998250832245734,
|
|
"loss": 5.6384,
|
|
"mean_token_accuracy": 0.17578463703393937,
|
|
"num_tokens": 5266195.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.6032106399536135,
|
|
"epoch": 0.22094140249759847,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998237290373494,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.17603587359189987,
|
|
"num_tokens": 5277499.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.8524679183959964,
|
|
"epoch": 0.22142170989433238,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499822369630386,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.15911103487014772,
|
|
"num_tokens": 5288622.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.773901891708374,
|
|
"epoch": 0.2219020172910663,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998210050037148,
|
|
"loss": 5.7959,
|
|
"mean_token_accuracy": 0.16207097768783568,
|
|
"num_tokens": 5299664.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.741703939437866,
|
|
"epoch": 0.2223823246878002,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998196351573674,
|
|
"loss": 5.6886,
|
|
"mean_token_accuracy": 0.1712455242872238,
|
|
"num_tokens": 5311627.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.623876667022705,
|
|
"epoch": 0.2228626320845341,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998182600913757,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.17991436272859573,
|
|
"num_tokens": 5323000.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.670632553100586,
|
|
"epoch": 0.22334293948126802,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998168798057715,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.17505657076835632,
|
|
"num_tokens": 5333811.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.704843616485595,
|
|
"epoch": 0.22382324687800192,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499815494300587,
|
|
"loss": 5.6257,
|
|
"mean_token_accuracy": 0.17499928623437883,
|
|
"num_tokens": 5344762.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.724334001541138,
|
|
"epoch": 0.22430355427473583,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998141035758542,
|
|
"loss": 5.6406,
|
|
"mean_token_accuracy": 0.17347200214862823,
|
|
"num_tokens": 5356112.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.661054706573486,
|
|
"epoch": 0.22478386167146974,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998127076316054,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.17038004398345946,
|
|
"num_tokens": 5367339.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.67761721611023,
|
|
"epoch": 0.22526416906820365,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998113064678734,
|
|
"loss": 5.674,
|
|
"mean_token_accuracy": 0.17715933173894882,
|
|
"num_tokens": 5378627.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.703079128265381,
|
|
"epoch": 0.22574447646493756,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998099000846901,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.169937065243721,
|
|
"num_tokens": 5390209.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.768410873413086,
|
|
"epoch": 0.22622478386167147,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998084884820887,
|
|
"loss": 5.6943,
|
|
"mean_token_accuracy": 0.1688449651002884,
|
|
"num_tokens": 5401578.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.615656137466431,
|
|
"epoch": 0.22670509125840538,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998070716601016,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.1754407674074173,
|
|
"num_tokens": 5413831.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.748986291885376,
|
|
"epoch": 0.2271853986551393,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998056496187618,
|
|
"loss": 5.6762,
|
|
"mean_token_accuracy": 0.16457515507936477,
|
|
"num_tokens": 5425430.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.546863603591919,
|
|
"epoch": 0.2276657060518732,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998042223581025,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.18393221646547317,
|
|
"num_tokens": 5435353.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.75008864402771,
|
|
"epoch": 0.2281460134486071,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998027898781565,
|
|
"loss": 5.7276,
|
|
"mean_token_accuracy": 0.16989402025938033,
|
|
"num_tokens": 5446925.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.627398490905762,
|
|
"epoch": 0.228626320845341,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998013521789574,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.17690314650535582,
|
|
"num_tokens": 5456613.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.727502870559692,
|
|
"epoch": 0.22910662824207492,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997999092605384,
|
|
"loss": 5.6458,
|
|
"mean_token_accuracy": 0.17188907861709596,
|
|
"num_tokens": 5467790.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.690616750717163,
|
|
"epoch": 0.22958693563880883,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499798461122933,
|
|
"loss": 5.6447,
|
|
"mean_token_accuracy": 0.17015563249588012,
|
|
"num_tokens": 5479166.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.6153504848480225,
|
|
"epoch": 0.23006724303554274,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997970077661748,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.18261955082416534,
|
|
"num_tokens": 5490186.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.676332139968872,
|
|
"epoch": 0.23054755043227665,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997955491902977,
|
|
"loss": 5.5856,
|
|
"mean_token_accuracy": 0.16712273508310319,
|
|
"num_tokens": 5500416.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.660897588729858,
|
|
"epoch": 0.23102785782901056,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997940853953354,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.16971836239099503,
|
|
"num_tokens": 5512189.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.60797348022461,
|
|
"epoch": 0.23150816522574447,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499792616381322,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.17806607335805893,
|
|
"num_tokens": 5523631.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.6375480651855465,
|
|
"epoch": 0.23198847262247838,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997911421482914,
|
|
"loss": 5.6082,
|
|
"mean_token_accuracy": 0.17522381991147995,
|
|
"num_tokens": 5535637.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.6304809093475345,
|
|
"epoch": 0.23246878001921228,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499789662696278,
|
|
"loss": 5.6073,
|
|
"mean_token_accuracy": 0.1792242631316185,
|
|
"num_tokens": 5546470.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.7677239894866945,
|
|
"epoch": 0.2329490874159462,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997881780253162,
|
|
"loss": 5.7783,
|
|
"mean_token_accuracy": 0.16586108207702638,
|
|
"num_tokens": 5558633.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.68570909500122,
|
|
"epoch": 0.2334293948126801,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997866881354403,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.16625906676054,
|
|
"num_tokens": 5570427.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.655580615997314,
|
|
"epoch": 0.23390970220941404,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499785193026685,
|
|
"loss": 5.652,
|
|
"mean_token_accuracy": 0.1722209334373474,
|
|
"num_tokens": 5580991.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.758580875396729,
|
|
"epoch": 0.23439000960614795,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997836926990851,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.16599331200122833,
|
|
"num_tokens": 5592777.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.616237497329712,
|
|
"epoch": 0.23487031700288186,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997821871526752,
|
|
"loss": 5.6158,
|
|
"mean_token_accuracy": 0.17849982529878616,
|
|
"num_tokens": 5603326.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.689610958099365,
|
|
"epoch": 0.23535062439961577,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997806763874905,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.17768498957157136,
|
|
"num_tokens": 5614504.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.616065263748169,
|
|
"epoch": 0.23583093179634967,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997791604035659,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.1749018743634224,
|
|
"num_tokens": 5625150.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.706295537948608,
|
|
"epoch": 0.23631123919308358,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997776392009366,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.17047384083271028,
|
|
"num_tokens": 5636815.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.708315181732178,
|
|
"epoch": 0.2367915465898175,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997761127796381,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.17045700550079346,
|
|
"num_tokens": 5648272.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.639753437042236,
|
|
"epoch": 0.2372718539865514,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997745811397056,
|
|
"loss": 5.5645,
|
|
"mean_token_accuracy": 0.1783196821808815,
|
|
"num_tokens": 5659227.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.675705432891846,
|
|
"epoch": 0.2377521613832853,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997730442811748,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.1714968904852867,
|
|
"num_tokens": 5670411.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.623871326446533,
|
|
"epoch": 0.23823246878001922,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997715022040814,
|
|
"loss": 5.5375,
|
|
"mean_token_accuracy": 0.17378956228494644,
|
|
"num_tokens": 5681570.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.572072505950928,
|
|
"epoch": 0.23871277617675313,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499769954908461,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.18674743324518203,
|
|
"num_tokens": 5693021.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.617792987823487,
|
|
"epoch": 0.23919308357348704,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997684023943498,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.17209588438272477,
|
|
"num_tokens": 5704043.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.6637180805206295,
|
|
"epoch": 0.23967339097022095,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997668446617837,
|
|
"loss": 5.6917,
|
|
"mean_token_accuracy": 0.1665050745010376,
|
|
"num_tokens": 5715735.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.777298212051392,
|
|
"epoch": 0.24015369836695485,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997652817107989,
|
|
"loss": 5.6638,
|
|
"mean_token_accuracy": 0.1674594148993492,
|
|
"num_tokens": 5725778.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.633906841278076,
|
|
"epoch": 0.24063400576368876,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997637135414315,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.1734729528427124,
|
|
"num_tokens": 5737224.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.786514043807983,
|
|
"epoch": 0.24111431316042267,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997621401537183,
|
|
"loss": 5.7104,
|
|
"mean_token_accuracy": 0.16915782541036606,
|
|
"num_tokens": 5749226.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.735674715042114,
|
|
"epoch": 0.24159462055715658,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004997605615476955,
|
|
"loss": 5.6882,
|
|
"mean_token_accuracy": 0.1680142268538475,
|
|
"num_tokens": 5760282.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.596765661239624,
|
|
"epoch": 0.2420749279538905,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997589777234,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.18090097308158876,
|
|
"num_tokens": 5771756.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.623631238937378,
|
|
"epoch": 0.2425552353506244,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997573886808684,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.16127828657627105,
|
|
"num_tokens": 5783237.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.7237598419189455,
|
|
"epoch": 0.2430355427473583,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997557944201375,
|
|
"loss": 5.7212,
|
|
"mean_token_accuracy": 0.16899894922971725,
|
|
"num_tokens": 5794825.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.713580799102783,
|
|
"epoch": 0.24351585014409222,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997541949412445,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.17922256290912628,
|
|
"num_tokens": 5805578.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.673787927627563,
|
|
"epoch": 0.24399615754082613,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997525902442266,
|
|
"loss": 5.6994,
|
|
"mean_token_accuracy": 0.16462765485048295,
|
|
"num_tokens": 5818201.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.651922988891601,
|
|
"epoch": 0.24447646493756003,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997509803291207,
|
|
"loss": 5.6342,
|
|
"mean_token_accuracy": 0.1722053050994873,
|
|
"num_tokens": 5830319.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.592335319519043,
|
|
"epoch": 0.24495677233429394,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997493651959647,
|
|
"loss": 5.5507,
|
|
"mean_token_accuracy": 0.17800200432538987,
|
|
"num_tokens": 5840638.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.679510593414307,
|
|
"epoch": 0.24543707973102785,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997477448447955,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.1699352577328682,
|
|
"num_tokens": 5852472.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.665648651123047,
|
|
"epoch": 0.24591738712776176,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997461192756512,
|
|
"loss": 5.6324,
|
|
"mean_token_accuracy": 0.16946420818567276,
|
|
"num_tokens": 5863455.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.532831478118896,
|
|
"epoch": 0.24639769452449567,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997444884885694,
|
|
"loss": 5.5446,
|
|
"mean_token_accuracy": 0.17266568541526794,
|
|
"num_tokens": 5873141.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.705326700210572,
|
|
"epoch": 0.24687800192122958,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997428524835879,
|
|
"loss": 5.6558,
|
|
"mean_token_accuracy": 0.17297983020544053,
|
|
"num_tokens": 5884363.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.732428312301636,
|
|
"epoch": 0.2473583093179635,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997412112607446,
|
|
"loss": 5.7007,
|
|
"mean_token_accuracy": 0.16773509830236435,
|
|
"num_tokens": 5895856.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.597812128067017,
|
|
"epoch": 0.2478386167146974,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997395648200778,
|
|
"loss": 5.5369,
|
|
"mean_token_accuracy": 0.1756013810634613,
|
|
"num_tokens": 5906657.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.662469291687012,
|
|
"epoch": 0.2483189241114313,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997379131616257,
|
|
"loss": 5.6515,
|
|
"mean_token_accuracy": 0.16843387484550476,
|
|
"num_tokens": 5919496.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.72010350227356,
|
|
"epoch": 0.24879923150816521,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997362562854266,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.16081342995166778,
|
|
"num_tokens": 5932593.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.672239303588867,
|
|
"epoch": 0.24927953890489912,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997345941915187,
|
|
"loss": 5.6365,
|
|
"mean_token_accuracy": 0.16822657883167266,
|
|
"num_tokens": 5944080.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.627252388000488,
|
|
"epoch": 0.24975984630163303,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997329268799412,
|
|
"loss": 5.606,
|
|
"mean_token_accuracy": 0.17856843024492264,
|
|
"num_tokens": 5955703.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.693896770477295,
|
|
"epoch": 0.25024015369836694,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997312543507322,
|
|
"loss": 5.6808,
|
|
"mean_token_accuracy": 0.1661712944507599,
|
|
"num_tokens": 5966979.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.673683929443359,
|
|
"epoch": 0.2507204610951009,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997295766039309,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.17391788810491562,
|
|
"num_tokens": 5978808.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.66244740486145,
|
|
"epoch": 0.25120076849183476,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997278936395761,
|
|
"loss": 5.7625,
|
|
"mean_token_accuracy": 0.16186216622591018,
|
|
"num_tokens": 5992145.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.731232213973999,
|
|
"epoch": 0.2516810758885687,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997262054577071,
|
|
"loss": 5.6037,
|
|
"mean_token_accuracy": 0.17375787049531938,
|
|
"num_tokens": 6003723.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.659373569488525,
|
|
"epoch": 0.2521613832853026,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997245120583627,
|
|
"loss": 5.6606,
|
|
"mean_token_accuracy": 0.17594955414533614,
|
|
"num_tokens": 6014064.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.593304252624511,
|
|
"epoch": 0.2526416906820365,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997228134415825,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.1786296159029007,
|
|
"num_tokens": 6025455.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.706792306900025,
|
|
"epoch": 0.2531219980787704,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997211096074059,
|
|
"loss": 5.6799,
|
|
"mean_token_accuracy": 0.16682123392820358,
|
|
"num_tokens": 6037347.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.611495780944824,
|
|
"epoch": 0.25360230547550433,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997194005558722,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.17720190733671187,
|
|
"num_tokens": 6049236.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.586591291427612,
|
|
"epoch": 0.2540826128722382,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997176862870216,
|
|
"loss": 5.5838,
|
|
"mean_token_accuracy": 0.17574792951345444,
|
|
"num_tokens": 6060982.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.609114742279052,
|
|
"epoch": 0.25456292026897215,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997159668008933,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.17881923615932466,
|
|
"num_tokens": 6070925.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.60413932800293,
|
|
"epoch": 0.25504322766570603,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997142420975277,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.177167809009552,
|
|
"num_tokens": 6081279.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.618051338195801,
|
|
"epoch": 0.25552353506243997,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997125121769647,
|
|
"loss": 5.642,
|
|
"mean_token_accuracy": 0.1760949596762657,
|
|
"num_tokens": 6091797.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.671202516555786,
|
|
"epoch": 0.25600384245917385,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997107770392444,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.17591851204633713,
|
|
"num_tokens": 6103435.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.691758155822754,
|
|
"epoch": 0.2564841498559078,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499709036684407,
|
|
"loss": 5.7044,
|
|
"mean_token_accuracy": 0.16775431036949157,
|
|
"num_tokens": 6114531.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.588616132736206,
|
|
"epoch": 0.25696445725264166,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997072911124932,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.17656420022249222,
|
|
"num_tokens": 6126110.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.714507722854615,
|
|
"epoch": 0.2574447646493756,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997055403235432,
|
|
"loss": 5.6422,
|
|
"mean_token_accuracy": 0.17070132046937941,
|
|
"num_tokens": 6137114.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.628438520431518,
|
|
"epoch": 0.2579250720461095,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997037843175978,
|
|
"loss": 5.6107,
|
|
"mean_token_accuracy": 0.17144765108823776,
|
|
"num_tokens": 6148696.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.610989427566528,
|
|
"epoch": 0.2584053794428434,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997020230946978,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.1747168093919754,
|
|
"num_tokens": 6160235.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.709567022323609,
|
|
"epoch": 0.25888568683957736,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997002566548841,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.16940530091524125,
|
|
"num_tokens": 6172031.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.461927366256714,
|
|
"epoch": 0.25936599423631124,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996984849981976,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.18867541551589967,
|
|
"num_tokens": 6183547.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.646917629241943,
|
|
"epoch": 0.2598463016330452,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996967081246794,
|
|
"loss": 5.6453,
|
|
"mean_token_accuracy": 0.16468724459409714,
|
|
"num_tokens": 6194768.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.650186204910279,
|
|
"epoch": 0.26032660902977905,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996949260343711,
|
|
"loss": 5.6576,
|
|
"mean_token_accuracy": 0.16891785562038422,
|
|
"num_tokens": 6206099.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.655857896804809,
|
|
"epoch": 0.260806916426513,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996931387273137,
|
|
"loss": 5.6504,
|
|
"mean_token_accuracy": 0.17782639116048812,
|
|
"num_tokens": 6217530.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.759098386764526,
|
|
"epoch": 0.2612872238232469,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996913462035487,
|
|
"loss": 5.68,
|
|
"mean_token_accuracy": 0.17465335577726365,
|
|
"num_tokens": 6228564.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.5744733810424805,
|
|
"epoch": 0.2617675312199808,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499689548463118,
|
|
"loss": 5.5468,
|
|
"mean_token_accuracy": 0.17481605410575868,
|
|
"num_tokens": 6239945.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.616865396499634,
|
|
"epoch": 0.2622478386167147,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996877455060631,
|
|
"loss": 5.656,
|
|
"mean_token_accuracy": 0.1666756272315979,
|
|
"num_tokens": 6251829.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.821361541748047,
|
|
"epoch": 0.2627281460134486,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996859373324259,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.15642182677984237,
|
|
"num_tokens": 6264823.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.604961299896241,
|
|
"epoch": 0.2632084534101825,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996841239422485,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.1777544304728508,
|
|
"num_tokens": 6276247.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.488066530227661,
|
|
"epoch": 0.26368876080691644,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996823053355729,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.17587606608867645,
|
|
"num_tokens": 6287593.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.753852605819702,
|
|
"epoch": 0.2641690682036503,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996804815124413,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.16802510619163513,
|
|
"num_tokens": 6299918.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.588559198379516,
|
|
"epoch": 0.26464937560038426,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996786524728962,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.17904944866895675,
|
|
"num_tokens": 6311147.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.464937686920166,
|
|
"epoch": 0.26512968299711814,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996768182169797,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.18499378114938736,
|
|
"num_tokens": 6323239.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.718430900573731,
|
|
"epoch": 0.2656099903938521,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996749787447349,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.173423171043396,
|
|
"num_tokens": 6334625.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.5834980487823485,
|
|
"epoch": 0.26609029779058596,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499673134056204,
|
|
"loss": 5.6118,
|
|
"mean_token_accuracy": 0.17362261265516282,
|
|
"num_tokens": 6346068.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.603063249588013,
|
|
"epoch": 0.2665706051873199,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996712841514303,
|
|
"loss": 5.6034,
|
|
"mean_token_accuracy": 0.1716381773352623,
|
|
"num_tokens": 6357097.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.689777565002442,
|
|
"epoch": 0.2670509125840538,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996694290304563,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.1637954369187355,
|
|
"num_tokens": 6367481.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.508364057540893,
|
|
"epoch": 0.2675312199807877,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996675686933255,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.18190633058547973,
|
|
"num_tokens": 6378873.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.739976024627685,
|
|
"epoch": 0.2680115273775216,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996657031400807,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.1723433554172516,
|
|
"num_tokens": 6390651.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.515517663955689,
|
|
"epoch": 0.26849183477425553,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996638323707655,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.18274116665124893,
|
|
"num_tokens": 6401631.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.475649976730347,
|
|
"epoch": 0.2689721421709894,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996619563854232,
|
|
"loss": 5.5759,
|
|
"mean_token_accuracy": 0.1792120084166527,
|
|
"num_tokens": 6413875.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.751020097732544,
|
|
"epoch": 0.26945244956772335,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996600751840974,
|
|
"loss": 5.5969,
|
|
"mean_token_accuracy": 0.16861645132303238,
|
|
"num_tokens": 6425764.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.556002569198609,
|
|
"epoch": 0.26993275696445723,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996581887668317,
|
|
"loss": 5.5146,
|
|
"mean_token_accuracy": 0.17818026393651962,
|
|
"num_tokens": 6437911.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.538363933563232,
|
|
"epoch": 0.27041306436119117,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049965629713367,
|
|
"loss": 5.5342,
|
|
"mean_token_accuracy": 0.1761205479502678,
|
|
"num_tokens": 6449942.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.654551982879639,
|
|
"epoch": 0.27089337175792505,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996544002846561,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.17214768826961518,
|
|
"num_tokens": 6461729.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.636355447769165,
|
|
"epoch": 0.271373679154659,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996524982198343,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.17879395484924315,
|
|
"num_tokens": 6472046.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.644113826751709,
|
|
"epoch": 0.27185398655139287,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996505909392485,
|
|
"loss": 5.6026,
|
|
"mean_token_accuracy": 0.1685856193304062,
|
|
"num_tokens": 6483308.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.505157804489135,
|
|
"epoch": 0.2723342939481268,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996486784429429,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.18083974868059158,
|
|
"num_tokens": 6495093.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.58596396446228,
|
|
"epoch": 0.2728146013448607,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996467607309622,
|
|
"loss": 5.5581,
|
|
"mean_token_accuracy": 0.17701218724250795,
|
|
"num_tokens": 6505933.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.634511089324951,
|
|
"epoch": 0.2732949087415946,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996448378033507,
|
|
"loss": 5.6005,
|
|
"mean_token_accuracy": 0.1716254621744156,
|
|
"num_tokens": 6517280.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.632332468032837,
|
|
"epoch": 0.2737752161383285,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996429096601532,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.16769653856754302,
|
|
"num_tokens": 6528980.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.65916337966919,
|
|
"epoch": 0.27425552353506244,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996409763014144,
|
|
"loss": 5.6504,
|
|
"mean_token_accuracy": 0.17413901090621947,
|
|
"num_tokens": 6540670.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.574322843551636,
|
|
"epoch": 0.2747358309317964,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996390377271791,
|
|
"loss": 5.6205,
|
|
"mean_token_accuracy": 0.17893006652593613,
|
|
"num_tokens": 6551302.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.6188043594360355,
|
|
"epoch": 0.27521613832853026,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996370939374924,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.17053322046995162,
|
|
"num_tokens": 6563177.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.793253755569458,
|
|
"epoch": 0.2756964457252642,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004996351449323994,
|
|
"loss": 5.6774,
|
|
"mean_token_accuracy": 0.17405274212360383,
|
|
"num_tokens": 6573323.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.619926929473877,
|
|
"epoch": 0.2761767531219981,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996331907119455,
|
|
"loss": 5.6065,
|
|
"mean_token_accuracy": 0.16668012738227844,
|
|
"num_tokens": 6585382.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.492765760421753,
|
|
"epoch": 0.276657060518732,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996312312761758,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.18380475640296937,
|
|
"num_tokens": 6596629.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.636275148391723,
|
|
"epoch": 0.2771373679154659,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499629266625136,
|
|
"loss": 5.6085,
|
|
"mean_token_accuracy": 0.17511519193649291,
|
|
"num_tokens": 6608408.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.689310741424561,
|
|
"epoch": 0.27761767531219983,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996272967588715,
|
|
"loss": 5.6317,
|
|
"mean_token_accuracy": 0.169224251806736,
|
|
"num_tokens": 6619375.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.665936088562011,
|
|
"epoch": 0.2780979827089337,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996253216774283,
|
|
"loss": 5.671,
|
|
"mean_token_accuracy": 0.17066159546375276,
|
|
"num_tokens": 6631317.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.633304929733276,
|
|
"epoch": 0.27857829010566765,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996233413808521,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.17339401245117186,
|
|
"num_tokens": 6642009.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.606546401977539,
|
|
"epoch": 0.27905859750240153,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996213558691889,
|
|
"loss": 5.6835,
|
|
"mean_token_accuracy": 0.16734906435012817,
|
|
"num_tokens": 6654713.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.642803955078125,
|
|
"epoch": 0.27953890489913547,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996193651424848,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.17135484665632247,
|
|
"num_tokens": 6667157.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.634487771987915,
|
|
"epoch": 0.28001921229586935,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499617369200786,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.18271744549274443,
|
|
"num_tokens": 6679573.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.687373352050781,
|
|
"epoch": 0.2804995196926033,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996153680441389,
|
|
"loss": 5.6516,
|
|
"mean_token_accuracy": 0.16726349741220475,
|
|
"num_tokens": 6691768.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.67548942565918,
|
|
"epoch": 0.28097982708933716,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049961336167259,
|
|
"loss": 5.6254,
|
|
"mean_token_accuracy": 0.1695394054055214,
|
|
"num_tokens": 6701964.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.653092575073242,
|
|
"epoch": 0.2814601344860711,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996113500861857,
|
|
"loss": 5.617,
|
|
"mean_token_accuracy": 0.1694892704486847,
|
|
"num_tokens": 6713506.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.646889019012451,
|
|
"epoch": 0.281940441882805,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996093332849729,
|
|
"loss": 5.6354,
|
|
"mean_token_accuracy": 0.17143076956272124,
|
|
"num_tokens": 6724616.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.568535089492798,
|
|
"epoch": 0.2824207492795389,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996073112689983,
|
|
"loss": 5.6211,
|
|
"mean_token_accuracy": 0.17045766562223436,
|
|
"num_tokens": 6735054.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.6508931636810305,
|
|
"epoch": 0.2829010566762728,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996052840383088,
|
|
"loss": 5.6673,
|
|
"mean_token_accuracy": 0.16961352303624153,
|
|
"num_tokens": 6746756.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.661314630508423,
|
|
"epoch": 0.28338136407300674,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996032515929516,
|
|
"loss": 5.5402,
|
|
"mean_token_accuracy": 0.17727758586406708,
|
|
"num_tokens": 6759566.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.557411527633667,
|
|
"epoch": 0.2838616714697406,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996012139329738,
|
|
"loss": 5.562,
|
|
"mean_token_accuracy": 0.16959619373083115,
|
|
"num_tokens": 6771375.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.659383296966553,
|
|
"epoch": 0.28434197886647455,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995991710584228,
|
|
"loss": 5.6667,
|
|
"mean_token_accuracy": 0.16246196776628494,
|
|
"num_tokens": 6783252.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.60762038230896,
|
|
"epoch": 0.28482228626320844,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995971229693459,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.16891720294952392,
|
|
"num_tokens": 6795525.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.709607172012329,
|
|
"epoch": 0.28530259365994237,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995950696657909,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.17235028892755508,
|
|
"num_tokens": 6807212.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.569004249572754,
|
|
"epoch": 0.28578290105667625,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995930111478051,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.1755308613181114,
|
|
"num_tokens": 6819367.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.616403675079345,
|
|
"epoch": 0.2862632084534102,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995909474154365,
|
|
"loss": 5.5999,
|
|
"mean_token_accuracy": 0.1746198445558548,
|
|
"num_tokens": 6830405.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.593991708755493,
|
|
"epoch": 0.28674351585014407,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995888784687331,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.17361628264188766,
|
|
"num_tokens": 6841479.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.516370010375977,
|
|
"epoch": 0.287223823246878,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995868043077428,
|
|
"loss": 5.6065,
|
|
"mean_token_accuracy": 0.17219199985265732,
|
|
"num_tokens": 6851585.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.608301115036011,
|
|
"epoch": 0.2877041306436119,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995847249325137,
|
|
"loss": 5.5876,
|
|
"mean_token_accuracy": 0.17400502115488053,
|
|
"num_tokens": 6863176.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.681745958328247,
|
|
"epoch": 0.2881844380403458,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995826403430942,
|
|
"loss": 5.6242,
|
|
"mean_token_accuracy": 0.17445267587900162,
|
|
"num_tokens": 6874021.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2881844380403458,
|
|
"eval_entropy": 5.460458407571756,
|
|
"eval_loss": 5.6124162673950195,
|
|
"eval_mean_token_accuracy": 0.1801256365830697,
|
|
"eval_num_tokens": 6874021.0,
|
|
"eval_runtime": 26.7169,
|
|
"eval_samples_per_second": 1228.251,
|
|
"eval_steps_per_second": 153.536,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.613573980331421,
|
|
"epoch": 0.2886647454370797,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995805505395328,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.1758129432797432,
|
|
"num_tokens": 6884999.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.621363687515259,
|
|
"epoch": 0.28914505283381364,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995784555218778,
|
|
"loss": 5.579,
|
|
"mean_token_accuracy": 0.17652602195739747,
|
|
"num_tokens": 6897021.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.566006374359131,
|
|
"epoch": 0.2896253602305475,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995763552901779,
|
|
"loss": 5.5985,
|
|
"mean_token_accuracy": 0.17294307798147202,
|
|
"num_tokens": 6908320.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.693685007095337,
|
|
"epoch": 0.29010566762728146,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995742498444818,
|
|
"loss": 5.562,
|
|
"mean_token_accuracy": 0.17986592799425125,
|
|
"num_tokens": 6919957.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.6058024883270265,
|
|
"epoch": 0.2905859750240154,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995721391848387,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.17189317792654038,
|
|
"num_tokens": 6930531.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.586360263824463,
|
|
"epoch": 0.2910662824207493,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995700233112972,
|
|
"loss": 5.655,
|
|
"mean_token_accuracy": 0.1715490236878395,
|
|
"num_tokens": 6942556.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.65383095741272,
|
|
"epoch": 0.2915465898174832,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995679022239066,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.17641045451164244,
|
|
"num_tokens": 6954410.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.595011138916016,
|
|
"epoch": 0.2920268972142171,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995657759227162,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.17521325647830963,
|
|
"num_tokens": 6964970.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.53864221572876,
|
|
"epoch": 0.29250720461095103,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995636444077751,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.17987639904022218,
|
|
"num_tokens": 6976016.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.621724224090576,
|
|
"epoch": 0.2929875120076849,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004995615076791333,
|
|
"loss": 5.5438,
|
|
"mean_token_accuracy": 0.18091933578252792,
|
|
"num_tokens": 6987199.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.5850824356079105,
|
|
"epoch": 0.29346781940441885,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995593657368399,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.1821291670203209,
|
|
"num_tokens": 6999174.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.623250341415405,
|
|
"epoch": 0.29394812680115273,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000499557218580945,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.17503387480974197,
|
|
"num_tokens": 7012148.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.538330459594727,
|
|
"epoch": 0.29442843419788667,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995550662114981,
|
|
"loss": 5.4914,
|
|
"mean_token_accuracy": 0.1787072852253914,
|
|
"num_tokens": 7023238.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.621415805816651,
|
|
"epoch": 0.29490874159462055,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995529086285495,
|
|
"loss": 5.5705,
|
|
"mean_token_accuracy": 0.17024941891431808,
|
|
"num_tokens": 7034944.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.636252975463867,
|
|
"epoch": 0.2953890489913545,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499550745832149,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.18431036323308944,
|
|
"num_tokens": 7046880.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.542232799530029,
|
|
"epoch": 0.29586935638808837,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995485778223471,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.17391062676906585,
|
|
"num_tokens": 7057678.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.485685729980469,
|
|
"epoch": 0.2963496637848223,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995464045991939,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.17980295270681382,
|
|
"num_tokens": 7068336.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.590327262878418,
|
|
"epoch": 0.2968299711815562,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049954422616274,
|
|
"loss": 5.5895,
|
|
"mean_token_accuracy": 0.1703091084957123,
|
|
"num_tokens": 7080341.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.684151220321655,
|
|
"epoch": 0.2973102785782901,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995420425130359,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.16605465561151506,
|
|
"num_tokens": 7090618.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.5475743293762205,
|
|
"epoch": 0.297790585975024,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004995398536501324,
|
|
"loss": 5.4886,
|
|
"mean_token_accuracy": 0.18272959291934968,
|
|
"num_tokens": 7101843.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.571886396408081,
|
|
"epoch": 0.29827089337175794,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995376595740801,
|
|
"loss": 5.53,
|
|
"mean_token_accuracy": 0.17730232179164887,
|
|
"num_tokens": 7112014.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.628252124786377,
|
|
"epoch": 0.2987512007684918,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995354602849302,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.1672294929623604,
|
|
"num_tokens": 7123860.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.642453289031982,
|
|
"epoch": 0.29923150816522576,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995332557827337,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.17241135835647584,
|
|
"num_tokens": 7135901.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.592183065414429,
|
|
"epoch": 0.29971181556195964,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004995310460675416,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.1816357359290123,
|
|
"num_tokens": 7148743.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.648265409469604,
|
|
"epoch": 0.3001921229586936,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995288311394053,
|
|
"loss": 5.6128,
|
|
"mean_token_accuracy": 0.17434070855379105,
|
|
"num_tokens": 7160731.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.630750370025635,
|
|
"epoch": 0.30067243035542746,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995266109983764,
|
|
"loss": 5.5982,
|
|
"mean_token_accuracy": 0.17709238231182098,
|
|
"num_tokens": 7172861.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.613532018661499,
|
|
"epoch": 0.3011527377521614,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995243856445062,
|
|
"loss": 5.5422,
|
|
"mean_token_accuracy": 0.1707857444882393,
|
|
"num_tokens": 7183954.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.506594276428222,
|
|
"epoch": 0.3016330451488953,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995221550778466,
|
|
"loss": 5.5098,
|
|
"mean_token_accuracy": 0.1764209136366844,
|
|
"num_tokens": 7195466.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.612970447540283,
|
|
"epoch": 0.3021133525456292,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995199192984491,
|
|
"loss": 5.5077,
|
|
"mean_token_accuracy": 0.17845915406942367,
|
|
"num_tokens": 7207173.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.644352006912231,
|
|
"epoch": 0.3025936599423631,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995176783063657,
|
|
"loss": 5.6428,
|
|
"mean_token_accuracy": 0.17586314529180527,
|
|
"num_tokens": 7220095.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.550618982315063,
|
|
"epoch": 0.30307396733909703,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004995154321016487,
|
|
"loss": 5.5581,
|
|
"mean_token_accuracy": 0.17573249340057373,
|
|
"num_tokens": 7230664.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.589782238006592,
|
|
"epoch": 0.3035542747358309,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995131806843499,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.17803725153207778,
|
|
"num_tokens": 7241278.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.573787212371826,
|
|
"epoch": 0.30403458213256485,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995109240545218,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.16872849464416503,
|
|
"num_tokens": 7252999.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.633689928054809,
|
|
"epoch": 0.3045148895292987,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995086622122167,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.17682646065950394,
|
|
"num_tokens": 7263949.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.588623523712158,
|
|
"epoch": 0.30499519692603266,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995063951574871,
|
|
"loss": 5.56,
|
|
"mean_token_accuracy": 0.17595675736665725,
|
|
"num_tokens": 7275467.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.585385513305664,
|
|
"epoch": 0.30547550432276654,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995041228903856,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.18359093517065048,
|
|
"num_tokens": 7285534.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.6909655094146725,
|
|
"epoch": 0.3059558117195005,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499501845410965,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.177760948240757,
|
|
"num_tokens": 7297252.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.6037369728088375,
|
|
"epoch": 0.30643611911623436,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994995627192781,
|
|
"loss": 5.5036,
|
|
"mean_token_accuracy": 0.18089882880449296,
|
|
"num_tokens": 7308492.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.505369377136231,
|
|
"epoch": 0.3069164265129683,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994972748153781,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.17417808324098588,
|
|
"num_tokens": 7319703.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.617596578598023,
|
|
"epoch": 0.30739673390970224,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000499494981699318,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.1807425305247307,
|
|
"num_tokens": 7331022.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.610428333282471,
|
|
"epoch": 0.3078770413064361,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499492683371151,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.18009235262870787,
|
|
"num_tokens": 7342977.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.638742399215698,
|
|
"epoch": 0.30835734870317005,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004994903798309306,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.1735951855778694,
|
|
"num_tokens": 7353227.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.638247394561768,
|
|
"epoch": 0.30883765609990393,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994880710787102,
|
|
"loss": 5.601,
|
|
"mean_token_accuracy": 0.166730073094368,
|
|
"num_tokens": 7364165.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.52378740310669,
|
|
"epoch": 0.30931796349663787,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994857571145432,
|
|
"loss": 5.5284,
|
|
"mean_token_accuracy": 0.1791498303413391,
|
|
"num_tokens": 7374800.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.497254800796509,
|
|
"epoch": 0.30979827089337175,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994834379384837,
|
|
"loss": 5.4846,
|
|
"mean_token_accuracy": 0.182875457406044,
|
|
"num_tokens": 7386360.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.625100612640381,
|
|
"epoch": 0.3102785782901057,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994811135505851,
|
|
"loss": 5.5069,
|
|
"mean_token_accuracy": 0.17930846512317658,
|
|
"num_tokens": 7397066.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.600756406784058,
|
|
"epoch": 0.31075888568683957,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004994787839509018,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.16974064260721206,
|
|
"num_tokens": 7408349.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.583713245391846,
|
|
"epoch": 0.3112391930835735,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994764491394876,
|
|
"loss": 5.6307,
|
|
"mean_token_accuracy": 0.17013027220964433,
|
|
"num_tokens": 7420343.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.664952898025513,
|
|
"epoch": 0.3117195004803074,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994741091163969,
|
|
"loss": 5.5421,
|
|
"mean_token_accuracy": 0.17812757194042206,
|
|
"num_tokens": 7431683.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.505253314971924,
|
|
"epoch": 0.3121998078770413,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499471763881684,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.1835172653198242,
|
|
"num_tokens": 7443327.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.620257759094239,
|
|
"epoch": 0.3126801152737752,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994694134354031,
|
|
"loss": 5.5647,
|
|
"mean_token_accuracy": 0.1741090565919876,
|
|
"num_tokens": 7454002.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.550648784637451,
|
|
"epoch": 0.31316042267050914,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499467057777609,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.17802659720182418,
|
|
"num_tokens": 7464074.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.471583032608033,
|
|
"epoch": 0.313640730067243,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994646969083565,
|
|
"loss": 5.4651,
|
|
"mean_token_accuracy": 0.18705809414386748,
|
|
"num_tokens": 7475543.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.6046764850616455,
|
|
"epoch": 0.31412103746397696,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994623308277002,
|
|
"loss": 5.5414,
|
|
"mean_token_accuracy": 0.17451809495687484,
|
|
"num_tokens": 7486818.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.604330968856812,
|
|
"epoch": 0.31460134486071084,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499459959535695,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.17568498849868774,
|
|
"num_tokens": 7499046.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.557371377944946,
|
|
"epoch": 0.3150816522574448,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004994575830323962,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.17285387217998505,
|
|
"num_tokens": 7509853.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.498314285278321,
|
|
"epoch": 0.31556195965417866,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994552013178586,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.18151895552873612,
|
|
"num_tokens": 7521091.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.514801788330078,
|
|
"epoch": 0.3160422670509126,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000499452814392138,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.1898494228720665,
|
|
"num_tokens": 7531317.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.573509597778321,
|
|
"epoch": 0.3165225744476465,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994504222552894,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.17439086809754373,
|
|
"num_tokens": 7542822.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.713440704345703,
|
|
"epoch": 0.3170028818443804,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004994480249073684,
|
|
"loss": 5.5679,
|
|
"mean_token_accuracy": 0.17728449702262877,
|
|
"num_tokens": 7552434.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.535713815689087,
|
|
"epoch": 0.3174831892411143,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994456223484308,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.18369303345680238,
|
|
"num_tokens": 7563895.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.404561233520508,
|
|
"epoch": 0.31796349663784823,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994432145785323,
|
|
"loss": 5.4716,
|
|
"mean_token_accuracy": 0.18563076108694077,
|
|
"num_tokens": 7575391.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.604758214950562,
|
|
"epoch": 0.3184438040345821,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994408015977288,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.18088502436876297,
|
|
"num_tokens": 7587119.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.6811892032623295,
|
|
"epoch": 0.31892411143131605,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004994383834060764,
|
|
"loss": 5.5996,
|
|
"mean_token_accuracy": 0.1736564055085182,
|
|
"num_tokens": 7598615.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.585067844390869,
|
|
"epoch": 0.31940441882804993,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994359600036311,
|
|
"loss": 5.5512,
|
|
"mean_token_accuracy": 0.18022585809230804,
|
|
"num_tokens": 7610159.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.6262510299682615,
|
|
"epoch": 0.31988472622478387,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994335313904493,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.1779860496520996,
|
|
"num_tokens": 7620922.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.5697978973388675,
|
|
"epoch": 0.32036503362151775,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994310975665873,
|
|
"loss": 5.4439,
|
|
"mean_token_accuracy": 0.18285417109727858,
|
|
"num_tokens": 7632343.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.636790323257446,
|
|
"epoch": 0.3208453410182517,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994286585321017,
|
|
"loss": 5.6346,
|
|
"mean_token_accuracy": 0.16847713887691498,
|
|
"num_tokens": 7644748.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.618470239639282,
|
|
"epoch": 0.32132564841498557,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499426214287049,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.1830369085073471,
|
|
"num_tokens": 7655449.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.6053215026855465,
|
|
"epoch": 0.3218059558117195,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994237648314862,
|
|
"loss": 5.5721,
|
|
"mean_token_accuracy": 0.17816869020462037,
|
|
"num_tokens": 7665623.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.523989295959472,
|
|
"epoch": 0.3222862632084534,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994213101654697,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.18045857846736907,
|
|
"num_tokens": 7676860.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.6266748905181885,
|
|
"epoch": 0.3227665706051873,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499418850289057,
|
|
"loss": 5.6436,
|
|
"mean_token_accuracy": 0.17685709446668624,
|
|
"num_tokens": 7687778.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.6022907257080075,
|
|
"epoch": 0.32324687800192126,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994163852023048,
|
|
"loss": 5.537,
|
|
"mean_token_accuracy": 0.18029210567474366,
|
|
"num_tokens": 7699154.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.533091831207275,
|
|
"epoch": 0.32372718539865514,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994139149052706,
|
|
"loss": 5.553,
|
|
"mean_token_accuracy": 0.17924581915140153,
|
|
"num_tokens": 7711010.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.606594371795654,
|
|
"epoch": 0.3242074927953891,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004994114393980117,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.1734212577342987,
|
|
"num_tokens": 7721969.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.613570785522461,
|
|
"epoch": 0.32468780019212296,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.17727082669734956,
|
|
"num_tokens": 7733762.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.577807235717773,
|
|
"epoch": 0.3251681075888569,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994064727530496,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.1757509931921959,
|
|
"num_tokens": 7744614.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.523240232467652,
|
|
"epoch": 0.3256484149855908,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994039816154618,
|
|
"loss": 5.4871,
|
|
"mean_token_accuracy": 0.18224907666444778,
|
|
"num_tokens": 7755799.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.492821311950683,
|
|
"epoch": 0.3261287223823247,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049940148526788,
|
|
"loss": 5.528,
|
|
"mean_token_accuracy": 0.17861508429050446,
|
|
"num_tokens": 7768140.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.5683966159820555,
|
|
"epoch": 0.3266090297790586,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004993989837103618,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.17852782905101777,
|
|
"num_tokens": 7778494.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.630914306640625,
|
|
"epoch": 0.3270893371757925,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993964769429657,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.17906586527824403,
|
|
"num_tokens": 7789234.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.539331579208374,
|
|
"epoch": 0.3275696445725264,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993939649657498,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.18031278550624846,
|
|
"num_tokens": 7800602.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.538713073730468,
|
|
"epoch": 0.32804995196926034,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993914477787721,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.18510278612375258,
|
|
"num_tokens": 7812803.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.69016580581665,
|
|
"epoch": 0.3285302593659942,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993889253820915,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.16508418023586274,
|
|
"num_tokens": 7825432.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.608712530136108,
|
|
"epoch": 0.32901056676272816,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993863977757663,
|
|
"loss": 5.5352,
|
|
"mean_token_accuracy": 0.17818592637777328,
|
|
"num_tokens": 7837258.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.451307344436645,
|
|
"epoch": 0.32949087415946204,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993838649598552,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.1869217112660408,
|
|
"num_tokens": 7847573.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.562351131439209,
|
|
"epoch": 0.329971181556196,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993813269344171,
|
|
"loss": 5.5428,
|
|
"mean_token_accuracy": 0.17355968356132506,
|
|
"num_tokens": 7857957.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.5080243110656735,
|
|
"epoch": 0.33045148895292986,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993787836995108,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.18813711851835252,
|
|
"num_tokens": 7867996.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.4890570640563965,
|
|
"epoch": 0.3309317963496638,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993762352551954,
|
|
"loss": 5.5079,
|
|
"mean_token_accuracy": 0.17222511023283005,
|
|
"num_tokens": 7879245.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.6612279415130615,
|
|
"epoch": 0.3314121037463977,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993736816015301,
|
|
"loss": 5.5954,
|
|
"mean_token_accuracy": 0.16992024034261705,
|
|
"num_tokens": 7891186.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.640943574905395,
|
|
"epoch": 0.3318924111431316,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993711227385742,
|
|
"loss": 5.6167,
|
|
"mean_token_accuracy": 0.17565465867519378,
|
|
"num_tokens": 7902231.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.621625375747681,
|
|
"epoch": 0.3323727185398655,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993685586663871,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.17738195657730102,
|
|
"num_tokens": 7913364.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.793933534622193,
|
|
"epoch": 0.33285302593659943,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993659893850281,
|
|
"loss": 5.7558,
|
|
"mean_token_accuracy": 0.16640468537807465,
|
|
"num_tokens": 7925217.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.558285045623779,
|
|
"epoch": 0.3333333333333333,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993634148945573,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.17263794988393782,
|
|
"num_tokens": 7937636.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.589412212371826,
|
|
"epoch": 0.33381364073006725,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993608351950341,
|
|
"loss": 5.532,
|
|
"mean_token_accuracy": 0.17014701440930366,
|
|
"num_tokens": 7948958.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.627977418899536,
|
|
"epoch": 0.33429394812680113,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004993582502865185,
|
|
"loss": 5.5697,
|
|
"mean_token_accuracy": 0.17802419364452363,
|
|
"num_tokens": 7960013.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.531227922439575,
|
|
"epoch": 0.33477425552353507,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993556601690706,
|
|
"loss": 5.5891,
|
|
"mean_token_accuracy": 0.17024275958538054,
|
|
"num_tokens": 7971041.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.681254148483276,
|
|
"epoch": 0.33525456292026895,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993530648427505,
|
|
"loss": 5.6087,
|
|
"mean_token_accuracy": 0.17211289405822755,
|
|
"num_tokens": 7982752.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.57779631614685,
|
|
"epoch": 0.3357348703170029,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993504643076184,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.17710510194301604,
|
|
"num_tokens": 7993681.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.543416976928711,
|
|
"epoch": 0.33621517771373677,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993478585637347,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.1808265820145607,
|
|
"num_tokens": 8004727.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.56981258392334,
|
|
"epoch": 0.3366954851104707,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993452476111599,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.18137534856796264,
|
|
"num_tokens": 8015423.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.511034727096558,
|
|
"epoch": 0.3371757925072046,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993426314499546,
|
|
"loss": 5.4934,
|
|
"mean_token_accuracy": 0.18413615524768828,
|
|
"num_tokens": 8027911.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.605849885940552,
|
|
"epoch": 0.3376560999039385,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993400100801796,
|
|
"loss": 5.5287,
|
|
"mean_token_accuracy": 0.1756324976682663,
|
|
"num_tokens": 8038831.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.46014552116394,
|
|
"epoch": 0.3381364073006724,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993373835018956,
|
|
"loss": 5.4022,
|
|
"mean_token_accuracy": 0.18955729454755782,
|
|
"num_tokens": 8049906.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.4005388736724855,
|
|
"epoch": 0.33861671469740634,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993347517151638,
|
|
"loss": 5.5152,
|
|
"mean_token_accuracy": 0.1809609442949295,
|
|
"num_tokens": 8061158.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.652207279205323,
|
|
"epoch": 0.3390970220941403,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993321147200452,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.17901494204998017,
|
|
"num_tokens": 8071958.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.549252033233643,
|
|
"epoch": 0.33957732949087416,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499329472516601,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.17660357058048248,
|
|
"num_tokens": 8084068.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.419362258911133,
|
|
"epoch": 0.3400576368876081,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993268251048925,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.1915588781237602,
|
|
"num_tokens": 8096132.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.527532863616943,
|
|
"epoch": 0.340537944284342,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993241724849814,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.1804182380437851,
|
|
"num_tokens": 8107327.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.589256048202515,
|
|
"epoch": 0.3410182516810759,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499321514656929,
|
|
"loss": 5.5251,
|
|
"mean_token_accuracy": 0.17919999361038208,
|
|
"num_tokens": 8118584.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.5927215099334715,
|
|
"epoch": 0.3414985590778098,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993188516207972,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.173704132437706,
|
|
"num_tokens": 8130081.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.5484973907470705,
|
|
"epoch": 0.34197886647454373,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004993161833766478,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.17699515223503112,
|
|
"num_tokens": 8141463.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.589907312393189,
|
|
"epoch": 0.3424591738712776,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993135099245426,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.1762032225728035,
|
|
"num_tokens": 8153863.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.478762912750244,
|
|
"epoch": 0.34293948126801155,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993108312645438,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.17794045358896254,
|
|
"num_tokens": 8165695.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.587690830230713,
|
|
"epoch": 0.34341978866474543,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993081473967135,
|
|
"loss": 5.5547,
|
|
"mean_token_accuracy": 0.1772906959056854,
|
|
"num_tokens": 8176456.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.579510450363159,
|
|
"epoch": 0.34390009606147937,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993054583211143,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.18039764165878297,
|
|
"num_tokens": 8189050.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.4583968162536625,
|
|
"epoch": 0.34438040345821325,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993027640378081,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.18434835076332093,
|
|
"num_tokens": 8200011.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.548676824569702,
|
|
"epoch": 0.3448607108549472,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499300064546858,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.17640567868947982,
|
|
"num_tokens": 8211770.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.561691761016846,
|
|
"epoch": 0.34534101825168106,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992973598483264,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.18221239149570465,
|
|
"num_tokens": 8223582.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.653462600708008,
|
|
"epoch": 0.345821325648415,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499294649942276,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.17930494397878646,
|
|
"num_tokens": 8234336.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.604247665405273,
|
|
"epoch": 0.3463016330451489,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004992919348287699,
|
|
"loss": 5.5269,
|
|
"mean_token_accuracy": 0.18303712606430053,
|
|
"num_tokens": 8244605.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.563096523284912,
|
|
"epoch": 0.3467819404418828,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992892145078711,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.1752590224146843,
|
|
"num_tokens": 8255876.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.521414184570313,
|
|
"epoch": 0.3472622478386167,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992864889796427,
|
|
"loss": 5.4705,
|
|
"mean_token_accuracy": 0.18474286049604416,
|
|
"num_tokens": 8266602.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.614775276184082,
|
|
"epoch": 0.34774255523535064,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992837582441481,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.17718978673219682,
|
|
"num_tokens": 8279804.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.589058923721313,
|
|
"epoch": 0.3482228626320845,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992810223014506,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.180307999253273,
|
|
"num_tokens": 8291020.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.521428012847901,
|
|
"epoch": 0.34870317002881845,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992782811516137,
|
|
"loss": 5.4981,
|
|
"mean_token_accuracy": 0.1806633874773979,
|
|
"num_tokens": 8302192.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.582447814941406,
|
|
"epoch": 0.34918347742555234,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992755347947011,
|
|
"loss": 5.4671,
|
|
"mean_token_accuracy": 0.17598280310630798,
|
|
"num_tokens": 8313649.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.479987573623657,
|
|
"epoch": 0.34966378482228627,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992727832307766,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.18262661695480348,
|
|
"num_tokens": 8324694.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.62206540107727,
|
|
"epoch": 0.35014409221902015,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992700264599039,
|
|
"loss": 5.6314,
|
|
"mean_token_accuracy": 0.1722588375210762,
|
|
"num_tokens": 8336517.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.588152599334717,
|
|
"epoch": 0.3506243996157541,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992672644821473,
|
|
"loss": 5.579,
|
|
"mean_token_accuracy": 0.17565614730119705,
|
|
"num_tokens": 8349001.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.600451421737671,
|
|
"epoch": 0.35110470701248797,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992644972975707,
|
|
"loss": 5.4963,
|
|
"mean_token_accuracy": 0.1849415972828865,
|
|
"num_tokens": 8361230.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.471852874755859,
|
|
"epoch": 0.3515850144092219,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992617249062383,
|
|
"loss": 5.4352,
|
|
"mean_token_accuracy": 0.1840439796447754,
|
|
"num_tokens": 8372159.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.546054649353027,
|
|
"epoch": 0.3520653218059558,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992589473082147,
|
|
"loss": 5.5432,
|
|
"mean_token_accuracy": 0.18210961669683456,
|
|
"num_tokens": 8383228.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.58235239982605,
|
|
"epoch": 0.3525456292026897,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004992561645035641,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.17832960337400436,
|
|
"num_tokens": 8394582.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.555625486373901,
|
|
"epoch": 0.3530259365994236,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992533764923515,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.17920332551002502,
|
|
"num_tokens": 8406784.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.535842752456665,
|
|
"epoch": 0.35350624399615754,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992505832746412,
|
|
"loss": 5.4737,
|
|
"mean_token_accuracy": 0.18762768656015397,
|
|
"num_tokens": 8418405.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.545845317840576,
|
|
"epoch": 0.3539865513928914,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004992477848504983,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.1787422627210617,
|
|
"num_tokens": 8430432.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.608061170578003,
|
|
"epoch": 0.35446685878962536,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992449812199877,
|
|
"loss": 5.5787,
|
|
"mean_token_accuracy": 0.17739484906196595,
|
|
"num_tokens": 8442423.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.59760103225708,
|
|
"epoch": 0.3549471661863593,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992421723831745,
|
|
"loss": 5.5934,
|
|
"mean_token_accuracy": 0.1774441123008728,
|
|
"num_tokens": 8454951.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.514939022064209,
|
|
"epoch": 0.3554274735830932,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992393583401239,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.18614033460617066,
|
|
"num_tokens": 8467758.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.551314973831177,
|
|
"epoch": 0.3559077809798271,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992365390909014,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.1789237827062607,
|
|
"num_tokens": 8479728.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.5682985305786135,
|
|
"epoch": 0.356388088376561,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992337146355721,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.17122279852628708,
|
|
"num_tokens": 8492099.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.6356853485107425,
|
|
"epoch": 0.35686839577329493,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992308849742019,
|
|
"loss": 5.5292,
|
|
"mean_token_accuracy": 0.1695133775472641,
|
|
"num_tokens": 8504657.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.541604042053223,
|
|
"epoch": 0.3573487031700288,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992280501068563,
|
|
"loss": 5.4946,
|
|
"mean_token_accuracy": 0.18488531708717346,
|
|
"num_tokens": 8514728.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.563294792175293,
|
|
"epoch": 0.35782901056676275,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992252100336012,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.1804689198732376,
|
|
"num_tokens": 8525588.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.62255368232727,
|
|
"epoch": 0.35830931796349663,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004992223647545027,
|
|
"loss": 5.5949,
|
|
"mean_token_accuracy": 0.1749206006526947,
|
|
"num_tokens": 8537468.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.59177885055542,
|
|
"epoch": 0.35878962536023057,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992195142696266,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.1799744501709938,
|
|
"num_tokens": 8548598.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.411002683639526,
|
|
"epoch": 0.35926993275696445,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992166585790391,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.19347753822803498,
|
|
"num_tokens": 8560301.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.513459062576294,
|
|
"epoch": 0.3597502401536984,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992137976828067,
|
|
"loss": 5.4568,
|
|
"mean_token_accuracy": 0.18400878608226776,
|
|
"num_tokens": 8571186.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.521359825134278,
|
|
"epoch": 0.36023054755043227,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992109315809955,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.18453473448753357,
|
|
"num_tokens": 8580725.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.540656566619873,
|
|
"epoch": 0.3607108549471662,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992080602736725,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.1723345473408699,
|
|
"num_tokens": 8594598.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.697948169708252,
|
|
"epoch": 0.3611911623439001,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992051837609039,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.17390913367271424,
|
|
"num_tokens": 8606733.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.6418304443359375,
|
|
"epoch": 0.361671469740634,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992023020427568,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.18220120668411255,
|
|
"num_tokens": 8618863.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.39378662109375,
|
|
"epoch": 0.3621517771373679,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991994151192979,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.1827904015779495,
|
|
"num_tokens": 8629270.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.53677225112915,
|
|
"epoch": 0.36263208453410184,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991965229905943,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.1815919578075409,
|
|
"num_tokens": 8641363.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.666194915771484,
|
|
"epoch": 0.3631123919308357,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004991936256567133,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.17837249636650085,
|
|
"num_tokens": 8653233.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.579335498809814,
|
|
"epoch": 0.36359269932756966,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499190723117722,
|
|
"loss": 5.5382,
|
|
"mean_token_accuracy": 0.1732911467552185,
|
|
"num_tokens": 8665192.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.67026720046997,
|
|
"epoch": 0.36407300672430354,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991878153736877,
|
|
"loss": 5.6196,
|
|
"mean_token_accuracy": 0.1725441560149193,
|
|
"num_tokens": 8677669.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.458724737167358,
|
|
"epoch": 0.3645533141210375,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991849024246781,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.18352104127407073,
|
|
"num_tokens": 8688002.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.485396385192871,
|
|
"epoch": 0.36503362151777136,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991819842707608,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.18270452916622162,
|
|
"num_tokens": 8698396.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.581181144714355,
|
|
"epoch": 0.3655139289145053,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991790609120035,
|
|
"loss": 5.4581,
|
|
"mean_token_accuracy": 0.18108633011579514,
|
|
"num_tokens": 8711135.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.55638952255249,
|
|
"epoch": 0.3659942363112392,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499176132348474,
|
|
"loss": 5.5174,
|
|
"mean_token_accuracy": 0.1873884156346321,
|
|
"num_tokens": 8723707.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.538628387451172,
|
|
"epoch": 0.3664745437079731,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991731985802405,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.18213894367218017,
|
|
"num_tokens": 8734193.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.551886796951294,
|
|
"epoch": 0.366954851104707,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004991702596073708,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.17546743005514145,
|
|
"num_tokens": 8745619.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.476492786407471,
|
|
"epoch": 0.36743515850144093,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991673154299335,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.18338788896799088,
|
|
"num_tokens": 8757331.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.537812089920044,
|
|
"epoch": 0.3679154658981748,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991643660479967,
|
|
"loss": 5.4845,
|
|
"mean_token_accuracy": 0.18190569281578065,
|
|
"num_tokens": 8768840.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.511652565002441,
|
|
"epoch": 0.36839577329490875,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991614114616289,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.1853283315896988,
|
|
"num_tokens": 8781214.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.55661973953247,
|
|
"epoch": 0.3688760806916426,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991584516708988,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.1824388399720192,
|
|
"num_tokens": 8791645.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.649739122390747,
|
|
"epoch": 0.36935638808837656,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004991554866758751,
|
|
"loss": 5.6796,
|
|
"mean_token_accuracy": 0.17237824574112892,
|
|
"num_tokens": 8803286.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.583400249481201,
|
|
"epoch": 0.36983669548511044,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004991525164766265,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.17779840528964996,
|
|
"num_tokens": 8814207.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.545863389968872,
|
|
"epoch": 0.3703170028818444,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991495410732222,
|
|
"loss": 5.5152,
|
|
"mean_token_accuracy": 0.172617669403553,
|
|
"num_tokens": 8825540.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.580052900314331,
|
|
"epoch": 0.37079731027857826,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991465604657311,
|
|
"loss": 5.6258,
|
|
"mean_token_accuracy": 0.16957491338253022,
|
|
"num_tokens": 8838182.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.531523561477661,
|
|
"epoch": 0.3712776176753122,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991435746542224,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.17840952724218367,
|
|
"num_tokens": 8850211.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.520380210876465,
|
|
"epoch": 0.37175792507204614,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991405836387655,
|
|
"loss": 5.5676,
|
|
"mean_token_accuracy": 0.17828516960144042,
|
|
"num_tokens": 8862804.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.594271183013916,
|
|
"epoch": 0.37223823246878,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991375874194298,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.1757369428873062,
|
|
"num_tokens": 8874112.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.472111082077026,
|
|
"epoch": 0.37271853986551395,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499134585996285,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.17891473472118377,
|
|
"num_tokens": 8885114.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.563468027114868,
|
|
"epoch": 0.37319884726224783,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004991315793694004,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.18485302925109864,
|
|
"num_tokens": 8895555.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.511318063735962,
|
|
"epoch": 0.37367915465898177,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991285675388463,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.1931263506412506,
|
|
"num_tokens": 8906073.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.578082704544068,
|
|
"epoch": 0.37415946205571565,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991255505046922,
|
|
"loss": 5.5528,
|
|
"mean_token_accuracy": 0.1823568508028984,
|
|
"num_tokens": 8916587.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.577627038955688,
|
|
"epoch": 0.3746397694524496,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991225282670083,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.1799926072359085,
|
|
"num_tokens": 8927923.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.495621871948242,
|
|
"epoch": 0.37512007684918347,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499119500825865,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.1821560814976692,
|
|
"num_tokens": 8939939.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.476370096206665,
|
|
"epoch": 0.3756003842459174,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004991164681813323,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.18590280860662461,
|
|
"num_tokens": 8951748.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.481526899337768,
|
|
"epoch": 0.3760806916426513,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991134303334807,
|
|
"loss": 5.3898,
|
|
"mean_token_accuracy": 0.19105241894721986,
|
|
"num_tokens": 8962922.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.454615783691406,
|
|
"epoch": 0.3765609990393852,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991103872823807,
|
|
"loss": 5.379,
|
|
"mean_token_accuracy": 0.19051530808210373,
|
|
"num_tokens": 8974013.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.45075740814209,
|
|
"epoch": 0.3770413064361191,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499107339028103,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.1802351951599121,
|
|
"num_tokens": 8986032.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.567822885513306,
|
|
"epoch": 0.37752161383285304,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991042855707184,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.18151425272226335,
|
|
"num_tokens": 8996889.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.488146257400513,
|
|
"epoch": 0.3780019212295869,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991012269102977,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.17930201143026353,
|
|
"num_tokens": 9007594.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.433380937576294,
|
|
"epoch": 0.37848222862632086,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004990981630469119,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.17844464033842086,
|
|
"num_tokens": 9018097.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.548726224899292,
|
|
"epoch": 0.37896253602305474,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990950939806323,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.17494198232889174,
|
|
"num_tokens": 9029554.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.552030324935913,
|
|
"epoch": 0.3794428434197887,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00049909201971153,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.17919899374246598,
|
|
"num_tokens": 9042518.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.480895614624023,
|
|
"epoch": 0.37992315081652256,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004990889402396763,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.1846231773495674,
|
|
"num_tokens": 9054524.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.544541501998902,
|
|
"epoch": 0.3804034582132565,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990858555651431,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.18396840542554854,
|
|
"num_tokens": 9065375.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.478338289260864,
|
|
"epoch": 0.3808837656099904,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990827656880015,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.1826442152261734,
|
|
"num_tokens": 9076338.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.509083604812622,
|
|
"epoch": 0.3813640730067243,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990796706083235,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.18144155889749528,
|
|
"num_tokens": 9088407.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.501113796234131,
|
|
"epoch": 0.3818443804034582,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990765703261809,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.18050579726696014,
|
|
"num_tokens": 9099833.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.390386772155762,
|
|
"epoch": 0.38232468780019213,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990734648416458,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.1893791913986206,
|
|
"num_tokens": 9111126.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.5150824069976805,
|
|
"epoch": 0.382804995196926,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990703541547901,
|
|
"loss": 5.48,
|
|
"mean_token_accuracy": 0.18026171922683715,
|
|
"num_tokens": 9121979.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.573945474624634,
|
|
"epoch": 0.38328530259365995,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004990672382656863,
|
|
"loss": 5.5085,
|
|
"mean_token_accuracy": 0.17997142374515535,
|
|
"num_tokens": 9132929.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.5391278743743895,
|
|
"epoch": 0.38376560999039383,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990641171744064,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.18611048609018327,
|
|
"num_tokens": 9143903.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.573569393157959,
|
|
"epoch": 0.38424591738712777,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990609908810231,
|
|
"loss": 5.53,
|
|
"mean_token_accuracy": 0.17738315910100938,
|
|
"num_tokens": 9154416.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.5358727931976315,
|
|
"epoch": 0.38472622478386165,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004990578593856089,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.17665785998106004,
|
|
"num_tokens": 9165613.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.506435346603394,
|
|
"epoch": 0.3852065321805956,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990547226882366,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.18606363832950593,
|
|
"num_tokens": 9177884.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.605308151245117,
|
|
"epoch": 0.38568683957732947,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004990515807889788,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.17133916020393372,
|
|
"num_tokens": 9190041.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.606444692611694,
|
|
"epoch": 0.3861671469740634,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004990484336879087,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.18263252079486847,
|
|
"num_tokens": 9202390.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.4758586406707765,
|
|
"epoch": 0.3866474543707973,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990452813850992,
|
|
"loss": 5.4895,
|
|
"mean_token_accuracy": 0.18195904642343522,
|
|
"num_tokens": 9213437.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.566554403305053,
|
|
"epoch": 0.3871277617675312,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004990421238806236,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.16883469372987747,
|
|
"num_tokens": 9226310.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.63280348777771,
|
|
"epoch": 0.38760806916426516,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990389611745551,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.18179821074008942,
|
|
"num_tokens": 9236271.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.56974515914917,
|
|
"epoch": 0.38808837656099904,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004990357932669672,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.18169892132282256,
|
|
"num_tokens": 9247755.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.494239139556885,
|
|
"epoch": 0.388568683957733,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004990326201579335,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.1900425061583519,
|
|
"num_tokens": 9259821.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.496672630310059,
|
|
"epoch": 0.38904899135446686,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004990294418475274,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.17817943990230561,
|
|
"num_tokens": 9270663.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.541696357727051,
|
|
"epoch": 0.3895292987512008,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004990262583358231,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.17560615092515947,
|
|
"num_tokens": 9282588.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.572092294692993,
|
|
"epoch": 0.3900096061479347,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990230696228943,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.17164741903543473,
|
|
"num_tokens": 9293368.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.542194414138794,
|
|
"epoch": 0.3904899135446686,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990198757088149,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.17514693439006807,
|
|
"num_tokens": 9305962.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.509642601013184,
|
|
"epoch": 0.3909702209414025,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004990166765936593,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.18677641898393632,
|
|
"num_tokens": 9317955.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.517404317855835,
|
|
"epoch": 0.3914505283381364,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990134722775016,
|
|
"loss": 5.4457,
|
|
"mean_token_accuracy": 0.18348104059696196,
|
|
"num_tokens": 9329491.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.540238523483277,
|
|
"epoch": 0.3919308357348703,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004990102627604162,
|
|
"loss": 5.5691,
|
|
"mean_token_accuracy": 0.18746854960918427,
|
|
"num_tokens": 9341612.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.625320625305176,
|
|
"epoch": 0.39241114313160425,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004990070480424778,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.17848047614097595,
|
|
"num_tokens": 9352302.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.504978513717651,
|
|
"epoch": 0.3928914505283381,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990038281237608,
|
|
"loss": 5.4549,
|
|
"mean_token_accuracy": 0.18171960562467576,
|
|
"num_tokens": 9363303.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.515370559692383,
|
|
"epoch": 0.39337175792507206,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990006030043401,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.17685695141553878,
|
|
"num_tokens": 9375878.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.535539054870606,
|
|
"epoch": 0.39385206532180594,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004989973726842906,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.17544336766004562,
|
|
"num_tokens": 9388342.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.464720916748047,
|
|
"epoch": 0.3943323727185399,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004989941371636872,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.1858261212706566,
|
|
"num_tokens": 9399047.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.544233131408691,
|
|
"epoch": 0.39481268011527376,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989908964426051,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.18549448251724243,
|
|
"num_tokens": 9410172.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.6142524719238285,
|
|
"epoch": 0.3952929875120077,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989876505211194,
|
|
"loss": 5.6152,
|
|
"mean_token_accuracy": 0.17758406400680543,
|
|
"num_tokens": 9422287.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.6228515148162845,
|
|
"epoch": 0.3957732949087416,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004989843993993056,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.18429362028837204,
|
|
"num_tokens": 9433709.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.456875514984131,
|
|
"epoch": 0.3962536023054755,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989811430772392,
|
|
"loss": 5.3601,
|
|
"mean_token_accuracy": 0.18258956223726272,
|
|
"num_tokens": 9445138.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.522043371200562,
|
|
"epoch": 0.3967339097022094,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004989778815549957,
|
|
"loss": 5.4981,
|
|
"mean_token_accuracy": 0.18228088766336442,
|
|
"num_tokens": 9455263.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.560954809188843,
|
|
"epoch": 0.39721421709894333,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004989746148326508,
|
|
"loss": 5.4539,
|
|
"mean_token_accuracy": 0.18290841579437256,
|
|
"num_tokens": 9465491.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.410928201675415,
|
|
"epoch": 0.3976945244956772,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989713429102805,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.17788441926240922,
|
|
"num_tokens": 9477601.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.511400461196899,
|
|
"epoch": 0.39817483189241115,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004989680657879607,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.18474960178136826,
|
|
"num_tokens": 9489385.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.5039530277252195,
|
|
"epoch": 0.39865513928914503,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004989647834657675,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.1888881355524063,
|
|
"num_tokens": 9501131.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.441250467300415,
|
|
"epoch": 0.39913544668587897,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000498961495943777,
|
|
"loss": 5.5146,
|
|
"mean_token_accuracy": 0.18456829488277435,
|
|
"num_tokens": 9513094.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.657707595825196,
|
|
"epoch": 0.39961575408261285,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004989582032220656,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.17549483478069305,
|
|
"num_tokens": 9524538.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.58910174369812,
|
|
"epoch": 0.4000960614793468,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004989549053007096,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.18928951025009155,
|
|
"num_tokens": 9535284.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.45146427154541,
|
|
"epoch": 0.40057636887608067,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004989516021797858,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.17948976159095764,
|
|
"num_tokens": 9546472.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.500121641159057,
|
|
"epoch": 0.4010566762728146,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000498948293859371,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.1782221570611,
|
|
"num_tokens": 9558358.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.575967025756836,
|
|
"epoch": 0.4015369836695485,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004989449803395415,
|
|
"loss": 5.541,
|
|
"mean_token_accuracy": 0.179440476000309,
|
|
"num_tokens": 9570653.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.587913465499878,
|
|
"epoch": 0.4020172910662824,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004989416616203747,
|
|
"loss": 5.4919,
|
|
"mean_token_accuracy": 0.1813455805182457,
|
|
"num_tokens": 9582150.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.561476802825927,
|
|
"epoch": 0.4024975984630163,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004989383377019476,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.18601921051740647,
|
|
"num_tokens": 9592462.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.475375366210938,
|
|
"epoch": 0.40297790585975024,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004989350085843371,
|
|
"loss": 5.417,
|
|
"mean_token_accuracy": 0.18254369199275972,
|
|
"num_tokens": 9604027.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.504195070266723,
|
|
"epoch": 0.4034582132564842,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989316742676207,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.18261410742998124,
|
|
"num_tokens": 9616325.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.421117448806763,
|
|
"epoch": 0.40393852065321806,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004989283347518757,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.18290347456932068,
|
|
"num_tokens": 9628133.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.585645580291748,
|
|
"epoch": 0.404418828049952,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004989249900371797,
|
|
"loss": 5.6046,
|
|
"mean_token_accuracy": 0.17469607889652253,
|
|
"num_tokens": 9639686.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.576600694656372,
|
|
"epoch": 0.4048991354466859,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004989216401236103,
|
|
"loss": 5.4863,
|
|
"mean_token_accuracy": 0.18374434411525725,
|
|
"num_tokens": 9650222.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.380108976364136,
|
|
"epoch": 0.4053794428434198,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989182850112455,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.19340623021125794,
|
|
"num_tokens": 9661792.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.521292495727539,
|
|
"epoch": 0.4058597502401537,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989149247001629,
|
|
"loss": 5.5115,
|
|
"mean_token_accuracy": 0.1784104362130165,
|
|
"num_tokens": 9673000.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.6082254409790036,
|
|
"epoch": 0.40634005763688763,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989115591904407,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.18488294780254363,
|
|
"num_tokens": 9685253.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.446391916275024,
|
|
"epoch": 0.4068203650336215,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004989081884821569,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.17681196182966233,
|
|
"num_tokens": 9697245.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.513550043106079,
|
|
"epoch": 0.40730067243035545,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004989048125753899,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.1809759959578514,
|
|
"num_tokens": 9710095.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.511830568313599,
|
|
"epoch": 0.40778097982708933,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000498901431470218,
|
|
"loss": 5.3622,
|
|
"mean_token_accuracy": 0.1893300712108612,
|
|
"num_tokens": 9721488.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.3263427257537845,
|
|
"epoch": 0.40826128722382327,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988980451667198,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.19156421422958375,
|
|
"num_tokens": 9733280.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.508168935775757,
|
|
"epoch": 0.40874159462055715,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988946536649737,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.177663654088974,
|
|
"num_tokens": 9744514.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.484134531021118,
|
|
"epoch": 0.4092219020172911,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004988912569650585,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.18552776724100112,
|
|
"num_tokens": 9754931.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.435315275192261,
|
|
"epoch": 0.40970220941402496,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004988878550670533,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.18660751730203629,
|
|
"num_tokens": 9765635.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.537139463424682,
|
|
"epoch": 0.4101825168107589,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004988844479710369,
|
|
"loss": 5.5225,
|
|
"mean_token_accuracy": 0.1758018046617508,
|
|
"num_tokens": 9777512.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.597617721557617,
|
|
"epoch": 0.4106628242074928,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004988810356770884,
|
|
"loss": 5.5557,
|
|
"mean_token_accuracy": 0.16869372874498367,
|
|
"num_tokens": 9790128.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.551325702667237,
|
|
"epoch": 0.4111431316042267,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000498877618185287,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.1843498706817627,
|
|
"num_tokens": 9802549.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.473504495620728,
|
|
"epoch": 0.4116234390009606,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004988741954957121,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.18176692277193068,
|
|
"num_tokens": 9813736.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.405496072769165,
|
|
"epoch": 0.41210374639769454,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004988707676084432,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.19114568531513215,
|
|
"num_tokens": 9823785.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.486332750320434,
|
|
"epoch": 0.4125840537944284,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004988673345235597,
|
|
"loss": 5.3615,
|
|
"mean_token_accuracy": 0.18773864805698395,
|
|
"num_tokens": 9834910.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.502135229110718,
|
|
"epoch": 0.41306436119116235,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004988638962411416,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.18564249128103255,
|
|
"num_tokens": 9845593.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.476961755752564,
|
|
"epoch": 0.41354466858789624,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988604527612685,
|
|
"loss": 5.3203,
|
|
"mean_token_accuracy": 0.19852617830038072,
|
|
"num_tokens": 9856763.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.537204456329346,
|
|
"epoch": 0.4140249759846302,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004988570040840205,
|
|
"loss": 5.5679,
|
|
"mean_token_accuracy": 0.17313459217548371,
|
|
"num_tokens": 9869528.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.449116659164429,
|
|
"epoch": 0.41450528338136405,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004988535502094774,
|
|
"loss": 5.4486,
|
|
"mean_token_accuracy": 0.18336778432130812,
|
|
"num_tokens": 9881170.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.5526079654693605,
|
|
"epoch": 0.414985590778098,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004988500911377198,
|
|
"loss": 5.5287,
|
|
"mean_token_accuracy": 0.17965437471866608,
|
|
"num_tokens": 9893119.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.4270538806915285,
|
|
"epoch": 0.41546589817483187,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988466268688276,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.19209852814674377,
|
|
"num_tokens": 9905339.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.568780183792114,
|
|
"epoch": 0.4159462055715658,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004988431574028814,
|
|
"loss": 5.4664,
|
|
"mean_token_accuracy": 0.18641627877950667,
|
|
"num_tokens": 9917500.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.552721977233887,
|
|
"epoch": 0.4164265129682997,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988396827399618,
|
|
"loss": 5.5565,
|
|
"mean_token_accuracy": 0.1737346515059471,
|
|
"num_tokens": 9929667.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.5436145782470705,
|
|
"epoch": 0.4169068203650336,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004988362028801495,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.1871032103896141,
|
|
"num_tokens": 9941102.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.434776878356933,
|
|
"epoch": 0.4173871277617675,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988327178235253,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.19279926568269729,
|
|
"num_tokens": 9951986.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.468888187408448,
|
|
"epoch": 0.41786743515850144,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004988292275701699,
|
|
"loss": 5.3677,
|
|
"mean_token_accuracy": 0.19006619602441788,
|
|
"num_tokens": 9964486.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.48706545829773,
|
|
"epoch": 0.4183477425552353,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004988257321201646,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.18283984959125518,
|
|
"num_tokens": 9975909.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.553270387649536,
|
|
"epoch": 0.41882804995196926,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004988222314735902,
|
|
"loss": 5.4706,
|
|
"mean_token_accuracy": 0.1822444513440132,
|
|
"num_tokens": 9986951.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.570775032043457,
|
|
"epoch": 0.41930835734870314,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004988187256305284,
|
|
"loss": 5.569,
|
|
"mean_token_accuracy": 0.17401701658964158,
|
|
"num_tokens": 9999234.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.4847218036651615,
|
|
"epoch": 0.4197886647454371,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004988152145910603,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.18869160115718842,
|
|
"num_tokens": 10010178.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.452528238296509,
|
|
"epoch": 0.420268972142171,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004988116983552675,
|
|
"loss": 5.3951,
|
|
"mean_token_accuracy": 0.18093497604131697,
|
|
"num_tokens": 10021183.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.649744462966919,
|
|
"epoch": 0.4207492795389049,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004988081769232317,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.17173523902893068,
|
|
"num_tokens": 10033686.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.52200403213501,
|
|
"epoch": 0.42122958693563883,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004988046502950346,
|
|
"loss": 5.3918,
|
|
"mean_token_accuracy": 0.18444338589906692,
|
|
"num_tokens": 10045923.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.294298982620239,
|
|
"epoch": 0.4217098943323727,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000498801118470758,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.1956006482243538,
|
|
"num_tokens": 10057196.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.4460125923156735,
|
|
"epoch": 0.42219020172910665,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000498797581450484,
|
|
"loss": 5.4902,
|
|
"mean_token_accuracy": 0.17721165865659713,
|
|
"num_tokens": 10069655.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.537206220626831,
|
|
"epoch": 0.42267050912584053,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004987940392342948,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.18441937863826752,
|
|
"num_tokens": 10080876.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.511677026748657,
|
|
"epoch": 0.42315081652257447,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987904918222726,
|
|
"loss": 5.4467,
|
|
"mean_token_accuracy": 0.1796922728419304,
|
|
"num_tokens": 10091986.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.5545533180236815,
|
|
"epoch": 0.42363112391930835,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004987869392144996,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.18445588648319244,
|
|
"num_tokens": 10104027.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.533651399612427,
|
|
"epoch": 0.4241114313160423,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004987833814110584,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.1845202013850212,
|
|
"num_tokens": 10114665.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.4492896556854244,
|
|
"epoch": 0.42459173871277617,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004987798184120316,
|
|
"loss": 5.419,
|
|
"mean_token_accuracy": 0.18481650501489638,
|
|
"num_tokens": 10126032.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.528508615493775,
|
|
"epoch": 0.4250720461095101,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004987762502175018,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.1785368174314499,
|
|
"num_tokens": 10137256.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.427718877792358,
|
|
"epoch": 0.425552353506244,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498772676827552,
|
|
"loss": 5.3493,
|
|
"mean_token_accuracy": 0.1878319725394249,
|
|
"num_tokens": 10149445.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.5632466793060305,
|
|
"epoch": 0.4260326609029779,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004987690982422652,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.1750901609659195,
|
|
"num_tokens": 10161607.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.577398109436035,
|
|
"epoch": 0.4265129682997118,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004987655144617243,
|
|
"loss": 5.5277,
|
|
"mean_token_accuracy": 0.17866371423006058,
|
|
"num_tokens": 10173184.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.468634033203125,
|
|
"epoch": 0.42699327569644574,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004987619254860126,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.1921435832977295,
|
|
"num_tokens": 10184617.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.455842161178589,
|
|
"epoch": 0.4274735830931796,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004987583313152134,
|
|
"loss": 5.4107,
|
|
"mean_token_accuracy": 0.18547915518283845,
|
|
"num_tokens": 10195608.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.498785591125488,
|
|
"epoch": 0.42795389048991356,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987547319494104,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.18357907682657243,
|
|
"num_tokens": 10206763.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.508453369140625,
|
|
"epoch": 0.42843419788664744,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004987511273886867,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.18445866256952287,
|
|
"num_tokens": 10218714.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.511985921859742,
|
|
"epoch": 0.4289145052833814,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004987475176331263,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.1775077238678932,
|
|
"num_tokens": 10229902.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.5037613868713375,
|
|
"epoch": 0.42939481268011526,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004987439026828129,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.18072725981473922,
|
|
"num_tokens": 10241578.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.384706926345825,
|
|
"epoch": 0.4298751200768492,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004987402825378305,
|
|
"loss": 5.3129,
|
|
"mean_token_accuracy": 0.19166758209466933,
|
|
"num_tokens": 10252109.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.496652555465698,
|
|
"epoch": 0.4303554274735831,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004987366571982631,
|
|
"loss": 5.4815,
|
|
"mean_token_accuracy": 0.1814267009496689,
|
|
"num_tokens": 10263357.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.537306404113769,
|
|
"epoch": 0.430835734870317,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004987330266641948,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.17700978517532348,
|
|
"num_tokens": 10275536.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.543120241165161,
|
|
"epoch": 0.4313160422670509,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004987293909357101,
|
|
"loss": 5.4706,
|
|
"mean_token_accuracy": 0.1841297224164009,
|
|
"num_tokens": 10286901.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.420794820785522,
|
|
"epoch": 0.43179634966378483,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004987257500128933,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.18086574822664261,
|
|
"num_tokens": 10298961.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.498356199264526,
|
|
"epoch": 0.4322766570605187,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004987221038958288,
|
|
"loss": 5.5081,
|
|
"mean_token_accuracy": 0.18090696036815643,
|
|
"num_tokens": 10310911.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.586230897903443,
|
|
"epoch": 0.43275696445725265,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987184525846015,
|
|
"loss": 5.4952,
|
|
"mean_token_accuracy": 0.17939264327287674,
|
|
"num_tokens": 10322267.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.460965919494629,
|
|
"epoch": 0.4332372718539865,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987147960792958,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.18221693485975266,
|
|
"num_tokens": 10335111.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.551294946670533,
|
|
"epoch": 0.43371757925072046,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004987111343799971,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.18530049920082092,
|
|
"num_tokens": 10345672.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.594976091384888,
|
|
"epoch": 0.43419788664745435,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00049870746748679,
|
|
"loss": 5.4413,
|
|
"mean_token_accuracy": 0.18363697528839112,
|
|
"num_tokens": 10357369.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.477105140686035,
|
|
"epoch": 0.4346781940441883,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004987037953997598,
|
|
"loss": 5.4611,
|
|
"mean_token_accuracy": 0.1811327040195465,
|
|
"num_tokens": 10368842.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.4907753467559814,
|
|
"epoch": 0.43515850144092216,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004987001181189918,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.18467935174703598,
|
|
"num_tokens": 10380096.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.391097974777222,
|
|
"epoch": 0.4356388088376561,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004986964356445713,
|
|
"loss": 5.4414,
|
|
"mean_token_accuracy": 0.18522116988897325,
|
|
"num_tokens": 10391996.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.478848934173584,
|
|
"epoch": 0.43611911623439004,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004986927479765837,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.1784711480140686,
|
|
"num_tokens": 10403607.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.490837240219117,
|
|
"epoch": 0.4365994236311239,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004986890551151148,
|
|
"loss": 5.429,
|
|
"mean_token_accuracy": 0.18094509243965148,
|
|
"num_tokens": 10413580.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.457474088668823,
|
|
"epoch": 0.43707973102785785,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004986853570602503,
|
|
"loss": 5.4459,
|
|
"mean_token_accuracy": 0.18024460822343827,
|
|
"num_tokens": 10426456.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.604650068283081,
|
|
"epoch": 0.43756003842459174,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004986816538120758,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.18038389682769776,
|
|
"num_tokens": 10438869.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.498773765563965,
|
|
"epoch": 0.43804034582132567,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004986779453706778,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.17989878952503205,
|
|
"num_tokens": 10450672.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.495636940002441,
|
|
"epoch": 0.43852065321805955,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004986742317361419,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.18654994070529937,
|
|
"num_tokens": 10461890.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.546713972091675,
|
|
"epoch": 0.4390009606147935,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004986705129085546,
|
|
"loss": 5.526,
|
|
"mean_token_accuracy": 0.17035581171512604,
|
|
"num_tokens": 10473866.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.543576002120972,
|
|
"epoch": 0.43948126801152737,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004986667888880021,
|
|
"loss": 5.4539,
|
|
"mean_token_accuracy": 0.18211366832256318,
|
|
"num_tokens": 10484889.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.432088327407837,
|
|
"epoch": 0.4399615754082613,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004986630596745709,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.18385321646928787,
|
|
"num_tokens": 10496108.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.461386775970459,
|
|
"epoch": 0.4404418828049952,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004986593252683477,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.18547086268663407,
|
|
"num_tokens": 10505472.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.373687839508056,
|
|
"epoch": 0.4409221902017291,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004986555856694191,
|
|
"loss": 5.3299,
|
|
"mean_token_accuracy": 0.19148807376623153,
|
|
"num_tokens": 10516954.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.614930868148804,
|
|
"epoch": 0.441402497598463,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986518408778718,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.18133965283632278,
|
|
"num_tokens": 10528166.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.407241439819336,
|
|
"epoch": 0.44188280499519694,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004986480908937929,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.18452172428369523,
|
|
"num_tokens": 10538112.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.496711540222168,
|
|
"epoch": 0.4423631123919308,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004986443357172695,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.18452446013689042,
|
|
"num_tokens": 10549888.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.677416658401489,
|
|
"epoch": 0.44284341978866476,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004986405753483887,
|
|
"loss": 5.5769,
|
|
"mean_token_accuracy": 0.17137915790081024,
|
|
"num_tokens": 10561710.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.502679777145386,
|
|
"epoch": 0.44332372718539864,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004986368097872377,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.18070939034223557,
|
|
"num_tokens": 10574564.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.517158842086792,
|
|
"epoch": 0.4438040345821326,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986330390339042,
|
|
"loss": 5.4323,
|
|
"mean_token_accuracy": 0.18373309820890427,
|
|
"num_tokens": 10586639.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.479751491546631,
|
|
"epoch": 0.44428434197886646,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004986292630884755,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.18545992523431779,
|
|
"num_tokens": 10598730.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.420074462890625,
|
|
"epoch": 0.4447646493756004,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004986254819510393,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.1930258169770241,
|
|
"num_tokens": 10610352.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.4433269023895265,
|
|
"epoch": 0.4452449567723343,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004986216956216835,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.18387746065855026,
|
|
"num_tokens": 10621951.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.470367765426635,
|
|
"epoch": 0.4457252641690682,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000498617904100496,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.18627140671014786,
|
|
"num_tokens": 10633207.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.544760608673096,
|
|
"epoch": 0.4462055715658021,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986141073875646,
|
|
"loss": 5.4758,
|
|
"mean_token_accuracy": 0.17636162787675858,
|
|
"num_tokens": 10645853.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.4318643569946286,
|
|
"epoch": 0.44668587896253603,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004986103054829779,
|
|
"loss": 5.3768,
|
|
"mean_token_accuracy": 0.18752384483814238,
|
|
"num_tokens": 10656892.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.445742559432984,
|
|
"epoch": 0.4471661863592699,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004986064983868237,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.17737783789634703,
|
|
"num_tokens": 10670110.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.482235908508301,
|
|
"epoch": 0.44764649375600385,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004986026860991906,
|
|
"loss": 5.5124,
|
|
"mean_token_accuracy": 0.18077742159366608,
|
|
"num_tokens": 10681255.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.56576509475708,
|
|
"epoch": 0.44812680115273773,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004985988686201672,
|
|
"loss": 5.5624,
|
|
"mean_token_accuracy": 0.1790735423564911,
|
|
"num_tokens": 10692631.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.500433683395386,
|
|
"epoch": 0.44860710854947167,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985950459498419,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.1898837685585022,
|
|
"num_tokens": 10704880.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.471106481552124,
|
|
"epoch": 0.44908741594620555,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004985912180883037,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.19305551052093506,
|
|
"num_tokens": 10715561.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.458360004425049,
|
|
"epoch": 0.4495677233429395,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004985873850356411,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.18060278296470642,
|
|
"num_tokens": 10727232.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.48356294631958,
|
|
"epoch": 0.45004803073967337,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004985835467919436,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.18828755617141724,
|
|
"num_tokens": 10739404.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.501414632797241,
|
|
"epoch": 0.4505283381364073,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004985797033572999,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.1817610442638397,
|
|
"num_tokens": 10751948.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.474892950057983,
|
|
"epoch": 0.4510086455331412,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985758547317994,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.1786559998989105,
|
|
"num_tokens": 10764611.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.516329956054688,
|
|
"epoch": 0.4514889529298751,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004985720009155315,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.17884828746318818,
|
|
"num_tokens": 10775954.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.53729100227356,
|
|
"epoch": 0.45196926032660906,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004985681419085856,
|
|
"loss": 5.4607,
|
|
"mean_token_accuracy": 0.17329588681459426,
|
|
"num_tokens": 10788723.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.484022426605224,
|
|
"epoch": 0.45244956772334294,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004985642777110513,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.18629533052444458,
|
|
"num_tokens": 10799879.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.390105772018432,
|
|
"epoch": 0.4529298751200769,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004985604083230183,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.18570472300052643,
|
|
"num_tokens": 10811838.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.506688117980957,
|
|
"epoch": 0.45341018251681076,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004985565337445765,
|
|
"loss": 5.3985,
|
|
"mean_token_accuracy": 0.1865394651889801,
|
|
"num_tokens": 10822910.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.528910541534424,
|
|
"epoch": 0.4538904899135447,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004985526539758158,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.181230391561985,
|
|
"num_tokens": 10835344.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.482353925704956,
|
|
"epoch": 0.4543707973102786,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004985487690168263,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.18611288368701934,
|
|
"num_tokens": 10846043.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.435640621185303,
|
|
"epoch": 0.4548511047070125,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000498544878867698,
|
|
"loss": 5.3768,
|
|
"mean_token_accuracy": 0.18816656321287156,
|
|
"num_tokens": 10857783.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.50838885307312,
|
|
"epoch": 0.4553314121037464,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004985409835285215,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.18389986604452133,
|
|
"num_tokens": 10870527.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.511764812469482,
|
|
"epoch": 0.45581171950048033,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004985370829993873,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.18304894864559174,
|
|
"num_tokens": 10882285.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.547654867172241,
|
|
"epoch": 0.4562920268972142,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985331772803857,
|
|
"loss": 5.4647,
|
|
"mean_token_accuracy": 0.18388849198818208,
|
|
"num_tokens": 10895319.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.571902132034301,
|
|
"epoch": 0.45677233429394815,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985292663716074,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.1853088766336441,
|
|
"num_tokens": 10906253.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.3311303615570065,
|
|
"epoch": 0.457252641690682,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985253502731435,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.18947790712118148,
|
|
"num_tokens": 10918197.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.478621578216552,
|
|
"epoch": 0.45773294908741596,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985214289850845,
|
|
"loss": 5.5233,
|
|
"mean_token_accuracy": 0.17755923867225648,
|
|
"num_tokens": 10930771.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.507424020767212,
|
|
"epoch": 0.45821325648414984,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985175025075217,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.18604848086833953,
|
|
"num_tokens": 10942759.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.68710732460022,
|
|
"epoch": 0.4586935638808838,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004985135708405462,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.17268539369106292,
|
|
"num_tokens": 10953557.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.5322432041168215,
|
|
"epoch": 0.45917387127761766,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004985096339842493,
|
|
"loss": 5.3802,
|
|
"mean_token_accuracy": 0.19421082735061646,
|
|
"num_tokens": 10963142.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.353709936141968,
|
|
"epoch": 0.4596541786743516,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004985056919387224,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.1882830962538719,
|
|
"num_tokens": 10974321.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.510710334777832,
|
|
"epoch": 0.4601344860710855,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004985017447040569,
|
|
"loss": 5.5528,
|
|
"mean_token_accuracy": 0.18205974102020264,
|
|
"num_tokens": 10985524.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.606180334091187,
|
|
"epoch": 0.4606147934678194,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004984977922803447,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.18467483967542647,
|
|
"num_tokens": 10997606.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.489244985580444,
|
|
"epoch": 0.4610951008645533,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004984938346676772,
|
|
"loss": 5.4411,
|
|
"mean_token_accuracy": 0.17622300386428832,
|
|
"num_tokens": 11010692.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.475787210464477,
|
|
"epoch": 0.46157540826128723,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004984898718661468,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.19200236350297928,
|
|
"num_tokens": 11022517.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.481667518615723,
|
|
"epoch": 0.4620557156580211,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004984859038758451,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.18805709928274156,
|
|
"num_tokens": 11033141.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.395406770706177,
|
|
"epoch": 0.46253602305475505,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004984819306968642,
|
|
"loss": 5.3745,
|
|
"mean_token_accuracy": 0.18240353912115098,
|
|
"num_tokens": 11044619.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.523858642578125,
|
|
"epoch": 0.46301633045148893,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004984779523292966,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.18529865592718125,
|
|
"num_tokens": 11055934.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.489401531219483,
|
|
"epoch": 0.46349663784822287,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004984739687732345,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.1878582939505577,
|
|
"num_tokens": 11066203.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.288503694534302,
|
|
"epoch": 0.46397694524495675,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984699800287705,
|
|
"loss": 5.2751,
|
|
"mean_token_accuracy": 0.1923237219452858,
|
|
"num_tokens": 11079664.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.383805751800537,
|
|
"epoch": 0.4644572526416907,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000498465986095997,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.19276348054409026,
|
|
"num_tokens": 11091186.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.554166507720947,
|
|
"epoch": 0.46493756003842457,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984619869750069,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.17982964515686034,
|
|
"num_tokens": 11102710.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.376062488555908,
|
|
"epoch": 0.4654178674351585,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000498457982665893,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.19003613591194152,
|
|
"num_tokens": 11114746.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.472731447219848,
|
|
"epoch": 0.4658981748318924,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004984539731687483,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.1846705749630928,
|
|
"num_tokens": 11126572.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.45322699546814,
|
|
"epoch": 0.4663784822286263,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004984499584836659,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.19166803508996963,
|
|
"num_tokens": 11137830.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.370902109146118,
|
|
"epoch": 0.4668587896253602,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000498445938610739,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.18561027497053145,
|
|
"num_tokens": 11148860.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.510472774505615,
|
|
"epoch": 0.46733909702209414,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004984419135500608,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.17668079435825348,
|
|
"num_tokens": 11161311.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.515774488449097,
|
|
"epoch": 0.4678194044188281,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004984378833017249,
|
|
"loss": 5.3646,
|
|
"mean_token_accuracy": 0.18542011827230453,
|
|
"num_tokens": 11173124.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.4339056491851805,
|
|
"epoch": 0.46829971181556196,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004984338478658248,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.18449425101280212,
|
|
"num_tokens": 11184879.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.513182306289673,
|
|
"epoch": 0.4687800192122959,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004984298072424542,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.17791427224874495,
|
|
"num_tokens": 11196243.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.477718782424927,
|
|
"epoch": 0.4692603266090298,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000498425761431707,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.19248305559158324,
|
|
"num_tokens": 11207485.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.348641490936279,
|
|
"epoch": 0.4697406340057637,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000498421710433677,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.18475315421819688,
|
|
"num_tokens": 11219891.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.546237564086914,
|
|
"epoch": 0.4702209414024976,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004984176542484584,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.18318279683589936,
|
|
"num_tokens": 11231329.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.44348635673523,
|
|
"epoch": 0.47070124879923153,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004984135928761452,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.19232119768857955,
|
|
"num_tokens": 11241367.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.438110876083374,
|
|
"epoch": 0.4711815561959654,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984095263168317,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.17885113060474395,
|
|
"num_tokens": 11254532.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.538582229614258,
|
|
"epoch": 0.47166186359269935,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004984054545706124,
|
|
"loss": 5.4954,
|
|
"mean_token_accuracy": 0.17841024249792098,
|
|
"num_tokens": 11265223.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.4387819290161135,
|
|
"epoch": 0.47214217098943323,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498401377637582,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.1836462765932083,
|
|
"num_tokens": 11278228.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.6043507099151615,
|
|
"epoch": 0.47262247838616717,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000498397295517835,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.17668805420398712,
|
|
"num_tokens": 11289654.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.478297710418701,
|
|
"epoch": 0.47310278578290105,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004983932082114659,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.19234221428632736,
|
|
"num_tokens": 11301911.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.5209691524505615,
|
|
"epoch": 0.473583093179635,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004983891157185699,
|
|
"loss": 5.5094,
|
|
"mean_token_accuracy": 0.17697086781263352,
|
|
"num_tokens": 11312945.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.635310935974121,
|
|
"epoch": 0.47406340057636887,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004983850180392421,
|
|
"loss": 5.5501,
|
|
"mean_token_accuracy": 0.17233145236968994,
|
|
"num_tokens": 11324126.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.538080453872681,
|
|
"epoch": 0.4745437079731028,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004983809151735775,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.17741195857524872,
|
|
"num_tokens": 11336395.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.502529907226562,
|
|
"epoch": 0.4750240153698367,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004983768071216713,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.18745690286159516,
|
|
"num_tokens": 11347387.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.418587064743042,
|
|
"epoch": 0.4755043227665706,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004983726938836189,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.18792222440242767,
|
|
"num_tokens": 11358467.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.530980110168457,
|
|
"epoch": 0.4759846301633045,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004983685754595159,
|
|
"loss": 5.5425,
|
|
"mean_token_accuracy": 0.17237244993448259,
|
|
"num_tokens": 11370322.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.417121362686157,
|
|
"epoch": 0.47646493756003844,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004983644518494578,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.1959451049566269,
|
|
"num_tokens": 11381719.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.392659473419189,
|
|
"epoch": 0.4769452449567723,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004983603230535403,
|
|
"loss": 5.3601,
|
|
"mean_token_accuracy": 0.1867404028773308,
|
|
"num_tokens": 11393561.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.505883884429932,
|
|
"epoch": 0.47742555235350626,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004983561890718594,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.18026447296142578,
|
|
"num_tokens": 11405411.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.63366813659668,
|
|
"epoch": 0.47790585975024014,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000498352049904511,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.17523400634527206,
|
|
"num_tokens": 11417419.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.489444303512573,
|
|
"epoch": 0.4783861671469741,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004983479055515914,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.18142345249652864,
|
|
"num_tokens": 11428145.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.389523935317993,
|
|
"epoch": 0.47886647454370795,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983437560131964,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.19079161137342454,
|
|
"num_tokens": 11439224.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.493164348602295,
|
|
"epoch": 0.4793467819404419,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004983396012894228,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.18582673072814943,
|
|
"num_tokens": 11451731.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.532618236541748,
|
|
"epoch": 0.47982708933717577,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983354413803666,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.18884219527244567,
|
|
"num_tokens": 11463058.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.58240065574646,
|
|
"epoch": 0.4803073967339097,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004983312762861248,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.17504217177629472,
|
|
"num_tokens": 11472618.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.462723016738892,
|
|
"epoch": 0.4807877041306436,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004983271060067939,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.1852528840303421,
|
|
"num_tokens": 11483114.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.36872410774231,
|
|
"epoch": 0.4812680115273775,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004983229305424707,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.18662553280591965,
|
|
"num_tokens": 11494281.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.43965973854065,
|
|
"epoch": 0.4817483189241114,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004983187498932522,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.17896797358989716,
|
|
"num_tokens": 11505962.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.623660659790039,
|
|
"epoch": 0.48222862632084534,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004983145640592354,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.1799820676445961,
|
|
"num_tokens": 11517558.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.496991491317749,
|
|
"epoch": 0.4827089337175792,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004983103730405176,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.17999202609062195,
|
|
"num_tokens": 11529184.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.473553848266602,
|
|
"epoch": 0.48318924111431316,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000498306176837196,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.1770265907049179,
|
|
"num_tokens": 11540727.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.47343430519104,
|
|
"epoch": 0.48366954851104704,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004983019754493681,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.1820858210325241,
|
|
"num_tokens": 11551510.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.506567716598511,
|
|
"epoch": 0.484149855907781,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004982977688771314,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.18421542793512344,
|
|
"num_tokens": 11563203.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.4313568592071535,
|
|
"epoch": 0.4846301633045149,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982935571205835,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.18974085450172423,
|
|
"num_tokens": 11576013.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.327564668655396,
|
|
"epoch": 0.4851104707012488,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004982893401798223,
|
|
"loss": 5.2878,
|
|
"mean_token_accuracy": 0.19698146283626555,
|
|
"num_tokens": 11587535.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.492436170578003,
|
|
"epoch": 0.48559077809798273,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004982851180549456,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.1917680472135544,
|
|
"num_tokens": 11598487.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.357746410369873,
|
|
"epoch": 0.4860710854947166,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004982808907460515,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.20567371547222138,
|
|
"num_tokens": 11609457.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.3394629001617435,
|
|
"epoch": 0.48655139289145055,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004982766582532382,
|
|
"loss": 5.305,
|
|
"mean_token_accuracy": 0.19116454273462297,
|
|
"num_tokens": 11620251.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.358263444900513,
|
|
"epoch": 0.48703170028818443,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004982724205766038,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.19739850610494614,
|
|
"num_tokens": 11630956.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.462496185302735,
|
|
"epoch": 0.48751200768491837,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004982681777162468,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.1866704523563385,
|
|
"num_tokens": 11642560.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.389966297149658,
|
|
"epoch": 0.48799231508165225,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982639296722657,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.19174274653196335,
|
|
"num_tokens": 11654050.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.405138921737671,
|
|
"epoch": 0.4884726224783862,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004982596764447591,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.18802273273468018,
|
|
"num_tokens": 11664947.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.504707288742066,
|
|
"epoch": 0.48895292987512007,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982554180338258,
|
|
"loss": 5.3734,
|
|
"mean_token_accuracy": 0.18692844957113267,
|
|
"num_tokens": 11676927.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.626816940307617,
|
|
"epoch": 0.489433237271854,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004982511544395646,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.176315513253212,
|
|
"num_tokens": 11688573.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.379479598999024,
|
|
"epoch": 0.4899135446685879,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004982468856620745,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.18237760961055755,
|
|
"num_tokens": 11698704.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.369692134857178,
|
|
"epoch": 0.4903938520653218,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004982426117014545,
|
|
"loss": 5.3167,
|
|
"mean_token_accuracy": 0.1890370160341263,
|
|
"num_tokens": 11709466.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.438330268859863,
|
|
"epoch": 0.4908741594620557,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004982383325578041,
|
|
"loss": 5.4104,
|
|
"mean_token_accuracy": 0.1841679647564888,
|
|
"num_tokens": 11721120.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.5197105884552,
|
|
"epoch": 0.49135446685878964,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004982340482312226,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.18008144646883012,
|
|
"num_tokens": 11732120.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.385369205474854,
|
|
"epoch": 0.4918347742555235,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004982297587218092,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.19454449862241746,
|
|
"num_tokens": 11743501.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.442886257171631,
|
|
"epoch": 0.49231508165225746,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004982254640296637,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.19070003032684327,
|
|
"num_tokens": 11755051.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.5254920482635494,
|
|
"epoch": 0.49279538904899134,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004982211641548857,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.18197977542877197,
|
|
"num_tokens": 11767663.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.499969148635865,
|
|
"epoch": 0.4932756964457253,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004982168590975752,
|
|
"loss": 5.368,
|
|
"mean_token_accuracy": 0.18997417241334916,
|
|
"num_tokens": 11778828.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.557691955566407,
|
|
"epoch": 0.49375600384245916,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004982125488578321,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.1773864060640335,
|
|
"num_tokens": 11790654.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.547347545623779,
|
|
"epoch": 0.4942363112391931,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004982082334357563,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.18511576652526857,
|
|
"num_tokens": 11801489.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.425420904159546,
|
|
"epoch": 0.494716618635927,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004982039128314481,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.18470419198274612,
|
|
"num_tokens": 11813818.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.401250219345092,
|
|
"epoch": 0.4951969260326609,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004981995870450079,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.18758803606033325,
|
|
"num_tokens": 11824814.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.525042152404785,
|
|
"epoch": 0.4956772334293948,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004981952560765361,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.18153419196605683,
|
|
"num_tokens": 11836252.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.455431985855102,
|
|
"epoch": 0.49615754082612873,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004981909199261331,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.18853455334901809,
|
|
"num_tokens": 11847715.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.333724403381348,
|
|
"epoch": 0.4966378482228626,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004981865785938998,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.1884511739015579,
|
|
"num_tokens": 11860309.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.385854196548462,
|
|
"epoch": 0.49711815561959655,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004981822320799367,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.18876803666353226,
|
|
"num_tokens": 11872569.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.424395275115967,
|
|
"epoch": 0.49759846301633043,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004981778803843449,
|
|
"loss": 5.3235,
|
|
"mean_token_accuracy": 0.18983414620161057,
|
|
"num_tokens": 11884778.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.493177986145019,
|
|
"epoch": 0.49807877041306436,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004981735235072256,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.18636035919189453,
|
|
"num_tokens": 11897324.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.474307632446289,
|
|
"epoch": 0.49855907780979825,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004981691614486796,
|
|
"loss": 5.44,
|
|
"mean_token_accuracy": 0.1859113469719887,
|
|
"num_tokens": 11909145.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.424824237823486,
|
|
"epoch": 0.4990393852065322,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004981647942088084,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.1902564585208893,
|
|
"num_tokens": 11921021.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.575285768508911,
|
|
"epoch": 0.49951969260326606,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004981604217877135,
|
|
"loss": 5.4919,
|
|
"mean_token_accuracy": 0.18358754068613053,
|
|
"num_tokens": 11932565.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.41848578453064,
|
|
"epoch": 0.5,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000498156044185496,
|
|
"loss": 5.4035,
|
|
"mean_token_accuracy": 0.18430701196193694,
|
|
"num_tokens": 11943225.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.479216051101685,
|
|
"epoch": 0.5004803073967339,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004981516614022579,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.1854826405644417,
|
|
"num_tokens": 11954821.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.537558364868164,
|
|
"epoch": 0.5009606147934679,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004981472734381008,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.19163989871740342,
|
|
"num_tokens": 11966090.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.5016881942749025,
|
|
"epoch": 0.5014409221902018,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004981428802931267,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.18924238681793212,
|
|
"num_tokens": 11977410.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.450854635238647,
|
|
"epoch": 0.5019212295869356,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004981384819674375,
|
|
"loss": 5.3687,
|
|
"mean_token_accuracy": 0.18447831720113755,
|
|
"num_tokens": 11989119.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.4909313201904295,
|
|
"epoch": 0.5024015369836695,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004981340784611354,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.18321627378463745,
|
|
"num_tokens": 12000165.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.470381069183349,
|
|
"epoch": 0.5028818443804035,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004981296697743224,
|
|
"loss": 5.4203,
|
|
"mean_token_accuracy": 0.18046394288539885,
|
|
"num_tokens": 12012118.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.491508102416992,
|
|
"epoch": 0.5033621517771374,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004981252559071012,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.1801182895898819,
|
|
"num_tokens": 12023432.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.467731094360351,
|
|
"epoch": 0.5038424591738713,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004981208368595739,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.192879718542099,
|
|
"num_tokens": 12034323.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.437429904937744,
|
|
"epoch": 0.5043227665706052,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004981164126318435,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.1880534842610359,
|
|
"num_tokens": 12045532.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.462672185897827,
|
|
"epoch": 0.5048030739673391,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004981119832240124,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.18699902594089507,
|
|
"num_tokens": 12057346.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.4001758098602295,
|
|
"epoch": 0.505283381364073,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004981075486361837,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.1923503741621971,
|
|
"num_tokens": 12068670.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.506455612182617,
|
|
"epoch": 0.5057636887608069,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004981031088684601,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.17762997150421142,
|
|
"num_tokens": 12079664.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.564687490463257,
|
|
"epoch": 0.5062439961575408,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004980986639209448,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.19255764037370682,
|
|
"num_tokens": 12089984.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.365544223785401,
|
|
"epoch": 0.5067243035542748,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000498094213793741,
|
|
"loss": 5.355,
|
|
"mean_token_accuracy": 0.19078680723905564,
|
|
"num_tokens": 12101182.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.467810153961182,
|
|
"epoch": 0.5072046109510087,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000498089758486952,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.1811884492635727,
|
|
"num_tokens": 12112002.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.576567554473877,
|
|
"epoch": 0.5076849183477425,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004980852980006812,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.1707650601863861,
|
|
"num_tokens": 12124194.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.438126897811889,
|
|
"epoch": 0.5081652257444764,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004980808323350323,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.1884203940629959,
|
|
"num_tokens": 12133966.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.447529745101929,
|
|
"epoch": 0.5086455331412104,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004980763614901089,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.1943483680486679,
|
|
"num_tokens": 12145643.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.438530969619751,
|
|
"epoch": 0.5091258405379443,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004980718854660146,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.18130405247211456,
|
|
"num_tokens": 12156804.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.422643804550171,
|
|
"epoch": 0.5096061479346782,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004980674042628537,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.18323032408952714,
|
|
"num_tokens": 12168700.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.508901882171631,
|
|
"epoch": 0.5100864553314121,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00049806291788073,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.18385652005672454,
|
|
"num_tokens": 12181050.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.564983940124511,
|
|
"epoch": 0.510566762728146,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004980584263197477,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.1835954710841179,
|
|
"num_tokens": 12192001.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.556123065948486,
|
|
"epoch": 0.5110470701248799,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004980539295800111,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.17819563448429107,
|
|
"num_tokens": 12202436.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.4623010635375975,
|
|
"epoch": 0.5115273775216138,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004980494276616246,
|
|
"loss": 5.3558,
|
|
"mean_token_accuracy": 0.18945049494504929,
|
|
"num_tokens": 12214454.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.464614200592041,
|
|
"epoch": 0.5120076849183477,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004980449205646926,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.19334665834903716,
|
|
"num_tokens": 12225924.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.4928870677948,
|
|
"epoch": 0.5124879923150817,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00049804040828932,
|
|
"loss": 5.3783,
|
|
"mean_token_accuracy": 0.18850814253091813,
|
|
"num_tokens": 12236456.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.500979089736939,
|
|
"epoch": 0.5129682997118156,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004980358908356113,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.1887237697839737,
|
|
"num_tokens": 12247719.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.428776454925537,
|
|
"epoch": 0.5134486071085494,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004980313682036717,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.1854885458946228,
|
|
"num_tokens": 12259141.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.562698698043823,
|
|
"epoch": 0.5139289145052833,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004980268403936058,
|
|
"loss": 5.5016,
|
|
"mean_token_accuracy": 0.1816779777407646,
|
|
"num_tokens": 12269748.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.521018171310425,
|
|
"epoch": 0.5144092219020173,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004980223074055189,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.18771007359027864,
|
|
"num_tokens": 12281456.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.514658069610595,
|
|
"epoch": 0.5148895292987512,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004980177692395164,
|
|
"loss": 5.4377,
|
|
"mean_token_accuracy": 0.17850431501865388,
|
|
"num_tokens": 12293763.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.445761108398438,
|
|
"epoch": 0.5153698366954851,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004980132258957035,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.1910960540175438,
|
|
"num_tokens": 12305398.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.385652112960815,
|
|
"epoch": 0.515850144092219,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004980086773741856,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.1843763157725334,
|
|
"num_tokens": 12316582.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.573035144805909,
|
|
"epoch": 0.516330451488953,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004980041236750685,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.1820385292172432,
|
|
"num_tokens": 12328463.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.524788522720337,
|
|
"epoch": 0.5168107588856868,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004979995647984577,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.18823000341653823,
|
|
"num_tokens": 12341040.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.405266761779785,
|
|
"epoch": 0.5172910662824207,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004979950007444593,
|
|
"loss": 5.3378,
|
|
"mean_token_accuracy": 0.18521044701337813,
|
|
"num_tokens": 12353024.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.445263433456421,
|
|
"epoch": 0.5177713736791547,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004979904315131792,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.1885697290301323,
|
|
"num_tokens": 12366100.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.413502740859985,
|
|
"epoch": 0.5182516810758886,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004979858571047233,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.18705111593008042,
|
|
"num_tokens": 12377829.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.549546813964843,
|
|
"epoch": 0.5187319884726225,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004979812775191979,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.18366268277168274,
|
|
"num_tokens": 12390830.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.420849847793579,
|
|
"epoch": 0.5192122958693564,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004979766927567094,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.18831842243671418,
|
|
"num_tokens": 12401642.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.432212781906128,
|
|
"epoch": 0.5196926032660903,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004979721028173643,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.1826647400856018,
|
|
"num_tokens": 12411653.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.485005664825439,
|
|
"epoch": 0.5201729106628242,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000497967507701269,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.19519912153482438,
|
|
"num_tokens": 12422891.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.53105902671814,
|
|
"epoch": 0.5206532180595581,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004979629074085303,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.18660257309675216,
|
|
"num_tokens": 12434190.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.5192982196807865,
|
|
"epoch": 0.521133525456292,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004979583019392548,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.1852166697382927,
|
|
"num_tokens": 12445796.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.535635995864868,
|
|
"epoch": 0.521613832853026,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004979536912935497,
|
|
"loss": 5.5212,
|
|
"mean_token_accuracy": 0.1820803016424179,
|
|
"num_tokens": 12456212.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.399430513381958,
|
|
"epoch": 0.5220941402497599,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000497949075471522,
|
|
"loss": 5.2357,
|
|
"mean_token_accuracy": 0.18977048248052597,
|
|
"num_tokens": 12467871.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.461675977706909,
|
|
"epoch": 0.5225744476464937,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004979444544732786,
|
|
"loss": 5.3681,
|
|
"mean_token_accuracy": 0.1819073423743248,
|
|
"num_tokens": 12478626.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.421274042129516,
|
|
"epoch": 0.5230547550432276,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000497939828298927,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.18347587585449218,
|
|
"num_tokens": 12491487.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.486813592910766,
|
|
"epoch": 0.5235350624399616,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004979351969485747,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.18118082880973815,
|
|
"num_tokens": 12503240.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.531888675689697,
|
|
"epoch": 0.5240153698366955,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004979305604223291,
|
|
"loss": 5.3472,
|
|
"mean_token_accuracy": 0.18776383846998215,
|
|
"num_tokens": 12513860.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.422585391998291,
|
|
"epoch": 0.5244956772334294,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004979259187202978,
|
|
"loss": 5.4165,
|
|
"mean_token_accuracy": 0.1879034698009491,
|
|
"num_tokens": 12525884.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.493587446212769,
|
|
"epoch": 0.5249759846301633,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004979212718425887,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.1858333483338356,
|
|
"num_tokens": 12536709.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.493948745727539,
|
|
"epoch": 0.5254562920268973,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004979166197893096,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.18854524344205856,
|
|
"num_tokens": 12549727.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.424930477142334,
|
|
"epoch": 0.5259365994236311,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004979119625605683,
|
|
"loss": 5.4022,
|
|
"mean_token_accuracy": 0.18080658316612244,
|
|
"num_tokens": 12562053.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.383013200759888,
|
|
"epoch": 0.526416906820365,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004979073001564734,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.19353855699300765,
|
|
"num_tokens": 12574096.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.578636407852173,
|
|
"epoch": 0.5268972142170989,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004979026325771328,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.17848226577043533,
|
|
"num_tokens": 12585416.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.469086170196533,
|
|
"epoch": 0.5273775216138329,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004978979598226549,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.18917791098356246,
|
|
"num_tokens": 12596861.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.409084892272949,
|
|
"epoch": 0.5278578290105668,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004978932818931483,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.19087722450494765,
|
|
"num_tokens": 12607761.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.472339725494384,
|
|
"epoch": 0.5283381364073007,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004978885987887216,
|
|
"loss": 5.4675,
|
|
"mean_token_accuracy": 0.1847461238503456,
|
|
"num_tokens": 12619889.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.592504024505615,
|
|
"epoch": 0.5288184438040345,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004978839105094833,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.182132388651371,
|
|
"num_tokens": 12630604.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.403963327407837,
|
|
"epoch": 0.5292987512007685,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004978792170555426,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.18854816257953644,
|
|
"num_tokens": 12641172.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.372640609741211,
|
|
"epoch": 0.5297790585975024,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004978745184270083,
|
|
"loss": 5.2372,
|
|
"mean_token_accuracy": 0.20051708668470383,
|
|
"num_tokens": 12651731.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.440945434570312,
|
|
"epoch": 0.5302593659942363,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004978698146239893,
|
|
"loss": 5.3686,
|
|
"mean_token_accuracy": 0.18961266726255416,
|
|
"num_tokens": 12663050.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.519006967544556,
|
|
"epoch": 0.5307396733909702,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004978651056465952,
|
|
"loss": 5.4775,
|
|
"mean_token_accuracy": 0.18122595995664598,
|
|
"num_tokens": 12674732.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.418521881103516,
|
|
"epoch": 0.5312199807877042,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000497860391494935,
|
|
"loss": 5.2848,
|
|
"mean_token_accuracy": 0.18724927604198455,
|
|
"num_tokens": 12685981.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.558603000640869,
|
|
"epoch": 0.531700288184438,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004978556721691183,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.17980359345674515,
|
|
"num_tokens": 12697139.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.472646284103393,
|
|
"epoch": 0.5321805955811719,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004978509476692547,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.185062737762928,
|
|
"num_tokens": 12708268.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.441774892807007,
|
|
"epoch": 0.5326609029779059,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004978462179954538,
|
|
"loss": 5.3759,
|
|
"mean_token_accuracy": 0.1865752547979355,
|
|
"num_tokens": 12720715.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.448896169662476,
|
|
"epoch": 0.5331412103746398,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004978414831478253,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.18887689411640168,
|
|
"num_tokens": 12732409.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.41620717048645,
|
|
"epoch": 0.5336215177713737,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004978367431264794,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.1768452689051628,
|
|
"num_tokens": 12745174.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.509043502807617,
|
|
"epoch": 0.5341018251681076,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004978319979315261,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.1847912609577179,
|
|
"num_tokens": 12756116.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.543591117858886,
|
|
"epoch": 0.5345821325648416,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004978272475630752,
|
|
"loss": 5.3729,
|
|
"mean_token_accuracy": 0.18236169666051866,
|
|
"num_tokens": 12768183.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.382640790939331,
|
|
"epoch": 0.5350624399615754,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004978224920212374,
|
|
"loss": 5.3482,
|
|
"mean_token_accuracy": 0.18348369300365447,
|
|
"num_tokens": 12778537.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.418297481536865,
|
|
"epoch": 0.5355427473583093,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004978177313061232,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.1862853392958641,
|
|
"num_tokens": 12789691.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.594165086746216,
|
|
"epoch": 0.5360230547550432,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004978129654178426,
|
|
"loss": 5.4372,
|
|
"mean_token_accuracy": 0.18656151443719865,
|
|
"num_tokens": 12801438.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.475440597534179,
|
|
"epoch": 0.5365033621517772,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004978081943565067,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.18200911283493043,
|
|
"num_tokens": 12812425.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.4256988048553465,
|
|
"epoch": 0.5369836695485111,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004978034181222261,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.1852479249238968,
|
|
"num_tokens": 12824735.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.534474468231201,
|
|
"epoch": 0.537463976945245,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977986367151119,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.1844639465212822,
|
|
"num_tokens": 12835454.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.5627998352050785,
|
|
"epoch": 0.5379442843419788,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004977938501352747,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.17603410929441451,
|
|
"num_tokens": 12847086.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.492933845520019,
|
|
"epoch": 0.5384245917387128,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004977890583828259,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.18292829245328904,
|
|
"num_tokens": 12857713.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.426962041854859,
|
|
"epoch": 0.5389048991354467,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977842614578768,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.18493927866220475,
|
|
"num_tokens": 12869967.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.525805282592773,
|
|
"epoch": 0.5393852065321806,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004977794593605386,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.18438492864370346,
|
|
"num_tokens": 12881230.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.463080644607544,
|
|
"epoch": 0.5398655139289145,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000497774652090923,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.18535702228546141,
|
|
"num_tokens": 12892376.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.5078428268432615,
|
|
"epoch": 0.5403458213256485,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004977698396491414,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.18862044513225557,
|
|
"num_tokens": 12903709.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.3969982147216795,
|
|
"epoch": 0.5408261287223823,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004977650220353055,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.18823839724063873,
|
|
"num_tokens": 12914958.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.387272214889526,
|
|
"epoch": 0.5413064361191162,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004977601992495274,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.18678779900074005,
|
|
"num_tokens": 12927418.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.49278416633606,
|
|
"epoch": 0.5417867435158501,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004977553712919189,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.18559475988149643,
|
|
"num_tokens": 12939874.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.519635915756226,
|
|
"epoch": 0.5422670509125841,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004977505381625921,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.17839331328868865,
|
|
"num_tokens": 12951113.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.415996885299682,
|
|
"epoch": 0.542747358309318,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004977456998616593,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.18952354341745375,
|
|
"num_tokens": 12961940.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.353330612182617,
|
|
"epoch": 0.5432276657060519,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004977408563892327,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.18591278642416,
|
|
"num_tokens": 12973938.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.47374382019043,
|
|
"epoch": 0.5437079731027857,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004977360077454249,
|
|
"loss": 5.3567,
|
|
"mean_token_accuracy": 0.18440620899200438,
|
|
"num_tokens": 12985400.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.475425958633423,
|
|
"epoch": 0.5441882804995197,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004977311539303483,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.19810850620269777,
|
|
"num_tokens": 12996402.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.374849462509156,
|
|
"epoch": 0.5446685878962536,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004977262949441158,
|
|
"loss": 5.2594,
|
|
"mean_token_accuracy": 0.19658494144678115,
|
|
"num_tokens": 13006991.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.455878686904907,
|
|
"epoch": 0.5451488952929875,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004977214307868399,
|
|
"loss": 5.3567,
|
|
"mean_token_accuracy": 0.19109013080596923,
|
|
"num_tokens": 13016969.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.443855857849121,
|
|
"epoch": 0.5456292026897214,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000497716561458634,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.19419611990451813,
|
|
"num_tokens": 13027759.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.548524188995361,
|
|
"epoch": 0.5461095100864554,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004977116869596107,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.18215428441762924,
|
|
"num_tokens": 13039881.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.532558298110962,
|
|
"epoch": 0.5465898174831892,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977068072898834,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.18541376143693925,
|
|
"num_tokens": 13051443.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.538778924942017,
|
|
"epoch": 0.5470701248799231,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004977019224495652,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.17853083163499833,
|
|
"num_tokens": 13063474.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.414380645751953,
|
|
"epoch": 0.547550432276657,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004976970324387698,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.19450528621673585,
|
|
"num_tokens": 13074365.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.442717218399048,
|
|
"epoch": 0.548030739673391,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004976921372576104,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.1856079876422882,
|
|
"num_tokens": 13087354.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.440215969085694,
|
|
"epoch": 0.5485110470701249,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004976872369062011,
|
|
"loss": 5.354,
|
|
"mean_token_accuracy": 0.18371471017599106,
|
|
"num_tokens": 13099306.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.483660745620727,
|
|
"epoch": 0.5489913544668588,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004976823313846552,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.17838382124900817,
|
|
"num_tokens": 13111259.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.586347818374634,
|
|
"epoch": 0.5494716618635928,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004976774206930869,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.18140600472688675,
|
|
"num_tokens": 13123589.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.43156247138977,
|
|
"epoch": 0.5499519692603266,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004976725048316101,
|
|
"loss": 5.3945,
|
|
"mean_token_accuracy": 0.18798534870147704,
|
|
"num_tokens": 13136485.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.504634428024292,
|
|
"epoch": 0.5504322766570605,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004976675838003388,
|
|
"loss": 5.3819,
|
|
"mean_token_accuracy": 0.18276953548192978,
|
|
"num_tokens": 13148067.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.487623453140259,
|
|
"epoch": 0.5509125840537944,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004976626575993877,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.18412308096885682,
|
|
"num_tokens": 13159813.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.480189371109009,
|
|
"epoch": 0.5513928914505284,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004976577262288705,
|
|
"loss": 5.4323,
|
|
"mean_token_accuracy": 0.18472933918237686,
|
|
"num_tokens": 13170828.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.39452486038208,
|
|
"epoch": 0.5518731988472623,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004976527896889023,
|
|
"loss": 5.261,
|
|
"mean_token_accuracy": 0.19969843626022338,
|
|
"num_tokens": 13181883.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.401394987106324,
|
|
"epoch": 0.5523535062439962,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004976478479795974,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.19158275723457335,
|
|
"num_tokens": 13193530.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.582884120941162,
|
|
"epoch": 0.55283381364073,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004976429011010706,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.1732182115316391,
|
|
"num_tokens": 13205822.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.448470878601074,
|
|
"epoch": 0.553314121037464,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004976379490534366,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.1925366371870041,
|
|
"num_tokens": 13216698.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.434690046310425,
|
|
"epoch": 0.5537944284341979,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004976329918368107,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.18587876260280609,
|
|
"num_tokens": 13228389.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.530614042282105,
|
|
"epoch": 0.5542747358309318,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004976280294513079,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.17906455248594283,
|
|
"num_tokens": 13239628.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.460711526870727,
|
|
"epoch": 0.5547550432276657,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004976230618970431,
|
|
"loss": 5.4342,
|
|
"mean_token_accuracy": 0.1860440641641617,
|
|
"num_tokens": 13251149.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.521969556808472,
|
|
"epoch": 0.5552353506243997,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000497618089174132,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.18198818415403367,
|
|
"num_tokens": 13264846.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.4133467197418215,
|
|
"epoch": 0.5557156580211335,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004976131112826898,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.19564270377159118,
|
|
"num_tokens": 13275409.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.3694216251373295,
|
|
"epoch": 0.5561959654178674,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004976081282228323,
|
|
"loss": 5.2484,
|
|
"mean_token_accuracy": 0.19129940122365952,
|
|
"num_tokens": 13287173.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.4618672847747805,
|
|
"epoch": 0.5566762728146013,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000497603139994675,
|
|
"loss": 5.3101,
|
|
"mean_token_accuracy": 0.1882663443684578,
|
|
"num_tokens": 13298225.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.439150953292847,
|
|
"epoch": 0.5571565802113353,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004975981465983338,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.18625201284885406,
|
|
"num_tokens": 13309685.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.414343070983887,
|
|
"epoch": 0.5576368876080692,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004975931480339246,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.19447833597660064,
|
|
"num_tokens": 13320837.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.499085521697998,
|
|
"epoch": 0.5581171950048031,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004975881443015635,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.18788741379976273,
|
|
"num_tokens": 13333512.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.563806200027466,
|
|
"epoch": 0.5585975024015369,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004975831354013667,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.18460088074207306,
|
|
"num_tokens": 13345189.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.460769557952881,
|
|
"epoch": 0.5590778097982709,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004975781213334503,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.18809652477502822,
|
|
"num_tokens": 13356123.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.430902719497681,
|
|
"epoch": 0.5595581171950048,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004975731020979309,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.1902136817574501,
|
|
"num_tokens": 13366902.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.4865504741668705,
|
|
"epoch": 0.5600384245917387,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004975680776949249,
|
|
"loss": 5.4193,
|
|
"mean_token_accuracy": 0.18472786694765092,
|
|
"num_tokens": 13377567.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.497785997390747,
|
|
"epoch": 0.5605187319884726,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004975630481245492,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.1940339207649231,
|
|
"num_tokens": 13387297.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.491007089614868,
|
|
"epoch": 0.5609990393852066,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004975580133869202,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.18964968025684356,
|
|
"num_tokens": 13397723.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.459242963790894,
|
|
"epoch": 0.5614793467819404,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004975529734821552,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.18466618210077285,
|
|
"num_tokens": 13409875.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.495382022857666,
|
|
"epoch": 0.5619596541786743,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004975479284103708,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.18971603512763976,
|
|
"num_tokens": 13421338.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.563063526153565,
|
|
"epoch": 0.5624399615754082,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004975428781716845,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.1888219103217125,
|
|
"num_tokens": 13431373.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.459006643295288,
|
|
"epoch": 0.5629202689721422,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004975378227662134,
|
|
"loss": 5.4187,
|
|
"mean_token_accuracy": 0.18726879209280015,
|
|
"num_tokens": 13443158.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.57106204032898,
|
|
"epoch": 0.5634005763688761,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004975327621940746,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.1814142122864723,
|
|
"num_tokens": 13454559.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.605140590667725,
|
|
"epoch": 0.56388088376561,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004975276964553861,
|
|
"loss": 5.5382,
|
|
"mean_token_accuracy": 0.18275455981492997,
|
|
"num_tokens": 13466934.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.454714250564575,
|
|
"epoch": 0.5643611911623438,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004975226255502651,
|
|
"loss": 5.2983,
|
|
"mean_token_accuracy": 0.1961760088801384,
|
|
"num_tokens": 13477770.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.485685920715332,
|
|
"epoch": 0.5648414985590778,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004975175494788297,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.17858719676733018,
|
|
"num_tokens": 13490093.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.568528890609741,
|
|
"epoch": 0.5653218059558117,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004975124682411974,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.18601441979408265,
|
|
"num_tokens": 13500663.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.548874759674073,
|
|
"epoch": 0.5658021133525456,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004975073818374863,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.18031107783317565,
|
|
"num_tokens": 13512369.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.447829055786133,
|
|
"epoch": 0.5662824207492796,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004975022902678145,
|
|
"loss": 5.3505,
|
|
"mean_token_accuracy": 0.1851808473467827,
|
|
"num_tokens": 13523181.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.416778421401977,
|
|
"epoch": 0.5667627281460135,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004974971935323003,
|
|
"loss": 5.2942,
|
|
"mean_token_accuracy": 0.18543916791677476,
|
|
"num_tokens": 13534113.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.427206420898438,
|
|
"epoch": 0.5672430355427474,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004974920916310619,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.18472990244627,
|
|
"num_tokens": 13545037.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.485990428924561,
|
|
"epoch": 0.5677233429394812,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004974869845642178,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.18833656311035157,
|
|
"num_tokens": 13555541.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.456688737869262,
|
|
"epoch": 0.5682036503362152,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004974818723318866,
|
|
"loss": 5.3704,
|
|
"mean_token_accuracy": 0.18553502410650252,
|
|
"num_tokens": 13566951.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.507200288772583,
|
|
"epoch": 0.5686839577329491,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004974767549341868,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.18253636211156846,
|
|
"num_tokens": 13578492.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.558397912979126,
|
|
"epoch": 0.569164265129683,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004974716323712376,
|
|
"loss": 5.3154,
|
|
"mean_token_accuracy": 0.19755436480045319,
|
|
"num_tokens": 13589183.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.479699182510376,
|
|
"epoch": 0.5696445725264169,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004974665046431576,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.1864132508635521,
|
|
"num_tokens": 13600588.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.369601821899414,
|
|
"epoch": 0.5701248799231509,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004974613717500659,
|
|
"loss": 5.3542,
|
|
"mean_token_accuracy": 0.1948661670088768,
|
|
"num_tokens": 13612107.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.614944744110107,
|
|
"epoch": 0.5706051873198847,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004974562336920818,
|
|
"loss": 5.5263,
|
|
"mean_token_accuracy": 0.17717201858758927,
|
|
"num_tokens": 13623973.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.561570024490356,
|
|
"epoch": 0.5710854947166186,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004974510904693245,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.18963621705770492,
|
|
"num_tokens": 13634994.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.481585597991943,
|
|
"epoch": 0.5715658021133525,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004974459420819134,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.17837628871202468,
|
|
"num_tokens": 13646361.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.40311279296875,
|
|
"epoch": 0.5720461095100865,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000497440788529968,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.18349276781082152,
|
|
"num_tokens": 13656975.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.541668272018432,
|
|
"epoch": 0.5725264169068204,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004974356298136081,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.18403804302215576,
|
|
"num_tokens": 13668434.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.4941794872283936,
|
|
"epoch": 0.5730067243035543,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004974304659329533,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.1841629058122635,
|
|
"num_tokens": 13679266.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.395178174972534,
|
|
"epoch": 0.5734870317002881,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004974252968881236,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.18129157572984694,
|
|
"num_tokens": 13690921.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.465007305145264,
|
|
"epoch": 0.5739673390970221,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000497420122679239,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.18827908337116242,
|
|
"num_tokens": 13702329.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.434066963195801,
|
|
"epoch": 0.574447646493756,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004974149433064196,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.19830148220062255,
|
|
"num_tokens": 13713356.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.3683380603790285,
|
|
"epoch": 0.5749279538904899,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004974097587697856,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.18436487317085265,
|
|
"num_tokens": 13724718.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.332650566101075,
|
|
"epoch": 0.5754082612872238,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004974045690694575,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.1889978528022766,
|
|
"num_tokens": 13736113.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.540743255615235,
|
|
"epoch": 0.5758885686839578,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004973993742055557,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.1878162443637848,
|
|
"num_tokens": 13748322.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.496477937698364,
|
|
"epoch": 0.5763688760806917,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004973941741782007,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.18022316098213195,
|
|
"num_tokens": 13759433.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5763688760806917,
|
|
"eval_entropy": 5.308242887243999,
|
|
"eval_loss": 5.407052040100098,
|
|
"eval_mean_token_accuracy": 0.19222877967988264,
|
|
"eval_num_tokens": 13759433.0,
|
|
"eval_runtime": 26.653,
|
|
"eval_samples_per_second": 1231.193,
|
|
"eval_steps_per_second": 153.904,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.336717510223389,
|
|
"epoch": 0.5768491834774255,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004973889689875135,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.19505809843540192,
|
|
"num_tokens": 13770181.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.403300809860229,
|
|
"epoch": 0.5773294908741594,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004973837586336147,
|
|
"loss": 5.3224,
|
|
"mean_token_accuracy": 0.1860598221421242,
|
|
"num_tokens": 13781792.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.473168659210205,
|
|
"epoch": 0.5778097982708934,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004973785431166254,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.1865010902285576,
|
|
"num_tokens": 13792101.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.404795694351196,
|
|
"epoch": 0.5782901056676273,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004973733224366666,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.18876308798789979,
|
|
"num_tokens": 13803640.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.485610485076904,
|
|
"epoch": 0.5787704130643612,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004973680965938597,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.19072410017251967,
|
|
"num_tokens": 13815017.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.531904315948486,
|
|
"epoch": 0.579250720461095,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004973628655883258,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.1793280780315399,
|
|
"num_tokens": 13826119.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.438629865646362,
|
|
"epoch": 0.579731027857829,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004973576294201865,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.18620188385248185,
|
|
"num_tokens": 13837869.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.660803699493409,
|
|
"epoch": 0.5802113352545629,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004973523880895633,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.17733443081378936,
|
|
"num_tokens": 13849333.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.525416374206543,
|
|
"epoch": 0.5806916426512968,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004973471415965779,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.1875547155737877,
|
|
"num_tokens": 13860648.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.540904521942139,
|
|
"epoch": 0.5811719500480308,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000497341889941352,
|
|
"loss": 5.5066,
|
|
"mean_token_accuracy": 0.1775931939482689,
|
|
"num_tokens": 13872979.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.429767322540283,
|
|
"epoch": 0.5816522574447647,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004973366331240078,
|
|
"loss": 5.379,
|
|
"mean_token_accuracy": 0.18415750563144684,
|
|
"num_tokens": 13884363.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.488360929489136,
|
|
"epoch": 0.5821325648414986,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000497331371144667,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.18459413945674896,
|
|
"num_tokens": 13895424.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.516450262069702,
|
|
"epoch": 0.5826128722382324,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004973261040034521,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.17663205564022064,
|
|
"num_tokens": 13907319.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.404473447799683,
|
|
"epoch": 0.5830931796349664,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004973208317004852,
|
|
"loss": 5.3351,
|
|
"mean_token_accuracy": 0.18712796717882157,
|
|
"num_tokens": 13920013.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.44327745437622,
|
|
"epoch": 0.5835734870317003,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004973155542358889,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.1865224525332451,
|
|
"num_tokens": 13932033.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.428007030487061,
|
|
"epoch": 0.5840537944284342,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004973102716097853,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.1927182972431183,
|
|
"num_tokens": 13943324.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.4614355087280275,
|
|
"epoch": 0.5845341018251681,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004973049838222973,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.19277631491422653,
|
|
"num_tokens": 13954291.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.570868873596192,
|
|
"epoch": 0.5850144092219021,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004972996908735479,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.17546490281820298,
|
|
"num_tokens": 13966264.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.518815565109253,
|
|
"epoch": 0.585494716618636,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004972943927636597,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.18197474628686905,
|
|
"num_tokens": 13977785.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.397167921066284,
|
|
"epoch": 0.5859750240153698,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004972890894927558,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.1924249678850174,
|
|
"num_tokens": 13989704.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.485292911529541,
|
|
"epoch": 0.5864553314121037,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004972837810609592,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.18864688128232956,
|
|
"num_tokens": 14000565.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.407932186126709,
|
|
"epoch": 0.5869356388088377,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004972784674683933,
|
|
"loss": 5.27,
|
|
"mean_token_accuracy": 0.19353238940238954,
|
|
"num_tokens": 14011521.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.380644464492798,
|
|
"epoch": 0.5874159462055716,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004972731487151815,
|
|
"loss": 5.3132,
|
|
"mean_token_accuracy": 0.1962801232933998,
|
|
"num_tokens": 14022966.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.551113605499268,
|
|
"epoch": 0.5878962536023055,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004972678248014471,
|
|
"loss": 5.4547,
|
|
"mean_token_accuracy": 0.1854662373661995,
|
|
"num_tokens": 14034905.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.425469636917114,
|
|
"epoch": 0.5883765609990393,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004972624957273139,
|
|
"loss": 5.2732,
|
|
"mean_token_accuracy": 0.1940221980214119,
|
|
"num_tokens": 14045816.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.366719484329224,
|
|
"epoch": 0.5888568683957733,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004972571614929055,
|
|
"loss": 5.2679,
|
|
"mean_token_accuracy": 0.18620713502168657,
|
|
"num_tokens": 14057316.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.484561729431152,
|
|
"epoch": 0.5893371757925072,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004972518220983457,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.18121753334999086,
|
|
"num_tokens": 14067542.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.37624192237854,
|
|
"epoch": 0.5898174831892411,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004972464775437586,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.18923442363739013,
|
|
"num_tokens": 14079467.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.373081493377685,
|
|
"epoch": 0.590297790585975,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004972411278292683,
|
|
"loss": 5.2206,
|
|
"mean_token_accuracy": 0.19451936483383178,
|
|
"num_tokens": 14090695.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.418972206115723,
|
|
"epoch": 0.590778097982709,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004972357729549988,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.1955699011683464,
|
|
"num_tokens": 14101380.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.397907876968384,
|
|
"epoch": 0.5912584053794429,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004972304129210746,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.19017670005559922,
|
|
"num_tokens": 14112265.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.428981828689575,
|
|
"epoch": 0.5917387127761767,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004972250477276202,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.1881480485200882,
|
|
"num_tokens": 14124294.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.424663782119751,
|
|
"epoch": 0.5922190201729106,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004972196773747599,
|
|
"loss": 5.3377,
|
|
"mean_token_accuracy": 0.1912159100174904,
|
|
"num_tokens": 14135230.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.472915410995483,
|
|
"epoch": 0.5926993275696446,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004972143018626186,
|
|
"loss": 5.4381,
|
|
"mean_token_accuracy": 0.18328657299280166,
|
|
"num_tokens": 14147576.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.439000749588013,
|
|
"epoch": 0.5931796349663785,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004972089211913211,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.19089951366186142,
|
|
"num_tokens": 14158834.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.502074909210205,
|
|
"epoch": 0.5936599423631124,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004972035353609923,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.1823180288076401,
|
|
"num_tokens": 14170694.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.430227136611938,
|
|
"epoch": 0.5941402497598463,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004971981443717572,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.18894438296556473,
|
|
"num_tokens": 14183184.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.5296406745910645,
|
|
"epoch": 0.5946205571565802,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004971927482237409,
|
|
"loss": 5.4331,
|
|
"mean_token_accuracy": 0.18128383308649063,
|
|
"num_tokens": 14194761.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.445153713226318,
|
|
"epoch": 0.5951008645533141,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004971873469170689,
|
|
"loss": 5.2659,
|
|
"mean_token_accuracy": 0.187596920132637,
|
|
"num_tokens": 14205820.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.291012477874756,
|
|
"epoch": 0.595581171950048,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004971819404518664,
|
|
"loss": 5.2955,
|
|
"mean_token_accuracy": 0.19431295692920686,
|
|
"num_tokens": 14217826.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.359121704101563,
|
|
"epoch": 0.5960614793467819,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000497176528828259,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.20106348842382432,
|
|
"num_tokens": 14228632.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.520589447021484,
|
|
"epoch": 0.5965417867435159,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004971711120463722,
|
|
"loss": 5.4825,
|
|
"mean_token_accuracy": 0.17871888875961303,
|
|
"num_tokens": 14240231.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.553158235549927,
|
|
"epoch": 0.5970220941402498,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000497165690106332,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.18950341790914535,
|
|
"num_tokens": 14251718.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.401737213134766,
|
|
"epoch": 0.5975024015369836,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004971602630082642,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.19666553288698196,
|
|
"num_tokens": 14263129.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.332192420959473,
|
|
"epoch": 0.5979827089337176,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004971548307522947,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.1868829682469368,
|
|
"num_tokens": 14274465.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.557712268829346,
|
|
"epoch": 0.5984630163304515,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004971493933385498,
|
|
"loss": 5.4464,
|
|
"mean_token_accuracy": 0.1863687291741371,
|
|
"num_tokens": 14286190.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.532757663726807,
|
|
"epoch": 0.5989433237271854,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004971439507671556,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.18160543069243432,
|
|
"num_tokens": 14297638.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.431942272186279,
|
|
"epoch": 0.5994236311239193,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004971385030382384,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.18987828344106675,
|
|
"num_tokens": 14309773.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.484018421173095,
|
|
"epoch": 0.5999039385206533,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004971330501519248,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.193427737057209,
|
|
"num_tokens": 14320543.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.468566370010376,
|
|
"epoch": 0.6003842459173871,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004971275921083414,
|
|
"loss": 5.3887,
|
|
"mean_token_accuracy": 0.17972762137651443,
|
|
"num_tokens": 14332076.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.388045883178711,
|
|
"epoch": 0.600864553314121,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000497122128907615,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.18734199851751326,
|
|
"num_tokens": 14343768.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.418327522277832,
|
|
"epoch": 0.6013448607108549,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004971166605498722,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.1787777841091156,
|
|
"num_tokens": 14357051.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.4918639183044435,
|
|
"epoch": 0.6018251681075889,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971111870352401,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.18439353555440902,
|
|
"num_tokens": 14368800.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.454588794708252,
|
|
"epoch": 0.6023054755043228,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004971057083638458,
|
|
"loss": 5.3497,
|
|
"mean_token_accuracy": 0.19261357337236404,
|
|
"num_tokens": 14379617.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.395484113693238,
|
|
"epoch": 0.6027857829010567,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004971002245358166,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.19179068356752396,
|
|
"num_tokens": 14391454.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.453966236114502,
|
|
"epoch": 0.6032660902977905,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004970947355512795,
|
|
"loss": 5.3238,
|
|
"mean_token_accuracy": 0.19410835951566696,
|
|
"num_tokens": 14402379.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.354841899871826,
|
|
"epoch": 0.6037463976945245,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004970892414103622,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.19113023281097413,
|
|
"num_tokens": 14415040.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.482425928115845,
|
|
"epoch": 0.6042267050912584,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004970837421131921,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.18193704932928084,
|
|
"num_tokens": 14426677.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.4797656536102295,
|
|
"epoch": 0.6047070124879923,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004970782376598972,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.19061803370714187,
|
|
"num_tokens": 14436676.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.462545442581177,
|
|
"epoch": 0.6051873198847262,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004970727280506048,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.18063507378101348,
|
|
"num_tokens": 14448294.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.39382963180542,
|
|
"epoch": 0.6056676272814602,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004970672132854431,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.1822672203183174,
|
|
"num_tokens": 14460642.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.407764863967896,
|
|
"epoch": 0.6061479346781941,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004970616933645403,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.19766226261854172,
|
|
"num_tokens": 14471370.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.5015716552734375,
|
|
"epoch": 0.6066282420749279,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004970561682880242,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.18795826137065888,
|
|
"num_tokens": 14482358.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.391323566436768,
|
|
"epoch": 0.6071085494716618,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004970506380560233,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.18854544907808304,
|
|
"num_tokens": 14494413.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.505666351318359,
|
|
"epoch": 0.6075888568683958,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004970451026686659,
|
|
"loss": 5.3364,
|
|
"mean_token_accuracy": 0.19639653265476226,
|
|
"num_tokens": 14506370.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.450813055038452,
|
|
"epoch": 0.6080691642651297,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004970395621260806,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.19249093383550644,
|
|
"num_tokens": 14517198.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.4772426128387455,
|
|
"epoch": 0.6085494716618636,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000497034016428396,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.1768304869532585,
|
|
"num_tokens": 14529434.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.38244047164917,
|
|
"epoch": 0.6090297790585975,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004970284655757409,
|
|
"loss": 5.3191,
|
|
"mean_token_accuracy": 0.1890508472919464,
|
|
"num_tokens": 14540857.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.410669469833374,
|
|
"epoch": 0.6095100864553314,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004970229095682439,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.19014334976673125,
|
|
"num_tokens": 14552594.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.517601013183594,
|
|
"epoch": 0.6099903938520653,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004970173484060344,
|
|
"loss": 5.3958,
|
|
"mean_token_accuracy": 0.1807664915919304,
|
|
"num_tokens": 14563599.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.468529176712036,
|
|
"epoch": 0.6104707012487992,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004970117820892414,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.18742034882307052,
|
|
"num_tokens": 14575905.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.4678120613098145,
|
|
"epoch": 0.6109510086455331,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004970062106179939,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.18920456171035765,
|
|
"num_tokens": 14587800.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.418091917037964,
|
|
"epoch": 0.6114313160422671,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004970006339924214,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.18997182846069335,
|
|
"num_tokens": 14600654.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.4359979152679445,
|
|
"epoch": 0.611911623439001,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004969950522126534,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.18815920799970626,
|
|
"num_tokens": 14611985.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.362273168563843,
|
|
"epoch": 0.6123919308357348,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004969894652788196,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.1951830878853798,
|
|
"num_tokens": 14625004.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.452715492248535,
|
|
"epoch": 0.6128722382324687,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004969838731910494,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.18963921070098877,
|
|
"num_tokens": 14635381.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.3693455219268795,
|
|
"epoch": 0.6133525456292027,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004969782759494729,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.19515298157930375,
|
|
"num_tokens": 14646582.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.399004077911377,
|
|
"epoch": 0.6138328530259366,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00049697267355422,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.19258141666650772,
|
|
"num_tokens": 14658024.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.56310396194458,
|
|
"epoch": 0.6143131604226705,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004969670660054208,
|
|
"loss": 5.4222,
|
|
"mean_token_accuracy": 0.18188196122646333,
|
|
"num_tokens": 14669933.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.4577123641967775,
|
|
"epoch": 0.6147934678194045,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004969614533032054,
|
|
"loss": 5.3669,
|
|
"mean_token_accuracy": 0.18193923085927963,
|
|
"num_tokens": 14681331.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.4239137172698975,
|
|
"epoch": 0.6152737752161384,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004969558354477041,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.20023514628410338,
|
|
"num_tokens": 14691361.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.383367300033569,
|
|
"epoch": 0.6157540826128722,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004969502124390474,
|
|
"loss": 5.3231,
|
|
"mean_token_accuracy": 0.19001203775405884,
|
|
"num_tokens": 14701791.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.439683055877685,
|
|
"epoch": 0.6162343900096061,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004969445842773658,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.18004728853702545,
|
|
"num_tokens": 14713672.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.412948560714722,
|
|
"epoch": 0.6167146974063401,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00049693895096279,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.19510987848043443,
|
|
"num_tokens": 14724789.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.4178173542022705,
|
|
"epoch": 0.617195004803074,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004969333124954508,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.18639664947986603,
|
|
"num_tokens": 14737212.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.351517677307129,
|
|
"epoch": 0.6176753121998079,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004969276688754791,
|
|
"loss": 5.294,
|
|
"mean_token_accuracy": 0.1881195992231369,
|
|
"num_tokens": 14748387.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.428181076049805,
|
|
"epoch": 0.6181556195965417,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004969220201030059,
|
|
"loss": 5.3351,
|
|
"mean_token_accuracy": 0.1851325124502182,
|
|
"num_tokens": 14758477.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.455732583999634,
|
|
"epoch": 0.6186359269932757,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004969163661781624,
|
|
"loss": 5.4372,
|
|
"mean_token_accuracy": 0.18978942334651946,
|
|
"num_tokens": 14769650.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.351653814315796,
|
|
"epoch": 0.6191162343900096,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004969107071010798,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.19496227502822877,
|
|
"num_tokens": 14780988.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.4191642761230465,
|
|
"epoch": 0.6195965417867435,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004969050428718895,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.19016269743442535,
|
|
"num_tokens": 14792458.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.441315317153931,
|
|
"epoch": 0.6200768491834774,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000496899373490723,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.18630974143743514,
|
|
"num_tokens": 14804772.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.481175136566162,
|
|
"epoch": 0.6205571565802114,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000496893698957712,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.1823722705245018,
|
|
"num_tokens": 14816126.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.542284631729126,
|
|
"epoch": 0.6210374639769453,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004968880192729882,
|
|
"loss": 5.4596,
|
|
"mean_token_accuracy": 0.18356692790985107,
|
|
"num_tokens": 14829376.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.390783023834229,
|
|
"epoch": 0.6215177713736791,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004968823344366835,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.19644530415534972,
|
|
"num_tokens": 14841098.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.401892757415771,
|
|
"epoch": 0.621998078770413,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004968766444489298,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.1938571035861969,
|
|
"num_tokens": 14852690.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.428385496139526,
|
|
"epoch": 0.622478386167147,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004968709493098593,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.1898894801735878,
|
|
"num_tokens": 14863327.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.455468559265137,
|
|
"epoch": 0.6229586935638809,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004968652490196041,
|
|
"loss": 5.4404,
|
|
"mean_token_accuracy": 0.18365329056978225,
|
|
"num_tokens": 14875213.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.424538660049438,
|
|
"epoch": 0.6234390009606148,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004968595435782967,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.1922861859202385,
|
|
"num_tokens": 14886129.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.510433626174927,
|
|
"epoch": 0.6239193083573487,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004968538329860695,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.18134763091802597,
|
|
"num_tokens": 14897217.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.493000507354736,
|
|
"epoch": 0.6243996157540826,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004968481172430549,
|
|
"loss": 5.4003,
|
|
"mean_token_accuracy": 0.18545977771282196,
|
|
"num_tokens": 14908438.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.356564664840699,
|
|
"epoch": 0.6248799231508165,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000496842396349386,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.19566935151815415,
|
|
"num_tokens": 14920472.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.404738044738769,
|
|
"epoch": 0.6253602305475504,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004968366703051952,
|
|
"loss": 5.345,
|
|
"mean_token_accuracy": 0.18626506626605988,
|
|
"num_tokens": 14932075.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.440768432617188,
|
|
"epoch": 0.6258405379442843,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004968309391106157,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.1897399201989174,
|
|
"num_tokens": 14942971.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.418161773681641,
|
|
"epoch": 0.6263208453410183,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004968252027657806,
|
|
"loss": 5.208,
|
|
"mean_token_accuracy": 0.20186962187290192,
|
|
"num_tokens": 14954288.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.287508726119995,
|
|
"epoch": 0.6268011527377522,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004968194612708229,
|
|
"loss": 5.2816,
|
|
"mean_token_accuracy": 0.18935247659683227,
|
|
"num_tokens": 14966017.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.461360311508178,
|
|
"epoch": 0.627281460134486,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004968137146258759,
|
|
"loss": 5.353,
|
|
"mean_token_accuracy": 0.1887847438454628,
|
|
"num_tokens": 14978022.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.388029527664185,
|
|
"epoch": 0.6277617675312199,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004968079628310732,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.19262229204177855,
|
|
"num_tokens": 14990370.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.334945869445801,
|
|
"epoch": 0.6282420749279539,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004968022058865482,
|
|
"loss": 5.2778,
|
|
"mean_token_accuracy": 0.19936337769031526,
|
|
"num_tokens": 15001535.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.500926876068116,
|
|
"epoch": 0.6287223823246878,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004967964437924346,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.1915559336543083,
|
|
"num_tokens": 15012560.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.374101877212524,
|
|
"epoch": 0.6292026897214217,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004967906765488662,
|
|
"loss": 5.2695,
|
|
"mean_token_accuracy": 0.19490104168653488,
|
|
"num_tokens": 15024594.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.397598314285278,
|
|
"epoch": 0.6296829971181557,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004967849041559769,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.1929749757051468,
|
|
"num_tokens": 15034735.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.437734985351563,
|
|
"epoch": 0.6301633045148896,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004967791266139006,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.18416496962308884,
|
|
"num_tokens": 15046955.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.421305131912232,
|
|
"epoch": 0.6306436119116234,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004967733439227716,
|
|
"loss": 5.2888,
|
|
"mean_token_accuracy": 0.19164934158325195,
|
|
"num_tokens": 15058250.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.415001773834229,
|
|
"epoch": 0.6311239193083573,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000496767556082724,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.18944820910692214,
|
|
"num_tokens": 15069451.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.442015266418457,
|
|
"epoch": 0.6316042267050913,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004967617630938924,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.19320383220911025,
|
|
"num_tokens": 15080920.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.393537425994873,
|
|
"epoch": 0.6320845341018252,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000496755964956411,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.19060759842395783,
|
|
"num_tokens": 15091579.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.467248773574829,
|
|
"epoch": 0.6325648414985591,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004967501616704147,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.1844722017645836,
|
|
"num_tokens": 15103097.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.387191390991211,
|
|
"epoch": 0.633045148895293,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000496744353236038,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.1875634878873825,
|
|
"num_tokens": 15114646.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.4654614448547365,
|
|
"epoch": 0.633525456292027,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000496738539653416,
|
|
"loss": 5.3451,
|
|
"mean_token_accuracy": 0.18893653005361558,
|
|
"num_tokens": 15126019.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.42381443977356,
|
|
"epoch": 0.6340057636887608,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004967327209226835,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.1934414729475975,
|
|
"num_tokens": 15136132.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.465039825439453,
|
|
"epoch": 0.6344860710854947,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004967268970439755,
|
|
"loss": 5.4342,
|
|
"mean_token_accuracy": 0.18379124850034714,
|
|
"num_tokens": 15149016.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.521249294281006,
|
|
"epoch": 0.6349663784822286,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004967210680174274,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.19461192935705185,
|
|
"num_tokens": 15160302.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.436076354980469,
|
|
"epoch": 0.6354466858789626,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004967152338431745,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.1848453998565674,
|
|
"num_tokens": 15171770.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.4191977977752686,
|
|
"epoch": 0.6359269932756965,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004967093945213523,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.19584206044673919,
|
|
"num_tokens": 15182283.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.385236978530884,
|
|
"epoch": 0.6364073006724303,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004967035500520962,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.19182001501321794,
|
|
"num_tokens": 15193917.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.558006954193115,
|
|
"epoch": 0.6368876080691642,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004966977004355421,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.17987558096647263,
|
|
"num_tokens": 15205854.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.395387458801269,
|
|
"epoch": 0.6373679154658982,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004966918456718256,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.1915591076016426,
|
|
"num_tokens": 15217884.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.482484340667725,
|
|
"epoch": 0.6378482228626321,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004966859857610828,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.1877623215317726,
|
|
"num_tokens": 15229493.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.452998447418213,
|
|
"epoch": 0.638328530259366,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004966801207034497,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.1853916272521019,
|
|
"num_tokens": 15241402.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.449325704574585,
|
|
"epoch": 0.6388088376560999,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004966742504990624,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.1885385736823082,
|
|
"num_tokens": 15252981.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.447603511810303,
|
|
"epoch": 0.6392891450528339,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004966683751480572,
|
|
"loss": 5.3168,
|
|
"mean_token_accuracy": 0.19100084751844407,
|
|
"num_tokens": 15264171.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.445246982574463,
|
|
"epoch": 0.6397694524495677,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004966624946505706,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.19131557494401932,
|
|
"num_tokens": 15275595.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.493398523330688,
|
|
"epoch": 0.6402497598463016,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004966566090067391,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.18670759797096254,
|
|
"num_tokens": 15286074.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.495991611480713,
|
|
"epoch": 0.6407300672430355,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004966507182166993,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.18945759087800979,
|
|
"num_tokens": 15296230.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.43350887298584,
|
|
"epoch": 0.6412103746397695,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000496644822280588,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.19255823343992234,
|
|
"num_tokens": 15307428.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.538673782348633,
|
|
"epoch": 0.6416906820365034,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000496638921198542,
|
|
"loss": 5.4314,
|
|
"mean_token_accuracy": 0.1818797394633293,
|
|
"num_tokens": 15318796.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.455525970458984,
|
|
"epoch": 0.6421709894332372,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004966330149706984,
|
|
"loss": 5.3376,
|
|
"mean_token_accuracy": 0.1922453224658966,
|
|
"num_tokens": 15330914.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.414509391784668,
|
|
"epoch": 0.6426512968299711,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004966271035971944,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.1837183192372322,
|
|
"num_tokens": 15341756.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.507179832458496,
|
|
"epoch": 0.6431316042267051,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004966211870781671,
|
|
"loss": 5.4075,
|
|
"mean_token_accuracy": 0.1858164593577385,
|
|
"num_tokens": 15353217.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.483891153335572,
|
|
"epoch": 0.643611911623439,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000496615265413754,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.18673000931739808,
|
|
"num_tokens": 15363813.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.443918371200562,
|
|
"epoch": 0.6440922190201729,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004966093386040923,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.1890939086675644,
|
|
"num_tokens": 15375223.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.406134843826294,
|
|
"epoch": 0.6445725264169068,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00049660340664932,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.19134920239448547,
|
|
"num_tokens": 15385523.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.488214349746704,
|
|
"epoch": 0.6450528338136408,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004965974695495746,
|
|
"loss": 5.384,
|
|
"mean_token_accuracy": 0.18182752281427383,
|
|
"num_tokens": 15397262.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.371902704238892,
|
|
"epoch": 0.6455331412103746,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004965915273049938,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.18797685503959655,
|
|
"num_tokens": 15409043.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.409085893630982,
|
|
"epoch": 0.6460134486071085,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004965855799157158,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.18886479139328002,
|
|
"num_tokens": 15420859.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.514894485473633,
|
|
"epoch": 0.6464937560038425,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004965796273818787,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.17818849682807922,
|
|
"num_tokens": 15433650.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.423994684219361,
|
|
"epoch": 0.6469740634005764,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004965736697036206,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.18954784125089646,
|
|
"num_tokens": 15445158.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.484338188171387,
|
|
"epoch": 0.6474543707973103,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004965677068810798,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.18143113404512407,
|
|
"num_tokens": 15456974.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.490060424804687,
|
|
"epoch": 0.6479346781940442,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004965617389143947,
|
|
"loss": 5.3692,
|
|
"mean_token_accuracy": 0.18711719065904617,
|
|
"num_tokens": 15467395.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.448015785217285,
|
|
"epoch": 0.6484149855907781,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000496555765803704,
|
|
"loss": 5.3736,
|
|
"mean_token_accuracy": 0.18850173205137252,
|
|
"num_tokens": 15479396.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.451170492172241,
|
|
"epoch": 0.648895292987512,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004965497875491462,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.1919165775179863,
|
|
"num_tokens": 15490992.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.570749807357788,
|
|
"epoch": 0.6493756003842459,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004965438041508604,
|
|
"loss": 5.3952,
|
|
"mean_token_accuracy": 0.17724586129188538,
|
|
"num_tokens": 15502413.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.414008474349975,
|
|
"epoch": 0.6498559077809798,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004965378156089851,
|
|
"loss": 5.3419,
|
|
"mean_token_accuracy": 0.183566053211689,
|
|
"num_tokens": 15512588.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.435138797760009,
|
|
"epoch": 0.6503362151777138,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004965318219236597,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.18619257360696792,
|
|
"num_tokens": 15523252.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.384022665023804,
|
|
"epoch": 0.6508165225744477,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004965258230950232,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.18608304411172866,
|
|
"num_tokens": 15534975.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.387798500061035,
|
|
"epoch": 0.6512968299711815,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004965198191232148,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.19524292051792144,
|
|
"num_tokens": 15545709.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.478466558456421,
|
|
"epoch": 0.6517771373679154,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000496513810008374,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.18920085579156876,
|
|
"num_tokens": 15557270.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.536807107925415,
|
|
"epoch": 0.6522574447646494,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004965077957506403,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.18810620605945588,
|
|
"num_tokens": 15569156.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.38745265007019,
|
|
"epoch": 0.6527377521613833,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004965017763501533,
|
|
"loss": 5.286,
|
|
"mean_token_accuracy": 0.18906647861003875,
|
|
"num_tokens": 15579270.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.348081445693969,
|
|
"epoch": 0.6532180595581172,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004964957518070529,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.19496051222085953,
|
|
"num_tokens": 15589912.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.433227682113648,
|
|
"epoch": 0.6536983669548511,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004964897221214788,
|
|
"loss": 5.362,
|
|
"mean_token_accuracy": 0.1896489828824997,
|
|
"num_tokens": 15601088.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.523972225189209,
|
|
"epoch": 0.654178674351585,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000496483687293571,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.18814890831708908,
|
|
"num_tokens": 15612520.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.406736421585083,
|
|
"epoch": 0.6546589817483189,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004964776473234696,
|
|
"loss": 5.2983,
|
|
"mean_token_accuracy": 0.197884202003479,
|
|
"num_tokens": 15623991.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.282617855072021,
|
|
"epoch": 0.6551392891450528,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000496471602211315,
|
|
"loss": 5.2159,
|
|
"mean_token_accuracy": 0.1966500237584114,
|
|
"num_tokens": 15635389.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.410062265396118,
|
|
"epoch": 0.6556195965417867,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004964655519572475,
|
|
"loss": 5.3329,
|
|
"mean_token_accuracy": 0.18896345645189286,
|
|
"num_tokens": 15646427.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.374318599700928,
|
|
"epoch": 0.6560999039385207,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004964594965614072,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.18793339431285858,
|
|
"num_tokens": 15657518.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.4491723537445065,
|
|
"epoch": 0.6565802113352546,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004964534360239353,
|
|
"loss": 5.3444,
|
|
"mean_token_accuracy": 0.18370084911584855,
|
|
"num_tokens": 15669775.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.463488531112671,
|
|
"epoch": 0.6570605187319885,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.000496447370344972,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.1814860925078392,
|
|
"num_tokens": 15682566.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.424590682983398,
|
|
"epoch": 0.6575408261287223,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004964412995246584,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.19295517802238465,
|
|
"num_tokens": 15693168.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.4528725147247314,
|
|
"epoch": 0.6580211335254563,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004964352235631354,
|
|
"loss": 5.3364,
|
|
"mean_token_accuracy": 0.190795373916626,
|
|
"num_tokens": 15703879.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.538533544540405,
|
|
"epoch": 0.6585014409221902,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000496429142460544,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.18669615387916566,
|
|
"num_tokens": 15716015.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.5108051776885985,
|
|
"epoch": 0.6589817483189241,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004964230562170254,
|
|
"loss": 5.3762,
|
|
"mean_token_accuracy": 0.1886669784784317,
|
|
"num_tokens": 15728254.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.410511684417725,
|
|
"epoch": 0.659462055715658,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004964169648327209,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.18697842955589294,
|
|
"num_tokens": 15738778.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.505636072158813,
|
|
"epoch": 0.659942363112392,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000496410868307772,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.1894264042377472,
|
|
"num_tokens": 15750305.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.546743631362915,
|
|
"epoch": 0.6604226705091258,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004964047666423203,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.18701291531324388,
|
|
"num_tokens": 15761303.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.389510774612427,
|
|
"epoch": 0.6609029779058597,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004963986598365072,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.19831403940916062,
|
|
"num_tokens": 15773095.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.481245470046997,
|
|
"epoch": 0.6613832853025937,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004963925478904746,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.18844132721424103,
|
|
"num_tokens": 15784405.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.382522535324097,
|
|
"epoch": 0.6618635926993276,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004963864308043645,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.18706224411725997,
|
|
"num_tokens": 15795178.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.37746033668518,
|
|
"epoch": 0.6623439000960615,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004963803085783189,
|
|
"loss": 5.2998,
|
|
"mean_token_accuracy": 0.19224480241537095,
|
|
"num_tokens": 15806205.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.438063526153565,
|
|
"epoch": 0.6628242074927954,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004963741812124799,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.1959727570414543,
|
|
"num_tokens": 15817474.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.37660846710205,
|
|
"epoch": 0.6633045148895294,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004963680487069898,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.18174040615558623,
|
|
"num_tokens": 15829728.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.4362406730651855,
|
|
"epoch": 0.6637848222862632,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004963619110619908,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.18489634096622468,
|
|
"num_tokens": 15840082.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.4697741031646725,
|
|
"epoch": 0.6642651296829971,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004963557682776256,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.18899585157632828,
|
|
"num_tokens": 15851450.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.500568294525147,
|
|
"epoch": 0.664745437079731,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004963496203540368,
|
|
"loss": 5.4574,
|
|
"mean_token_accuracy": 0.18260498195886612,
|
|
"num_tokens": 15864168.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.524448299407959,
|
|
"epoch": 0.665225744476465,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004963434672913671,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.1858983799815178,
|
|
"num_tokens": 15875634.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.543059635162353,
|
|
"epoch": 0.6657060518731989,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004963373090897592,
|
|
"loss": 5.4231,
|
|
"mean_token_accuracy": 0.18313183039426803,
|
|
"num_tokens": 15888411.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.488481140136718,
|
|
"epoch": 0.6661863592699327,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004963311457493563,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.18110776841640472,
|
|
"num_tokens": 15901084.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.5705633640289305,
|
|
"epoch": 0.6666666666666666,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004963249772703015,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.18582073003053665,
|
|
"num_tokens": 15912061.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.4733664989471436,
|
|
"epoch": 0.6671469740634006,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004963188036527378,
|
|
"loss": 5.4671,
|
|
"mean_token_accuracy": 0.1836829200387001,
|
|
"num_tokens": 15925439.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.360389137268067,
|
|
"epoch": 0.6676272814601345,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004963126248968087,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.19691102355718612,
|
|
"num_tokens": 15937762.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.33357982635498,
|
|
"epoch": 0.6681075888568684,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004963064410026577,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.19435681402683258,
|
|
"num_tokens": 15948656.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.52286467552185,
|
|
"epoch": 0.6685878962536023,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004963002519704281,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.1827905774116516,
|
|
"num_tokens": 15960376.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.465535402297974,
|
|
"epoch": 0.6690682036503363,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000496294057800264,
|
|
"loss": 5.3464,
|
|
"mean_token_accuracy": 0.18602777272462845,
|
|
"num_tokens": 15971913.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.410175418853759,
|
|
"epoch": 0.6695485110470701,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004962878584923089,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.1800703749060631,
|
|
"num_tokens": 15984775.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.460405778884888,
|
|
"epoch": 0.670028818443804,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004962816540467068,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.18129705935716628,
|
|
"num_tokens": 15996717.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.5016676902771,
|
|
"epoch": 0.6705091258405379,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004962754444636017,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.19334876537322998,
|
|
"num_tokens": 16007964.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.406117868423462,
|
|
"epoch": 0.6709894332372719,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000496269229743138,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.1841004103422165,
|
|
"num_tokens": 16019185.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.412761878967285,
|
|
"epoch": 0.6714697406340058,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004962630098854597,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.18938947319984437,
|
|
"num_tokens": 16029983.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.448397588729859,
|
|
"epoch": 0.6719500480307397,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004962567848907113,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.18739537000656128,
|
|
"num_tokens": 16040574.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.523692989349366,
|
|
"epoch": 0.6724303554274735,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004962505547590374,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.18181353956460952,
|
|
"num_tokens": 16052037.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.481429386138916,
|
|
"epoch": 0.6729106628242075,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004962443194905826,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.1863175079226494,
|
|
"num_tokens": 16063413.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.405903291702271,
|
|
"epoch": 0.6733909702209414,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004962380790854916,
|
|
"loss": 5.2789,
|
|
"mean_token_accuracy": 0.18917119055986403,
|
|
"num_tokens": 16074373.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.463232088088989,
|
|
"epoch": 0.6738712776176753,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004962318335439094,
|
|
"loss": 5.4372,
|
|
"mean_token_accuracy": 0.1830749422311783,
|
|
"num_tokens": 16086575.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.503147411346435,
|
|
"epoch": 0.6743515850144092,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962255828659809,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.18638003915548323,
|
|
"num_tokens": 16098529.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.384181547164917,
|
|
"epoch": 0.6748318924111432,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004962193270518513,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.1892055630683899,
|
|
"num_tokens": 16110085.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.380576133728027,
|
|
"epoch": 0.675312199807877,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004962130661016659,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.19332100152969361,
|
|
"num_tokens": 16120249.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.5124317646026615,
|
|
"epoch": 0.6757925072046109,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004962068000155699,
|
|
"loss": 5.5046,
|
|
"mean_token_accuracy": 0.17785520255565643,
|
|
"num_tokens": 16132645.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.515433073043823,
|
|
"epoch": 0.6762728146013448,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004962005287937088,
|
|
"loss": 5.3644,
|
|
"mean_token_accuracy": 0.19239817708730697,
|
|
"num_tokens": 16143808.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.365938329696656,
|
|
"epoch": 0.6767531219980788,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004961942524362283,
|
|
"loss": 5.3567,
|
|
"mean_token_accuracy": 0.19059740602970124,
|
|
"num_tokens": 16154309.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.418550062179565,
|
|
"epoch": 0.6772334293948127,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004961879709432741,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.18868623673915863,
|
|
"num_tokens": 16164654.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.52740478515625,
|
|
"epoch": 0.6777137367915466,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000496181684314992,
|
|
"loss": 5.3663,
|
|
"mean_token_accuracy": 0.18792993426322938,
|
|
"num_tokens": 16177837.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.464639711380005,
|
|
"epoch": 0.6781940441882806,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004961753925515279,
|
|
"loss": 5.2619,
|
|
"mean_token_accuracy": 0.19379691779613495,
|
|
"num_tokens": 16189073.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.503693580627441,
|
|
"epoch": 0.6786743515850144,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000496169095653028,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.18417260944843292,
|
|
"num_tokens": 16200371.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.441987180709839,
|
|
"epoch": 0.6791546589817483,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004961627936196384,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.19362588375806808,
|
|
"num_tokens": 16210526.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.3984198570251465,
|
|
"epoch": 0.6796349663784822,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004961564864515055,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.19256835877895356,
|
|
"num_tokens": 16221687.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.368382549285888,
|
|
"epoch": 0.6801152737752162,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004961501741487757,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.2003920391201973,
|
|
"num_tokens": 16233828.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.399231243133545,
|
|
"epoch": 0.6805955811719501,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004961438567115955,
|
|
"loss": 5.208,
|
|
"mean_token_accuracy": 0.2008877530694008,
|
|
"num_tokens": 16243900.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.375023412704468,
|
|
"epoch": 0.681075888568684,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004961375341401116,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.1934341922402382,
|
|
"num_tokens": 16256347.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.393912887573242,
|
|
"epoch": 0.6815561959654178,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004961312064344708,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.19255869686603547,
|
|
"num_tokens": 16267743.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.337748241424561,
|
|
"epoch": 0.6820365033621518,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00049612487359482,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.19605728834867478,
|
|
"num_tokens": 16278280.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.369137763977051,
|
|
"epoch": 0.6825168107588857,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004961185356213062,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.19587764739990235,
|
|
"num_tokens": 16288568.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.403664684295654,
|
|
"epoch": 0.6829971181556196,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004961121925140767,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.19065249413251878,
|
|
"num_tokens": 16300730.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.410425090789795,
|
|
"epoch": 0.6834774255523535,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004961058442732786,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.18698061108589173,
|
|
"num_tokens": 16311789.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.42126579284668,
|
|
"epoch": 0.6839577329490875,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004960994908990594,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.18519164621829987,
|
|
"num_tokens": 16324439.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.550486707687378,
|
|
"epoch": 0.6844380403458213,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004960931323915665,
|
|
"loss": 5.4466,
|
|
"mean_token_accuracy": 0.19609829783439636,
|
|
"num_tokens": 16335344.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.415621185302735,
|
|
"epoch": 0.6849183477425552,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004960867687509475,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.19076128602027892,
|
|
"num_tokens": 16349018.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.415049839019775,
|
|
"epoch": 0.6853986551392891,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004960803999773504,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.18157496601343154,
|
|
"num_tokens": 16360137.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.515894556045533,
|
|
"epoch": 0.6858789625360231,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004960740260709228,
|
|
"loss": 5.3745,
|
|
"mean_token_accuracy": 0.18794575333595276,
|
|
"num_tokens": 16372277.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.483719968795777,
|
|
"epoch": 0.686359269932757,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004960676470318128,
|
|
"loss": 5.3701,
|
|
"mean_token_accuracy": 0.1854420781135559,
|
|
"num_tokens": 16383440.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.447765493392945,
|
|
"epoch": 0.6868395773294909,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004960612628601683,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.18878995180130004,
|
|
"num_tokens": 16394330.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.374434518814087,
|
|
"epoch": 0.6873198847262247,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004960548735561379,
|
|
"loss": 5.2555,
|
|
"mean_token_accuracy": 0.19584026634693147,
|
|
"num_tokens": 16405734.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.383916187286377,
|
|
"epoch": 0.6878001921229587,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004960484791198697,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.19005635231733323,
|
|
"num_tokens": 16416025.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.404208564758301,
|
|
"epoch": 0.6882804995196926,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004960420795515121,
|
|
"loss": 5.2864,
|
|
"mean_token_accuracy": 0.18874610513448714,
|
|
"num_tokens": 16427416.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.409447383880615,
|
|
"epoch": 0.6887608069164265,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004960356748512138,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.19459613412618637,
|
|
"num_tokens": 16438073.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.352252960205078,
|
|
"epoch": 0.6892411143131604,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004960292650191236,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.19079190939664842,
|
|
"num_tokens": 16449994.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.373232984542847,
|
|
"epoch": 0.6897214217098944,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004960228500553899,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.20400338619947433,
|
|
"num_tokens": 16460355.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.497406816482544,
|
|
"epoch": 0.6902017291066282,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004960164299601623,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.18565243631601333,
|
|
"num_tokens": 16472274.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.508424472808838,
|
|
"epoch": 0.6906820365033621,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004960100047335892,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.18871129304170609,
|
|
"num_tokens": 16482959.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.395152616500854,
|
|
"epoch": 0.691162343900096,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004960035743758202,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.186780945956707,
|
|
"num_tokens": 16494533.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.3192685604095455,
|
|
"epoch": 0.69164265129683,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004959971388870044,
|
|
"loss": 5.2747,
|
|
"mean_token_accuracy": 0.19172853976488113,
|
|
"num_tokens": 16506124.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.409257411956787,
|
|
"epoch": 0.6921229586935639,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004959906982672912,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.18570771366357802,
|
|
"num_tokens": 16517867.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.377297019958496,
|
|
"epoch": 0.6926032660902978,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004959842525168302,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.1961120381951332,
|
|
"num_tokens": 16529075.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.391007947921753,
|
|
"epoch": 0.6930835734870316,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004959778016357712,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.19782263785600662,
|
|
"num_tokens": 16540326.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.398585557937622,
|
|
"epoch": 0.6935638808837656,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004959713456242637,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.18707880675792693,
|
|
"num_tokens": 16551570.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.4765325546264645,
|
|
"epoch": 0.6940441882804995,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004959648844824576,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.18743495345115663,
|
|
"num_tokens": 16562636.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.473107719421387,
|
|
"epoch": 0.6945244956772334,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004959584182105032,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.194345161318779,
|
|
"num_tokens": 16573867.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.38476333618164,
|
|
"epoch": 0.6950048030739674,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004959519468085504,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.2006682425737381,
|
|
"num_tokens": 16584533.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.343054485321045,
|
|
"epoch": 0.6954851104707013,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004959454702767494,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.1895986944437027,
|
|
"num_tokens": 16596562.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.408606100082397,
|
|
"epoch": 0.6959654178674352,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004959389886152507,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.1998280704021454,
|
|
"num_tokens": 16607508.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.421170377731324,
|
|
"epoch": 0.696445725264169,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004959325018242048,
|
|
"loss": 5.3545,
|
|
"mean_token_accuracy": 0.19064907133579254,
|
|
"num_tokens": 16617737.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.50282473564148,
|
|
"epoch": 0.696926032660903,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004959260099037622,
|
|
"loss": 5.3768,
|
|
"mean_token_accuracy": 0.18397812098264693,
|
|
"num_tokens": 16628518.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.4236818790435795,
|
|
"epoch": 0.6974063400576369,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.0004959195128540737,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.18393784612417222,
|
|
"num_tokens": 16639644.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.515799427032471,
|
|
"epoch": 0.6978866474543708,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00049591301067529,
|
|
"loss": 5.4577,
|
|
"mean_token_accuracy": 0.17506887316703795,
|
|
"num_tokens": 16650882.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.54480299949646,
|
|
"epoch": 0.6983669548511047,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004959065033675623,
|
|
"loss": 5.3583,
|
|
"mean_token_accuracy": 0.18431620299816132,
|
|
"num_tokens": 16662464.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.454852342605591,
|
|
"epoch": 0.6988472622478387,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004958999909310414,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.18296234607696532,
|
|
"num_tokens": 16673718.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.398219060897827,
|
|
"epoch": 0.6993275696445725,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004958934733658788,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.1886419177055359,
|
|
"num_tokens": 16684957.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.457288551330566,
|
|
"epoch": 0.6998078770413064,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004958869506722256,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.18857708871364592,
|
|
"num_tokens": 16695782.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.476930618286133,
|
|
"epoch": 0.7002881844380403,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004958804228502332,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.19507861733436585,
|
|
"num_tokens": 16707448.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.356259441375732,
|
|
"epoch": 0.7007684918347743,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004958738899000534,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.19029063284397124,
|
|
"num_tokens": 16718074.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.416971826553345,
|
|
"epoch": 0.7012487992315082,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004958673518218377,
|
|
"loss": 5.3141,
|
|
"mean_token_accuracy": 0.1890144631266594,
|
|
"num_tokens": 16728656.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.4403563976287845,
|
|
"epoch": 0.7017291066282421,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004958608086157379,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.19000608175992967,
|
|
"num_tokens": 16740703.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.431931447982788,
|
|
"epoch": 0.7022094140249759,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000495854260281906,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.19730661660432816,
|
|
"num_tokens": 16753320.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.361083173751831,
|
|
"epoch": 0.7026897214217099,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004958477068204941,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.18938911855220794,
|
|
"num_tokens": 16764889.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.472226142883301,
|
|
"epoch": 0.7031700288184438,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000495841148231654,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.19412004202604294,
|
|
"num_tokens": 16776301.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.4432065963745115,
|
|
"epoch": 0.7036503362151777,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004958345845155383,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.19692272543907166,
|
|
"num_tokens": 16786935.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.374418115615844,
|
|
"epoch": 0.7041306436119116,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004958280156722992,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.19164909273386002,
|
|
"num_tokens": 16799335.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.343346738815308,
|
|
"epoch": 0.7046109510086456,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004958214417020894,
|
|
"loss": 5.268,
|
|
"mean_token_accuracy": 0.189383427798748,
|
|
"num_tokens": 16811376.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.476910018920899,
|
|
"epoch": 0.7050912584053795,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004958148626050614,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.18298167139291763,
|
|
"num_tokens": 16822859.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.429091262817383,
|
|
"epoch": 0.7055715658021133,
|
|
"grad_norm": 5.9375,
|
|
"learning_rate": 0.000495808278381368,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.19157274961471557,
|
|
"num_tokens": 16833831.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.4169148921966555,
|
|
"epoch": 0.7060518731988472,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000495801689031162,
|
|
"loss": 5.3385,
|
|
"mean_token_accuracy": 0.1874571070075035,
|
|
"num_tokens": 16846827.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.422062873840332,
|
|
"epoch": 0.7065321805955812,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004957950945545965,
|
|
"loss": 5.3034,
|
|
"mean_token_accuracy": 0.18981092274188996,
|
|
"num_tokens": 16858166.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.509169101715088,
|
|
"epoch": 0.7070124879923151,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004957884949518246,
|
|
"loss": 5.4395,
|
|
"mean_token_accuracy": 0.17802689522504805,
|
|
"num_tokens": 16870201.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.474486398696899,
|
|
"epoch": 0.707492795389049,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004957818902229992,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.18811087310314178,
|
|
"num_tokens": 16880891.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.464091110229492,
|
|
"epoch": 0.7079731027857828,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004957752803682741,
|
|
"loss": 5.3768,
|
|
"mean_token_accuracy": 0.1848767802119255,
|
|
"num_tokens": 16893498.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.444340562820434,
|
|
"epoch": 0.7084534101825168,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004957686653878024,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.18634562194347382,
|
|
"num_tokens": 16904959.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.537218427658081,
|
|
"epoch": 0.7089337175792507,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000495762045281738,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.18827713876962662,
|
|
"num_tokens": 16916547.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.416225814819336,
|
|
"epoch": 0.7094140249759846,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004957554200502344,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.19104671031236647,
|
|
"num_tokens": 16928580.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.443052768707275,
|
|
"epoch": 0.7098943323727186,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004957487896934454,
|
|
"loss": 5.3453,
|
|
"mean_token_accuracy": 0.18696927279233932,
|
|
"num_tokens": 16941247.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.486386775970459,
|
|
"epoch": 0.7103746397694525,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000495742154211525,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.18901167064905167,
|
|
"num_tokens": 16951119.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.4267778396606445,
|
|
"epoch": 0.7108549471661864,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004957355136046272,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.19096522480249406,
|
|
"num_tokens": 16962608.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.439266681671143,
|
|
"epoch": 0.7113352545629202,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004957288678729064,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.1882279932498932,
|
|
"num_tokens": 16973291.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.566749525070191,
|
|
"epoch": 0.7118155619596542,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004957222170165166,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.18324741423130037,
|
|
"num_tokens": 16984895.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.43397011756897,
|
|
"epoch": 0.7122958693563881,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004957155610356124,
|
|
"loss": 5.3513,
|
|
"mean_token_accuracy": 0.179252927005291,
|
|
"num_tokens": 16997109.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.390065908432007,
|
|
"epoch": 0.712776176753122,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004957088999303481,
|
|
"loss": 5.2973,
|
|
"mean_token_accuracy": 0.18766732066869735,
|
|
"num_tokens": 17008640.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.406141757965088,
|
|
"epoch": 0.7132564841498559,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004957022337008787,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.19368757903575898,
|
|
"num_tokens": 17018924.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.368246364593506,
|
|
"epoch": 0.7137367915465899,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004956955623473587,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.18941244333982468,
|
|
"num_tokens": 17029932.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.4839025974273685,
|
|
"epoch": 0.7142170989433237,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000495688885869943,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.18623648434877396,
|
|
"num_tokens": 17042164.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.502608108520508,
|
|
"epoch": 0.7146974063400576,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004956822042687868,
|
|
"loss": 5.385,
|
|
"mean_token_accuracy": 0.17899369895458223,
|
|
"num_tokens": 17054729.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.404917049407959,
|
|
"epoch": 0.7151777137367915,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004956755175440451,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.20205610245466232,
|
|
"num_tokens": 17066537.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.379066371917725,
|
|
"epoch": 0.7156580211335255,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004956688256958731,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.19262725859880447,
|
|
"num_tokens": 17077787.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.362291383743286,
|
|
"epoch": 0.7161383285302594,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004956621287244262,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.18543240875005723,
|
|
"num_tokens": 17089555.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.539840173721314,
|
|
"epoch": 0.7166186359269933,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004956554266298599,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.19296886026859283,
|
|
"num_tokens": 17099911.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.3922951221466064,
|
|
"epoch": 0.7170989433237271,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004956487194123298,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.1903640568256378,
|
|
"num_tokens": 17110880.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.35172324180603,
|
|
"epoch": 0.7175792507204611,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004956420070719918,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.19411149621009827,
|
|
"num_tokens": 17122272.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.437594842910767,
|
|
"epoch": 0.718059558117195,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004956352896090014,
|
|
"loss": 5.3684,
|
|
"mean_token_accuracy": 0.18836570978164674,
|
|
"num_tokens": 17133995.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.487672805786133,
|
|
"epoch": 0.7185398655139289,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004956285670235147,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.1950314924120903,
|
|
"num_tokens": 17145970.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.489817953109741,
|
|
"epoch": 0.7190201729106628,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004956218393156879,
|
|
"loss": 5.4375,
|
|
"mean_token_accuracy": 0.1796429142355919,
|
|
"num_tokens": 17157747.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.42591962814331,
|
|
"epoch": 0.7195004803073968,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004956151064856772,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.19603702276945115,
|
|
"num_tokens": 17168357.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.454504013061523,
|
|
"epoch": 0.7199807877041307,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004956083685336386,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.20013804435729982,
|
|
"num_tokens": 17179871.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.439360809326172,
|
|
"epoch": 0.7204610951008645,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004956016254597289,
|
|
"loss": 5.2734,
|
|
"mean_token_accuracy": 0.19816163033246995,
|
|
"num_tokens": 17190456.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.367860460281372,
|
|
"epoch": 0.7209414024975984,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004955948772641044,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.1809507429599762,
|
|
"num_tokens": 17201623.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.365807914733887,
|
|
"epoch": 0.7214217098943324,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000495588123946922,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.19150221943855286,
|
|
"num_tokens": 17212891.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.457305765151977,
|
|
"epoch": 0.7219020172910663,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004955813655083384,
|
|
"loss": 5.3218,
|
|
"mean_token_accuracy": 0.1914539560675621,
|
|
"num_tokens": 17223983.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.487482023239136,
|
|
"epoch": 0.7223823246878002,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004955746019485104,
|
|
"loss": 5.3582,
|
|
"mean_token_accuracy": 0.19416608065366744,
|
|
"num_tokens": 17233701.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.415124368667603,
|
|
"epoch": 0.722862632084534,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000495567833267595,
|
|
"loss": 5.3581,
|
|
"mean_token_accuracy": 0.18595242351293564,
|
|
"num_tokens": 17245958.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.490132617950439,
|
|
"epoch": 0.723342939481268,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004955610594657496,
|
|
"loss": 5.3663,
|
|
"mean_token_accuracy": 0.18382639288902283,
|
|
"num_tokens": 17257687.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.53135051727295,
|
|
"epoch": 0.7238232468780019,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004955542805431313,
|
|
"loss": 5.4091,
|
|
"mean_token_accuracy": 0.18521798700094222,
|
|
"num_tokens": 17270247.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.467233085632325,
|
|
"epoch": 0.7243035542747358,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004955474964998976,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.19140195101499557,
|
|
"num_tokens": 17281920.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.510559225082398,
|
|
"epoch": 0.7247838616714697,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004955407073362058,
|
|
"loss": 5.4794,
|
|
"mean_token_accuracy": 0.1766323372721672,
|
|
"num_tokens": 17293602.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.558656120300293,
|
|
"epoch": 0.7252641690682037,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004955339130522136,
|
|
"loss": 5.2844,
|
|
"mean_token_accuracy": 0.18899479508399963,
|
|
"num_tokens": 17304484.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.327901315689087,
|
|
"epoch": 0.7257444764649376,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000495527113648079,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.19256725907325745,
|
|
"num_tokens": 17314953.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.399320936203003,
|
|
"epoch": 0.7262247838616714,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004955203091239596,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.18690313547849655,
|
|
"num_tokens": 17326813.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.534193897247315,
|
|
"epoch": 0.7267050912584054,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004955134994800134,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.18529947698116303,
|
|
"num_tokens": 17337968.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.567023992538452,
|
|
"epoch": 0.7271853986551393,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004955066847163984,
|
|
"loss": 5.3303,
|
|
"mean_token_accuracy": 0.1871946707367897,
|
|
"num_tokens": 17350406.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.40588150024414,
|
|
"epoch": 0.7276657060518732,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004954998648332731,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.19346969872713088,
|
|
"num_tokens": 17361888.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.392457675933838,
|
|
"epoch": 0.7281460134486071,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004954930398307956,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.18660264909267427,
|
|
"num_tokens": 17374047.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.448021173477173,
|
|
"epoch": 0.7286263208453411,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004954862097091245,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.18306700140237808,
|
|
"num_tokens": 17386175.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.450073337554931,
|
|
"epoch": 0.729106628242075,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004954793744684184,
|
|
"loss": 5.3513,
|
|
"mean_token_accuracy": 0.198377825319767,
|
|
"num_tokens": 17398168.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.443664407730102,
|
|
"epoch": 0.7295869356388088,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004954725341088358,
|
|
"loss": 5.238,
|
|
"mean_token_accuracy": 0.19219654202461242,
|
|
"num_tokens": 17408825.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.42207555770874,
|
|
"epoch": 0.7300672430355427,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004954656886305356,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.1905752092599869,
|
|
"num_tokens": 17419813.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.479459142684936,
|
|
"epoch": 0.7305475504322767,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004954588380336768,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.1877987340092659,
|
|
"num_tokens": 17431134.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.370573472976685,
|
|
"epoch": 0.7310278578290106,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004954519823184184,
|
|
"loss": 5.2812,
|
|
"mean_token_accuracy": 0.19331644028425216,
|
|
"num_tokens": 17442614.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.477926921844483,
|
|
"epoch": 0.7315081652257445,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004954451214849196,
|
|
"loss": 5.2861,
|
|
"mean_token_accuracy": 0.193308524787426,
|
|
"num_tokens": 17454615.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.506645917892456,
|
|
"epoch": 0.7319884726224783,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004954382555333397,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.1888895571231842,
|
|
"num_tokens": 17467025.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.364077568054199,
|
|
"epoch": 0.7324687800192123,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000495431384463838,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.1932027593255043,
|
|
"num_tokens": 17477681.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.407464075088501,
|
|
"epoch": 0.7329490874159462,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004954245082765741,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.18895117044448853,
|
|
"num_tokens": 17489814.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.45061731338501,
|
|
"epoch": 0.7334293948126801,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004954176269717077,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.18977221250534057,
|
|
"num_tokens": 17501701.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.446993637084961,
|
|
"epoch": 0.733909702209414,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004954107405493984,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.1934464082121849,
|
|
"num_tokens": 17513585.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.505724191665649,
|
|
"epoch": 0.734390009606148,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004954038490098064,
|
|
"loss": 5.3887,
|
|
"mean_token_accuracy": 0.18925999402999877,
|
|
"num_tokens": 17525557.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.4314882278442385,
|
|
"epoch": 0.7348703170028819,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004953969523530914,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.18967188000679017,
|
|
"num_tokens": 17538312.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.550967025756836,
|
|
"epoch": 0.7353506243996157,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004953900505794136,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.18929269015789033,
|
|
"num_tokens": 17550248.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.4399162292480465,
|
|
"epoch": 0.7358309317963496,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004953831436889332,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.18886225521564484,
|
|
"num_tokens": 17560624.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.439819860458374,
|
|
"epoch": 0.7363112391930836,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004953762316818106,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.19017945230007172,
|
|
"num_tokens": 17572439.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.527974700927734,
|
|
"epoch": 0.7367915465898175,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004953693145582064,
|
|
"loss": 5.3694,
|
|
"mean_token_accuracy": 0.18149060010910034,
|
|
"num_tokens": 17583120.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.370331287384033,
|
|
"epoch": 0.7372718539865514,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000495362392318281,
|
|
"loss": 5.1867,
|
|
"mean_token_accuracy": 0.1951387733221054,
|
|
"num_tokens": 17593677.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.358538103103638,
|
|
"epoch": 0.7377521613832853,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004953554649621951,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.18531646132469176,
|
|
"num_tokens": 17605180.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.483230400085449,
|
|
"epoch": 0.7382324687800192,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004953485324901098,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.1921133205294609,
|
|
"num_tokens": 17617459.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.497286987304688,
|
|
"epoch": 0.7387127761767531,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004953415949021857,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.18997854739427567,
|
|
"num_tokens": 17628024.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.398489141464234,
|
|
"epoch": 0.739193083573487,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004953346521985843,
|
|
"loss": 5.3289,
|
|
"mean_token_accuracy": 0.1931114211678505,
|
|
"num_tokens": 17639833.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.438334798812866,
|
|
"epoch": 0.7396733909702209,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004953277043794663,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.1844191625714302,
|
|
"num_tokens": 17651057.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.445753192901611,
|
|
"epoch": 0.7401536983669549,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004953207514449933,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.19395927637815474,
|
|
"num_tokens": 17662288.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.523833227157593,
|
|
"epoch": 0.7406340057636888,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004953137933953267,
|
|
"loss": 5.2949,
|
|
"mean_token_accuracy": 0.18855485022068025,
|
|
"num_tokens": 17673885.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.407365131378174,
|
|
"epoch": 0.7411143131604226,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000495306830230628,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.19278490245342256,
|
|
"num_tokens": 17685030.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.420984506607056,
|
|
"epoch": 0.7415946205571565,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004952998619510589,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.19666706174612045,
|
|
"num_tokens": 17696624.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.420668029785157,
|
|
"epoch": 0.7420749279538905,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004952928885567811,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.19152073562145233,
|
|
"num_tokens": 17707386.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.532713127136231,
|
|
"epoch": 0.7425552353506244,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004952859100479566,
|
|
"loss": 5.5064,
|
|
"mean_token_accuracy": 0.18392106294631957,
|
|
"num_tokens": 17718605.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.473436069488526,
|
|
"epoch": 0.7430355427473583,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004952789264247474,
|
|
"loss": 5.308,
|
|
"mean_token_accuracy": 0.19038950204849242,
|
|
"num_tokens": 17730275.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.550911569595337,
|
|
"epoch": 0.7435158501440923,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004952719376873156,
|
|
"loss": 5.4044,
|
|
"mean_token_accuracy": 0.18317733705043793,
|
|
"num_tokens": 17741390.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.44356632232666,
|
|
"epoch": 0.7439961575408262,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004952649438358234,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.19425007700920105,
|
|
"num_tokens": 17752354.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.42779393196106,
|
|
"epoch": 0.74447646493756,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004952579448704334,
|
|
"loss": 5.2714,
|
|
"mean_token_accuracy": 0.18687344789505006,
|
|
"num_tokens": 17762839.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.5058518409729,
|
|
"epoch": 0.7449567723342939,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000495250940791308,
|
|
"loss": 5.3788,
|
|
"mean_token_accuracy": 0.18239201605319977,
|
|
"num_tokens": 17775800.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.482727479934693,
|
|
"epoch": 0.7454370797310279,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004952439315986096,
|
|
"loss": 5.3165,
|
|
"mean_token_accuracy": 0.18906346410512925,
|
|
"num_tokens": 17787804.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.489138507843018,
|
|
"epoch": 0.7459173871277618,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004952369172925012,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.1915716513991356,
|
|
"num_tokens": 17800291.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.40567946434021,
|
|
"epoch": 0.7463976945244957,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004952298978731454,
|
|
"loss": 5.2758,
|
|
"mean_token_accuracy": 0.19481030255556106,
|
|
"num_tokens": 17811548.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.4649085521698,
|
|
"epoch": 0.7468780019212296,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004952228733407055,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.19582658410072326,
|
|
"num_tokens": 17822589.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.3924812316894535,
|
|
"epoch": 0.7473583093179635,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004952158436953444,
|
|
"loss": 5.2422,
|
|
"mean_token_accuracy": 0.19220336973667146,
|
|
"num_tokens": 17834203.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.433532476425171,
|
|
"epoch": 0.7478386167146974,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004952088089372252,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.18726081848144532,
|
|
"num_tokens": 17846238.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.464939117431641,
|
|
"epoch": 0.7483189241114313,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004952017690665114,
|
|
"loss": 5.2449,
|
|
"mean_token_accuracy": 0.19074853509664536,
|
|
"num_tokens": 17857640.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.416226243972778,
|
|
"epoch": 0.7487992315081652,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004951947240833664,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.19461538940668105,
|
|
"num_tokens": 17868755.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.402211904525757,
|
|
"epoch": 0.7492795389048992,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004951876739879537,
|
|
"loss": 5.3358,
|
|
"mean_token_accuracy": 0.1874142438173294,
|
|
"num_tokens": 17881078.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.390611696243286,
|
|
"epoch": 0.7497598463016331,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004951806187804371,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.1924992859363556,
|
|
"num_tokens": 17893888.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.476023721694946,
|
|
"epoch": 0.7502401536983669,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004951735584609804,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.18642262518405914,
|
|
"num_tokens": 17904443.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.464403772354126,
|
|
"epoch": 0.7507204610951008,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004951664930297474,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.19122353941202164,
|
|
"num_tokens": 17918090.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.365573883056641,
|
|
"epoch": 0.7512007684918348,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000495159422486902,
|
|
"loss": 5.2867,
|
|
"mean_token_accuracy": 0.193510065972805,
|
|
"num_tokens": 17929233.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.456695604324341,
|
|
"epoch": 0.7516810758885687,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004951523468326088,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.18878775835037231,
|
|
"num_tokens": 17940580.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.539548444747925,
|
|
"epoch": 0.7521613832853026,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004951452660670317,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.18070729821920395,
|
|
"num_tokens": 17953993.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.447207450866699,
|
|
"epoch": 0.7526416906820365,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004951381801903352,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.18752162605524064,
|
|
"num_tokens": 17966033.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.34521975517273,
|
|
"epoch": 0.7531219980787704,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004951310892026839,
|
|
"loss": 5.2088,
|
|
"mean_token_accuracy": 0.19722351878881456,
|
|
"num_tokens": 17977943.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.455227899551391,
|
|
"epoch": 0.7536023054755043,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004951239931042424,
|
|
"loss": 5.286,
|
|
"mean_token_accuracy": 0.1925072118639946,
|
|
"num_tokens": 17990135.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.415983009338379,
|
|
"epoch": 0.7540826128722382,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004951168918951753,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.19400670379400253,
|
|
"num_tokens": 18002126.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.325727224349976,
|
|
"epoch": 0.7545629202689721,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004951097855756476,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.19335832595825195,
|
|
"num_tokens": 18013147.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.4841619491577145,
|
|
"epoch": 0.7550432276657061,
|
|
"grad_norm": 5.5625,
|
|
"learning_rate": 0.0004951026741458243,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.19127957075834273,
|
|
"num_tokens": 18025146.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.43231167793274,
|
|
"epoch": 0.75552353506244,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004950955576058705,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.19233157187700273,
|
|
"num_tokens": 18036412.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.436884164810181,
|
|
"epoch": 0.7560038424591738,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004950884359559513,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.19388701468706132,
|
|
"num_tokens": 18048041.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.445731449127197,
|
|
"epoch": 0.7564841498559077,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004950813091962324,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.18321080952882768,
|
|
"num_tokens": 18060163.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.516049766540528,
|
|
"epoch": 0.7569644572526417,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004950741773268788,
|
|
"loss": 5.3257,
|
|
"mean_token_accuracy": 0.18516390025615692,
|
|
"num_tokens": 18071628.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.327418518066406,
|
|
"epoch": 0.7574447646493756,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004950670403480562,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.19050661027431487,
|
|
"num_tokens": 18082979.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.406103658676147,
|
|
"epoch": 0.7579250720461095,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004950598982599306,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.19290697425603867,
|
|
"num_tokens": 18093889.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.4393257141113285,
|
|
"epoch": 0.7584053794428435,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004950527510626675,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.1900480017066002,
|
|
"num_tokens": 18105559.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.467070627212524,
|
|
"epoch": 0.7588856868395774,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004950455987564329,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.18369181007146834,
|
|
"num_tokens": 18116316.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.500452136993408,
|
|
"epoch": 0.7593659942363112,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004950384413413931,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.19034132808446885,
|
|
"num_tokens": 18126851.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.52796893119812,
|
|
"epoch": 0.7598463016330451,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004950312788177139,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.18037617802619935,
|
|
"num_tokens": 18139571.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.554152488708496,
|
|
"epoch": 0.7603266090297791,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004950241111855618,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.1849069267511368,
|
|
"num_tokens": 18150680.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.460306978225708,
|
|
"epoch": 0.760806916426513,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004950169384451031,
|
|
"loss": 5.3156,
|
|
"mean_token_accuracy": 0.19223465919494628,
|
|
"num_tokens": 18161911.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.393625068664551,
|
|
"epoch": 0.7612872238232469,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004950097605965045,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.19338213801383972,
|
|
"num_tokens": 18172714.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.445776176452637,
|
|
"epoch": 0.7617675312199808,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004950025776399326,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.19192568808794022,
|
|
"num_tokens": 18184250.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.52476806640625,
|
|
"epoch": 0.7622478386167147,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.000494995389575554,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.18279454708099366,
|
|
"num_tokens": 18195299.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.535164833068848,
|
|
"epoch": 0.7627281460134486,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004949881964035357,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.1827154889702797,
|
|
"num_tokens": 18206863.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.549646806716919,
|
|
"epoch": 0.7632084534101825,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004949809981240448,
|
|
"loss": 5.4051,
|
|
"mean_token_accuracy": 0.18091683685779572,
|
|
"num_tokens": 18219643.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.407581233978272,
|
|
"epoch": 0.7636887608069164,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004949737947372483,
|
|
"loss": 5.2511,
|
|
"mean_token_accuracy": 0.1951652243733406,
|
|
"num_tokens": 18230461.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.4360105991363525,
|
|
"epoch": 0.7641690682036504,
|
|
"grad_norm": 5.4375,
|
|
"learning_rate": 0.0004949665862433134,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.1828230619430542,
|
|
"num_tokens": 18243768.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.452644205093383,
|
|
"epoch": 0.7646493756003843,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004949593726424077,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.18666255176067353,
|
|
"num_tokens": 18255322.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.467182683944702,
|
|
"epoch": 0.7651296829971181,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004949521539346985,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.1967984065413475,
|
|
"num_tokens": 18267262.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.470462226867676,
|
|
"epoch": 0.765609990393852,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004949449301203533,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.1920719027519226,
|
|
"num_tokens": 18277332.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.4518725872039795,
|
|
"epoch": 0.766090297790586,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004949377011995399,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.19250051379203797,
|
|
"num_tokens": 18289547.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.414010667800904,
|
|
"epoch": 0.7665706051873199,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004949304671724263,
|
|
"loss": 5.266,
|
|
"mean_token_accuracy": 0.19358395636081696,
|
|
"num_tokens": 18302097.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.486215448379516,
|
|
"epoch": 0.7670509125840538,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004949232280391802,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.1902744859457016,
|
|
"num_tokens": 18314151.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.435534381866455,
|
|
"epoch": 0.7675312199807877,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004949159837999698,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.18555608987808228,
|
|
"num_tokens": 18326085.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.445125961303711,
|
|
"epoch": 0.7680115273775217,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004949087344549633,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.18601425886154174,
|
|
"num_tokens": 18338158.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.422890758514404,
|
|
"epoch": 0.7684918347742555,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000494901480004329,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.19271600246429443,
|
|
"num_tokens": 18349418.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.469140529632568,
|
|
"epoch": 0.7689721421709894,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004948942204482351,
|
|
"loss": 5.3091,
|
|
"mean_token_accuracy": 0.18944568783044816,
|
|
"num_tokens": 18361964.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.416598510742188,
|
|
"epoch": 0.7694524495677233,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004948869557868506,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.19918626695871353,
|
|
"num_tokens": 18373108.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.304902362823486,
|
|
"epoch": 0.7699327569644573,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004948796860203439,
|
|
"loss": 5.251,
|
|
"mean_token_accuracy": 0.19057904034852982,
|
|
"num_tokens": 18385310.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.489623117446899,
|
|
"epoch": 0.7704130643611912,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004948724111488838,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.18425999730825424,
|
|
"num_tokens": 18396132.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.638503932952881,
|
|
"epoch": 0.770893371757925,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004948651311726391,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.18200746327638626,
|
|
"num_tokens": 18409930.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.526231002807617,
|
|
"epoch": 0.7713736791546589,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004948578460917789,
|
|
"loss": 5.4011,
|
|
"mean_token_accuracy": 0.18231112957000734,
|
|
"num_tokens": 18421204.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.448295974731446,
|
|
"epoch": 0.7718539865513929,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004948505559064725,
|
|
"loss": 5.2857,
|
|
"mean_token_accuracy": 0.1940631464123726,
|
|
"num_tokens": 18433194.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.403420782089233,
|
|
"epoch": 0.7723342939481268,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004948432606168889,
|
|
"loss": 5.2619,
|
|
"mean_token_accuracy": 0.1919160380959511,
|
|
"num_tokens": 18445282.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.429835987091065,
|
|
"epoch": 0.7728146013448607,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004948359602231976,
|
|
"loss": 5.3132,
|
|
"mean_token_accuracy": 0.1893114924430847,
|
|
"num_tokens": 18456264.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.383267116546631,
|
|
"epoch": 0.7732949087415946,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004948286547255681,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.19209939986467361,
|
|
"num_tokens": 18467573.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.428293609619141,
|
|
"epoch": 0.7737752161383286,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00049482134412417,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.19604541212320328,
|
|
"num_tokens": 18478333.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.403275203704834,
|
|
"epoch": 0.7742555235350624,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000494814028419173,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.19981560111045837,
|
|
"num_tokens": 18489106.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.460156059265136,
|
|
"epoch": 0.7747358309317963,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000494806707610747,
|
|
"loss": 5.3532,
|
|
"mean_token_accuracy": 0.18627351224422456,
|
|
"num_tokens": 18500090.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.509449052810669,
|
|
"epoch": 0.7752161383285303,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000494799381699062,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.1949794426560402,
|
|
"num_tokens": 18510305.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.469287300109864,
|
|
"epoch": 0.7756964457252642,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004947920506842879,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.18977378606796264,
|
|
"num_tokens": 18523048.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.394409322738648,
|
|
"epoch": 0.7761767531219981,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004947847145665951,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.1947533071041107,
|
|
"num_tokens": 18534145.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.435162734985352,
|
|
"epoch": 0.776657060518732,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004947773733461539,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.1919109880924225,
|
|
"num_tokens": 18545045.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.486386394500732,
|
|
"epoch": 0.777137367915466,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004947700270231347,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.19513138830661775,
|
|
"num_tokens": 18557531.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.393535518646241,
|
|
"epoch": 0.7776176753121998,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004947626755977079,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.1869373917579651,
|
|
"num_tokens": 18569127.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.462738466262818,
|
|
"epoch": 0.7780979827089337,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004947553190700444,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.1943922221660614,
|
|
"num_tokens": 18580606.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.568971490859985,
|
|
"epoch": 0.7785782901056676,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000494747957440315,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.18097027838230134,
|
|
"num_tokens": 18592330.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.598490762710571,
|
|
"epoch": 0.7790585975024016,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004947405907086905,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.18295304626226425,
|
|
"num_tokens": 18604721.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.4386146068573,
|
|
"epoch": 0.7795389048991355,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004947332188753419,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.19227023422718048,
|
|
"num_tokens": 18616814.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.459168720245361,
|
|
"epoch": 0.7800192122958693,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004947258419404405,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.19001483023166657,
|
|
"num_tokens": 18628224.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.446760177612305,
|
|
"epoch": 0.7804995196926032,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004947184599041576,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.18481643348932267,
|
|
"num_tokens": 18639777.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.426401996612549,
|
|
"epoch": 0.7809798270893372,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004947110727666644,
|
|
"loss": 5.2776,
|
|
"mean_token_accuracy": 0.19305975288152694,
|
|
"num_tokens": 18651044.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.424715375900268,
|
|
"epoch": 0.7814601344860711,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004947036805281325,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.1926332399249077,
|
|
"num_tokens": 18663142.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.5354392528533936,
|
|
"epoch": 0.781940441882805,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004946962831887336,
|
|
"loss": 5.3958,
|
|
"mean_token_accuracy": 0.18595205545425414,
|
|
"num_tokens": 18674079.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.519014644622803,
|
|
"epoch": 0.7824207492795389,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004946888807486393,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.1853330746293068,
|
|
"num_tokens": 18685744.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.380872821807861,
|
|
"epoch": 0.7829010566762729,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004946814732080214,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.18800440579652786,
|
|
"num_tokens": 18697049.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.378533887863159,
|
|
"epoch": 0.7833813640730067,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004946740605670523,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.19208532720804214,
|
|
"num_tokens": 18708765.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.414113092422485,
|
|
"epoch": 0.7838616714697406,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004946666428259037,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.1927352786064148,
|
|
"num_tokens": 18719819.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.549100017547607,
|
|
"epoch": 0.7843419788664745,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004946592199847478,
|
|
"loss": 5.3492,
|
|
"mean_token_accuracy": 0.1841299206018448,
|
|
"num_tokens": 18730668.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.376577615737915,
|
|
"epoch": 0.7848222862632085,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004946517920437571,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.19331753104925156,
|
|
"num_tokens": 18741991.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.342368412017822,
|
|
"epoch": 0.7853025936599424,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004946443590031041,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.18789397180080414,
|
|
"num_tokens": 18753919.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.436485338211059,
|
|
"epoch": 0.7857829010566763,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004946369208629613,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.19887305349111556,
|
|
"num_tokens": 18764342.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.393796682357788,
|
|
"epoch": 0.7862632084534101,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004946294776235013,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.189849916100502,
|
|
"num_tokens": 18776044.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.510861587524414,
|
|
"epoch": 0.7867435158501441,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004946220292848971,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.1867060512304306,
|
|
"num_tokens": 18787354.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.46175594329834,
|
|
"epoch": 0.787223823246878,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004946145758473214,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.19070928990840913,
|
|
"num_tokens": 18797845.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.449837017059326,
|
|
"epoch": 0.7877041306436119,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004946071173109475,
|
|
"loss": 5.3396,
|
|
"mean_token_accuracy": 0.18716363608837128,
|
|
"num_tokens": 18809253.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.3513405323028564,
|
|
"epoch": 0.7881844380403458,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004945996536759484,
|
|
"loss": 5.2064,
|
|
"mean_token_accuracy": 0.19941684752702712,
|
|
"num_tokens": 18819768.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.559111213684082,
|
|
"epoch": 0.7886647454370798,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004945921849424974,
|
|
"loss": 5.4626,
|
|
"mean_token_accuracy": 0.1826834797859192,
|
|
"num_tokens": 18831151.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.435736131668091,
|
|
"epoch": 0.7891450528338136,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004945847111107679,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.19682194143533707,
|
|
"num_tokens": 18842133.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.402924823760986,
|
|
"epoch": 0.7896253602305475,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004945772321809334,
|
|
"loss": 5.3724,
|
|
"mean_token_accuracy": 0.18223796933889388,
|
|
"num_tokens": 18853295.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.370457410812378,
|
|
"epoch": 0.7901056676272814,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004945697481531677,
|
|
"loss": 5.3394,
|
|
"mean_token_accuracy": 0.18799475729465484,
|
|
"num_tokens": 18865802.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.41959547996521,
|
|
"epoch": 0.7905859750240154,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004945622590276443,
|
|
"loss": 5.2509,
|
|
"mean_token_accuracy": 0.199704909324646,
|
|
"num_tokens": 18877693.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.448678016662598,
|
|
"epoch": 0.7910662824207493,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004945547648045373,
|
|
"loss": 5.3034,
|
|
"mean_token_accuracy": 0.19510304629802705,
|
|
"num_tokens": 18888549.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.383643054962159,
|
|
"epoch": 0.7915465898174832,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004945472654840206,
|
|
"loss": 5.2528,
|
|
"mean_token_accuracy": 0.19469839185476304,
|
|
"num_tokens": 18899132.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.332378721237182,
|
|
"epoch": 0.7920268972142172,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004945397610662683,
|
|
"loss": 5.2669,
|
|
"mean_token_accuracy": 0.18720251321792603,
|
|
"num_tokens": 18911774.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.511254453659058,
|
|
"epoch": 0.792507204610951,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004945322515514547,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.18927176892757416,
|
|
"num_tokens": 18922806.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.4477160453796385,
|
|
"epoch": 0.7929875120076849,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000494524736939754,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.1946116179227829,
|
|
"num_tokens": 18934861.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.501181507110596,
|
|
"epoch": 0.7934678194044188,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004945172172313408,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.196722511947155,
|
|
"num_tokens": 18944269.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.460241794586182,
|
|
"epoch": 0.7939481268011528,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004945096924263896,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.18492037802934647,
|
|
"num_tokens": 18957197.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.45379958152771,
|
|
"epoch": 0.7944284341978867,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004945021625250753,
|
|
"loss": 5.3238,
|
|
"mean_token_accuracy": 0.18502913117408754,
|
|
"num_tokens": 18968254.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.380208730697632,
|
|
"epoch": 0.7949087415946205,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004944946275275724,
|
|
"loss": 5.2511,
|
|
"mean_token_accuracy": 0.19607954174280168,
|
|
"num_tokens": 18979372.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.377955198287964,
|
|
"epoch": 0.7953890489913544,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004944870874340561,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.19273356199264527,
|
|
"num_tokens": 18991075.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.339691877365112,
|
|
"epoch": 0.7958693563880884,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004944795422447013,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.1929136782884598,
|
|
"num_tokens": 19002324.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.4347127914428714,
|
|
"epoch": 0.7963496637848223,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004944719919596835,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.18703622221946717,
|
|
"num_tokens": 19014406.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.417851257324219,
|
|
"epoch": 0.7968299711815562,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004944644365791776,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.1931007146835327,
|
|
"num_tokens": 19025984.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.462738418579102,
|
|
"epoch": 0.7973102785782901,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.000494456876103359,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.19296077787876129,
|
|
"num_tokens": 19036189.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.458130979537964,
|
|
"epoch": 0.7977905859750241,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004944493105324035,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.1877345398068428,
|
|
"num_tokens": 19047587.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.459564208984375,
|
|
"epoch": 0.7982708933717579,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004944417398664866,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.18953346759080886,
|
|
"num_tokens": 19058467.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.454111480712891,
|
|
"epoch": 0.7987512007684918,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004944341641057843,
|
|
"loss": 5.3967,
|
|
"mean_token_accuracy": 0.18493064045906066,
|
|
"num_tokens": 19070235.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.4866527080535885,
|
|
"epoch": 0.7992315081652257,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004944265832504721,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.18924559652805328,
|
|
"num_tokens": 19082005.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.48219485282898,
|
|
"epoch": 0.7997118155619597,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004944189973007262,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.1910828694701195,
|
|
"num_tokens": 19092922.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.490187454223633,
|
|
"epoch": 0.8001921229586936,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004944114062567229,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.1872426077723503,
|
|
"num_tokens": 19104832.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.429300737380982,
|
|
"epoch": 0.8006724303554275,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004944038101186381,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.192307049036026,
|
|
"num_tokens": 19116261.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.447351121902466,
|
|
"epoch": 0.8011527377521613,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004943962088866483,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.18607832938432695,
|
|
"num_tokens": 19127195.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.504926490783691,
|
|
"epoch": 0.8016330451488953,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004943886025609301,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.18687803000211717,
|
|
"num_tokens": 19138164.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.519906806945801,
|
|
"epoch": 0.8021133525456292,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00049438099114166,
|
|
"loss": 5.3479,
|
|
"mean_token_accuracy": 0.18315576612949372,
|
|
"num_tokens": 19149153.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.4653278350830075,
|
|
"epoch": 0.8025936599423631,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004943733746290147,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.1829417422413826,
|
|
"num_tokens": 19161023.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.3256079196929935,
|
|
"epoch": 0.803073967339097,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000494365753023171,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.20271517485380172,
|
|
"num_tokens": 19172466.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.420790147781372,
|
|
"epoch": 0.803554274735831,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004943581263243059,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.19215305149555206,
|
|
"num_tokens": 19183684.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.387237548828125,
|
|
"epoch": 0.8040345821325648,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004943504945325965,
|
|
"loss": 5.2071,
|
|
"mean_token_accuracy": 0.19915805160999298,
|
|
"num_tokens": 19194479.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.486040210723877,
|
|
"epoch": 0.8045148895292987,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004943428576482198,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.1853162929415703,
|
|
"num_tokens": 19206323.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.524908256530762,
|
|
"epoch": 0.8049951969260326,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004943352156713535,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.18050336390733718,
|
|
"num_tokens": 19218849.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.378326368331909,
|
|
"epoch": 0.8054755043227666,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004943275686021747,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.19283648282289506,
|
|
"num_tokens": 19229603.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.45412769317627,
|
|
"epoch": 0.8059558117195005,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000494319916440861,
|
|
"loss": 5.3767,
|
|
"mean_token_accuracy": 0.1857156127691269,
|
|
"num_tokens": 19241318.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.506405687332153,
|
|
"epoch": 0.8064361191162344,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004943122591875901,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.1883388116955757,
|
|
"num_tokens": 19252640.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.376809740066529,
|
|
"epoch": 0.8069164265129684,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004943045968425398,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.19249245077371596,
|
|
"num_tokens": 19262971.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.40840973854065,
|
|
"epoch": 0.8073967339097022,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004942969294058878,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.19400492906570435,
|
|
"num_tokens": 19274426.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.423577404022216,
|
|
"epoch": 0.8078770413064361,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004942892568778125,
|
|
"loss": 5.3178,
|
|
"mean_token_accuracy": 0.19099642783403398,
|
|
"num_tokens": 19286806.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.421319198608399,
|
|
"epoch": 0.80835734870317,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004942815792584917,
|
|
"loss": 5.2886,
|
|
"mean_token_accuracy": 0.1912714347243309,
|
|
"num_tokens": 19297997.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.429638195037842,
|
|
"epoch": 0.808837656099904,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004942738965481038,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.1927062064409256,
|
|
"num_tokens": 19309789.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.481442499160766,
|
|
"epoch": 0.8093179634966379,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004942662087468272,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.1988959088921547,
|
|
"num_tokens": 19320688.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.466083526611328,
|
|
"epoch": 0.8097982708933718,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004942585158548402,
|
|
"loss": 5.3,
|
|
"mean_token_accuracy": 0.19300891906023027,
|
|
"num_tokens": 19331670.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.411867380142212,
|
|
"epoch": 0.8102785782901056,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004942508178723214,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.1901465341448784,
|
|
"num_tokens": 19343578.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.404733514785766,
|
|
"epoch": 0.8107588856868396,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004942431147994499,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.18797844797372817,
|
|
"num_tokens": 19354875.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.397558355331421,
|
|
"epoch": 0.8112391930835735,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004942354066364042,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.19307279735803604,
|
|
"num_tokens": 19366353.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.365726041793823,
|
|
"epoch": 0.8117195004803074,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004942276933833634,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.2018436923623085,
|
|
"num_tokens": 19377534.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.49608883857727,
|
|
"epoch": 0.8121998078770413,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004942199750405064,
|
|
"loss": 5.3522,
|
|
"mean_token_accuracy": 0.18297522366046906,
|
|
"num_tokens": 19388188.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.351274061203003,
|
|
"epoch": 0.8126801152737753,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004942122516080127,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.20403366088867186,
|
|
"num_tokens": 19399910.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.399643898010254,
|
|
"epoch": 0.8131604226705091,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004942045230860614,
|
|
"loss": 5.3242,
|
|
"mean_token_accuracy": 0.1914950430393219,
|
|
"num_tokens": 19411715.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.518057441711425,
|
|
"epoch": 0.813640730067243,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004941967894748319,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.1805759996175766,
|
|
"num_tokens": 19423275.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.468633556365967,
|
|
"epoch": 0.8141210374639769,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004941890507745039,
|
|
"loss": 5.3439,
|
|
"mean_token_accuracy": 0.1881400853395462,
|
|
"num_tokens": 19436035.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.334964370727539,
|
|
"epoch": 0.8146013448607109,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004941813069852569,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.19211569279432297,
|
|
"num_tokens": 19447755.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.442940282821655,
|
|
"epoch": 0.8150816522574448,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004941735581072708,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.19524805694818498,
|
|
"num_tokens": 19459044.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.463700771331787,
|
|
"epoch": 0.8155619596541787,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004941658041407255,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.19276389479637146,
|
|
"num_tokens": 19471486.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.3289789199829105,
|
|
"epoch": 0.8160422670509125,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000494158045085801,
|
|
"loss": 5.2032,
|
|
"mean_token_accuracy": 0.19632963836193085,
|
|
"num_tokens": 19482428.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.3796313285827635,
|
|
"epoch": 0.8165225744476465,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004941502809426776,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.18650323897600174,
|
|
"num_tokens": 19494616.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.458334255218506,
|
|
"epoch": 0.8170028818443804,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004941425117115354,
|
|
"loss": 5.2576,
|
|
"mean_token_accuracy": 0.18943592607975007,
|
|
"num_tokens": 19504953.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.4868889331817625,
|
|
"epoch": 0.8174831892411143,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004941347373925547,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.19201811403036118,
|
|
"num_tokens": 19517408.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.341999959945679,
|
|
"epoch": 0.8179634966378482,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004941269579859161,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.19638950228691102,
|
|
"num_tokens": 19529190.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.413870716094971,
|
|
"epoch": 0.8184438040345822,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.0004941191734918002,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.188216133415699,
|
|
"num_tokens": 19540278.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.504590129852295,
|
|
"epoch": 0.818924111431316,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000494111383910388,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.19409725069999695,
|
|
"num_tokens": 19551224.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.531445264816284,
|
|
"epoch": 0.8194044188280499,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004941035892418597,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.1864960640668869,
|
|
"num_tokens": 19564386.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.431317234039307,
|
|
"epoch": 0.8198847262247838,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004940957894863968,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.1914148211479187,
|
|
"num_tokens": 19576170.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.4451305866241455,
|
|
"epoch": 0.8203650336215178,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004940879846441804,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.1870593547821045,
|
|
"num_tokens": 19587220.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.423466682434082,
|
|
"epoch": 0.8208453410182517,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004940801747153914,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.1941332072019577,
|
|
"num_tokens": 19598649.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.417064952850342,
|
|
"epoch": 0.8213256484149856,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004940723597002113,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.18709755837917327,
|
|
"num_tokens": 19610243.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.425043964385987,
|
|
"epoch": 0.8218059558117194,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004940645395988216,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.1864430233836174,
|
|
"num_tokens": 19621467.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.518671655654908,
|
|
"epoch": 0.8222862632084534,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004940567144114036,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.18262853622436523,
|
|
"num_tokens": 19633367.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.375760507583618,
|
|
"epoch": 0.8227665706051873,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004940488841381393,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.19268843829631804,
|
|
"num_tokens": 19643144.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.439542007446289,
|
|
"epoch": 0.8232468780019212,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004940410487792103,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.18914695084095,
|
|
"num_tokens": 19654501.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.494971895217896,
|
|
"epoch": 0.8237271853986552,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004940332083347986,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.18960674852132797,
|
|
"num_tokens": 19665382.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.38565502166748,
|
|
"epoch": 0.8242074927953891,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004940253628050861,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.19930313229560853,
|
|
"num_tokens": 19677222.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.33594970703125,
|
|
"epoch": 0.824687800192123,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004940175121902552,
|
|
"loss": 5.255,
|
|
"mean_token_accuracy": 0.19458593130111695,
|
|
"num_tokens": 19688550.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.49790768623352,
|
|
"epoch": 0.8251681075888568,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000494009656490488,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.18417551070451738,
|
|
"num_tokens": 19700125.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.511040163040161,
|
|
"epoch": 0.8256484149855908,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004940017957059668,
|
|
"loss": 5.3556,
|
|
"mean_token_accuracy": 0.188738214969635,
|
|
"num_tokens": 19711969.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.419063425064087,
|
|
"epoch": 0.8261287223823247,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004939939298368742,
|
|
"loss": 5.3188,
|
|
"mean_token_accuracy": 0.1901100218296051,
|
|
"num_tokens": 19723813.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.435970211029053,
|
|
"epoch": 0.8266090297790586,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004939860588833929,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.18464711755514146,
|
|
"num_tokens": 19735539.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.573549032211304,
|
|
"epoch": 0.8270893371757925,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004939781828457055,
|
|
"loss": 5.4186,
|
|
"mean_token_accuracy": 0.18291396051645278,
|
|
"num_tokens": 19747106.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.4567383289337155,
|
|
"epoch": 0.8275696445725265,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000493970301723995,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.20237549394369125,
|
|
"num_tokens": 19760156.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.34077558517456,
|
|
"epoch": 0.8280499519692603,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004939624155184443,
|
|
"loss": 5.1876,
|
|
"mean_token_accuracy": 0.1963546797633171,
|
|
"num_tokens": 19771256.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.395107698440552,
|
|
"epoch": 0.8285302593659942,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004939545242292365,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.19642242640256882,
|
|
"num_tokens": 19781332.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.490071439743042,
|
|
"epoch": 0.8290105667627281,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004939466278565547,
|
|
"loss": 5.3844,
|
|
"mean_token_accuracy": 0.18415915966033936,
|
|
"num_tokens": 19793573.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.493253135681153,
|
|
"epoch": 0.8294908741594621,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004939387264005825,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.19739039540290831,
|
|
"num_tokens": 19803421.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.364841461181641,
|
|
"epoch": 0.829971181556196,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004939308198615031,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.20276711583137513,
|
|
"num_tokens": 19814440.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.329202556610108,
|
|
"epoch": 0.8304514889529299,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004939229082395001,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.19710343182086945,
|
|
"num_tokens": 19825721.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.397264242172241,
|
|
"epoch": 0.8309317963496637,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004939149915347573,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.1956174924969673,
|
|
"num_tokens": 19837273.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.432893228530884,
|
|
"epoch": 0.8314121037463977,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004939070697474585,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.19328472763299942,
|
|
"num_tokens": 19849436.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.3606202602386475,
|
|
"epoch": 0.8318924111431316,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004938991428777875,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.20372211039066315,
|
|
"num_tokens": 19860222.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.417522144317627,
|
|
"epoch": 0.8323727185398655,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004938912109259284,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.1950880378484726,
|
|
"num_tokens": 19870934.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.42161226272583,
|
|
"epoch": 0.8328530259365994,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004938832738920654,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.18586503565311432,
|
|
"num_tokens": 19882149.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.408535623550415,
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004938753317763826,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.19854941815137864,
|
|
"num_tokens": 19893276.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.444899177551269,
|
|
"epoch": 0.8338136407300673,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004938673845790646,
|
|
"loss": 5.3907,
|
|
"mean_token_accuracy": 0.18177414834499359,
|
|
"num_tokens": 19904723.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.429121828079223,
|
|
"epoch": 0.8342939481268011,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004938594323002957,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.18887486606836318,
|
|
"num_tokens": 19915226.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.474567461013794,
|
|
"epoch": 0.834774255523535,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004938514749402609,
|
|
"loss": 5.3154,
|
|
"mean_token_accuracy": 0.19146300554275514,
|
|
"num_tokens": 19927911.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.416434335708618,
|
|
"epoch": 0.835254562920269,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004938435124991447,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.1899621829390526,
|
|
"num_tokens": 19940356.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.456482315063477,
|
|
"epoch": 0.8357348703170029,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004938355449771318,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.1840689241886139,
|
|
"num_tokens": 19951108.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.391934776306153,
|
|
"epoch": 0.8362151777137368,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004938275723744075,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.1951828345656395,
|
|
"num_tokens": 19962427.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.477988290786743,
|
|
"epoch": 0.8366954851104706,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004938195946911567,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.18400087505578994,
|
|
"num_tokens": 19973476.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.459586954116821,
|
|
"epoch": 0.8371757925072046,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004938116119275645,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.19358986765146255,
|
|
"num_tokens": 19984034.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.461347770690918,
|
|
"epoch": 0.8376560999039385,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004938036240838166,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.1869371846318245,
|
|
"num_tokens": 19996035.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.48123517036438,
|
|
"epoch": 0.8381364073006724,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004937956311600983,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.19443193972110748,
|
|
"num_tokens": 20007259.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.387519788742066,
|
|
"epoch": 0.8386167146974063,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004937876331565951,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.191537244617939,
|
|
"num_tokens": 20018673.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.405492687225342,
|
|
"epoch": 0.8390970220941403,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004937796300734926,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.19398470222949982,
|
|
"num_tokens": 20030767.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.465118265151977,
|
|
"epoch": 0.8395773294908742,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004937716219109769,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.18796655386686326,
|
|
"num_tokens": 20041268.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.393164873123169,
|
|
"epoch": 0.840057636887608,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004937636086692336,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.19626713842153548,
|
|
"num_tokens": 20052285.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.479882860183716,
|
|
"epoch": 0.840537944284342,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000493755590348449,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.18523990362882614,
|
|
"num_tokens": 20065113.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.5238039016723635,
|
|
"epoch": 0.8410182516810759,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004937475669488091,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.18915547877550126,
|
|
"num_tokens": 20076151.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.433921766281128,
|
|
"epoch": 0.8414985590778098,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004937395384705004,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.1922421559691429,
|
|
"num_tokens": 20088195.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.366722965240479,
|
|
"epoch": 0.8419788664745437,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004937315049137089,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.20207698196172713,
|
|
"num_tokens": 20098576.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.47697081565857,
|
|
"epoch": 0.8424591738712777,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004937234662786216,
|
|
"loss": 5.3855,
|
|
"mean_token_accuracy": 0.18147180378437042,
|
|
"num_tokens": 20110176.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.497801446914673,
|
|
"epoch": 0.8429394812680115,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004937154225654246,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.19353261291980745,
|
|
"num_tokens": 20121713.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.4794285774230955,
|
|
"epoch": 0.8434197886647454,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004937073737743051,
|
|
"loss": 5.387,
|
|
"mean_token_accuracy": 0.18549911230802535,
|
|
"num_tokens": 20134126.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.411435079574585,
|
|
"epoch": 0.8439000960614793,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004936993199054499,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.19265223741531373,
|
|
"num_tokens": 20144791.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.504547548294068,
|
|
"epoch": 0.8443804034582133,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004936912609590458,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.18888544291257858,
|
|
"num_tokens": 20157214.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.520567083358765,
|
|
"epoch": 0.8448607108549472,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00049368319693528,
|
|
"loss": 5.4363,
|
|
"mean_token_accuracy": 0.18187134712934494,
|
|
"num_tokens": 20168952.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.427335262298584,
|
|
"epoch": 0.8453410182516811,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004936751278343397,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.18625982999801635,
|
|
"num_tokens": 20181829.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.497209167480468,
|
|
"epoch": 0.845821325648415,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004936670536564123,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.1777316763997078,
|
|
"num_tokens": 20193362.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.467062711715698,
|
|
"epoch": 0.8463016330451489,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004936589744016853,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.18980531096458436,
|
|
"num_tokens": 20205159.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.457325077056884,
|
|
"epoch": 0.8467819404418828,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000493650890070346,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.19815688878297805,
|
|
"num_tokens": 20217075.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.4429614543914795,
|
|
"epoch": 0.8472622478386167,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004936428006625824,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.19235170334577562,
|
|
"num_tokens": 20227901.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.43179841041565,
|
|
"epoch": 0.8477425552353506,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004936347061785823,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.19602776765823365,
|
|
"num_tokens": 20239945.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.503558683395386,
|
|
"epoch": 0.8482228626320846,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004936266066185334,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.18627352267503738,
|
|
"num_tokens": 20251503.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.4219482898712155,
|
|
"epoch": 0.8487031700288185,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004936185019826239,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.19256945699453354,
|
|
"num_tokens": 20263044.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.430175113677978,
|
|
"epoch": 0.8491834774255523,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004936103922710419,
|
|
"loss": 5.2749,
|
|
"mean_token_accuracy": 0.19340976625680922,
|
|
"num_tokens": 20273563.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.429841232299805,
|
|
"epoch": 0.8496637848222862,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004936022774839759,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.19277847558259964,
|
|
"num_tokens": 20285482.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.55850625038147,
|
|
"epoch": 0.8501440922190202,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004935941576216141,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.18891362249851226,
|
|
"num_tokens": 20296666.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.324230718612671,
|
|
"epoch": 0.8506243996157541,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000493586032684145,
|
|
"loss": 5.1867,
|
|
"mean_token_accuracy": 0.20015221387147902,
|
|
"num_tokens": 20308978.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.396427583694458,
|
|
"epoch": 0.851104707012488,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004935779026717573,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.1915975570678711,
|
|
"num_tokens": 20321488.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.392654228210449,
|
|
"epoch": 0.8515850144092219,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004935697675846396,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.20899215042591096,
|
|
"num_tokens": 20332938.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.3349143981933596,
|
|
"epoch": 0.8520653218059558,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004935616274229811,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.20433661639690398,
|
|
"num_tokens": 20342986.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.402394390106201,
|
|
"epoch": 0.8525456292026897,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004935534821869705,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.1873833268880844,
|
|
"num_tokens": 20355791.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.331464433670044,
|
|
"epoch": 0.8530259365994236,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004935453318767971,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.1992361932992935,
|
|
"num_tokens": 20367080.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.449164867401123,
|
|
"epoch": 0.8535062439961575,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00049353717649265,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.19925762861967086,
|
|
"num_tokens": 20376697.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.411453199386597,
|
|
"epoch": 0.8539865513928915,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004935290160347185,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.19461767822504045,
|
|
"num_tokens": 20387430.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.4372375965118405,
|
|
"epoch": 0.8544668587896254,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004935208505031922,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.19331432580947877,
|
|
"num_tokens": 20398488.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.35177903175354,
|
|
"epoch": 0.8549471661863592,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004935126798982606,
|
|
"loss": 5.2947,
|
|
"mean_token_accuracy": 0.19315535128116607,
|
|
"num_tokens": 20410316.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.422860813140869,
|
|
"epoch": 0.8554274735830932,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004935045042201135,
|
|
"loss": 5.2159,
|
|
"mean_token_accuracy": 0.20096342861652375,
|
|
"num_tokens": 20421645.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.489001989364624,
|
|
"epoch": 0.8559077809798271,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004934963234689407,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.183612222969532,
|
|
"num_tokens": 20433397.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.379166746139527,
|
|
"epoch": 0.856388088376561,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000493488137644932,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.19305571168661118,
|
|
"num_tokens": 20446218.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.44214973449707,
|
|
"epoch": 0.8568683957732949,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004934799467482774,
|
|
"loss": 5.3219,
|
|
"mean_token_accuracy": 0.19116387367248536,
|
|
"num_tokens": 20457265.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.4222705364227295,
|
|
"epoch": 0.8573487031700289,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004934717507791673,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.18659937530755996,
|
|
"num_tokens": 20468748.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.445251178741455,
|
|
"epoch": 0.8578290105667628,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004934635497377919,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.19034985303878785,
|
|
"num_tokens": 20481416.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.368124771118164,
|
|
"epoch": 0.8583093179634966,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004934553436243415,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.19576380997896195,
|
|
"num_tokens": 20493063.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.364702558517456,
|
|
"epoch": 0.8587896253602305,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004934471324390067,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.19291483908891677,
|
|
"num_tokens": 20504000.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.429334592819214,
|
|
"epoch": 0.8592699327569645,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004934389161819783,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.19717443138360977,
|
|
"num_tokens": 20516419.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.420124769210815,
|
|
"epoch": 0.8597502401536984,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004934306948534467,
|
|
"loss": 5.2838,
|
|
"mean_token_accuracy": 0.19301420897245408,
|
|
"num_tokens": 20527385.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.477877616882324,
|
|
"epoch": 0.8602305475504323,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004934224684536031,
|
|
"loss": 5.2749,
|
|
"mean_token_accuracy": 0.19428442865610124,
|
|
"num_tokens": 20538051.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.45963487625122,
|
|
"epoch": 0.8607108549471661,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004934142369826382,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.18439266681671143,
|
|
"num_tokens": 20550321.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.412842273712158,
|
|
"epoch": 0.8611911623439001,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004934060004407434,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.19368817657232285,
|
|
"num_tokens": 20561229.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.422095060348511,
|
|
"epoch": 0.861671469740634,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004933977588281099,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.19638503342866898,
|
|
"num_tokens": 20572040.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.39437084197998,
|
|
"epoch": 0.8621517771373679,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004933895121449288,
|
|
"loss": 5.2601,
|
|
"mean_token_accuracy": 0.19693639874458313,
|
|
"num_tokens": 20583110.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.377373886108399,
|
|
"epoch": 0.8626320845341018,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004933812603913917,
|
|
"loss": 5.2503,
|
|
"mean_token_accuracy": 0.19587540477514268,
|
|
"num_tokens": 20593647.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.313106870651245,
|
|
"epoch": 0.8631123919308358,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004933730035676903,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.20811958760023117,
|
|
"num_tokens": 20604428.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.324781608581543,
|
|
"epoch": 0.8635926993275697,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004933647416740161,
|
|
"loss": 5.193,
|
|
"mean_token_accuracy": 0.2043803945183754,
|
|
"num_tokens": 20615811.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.465307807922363,
|
|
"epoch": 0.8640730067243035,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000493356474710561,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.19291181564331056,
|
|
"num_tokens": 20627679.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.462645196914673,
|
|
"epoch": 0.8645533141210374,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000493348202677517,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.19695123583078383,
|
|
"num_tokens": 20638879.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.8645533141210374,
|
|
"eval_entropy": 5.286723673488964,
|
|
"eval_loss": 5.325511455535889,
|
|
"eval_mean_token_accuracy": 0.1974526095666765,
|
|
"eval_num_tokens": 20638879.0,
|
|
"eval_runtime": 26.6951,
|
|
"eval_samples_per_second": 1229.251,
|
|
"eval_steps_per_second": 153.661,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.426865434646606,
|
|
"epoch": 0.8650336215177714,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004933399255750761,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.19479126036167144,
|
|
"num_tokens": 20649729.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.488546895980835,
|
|
"epoch": 0.8655139289145053,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004933316434034304,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.19636655002832412,
|
|
"num_tokens": 20660473.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.430379104614258,
|
|
"epoch": 0.8659942363112392,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004933233561627723,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.19236456006765365,
|
|
"num_tokens": 20671776.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.36920862197876,
|
|
"epoch": 0.866474543707973,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004933150638532942,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.19504862427711486,
|
|
"num_tokens": 20684147.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.4135294437408445,
|
|
"epoch": 0.866954851104707,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004933067664751885,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.19196840822696687,
|
|
"num_tokens": 20695248.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.4506837844848635,
|
|
"epoch": 0.8674351585014409,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000493298464028648,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.19254141598939895,
|
|
"num_tokens": 20707772.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.383131408691407,
|
|
"epoch": 0.8679154658981748,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004932901565138653,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.1917433649301529,
|
|
"num_tokens": 20718813.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.361244630813599,
|
|
"epoch": 0.8683957732949087,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004932818439310334,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.2007886528968811,
|
|
"num_tokens": 20730939.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.520299577713013,
|
|
"epoch": 0.8688760806916427,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004932735262803452,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.18674698919057847,
|
|
"num_tokens": 20742990.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.398456239700318,
|
|
"epoch": 0.8693563880883766,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004932652035619939,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.19423752874135972,
|
|
"num_tokens": 20754076.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.396093511581421,
|
|
"epoch": 0.8698366954851104,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004932568757761727,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.1945582628250122,
|
|
"num_tokens": 20765538.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.43677659034729,
|
|
"epoch": 0.8703170028818443,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004932485429230748,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.18673224449157716,
|
|
"num_tokens": 20776359.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.434298849105835,
|
|
"epoch": 0.8707973102785783,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000493240205002894,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.19699715822935104,
|
|
"num_tokens": 20787581.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.400527620315552,
|
|
"epoch": 0.8712776176753122,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004932318620158235,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.1865576073527336,
|
|
"num_tokens": 20799904.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.420672225952148,
|
|
"epoch": 0.8717579250720461,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004932235139620574,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.19597328156232835,
|
|
"num_tokens": 20810238.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.439179420471191,
|
|
"epoch": 0.8722382324687801,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004932151608417892,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.1971805915236473,
|
|
"num_tokens": 20821349.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.347060632705689,
|
|
"epoch": 0.872718539865514,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004932068026552127,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.1895262524485588,
|
|
"num_tokens": 20834788.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.401967573165893,
|
|
"epoch": 0.8731988472622478,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004931984394025224,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.18734365105628967,
|
|
"num_tokens": 20845571.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.515474128723144,
|
|
"epoch": 0.8736791546589817,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004931900710839123,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.19314252138137816,
|
|
"num_tokens": 20857209.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.58108434677124,
|
|
"epoch": 0.8741594620557157,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004931816976995766,
|
|
"loss": 5.3877,
|
|
"mean_token_accuracy": 0.1860686019062996,
|
|
"num_tokens": 20870624.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.389701843261719,
|
|
"epoch": 0.8746397694524496,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004931733192497097,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.19380870908498765,
|
|
"num_tokens": 20881769.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.347037696838379,
|
|
"epoch": 0.8751200768491835,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004931649357345062,
|
|
"loss": 5.268,
|
|
"mean_token_accuracy": 0.19019660502672195,
|
|
"num_tokens": 20892817.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.417110347747803,
|
|
"epoch": 0.8756003842459174,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004931565471541606,
|
|
"loss": 5.2223,
|
|
"mean_token_accuracy": 0.1976736456155777,
|
|
"num_tokens": 20903042.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.366578245162964,
|
|
"epoch": 0.8760806916426513,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004931481535088679,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.20431646704673767,
|
|
"num_tokens": 20914684.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.304960870742798,
|
|
"epoch": 0.8765609990393852,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004931397547988229,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.20247095227241516,
|
|
"num_tokens": 20926585.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.463677930831909,
|
|
"epoch": 0.8770413064361191,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004931313510242204,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.1939797580242157,
|
|
"num_tokens": 20939729.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.428589010238648,
|
|
"epoch": 0.877521613832853,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004931229421852557,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.19262615442276002,
|
|
"num_tokens": 20951697.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.455162096023559,
|
|
"epoch": 0.878001921229587,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000493114528282124,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.19121593236923218,
|
|
"num_tokens": 20962729.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.3391868591308596,
|
|
"epoch": 0.8784822286263209,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004931061093150206,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.19951595962047577,
|
|
"num_tokens": 20973331.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.30279426574707,
|
|
"epoch": 0.8789625360230547,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004930976852841409,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.1909520596265793,
|
|
"num_tokens": 20985609.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.3875815868377686,
|
|
"epoch": 0.8794428434197886,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004930892561896806,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.18779444694519043,
|
|
"num_tokens": 20997231.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.474369382858276,
|
|
"epoch": 0.8799231508165226,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004930808220318354,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.19536698013544082,
|
|
"num_tokens": 21008511.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.363372564315796,
|
|
"epoch": 0.8804034582132565,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004930723828108012,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.196178437769413,
|
|
"num_tokens": 21019108.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.387450408935547,
|
|
"epoch": 0.8808837656099904,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004930639385267736,
|
|
"loss": 5.2726,
|
|
"mean_token_accuracy": 0.19503167718648912,
|
|
"num_tokens": 21030621.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.348882246017456,
|
|
"epoch": 0.8813640730067243,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000493055489179949,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.192335869371891,
|
|
"num_tokens": 21041778.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.387232732772827,
|
|
"epoch": 0.8818443804034583,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004930470347705234,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.19484953433275223,
|
|
"num_tokens": 21054257.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.413940906524658,
|
|
"epoch": 0.8823246878001921,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000493038575298693,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.1887539103627205,
|
|
"num_tokens": 21066378.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.3667442321777346,
|
|
"epoch": 0.882804995196926,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004930301107646545,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.19099806249141693,
|
|
"num_tokens": 21078913.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.448846292495728,
|
|
"epoch": 0.8832853025936599,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004930216411686042,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.191778327524662,
|
|
"num_tokens": 21090500.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.379825496673584,
|
|
"epoch": 0.8837656099903939,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004930131665107387,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.1909867912530899,
|
|
"num_tokens": 21102793.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.45488395690918,
|
|
"epoch": 0.8842459173871278,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000493004686791255,
|
|
"loss": 5.3684,
|
|
"mean_token_accuracy": 0.1828697770833969,
|
|
"num_tokens": 21114504.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.463016366958618,
|
|
"epoch": 0.8847262247838616,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004929962020103496,
|
|
"loss": 5.2191,
|
|
"mean_token_accuracy": 0.19329135566949845,
|
|
"num_tokens": 21126733.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.393966102600098,
|
|
"epoch": 0.8852065321805955,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004929877121682198,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.19551412165164947,
|
|
"num_tokens": 21138045.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.377452850341797,
|
|
"epoch": 0.8856868395773295,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004929792172650627,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.18592798262834548,
|
|
"num_tokens": 21151562.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.428852367401123,
|
|
"epoch": 0.8861671469740634,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004929707173010753,
|
|
"loss": 5.255,
|
|
"mean_token_accuracy": 0.19008971899747848,
|
|
"num_tokens": 21162943.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.399478769302368,
|
|
"epoch": 0.8866474543707973,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004929622122764552,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.1919425219297409,
|
|
"num_tokens": 21174392.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.352005243301392,
|
|
"epoch": 0.8871277617675313,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004929537021913997,
|
|
"loss": 5.1559,
|
|
"mean_token_accuracy": 0.2034900963306427,
|
|
"num_tokens": 21185372.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.383670997619629,
|
|
"epoch": 0.8876080691642652,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004929451870461064,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.1892882540822029,
|
|
"num_tokens": 21197044.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.367713785171508,
|
|
"epoch": 0.888088376560999,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004929366668407731,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.2033403143286705,
|
|
"num_tokens": 21207729.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.42926664352417,
|
|
"epoch": 0.8885686839577329,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004929281415755974,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.1902792662382126,
|
|
"num_tokens": 21218909.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.449072790145874,
|
|
"epoch": 0.8890489913544669,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004929196112507775,
|
|
"loss": 5.3681,
|
|
"mean_token_accuracy": 0.18844604790210723,
|
|
"num_tokens": 21230543.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.416154241561889,
|
|
"epoch": 0.8895292987512008,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004929110758665112,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.1925010174512863,
|
|
"num_tokens": 21242064.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.459584474563599,
|
|
"epoch": 0.8900096061479347,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004929025354229969,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.1879194974899292,
|
|
"num_tokens": 21254321.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.325783538818359,
|
|
"epoch": 0.8904899135446686,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004928939899204326,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.19764553308486937,
|
|
"num_tokens": 21264741.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.373823833465576,
|
|
"epoch": 0.8909702209414025,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000492885439359017,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.1942809045314789,
|
|
"num_tokens": 21276834.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.346015501022339,
|
|
"epoch": 0.8914505283381364,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004928768837389485,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.199334117770195,
|
|
"num_tokens": 21287108.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.389419937133789,
|
|
"epoch": 0.8919308357348703,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004928683230604257,
|
|
"loss": 5.2588,
|
|
"mean_token_accuracy": 0.19463921040296556,
|
|
"num_tokens": 21299942.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.5489719867706295,
|
|
"epoch": 0.8924111431316042,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004928597573236474,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.18777535408735274,
|
|
"num_tokens": 21311243.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.459582376480102,
|
|
"epoch": 0.8928914505283382,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004928511865288123,
|
|
"loss": 5.2236,
|
|
"mean_token_accuracy": 0.1973385766148567,
|
|
"num_tokens": 21322291.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.399600267410278,
|
|
"epoch": 0.8933717579250721,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004928426106761197,
|
|
"loss": 5.3136,
|
|
"mean_token_accuracy": 0.1954808861017227,
|
|
"num_tokens": 21333257.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.341015815734863,
|
|
"epoch": 0.8938520653218059,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004928340297657685,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.19164499044418334,
|
|
"num_tokens": 21345848.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.4385558605194095,
|
|
"epoch": 0.8943323727185398,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004928254437979578,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.1927623987197876,
|
|
"num_tokens": 21357693.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.458484649658203,
|
|
"epoch": 0.8948126801152738,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004928168527728873,
|
|
"loss": 5.3709,
|
|
"mean_token_accuracy": 0.18755813539028168,
|
|
"num_tokens": 21369653.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.543262577056884,
|
|
"epoch": 0.8952929875120077,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004928082566907562,
|
|
"loss": 5.3255,
|
|
"mean_token_accuracy": 0.1884707823395729,
|
|
"num_tokens": 21383924.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.4852776527404785,
|
|
"epoch": 0.8957732949087416,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004927996555517642,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.18983328938484192,
|
|
"num_tokens": 21395963.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.425003719329834,
|
|
"epoch": 0.8962536023054755,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004927910493561109,
|
|
"loss": 5.2752,
|
|
"mean_token_accuracy": 0.19515893906354903,
|
|
"num_tokens": 21408200.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.4679985523223875,
|
|
"epoch": 0.8967339097022095,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000492782438103996,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.18257422894239425,
|
|
"num_tokens": 21419963.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.437906932830811,
|
|
"epoch": 0.8972142170989433,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004927738217956197,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.18973549902439119,
|
|
"num_tokens": 21431824.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.327432775497437,
|
|
"epoch": 0.8976945244956772,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004927652004311819,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.20318118929862977,
|
|
"num_tokens": 21442354.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.440683889389038,
|
|
"epoch": 0.8981748318924111,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004927565740108828,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.1906980961561203,
|
|
"num_tokens": 21453734.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.4258686065673825,
|
|
"epoch": 0.8986551392891451,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004927479425349226,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.19533486664295197,
|
|
"num_tokens": 21465471.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.492523622512818,
|
|
"epoch": 0.899135446685879,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004927393060035018,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.18077984899282457,
|
|
"num_tokens": 21477775.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.405123376846314,
|
|
"epoch": 0.8996157540826129,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004927306644168207,
|
|
"loss": 5.2012,
|
|
"mean_token_accuracy": 0.20006951242685317,
|
|
"num_tokens": 21489319.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.508348512649536,
|
|
"epoch": 0.9000960614793467,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004927220177750803,
|
|
"loss": 5.4212,
|
|
"mean_token_accuracy": 0.19082773178815843,
|
|
"num_tokens": 21499742.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.399679660797119,
|
|
"epoch": 0.9005763688760807,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004927133660784811,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.20286231786012648,
|
|
"num_tokens": 21511063.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.404744958877563,
|
|
"epoch": 0.9010566762728146,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004927047093272241,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.19534123539924622,
|
|
"num_tokens": 21522500.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.436342525482178,
|
|
"epoch": 0.9015369836695485,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00049269604752151,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.19065677970647812,
|
|
"num_tokens": 21533578.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.411119651794434,
|
|
"epoch": 0.9020172910662824,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004926873806615403,
|
|
"loss": 5.3024,
|
|
"mean_token_accuracy": 0.18923772126436234,
|
|
"num_tokens": 21544296.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.43097562789917,
|
|
"epoch": 0.9024975984630164,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004926787087475158,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.18127409368753433,
|
|
"num_tokens": 21555386.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.356047916412353,
|
|
"epoch": 0.9029779058597502,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004926700317796382,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.20390814691781997,
|
|
"num_tokens": 21566527.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.434009695053101,
|
|
"epoch": 0.9034582132564841,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004926613497581088,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.1898590251803398,
|
|
"num_tokens": 21576870.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.356769323348999,
|
|
"epoch": 0.9039385206532181,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004926526626831292,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.19836246818304062,
|
|
"num_tokens": 21588113.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.392736721038818,
|
|
"epoch": 0.904418828049952,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004926439705549011,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.19404949098825455,
|
|
"num_tokens": 21599307.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.383234214782715,
|
|
"epoch": 0.9048991354466859,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004926352733736262,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.1982460543513298,
|
|
"num_tokens": 21609961.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.364962196350097,
|
|
"epoch": 0.9053794428434198,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004926265711395065,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.1919900208711624,
|
|
"num_tokens": 21622222.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.370779514312744,
|
|
"epoch": 0.9058597502401537,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000492617863852744,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.20107990950345994,
|
|
"num_tokens": 21632843.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.418545484542847,
|
|
"epoch": 0.9063400576368876,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004926091515135409,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.18908582478761674,
|
|
"num_tokens": 21645387.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.415970802307129,
|
|
"epoch": 0.9068203650336215,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004926004341220995,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.19440100640058516,
|
|
"num_tokens": 21656787.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.442439126968384,
|
|
"epoch": 0.9073006724303554,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004925917116786222,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.19421052783727646,
|
|
"num_tokens": 21667800.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.464588165283203,
|
|
"epoch": 0.9077809798270894,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004925829841833114,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.1884922429919243,
|
|
"num_tokens": 21679297.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.408057069778442,
|
|
"epoch": 0.9082612872238233,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004925742516363699,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.18808504492044448,
|
|
"num_tokens": 21692956.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.407996463775635,
|
|
"epoch": 0.9087415946205571,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004925655140380002,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.2052278771996498,
|
|
"num_tokens": 21704852.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.45927472114563,
|
|
"epoch": 0.909221902017291,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004925567713884054,
|
|
"loss": 5.2578,
|
|
"mean_token_accuracy": 0.19473172575235367,
|
|
"num_tokens": 21715886.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.401573848724365,
|
|
"epoch": 0.909702209414025,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004925480236877884,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.19722514152526854,
|
|
"num_tokens": 21727157.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.4117827892303465,
|
|
"epoch": 0.9101825168107589,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004925392709363522,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.19634680896997453,
|
|
"num_tokens": 21738232.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.409385728836059,
|
|
"epoch": 0.9106628242074928,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004925305131343001,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.1936059057712555,
|
|
"num_tokens": 21749029.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.51549596786499,
|
|
"epoch": 0.9111431316042267,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004925217502818355,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.18913210481405257,
|
|
"num_tokens": 21761243.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.4305503368377686,
|
|
"epoch": 0.9116234390009607,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004925129823791616,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.19023691713809968,
|
|
"num_tokens": 21772623.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.465691757202149,
|
|
"epoch": 0.9121037463976945,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004925042094264822,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.1913660869002342,
|
|
"num_tokens": 21782611.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.313049983978272,
|
|
"epoch": 0.9125840537944284,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000492495431424001,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.2026291459798813,
|
|
"num_tokens": 21793946.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.475982236862182,
|
|
"epoch": 0.9130643611911623,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004924866483719216,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.18050995022058486,
|
|
"num_tokens": 21803878.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.450708389282227,
|
|
"epoch": 0.9135446685878963,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004924778602704481,
|
|
"loss": 5.2886,
|
|
"mean_token_accuracy": 0.19575434625148774,
|
|
"num_tokens": 21815187.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.433311939239502,
|
|
"epoch": 0.9140249759846302,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004924690671197845,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.19489923864603043,
|
|
"num_tokens": 21825597.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.3661191940307615,
|
|
"epoch": 0.914505283381364,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004924602689201348,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.19445350468158723,
|
|
"num_tokens": 21837110.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.603121995925903,
|
|
"epoch": 0.9149855907780979,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004924514656717034,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.1843995526432991,
|
|
"num_tokens": 21847754.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.447726488113403,
|
|
"epoch": 0.9154658981748319,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004924426573746948,
|
|
"loss": 5.2908,
|
|
"mean_token_accuracy": 0.18690086007118226,
|
|
"num_tokens": 21859162.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.404438161849976,
|
|
"epoch": 0.9159462055715658,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004924338440293131,
|
|
"loss": 5.2333,
|
|
"mean_token_accuracy": 0.19627159386873244,
|
|
"num_tokens": 21870826.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.4182967185974125,
|
|
"epoch": 0.9164265129682997,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004924250256357635,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.19008689969778061,
|
|
"num_tokens": 21882003.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.389998245239258,
|
|
"epoch": 0.9169068203650336,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004924162021942502,
|
|
"loss": 5.2472,
|
|
"mean_token_accuracy": 0.19206658601760865,
|
|
"num_tokens": 21894132.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.338420677185058,
|
|
"epoch": 0.9173871277617676,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004924073737049784,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.19588926136493684,
|
|
"num_tokens": 21904951.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.401744174957275,
|
|
"epoch": 0.9178674351585014,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004923985401681528,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.20093705058097838,
|
|
"num_tokens": 21917100.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.462101602554322,
|
|
"epoch": 0.9183477425552353,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004923897015839788,
|
|
"loss": 5.2739,
|
|
"mean_token_accuracy": 0.19497210830450057,
|
|
"num_tokens": 21927541.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.449558544158935,
|
|
"epoch": 0.9188280499519692,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004923808579526613,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.19599201083183287,
|
|
"num_tokens": 21938723.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.374184608459473,
|
|
"epoch": 0.9193083573487032,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004923720092744059,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.1993010923266411,
|
|
"num_tokens": 21950424.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.397815418243408,
|
|
"epoch": 0.9197886647454371,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004923631555494179,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.19077160507440566,
|
|
"num_tokens": 21961030.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.41737380027771,
|
|
"epoch": 0.920268972142171,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004923542967779028,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.1949952483177185,
|
|
"num_tokens": 21971625.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.4148094177246096,
|
|
"epoch": 0.920749279538905,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004923454329600664,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.198010678589344,
|
|
"num_tokens": 21983733.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.334598779678345,
|
|
"epoch": 0.9212295869356388,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004923365640961143,
|
|
"loss": 5.2057,
|
|
"mean_token_accuracy": 0.19944100826978683,
|
|
"num_tokens": 21995621.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.459947204589843,
|
|
"epoch": 0.9217098943323727,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004923276901862526,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.19173183292150497,
|
|
"num_tokens": 22007325.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.43211669921875,
|
|
"epoch": 0.9221902017291066,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004923188112306874,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.19493019580841064,
|
|
"num_tokens": 22017733.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.417488241195679,
|
|
"epoch": 0.9226705091258406,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004923099272296246,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.19075092375278474,
|
|
"num_tokens": 22030451.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.426124238967896,
|
|
"epoch": 0.9231508165225745,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004923010381832706,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.1840654045343399,
|
|
"num_tokens": 22042626.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.407853460311889,
|
|
"epoch": 0.9236311239193083,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004922921440918318,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.19261801093816758,
|
|
"num_tokens": 22053314.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.52217845916748,
|
|
"epoch": 0.9241114313160422,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004922832449555144,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.18501444160938263,
|
|
"num_tokens": 22064395.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.40311222076416,
|
|
"epoch": 0.9245917387127762,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004922743407745255,
|
|
"loss": 5.2271,
|
|
"mean_token_accuracy": 0.18991311341524125,
|
|
"num_tokens": 22075960.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.428620338439941,
|
|
"epoch": 0.9250720461095101,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004922654315490714,
|
|
"loss": 5.3243,
|
|
"mean_token_accuracy": 0.19108506590127944,
|
|
"num_tokens": 22086034.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.434694719314575,
|
|
"epoch": 0.925552353506244,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004922565172793593,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.19030589908361434,
|
|
"num_tokens": 22096184.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.423196697235108,
|
|
"epoch": 0.9260326609029779,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004922475979655958,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.19332934468984603,
|
|
"num_tokens": 22108795.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.418170070648193,
|
|
"epoch": 0.9265129682997119,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004922386736079883,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.191836179792881,
|
|
"num_tokens": 22119608.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.378561210632324,
|
|
"epoch": 0.9269932756964457,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004922297442067438,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.19876005500555038,
|
|
"num_tokens": 22131621.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.464224720001221,
|
|
"epoch": 0.9274735830931796,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004922208097620697,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.19660566002130508,
|
|
"num_tokens": 22142745.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.418359851837158,
|
|
"epoch": 0.9279538904899135,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004922118702741735,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.18781233131885527,
|
|
"num_tokens": 22155457.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.480670833587647,
|
|
"epoch": 0.9284341978866475,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004922029257432625,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.2006593480706215,
|
|
"num_tokens": 22165955.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.384228754043579,
|
|
"epoch": 0.9289145052833814,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004921939761695446,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.19348620921373366,
|
|
"num_tokens": 22178142.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.303427600860596,
|
|
"epoch": 0.9293948126801153,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004921850215532275,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.19445398151874543,
|
|
"num_tokens": 22190315.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.416773939132691,
|
|
"epoch": 0.9298751200768491,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004921760618945192,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.19506083726882933,
|
|
"num_tokens": 22201785.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.412764978408814,
|
|
"epoch": 0.9303554274735831,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004921670971936276,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.19745925962924957,
|
|
"num_tokens": 22212471.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.376064443588257,
|
|
"epoch": 0.930835734870317,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004921581274507607,
|
|
"loss": 5.2887,
|
|
"mean_token_accuracy": 0.1926201105117798,
|
|
"num_tokens": 22223188.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.3791242122650145,
|
|
"epoch": 0.9313160422670509,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000492149152666127,
|
|
"loss": 5.2856,
|
|
"mean_token_accuracy": 0.19516640305519103,
|
|
"num_tokens": 22233978.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.40447883605957,
|
|
"epoch": 0.9317963496637848,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004921401728399348,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.20306110829114915,
|
|
"num_tokens": 22244713.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.402577543258667,
|
|
"epoch": 0.9322766570605188,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004921311879723926,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.19104549735784532,
|
|
"num_tokens": 22256192.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.445900964736938,
|
|
"epoch": 0.9327569644572526,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004921221980637088,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.1911557674407959,
|
|
"num_tokens": 22268294.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.463947582244873,
|
|
"epoch": 0.9332372718539865,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004921132031140925,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.19660613536834717,
|
|
"num_tokens": 22278952.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.36893048286438,
|
|
"epoch": 0.9337175792507204,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004921042031237521,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.1908170387148857,
|
|
"num_tokens": 22291057.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.458996820449829,
|
|
"epoch": 0.9341978866474544,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004920951980928969,
|
|
"loss": 5.3339,
|
|
"mean_token_accuracy": 0.19554236233234407,
|
|
"num_tokens": 22302479.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.513638114929199,
|
|
"epoch": 0.9346781940441883,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004920861880217359,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.18645547479391097,
|
|
"num_tokens": 22315116.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.492982959747314,
|
|
"epoch": 0.9351585014409222,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004920771729104781,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.18933530002832413,
|
|
"num_tokens": 22327548.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.377474308013916,
|
|
"epoch": 0.9356388088376562,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004920681527593329,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.19977929592132568,
|
|
"num_tokens": 22339154.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.3696592330932615,
|
|
"epoch": 0.93611911623439,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004920591275685098,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.19381391257047653,
|
|
"num_tokens": 22350781.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.443421649932861,
|
|
"epoch": 0.9365994236311239,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004920500973382184,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.19356204867362975,
|
|
"num_tokens": 22361990.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.353968524932862,
|
|
"epoch": 0.9370797310278578,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004920410620686682,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.20645563155412675,
|
|
"num_tokens": 22372973.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.36474575996399,
|
|
"epoch": 0.9375600384245918,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004920320217600689,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.19961441308259964,
|
|
"num_tokens": 22384369.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.446927213668824,
|
|
"epoch": 0.9380403458213257,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004920229764126306,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.19389163255691527,
|
|
"num_tokens": 22395792.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.431899785995483,
|
|
"epoch": 0.9385206532180596,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004920139260265632,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.19007924795150757,
|
|
"num_tokens": 22408182.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.4953932762146,
|
|
"epoch": 0.9390009606147934,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004920048706020769,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.18371987342834473,
|
|
"num_tokens": 22419774.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.348086547851563,
|
|
"epoch": 0.9394812680115274,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004919958101393817,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.2039043888449669,
|
|
"num_tokens": 22430210.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.391155433654785,
|
|
"epoch": 0.9399615754082613,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004919867446386883,
|
|
"loss": 5.2791,
|
|
"mean_token_accuracy": 0.19603109657764434,
|
|
"num_tokens": 22442444.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.35087218284607,
|
|
"epoch": 0.9404418828049952,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000491977674100207,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.19905803799629213,
|
|
"num_tokens": 22455521.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.477018976211548,
|
|
"epoch": 0.9409221902017291,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004919685985241483,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.19539268165826798,
|
|
"num_tokens": 22466997.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.386546516418457,
|
|
"epoch": 0.9414024975984631,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000491959517910723,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.202252659201622,
|
|
"num_tokens": 22477851.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.320065689086914,
|
|
"epoch": 0.9418828049951969,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004919504322601421,
|
|
"loss": 5.3132,
|
|
"mean_token_accuracy": 0.19332796037197114,
|
|
"num_tokens": 22489319.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.342875003814697,
|
|
"epoch": 0.9423631123919308,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004919413415726162,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.19893711507320405,
|
|
"num_tokens": 22500847.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.452093172073364,
|
|
"epoch": 0.9428434197886647,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004919322458483566,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.19633806645870208,
|
|
"num_tokens": 22512719.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.324878454208374,
|
|
"epoch": 0.9433237271853987,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004919231450875745,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.19778069853782654,
|
|
"num_tokens": 22522984.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.425866222381591,
|
|
"epoch": 0.9438040345821326,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004919140392904809,
|
|
"loss": 5.2497,
|
|
"mean_token_accuracy": 0.19792675375938415,
|
|
"num_tokens": 22534816.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.438334560394287,
|
|
"epoch": 0.9442843419788665,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004919049284572875,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.19195370823144914,
|
|
"num_tokens": 22545753.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.40117917060852,
|
|
"epoch": 0.9447646493756003,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004918958125882058,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.18848390877246857,
|
|
"num_tokens": 22557237.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.439273500442505,
|
|
"epoch": 0.9452449567723343,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004918866916834474,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.19711952954530715,
|
|
"num_tokens": 22568909.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.475560426712036,
|
|
"epoch": 0.9457252641690682,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004918775657432239,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.1842176839709282,
|
|
"num_tokens": 22582162.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.3728752613067625,
|
|
"epoch": 0.9462055715658021,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004918684347677474,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.19275673925876619,
|
|
"num_tokens": 22592405.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.4401397705078125,
|
|
"epoch": 0.946685878962536,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004918592987572298,
|
|
"loss": 5.2647,
|
|
"mean_token_accuracy": 0.19761363714933394,
|
|
"num_tokens": 22603588.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.515864324569702,
|
|
"epoch": 0.94716618635927,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004918501577118832,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.1965626984834671,
|
|
"num_tokens": 22614995.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.382491636276245,
|
|
"epoch": 0.9476464937560038,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00049184101163192,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.18818577975034714,
|
|
"num_tokens": 22627556.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.449089384078979,
|
|
"epoch": 0.9481268011527377,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004918318605175522,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.19725801050662994,
|
|
"num_tokens": 22638339.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.453399896621704,
|
|
"epoch": 0.9486071085494716,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004918227043689924,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.19545401781797409,
|
|
"num_tokens": 22648922.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.304767704010009,
|
|
"epoch": 0.9490874159462056,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004918135431864534,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.1971495494246483,
|
|
"num_tokens": 22662006.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.393329429626465,
|
|
"epoch": 0.9495677233429395,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004918043769701478,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.19754824191331863,
|
|
"num_tokens": 22674649.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.528796529769897,
|
|
"epoch": 0.9500480307396734,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004917952057202882,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.1825731188058853,
|
|
"num_tokens": 22685971.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.301946544647217,
|
|
"epoch": 0.9505283381364072,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004917860294370877,
|
|
"loss": 5.1947,
|
|
"mean_token_accuracy": 0.19821407943964003,
|
|
"num_tokens": 22696174.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.471351623535156,
|
|
"epoch": 0.9510086455331412,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004917768481207593,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.19532018154859543,
|
|
"num_tokens": 22706983.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.409218454360962,
|
|
"epoch": 0.9514889529298751,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004917676617715162,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.19715631008148193,
|
|
"num_tokens": 22718251.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.315121698379516,
|
|
"epoch": 0.951969260326609,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004917584703895717,
|
|
"loss": 5.2161,
|
|
"mean_token_accuracy": 0.1994723528623581,
|
|
"num_tokens": 22730071.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.380769062042236,
|
|
"epoch": 0.952449567723343,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004917492739751391,
|
|
"loss": 5.2659,
|
|
"mean_token_accuracy": 0.19452988654375075,
|
|
"num_tokens": 22742027.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.326001262664795,
|
|
"epoch": 0.9529298751200769,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000491740072528432,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.2100890174508095,
|
|
"num_tokens": 22752946.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.4174408435821535,
|
|
"epoch": 0.9534101825168108,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000491730866049664,
|
|
"loss": 5.2472,
|
|
"mean_token_accuracy": 0.19573100060224533,
|
|
"num_tokens": 22763944.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.352676486968994,
|
|
"epoch": 0.9538904899135446,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004917216545390489,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.20111109614372252,
|
|
"num_tokens": 22774414.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.304869508743286,
|
|
"epoch": 0.9543707973102786,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004917124379968004,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.2041419267654419,
|
|
"num_tokens": 22785533.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.272375917434692,
|
|
"epoch": 0.9548511047070125,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004917032164231327,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.2012497216463089,
|
|
"num_tokens": 22795809.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.401274967193603,
|
|
"epoch": 0.9553314121037464,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004916939898182598,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.1905418187379837,
|
|
"num_tokens": 22807705.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.4072511196136475,
|
|
"epoch": 0.9558117195004803,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004916847581823958,
|
|
"loss": 5.2487,
|
|
"mean_token_accuracy": 0.20086493641138076,
|
|
"num_tokens": 22818852.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.33159613609314,
|
|
"epoch": 0.9562920268972143,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004916755215157552,
|
|
"loss": 5.1487,
|
|
"mean_token_accuracy": 0.20367432683706282,
|
|
"num_tokens": 22829146.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.364164543151856,
|
|
"epoch": 0.9567723342939481,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004916662798185524,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.2021937385201454,
|
|
"num_tokens": 22840088.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.354869699478149,
|
|
"epoch": 0.957252641690682,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004916570330910019,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.19408445060253143,
|
|
"num_tokens": 22852470.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.425803709030151,
|
|
"epoch": 0.9577329490874159,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004916477813333185,
|
|
"loss": 5.2942,
|
|
"mean_token_accuracy": 0.18949523270130159,
|
|
"num_tokens": 22863673.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.4098917007446286,
|
|
"epoch": 0.9582132564841499,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004916385245457168,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.18925181925296783,
|
|
"num_tokens": 22874888.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.406922769546509,
|
|
"epoch": 0.9586935638808838,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000491629262728412,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.18747647106647491,
|
|
"num_tokens": 22886811.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.434124183654785,
|
|
"epoch": 0.9591738712776177,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004916199958816188,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.19523006677627563,
|
|
"num_tokens": 22898777.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.391091823577881,
|
|
"epoch": 0.9596541786743515,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004916107240055527,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.1985740229487419,
|
|
"num_tokens": 22910804.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.420175695419312,
|
|
"epoch": 0.9601344860710855,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004916014471004287,
|
|
"loss": 5.3444,
|
|
"mean_token_accuracy": 0.1966828003525734,
|
|
"num_tokens": 22922002.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.453226852416992,
|
|
"epoch": 0.9606147934678194,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004915921651664622,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.1926241248846054,
|
|
"num_tokens": 22933471.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.323097276687622,
|
|
"epoch": 0.9610951008645533,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000491582878203869,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.20190350860357284,
|
|
"num_tokens": 22945303.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.345221710205078,
|
|
"epoch": 0.9615754082612872,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004915735862128643,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.1882185682654381,
|
|
"num_tokens": 22956620.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.455479526519776,
|
|
"epoch": 0.9620557156580212,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004915642891936641,
|
|
"loss": 5.3164,
|
|
"mean_token_accuracy": 0.1943290799856186,
|
|
"num_tokens": 22968941.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.449977207183838,
|
|
"epoch": 0.962536023054755,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004915549871464841,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.19244649559259414,
|
|
"num_tokens": 22980222.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.4722264289855955,
|
|
"epoch": 0.9630163304514889,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004915456800715403,
|
|
"loss": 5.2918,
|
|
"mean_token_accuracy": 0.18933727145195006,
|
|
"num_tokens": 22991156.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.469904994964599,
|
|
"epoch": 0.9634966378482228,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000491536367969049,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.18904657065868377,
|
|
"num_tokens": 23002939.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.5011820793151855,
|
|
"epoch": 0.9639769452449568,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004915270508392261,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.19101351946592332,
|
|
"num_tokens": 23015590.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.303774166107178,
|
|
"epoch": 0.9644572526416907,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000491517728682288,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.202765029668808,
|
|
"num_tokens": 23026387.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.329340124130249,
|
|
"epoch": 0.9649375600384246,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004915084014984512,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.200466650724411,
|
|
"num_tokens": 23037475.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.398989963531494,
|
|
"epoch": 0.9654178674351584,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004914990692879322,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.19833045303821564,
|
|
"num_tokens": 23049305.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.356845140457153,
|
|
"epoch": 0.9658981748318924,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004914897320509478,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.196075040102005,
|
|
"num_tokens": 23061765.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.355252361297607,
|
|
"epoch": 0.9663784822286263,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004914803897877146,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.18955439180135727,
|
|
"num_tokens": 23072355.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.483932542800903,
|
|
"epoch": 0.9668587896253602,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004914710424984495,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.18913675248622894,
|
|
"num_tokens": 23085583.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.467744159698486,
|
|
"epoch": 0.9673390970220941,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004914616901833696,
|
|
"loss": 5.2723,
|
|
"mean_token_accuracy": 0.1920119196176529,
|
|
"num_tokens": 23095942.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.357844448089599,
|
|
"epoch": 0.9678194044188281,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000491452332842692,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.2039779394865036,
|
|
"num_tokens": 23106540.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.352479410171509,
|
|
"epoch": 0.968299711815562,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000491442970476634,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.19735341668128967,
|
|
"num_tokens": 23118006.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.345590877532959,
|
|
"epoch": 0.9687800192122958,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004914336030854129,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.2065720424056053,
|
|
"num_tokens": 23129103.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.330022239685059,
|
|
"epoch": 0.9692603266090298,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004914242306692461,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.19998914003372192,
|
|
"num_tokens": 23140009.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.416161441802979,
|
|
"epoch": 0.9697406340057637,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004914148532283516,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.19606619477272033,
|
|
"num_tokens": 23150982.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.406745910644531,
|
|
"epoch": 0.9702209414024976,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004914054707629466,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.19777030646800994,
|
|
"num_tokens": 23161834.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.45628080368042,
|
|
"epoch": 0.9707012487992315,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004913960832732493,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.18800290077924728,
|
|
"num_tokens": 23173355.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.42010383605957,
|
|
"epoch": 0.9711815561959655,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004913866907594774,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.19660599082708358,
|
|
"num_tokens": 23185075.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.391371870040894,
|
|
"epoch": 0.9716618635926993,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004913772932218491,
|
|
"loss": 5.2601,
|
|
"mean_token_accuracy": 0.2029203936457634,
|
|
"num_tokens": 23195590.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.436680269241333,
|
|
"epoch": 0.9721421709894332,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004913678906605825,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.1935755655169487,
|
|
"num_tokens": 23207668.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.3114851951599125,
|
|
"epoch": 0.9726224783861671,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004913584830758961,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.2029471591114998,
|
|
"num_tokens": 23218497.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.471644878387451,
|
|
"epoch": 0.9731027857829011,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004913490704680081,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.18757040202617645,
|
|
"num_tokens": 23230575.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.415591669082642,
|
|
"epoch": 0.973583093179635,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004913396528371371,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.19895608425140382,
|
|
"num_tokens": 23242348.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.395736980438232,
|
|
"epoch": 0.9740634005763689,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004913302301835018,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.19757096320390702,
|
|
"num_tokens": 23253297.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.3581959247589115,
|
|
"epoch": 0.9745437079731027,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000491320802507321,
|
|
"loss": 5.2125,
|
|
"mean_token_accuracy": 0.2049126699566841,
|
|
"num_tokens": 23265830.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.357705354690552,
|
|
"epoch": 0.9750240153698367,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004913113698088133,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.19356786459684372,
|
|
"num_tokens": 23275591.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.392214441299439,
|
|
"epoch": 0.9755043227665706,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000491301932088198,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.20286039113998414,
|
|
"num_tokens": 23286685.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.369827604293823,
|
|
"epoch": 0.9759846301633045,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004912924893456942,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.20111585557460784,
|
|
"num_tokens": 23298776.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.375048875808716,
|
|
"epoch": 0.9764649375600384,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000491283041581521,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.1966169446706772,
|
|
"num_tokens": 23310498.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.399423742294312,
|
|
"epoch": 0.9769452449567724,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004912735887958978,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.195260588824749,
|
|
"num_tokens": 23321089.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.412667226791382,
|
|
"epoch": 0.9774255523535063,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004912641309890441,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.19705213457345963,
|
|
"num_tokens": 23332142.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.358434724807739,
|
|
"epoch": 0.9779058597502401,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004912546681611794,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.2035938933491707,
|
|
"num_tokens": 23343014.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.356276416778565,
|
|
"epoch": 0.978386167146974,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004912452003125234,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.2011845201253891,
|
|
"num_tokens": 23354611.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.375174903869629,
|
|
"epoch": 0.978866474543708,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000491235727443296,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.1941805824637413,
|
|
"num_tokens": 23365608.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.417257165908813,
|
|
"epoch": 0.9793467819404419,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004912262495537171,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.19640244841575621,
|
|
"num_tokens": 23377884.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.319071435928345,
|
|
"epoch": 0.9798270893371758,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004912167666440068,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.19503784626722337,
|
|
"num_tokens": 23389553.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.344862031936645,
|
|
"epoch": 0.9803073967339097,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004912072787143852,
|
|
"loss": 5.169,
|
|
"mean_token_accuracy": 0.195979243516922,
|
|
"num_tokens": 23401079.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.341659212112427,
|
|
"epoch": 0.9807877041306436,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004911977857650725,
|
|
"loss": 5.2333,
|
|
"mean_token_accuracy": 0.1943848967552185,
|
|
"num_tokens": 23412886.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.4430173397064205,
|
|
"epoch": 0.9812680115273775,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004911882877962893,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.19466811865568162,
|
|
"num_tokens": 23424758.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.338826704025268,
|
|
"epoch": 0.9817483189241114,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004911787848082559,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.20620550960302353,
|
|
"num_tokens": 23435552.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.280716180801392,
|
|
"epoch": 0.9822286263208453,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004911692768011931,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.20014816224575044,
|
|
"num_tokens": 23446584.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.44210524559021,
|
|
"epoch": 0.9827089337175793,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004911597637753217,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.1842656821012497,
|
|
"num_tokens": 23458452.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.408960008621216,
|
|
"epoch": 0.9831892411143132,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004911502457308623,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.19283388555049896,
|
|
"num_tokens": 23470310.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.42606520652771,
|
|
"epoch": 0.983669548511047,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000491140722668036,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.19637373685836793,
|
|
"num_tokens": 23481166.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.41834397315979,
|
|
"epoch": 0.984149855907781,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000491131194587064,
|
|
"loss": 5.2749,
|
|
"mean_token_accuracy": 0.19855717122554778,
|
|
"num_tokens": 23493134.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.328420972824096,
|
|
"epoch": 0.9846301633045149,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004911216614881675,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.1988489121198654,
|
|
"num_tokens": 23504983.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.389592123031616,
|
|
"epoch": 0.9851104707012488,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004911121233715677,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.19755271226167678,
|
|
"num_tokens": 23516119.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.463020277023316,
|
|
"epoch": 0.9855907780979827,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004911025802374861,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.1930815413594246,
|
|
"num_tokens": 23528242.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.365986776351929,
|
|
"epoch": 0.9860710854947167,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004910930320861442,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.20747936964035035,
|
|
"num_tokens": 23539738.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.2247661590576175,
|
|
"epoch": 0.9865513928914506,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004910834789177639,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.2057154133915901,
|
|
"num_tokens": 23551228.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.445699024200439,
|
|
"epoch": 0.9870317002881844,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004910739207325668,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.20087556540966034,
|
|
"num_tokens": 23563084.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.434138298034668,
|
|
"epoch": 0.9875120076849183,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004910643575307749,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.19552823156118393,
|
|
"num_tokens": 23574328.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.278770446777344,
|
|
"epoch": 0.9879923150816523,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004910547893126102,
|
|
"loss": 5.1987,
|
|
"mean_token_accuracy": 0.1975170463323593,
|
|
"num_tokens": 23585230.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.326727247238159,
|
|
"epoch": 0.9884726224783862,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004910452160782948,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.19465228021144867,
|
|
"num_tokens": 23596951.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.455601215362549,
|
|
"epoch": 0.9889529298751201,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000491035637828051,
|
|
"loss": 5.2505,
|
|
"mean_token_accuracy": 0.20382542461156844,
|
|
"num_tokens": 23607759.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.409031343460083,
|
|
"epoch": 0.989433237271854,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004910260545621012,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.19009001851081847,
|
|
"num_tokens": 23619631.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.362862920761108,
|
|
"epoch": 0.9899135446685879,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004910164662806679,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.20407866090536117,
|
|
"num_tokens": 23630601.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.374560165405273,
|
|
"epoch": 0.9903938520653218,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004910068729839736,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.20355131328105927,
|
|
"num_tokens": 23641330.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.386803245544433,
|
|
"epoch": 0.9908741594620557,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004909972746722413,
|
|
"loss": 5.2623,
|
|
"mean_token_accuracy": 0.19177590310573578,
|
|
"num_tokens": 23651492.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.316884517669678,
|
|
"epoch": 0.9913544668587896,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004909876713456935,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.19862142354249954,
|
|
"num_tokens": 23661773.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.344232273101807,
|
|
"epoch": 0.9918347742555236,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004909780630045534,
|
|
"loss": 5.2041,
|
|
"mean_token_accuracy": 0.1977642372250557,
|
|
"num_tokens": 23673534.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.420243787765503,
|
|
"epoch": 0.9923150816522575,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000490968449649044,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.19253074675798415,
|
|
"num_tokens": 23684892.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.43662052154541,
|
|
"epoch": 0.9927953890489913,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004909588312793884,
|
|
"loss": 5.2844,
|
|
"mean_token_accuracy": 0.19027261286973954,
|
|
"num_tokens": 23696076.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.44582724571228,
|
|
"epoch": 0.9932756964457252,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004909492078958101,
|
|
"loss": 5.2803,
|
|
"mean_token_accuracy": 0.19569143950939177,
|
|
"num_tokens": 23707795.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.394563102722168,
|
|
"epoch": 0.9937560038424592,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004909395794985324,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.1983860120177269,
|
|
"num_tokens": 23720802.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.385411500930786,
|
|
"epoch": 0.9942363112391931,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004909299460877788,
|
|
"loss": 5.2243,
|
|
"mean_token_accuracy": 0.19454858750104903,
|
|
"num_tokens": 23732854.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.432509183883667,
|
|
"epoch": 0.994716618635927,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004909203076637732,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.18953678011894226,
|
|
"num_tokens": 23743593.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.425855255126953,
|
|
"epoch": 0.9951969260326609,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004909106642267392,
|
|
"loss": 5.2828,
|
|
"mean_token_accuracy": 0.1890368193387985,
|
|
"num_tokens": 23755447.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.391558885574341,
|
|
"epoch": 0.9956772334293948,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004909010157769006,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.19220681935548783,
|
|
"num_tokens": 23767181.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.459505701065064,
|
|
"epoch": 0.9961575408261287,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004908913623144814,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.18672704845666885,
|
|
"num_tokens": 23776356.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.407767581939697,
|
|
"epoch": 0.9966378482228626,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000490881703839706,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.19368094354867935,
|
|
"num_tokens": 23787965.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.298969841003418,
|
|
"epoch": 0.9971181556195965,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004908720403527984,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.20529055297374726,
|
|
"num_tokens": 23800327.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.350721836090088,
|
|
"epoch": 0.9975984630163305,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000490862371853983,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.19606084525585174,
|
|
"num_tokens": 23812845.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.495653438568115,
|
|
"epoch": 0.9980787704130644,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004908526983434844,
|
|
"loss": 5.3329,
|
|
"mean_token_accuracy": 0.18945523351430893,
|
|
"num_tokens": 23824831.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.385914611816406,
|
|
"epoch": 0.9985590778097982,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000490843019821527,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.20086916983127595,
|
|
"num_tokens": 23836697.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.328553867340088,
|
|
"epoch": 0.9990393852065321,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004908333362883358,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.20100513249635696,
|
|
"num_tokens": 23847112.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.443840217590332,
|
|
"epoch": 0.9995196926032661,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004908236477441353,
|
|
"loss": 5.3105,
|
|
"mean_token_accuracy": 0.19728704988956453,
|
|
"num_tokens": 23858185.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.292560720443726,
|
|
"epoch": 1.0,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004908139541891505,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.20787130445241928,
|
|
"num_tokens": 23868536.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.435236978530884,
|
|
"epoch": 1.0004803073967339,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004908042556236066,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.20785519182682038,
|
|
"num_tokens": 23880283.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.4062717914581295,
|
|
"epoch": 1.0009606147934678,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004907945520477286,
|
|
"loss": 5.2264,
|
|
"mean_token_accuracy": 0.19787705838680267,
|
|
"num_tokens": 23892413.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.41930193901062,
|
|
"epoch": 1.0014409221902016,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004907848434617419,
|
|
"loss": 5.3167,
|
|
"mean_token_accuracy": 0.1875617653131485,
|
|
"num_tokens": 23903977.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.423424100875854,
|
|
"epoch": 1.0019212295869357,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000490775129865872,
|
|
"loss": 5.2751,
|
|
"mean_token_accuracy": 0.18869033455848694,
|
|
"num_tokens": 23915153.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.366645860671997,
|
|
"epoch": 1.0024015369836696,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004907654112603442,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.19909880310297012,
|
|
"num_tokens": 23926043.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.2599043369293215,
|
|
"epoch": 1.0028818443804035,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004907556876453843,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.20281803011894226,
|
|
"num_tokens": 23936658.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.371670436859131,
|
|
"epoch": 1.0033621517771374,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000490745959021218,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.1904056116938591,
|
|
"num_tokens": 23947676.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.426939535140991,
|
|
"epoch": 1.0038424591738713,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004907362253880711,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.19587726891040802,
|
|
"num_tokens": 23959130.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.432654142379761,
|
|
"epoch": 1.0043227665706052,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004907264867461697,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.19331410825252532,
|
|
"num_tokens": 23969905.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.304448175430298,
|
|
"epoch": 1.004803073967339,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004907167430957399,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.20084474980831146,
|
|
"num_tokens": 23982016.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.395643186569214,
|
|
"epoch": 1.005283381364073,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004907069944370077,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.1919062003493309,
|
|
"num_tokens": 23994200.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.480698490142823,
|
|
"epoch": 1.005763688760807,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004906972407701998,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.2071074828505516,
|
|
"num_tokens": 24004695.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.304565954208374,
|
|
"epoch": 1.006243996157541,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004906874820955423,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.20207276046276093,
|
|
"num_tokens": 24015922.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.292526960372925,
|
|
"epoch": 1.0067243035542748,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004906777184132621,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.19816240072250366,
|
|
"num_tokens": 24026759.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.412112998962402,
|
|
"epoch": 1.0072046109510087,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004906679497235856,
|
|
"loss": 5.2203,
|
|
"mean_token_accuracy": 0.18899215310811995,
|
|
"num_tokens": 24037988.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.412247896194458,
|
|
"epoch": 1.0076849183477425,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004906581760267397,
|
|
"loss": 5.2561,
|
|
"mean_token_accuracy": 0.20096997916698456,
|
|
"num_tokens": 24050837.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.337458801269531,
|
|
"epoch": 1.0081652257444764,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004906483973229513,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.1990055963397026,
|
|
"num_tokens": 24063085.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.315743684768677,
|
|
"epoch": 1.0086455331412103,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004906386136124476,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.19925360530614852,
|
|
"num_tokens": 24074082.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.446903562545776,
|
|
"epoch": 1.0091258405379442,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004906288248954554,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.19767555147409438,
|
|
"num_tokens": 24085050.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.3743712425231935,
|
|
"epoch": 1.0096061479346783,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004906190311722023,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.2029238983988762,
|
|
"num_tokens": 24095523.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.280368709564209,
|
|
"epoch": 1.0100864553314122,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004906092324429155,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.1979474738240242,
|
|
"num_tokens": 24107157.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.427689743041992,
|
|
"epoch": 1.010566762728146,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004905994287078227,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.20026973634958267,
|
|
"num_tokens": 24118668.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.384921646118164,
|
|
"epoch": 1.01104707012488,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004905896199671512,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.19712361097335815,
|
|
"num_tokens": 24129563.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.439377784729004,
|
|
"epoch": 1.0115273775216138,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000490579806221129,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.18765364736318588,
|
|
"num_tokens": 24139965.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.419678449630737,
|
|
"epoch": 1.0120076849183477,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004905699874699838,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.19088760316371917,
|
|
"num_tokens": 24152109.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.350772714614868,
|
|
"epoch": 1.0124879923150816,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004905601637139436,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.19320061057806015,
|
|
"num_tokens": 24162558.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.310645484924317,
|
|
"epoch": 1.0129682997118155,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004905503349532365,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.20582576990127563,
|
|
"num_tokens": 24173963.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.311681890487671,
|
|
"epoch": 1.0134486071085496,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004905405011880906,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.20559390634298325,
|
|
"num_tokens": 24184369.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.458524513244629,
|
|
"epoch": 1.0139289145052834,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004905306624187343,
|
|
"loss": 5.2659,
|
|
"mean_token_accuracy": 0.19492665827274322,
|
|
"num_tokens": 24194692.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.387073612213134,
|
|
"epoch": 1.0144092219020173,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004905208186453961,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.19798000305891036,
|
|
"num_tokens": 24205363.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.377963972091675,
|
|
"epoch": 1.0148895292987512,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004905109698683044,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.19431522041559218,
|
|
"num_tokens": 24216678.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.304928827285766,
|
|
"epoch": 1.015369836695485,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004905011160876878,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.19902242720127106,
|
|
"num_tokens": 24227541.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.420691347122192,
|
|
"epoch": 1.015850144092219,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004904912573037753,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.20176420211791993,
|
|
"num_tokens": 24238118.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.370762825012207,
|
|
"epoch": 1.0163304514889528,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004904813935167957,
|
|
"loss": 5.2659,
|
|
"mean_token_accuracy": 0.1881776973605156,
|
|
"num_tokens": 24250044.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.399740934371948,
|
|
"epoch": 1.0168107588856867,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004904715247269779,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.18685061484575272,
|
|
"num_tokens": 24262805.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.40922179222107,
|
|
"epoch": 1.0172910662824208,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004904616509345514,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.1913820043206215,
|
|
"num_tokens": 24274287.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.275315380096435,
|
|
"epoch": 1.0177713736791547,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004904517721397449,
|
|
"loss": 5.0897,
|
|
"mean_token_accuracy": 0.20330840349197388,
|
|
"num_tokens": 24284839.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.315784740447998,
|
|
"epoch": 1.0182516810758886,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004904418883427881,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.19757491052150727,
|
|
"num_tokens": 24295812.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.369445419311523,
|
|
"epoch": 1.0187319884726225,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004904319995439104,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.20506100803613664,
|
|
"num_tokens": 24306365.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.341662502288818,
|
|
"epoch": 1.0192122958693564,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004904221057433412,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.19272904247045516,
|
|
"num_tokens": 24317557.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.304598140716553,
|
|
"epoch": 1.0196926032660902,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004904122069413105,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.20127242654561997,
|
|
"num_tokens": 24328874.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.456245756149292,
|
|
"epoch": 1.0201729106628241,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000490402303138048,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.18897756338119506,
|
|
"num_tokens": 24340918.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.465630102157593,
|
|
"epoch": 1.0206532180595582,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004903923943337836,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.19590210765600205,
|
|
"num_tokens": 24352642.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.357732105255127,
|
|
"epoch": 1.021133525456292,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004903824805287475,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.20546759963035582,
|
|
"num_tokens": 24364874.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.323757553100586,
|
|
"epoch": 1.021613832853026,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004903725617231696,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.19685495942831038,
|
|
"num_tokens": 24376566.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.346426725387573,
|
|
"epoch": 1.0220941402497599,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004903626379172805,
|
|
"loss": 5.0553,
|
|
"mean_token_accuracy": 0.20748411118984222,
|
|
"num_tokens": 24387283.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.438922548294068,
|
|
"epoch": 1.0225744476464937,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004903527091113102,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.19447067081928254,
|
|
"num_tokens": 24397970.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.368396377563476,
|
|
"epoch": 1.0230547550432276,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004903427753054897,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.19714905321598053,
|
|
"num_tokens": 24411223.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.396991777420044,
|
|
"epoch": 1.0235350624399615,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004903328365000492,
|
|
"loss": 5.2223,
|
|
"mean_token_accuracy": 0.1944411039352417,
|
|
"num_tokens": 24422117.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.358843660354614,
|
|
"epoch": 1.0240153698366954,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004903228926952199,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.19198838472366334,
|
|
"num_tokens": 24434142.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.329892301559449,
|
|
"epoch": 1.0244956772334295,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004903129438912322,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.20412420481443405,
|
|
"num_tokens": 24445295.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.322643995285034,
|
|
"epoch": 1.0249759846301634,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004903029900883174,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.20376460403203964,
|
|
"num_tokens": 24456092.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.410270166397095,
|
|
"epoch": 1.0254562920268973,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004902930312867063,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.18903751224279403,
|
|
"num_tokens": 24467653.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.434236717224121,
|
|
"epoch": 1.0259365994236311,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004902830674866306,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.1995964840054512,
|
|
"num_tokens": 24479164.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.330602598190308,
|
|
"epoch": 1.026416906820365,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004902730986883211,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.20510244518518447,
|
|
"num_tokens": 24489785.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.3588080406188965,
|
|
"epoch": 1.026897214217099,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004902631248920096,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.20333358347415925,
|
|
"num_tokens": 24500158.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.417629766464233,
|
|
"epoch": 1.0273775216138328,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004902531460979274,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.18919293582439423,
|
|
"num_tokens": 24512851.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.436899328231812,
|
|
"epoch": 1.0278578290105667,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004902431623063065,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.19824332892894744,
|
|
"num_tokens": 24524016.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.261787366867066,
|
|
"epoch": 1.0283381364073008,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004902331735173785,
|
|
"loss": 5.1304,
|
|
"mean_token_accuracy": 0.19517125487327575,
|
|
"num_tokens": 24536348.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.261876392364502,
|
|
"epoch": 1.0288184438040346,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004902231797313752,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.19755610972642898,
|
|
"num_tokens": 24548718.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.329359483718872,
|
|
"epoch": 1.0292987512007685,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004902131809485288,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.21024449169635773,
|
|
"num_tokens": 24560567.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.382399082183838,
|
|
"epoch": 1.0297790585975024,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004902031771690713,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.20265196710824968,
|
|
"num_tokens": 24572610.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.350890302658081,
|
|
"epoch": 1.0302593659942363,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004901931683932352,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.19585792869329452,
|
|
"num_tokens": 24584738.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.354901123046875,
|
|
"epoch": 1.0307396733909702,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004901831546212526,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.19840895384550095,
|
|
"num_tokens": 24596603.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.320991373062133,
|
|
"epoch": 1.031219980787704,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004901731358533562,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.2013448879122734,
|
|
"num_tokens": 24607061.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.304887819290161,
|
|
"epoch": 1.031700288184438,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004901631120897785,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.20006772726774216,
|
|
"num_tokens": 24619177.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.320425033569336,
|
|
"epoch": 1.032180595581172,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004901530833307522,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.20181941986083984,
|
|
"num_tokens": 24631336.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.309013700485229,
|
|
"epoch": 1.032660902977906,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004901430495765103,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.20650936663150787,
|
|
"num_tokens": 24641743.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.358404350280762,
|
|
"epoch": 1.0331412103746398,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004901330108272855,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.20354704409837723,
|
|
"num_tokens": 24652318.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.31702880859375,
|
|
"epoch": 1.0336215177713737,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004901229670833111,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.19503468424081802,
|
|
"num_tokens": 24664129.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.380639696121216,
|
|
"epoch": 1.0341018251681076,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004901129183448201,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.1994999513030052,
|
|
"num_tokens": 24674921.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.351299571990967,
|
|
"epoch": 1.0345821325648414,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004901028646120459,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.19835921823978425,
|
|
"num_tokens": 24686052.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.356468725204468,
|
|
"epoch": 1.0350624399615753,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000490092805885222,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.20404745638370514,
|
|
"num_tokens": 24698625.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.366477060317993,
|
|
"epoch": 1.0355427473583094,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004900827421645816,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.20705388933420182,
|
|
"num_tokens": 24709322.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.238262605667114,
|
|
"epoch": 1.0360230547550433,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004900726734503589,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.20648913234472274,
|
|
"num_tokens": 24719512.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.247006034851074,
|
|
"epoch": 1.0365033621517772,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004900625997427872,
|
|
"loss": 5.1145,
|
|
"mean_token_accuracy": 0.20419507026672362,
|
|
"num_tokens": 24729947.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.283418369293213,
|
|
"epoch": 1.036983669548511,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004900525210421006,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.2116354674100876,
|
|
"num_tokens": 24741423.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.445623874664307,
|
|
"epoch": 1.037463976945245,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004900424373485329,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.1976199597120285,
|
|
"num_tokens": 24753403.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.391568040847778,
|
|
"epoch": 1.0379442843419788,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004900323486623185,
|
|
"loss": 5.2553,
|
|
"mean_token_accuracy": 0.19515856951475144,
|
|
"num_tokens": 24763660.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.39634337425232,
|
|
"epoch": 1.0384245917387127,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004900222549836914,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.20539874136447905,
|
|
"num_tokens": 24775061.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.378425741195679,
|
|
"epoch": 1.0389048991354466,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000490012156312886,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.19919242113828659,
|
|
"num_tokens": 24785248.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.268604803085327,
|
|
"epoch": 1.0393852065321807,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004900020526501369,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.2100047215819359,
|
|
"num_tokens": 24797024.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.451608514785766,
|
|
"epoch": 1.0398655139289146,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004899919439956785,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.19198151379823686,
|
|
"num_tokens": 24808500.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.465541744232178,
|
|
"epoch": 1.0403458213256485,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004899818303497455,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.19433923214673995,
|
|
"num_tokens": 24818805.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.438117647171021,
|
|
"epoch": 1.0408261287223823,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004899717117125728,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.1980220302939415,
|
|
"num_tokens": 24829247.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.301720237731933,
|
|
"epoch": 1.0413064361191162,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004899615880843953,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.20617035776376724,
|
|
"num_tokens": 24840139.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.394835042953491,
|
|
"epoch": 1.04178674351585,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004899514594654481,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.192458139359951,
|
|
"num_tokens": 24851734.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.422420835494995,
|
|
"epoch": 1.042267050912584,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004899413258559662,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.1989765375852585,
|
|
"num_tokens": 24863424.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.434455251693725,
|
|
"epoch": 1.0427473583093179,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004899311872561849,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.19243794828653335,
|
|
"num_tokens": 24875086.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.322672510147095,
|
|
"epoch": 1.043227665706052,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004899210436663398,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.1988014906644821,
|
|
"num_tokens": 24888408.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.327753591537475,
|
|
"epoch": 1.0437079731027858,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004899108950866661,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.20667046457529067,
|
|
"num_tokens": 24900357.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.40319333076477,
|
|
"epoch": 1.0441882804995197,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004899007415173997,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.2009931266307831,
|
|
"num_tokens": 24910790.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.320023822784424,
|
|
"epoch": 1.0446685878962536,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004898905829587762,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.2014652118086815,
|
|
"num_tokens": 24922124.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.275033807754516,
|
|
"epoch": 1.0451488952929875,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004898804194110313,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.20937170088291168,
|
|
"num_tokens": 24933591.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.300174331665039,
|
|
"epoch": 1.0456292026897214,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004898702508744012,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.19856639504432677,
|
|
"num_tokens": 24944708.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.2619682312011715,
|
|
"epoch": 1.0461095100864553,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004898600773491221,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.2036272794008255,
|
|
"num_tokens": 24955966.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.376646614074707,
|
|
"epoch": 1.0465898174831891,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004898498988354297,
|
|
"loss": 5.1813,
|
|
"mean_token_accuracy": 0.19692723751068114,
|
|
"num_tokens": 24967292.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.39042649269104,
|
|
"epoch": 1.0470701248799232,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004898397153335608,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.20110921412706376,
|
|
"num_tokens": 24977407.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.433729457855224,
|
|
"epoch": 1.0475504322766571,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004898295268437517,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.19937244802713394,
|
|
"num_tokens": 24988804.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.350980663299561,
|
|
"epoch": 1.048030739673391,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004898193333662388,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.1995232880115509,
|
|
"num_tokens": 25000297.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.392283821105957,
|
|
"epoch": 1.0485110470701249,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004898091349012588,
|
|
"loss": 5.1583,
|
|
"mean_token_accuracy": 0.20086133480072021,
|
|
"num_tokens": 25012135.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.337120294570923,
|
|
"epoch": 1.0489913544668588,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004897989314490486,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.2088720515370369,
|
|
"num_tokens": 25023572.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.338649129867553,
|
|
"epoch": 1.0494716618635926,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004897887230098451,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.19930736422538758,
|
|
"num_tokens": 25035015.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.372995042800904,
|
|
"epoch": 1.0499519692603265,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004897785095838852,
|
|
"loss": 5.1396,
|
|
"mean_token_accuracy": 0.19902097433805466,
|
|
"num_tokens": 25045931.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.40575098991394,
|
|
"epoch": 1.0504322766570606,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004897682911714061,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.19932707995176316,
|
|
"num_tokens": 25056767.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.306687498092652,
|
|
"epoch": 1.0509125840537945,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000489758067772645,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.20617768466472625,
|
|
"num_tokens": 25068731.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.411169052124023,
|
|
"epoch": 1.0513928914505284,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004897478393878392,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.1896729439496994,
|
|
"num_tokens": 25081268.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.304495429992675,
|
|
"epoch": 1.0518731988472623,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004897376060172264,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.20454332381486892,
|
|
"num_tokens": 25093105.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.282596778869629,
|
|
"epoch": 1.0523535062439962,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004897273676610438,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.2055801644921303,
|
|
"num_tokens": 25103766.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.380429410934449,
|
|
"epoch": 1.05283381364073,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004897171243195295,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.19875359386205674,
|
|
"num_tokens": 25115675.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.367063045501709,
|
|
"epoch": 1.053314121037464,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000489706875992921,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.19679145216941835,
|
|
"num_tokens": 25127907.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.350911712646484,
|
|
"epoch": 1.0537944284341978,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004896966226814565,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.1969701737165451,
|
|
"num_tokens": 25139675.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.401399850845337,
|
|
"epoch": 1.054274735830932,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004896863643853739,
|
|
"loss": 5.2827,
|
|
"mean_token_accuracy": 0.19578592479228973,
|
|
"num_tokens": 25150960.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.435582876205444,
|
|
"epoch": 1.0547550432276658,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004896761011049114,
|
|
"loss": 5.2484,
|
|
"mean_token_accuracy": 0.19553759098052978,
|
|
"num_tokens": 25163676.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.345992851257324,
|
|
"epoch": 1.0552353506243997,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004896658328403074,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.19865147918462753,
|
|
"num_tokens": 25174317.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.356166124343872,
|
|
"epoch": 1.0557156580211335,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004896555595918001,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.19747304618358613,
|
|
"num_tokens": 25186585.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.386865186691284,
|
|
"epoch": 1.0561959654178674,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004896452813596281,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.19755746871232988,
|
|
"num_tokens": 25199014.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.4097068309783936,
|
|
"epoch": 1.0566762728146013,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004896349981440301,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.19502251148223876,
|
|
"num_tokens": 25210544.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.404106616973877,
|
|
"epoch": 1.0571565802113352,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004896247099452447,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.20019677132368088,
|
|
"num_tokens": 25221583.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.359276819229126,
|
|
"epoch": 1.057636887608069,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004896144167635108,
|
|
"loss": 5.1692,
|
|
"mean_token_accuracy": 0.2065974220633507,
|
|
"num_tokens": 25231724.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.366830158233642,
|
|
"epoch": 1.0581171950048032,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004896041185990675,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.1952083557844162,
|
|
"num_tokens": 25243021.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.440467262268067,
|
|
"epoch": 1.058597502401537,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004895938154521538,
|
|
"loss": 5.2151,
|
|
"mean_token_accuracy": 0.19677592515945436,
|
|
"num_tokens": 25254189.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.378790712356567,
|
|
"epoch": 1.059077809798271,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004895835073230089,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.19986312836408615,
|
|
"num_tokens": 25265556.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.276179027557373,
|
|
"epoch": 1.0595581171950048,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004895731942118722,
|
|
"loss": 5.0815,
|
|
"mean_token_accuracy": 0.19784061163663863,
|
|
"num_tokens": 25276789.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.368158769607544,
|
|
"epoch": 1.0600384245917387,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004895628761189829,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.19195080697536468,
|
|
"num_tokens": 25288505.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.3320859432220455,
|
|
"epoch": 1.0605187319884726,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004895525530445809,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.21157157123088838,
|
|
"num_tokens": 25301490.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.355728483200073,
|
|
"epoch": 1.0609990393852065,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004895422249889057,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.1939198449254036,
|
|
"num_tokens": 25313303.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.462080717086792,
|
|
"epoch": 1.0614793467819403,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004895318919521971,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.18565141558647155,
|
|
"num_tokens": 25324379.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.311128091812134,
|
|
"epoch": 1.0619596541786744,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004895215539346949,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.20124406069517137,
|
|
"num_tokens": 25335834.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.274025201797485,
|
|
"epoch": 1.0624399615754083,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004895112109366393,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.19837718158960344,
|
|
"num_tokens": 25347591.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.379197502136231,
|
|
"epoch": 1.0629202689721422,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004895008629582703,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.19955977648496628,
|
|
"num_tokens": 25358483.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.356401252746582,
|
|
"epoch": 1.063400576368876,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004894905099998283,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.1960717409849167,
|
|
"num_tokens": 25369434.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.312747764587402,
|
|
"epoch": 1.06388088376561,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004894801520615535,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.1999019891023636,
|
|
"num_tokens": 25381007.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.354256200790405,
|
|
"epoch": 1.0643611911623438,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004894697891436863,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.19543883353471755,
|
|
"num_tokens": 25393809.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.392571353912354,
|
|
"epoch": 1.0648414985590777,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004894594212464676,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.19979428946971894,
|
|
"num_tokens": 25404967.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.353606224060059,
|
|
"epoch": 1.0653218059558118,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004894490483701381,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.21081098914146423,
|
|
"num_tokens": 25417092.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.3749908924102785,
|
|
"epoch": 1.0658021133525457,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004894386705149382,
|
|
"loss": 5.2471,
|
|
"mean_token_accuracy": 0.19123061150312423,
|
|
"num_tokens": 25428425.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.3272566318511965,
|
|
"epoch": 1.0662824207492796,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004894282876811093,
|
|
"loss": 5.0902,
|
|
"mean_token_accuracy": 0.20587802231311797,
|
|
"num_tokens": 25440134.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.277375268936157,
|
|
"epoch": 1.0667627281460135,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004894178998688921,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.20245763063430786,
|
|
"num_tokens": 25452222.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.3369011878967285,
|
|
"epoch": 1.0672430355427474,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004894075070785281,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.19930659383535385,
|
|
"num_tokens": 25464541.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.442348051071167,
|
|
"epoch": 1.0677233429394812,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004893971093102585,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.18957502394914627,
|
|
"num_tokens": 25476537.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.399827194213867,
|
|
"epoch": 1.0682036503362151,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004893867065643245,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.19005922377109527,
|
|
"num_tokens": 25486737.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.307654809951782,
|
|
"epoch": 1.068683957732949,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004893762988409678,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.19470080137252807,
|
|
"num_tokens": 25497278.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.367532730102539,
|
|
"epoch": 1.069164265129683,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004893658861404301,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.1909480333328247,
|
|
"num_tokens": 25508716.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.4374596118927006,
|
|
"epoch": 1.069644572526417,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004893554684629529,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.1901407927274704,
|
|
"num_tokens": 25519439.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.334210538864136,
|
|
"epoch": 1.0701248799231509,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004893450458087784,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.2050735205411911,
|
|
"num_tokens": 25530911.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.407543706893921,
|
|
"epoch": 1.0706051873198847,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004893346181781483,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.18421210050582887,
|
|
"num_tokens": 25542452.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.414454364776612,
|
|
"epoch": 1.0710854947166186,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004893241855713048,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.18724402636289597,
|
|
"num_tokens": 25554105.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.476910924911499,
|
|
"epoch": 1.0715658021133525,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004893137479884903,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.1946733772754669,
|
|
"num_tokens": 25564806.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.314055728912353,
|
|
"epoch": 1.0720461095100864,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004893033054299468,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.2048540711402893,
|
|
"num_tokens": 25575664.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.308312225341797,
|
|
"epoch": 1.0725264169068203,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000489292857895917,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.2044521987438202,
|
|
"num_tokens": 25586227.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.41708779335022,
|
|
"epoch": 1.0730067243035544,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004892824053866432,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.19560645669698715,
|
|
"num_tokens": 25597475.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.322979593276978,
|
|
"epoch": 1.0734870317002883,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004892719479023683,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.2073204532265663,
|
|
"num_tokens": 25608098.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.379103708267212,
|
|
"epoch": 1.0739673390970221,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000489261485443335,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.1946496918797493,
|
|
"num_tokens": 25620053.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.421007204055786,
|
|
"epoch": 1.074447646493756,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004892510180097863,
|
|
"loss": 5.1509,
|
|
"mean_token_accuracy": 0.19677818268537522,
|
|
"num_tokens": 25630534.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.391182947158813,
|
|
"epoch": 1.07492795389049,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004892405456019651,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.2003046229481697,
|
|
"num_tokens": 25641413.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.245150375366211,
|
|
"epoch": 1.0754082612872238,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004892300682201147,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.20695517361164092,
|
|
"num_tokens": 25652081.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.382082080841064,
|
|
"epoch": 1.0758885686839577,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004892195858644782,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.20351504981517793,
|
|
"num_tokens": 25664282.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.4394091129302975,
|
|
"epoch": 1.0763688760806915,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000489209098535299,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.19555938839912415,
|
|
"num_tokens": 25675310.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.484385681152344,
|
|
"epoch": 1.0768491834774256,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004891986062328205,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.19938010424375535,
|
|
"num_tokens": 25686895.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.3427972316741945,
|
|
"epoch": 1.0773294908741595,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004891881089572865,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.20346538573503495,
|
|
"num_tokens": 25697778.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.324303340911865,
|
|
"epoch": 1.0778097982708934,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004891776067089406,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.1929355412721634,
|
|
"num_tokens": 25708602.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.370334243774414,
|
|
"epoch": 1.0782901056676273,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004891670994880266,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.2028239846229553,
|
|
"num_tokens": 25719671.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.433915042877198,
|
|
"epoch": 1.0787704130643612,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004891565872947888,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.1901620402932167,
|
|
"num_tokens": 25731797.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.309804010391235,
|
|
"epoch": 1.079250720461095,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004891460701294706,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.19942902475595475,
|
|
"num_tokens": 25743984.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.286370277404785,
|
|
"epoch": 1.079731027857829,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004891355479923167,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.19926074594259263,
|
|
"num_tokens": 25755252.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.301422739028931,
|
|
"epoch": 1.080211335254563,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004891250208835712,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.19988674074411392,
|
|
"num_tokens": 25765715.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.4079889297485355,
|
|
"epoch": 1.080691642651297,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004891144888034784,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.19131870567798615,
|
|
"num_tokens": 25777866.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.352594518661499,
|
|
"epoch": 1.0811719500480308,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004891039517522832,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.20011763870716096,
|
|
"num_tokens": 25791199.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.255130672454834,
|
|
"epoch": 1.0816522574447647,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004890934097302299,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.2159181520342827,
|
|
"num_tokens": 25802979.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.242046928405761,
|
|
"epoch": 1.0821325648414986,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004890828627375632,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.20288678854703904,
|
|
"num_tokens": 25814696.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.337868499755859,
|
|
"epoch": 1.0826128722382324,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004890723107745283,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.1878681883215904,
|
|
"num_tokens": 25825376.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.377805423736572,
|
|
"epoch": 1.0830931796349663,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004890617538413699,
|
|
"loss": 5.1553,
|
|
"mean_token_accuracy": 0.19813374280929566,
|
|
"num_tokens": 25835491.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.4203550815582275,
|
|
"epoch": 1.0835734870317002,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004890511919383333,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.1960090294480324,
|
|
"num_tokens": 25848154.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.368510389328003,
|
|
"epoch": 1.084053794428434,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004890406250656636,
|
|
"loss": 5.1895,
|
|
"mean_token_accuracy": 0.19684653133153915,
|
|
"num_tokens": 25859471.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.373747444152832,
|
|
"epoch": 1.0845341018251682,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004890300532236062,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.20310529917478562,
|
|
"num_tokens": 25869460.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.368363380432129,
|
|
"epoch": 1.085014409221902,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004890194764124064,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.20217566788196564,
|
|
"num_tokens": 25881892.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.36700291633606,
|
|
"epoch": 1.085494716618636,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004890088946323099,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.1901961624622345,
|
|
"num_tokens": 25893774.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.3004192352294925,
|
|
"epoch": 1.0859750240153698,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004889983078835623,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.2001173973083496,
|
|
"num_tokens": 25904758.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.355261278152466,
|
|
"epoch": 1.0864553314121037,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004889877161664096,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.19506046622991563,
|
|
"num_tokens": 25917013.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.470705032348633,
|
|
"epoch": 1.0869356388088376,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004889771194810974,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.19948432594537735,
|
|
"num_tokens": 25927780.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.26608452796936,
|
|
"epoch": 1.0874159462055715,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004889665178278719,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.20162168890237808,
|
|
"num_tokens": 25939339.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.323513793945312,
|
|
"epoch": 1.0878962536023056,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004889559112069792,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.2076476275920868,
|
|
"num_tokens": 25950440.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.401596450805664,
|
|
"epoch": 1.0883765609990395,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004889452996186657,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.19381099045276642,
|
|
"num_tokens": 25962849.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.310946369171143,
|
|
"epoch": 1.0888568683957733,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004889346830631774,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.19960491508245468,
|
|
"num_tokens": 25973616.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.304806518554687,
|
|
"epoch": 1.0893371757925072,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000488924061540761,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.20609148293733598,
|
|
"num_tokens": 25984727.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.3581455707550045,
|
|
"epoch": 1.089817483189241,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004889134350516633,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.19956897497177123,
|
|
"num_tokens": 25996431.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.382833862304688,
|
|
"epoch": 1.090297790585975,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004889028035961308,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.20036507546901702,
|
|
"num_tokens": 26008936.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.424931526184082,
|
|
"epoch": 1.0907780979827089,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004888921671744103,
|
|
"loss": 5.2278,
|
|
"mean_token_accuracy": 0.19489723294973374,
|
|
"num_tokens": 26019308.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.370683240890503,
|
|
"epoch": 1.0912584053794427,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004888815257867488,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.2062639430165291,
|
|
"num_tokens": 26030705.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.318453216552735,
|
|
"epoch": 1.0917387127761768,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004888708794333934,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.2029062792658806,
|
|
"num_tokens": 26042759.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.343652439117432,
|
|
"epoch": 1.0922190201729107,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004888602281145913,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.1968962162733078,
|
|
"num_tokens": 26054719.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.369729948043823,
|
|
"epoch": 1.0926993275696446,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004888495718305897,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.19347385168075562,
|
|
"num_tokens": 26065765.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.280622959136963,
|
|
"epoch": 1.0931796349663785,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000488838910581636,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.20374534130096436,
|
|
"num_tokens": 26077719.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.352468585968017,
|
|
"epoch": 1.0936599423631124,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004888282443679777,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.19052414000034332,
|
|
"num_tokens": 26089924.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.5069104671478275,
|
|
"epoch": 1.0941402497598463,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004888175731898627,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.18762553185224534,
|
|
"num_tokens": 26100312.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.3536378860473635,
|
|
"epoch": 1.0946205571565801,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004888068970475384,
|
|
"loss": 5.2153,
|
|
"mean_token_accuracy": 0.19696459472179412,
|
|
"num_tokens": 26111932.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.354318857192993,
|
|
"epoch": 1.0951008645533142,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004887962159412529,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.2008897542953491,
|
|
"num_tokens": 26123989.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.422485828399658,
|
|
"epoch": 1.0955811719500481,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004887855298712541,
|
|
"loss": 5.2284,
|
|
"mean_token_accuracy": 0.1971900701522827,
|
|
"num_tokens": 26135589.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.249070072174073,
|
|
"epoch": 1.096061479346782,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048877483883779,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.20677980184555053,
|
|
"num_tokens": 26147069.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.283880949020386,
|
|
"epoch": 1.0965417867435159,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004887641428411091,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.19866887480020523,
|
|
"num_tokens": 26159331.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.4083091735839846,
|
|
"epoch": 1.0970220941402498,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004887534418814595,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.200238499045372,
|
|
"num_tokens": 26169863.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.3809222221374515,
|
|
"epoch": 1.0975024015369836,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004887427359590897,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.19337329715490342,
|
|
"num_tokens": 26182888.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.347376680374145,
|
|
"epoch": 1.0979827089337175,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004887320250742482,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.20518355220556259,
|
|
"num_tokens": 26194979.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.29439754486084,
|
|
"epoch": 1.0984630163304514,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004887213092271838,
|
|
"loss": 5.1715,
|
|
"mean_token_accuracy": 0.20823599994182587,
|
|
"num_tokens": 26207309.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.377480602264404,
|
|
"epoch": 1.0989433237271853,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004887105884181451,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.19874830096960067,
|
|
"num_tokens": 26219231.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.430906915664673,
|
|
"epoch": 1.0994236311239194,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004886998626473813,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.19606766551733018,
|
|
"num_tokens": 26229355.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.344922113418579,
|
|
"epoch": 1.0999039385206533,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004886891319151411,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.20009531527757646,
|
|
"num_tokens": 26239069.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.350154209136963,
|
|
"epoch": 1.1003842459173871,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004886783962216738,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.1945774257183075,
|
|
"num_tokens": 26250403.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.361779069900512,
|
|
"epoch": 1.100864553314121,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004886676555672287,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.19954846948385238,
|
|
"num_tokens": 26262926.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.453261375427246,
|
|
"epoch": 1.101344860710855,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004886569099520551,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.1885857418179512,
|
|
"num_tokens": 26274030.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.322421884536743,
|
|
"epoch": 1.1018251681075888,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004886461593764024,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.2093471556901932,
|
|
"num_tokens": 26284799.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.2471343040466305,
|
|
"epoch": 1.1023054755043227,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004886354038405204,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.20640188008546828,
|
|
"num_tokens": 26295154.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.391257238388062,
|
|
"epoch": 1.1027857829010568,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004886246433446586,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.1964474469423294,
|
|
"num_tokens": 26306181.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.444426679611206,
|
|
"epoch": 1.1032660902977907,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004886138778890669,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.18726618140935897,
|
|
"num_tokens": 26318674.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.421746253967285,
|
|
"epoch": 1.1037463976945245,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004886031074739953,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.18897231817245483,
|
|
"num_tokens": 26330257.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.390989160537719,
|
|
"epoch": 1.1042267050912584,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004885923320996938,
|
|
"loss": 5.169,
|
|
"mean_token_accuracy": 0.19159701019525527,
|
|
"num_tokens": 26342035.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.341862297058105,
|
|
"epoch": 1.1047070124879923,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004885815517664127,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.19595280289649963,
|
|
"num_tokens": 26352703.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.36245288848877,
|
|
"epoch": 1.1051873198847262,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000488570766474402,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.2024245485663414,
|
|
"num_tokens": 26362324.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.395856332778931,
|
|
"epoch": 1.10566762728146,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004885599762239124,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.18966627717018128,
|
|
"num_tokens": 26373540.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.355940246582032,
|
|
"epoch": 1.106147934678194,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004885491810151943,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.20222342163324356,
|
|
"num_tokens": 26384259.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.283168792724609,
|
|
"epoch": 1.106628242074928,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004885383808484982,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.20647242665290833,
|
|
"num_tokens": 26395193.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.330464506149292,
|
|
"epoch": 1.107108549471662,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004885275757240751,
|
|
"loss": 5.1204,
|
|
"mean_token_accuracy": 0.2024265706539154,
|
|
"num_tokens": 26408556.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.316191673278809,
|
|
"epoch": 1.1075888568683958,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004885167656421757,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.20303579270839692,
|
|
"num_tokens": 26420066.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.339257431030274,
|
|
"epoch": 1.1080691642651297,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000488505950603051,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.20111494809389113,
|
|
"num_tokens": 26432533.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.336350202560425,
|
|
"epoch": 1.1085494716618636,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000488495130606952,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.20029998570680618,
|
|
"num_tokens": 26443878.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.358038806915284,
|
|
"epoch": 1.1090297790585975,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004884843056541302,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.19885462075471877,
|
|
"num_tokens": 26455111.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.359009742736816,
|
|
"epoch": 1.1095100864553313,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004884734757448367,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.20248016119003295,
|
|
"num_tokens": 26466577.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.332743501663208,
|
|
"epoch": 1.1099903938520654,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000488462640879323,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.19827953726053238,
|
|
"num_tokens": 26479637.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.310396337509156,
|
|
"epoch": 1.1104707012487993,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004884518010578405,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.20312774926424026,
|
|
"num_tokens": 26489923.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.437951564788818,
|
|
"epoch": 1.1109510086455332,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004884409562806411,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.19573938846588135,
|
|
"num_tokens": 26501236.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.3305095672607425,
|
|
"epoch": 1.111431316042267,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004884301065479765,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.20193921029567719,
|
|
"num_tokens": 26511509.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.274600315093994,
|
|
"epoch": 1.111911623439001,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004884192518600986,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.21048857867717743,
|
|
"num_tokens": 26520931.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.238495635986328,
|
|
"epoch": 1.1123919308357348,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004884083922172593,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.21290600448846816,
|
|
"num_tokens": 26531333.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.324881172180175,
|
|
"epoch": 1.1128722382324687,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004883975276197108,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.2006787285208702,
|
|
"num_tokens": 26543696.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.352763605117798,
|
|
"epoch": 1.1133525456292026,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004883866580677055,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.2044229879975319,
|
|
"num_tokens": 26556292.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.376569938659668,
|
|
"epoch": 1.1138328530259365,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004883757835614956,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.19124004989862442,
|
|
"num_tokens": 26568023.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.306491947174072,
|
|
"epoch": 1.1143131604226706,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004883649041013335,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.20518676340579986,
|
|
"num_tokens": 26579469.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.363338899612427,
|
|
"epoch": 1.1147934678194045,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000488354019687472,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.19474094957113267,
|
|
"num_tokens": 26591592.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.35415735244751,
|
|
"epoch": 1.1152737752161384,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004883431303201636,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.20090872049331665,
|
|
"num_tokens": 26604075.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.268262815475464,
|
|
"epoch": 1.1157540826128722,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004883322359996613,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.20528751462697983,
|
|
"num_tokens": 26616448.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.411426734924317,
|
|
"epoch": 1.1162343900096061,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004883213367262179,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.20876433551311493,
|
|
"num_tokens": 26628749.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.335214996337891,
|
|
"epoch": 1.11671469740634,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004883104325000866,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.20761633813381195,
|
|
"num_tokens": 26640163.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.318319606781006,
|
|
"epoch": 1.1171950048030739,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004882995233215203,
|
|
"loss": 5.1507,
|
|
"mean_token_accuracy": 0.201147423684597,
|
|
"num_tokens": 26650729.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.326730585098266,
|
|
"epoch": 1.117675312199808,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004882886091907726,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.19870569407939911,
|
|
"num_tokens": 26661995.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.303139686584473,
|
|
"epoch": 1.1181556195965419,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048827769010809666,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.2046387806534767,
|
|
"num_tokens": 26673224.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.3557548999786375,
|
|
"epoch": 1.1186359269932757,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048826676607374606,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.19689726680517197,
|
|
"num_tokens": 26686331.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.440866422653198,
|
|
"epoch": 1.1191162343900096,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048825583708797434,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.1979443311691284,
|
|
"num_tokens": 26696816.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.301677322387695,
|
|
"epoch": 1.1195965417867435,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004882449031510354,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.20158976912498475,
|
|
"num_tokens": 26708126.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.422862577438354,
|
|
"epoch": 1.1200768491834774,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000488233964263183,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.20041984021663667,
|
|
"num_tokens": 26718951.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.42459545135498,
|
|
"epoch": 1.1205571565802113,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048822302042467115,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.19684413373470305,
|
|
"num_tokens": 26730550.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.254698896408081,
|
|
"epoch": 1.1210374639769451,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004882120716357539,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.20863116383552552,
|
|
"num_tokens": 26741485.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.244581127166748,
|
|
"epoch": 1.1215177713736793,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004882011178966854,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.20741567015647888,
|
|
"num_tokens": 26753947.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.362546443939209,
|
|
"epoch": 1.1219980787704131,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004881901592077201,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.21280643343925476,
|
|
"num_tokens": 26764921.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.365961599349975,
|
|
"epoch": 1.122478386167147,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004881791955691123,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.20025546103715897,
|
|
"num_tokens": 26777384.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.363601875305176,
|
|
"epoch": 1.122958693563881,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048816822698111655,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.19591017961502075,
|
|
"num_tokens": 26789916.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.333237934112549,
|
|
"epoch": 1.1234390009606148,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048815725344398766,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.20155715346336364,
|
|
"num_tokens": 26801167.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.41467432975769,
|
|
"epoch": 1.1239193083573487,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048814627495798017,
|
|
"loss": 5.2301,
|
|
"mean_token_accuracy": 0.19553892761468888,
|
|
"num_tokens": 26813235.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.438925266265869,
|
|
"epoch": 1.1243996157540825,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004881352915233492,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.1997187316417694,
|
|
"num_tokens": 26824758.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.396060514450073,
|
|
"epoch": 1.1248799231508164,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048812430314034956,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.19574963599443435,
|
|
"num_tokens": 26836877.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.243312835693359,
|
|
"epoch": 1.1253602305475505,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004881133098092365,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.21429189890623093,
|
|
"num_tokens": 26848394.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.298948669433594,
|
|
"epoch": 1.1258405379442844,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004881023115302652,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.19880813360214233,
|
|
"num_tokens": 26859064.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.4337669849395756,
|
|
"epoch": 1.1263208453410183,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000488091308303691,
|
|
"loss": 5.2838,
|
|
"mean_token_accuracy": 0.18668971657752992,
|
|
"num_tokens": 26870401.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.415605592727661,
|
|
"epoch": 1.1268011527377522,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004880803001297694,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.20082213282585143,
|
|
"num_tokens": 26881767.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.2938731670379635,
|
|
"epoch": 1.127281460134486,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004880692870087559,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.19766482561826706,
|
|
"num_tokens": 26892854.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.46474814414978,
|
|
"epoch": 1.12776176753122,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048805826894090626,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.19346135407686232,
|
|
"num_tokens": 26905079.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.458511829376221,
|
|
"epoch": 1.1282420749279538,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048804724592647626,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.1949668362736702,
|
|
"num_tokens": 26915640.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.379979372024536,
|
|
"epoch": 1.1287223823246877,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004880362179657218,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.1968240723013878,
|
|
"num_tokens": 26927039.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.3200023651123045,
|
|
"epoch": 1.1292026897214218,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048802518505889904,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.20264241844415665,
|
|
"num_tokens": 26939368.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.3155125141143795,
|
|
"epoch": 1.1296829971181557,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048801414720626404,
|
|
"loss": 5.3007,
|
|
"mean_token_accuracy": 0.18428440541028976,
|
|
"num_tokens": 26952051.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.327211523056031,
|
|
"epoch": 1.1301633045148896,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048800310440807294,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.19804711639881134,
|
|
"num_tokens": 26963680.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.250942754745483,
|
|
"epoch": 1.1306436119116234,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004879920566645823,
|
|
"loss": 5.0247,
|
|
"mean_token_accuracy": 0.2092566356062889,
|
|
"num_tokens": 26973899.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.3595212459564205,
|
|
"epoch": 1.1311239193083573,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004879810039760486,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.19472529143095016,
|
|
"num_tokens": 26985692.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.393111801147461,
|
|
"epoch": 1.1316042267050912,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004879699463427284,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.2022596463561058,
|
|
"num_tokens": 26996354.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.397092676162719,
|
|
"epoch": 1.132084534101825,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004879588837648785,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.20191200226545333,
|
|
"num_tokens": 27007925.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.275743579864502,
|
|
"epoch": 1.1325648414985592,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048794781624275554,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.20811303406953813,
|
|
"num_tokens": 27019222.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.265031528472901,
|
|
"epoch": 1.133045148895293,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048793674377661664,
|
|
"loss": 5.0858,
|
|
"mean_token_accuracy": 0.20922469794750215,
|
|
"num_tokens": 27029973.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.40197229385376,
|
|
"epoch": 1.133525456292027,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048792566636671886,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.1964692324399948,
|
|
"num_tokens": 27042002.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.315465116500855,
|
|
"epoch": 1.1340057636887608,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004879145840133194,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.20235575884580612,
|
|
"num_tokens": 27052770.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.350915718078613,
|
|
"epoch": 1.1344860710854947,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004879034967166755,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.19082554131746293,
|
|
"num_tokens": 27063375.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.335880184173584,
|
|
"epoch": 1.1349663784822286,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004878924044770446,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.19843424409627913,
|
|
"num_tokens": 27075908.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.310676527023316,
|
|
"epoch": 1.1354466858789625,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004878813072946843,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.2001047909259796,
|
|
"num_tokens": 27087590.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.325092935562134,
|
|
"epoch": 1.1359269932756964,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048787020516985203,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.20204468369483947,
|
|
"num_tokens": 27098076.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.350109386444092,
|
|
"epoch": 1.1364073006724302,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048785909810280576,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.20951852053403855,
|
|
"num_tokens": 27109851.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.298949193954468,
|
|
"epoch": 1.1368876080691643,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004878479860938033,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.2042803704738617,
|
|
"num_tokens": 27121288.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.346423006057739,
|
|
"epoch": 1.1373679154658982,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048783686914310266,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.20013950765132904,
|
|
"num_tokens": 27133877.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.18982048034668,
|
|
"epoch": 1.137848222862632,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004878257472509619,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.20817715376615525,
|
|
"num_tokens": 27145616.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.238079977035523,
|
|
"epoch": 1.138328530259366,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004878146204176392,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.20007787495851517,
|
|
"num_tokens": 27157182.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.377351951599121,
|
|
"epoch": 1.1388088376560999,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000487803488643393,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.2075334221124649,
|
|
"num_tokens": 27167609.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.3923482418060305,
|
|
"epoch": 1.1392891450528337,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048779235192848166,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.18902066946029664,
|
|
"num_tokens": 27180043.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.245966243743896,
|
|
"epoch": 1.1397694524495678,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004877812102731638,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.20914900600910186,
|
|
"num_tokens": 27191870.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.287700366973877,
|
|
"epoch": 1.1402497598463017,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048777006367769804,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.2026633709669113,
|
|
"num_tokens": 27203291.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.350346660614013,
|
|
"epoch": 1.1407300672430356,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004877589121423432,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.20331001430749893,
|
|
"num_tokens": 27214607.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.319932460784912,
|
|
"epoch": 1.1412103746397695,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004877477556673582,
|
|
"loss": 5.0431,
|
|
"mean_token_accuracy": 0.20541132539510726,
|
|
"num_tokens": 27224658.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.258152914047241,
|
|
"epoch": 1.1416906820365034,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000487736594253002,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.19404602497816087,
|
|
"num_tokens": 27235306.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.40604796409607,
|
|
"epoch": 1.1421709894332372,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048772542789953384,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.19239812344312668,
|
|
"num_tokens": 27246679.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.409171199798584,
|
|
"epoch": 1.1426512968299711,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048771425660721284,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.1989218920469284,
|
|
"num_tokens": 27257799.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.274768352508545,
|
|
"epoch": 1.143131604226705,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048770308037629853,
|
|
"loss": 5.1583,
|
|
"mean_token_accuracy": 0.1964280918240547,
|
|
"num_tokens": 27268651.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.318347549438476,
|
|
"epoch": 1.143611911623439,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004876918992070502,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.20458992272615434,
|
|
"num_tokens": 27280655.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.351888704299927,
|
|
"epoch": 1.144092219020173,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004876807130997276,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.1967310428619385,
|
|
"num_tokens": 27292664.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.384659242630005,
|
|
"epoch": 1.1445725264169069,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004876695220545903,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.19868590980768203,
|
|
"num_tokens": 27306143.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.349447870254517,
|
|
"epoch": 1.1450528338136408,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048765832607189824,
|
|
"loss": 5.119,
|
|
"mean_token_accuracy": 0.20023303031921386,
|
|
"num_tokens": 27316926.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.408103275299072,
|
|
"epoch": 1.1455331412103746,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048764712515191136,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.20315809845924376,
|
|
"num_tokens": 27327472.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.345971155166626,
|
|
"epoch": 1.1460134486071085,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048763591929488966,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.19940067380666732,
|
|
"num_tokens": 27338388.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.338276004791259,
|
|
"epoch": 1.1464937560038424,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004876247085010933,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.20268147736787795,
|
|
"num_tokens": 27349879.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.307774400711059,
|
|
"epoch": 1.1469740634005763,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048761349277078253,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.20198409706354142,
|
|
"num_tokens": 27361226.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.335858774185181,
|
|
"epoch": 1.1474543707973104,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048760227210421775,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.20722505152225495,
|
|
"num_tokens": 27373512.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.279110383987427,
|
|
"epoch": 1.1479346781940443,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004875910465016596,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.2042992666363716,
|
|
"num_tokens": 27384950.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.488682270050049,
|
|
"epoch": 1.1484149855907781,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004875798159633686,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.20061515718698503,
|
|
"num_tokens": 27395877.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.357973861694336,
|
|
"epoch": 1.148895292987512,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004875685804896055,
|
|
"loss": 5.2294,
|
|
"mean_token_accuracy": 0.2018139734864235,
|
|
"num_tokens": 27407783.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.309019708633423,
|
|
"epoch": 1.149375600384246,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004875573400806312,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.19884290546178818,
|
|
"num_tokens": 27420598.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.340104770660401,
|
|
"epoch": 1.1498559077809798,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048754609473670654,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.19572806507349014,
|
|
"num_tokens": 27431961.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.330755662918091,
|
|
"epoch": 1.1503362151777137,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004875348444580927,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.20368386059999466,
|
|
"num_tokens": 27444010.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.36952953338623,
|
|
"epoch": 1.1508165225744476,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.000487523589245051,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.20183252096176146,
|
|
"num_tokens": 27455576.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.315498113632202,
|
|
"epoch": 1.1512968299711814,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004875123290978425,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.1970788761973381,
|
|
"num_tokens": 27468957.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.33052339553833,
|
|
"epoch": 1.1517771373679155,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048750106401672876,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.2106876477599144,
|
|
"num_tokens": 27479992.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.373970985412598,
|
|
"epoch": 1.1522574447646494,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048748979400197134,
|
|
"loss": 5.2223,
|
|
"mean_token_accuracy": 0.1930154100060463,
|
|
"num_tokens": 27490878.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.279443311691284,
|
|
"epoch": 1.1527377521613833,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048747851905383183,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.20705019384622575,
|
|
"num_tokens": 27502009.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.1527377521613833,
|
|
"eval_entropy": 5.181525880798719,
|
|
"eval_loss": 5.2455735206604,
|
|
"eval_mean_token_accuracy": 0.20400699958484939,
|
|
"eval_num_tokens": 27502009.0,
|
|
"eval_runtime": 26.6751,
|
|
"eval_samples_per_second": 1230.173,
|
|
"eval_steps_per_second": 153.776,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.3908524990081785,
|
|
"epoch": 1.1532180595581172,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004874672391725721,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.19319112598896027,
|
|
"num_tokens": 27513376.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.280206108093262,
|
|
"epoch": 1.153698366954851,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004874559543584539,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.19944672733545304,
|
|
"num_tokens": 27525166.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.2417620658874515,
|
|
"epoch": 1.154178674351585,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004874446646117394,
|
|
"loss": 5.0155,
|
|
"mean_token_accuracy": 0.21257457435131072,
|
|
"num_tokens": 27535994.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.29957766532898,
|
|
"epoch": 1.154658981748319,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004874333699326906,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.2040296822786331,
|
|
"num_tokens": 27546883.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.437859535217285,
|
|
"epoch": 1.155139289145053,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004874220703215697,
|
|
"loss": 5.2315,
|
|
"mean_token_accuracy": 0.19461966902017594,
|
|
"num_tokens": 27558840.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.270661973953247,
|
|
"epoch": 1.1556195965417868,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004874107657786391,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.20360291451215745,
|
|
"num_tokens": 27569776.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.33494119644165,
|
|
"epoch": 1.1560999039385207,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048739945630416124,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.20274856984615325,
|
|
"num_tokens": 27580097.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.389014530181885,
|
|
"epoch": 1.1565802113352546,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004873881418983987,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.197333362698555,
|
|
"num_tokens": 27592035.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.346986246109009,
|
|
"epoch": 1.1570605187319885,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004873768225616141,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.2008766934275627,
|
|
"num_tokens": 27604409.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.408114004135132,
|
|
"epoch": 1.1575408261287223,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048736549829407047,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.20172157883644104,
|
|
"num_tokens": 27615019.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.387735271453858,
|
|
"epoch": 1.1580211335254562,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004873541690960305,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.19293405264616012,
|
|
"num_tokens": 27627924.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.284401321411133,
|
|
"epoch": 1.15850144092219,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004873428349677573,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.20180596858263017,
|
|
"num_tokens": 27639188.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.420152568817139,
|
|
"epoch": 1.1589817483189242,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000487331495909514,
|
|
"loss": 5.2719,
|
|
"mean_token_accuracy": 0.18863337188959123,
|
|
"num_tokens": 27652621.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.392624855041504,
|
|
"epoch": 1.159462055715658,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048732015192156383,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.1932012125849724,
|
|
"num_tokens": 27665726.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.367257452011108,
|
|
"epoch": 1.159942363112392,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048730880300417015,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.19835880994796753,
|
|
"num_tokens": 27676984.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.389113235473633,
|
|
"epoch": 1.1604226705091258,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048729744915759657,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.1977803260087967,
|
|
"num_tokens": 27688812.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.24800181388855,
|
|
"epoch": 1.1609029779058597,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048728609038210655,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.20651137828826904,
|
|
"num_tokens": 27699152.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.3268351554870605,
|
|
"epoch": 1.1613832853025936,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048727472667796395,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.19925030022859574,
|
|
"num_tokens": 27710347.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.3113635063171385,
|
|
"epoch": 1.1618635926993275,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004872633580454325,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.2069007486104965,
|
|
"num_tokens": 27721112.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.352517461776733,
|
|
"epoch": 1.1623439000960616,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048725198448477616,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.2020840123295784,
|
|
"num_tokens": 27731766.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.318842506408691,
|
|
"epoch": 1.1628242074927955,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048724060599625893,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.20582252740859985,
|
|
"num_tokens": 27743718.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.334585905075073,
|
|
"epoch": 1.1633045148895294,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048722922258014506,
|
|
"loss": 5.185,
|
|
"mean_token_accuracy": 0.20029875338077546,
|
|
"num_tokens": 27754999.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.3835546493530275,
|
|
"epoch": 1.1637848222862632,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004872178342366989,
|
|
"loss": 5.2847,
|
|
"mean_token_accuracy": 0.18913753926753998,
|
|
"num_tokens": 27767684.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.3171546459198,
|
|
"epoch": 1.1642651296829971,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048720644096618475,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.20750762820243834,
|
|
"num_tokens": 27779103.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.307455253601074,
|
|
"epoch": 1.164745437079731,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004871950427688672,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.20654143989086152,
|
|
"num_tokens": 27791223.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.317896223068237,
|
|
"epoch": 1.1652257444764649,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048718363964501087,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.20144564509391785,
|
|
"num_tokens": 27802660.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.364362478256226,
|
|
"epoch": 1.1657060518731988,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004871722315948805,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.19797608256340027,
|
|
"num_tokens": 27814370.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.275074481964111,
|
|
"epoch": 1.1661863592699326,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004871608186187408,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.20328809469938278,
|
|
"num_tokens": 27825035.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.246714496612549,
|
|
"epoch": 1.1666666666666667,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048714940071685703,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.2025137186050415,
|
|
"num_tokens": 27837276.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.38623685836792,
|
|
"epoch": 1.1671469740634006,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048713797788949405,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.1924775794148445,
|
|
"num_tokens": 27848618.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.316412687301636,
|
|
"epoch": 1.1676272814601345,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048712655013691714,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.19082323163747789,
|
|
"num_tokens": 27861556.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.390494441986084,
|
|
"epoch": 1.1681075888568684,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048711511745939165,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.1976610988378525,
|
|
"num_tokens": 27873211.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.360829305648804,
|
|
"epoch": 1.1685878962536023,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000487103679857183,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.20867001563310622,
|
|
"num_tokens": 27883365.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.2430624008178714,
|
|
"epoch": 1.1690682036503361,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004870922373305567,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.20538025051355363,
|
|
"num_tokens": 27894669.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.312198209762573,
|
|
"epoch": 1.1695485110470702,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048708078987977837,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.19798873960971833,
|
|
"num_tokens": 27906480.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.31582727432251,
|
|
"epoch": 1.1700288184438041,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048706933750511394,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.2079410046339035,
|
|
"num_tokens": 27918383.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.410451364517212,
|
|
"epoch": 1.170509125840538,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004870578802068292,
|
|
"loss": 5.1813,
|
|
"mean_token_accuracy": 0.1963541701436043,
|
|
"num_tokens": 27928944.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.286853790283203,
|
|
"epoch": 1.170989433237272,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048704641798519006,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.20326893627643586,
|
|
"num_tokens": 27941105.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.345436906814575,
|
|
"epoch": 1.1714697406340058,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048703495084046286,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.20418674647808074,
|
|
"num_tokens": 27952925.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.250399494171143,
|
|
"epoch": 1.1719500480307397,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004870234787729137,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.2087944358587265,
|
|
"num_tokens": 27965504.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.301664209365844,
|
|
"epoch": 1.1724303554274735,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004870120017828089,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.21204709708690644,
|
|
"num_tokens": 27975985.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.453875732421875,
|
|
"epoch": 1.1729106628242074,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000487000519870415,
|
|
"loss": 5.2105,
|
|
"mean_token_accuracy": 0.1855822190642357,
|
|
"num_tokens": 27987784.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.309272909164429,
|
|
"epoch": 1.1733909702209413,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004869890330359986,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.1975688174366951,
|
|
"num_tokens": 27999623.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.291332721710205,
|
|
"epoch": 1.1738712776176754,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004869775412798262,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.1994726240634918,
|
|
"num_tokens": 28011561.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.420221567153931,
|
|
"epoch": 1.1743515850144093,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048696604460216476,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.20704235136508942,
|
|
"num_tokens": 28022108.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.399952697753906,
|
|
"epoch": 1.1748318924111432,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048695454300328123,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.19748488664627076,
|
|
"num_tokens": 28033497.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.328026628494262,
|
|
"epoch": 1.175312199807877,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048694303648344256,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.20121422708034514,
|
|
"num_tokens": 28044790.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.2670207023620605,
|
|
"epoch": 1.175792507204611,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048693152504291595,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.20478794872760772,
|
|
"num_tokens": 28056000.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.34293212890625,
|
|
"epoch": 1.1762728146013448,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004869200086819686,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.1993146762251854,
|
|
"num_tokens": 28068264.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.352593803405762,
|
|
"epoch": 1.1767531219980787,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048690848740086796,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.2070430725812912,
|
|
"num_tokens": 28080220.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.375977659225464,
|
|
"epoch": 1.1772334293948128,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004868969611998814,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.20049103498458862,
|
|
"num_tokens": 28091531.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.267001152038574,
|
|
"epoch": 1.1777137367915467,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004868854300792767,
|
|
"loss": 5.1145,
|
|
"mean_token_accuracy": 0.19694308787584305,
|
|
"num_tokens": 28102982.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.308177185058594,
|
|
"epoch": 1.1781940441882806,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048687389403932144,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.20323159396648408,
|
|
"num_tokens": 28114131.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.374611759185791,
|
|
"epoch": 1.1786743515850144,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004868623530802835,
|
|
"loss": 5.1027,
|
|
"mean_token_accuracy": 0.19908516407012938,
|
|
"num_tokens": 28125637.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.4075010299682615,
|
|
"epoch": 1.1791546589817483,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048685080720243086,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.20386240929365157,
|
|
"num_tokens": 28137284.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.3738508224487305,
|
|
"epoch": 1.1796349663784822,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004868392564060315,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.20342936962842942,
|
|
"num_tokens": 28148909.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.410213851928711,
|
|
"epoch": 1.180115273775216,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004868277006913537,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.20435544550418855,
|
|
"num_tokens": 28160392.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.333761262893677,
|
|
"epoch": 1.18059558117195,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004868161400586656,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.19262638986110686,
|
|
"num_tokens": 28172957.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.454390573501587,
|
|
"epoch": 1.1810758885686838,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004868045745082357,
|
|
"loss": 5.2099,
|
|
"mean_token_accuracy": 0.19358927756547928,
|
|
"num_tokens": 28183239.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.302633810043335,
|
|
"epoch": 1.181556195965418,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004867930040403326,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.1984902948141098,
|
|
"num_tokens": 28195382.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.316921281814575,
|
|
"epoch": 1.1820365033621518,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048678142865522475,
|
|
"loss": 5.2071,
|
|
"mean_token_accuracy": 0.19107128381729127,
|
|
"num_tokens": 28206645.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.407915878295898,
|
|
"epoch": 1.1825168107588857,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000486769848353181,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.20019783228635787,
|
|
"num_tokens": 28218420.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.384075784683228,
|
|
"epoch": 1.1829971181556196,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048675826313447027,
|
|
"loss": 5.1871,
|
|
"mean_token_accuracy": 0.19635487198829651,
|
|
"num_tokens": 28229458.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.365120935440063,
|
|
"epoch": 1.1834774255523535,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00048674667299936135,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.19787353724241258,
|
|
"num_tokens": 28242240.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.487725305557251,
|
|
"epoch": 1.1839577329490873,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048673507794812356,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.19035686552524567,
|
|
"num_tokens": 28254597.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.371772146224975,
|
|
"epoch": 1.1844380403458212,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004867234779810259,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.198590649664402,
|
|
"num_tokens": 28266674.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.341756677627563,
|
|
"epoch": 1.1849183477425553,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004867118730983378,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.20262406170368194,
|
|
"num_tokens": 28278671.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.406499719619751,
|
|
"epoch": 1.1853986551392892,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004867002633003286,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.20296962261199952,
|
|
"num_tokens": 28291085.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.293211460113525,
|
|
"epoch": 1.185878962536023,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000486688648587268,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.20380455404520034,
|
|
"num_tokens": 28303457.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.349237155914307,
|
|
"epoch": 1.186359269932757,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004866770289594256,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.19498010724782944,
|
|
"num_tokens": 28314599.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.476745986938477,
|
|
"epoch": 1.1868395773294909,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048666540441707107,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.19895642697811128,
|
|
"num_tokens": 28326266.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.3687187194824215,
|
|
"epoch": 1.1873198847262247,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004866537749604744,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.1968431815505028,
|
|
"num_tokens": 28337238.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.231341552734375,
|
|
"epoch": 1.1878001921229586,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00048664214058990546,
|
|
"loss": 5.1164,
|
|
"mean_token_accuracy": 0.20339395552873613,
|
|
"num_tokens": 28348060.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.3087671279907225,
|
|
"epoch": 1.1882804995196925,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004866305013056346,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.197100405395031,
|
|
"num_tokens": 28359442.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.36939115524292,
|
|
"epoch": 1.1887608069164266,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004866188571079318,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.19921409636735915,
|
|
"num_tokens": 28370827.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.37849793434143,
|
|
"epoch": 1.1892411143131605,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004866072079970676,
|
|
"loss": 5.2509,
|
|
"mean_token_accuracy": 0.1878717303276062,
|
|
"num_tokens": 28383115.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.361561584472656,
|
|
"epoch": 1.1897214217098944,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048659555397331236,
|
|
"loss": 5.119,
|
|
"mean_token_accuracy": 0.2036876305937767,
|
|
"num_tokens": 28394904.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.359992361068725,
|
|
"epoch": 1.1902017291066282,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004865838950369366,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.19382551610469817,
|
|
"num_tokens": 28407357.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.37358341217041,
|
|
"epoch": 1.1906820365033621,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048657223118821116,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.20295656025409697,
|
|
"num_tokens": 28418088.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.20915002822876,
|
|
"epoch": 1.191162343900096,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048656056242740665,
|
|
"loss": 5.0261,
|
|
"mean_token_accuracy": 0.20811841934919356,
|
|
"num_tokens": 28430022.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.285872602462769,
|
|
"epoch": 1.19164265129683,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004865488887547942,
|
|
"loss": 5.1158,
|
|
"mean_token_accuracy": 0.20396342128515244,
|
|
"num_tokens": 28440530.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.392705678939819,
|
|
"epoch": 1.192122958693564,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004865372101706446,
|
|
"loss": 5.2356,
|
|
"mean_token_accuracy": 0.19170499444007874,
|
|
"num_tokens": 28452707.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.275023937225342,
|
|
"epoch": 1.1926032660902979,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004865255266752292,
|
|
"loss": 5.0373,
|
|
"mean_token_accuracy": 0.21347523033618926,
|
|
"num_tokens": 28465131.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.276062774658203,
|
|
"epoch": 1.1930835734870318,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004865138382688191,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.2041534259915352,
|
|
"num_tokens": 28476136.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.3788856029510494,
|
|
"epoch": 1.1935638808837656,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004865021449516859,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.19920985996723176,
|
|
"num_tokens": 28488374.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.338430595397949,
|
|
"epoch": 1.1940441882804995,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004864904467241008,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.19819955229759217,
|
|
"num_tokens": 28499585.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.281917428970337,
|
|
"epoch": 1.1945244956772334,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048647874358633556,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.20740209370851517,
|
|
"num_tokens": 28510707.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.391925573348999,
|
|
"epoch": 1.1950048030739673,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048646703553866183,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.19639266431331634,
|
|
"num_tokens": 28522398.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.283515739440918,
|
|
"epoch": 1.1954851104707012,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004864553225813515,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.2065272659063339,
|
|
"num_tokens": 28532949.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.240192222595215,
|
|
"epoch": 1.195965417867435,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004864436047146765,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.20735208988189696,
|
|
"num_tokens": 28544292.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.344904088973999,
|
|
"epoch": 1.1964457252641691,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048643188193890874,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.20040458887815477,
|
|
"num_tokens": 28556430.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.410895824432373,
|
|
"epoch": 1.196926032660903,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004864201542543206,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.19830642491579056,
|
|
"num_tokens": 28568475.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.375480031967163,
|
|
"epoch": 1.197406340057637,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004864084216611843,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.19795463383197784,
|
|
"num_tokens": 28579653.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.31444149017334,
|
|
"epoch": 1.1978866474543708,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048639668415977207,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.19961393177509307,
|
|
"num_tokens": 28590108.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.339989519119262,
|
|
"epoch": 1.1983669548511047,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048638494175035665,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.20756358951330184,
|
|
"num_tokens": 28602008.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.270875787734985,
|
|
"epoch": 1.1988472622478386,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004863731944332105,
|
|
"loss": 5.0395,
|
|
"mean_token_accuracy": 0.20752338021993638,
|
|
"num_tokens": 28613286.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.287977457046509,
|
|
"epoch": 1.1993275696445724,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004863614422086065,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.21101954132318496,
|
|
"num_tokens": 28625497.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.322183895111084,
|
|
"epoch": 1.1998078770413065,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004863496850768174,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.20710864216089248,
|
|
"num_tokens": 28638046.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.259683990478516,
|
|
"epoch": 1.2002881844380404,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004863379230381162,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.206351138651371,
|
|
"num_tokens": 28647923.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.277581071853637,
|
|
"epoch": 1.2007684918347743,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000486326156092776,
|
|
"loss": 5.0845,
|
|
"mean_token_accuracy": 0.2095193788409233,
|
|
"num_tokens": 28660023.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.315068054199219,
|
|
"epoch": 1.2012487992315082,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048631438424106985,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.20518602132797242,
|
|
"num_tokens": 28671568.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.253316974639892,
|
|
"epoch": 1.201729106628242,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048630260748327124,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.2101099744439125,
|
|
"num_tokens": 28682897.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.307678318023681,
|
|
"epoch": 1.202209414024976,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048629082581965355,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.20042741745710374,
|
|
"num_tokens": 28694067.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.363761615753174,
|
|
"epoch": 1.2026897214217098,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048627903925049033,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.2069265976548195,
|
|
"num_tokens": 28705738.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.307748889923095,
|
|
"epoch": 1.2031700288184437,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048626724777605507,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.20257478207349777,
|
|
"num_tokens": 28717419.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.327852964401245,
|
|
"epoch": 1.2036503362151778,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004862554513966217,
|
|
"loss": 5.2303,
|
|
"mean_token_accuracy": 0.1898307904601097,
|
|
"num_tokens": 28728587.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.3661370277404785,
|
|
"epoch": 1.2041306436119117,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048624365011246405,
|
|
"loss": 5.2206,
|
|
"mean_token_accuracy": 0.19443798512220384,
|
|
"num_tokens": 28740818.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.311012125015258,
|
|
"epoch": 1.2046109510086456,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004862318439238561,
|
|
"loss": 5.067,
|
|
"mean_token_accuracy": 0.20935198664665222,
|
|
"num_tokens": 28751936.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.286559820175171,
|
|
"epoch": 1.2050912584053795,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000486220032831072,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.19886787682771684,
|
|
"num_tokens": 28763271.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.396122455596924,
|
|
"epoch": 1.2055715658021133,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004862082168343859,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.20383376777172088,
|
|
"num_tokens": 28774282.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.393498945236206,
|
|
"epoch": 1.2060518731988472,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004861963959340722,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.19689911007881164,
|
|
"num_tokens": 28785826.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.241088438034057,
|
|
"epoch": 1.206532180595581,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004861845701304053,
|
|
"loss": 5.0337,
|
|
"mean_token_accuracy": 0.20936149209737778,
|
|
"num_tokens": 28797669.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.348894882202148,
|
|
"epoch": 1.2070124879923152,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048617273942365977,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.19653456509113312,
|
|
"num_tokens": 28808438.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.297219514846802,
|
|
"epoch": 1.207492795389049,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004861609038141103,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.21038172245025635,
|
|
"num_tokens": 28819707.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.344007349014282,
|
|
"epoch": 1.207973102785783,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00048614906330203165,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.20138845592737198,
|
|
"num_tokens": 28831829.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.295113754272461,
|
|
"epoch": 1.2084534101825168,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004861372178876987,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.2024746537208557,
|
|
"num_tokens": 28843429.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.308295345306396,
|
|
"epoch": 1.2089337175792507,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048612536757138653,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.20810484290122985,
|
|
"num_tokens": 28856239.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.354773092269897,
|
|
"epoch": 1.2094140249759846,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004861135123533702,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.2034955456852913,
|
|
"num_tokens": 28868599.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.356560754776001,
|
|
"epoch": 1.2098943323727185,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048610165223392503,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.20118624716997147,
|
|
"num_tokens": 28880234.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.40856523513794,
|
|
"epoch": 1.2103746397694524,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004860897872133263,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.1967000976204872,
|
|
"num_tokens": 28892198.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.314138031005859,
|
|
"epoch": 1.2108549471661862,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004860779172918496,
|
|
"loss": 5.2181,
|
|
"mean_token_accuracy": 0.1968151405453682,
|
|
"num_tokens": 28904153.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.397249555587768,
|
|
"epoch": 1.2113352545629203,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004860660424697704,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.2001808002591133,
|
|
"num_tokens": 28915284.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.386776304244995,
|
|
"epoch": 1.2118155619596542,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048605416274736434,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.1964868798851967,
|
|
"num_tokens": 28928168.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.3091977596282955,
|
|
"epoch": 1.2122958693563881,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048604227812490744,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.2092862457036972,
|
|
"num_tokens": 28938548.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.288661479949951,
|
|
"epoch": 1.212776176753122,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048603038860267546,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.2027292624115944,
|
|
"num_tokens": 28949252.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.32654595375061,
|
|
"epoch": 1.2132564841498559,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004860184941809445,
|
|
"loss": 5.1619,
|
|
"mean_token_accuracy": 0.2056921511888504,
|
|
"num_tokens": 28960758.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.391355228424072,
|
|
"epoch": 1.2137367915465898,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048600659485999073,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.20107527673244477,
|
|
"num_tokens": 28972604.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.374255657196045,
|
|
"epoch": 1.2142170989433236,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048599469064009027,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.20516385585069657,
|
|
"num_tokens": 28983617.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.272982597351074,
|
|
"epoch": 1.2146974063400577,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048598278152151974,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.20447977930307387,
|
|
"num_tokens": 28994277.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.386844205856323,
|
|
"epoch": 1.2151777137367916,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004859708675045555,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.20241004079580308,
|
|
"num_tokens": 29004844.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.243856477737427,
|
|
"epoch": 1.2156580211335255,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004859589485894741,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.2110291451215744,
|
|
"num_tokens": 29015978.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.392196273803711,
|
|
"epoch": 1.2161383285302594,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004859470247765524,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.2033882185816765,
|
|
"num_tokens": 29026966.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.303181219100952,
|
|
"epoch": 1.2166186359269933,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004859350960660671,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.2062980353832245,
|
|
"num_tokens": 29037943.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.341811084747315,
|
|
"epoch": 1.2170989433237271,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004859231624582953,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.19455116242170334,
|
|
"num_tokens": 29049939.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.300059413909912,
|
|
"epoch": 1.217579250720461,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048591122395351394,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.20225424319505692,
|
|
"num_tokens": 29062442.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.286792230606079,
|
|
"epoch": 1.218059558117195,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004858992805520003,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.20164866000413895,
|
|
"num_tokens": 29074240.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.357754802703857,
|
|
"epoch": 1.218539865513929,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048588733225403153,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.19644758701324463,
|
|
"num_tokens": 29085550.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.288479042053223,
|
|
"epoch": 1.219020172910663,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004858753790598851,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.20078130513429643,
|
|
"num_tokens": 29097092.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.282299661636353,
|
|
"epoch": 1.2195004803073968,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004858634209698386,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.20196508020162582,
|
|
"num_tokens": 29108119.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.308382225036621,
|
|
"epoch": 1.2199807877041307,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048585145798416956,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.1983231782913208,
|
|
"num_tokens": 29120605.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.333104133605957,
|
|
"epoch": 1.2204610951008645,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004858394901031558,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.20267568230628968,
|
|
"num_tokens": 29131582.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.408512306213379,
|
|
"epoch": 1.2209414024975984,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004858275173270751,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.196755950152874,
|
|
"num_tokens": 29143436.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.317536783218384,
|
|
"epoch": 1.2214217098943323,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048581553965620553,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.20707447379827498,
|
|
"num_tokens": 29154445.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.33020052909851,
|
|
"epoch": 1.2219020172910664,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048580355709082506,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.20091477930545806,
|
|
"num_tokens": 29164599.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.345781230926514,
|
|
"epoch": 1.2223823246878003,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000485791569631212,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.19878381490707397,
|
|
"num_tokens": 29176275.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.386361074447632,
|
|
"epoch": 1.2228626320845342,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004857795772776446,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.20044123828411103,
|
|
"num_tokens": 29189102.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.347451305389404,
|
|
"epoch": 1.223342939481268,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048576758003040127,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.20021715760231018,
|
|
"num_tokens": 29200953.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.329083585739136,
|
|
"epoch": 1.223823246878002,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048575557788976066,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.19077558666467667,
|
|
"num_tokens": 29212942.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.3068922996521,
|
|
"epoch": 1.2243035542747358,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004857435708560013,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.20546870827674865,
|
|
"num_tokens": 29224949.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.4252156734466555,
|
|
"epoch": 1.2247838616714697,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048573155892940204,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.1958234503865242,
|
|
"num_tokens": 29236044.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.314380502700805,
|
|
"epoch": 1.2252641690682036,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048571954211024164,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.20146780759096145,
|
|
"num_tokens": 29248084.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.305870580673218,
|
|
"epoch": 1.2257444764649374,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048570752039879924,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.20470981895923615,
|
|
"num_tokens": 29258710.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.3580351829528805,
|
|
"epoch": 1.2262247838616716,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004856954937953539,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.18894563764333724,
|
|
"num_tokens": 29270173.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.379156494140625,
|
|
"epoch": 1.2267050912584054,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004856834623001848,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.19946112632751464,
|
|
"num_tokens": 29280407.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.316649532318115,
|
|
"epoch": 1.2271853986551393,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004856714259135713,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.20940244048833848,
|
|
"num_tokens": 29292287.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.323112058639526,
|
|
"epoch": 1.2276657060518732,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004856593846357929,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.19719885289669037,
|
|
"num_tokens": 29303099.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.389344024658203,
|
|
"epoch": 1.228146013448607,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004856473384671291,
|
|
"loss": 5.2318,
|
|
"mean_token_accuracy": 0.19985658377408982,
|
|
"num_tokens": 29314445.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.295089817047119,
|
|
"epoch": 1.228626320845341,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048563528740785955,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.201399527490139,
|
|
"num_tokens": 29325309.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.2874024391174315,
|
|
"epoch": 1.2291066282420748,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048562323145826414,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.2118099346756935,
|
|
"num_tokens": 29338582.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.3354024410247805,
|
|
"epoch": 1.229586935638809,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004856111706186227,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.20759699642658233,
|
|
"num_tokens": 29349875.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.447449636459351,
|
|
"epoch": 1.2300672430355428,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048559910488921534,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.19368140548467636,
|
|
"num_tokens": 29361800.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.3165998458862305,
|
|
"epoch": 1.2305475504322767,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000485587034270322,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.20618117451667786,
|
|
"num_tokens": 29372795.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.343142032623291,
|
|
"epoch": 1.2310278578290106,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000485574958762223,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.19879169762134552,
|
|
"num_tokens": 29385391.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.263661003112793,
|
|
"epoch": 1.2315081652257445,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048556287836519886,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.2091962918639183,
|
|
"num_tokens": 29397113.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.390621662139893,
|
|
"epoch": 1.2319884726224783,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004855507930795299,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.20469078421592712,
|
|
"num_tokens": 29407552.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.357895135879517,
|
|
"epoch": 1.2324687800192122,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048553870290549665,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.20246838182210922,
|
|
"num_tokens": 29418500.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.434592390060425,
|
|
"epoch": 1.232949087415946,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00048552660784338,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.19819416105747223,
|
|
"num_tokens": 29430335.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.3018989086151125,
|
|
"epoch": 1.23342939481268,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004855145078934606,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.1949135735630989,
|
|
"num_tokens": 29441435.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.338494110107422,
|
|
"epoch": 1.233909702209414,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004855024030560195,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.20450785905122756,
|
|
"num_tokens": 29453140.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.274100017547608,
|
|
"epoch": 1.234390009606148,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004854902933313376,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.21276862919330597,
|
|
"num_tokens": 29464572.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.416504764556885,
|
|
"epoch": 1.2348703170028819,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048547817871969607,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.1941487669944763,
|
|
"num_tokens": 29477069.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.389190006256103,
|
|
"epoch": 1.2353506243996157,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048546605922137633,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.20182060003280639,
|
|
"num_tokens": 29486860.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.39966049194336,
|
|
"epoch": 1.2358309317963496,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004854539348366596,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.19653943032026291,
|
|
"num_tokens": 29499129.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.236139249801636,
|
|
"epoch": 1.2363112391930835,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004854418055658274,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.20503242909908295,
|
|
"num_tokens": 29510764.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.336893701553345,
|
|
"epoch": 1.2367915465898176,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048542967140916134,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.19962415844202042,
|
|
"num_tokens": 29522882.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.4004346370697025,
|
|
"epoch": 1.2372718539865515,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004854175323669432,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.19564027190208436,
|
|
"num_tokens": 29533348.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.288814496994019,
|
|
"epoch": 1.2377521613832854,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004854053884394547,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.2054067462682724,
|
|
"num_tokens": 29545649.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.350157690048218,
|
|
"epoch": 1.2382324687800192,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048539323962697796,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.20031842738389968,
|
|
"num_tokens": 29558252.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.4833907127380375,
|
|
"epoch": 1.2387127761767531,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004853810859297949,
|
|
"loss": 5.2464,
|
|
"mean_token_accuracy": 0.1997705340385437,
|
|
"num_tokens": 29569495.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.352335262298584,
|
|
"epoch": 1.239193083573487,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048536892734818773,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.20249464958906174,
|
|
"num_tokens": 29582167.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.367276811599732,
|
|
"epoch": 1.239673390970221,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004853567638824387,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.20128172188997268,
|
|
"num_tokens": 29593964.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.368005704879761,
|
|
"epoch": 1.2401536983669548,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048534459553283026,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.20648843050003052,
|
|
"num_tokens": 29604844.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.346329975128174,
|
|
"epoch": 1.2406340057636887,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004853324222996449,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.2047807827591896,
|
|
"num_tokens": 29615219.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.459403705596924,
|
|
"epoch": 1.2411143131604228,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048532024418316525,
|
|
"loss": 5.237,
|
|
"mean_token_accuracy": 0.19680690467357637,
|
|
"num_tokens": 29626472.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.3043745994567875,
|
|
"epoch": 1.2415946205571566,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004853080611836741,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.207733391225338,
|
|
"num_tokens": 29637966.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.242879915237427,
|
|
"epoch": 1.2420749279538905,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048529587330145427,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.21052529215812682,
|
|
"num_tokens": 29648730.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.242168235778808,
|
|
"epoch": 1.2425552353506244,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048528368053678863,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.19818065613508223,
|
|
"num_tokens": 29660576.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.336780214309693,
|
|
"epoch": 1.2430355427473583,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004852714828899604,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.2058456614613533,
|
|
"num_tokens": 29672906.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.326187801361084,
|
|
"epoch": 1.2435158501440922,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048525928036125264,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.20572283416986464,
|
|
"num_tokens": 29685360.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.348163652420044,
|
|
"epoch": 1.243996157540826,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048524707295094884,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.19467228949069976,
|
|
"num_tokens": 29697257.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.334978532791138,
|
|
"epoch": 1.2444764649375601,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004852348606593322,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.20818641632795334,
|
|
"num_tokens": 29707877.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.349760055541992,
|
|
"epoch": 1.244956772334294,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048522264348668646,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.20347986072301866,
|
|
"num_tokens": 29719358.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.255683946609497,
|
|
"epoch": 1.245437079731028,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004852104214332951,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.21716088205575942,
|
|
"num_tokens": 29730383.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.3465338230133055,
|
|
"epoch": 1.2459173871277618,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048519819449944205,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.2054044246673584,
|
|
"num_tokens": 29741142.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.317774391174316,
|
|
"epoch": 1.2463976945244957,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000485185962685411,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.20206799656152724,
|
|
"num_tokens": 29754618.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.37565426826477,
|
|
"epoch": 1.2468780019212296,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000485173725991486,
|
|
"loss": 5.125,
|
|
"mean_token_accuracy": 0.2017595186829567,
|
|
"num_tokens": 29767115.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.384836626052857,
|
|
"epoch": 1.2473583093179634,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048516148441795124,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.19355375617742537,
|
|
"num_tokens": 29778165.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.440066719055176,
|
|
"epoch": 1.2478386167146973,
|
|
"grad_norm": 8.8125,
|
|
"learning_rate": 0.0004851492379650908,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.19170975238084792,
|
|
"num_tokens": 29790528.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.307202911376953,
|
|
"epoch": 1.2483189241114312,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004851369866331891,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.20269097238779069,
|
|
"num_tokens": 29801709.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.371226072311401,
|
|
"epoch": 1.2487992315081653,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004851247304225306,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.19693203270435333,
|
|
"num_tokens": 29812963.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.393985033035278,
|
|
"epoch": 1.2492795389048992,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004851124693333997,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.20324223935604097,
|
|
"num_tokens": 29823711.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.284325981140137,
|
|
"epoch": 1.249759846301633,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004851002033660812,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.20553406476974487,
|
|
"num_tokens": 29834038.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.357745170593262,
|
|
"epoch": 1.250240153698367,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048508793252085994,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.2065795138478279,
|
|
"num_tokens": 29844759.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.229052400588989,
|
|
"epoch": 1.2507204610951008,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004850756567980206,
|
|
"loss": 4.9908,
|
|
"mean_token_accuracy": 0.2080628678202629,
|
|
"num_tokens": 29855643.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.352957439422608,
|
|
"epoch": 1.2512007684918347,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048506337619784836,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.20088895559310913,
|
|
"num_tokens": 29866917.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.436763715744019,
|
|
"epoch": 1.2516810758885688,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004850510907206283,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.1936774730682373,
|
|
"num_tokens": 29878937.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.292483854293823,
|
|
"epoch": 1.2521613832853027,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048503880036664555,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.2079023912549019,
|
|
"num_tokens": 29889544.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.288785552978515,
|
|
"epoch": 1.2526416906820366,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004850265051361857,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.20292175561189651,
|
|
"num_tokens": 29901919.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.341815042495727,
|
|
"epoch": 1.2531219980787704,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004850142050295339,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.20138135105371474,
|
|
"num_tokens": 29913870.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.326466178894043,
|
|
"epoch": 1.2536023054755043,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.00048500190004697595,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.2121969372034073,
|
|
"num_tokens": 29925180.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.2325080871582035,
|
|
"epoch": 1.2540826128722382,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004849895901887974,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.21380835622549058,
|
|
"num_tokens": 29936433.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.314672756195068,
|
|
"epoch": 1.254562920268972,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004849772754552842,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.1985726237297058,
|
|
"num_tokens": 29948891.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.2738494873046875,
|
|
"epoch": 1.255043227665706,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048496495584672214,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.21319225281476975,
|
|
"num_tokens": 29960113.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.308318853378296,
|
|
"epoch": 1.2555235350624399,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048495263136339725,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.1985704407095909,
|
|
"num_tokens": 29972168.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.34911527633667,
|
|
"epoch": 1.2560038424591737,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004849403020055956,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.20133336037397384,
|
|
"num_tokens": 29982996.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.355523777008057,
|
|
"epoch": 1.2564841498559078,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048492796777360373,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.199578258395195,
|
|
"num_tokens": 29994088.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.404811668395996,
|
|
"epoch": 1.2569644572526417,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048491562866770767,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.20294545739889144,
|
|
"num_tokens": 30005403.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.309027671813965,
|
|
"epoch": 1.2574447646493756,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048490328468819404,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.2134782239794731,
|
|
"num_tokens": 30015961.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.309994268417358,
|
|
"epoch": 1.2579250720461095,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048489093583534945,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.20673038065433502,
|
|
"num_tokens": 30026670.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.295586490631104,
|
|
"epoch": 1.2584053794428434,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004848785821094606,
|
|
"loss": 5.0907,
|
|
"mean_token_accuracy": 0.2088955283164978,
|
|
"num_tokens": 30036711.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.355640602111817,
|
|
"epoch": 1.2588856868395775,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004848662235108142,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.19668724685907363,
|
|
"num_tokens": 30047587.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.369058561325073,
|
|
"epoch": 1.2593659942363113,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004848538600396973,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.2060765504837036,
|
|
"num_tokens": 30059348.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.334674549102783,
|
|
"epoch": 1.2598463016330452,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048484149169639694,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.20623685717582702,
|
|
"num_tokens": 30070485.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.266217803955078,
|
|
"epoch": 1.260326609029779,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004848291184812003,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.21557125598192214,
|
|
"num_tokens": 30081114.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.307503890991211,
|
|
"epoch": 1.260806916426513,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004848167403943945,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.20292728245258332,
|
|
"num_tokens": 30092634.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.30598258972168,
|
|
"epoch": 1.2612872238232469,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048480435743626703,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.20527009516954423,
|
|
"num_tokens": 30104205.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.3124174118042,
|
|
"epoch": 1.2617675312199808,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004847919696071054,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.20105741620063783,
|
|
"num_tokens": 30116978.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.3235023021698,
|
|
"epoch": 1.2622478386167146,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048477957690719716,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.20795579254627228,
|
|
"num_tokens": 30128549.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.340668869018555,
|
|
"epoch": 1.2627281460134485,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004847671793368301,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.20582612454891205,
|
|
"num_tokens": 30139492.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.28126540184021,
|
|
"epoch": 1.2632084534101824,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000484754776896292,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.20332895070314408,
|
|
"num_tokens": 30150450.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.399092817306519,
|
|
"epoch": 1.2636887608069165,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004847423695858708,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.20416964292526246,
|
|
"num_tokens": 30162204.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.4091370582580565,
|
|
"epoch": 1.2641690682036504,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048472995740585456,
|
|
"loss": 5.1158,
|
|
"mean_token_accuracy": 0.20212129652500152,
|
|
"num_tokens": 30172574.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.228682899475098,
|
|
"epoch": 1.2646493756003843,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004847175403565316,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.20649578124284745,
|
|
"num_tokens": 30183957.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.379299545288086,
|
|
"epoch": 1.2651296829971181,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048470511843818996,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.21059217751026155,
|
|
"num_tokens": 30194207.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.272221565246582,
|
|
"epoch": 1.265609990393852,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004846926916511182,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.2126378446817398,
|
|
"num_tokens": 30205180.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.288595581054688,
|
|
"epoch": 1.266090297790586,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004846802599956048,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.20442663878202438,
|
|
"num_tokens": 30217734.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.430343294143677,
|
|
"epoch": 1.26657060518732,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048466782347193847,
|
|
"loss": 5.3218,
|
|
"mean_token_accuracy": 0.19318536072969436,
|
|
"num_tokens": 30229835.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.406239032745361,
|
|
"epoch": 1.267050912584054,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048465538208040775,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.19637912064790725,
|
|
"num_tokens": 30241932.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.334412956237793,
|
|
"epoch": 1.2675312199807878,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048464293582130166,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.1996375486254692,
|
|
"num_tokens": 30253149.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.361319255828858,
|
|
"epoch": 1.2680115273775217,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004846304846949091,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.20498671084642411,
|
|
"num_tokens": 30264083.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.325912284851074,
|
|
"epoch": 1.2684918347742555,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048461802870151916,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.2105726808309555,
|
|
"num_tokens": 30274832.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.22253451347351,
|
|
"epoch": 1.2689721421709894,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00048460556784142106,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.2039416551589966,
|
|
"num_tokens": 30284945.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.3733154296875,
|
|
"epoch": 1.2694524495677233,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048459310211490406,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.21063536405563354,
|
|
"num_tokens": 30295133.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.339078330993653,
|
|
"epoch": 1.2699327569644572,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004845806315222576,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.19850462377071382,
|
|
"num_tokens": 30305268.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.231999731063842,
|
|
"epoch": 1.270413064361191,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004845681560637711,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.20705202370882034,
|
|
"num_tokens": 30317118.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.382595205307007,
|
|
"epoch": 1.270893371757925,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004845556757397344,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.19738674014806748,
|
|
"num_tokens": 30328684.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.4472630500793455,
|
|
"epoch": 1.271373679154659,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004845431905504372,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.19680536687374114,
|
|
"num_tokens": 30341433.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.286834955215454,
|
|
"epoch": 1.271853986551393,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048453070049616926,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.2148544356226921,
|
|
"num_tokens": 30353159.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.22610034942627,
|
|
"epoch": 1.2723342939481268,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048451820557722064,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.20492613017559053,
|
|
"num_tokens": 30363251.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.412603521347046,
|
|
"epoch": 1.2728146013448607,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004845057057938815,
|
|
"loss": 5.2012,
|
|
"mean_token_accuracy": 0.20237422436475755,
|
|
"num_tokens": 30375850.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.435606288909912,
|
|
"epoch": 1.2732949087415946,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048449320114644185,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.196502947807312,
|
|
"num_tokens": 30386839.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.336371803283692,
|
|
"epoch": 1.2737752161383284,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004844806916351922,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.19653100222349168,
|
|
"num_tokens": 30398872.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.283555173873902,
|
|
"epoch": 1.2742555235350626,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004844681772604229,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.2072995349764824,
|
|
"num_tokens": 30409581.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.372207975387573,
|
|
"epoch": 1.2747358309317964,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048445565802242454,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.2023988574743271,
|
|
"num_tokens": 30420209.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.3756507396697994,
|
|
"epoch": 1.2752161383285303,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004844431339214878,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.2070294514298439,
|
|
"num_tokens": 30432093.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.285613012313843,
|
|
"epoch": 1.2756964457252642,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004844306049579034,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.2047084614634514,
|
|
"num_tokens": 30442796.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.356792211532593,
|
|
"epoch": 1.276176753121998,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048441807113196216,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.19637279063463212,
|
|
"num_tokens": 30455226.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.434659671783447,
|
|
"epoch": 1.276657060518732,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048440553244395517,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.19661564230918885,
|
|
"num_tokens": 30467082.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.368526268005371,
|
|
"epoch": 1.2771373679154658,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048439298889417357,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.19788520336151122,
|
|
"num_tokens": 30479051.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.330491733551026,
|
|
"epoch": 1.2776176753121997,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048438044048290847,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.20350819528102876,
|
|
"num_tokens": 30489989.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.361014938354492,
|
|
"epoch": 1.2780979827089336,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048436788721045135,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.20400741547346116,
|
|
"num_tokens": 30501533.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.313574743270874,
|
|
"epoch": 1.2785782901056677,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004843553290770935,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.2034912034869194,
|
|
"num_tokens": 30512231.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.310039758682251,
|
|
"epoch": 1.2790585975024016,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004843427660831266,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.20351369082927703,
|
|
"num_tokens": 30523204.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.407680702209473,
|
|
"epoch": 1.2795389048991355,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048433019822884235,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.19203908890485763,
|
|
"num_tokens": 30534956.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.330079650878906,
|
|
"epoch": 1.2800192122958693,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004843176255145325,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.207986082136631,
|
|
"num_tokens": 30545938.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.339921236038208,
|
|
"epoch": 1.2804995196926032,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004843050479404888,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.2096344858407974,
|
|
"num_tokens": 30557323.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.3202189922332765,
|
|
"epoch": 1.280979827089337,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048429246550700343,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.20463781505823136,
|
|
"num_tokens": 30569960.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.258479356765747,
|
|
"epoch": 1.2814601344860712,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004842798782143686,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.1994305208325386,
|
|
"num_tokens": 30581904.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.328444719314575,
|
|
"epoch": 1.281940441882805,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048426728606287627,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.20932208150625228,
|
|
"num_tokens": 30592955.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.3360802173614506,
|
|
"epoch": 1.282420749279539,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004842546890528191,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.2063537433743477,
|
|
"num_tokens": 30604020.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.292958211898804,
|
|
"epoch": 1.2829010566762729,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004842420871844893,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.1985606551170349,
|
|
"num_tokens": 30615623.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.349683237075806,
|
|
"epoch": 1.2833813640730067,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004842294804581796,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.20456679314374923,
|
|
"num_tokens": 30626258.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.3351184844970705,
|
|
"epoch": 1.2838616714697406,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048421686887418266,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.1923002451658249,
|
|
"num_tokens": 30637861.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.376630210876465,
|
|
"epoch": 1.2843419788664745,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004842042524327912,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.20593827217817307,
|
|
"num_tokens": 30648835.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.440468120574951,
|
|
"epoch": 1.2848222862632084,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004841916311342983,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.19308738708496093,
|
|
"num_tokens": 30659117.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.322964382171631,
|
|
"epoch": 1.2853025936599423,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004841790049789969,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.20512634366750718,
|
|
"num_tokens": 30670282.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.322717380523682,
|
|
"epoch": 1.2857829010566761,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048416637396718004,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.1959889143705368,
|
|
"num_tokens": 30681967.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.433527517318725,
|
|
"epoch": 1.2862632084534102,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004841537380991411,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.19976315647363663,
|
|
"num_tokens": 30692803.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.304678869247437,
|
|
"epoch": 1.2867435158501441,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048414109737517346,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.20984013825654985,
|
|
"num_tokens": 30704097.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.331026220321656,
|
|
"epoch": 1.287223823246878,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004841284517955706,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.1948239654302597,
|
|
"num_tokens": 30717983.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.271629333496094,
|
|
"epoch": 1.2877041306436119,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000484115801360626,
|
|
"loss": 4.9832,
|
|
"mean_token_accuracy": 0.2144336149096489,
|
|
"num_tokens": 30728446.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.221250820159912,
|
|
"epoch": 1.2881844380403458,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004841031460706335,
|
|
"loss": 4.9504,
|
|
"mean_token_accuracy": 0.21350116431713104,
|
|
"num_tokens": 30739587.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.225469636917114,
|
|
"epoch": 1.2886647454370797,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048409048592588683,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.20739102661609649,
|
|
"num_tokens": 30750093.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.315593433380127,
|
|
"epoch": 1.2891450528338138,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004840778209266799,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.20505328178405763,
|
|
"num_tokens": 30761692.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.2793889999389645,
|
|
"epoch": 1.2896253602305476,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048406515107330685,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.2072036311030388,
|
|
"num_tokens": 30773474.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.427170467376709,
|
|
"epoch": 1.2901056676272815,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048405247636606173,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.19088612198829652,
|
|
"num_tokens": 30785464.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.3426981449127195,
|
|
"epoch": 1.2905859750240154,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048403979680523894,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.20442133098840715,
|
|
"num_tokens": 30796343.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.327409362792968,
|
|
"epoch": 1.2910662824207493,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004840271123911328,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.20224396288394927,
|
|
"num_tokens": 30807795.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.333598232269287,
|
|
"epoch": 1.2915465898174832,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004840144231240377,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.19949955642223358,
|
|
"num_tokens": 30819629.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.30218734741211,
|
|
"epoch": 1.292026897214217,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004840017290042484,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.20655560195446016,
|
|
"num_tokens": 30831545.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.3127720832824705,
|
|
"epoch": 1.292507204610951,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048398903003205957,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.20276347994804383,
|
|
"num_tokens": 30843614.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.284966945648193,
|
|
"epoch": 1.2929875120076848,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048397632620776604,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.21090589612722396,
|
|
"num_tokens": 30853749.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.337891864776611,
|
|
"epoch": 1.293467819404419,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048396361753166276,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.2085747867822647,
|
|
"num_tokens": 30865065.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.335180854797363,
|
|
"epoch": 1.2939481268011528,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048395090400404466,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.19625414311885833,
|
|
"num_tokens": 30876746.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.369691848754883,
|
|
"epoch": 1.2944284341978867,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048393818562520715,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.20005687028169633,
|
|
"num_tokens": 30889543.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.370407676696777,
|
|
"epoch": 1.2949087415946205,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048392546239544535,
|
|
"loss": 5.163,
|
|
"mean_token_accuracy": 0.1987001344561577,
|
|
"num_tokens": 30901949.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.3753221988677975,
|
|
"epoch": 1.2953890489913544,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004839127343150547,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.20363592803478242,
|
|
"num_tokens": 30912660.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.300466585159302,
|
|
"epoch": 1.2958693563880883,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004839000013843307,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.2054862529039383,
|
|
"num_tokens": 30924276.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.284430980682373,
|
|
"epoch": 1.2963496637848224,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048388726360356894,
|
|
"loss": 5.0641,
|
|
"mean_token_accuracy": 0.20309265404939653,
|
|
"num_tokens": 30935169.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.429208517074585,
|
|
"epoch": 1.2968299711815563,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004838745209730653,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.1935327857732773,
|
|
"num_tokens": 30946116.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.382719278335571,
|
|
"epoch": 1.2973102785782902,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048386177349311535,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.2007138356566429,
|
|
"num_tokens": 30958509.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.348816871643066,
|
|
"epoch": 1.297790585975024,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004838490211640153,
|
|
"loss": 5.1597,
|
|
"mean_token_accuracy": 0.20271141082048416,
|
|
"num_tokens": 30969501.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.252405309677124,
|
|
"epoch": 1.298270893371758,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004838362639860611,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.20213902294635772,
|
|
"num_tokens": 30979768.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.257536506652832,
|
|
"epoch": 1.2987512007684918,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000483823501959549,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.20978472530841827,
|
|
"num_tokens": 30992020.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.3866595268249515,
|
|
"epoch": 1.2992315081652257,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00048381073508477527,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.19902147948741913,
|
|
"num_tokens": 31004081.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.400084209442139,
|
|
"epoch": 1.2997118155619596,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048379796336203625,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.19574200063943864,
|
|
"num_tokens": 31015776.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.336989879608154,
|
|
"epoch": 1.3001921229586935,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004837851867916286,
|
|
"loss": 5.0572,
|
|
"mean_token_accuracy": 0.20255800038576127,
|
|
"num_tokens": 31028066.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.26880784034729,
|
|
"epoch": 1.3006724303554273,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004837724053738488,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.20293700993061065,
|
|
"num_tokens": 31040234.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.327396488189697,
|
|
"epoch": 1.3011527377521614,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048375961910899373,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.20297430604696273,
|
|
"num_tokens": 31051158.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.4304670810699465,
|
|
"epoch": 1.3016330451488953,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004837468279973602,
|
|
"loss": 5.1708,
|
|
"mean_token_accuracy": 0.20110202878713607,
|
|
"num_tokens": 31063404.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.3542815208435055,
|
|
"epoch": 1.3021133525456292,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004837340320392451,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.2039550557732582,
|
|
"num_tokens": 31073845.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.271122741699219,
|
|
"epoch": 1.302593659942363,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048372123123494563,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.1971679672598839,
|
|
"num_tokens": 31086914.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.350509691238403,
|
|
"epoch": 1.303073967339097,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000483708425584759,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.21023936867713927,
|
|
"num_tokens": 31098627.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.457568264007568,
|
|
"epoch": 1.3035542747358309,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004836956150889825,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.19631621092557908,
|
|
"num_tokens": 31110064.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.370202970504761,
|
|
"epoch": 1.304034582132565,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004836827997479134,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.21120267808437349,
|
|
"num_tokens": 31121572.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.398817873001098,
|
|
"epoch": 1.3045148895292988,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004836699795618494,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.19796111285686493,
|
|
"num_tokens": 31133276.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.344299602508545,
|
|
"epoch": 1.3049951969260327,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004836571545310881,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.19892845749855043,
|
|
"num_tokens": 31144524.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.308568382263184,
|
|
"epoch": 1.3054755043227666,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048364432465592723,
|
|
"loss": 5.0907,
|
|
"mean_token_accuracy": 0.2100561410188675,
|
|
"num_tokens": 31155775.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.3069658279418945,
|
|
"epoch": 1.3059558117195005,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004836314899366647,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.20779447853565217,
|
|
"num_tokens": 31166176.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.337185430526733,
|
|
"epoch": 1.3064361191162344,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048361865037359846,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.20149748474359513,
|
|
"num_tokens": 31178568.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.374857091903687,
|
|
"epoch": 1.3069164265129682,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048360580596702664,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.20129059106111527,
|
|
"num_tokens": 31188897.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.356337547302246,
|
|
"epoch": 1.3073967339097021,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048359295671724744,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.20114662051200866,
|
|
"num_tokens": 31201370.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.324505567550659,
|
|
"epoch": 1.307877041306436,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004835801026245592,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.20189398527145386,
|
|
"num_tokens": 31212704.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.367878150939942,
|
|
"epoch": 1.30835734870317,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048356724368926035,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.203536319732666,
|
|
"num_tokens": 31224447.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.384316873550415,
|
|
"epoch": 1.308837656099904,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048355437991164937,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.20713951587677001,
|
|
"num_tokens": 31235648.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.316817378997802,
|
|
"epoch": 1.3093179634966379,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000483541511292025,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.20163041800260545,
|
|
"num_tokens": 31248330.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.4073339939117435,
|
|
"epoch": 1.3097982708933718,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048352863783068594,
|
|
"loss": 5.2053,
|
|
"mean_token_accuracy": 0.20048494189977645,
|
|
"num_tokens": 31260036.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.286585998535156,
|
|
"epoch": 1.3102785782901056,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048351575952793117,
|
|
"loss": 5.0006,
|
|
"mean_token_accuracy": 0.20814769119024276,
|
|
"num_tokens": 31271473.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.184717988967895,
|
|
"epoch": 1.3107588856868395,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004835028763840595,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.21636545658111572,
|
|
"num_tokens": 31282045.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.372507524490357,
|
|
"epoch": 1.3112391930835736,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004834899883993703,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.19954511970281602,
|
|
"num_tokens": 31292644.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.350517129898071,
|
|
"epoch": 1.3117195004803075,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048347709557416263,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.20851929038763045,
|
|
"num_tokens": 31304422.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.219803714752198,
|
|
"epoch": 1.3121998078770414,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004834641979087359,
|
|
"loss": 5.0572,
|
|
"mean_token_accuracy": 0.2028743028640747,
|
|
"num_tokens": 31314845.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.408175468444824,
|
|
"epoch": 1.3126801152737753,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004834512954033894,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.20442388206720352,
|
|
"num_tokens": 31325669.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.332046175003052,
|
|
"epoch": 1.3131604226705091,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048343838805842284,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.20781288743019105,
|
|
"num_tokens": 31336023.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.358465147018433,
|
|
"epoch": 1.313640730067243,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048342547587413583,
|
|
"loss": 5.2018,
|
|
"mean_token_accuracy": 0.20342886298894883,
|
|
"num_tokens": 31347146.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.351632785797119,
|
|
"epoch": 1.314121037463977,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004834125588508282,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.20031936317682267,
|
|
"num_tokens": 31357616.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.392553091049194,
|
|
"epoch": 1.3146013448607108,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004833996369887998,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.20433993339538575,
|
|
"num_tokens": 31369189.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.309914493560791,
|
|
"epoch": 1.3150816522574447,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048338671028835063,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.21009437143802642,
|
|
"num_tokens": 31380841.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.235025644302368,
|
|
"epoch": 1.3155619596541785,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048337377874978086,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.2137564018368721,
|
|
"num_tokens": 31393092.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.297566986083984,
|
|
"epoch": 1.3160422670509127,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048336084237339067,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.2014407128095627,
|
|
"num_tokens": 31404228.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.379121112823486,
|
|
"epoch": 1.3165225744476465,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004833479011594804,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.19400792866945266,
|
|
"num_tokens": 31416233.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.4252604961395265,
|
|
"epoch": 1.3170028818443804,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048333495510835057,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.19987989068031312,
|
|
"num_tokens": 31427787.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.176429224014282,
|
|
"epoch": 1.3174831892411143,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048332200422030163,
|
|
"loss": 4.9828,
|
|
"mean_token_accuracy": 0.209286168217659,
|
|
"num_tokens": 31438736.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.207972192764283,
|
|
"epoch": 1.3179634966378482,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004833090484956345,
|
|
"loss": 5.0015,
|
|
"mean_token_accuracy": 0.20614672154188157,
|
|
"num_tokens": 31449225.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.421485424041748,
|
|
"epoch": 1.318443804034582,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048329608793464966,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.2014114335179329,
|
|
"num_tokens": 31461223.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.448719596862793,
|
|
"epoch": 1.3189241114313162,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004832831225376482,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.1978832259774208,
|
|
"num_tokens": 31472397.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.301409721374512,
|
|
"epoch": 1.31940441882805,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004832701523049312,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.21165216714143753,
|
|
"num_tokens": 31484079.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.255009460449219,
|
|
"epoch": 1.319884726224784,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004832571772367997,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.20456670522689818,
|
|
"num_tokens": 31496732.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.283354377746582,
|
|
"epoch": 1.3203650336215178,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048324419733355485,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.21242745220661163,
|
|
"num_tokens": 31507601.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.288519096374512,
|
|
"epoch": 1.3208453410182517,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048323121259549805,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.20451494455337524,
|
|
"num_tokens": 31519551.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.266066646575927,
|
|
"epoch": 1.3213256484149856,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048321822302293095,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.20409016013145448,
|
|
"num_tokens": 31531531.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.326609373092651,
|
|
"epoch": 1.3218059558117194,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004832052286161549,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.1970664381980896,
|
|
"num_tokens": 31542386.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.3591383934021,
|
|
"epoch": 1.3222862632084533,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048319222937547176,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20662872046232222,
|
|
"num_tokens": 31554142.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.3198089599609375,
|
|
"epoch": 1.3227665706051872,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048317922530118323,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.1990684062242508,
|
|
"num_tokens": 31566687.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.3402245998382565,
|
|
"epoch": 1.3232468780019213,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004831662163935912,
|
|
"loss": 5.2159,
|
|
"mean_token_accuracy": 0.19487221539020538,
|
|
"num_tokens": 31577893.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.460074853897095,
|
|
"epoch": 1.3237271853986552,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048315320265299784,
|
|
"loss": 5.2615,
|
|
"mean_token_accuracy": 0.19661335051059722,
|
|
"num_tokens": 31590483.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.378990507125854,
|
|
"epoch": 1.324207492795389,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048314018407970516,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.20219608396291733,
|
|
"num_tokens": 31601373.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.315431404113769,
|
|
"epoch": 1.324687800192123,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048312716067401535,
|
|
"loss": 5.1786,
|
|
"mean_token_accuracy": 0.1981915459036827,
|
|
"num_tokens": 31613981.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.402023792266846,
|
|
"epoch": 1.3251681075888568,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000483114132436231,
|
|
"loss": 5.1669,
|
|
"mean_token_accuracy": 0.19695232659578324,
|
|
"num_tokens": 31626727.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.2824366092681885,
|
|
"epoch": 1.3256484149855907,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004831010993666545,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.20715029239654542,
|
|
"num_tokens": 31638519.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.205135202407837,
|
|
"epoch": 1.3261287223823248,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004830880614655884,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.20082445591688156,
|
|
"num_tokens": 31649184.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.309788513183594,
|
|
"epoch": 1.3266090297790587,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048307501873333527,
|
|
"loss": 5.1338,
|
|
"mean_token_accuracy": 0.20498052686452867,
|
|
"num_tokens": 31660266.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.312769794464112,
|
|
"epoch": 1.3270893371757926,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004830619711701982,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.2089269131422043,
|
|
"num_tokens": 31670841.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.311260032653808,
|
|
"epoch": 1.3275696445725265,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004830489187764799,
|
|
"loss": 5.0907,
|
|
"mean_token_accuracy": 0.201044499874115,
|
|
"num_tokens": 31680786.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.25435242652893,
|
|
"epoch": 1.3280499519692603,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004830358615524835,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.20657743662595748,
|
|
"num_tokens": 31692639.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.436718320846557,
|
|
"epoch": 1.3285302593659942,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048302279949851215,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.2028724208474159,
|
|
"num_tokens": 31703520.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.307067918777466,
|
|
"epoch": 1.329010566762728,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048300973261486906,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.21658166497945786,
|
|
"num_tokens": 31715659.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.307044506072998,
|
|
"epoch": 1.329490874159462,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004829966609018577,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.19999735653400422,
|
|
"num_tokens": 31727896.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.312028789520264,
|
|
"epoch": 1.3299711815561959,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048298358435978146,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.21006526350975036,
|
|
"num_tokens": 31738618.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.34788966178894,
|
|
"epoch": 1.3304514889529298,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048297050298894394,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.19916528165340425,
|
|
"num_tokens": 31750306.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.381071281433106,
|
|
"epoch": 1.3309317963496639,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004829574167896489,
|
|
"loss": 5.2324,
|
|
"mean_token_accuracy": 0.1933632582426071,
|
|
"num_tokens": 31762015.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.334798097610474,
|
|
"epoch": 1.3314121037463977,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048294432576220027,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.2058800205588341,
|
|
"num_tokens": 31774120.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.295610952377319,
|
|
"epoch": 1.3318924111431316,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004829312299069017,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.21235489696264268,
|
|
"num_tokens": 31785485.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.348644399642945,
|
|
"epoch": 1.3323727185398655,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048291812922405755,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.20100979655981063,
|
|
"num_tokens": 31795621.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.277051734924316,
|
|
"epoch": 1.3328530259365994,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004829050237139717,
|
|
"loss": 5.0357,
|
|
"mean_token_accuracy": 0.2080575257539749,
|
|
"num_tokens": 31806761.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.36189284324646,
|
|
"epoch": 1.3333333333333333,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004828919133769486,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.19850631654262543,
|
|
"num_tokens": 31817996.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.353771162033081,
|
|
"epoch": 1.3338136407300674,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004828787982132926,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.20233895778656005,
|
|
"num_tokens": 31829888.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.407914876937866,
|
|
"epoch": 1.3342939481268012,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048286567822330815,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.199880650639534,
|
|
"num_tokens": 31842582.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.236108827590942,
|
|
"epoch": 1.3347742555235351,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004828525534072999,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.2108187898993492,
|
|
"num_tokens": 31854765.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.310104513168335,
|
|
"epoch": 1.335254562920269,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048283942376557254,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.2035674199461937,
|
|
"num_tokens": 31865505.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.275545406341553,
|
|
"epoch": 1.3357348703170029,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048282628929843097,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.20467293113470078,
|
|
"num_tokens": 31876599.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.332110786437989,
|
|
"epoch": 1.3362151777137368,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048281315000617996,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.20581955909729005,
|
|
"num_tokens": 31887292.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.3436487197875975,
|
|
"epoch": 1.3366954851104706,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004828000058891248,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.19646859765052796,
|
|
"num_tokens": 31899018.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.279466581344605,
|
|
"epoch": 1.3371757925072045,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004827868569475706,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.21112978905439378,
|
|
"num_tokens": 31910402.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.329484558105468,
|
|
"epoch": 1.3376560999039384,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048277370318182243,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.1966124728322029,
|
|
"num_tokens": 31921792.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.385334491729736,
|
|
"epoch": 1.3381364073006723,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048276054459218596,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.1974025323987007,
|
|
"num_tokens": 31932786.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.364981555938721,
|
|
"epoch": 1.3386167146974064,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048274738117896643,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.20311573892831802,
|
|
"num_tokens": 31944286.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.270573472976684,
|
|
"epoch": 1.3390970220941403,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048273421294246966,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.19877077639102936,
|
|
"num_tokens": 31956304.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.324054193496704,
|
|
"epoch": 1.3395773294908742,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048272103988300134,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.206067818403244,
|
|
"num_tokens": 31968978.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.364972162246704,
|
|
"epoch": 1.340057636887608,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004827078620008672,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.19601981937885285,
|
|
"num_tokens": 31980133.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.316045331954956,
|
|
"epoch": 1.340537944284342,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048269467929637337,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.21538587808609008,
|
|
"num_tokens": 31990331.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.322788858413697,
|
|
"epoch": 1.341018251681076,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048268149176982576,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.20191341489553452,
|
|
"num_tokens": 32001956.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.391653156280517,
|
|
"epoch": 1.34149855907781,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048266829942153055,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.2021912381052971,
|
|
"num_tokens": 32013577.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.464861726760864,
|
|
"epoch": 1.3419788664745438,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048265510225179413,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.19848244339227678,
|
|
"num_tokens": 32025751.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.2950342178344725,
|
|
"epoch": 1.3424591738712777,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004826419002609229,
|
|
"loss": 5.1836,
|
|
"mean_token_accuracy": 0.19990646839141846,
|
|
"num_tokens": 32036592.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.40626711845398,
|
|
"epoch": 1.3429394812680115,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048262869344922326,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.2031440943479538,
|
|
"num_tokens": 32048122.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.350680685043335,
|
|
"epoch": 1.3434197886647454,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048261548181700186,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.20183824598789216,
|
|
"num_tokens": 32058673.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.1969029903411865,
|
|
"epoch": 1.3439000960614793,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004826022653645655,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.207687845826149,
|
|
"num_tokens": 32070219.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.3754195213317875,
|
|
"epoch": 1.3443804034582132,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000482589044092221,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.20194545686244963,
|
|
"num_tokens": 32081883.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.475633955001831,
|
|
"epoch": 1.344860710854947,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048257581800027527,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.19760601222515106,
|
|
"num_tokens": 32094107.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.300419282913208,
|
|
"epoch": 1.345341018251681,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004825625870890354,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.2045585945248604,
|
|
"num_tokens": 32105242.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.3196155548095705,
|
|
"epoch": 1.345821325648415,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004825493513588086,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.2054128095507622,
|
|
"num_tokens": 32117326.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.378720808029175,
|
|
"epoch": 1.346301633045149,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048253611080990226,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.19973362237215042,
|
|
"num_tokens": 32129002.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.375880527496338,
|
|
"epoch": 1.3467819404418828,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004825228654426236,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.20060565322637558,
|
|
"num_tokens": 32140380.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.282519292831421,
|
|
"epoch": 1.3472622478386167,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004825096152572803,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.21106188297271727,
|
|
"num_tokens": 32151806.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.309278202056885,
|
|
"epoch": 1.3477425552353506,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048249636025417974,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.20241262316703795,
|
|
"num_tokens": 32163426.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.4002800464630125,
|
|
"epoch": 1.3482228626320845,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048248310043362997,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.20910084694623948,
|
|
"num_tokens": 32174349.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.419577693939209,
|
|
"epoch": 1.3487031700288186,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004824698357959386,
|
|
"loss": 5.2176,
|
|
"mean_token_accuracy": 0.19922328740358353,
|
|
"num_tokens": 32185382.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.294965171813965,
|
|
"epoch": 1.3491834774255524,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048245656634141385,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.20888923704624177,
|
|
"num_tokens": 32195687.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.324030542373658,
|
|
"epoch": 1.3496637848222863,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048244329207036354,
|
|
"loss": 5.0651,
|
|
"mean_token_accuracy": 0.21017236709594728,
|
|
"num_tokens": 32205973.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.294116497039795,
|
|
"epoch": 1.3501440922190202,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048243001298309604,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.2027316302061081,
|
|
"num_tokens": 32217469.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.309836149215698,
|
|
"epoch": 1.350624399615754,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048241672907991954,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.2043677568435669,
|
|
"num_tokens": 32228257.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.331676197052002,
|
|
"epoch": 1.351104707012488,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004824034403611424,
|
|
"loss": 5.1321,
|
|
"mean_token_accuracy": 0.20526184886693954,
|
|
"num_tokens": 32239420.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.348117351531982,
|
|
"epoch": 1.3515850144092219,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004823901468270733,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.2043563351035118,
|
|
"num_tokens": 32250962.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.309895706176758,
|
|
"epoch": 1.3520653218059557,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004823768484780209,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.20718141347169877,
|
|
"num_tokens": 32262310.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.2869795799255375,
|
|
"epoch": 1.3525456292026896,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048236354531429375,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.2090473234653473,
|
|
"num_tokens": 32273373.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.406088542938233,
|
|
"epoch": 1.3530259365994235,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004823502373362009,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.20260330140590668,
|
|
"num_tokens": 32285020.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.264684820175171,
|
|
"epoch": 1.3535062439961576,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004823369245440512,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.1996792122721672,
|
|
"num_tokens": 32296224.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.3023439884185795,
|
|
"epoch": 1.3539865513928915,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048232360693815387,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.20575822293758392,
|
|
"num_tokens": 32306913.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.365391254425049,
|
|
"epoch": 1.3544668587896254,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048231028451881786,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.2017486184835434,
|
|
"num_tokens": 32317981.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.201748847961426,
|
|
"epoch": 1.3549471661863592,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004822969572863527,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.20958283096551894,
|
|
"num_tokens": 32329656.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.353098440170288,
|
|
"epoch": 1.3554274735830931,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048228362524106776,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.2124091938138008,
|
|
"num_tokens": 32339460.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.303189134597778,
|
|
"epoch": 1.3559077809798272,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048227028838327253,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.20099968016147612,
|
|
"num_tokens": 32351237.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.306602716445923,
|
|
"epoch": 1.356388088376561,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048225694671327665,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.20421310961246492,
|
|
"num_tokens": 32362368.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.251869869232178,
|
|
"epoch": 1.356868395773295,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004822436002313899,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.21089618653059006,
|
|
"num_tokens": 32373738.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.336496448516845,
|
|
"epoch": 1.3573487031700289,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004822302489379222,
|
|
"loss": 5.1316,
|
|
"mean_token_accuracy": 0.20297233164310455,
|
|
"num_tokens": 32384274.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.233032846450806,
|
|
"epoch": 1.3578290105667628,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048221689283318335,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.21008917838335037,
|
|
"num_tokens": 32395692.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.267216920852661,
|
|
"epoch": 1.3583093179634966,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004822035319174837,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.20631051063537598,
|
|
"num_tokens": 32407367.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.372434139251709,
|
|
"epoch": 1.3587896253602305,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004821901661911332,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.20439281016588212,
|
|
"num_tokens": 32418753.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.366323947906494,
|
|
"epoch": 1.3592699327569644,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004821767956544423,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.2034110829234123,
|
|
"num_tokens": 32429499.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.233653926849366,
|
|
"epoch": 1.3597502401536983,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004821634203077214,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.20325486063957215,
|
|
"num_tokens": 32441246.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.368150615692139,
|
|
"epoch": 1.3602305475504322,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000482150040151281,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.19597090035676956,
|
|
"num_tokens": 32452953.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.371655035018921,
|
|
"epoch": 1.3607108549471663,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004821366551854318,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.20299185961484909,
|
|
"num_tokens": 32464030.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.2160319805145265,
|
|
"epoch": 1.3611911623439001,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004821232654104845,
|
|
"loss": 4.9463,
|
|
"mean_token_accuracy": 0.21027858853340148,
|
|
"num_tokens": 32475091.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.278345537185669,
|
|
"epoch": 1.361671469740634,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048210987082675005,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.20232982635498048,
|
|
"num_tokens": 32486047.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.312158203125,
|
|
"epoch": 1.362151777137368,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048209647143453946,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.20661706626415252,
|
|
"num_tokens": 32497141.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.33510193824768,
|
|
"epoch": 1.3626320845341018,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048208306723416356,
|
|
"loss": 5.1185,
|
|
"mean_token_accuracy": 0.2002816841006279,
|
|
"num_tokens": 32509282.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.335775327682495,
|
|
"epoch": 1.3631123919308357,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004820696582259339,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.19599066078662872,
|
|
"num_tokens": 32521383.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.2759768009185795,
|
|
"epoch": 1.3635926993275698,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004820562444101616,
|
|
"loss": 5.0774,
|
|
"mean_token_accuracy": 0.2044411778450012,
|
|
"num_tokens": 32533168.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.284418773651123,
|
|
"epoch": 1.3640730067243036,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004820428257871581,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.20707476437091826,
|
|
"num_tokens": 32545333.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.265059328079223,
|
|
"epoch": 1.3645533141210375,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004820294023572351,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.20724462121725082,
|
|
"num_tokens": 32556665.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.370101261138916,
|
|
"epoch": 1.3650336215177714,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000482015974120704,
|
|
"loss": 5.2606,
|
|
"mean_token_accuracy": 0.19468679130077363,
|
|
"num_tokens": 32568318.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.356539916992188,
|
|
"epoch": 1.3655139289145053,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048200254107787677,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.20446783900260926,
|
|
"num_tokens": 32580010.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.356628894805908,
|
|
"epoch": 1.3659942363112392,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048198910322906516,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.19546498358249664,
|
|
"num_tokens": 32592075.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.4201192378997805,
|
|
"epoch": 1.366474543707973,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048197566057458125,
|
|
"loss": 5.2494,
|
|
"mean_token_accuracy": 0.20288346111774444,
|
|
"num_tokens": 32604548.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.41939492225647,
|
|
"epoch": 1.366954851104707,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000481962213114737,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.2002335876226425,
|
|
"num_tokens": 32616036.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.278404283523559,
|
|
"epoch": 1.3674351585014408,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004819487608498448,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.20552545934915542,
|
|
"num_tokens": 32628157.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.43530011177063,
|
|
"epoch": 1.3679154658981747,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048193530378021687,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.19844263941049575,
|
|
"num_tokens": 32640571.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.324884653091431,
|
|
"epoch": 1.3683957732949088,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048192184190616567,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.20002733469009398,
|
|
"num_tokens": 32652005.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.2830933094024655,
|
|
"epoch": 1.3688760806916427,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004819083752280037,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.20887762755155564,
|
|
"num_tokens": 32663655.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.26043291091919,
|
|
"epoch": 1.3693563880883766,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048189490374604373,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.19694132059812547,
|
|
"num_tokens": 32675419.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.349244117736816,
|
|
"epoch": 1.3698366954851104,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004818814274605983,
|
|
"loss": 5.0933,
|
|
"mean_token_accuracy": 0.20281608998775483,
|
|
"num_tokens": 32686680.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.263651609420776,
|
|
"epoch": 1.3703170028818443,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004818679463719805,
|
|
"loss": 5.0132,
|
|
"mean_token_accuracy": 0.21258011609315872,
|
|
"num_tokens": 32697321.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.1938032627105715,
|
|
"epoch": 1.3707973102785782,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004818544604805033,
|
|
"loss": 5.1226,
|
|
"mean_token_accuracy": 0.19536699652671813,
|
|
"num_tokens": 32708885.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.370037031173706,
|
|
"epoch": 1.3712776176753123,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004818409697864798,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.20941568166017532,
|
|
"num_tokens": 32720517.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.355639505386352,
|
|
"epoch": 1.3717579250720462,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048182747429022303,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.2054177075624466,
|
|
"num_tokens": 32731072.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.421905136108398,
|
|
"epoch": 1.37223823246878,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004818139739920465,
|
|
"loss": 5.1914,
|
|
"mean_token_accuracy": 0.20285213738679886,
|
|
"num_tokens": 32742117.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.285949182510376,
|
|
"epoch": 1.372718539865514,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004818004688922637,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.20148088335990905,
|
|
"num_tokens": 32753754.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.273839950561523,
|
|
"epoch": 1.3731988472622478,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000481786958991188,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.20738285034894943,
|
|
"num_tokens": 32766511.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.402833795547485,
|
|
"epoch": 1.3736791546589817,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048177344428913316,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.2027527093887329,
|
|
"num_tokens": 32777715.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.397093009948731,
|
|
"epoch": 1.3741594620557156,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048175992478641293,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.20619010776281357,
|
|
"num_tokens": 32789132.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.4120677471160885,
|
|
"epoch": 1.3746397694524495,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004817464004833412,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.19753448218107222,
|
|
"num_tokens": 32800439.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.2900477886199955,
|
|
"epoch": 1.3751200768491834,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048173287138023204,
|
|
"loss": 5.0964,
|
|
"mean_token_accuracy": 0.20184248089790344,
|
|
"num_tokens": 32813605.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.420122194290161,
|
|
"epoch": 1.3756003842459175,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004817193374773993,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.2052524745464325,
|
|
"num_tokens": 32824225.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.416957855224609,
|
|
"epoch": 1.3760806916426513,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048170579877515753,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.191039477288723,
|
|
"num_tokens": 32836917.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.306473875045777,
|
|
"epoch": 1.3765609990393852,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004816922552738209,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.20788173228502274,
|
|
"num_tokens": 32847972.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.251850223541259,
|
|
"epoch": 1.377041306436119,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00048167870697370373,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.21205616742372513,
|
|
"num_tokens": 32858922.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.317171192169189,
|
|
"epoch": 1.377521613832853,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004816651538751207,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.20716217905282974,
|
|
"num_tokens": 32869788.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.447834539413452,
|
|
"epoch": 1.3780019212295869,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048165159597838664,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.1883351430296898,
|
|
"num_tokens": 32881678.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.391602277755737,
|
|
"epoch": 1.378482228626321,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000481638033283816,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.1988083690404892,
|
|
"num_tokens": 32894183.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.315912532806396,
|
|
"epoch": 1.3789625360230549,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048162446579172387,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.20627661496400834,
|
|
"num_tokens": 32906001.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.319640016555786,
|
|
"epoch": 1.3794428434197887,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004816108935024252,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.19860074371099473,
|
|
"num_tokens": 32917236.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.368699264526367,
|
|
"epoch": 1.3799231508165226,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048159731641623507,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.19798433035612106,
|
|
"num_tokens": 32929710.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.345403814315796,
|
|
"epoch": 1.3804034582132565,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004815837345334687,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.20611637979745864,
|
|
"num_tokens": 32941565.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.398605918884277,
|
|
"epoch": 1.3808837656099904,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004815701478544415,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.19542285352945327,
|
|
"num_tokens": 32952730.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.291153764724731,
|
|
"epoch": 1.3813640730067243,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048155655637946876,
|
|
"loss": 5.061,
|
|
"mean_token_accuracy": 0.20605909675359727,
|
|
"num_tokens": 32963589.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.335979652404785,
|
|
"epoch": 1.3818443804034581,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004815429601088662,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.20512252449989318,
|
|
"num_tokens": 32975008.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.38799409866333,
|
|
"epoch": 1.382324687800192,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004815293590429494,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.19260978400707246,
|
|
"num_tokens": 32986497.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.236591434478759,
|
|
"epoch": 1.382804995196926,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048151575318203417,
|
|
"loss": 4.9675,
|
|
"mean_token_accuracy": 0.21276138424873353,
|
|
"num_tokens": 32998298.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.400460147857666,
|
|
"epoch": 1.38328530259366,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048150214252643637,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.19561213105916977,
|
|
"num_tokens": 33010943.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.388495922088623,
|
|
"epoch": 1.3837656099903939,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000481488527076472,
|
|
"loss": 5.1284,
|
|
"mean_token_accuracy": 0.20546164512634277,
|
|
"num_tokens": 33022139.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.3526999950408936,
|
|
"epoch": 1.3842459173871278,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004814749068324571,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.20119890868663787,
|
|
"num_tokens": 33034653.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.275128412246704,
|
|
"epoch": 1.3847262247838616,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048146128179470804,
|
|
"loss": 4.9046,
|
|
"mean_token_accuracy": 0.22393604516983032,
|
|
"num_tokens": 33044339.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.261203718185425,
|
|
"epoch": 1.3852065321805955,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004814476519635411,
|
|
"loss": 5.1222,
|
|
"mean_token_accuracy": 0.20802053213119506,
|
|
"num_tokens": 33055418.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.35328631401062,
|
|
"epoch": 1.3856868395773294,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048143401733927274,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.20355482399463654,
|
|
"num_tokens": 33067239.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.318495082855224,
|
|
"epoch": 1.3861671469740635,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048142037792221943,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.20811743885278702,
|
|
"num_tokens": 33079101.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.323478412628174,
|
|
"epoch": 1.3866474543707974,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004814067337126978,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.2097962960600853,
|
|
"num_tokens": 33090265.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.321341514587402,
|
|
"epoch": 1.3871277617675313,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004813930847110248,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.20941036343574523,
|
|
"num_tokens": 33101724.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.2869274616241455,
|
|
"epoch": 1.3876080691642652,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004813794309175173,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.20982307344675064,
|
|
"num_tokens": 33113111.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.368390274047852,
|
|
"epoch": 1.388088376560999,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048136577233249205,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.19650210589170455,
|
|
"num_tokens": 33123925.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.387375164031982,
|
|
"epoch": 1.388568683957733,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004813521089562666,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.19728047549724578,
|
|
"num_tokens": 33137400.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.264138078689575,
|
|
"epoch": 1.3890489913544668,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004813384407891577,
|
|
"loss": 5.0015,
|
|
"mean_token_accuracy": 0.21226510256528855,
|
|
"num_tokens": 33149326.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.37453145980835,
|
|
"epoch": 1.3895292987512007,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000481324767831483,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.19442261904478073,
|
|
"num_tokens": 33159904.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.29682765007019,
|
|
"epoch": 1.3900096061479346,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004813110900835598,
|
|
"loss": 5.0916,
|
|
"mean_token_accuracy": 0.20721136033535004,
|
|
"num_tokens": 33171701.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.2880464553833,
|
|
"epoch": 1.3904899135446687,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004812974075457058,
|
|
"loss": 4.9959,
|
|
"mean_token_accuracy": 0.20940209031105042,
|
|
"num_tokens": 33181598.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.2654839038848875,
|
|
"epoch": 1.3909702209414025,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048128372021823845,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.2095649152994156,
|
|
"num_tokens": 33192674.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.247911977767944,
|
|
"epoch": 1.3914505283381364,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048127002810147574,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.205610491335392,
|
|
"num_tokens": 33203356.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.340231943130493,
|
|
"epoch": 1.3919308357348703,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004812563311957355,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.19978511035442353,
|
|
"num_tokens": 33215471.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.336901521682739,
|
|
"epoch": 1.3924111431316042,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004812426295013356,
|
|
"loss": 5.104,
|
|
"mean_token_accuracy": 0.19993801563978195,
|
|
"num_tokens": 33227656.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.3663877010345455,
|
|
"epoch": 1.392891450528338,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048122892301859433,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.19964019656181337,
|
|
"num_tokens": 33239752.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.381220912933349,
|
|
"epoch": 1.3933717579250722,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048121521174782983,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.20105863660573958,
|
|
"num_tokens": 33251352.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.392067193984985,
|
|
"epoch": 1.393852065321806,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048120149568936044,
|
|
"loss": 5.1432,
|
|
"mean_token_accuracy": 0.19658627957105637,
|
|
"num_tokens": 33262276.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.4076904296875,
|
|
"epoch": 1.39433237271854,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004811877748435046,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.20201178938150405,
|
|
"num_tokens": 33273615.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.348117876052856,
|
|
"epoch": 1.3948126801152738,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004811740492105809,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.2087197408080101,
|
|
"num_tokens": 33283990.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.284138298034668,
|
|
"epoch": 1.3952929875120077,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000481160318790908,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.2084584653377533,
|
|
"num_tokens": 33295472.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.339506769180298,
|
|
"epoch": 1.3957732949087416,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048114658358480467,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.20297127217054367,
|
|
"num_tokens": 33306742.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.390817928314209,
|
|
"epoch": 1.3962536023054755,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048113284359258977,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.20161493867635727,
|
|
"num_tokens": 33317737.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.30466628074646,
|
|
"epoch": 1.3967339097022093,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048111909881458234,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.19905370771884917,
|
|
"num_tokens": 33329673.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.2488072395324705,
|
|
"epoch": 1.3972142170989432,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048110534925110146,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.21547752916812896,
|
|
"num_tokens": 33342047.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.290526866912842,
|
|
"epoch": 1.397694524495677,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004810915949024664,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.21022906452417373,
|
|
"num_tokens": 33353287.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.380938577651977,
|
|
"epoch": 1.3981748318924112,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004810778357689965,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.2094163179397583,
|
|
"num_tokens": 33365465.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.303643274307251,
|
|
"epoch": 1.398655139289145,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048106407185101116,
|
|
"loss": 5.0912,
|
|
"mean_token_accuracy": 0.20320398062467576,
|
|
"num_tokens": 33376680.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.2814196109771725,
|
|
"epoch": 1.399135446685879,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048105030314883,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.20694720298051833,
|
|
"num_tokens": 33387995.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.29057765007019,
|
|
"epoch": 1.3996157540826129,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004810365296627725,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.20241359919309615,
|
|
"num_tokens": 33400455.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.334546041488648,
|
|
"epoch": 1.4000960614793467,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004810227513931587,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.19994840621948243,
|
|
"num_tokens": 33413264.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.27220983505249,
|
|
"epoch": 1.4005763688760806,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004810089683403084,
|
|
"loss": 4.9951,
|
|
"mean_token_accuracy": 0.21866356283426286,
|
|
"num_tokens": 33423516.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.321939325332641,
|
|
"epoch": 1.4010566762728147,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004809951805045415,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.20145438462495804,
|
|
"num_tokens": 33434952.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.322064733505249,
|
|
"epoch": 1.4015369836695486,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048098138788617815,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.20345403552055358,
|
|
"num_tokens": 33447025.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.342529726028443,
|
|
"epoch": 1.4020172910662825,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004809675904855387,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.20025157332420349,
|
|
"num_tokens": 33459990.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.336059951782227,
|
|
"epoch": 1.4024975984630164,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048095378830294343,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.2082558959722519,
|
|
"num_tokens": 33471334.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.341049146652222,
|
|
"epoch": 1.4029779058597502,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048093998133871276,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.20245918333530427,
|
|
"num_tokens": 33483744.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.3575904846191404,
|
|
"epoch": 1.4034582132564841,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004809261695931671,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.2035977154970169,
|
|
"num_tokens": 33496532.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.317589378356933,
|
|
"epoch": 1.403938520653218,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004809123530666273,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.21142247766256334,
|
|
"num_tokens": 33507545.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.333917474746704,
|
|
"epoch": 1.4044188280499519,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004808985317594142,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.2109460636973381,
|
|
"num_tokens": 33519232.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.2535604476928714,
|
|
"epoch": 1.4048991354466858,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048088470567184854,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.2031296119093895,
|
|
"num_tokens": 33531088.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.352203273773194,
|
|
"epoch": 1.4053794428434199,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048087087480425133,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.19971330165863038,
|
|
"num_tokens": 33543991.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.420684576034546,
|
|
"epoch": 1.4058597502401537,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004808570391569437,
|
|
"loss": 5.2051,
|
|
"mean_token_accuracy": 0.1991143688559532,
|
|
"num_tokens": 33555303.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.333457040786743,
|
|
"epoch": 1.4063400576368876,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048084319873024694,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.19936081320047377,
|
|
"num_tokens": 33565587.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.328165531158447,
|
|
"epoch": 1.4068203650336215,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004808293535244823,
|
|
"loss": 5.0249,
|
|
"mean_token_accuracy": 0.20404641926288605,
|
|
"num_tokens": 33576874.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.294593572616577,
|
|
"epoch": 1.4073006724303554,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004808155035399712,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.21204702705144882,
|
|
"num_tokens": 33587703.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.250318622589111,
|
|
"epoch": 1.4077809798270893,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004808016487770354,
|
|
"loss": 5.0112,
|
|
"mean_token_accuracy": 0.21183853596448898,
|
|
"num_tokens": 33598487.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.276059627532959,
|
|
"epoch": 1.4082612872238234,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048078778923599637,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.19690126925706863,
|
|
"num_tokens": 33610838.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.31818995475769,
|
|
"epoch": 1.4087415946205573,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048077392491717593,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.20165991187095642,
|
|
"num_tokens": 33622726.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.29600510597229,
|
|
"epoch": 1.4092219020172911,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048076005582089597,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.20718360990285872,
|
|
"num_tokens": 33635922.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.434097862243652,
|
|
"epoch": 1.409702209414025,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048074618194747845,
|
|
"loss": 5.2462,
|
|
"mean_token_accuracy": 0.19366284757852553,
|
|
"num_tokens": 33648486.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.356406402587891,
|
|
"epoch": 1.410182516810759,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004807323032972456,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.20749374181032182,
|
|
"num_tokens": 33659812.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.303922557830811,
|
|
"epoch": 1.4106628242074928,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004807184198705196,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.2050963044166565,
|
|
"num_tokens": 33671878.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.231839799880982,
|
|
"epoch": 1.4111431316042267,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004807045316676226,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.20936548560857773,
|
|
"num_tokens": 33683759.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.370224332809448,
|
|
"epoch": 1.4116234390009605,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004806906386888773,
|
|
"loss": 5.2012,
|
|
"mean_token_accuracy": 0.19590017199516296,
|
|
"num_tokens": 33694085.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.349936771392822,
|
|
"epoch": 1.4121037463976944,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048067674093460607,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.2023450642824173,
|
|
"num_tokens": 33705810.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.329317569732666,
|
|
"epoch": 1.4125840537944283,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048066283840513175,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.20658555924892424,
|
|
"num_tokens": 33716798.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.258311414718628,
|
|
"epoch": 1.4130643611911624,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004806489311007769,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.21074948757886885,
|
|
"num_tokens": 33728515.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.342688322067261,
|
|
"epoch": 1.4135446685878963,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048063501902186463,
|
|
"loss": 5.1192,
|
|
"mean_token_accuracy": 0.20531529635190965,
|
|
"num_tokens": 33740684.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.345589208602905,
|
|
"epoch": 1.4140249759846302,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048062110216871775,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.20441545993089677,
|
|
"num_tokens": 33753017.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.305095100402832,
|
|
"epoch": 1.414505283381364,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048060718054165945,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.20333767980337142,
|
|
"num_tokens": 33764393.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.375625801086426,
|
|
"epoch": 1.414985590778098,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000480593254141013,
|
|
"loss": 5.2164,
|
|
"mean_token_accuracy": 0.1940871924161911,
|
|
"num_tokens": 33774941.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.255793666839599,
|
|
"epoch": 1.4154658981748318,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048057932296710165,
|
|
"loss": 4.995,
|
|
"mean_token_accuracy": 0.21755029261112213,
|
|
"num_tokens": 33786534.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.40552864074707,
|
|
"epoch": 1.415946205571566,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004805653870202489,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.19631996303796767,
|
|
"num_tokens": 33798339.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.399875164031982,
|
|
"epoch": 1.4164265129682998,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048055144630077825,
|
|
"loss": 5.2562,
|
|
"mean_token_accuracy": 0.19238245487213135,
|
|
"num_tokens": 33810368.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.382369327545166,
|
|
"epoch": 1.4169068203650337,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048053750080901336,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.20257769525051117,
|
|
"num_tokens": 33821111.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.313670063018799,
|
|
"epoch": 1.4173871277617676,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048052355054527794,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.20262081921100616,
|
|
"num_tokens": 33833629.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.360271310806274,
|
|
"epoch": 1.4178674351585014,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048050959550989606,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.20092410445213318,
|
|
"num_tokens": 33846531.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.244972801208496,
|
|
"epoch": 1.4183477425552353,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004804956357031916,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.2073008120059967,
|
|
"num_tokens": 33857251.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.264308834075928,
|
|
"epoch": 1.4188280499519692,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048048167112548873,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.20398729741573335,
|
|
"num_tokens": 33869314.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.465280199050904,
|
|
"epoch": 1.419308357348703,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048046770177711157,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.19564958810806274,
|
|
"num_tokens": 33880203.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.346956968307495,
|
|
"epoch": 1.419788664745437,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004804537276583844,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.21183545738458634,
|
|
"num_tokens": 33891379.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.264871263504029,
|
|
"epoch": 1.420268972142171,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004804397487696319,
|
|
"loss": 5.056,
|
|
"mean_token_accuracy": 0.2098393201828003,
|
|
"num_tokens": 33902788.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.277692031860352,
|
|
"epoch": 1.420749279538905,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004804257651111783,
|
|
"loss": 5.0994,
|
|
"mean_token_accuracy": 0.2116919532418251,
|
|
"num_tokens": 33913609.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.295864772796631,
|
|
"epoch": 1.4212295869356388,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048041177668334853,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.20734041035175324,
|
|
"num_tokens": 33924379.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.315137434005737,
|
|
"epoch": 1.4217098943323727,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004803977834864672,
|
|
"loss": 5.1451,
|
|
"mean_token_accuracy": 0.2010494962334633,
|
|
"num_tokens": 33936209.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.358670902252197,
|
|
"epoch": 1.4221902017291066,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048038378552085927,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.20135407149791718,
|
|
"num_tokens": 33947679.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.308043432235718,
|
|
"epoch": 1.4226705091258405,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048036978278684974,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.2011452928185463,
|
|
"num_tokens": 33959474.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.448321533203125,
|
|
"epoch": 1.4231508165225746,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004803557752847636,
|
|
"loss": 5.2311,
|
|
"mean_token_accuracy": 0.19840982109308242,
|
|
"num_tokens": 33970831.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.434389448165893,
|
|
"epoch": 1.4236311239193085,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048034176301492616,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.19986116737127305,
|
|
"num_tokens": 33981765.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.293845701217651,
|
|
"epoch": 1.4241114313160423,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004803277459776628,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.20737242251634597,
|
|
"num_tokens": 33992435.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.284368324279785,
|
|
"epoch": 1.4245917387127762,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048031372417329875,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.211997452378273,
|
|
"num_tokens": 34004570.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.350895357131958,
|
|
"epoch": 1.42507204610951,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004802996976021598,
|
|
"loss": 5.0576,
|
|
"mean_token_accuracy": 0.212220998108387,
|
|
"num_tokens": 34015494.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.408072757720947,
|
|
"epoch": 1.425552353506244,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00048028566626457145,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.199194972217083,
|
|
"num_tokens": 34026684.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.310731077194214,
|
|
"epoch": 1.4260326609029779,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048027163016085947,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.201174359023571,
|
|
"num_tokens": 34038948.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.35792760848999,
|
|
"epoch": 1.4265129682997117,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048025758929134976,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.19278012365102767,
|
|
"num_tokens": 34052216.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.433176136016845,
|
|
"epoch": 1.4269932756964456,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004802435436563684,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.2075638771057129,
|
|
"num_tokens": 34062602.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.336629104614258,
|
|
"epoch": 1.4274735830931795,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048022949325624134,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.20789820104837417,
|
|
"num_tokens": 34075049.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.287557601928711,
|
|
"epoch": 1.4279538904899136,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048021543809129483,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.19863296300172806,
|
|
"num_tokens": 34086719.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.33528356552124,
|
|
"epoch": 1.4284341978866475,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004802013781618552,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.20403222739696503,
|
|
"num_tokens": 34098439.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.4500833511352536,
|
|
"epoch": 1.4289145052833814,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048018731346824895,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.20610259622335433,
|
|
"num_tokens": 34110711.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.322064447402954,
|
|
"epoch": 1.4293948126801153,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004801732440108026,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.2035185933113098,
|
|
"num_tokens": 34122191.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.202870082855225,
|
|
"epoch": 1.4298751200768491,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004801591697898427,
|
|
"loss": 5.0176,
|
|
"mean_token_accuracy": 0.2115804672241211,
|
|
"num_tokens": 34132838.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.3451203346252445,
|
|
"epoch": 1.430355427473583,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004801450908056961,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.20066034346818923,
|
|
"num_tokens": 34143394.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.477582836151123,
|
|
"epoch": 1.4308357348703171,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004801310070586896,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.20249147862195968,
|
|
"num_tokens": 34155934.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.199370241165161,
|
|
"epoch": 1.431316042267051,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004801169185491503,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.21835024654865265,
|
|
"num_tokens": 34167949.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.348527717590332,
|
|
"epoch": 1.4317963496637849,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048010282527740516,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.194187493622303,
|
|
"num_tokens": 34179733.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.329934787750244,
|
|
"epoch": 1.4322766570605188,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048008872724378146,
|
|
"loss": 5.0146,
|
|
"mean_token_accuracy": 0.21136139333248138,
|
|
"num_tokens": 34190513.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.312529563903809,
|
|
"epoch": 1.4327569644572526,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004800746244486065,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.2081599086523056,
|
|
"num_tokens": 34201562.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.210018873214722,
|
|
"epoch": 1.4332372718539865,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004800605168922077,
|
|
"loss": 5.036,
|
|
"mean_token_accuracy": 0.20967738926410676,
|
|
"num_tokens": 34212637.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.271615076065063,
|
|
"epoch": 1.4337175792507204,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048004640457491267,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.20250353813171387,
|
|
"num_tokens": 34225394.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.3767602920532225,
|
|
"epoch": 1.4341978866474543,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000480032287497049,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.20467493683099747,
|
|
"num_tokens": 34236977.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.385453462600708,
|
|
"epoch": 1.4346781940441882,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048001816565894427,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.20524943768978118,
|
|
"num_tokens": 34247486.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.288991498947143,
|
|
"epoch": 1.435158501440922,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004800040390609267,
|
|
"loss": 5.0748,
|
|
"mean_token_accuracy": 0.20962218642234803,
|
|
"num_tokens": 34259404.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.279502439498901,
|
|
"epoch": 1.4356388088376562,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047998990770332396,
|
|
"loss": 5.052,
|
|
"mean_token_accuracy": 0.21017899215221406,
|
|
"num_tokens": 34270388.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.366046476364136,
|
|
"epoch": 1.43611911623439,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004799757715864643,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.2052116096019745,
|
|
"num_tokens": 34281321.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.409050226211548,
|
|
"epoch": 1.436599423631124,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004799616307106759,
|
|
"loss": 5.1876,
|
|
"mean_token_accuracy": 0.19496841430664064,
|
|
"num_tokens": 34293177.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.353391551971436,
|
|
"epoch": 1.4370797310278578,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000479947485076287,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.20239377170801162,
|
|
"num_tokens": 34305175.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.347495412826538,
|
|
"epoch": 1.4375600384245917,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047993333468362607,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.19625078588724137,
|
|
"num_tokens": 34317969.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.43083086013794,
|
|
"epoch": 1.4380403458213258,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047991917953302173,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.19622268974781037,
|
|
"num_tokens": 34329913.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.398012685775757,
|
|
"epoch": 1.4385206532180597,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047990501962480236,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.20956200808286668,
|
|
"num_tokens": 34341656.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.310992431640625,
|
|
"epoch": 1.4390009606147935,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000479890854959297,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.20245364010334016,
|
|
"num_tokens": 34351767.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.275381660461425,
|
|
"epoch": 1.4394812680115274,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004798766855368344,
|
|
"loss": 5.0805,
|
|
"mean_token_accuracy": 0.20426031947135925,
|
|
"num_tokens": 34363437.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.389877700805664,
|
|
"epoch": 1.4399615754082613,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047986251135774343,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.1980758860707283,
|
|
"num_tokens": 34374991.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.311112642288208,
|
|
"epoch": 1.4404418828049952,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004798483324223533,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.20535701215267183,
|
|
"num_tokens": 34386218.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.335395574569702,
|
|
"epoch": 1.440922190201729,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004798341487309932,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.2016810193657875,
|
|
"num_tokens": 34396287.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.440922190201729,
|
|
"eval_entropy": 5.097043277111825,
|
|
"eval_loss": 5.188806533813477,
|
|
"eval_mean_token_accuracy": 0.2089425852692081,
|
|
"eval_num_tokens": 34396287.0,
|
|
"eval_runtime": 26.6824,
|
|
"eval_samples_per_second": 1229.838,
|
|
"eval_steps_per_second": 153.734,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.337317848205567,
|
|
"epoch": 1.441402497598463,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047981996028399233,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.19811626374721528,
|
|
"num_tokens": 34407251.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.4460373878479,
|
|
"epoch": 1.4418828049951968,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004798057670816802,
|
|
"loss": 5.2654,
|
|
"mean_token_accuracy": 0.19626001715660096,
|
|
"num_tokens": 34419185.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.346108293533325,
|
|
"epoch": 1.4423631123919307,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004797915691243863,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.20205942541360855,
|
|
"num_tokens": 34431159.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.265436315536499,
|
|
"epoch": 1.4428434197886648,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004797773664124403,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.20629168450832366,
|
|
"num_tokens": 34442614.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.239840698242188,
|
|
"epoch": 1.4433237271853987,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047976315894617195,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.2099069520831108,
|
|
"num_tokens": 34453984.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.2642059326171875,
|
|
"epoch": 1.4438040345821326,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000479748946725911,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.20485440343618394,
|
|
"num_tokens": 34466296.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.453430271148681,
|
|
"epoch": 1.4442843419788665,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004797347297519875,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.19689891189336778,
|
|
"num_tokens": 34478088.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.345515203475952,
|
|
"epoch": 1.4447646493756003,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00047972050802473154,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.1974620208144188,
|
|
"num_tokens": 34491664.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.246814441680908,
|
|
"epoch": 1.4452449567723342,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004797062815444733,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.20806906521320342,
|
|
"num_tokens": 34502977.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.312552261352539,
|
|
"epoch": 1.4457252641690683,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000479692050311543,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.2078175202012062,
|
|
"num_tokens": 34515067.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.354199504852295,
|
|
"epoch": 1.4462055715658022,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004796778143262711,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.20123948007822037,
|
|
"num_tokens": 34525012.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.248608922958374,
|
|
"epoch": 1.446685878962536,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004796635735889882,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.21973000317811966,
|
|
"num_tokens": 34535789.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.354912424087525,
|
|
"epoch": 1.44716618635927,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047964932810002476,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.20739879608154296,
|
|
"num_tokens": 34546276.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.269332075119019,
|
|
"epoch": 1.4476464937560038,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004796350778597117,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.20098229199647905,
|
|
"num_tokens": 34558361.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.255196952819825,
|
|
"epoch": 1.4481268011527377,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004796208228683796,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.20984025150537491,
|
|
"num_tokens": 34569482.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.419500064849854,
|
|
"epoch": 1.4486071085494716,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047960656312635977,
|
|
"loss": 5.1669,
|
|
"mean_token_accuracy": 0.2102190762758255,
|
|
"num_tokens": 34580128.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.3315976619720455,
|
|
"epoch": 1.4490874159462055,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004795922986339831,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.20201931446790694,
|
|
"num_tokens": 34591105.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.36387996673584,
|
|
"epoch": 1.4495677233429394,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047957802939158057,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.20711608231067657,
|
|
"num_tokens": 34602618.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.348424911499023,
|
|
"epoch": 1.4500480307396733,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004795637553994838,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.19663694202899934,
|
|
"num_tokens": 34614179.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.416663980484008,
|
|
"epoch": 1.4505283381364074,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047954947665802404,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.19367124885320663,
|
|
"num_tokens": 34625456.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.3214311599731445,
|
|
"epoch": 1.4510086455331412,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004795351931675329,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.21167623549699782,
|
|
"num_tokens": 34636268.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.2295900821685795,
|
|
"epoch": 1.4514889529298751,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004795209049283419,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.21171180456876754,
|
|
"num_tokens": 34647665.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.364864873886108,
|
|
"epoch": 1.451969260326609,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004795066119407827,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.19991405457258224,
|
|
"num_tokens": 34659965.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.350704717636108,
|
|
"epoch": 1.4524495677233429,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004794923142051873,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.19869100749492646,
|
|
"num_tokens": 34671724.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.268422794342041,
|
|
"epoch": 1.452929875120077,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047947801172188755,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.21729401350021363,
|
|
"num_tokens": 34682445.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.211649370193482,
|
|
"epoch": 1.4534101825168109,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004794637044912155,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.21284156441688537,
|
|
"num_tokens": 34693621.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.232990884780884,
|
|
"epoch": 1.4538904899135447,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004794493925135034,
|
|
"loss": 4.9727,
|
|
"mean_token_accuracy": 0.2195131480693817,
|
|
"num_tokens": 34703978.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.326969718933105,
|
|
"epoch": 1.4543707973102786,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00047943507578908357,
|
|
"loss": 5.1635,
|
|
"mean_token_accuracy": 0.20973362475633622,
|
|
"num_tokens": 34715468.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.414375448226929,
|
|
"epoch": 1.4548511047070125,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004794207543182883,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.2016703352332115,
|
|
"num_tokens": 34726383.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.386307430267334,
|
|
"epoch": 1.4553314121037464,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047940642810145005,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.2055014044046402,
|
|
"num_tokens": 34737123.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.249415731430053,
|
|
"epoch": 1.4558117195004803,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047939209713890156,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.2081184446811676,
|
|
"num_tokens": 34749197.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.309644603729248,
|
|
"epoch": 1.4562920268972142,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047937776143097547,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.20621941834688187,
|
|
"num_tokens": 34759785.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.286391973495483,
|
|
"epoch": 1.456772334293948,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004793634209780047,
|
|
"loss": 4.9687,
|
|
"mean_token_accuracy": 0.21371437907218932,
|
|
"num_tokens": 34770938.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.311548566818237,
|
|
"epoch": 1.457252641690682,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004793490757803221,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.21234200149774551,
|
|
"num_tokens": 34782126.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.236219167709351,
|
|
"epoch": 1.457732949087416,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047933472583826063,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.20544045716524123,
|
|
"num_tokens": 34793802.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.265268039703369,
|
|
"epoch": 1.45821325648415,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004793203711521537,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.2088106766343117,
|
|
"num_tokens": 34805696.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.409330081939697,
|
|
"epoch": 1.4586935638808838,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047930601172233446,
|
|
"loss": 5.2647,
|
|
"mean_token_accuracy": 0.19519505947828292,
|
|
"num_tokens": 34818679.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.388585329055786,
|
|
"epoch": 1.4591738712776177,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047929164754913624,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.2056439623236656,
|
|
"num_tokens": 34830528.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.3067302227020265,
|
|
"epoch": 1.4596541786743515,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004792772786328926,
|
|
"loss": 4.997,
|
|
"mean_token_accuracy": 0.21222482174634932,
|
|
"num_tokens": 34841621.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.271059513092041,
|
|
"epoch": 1.4601344860710854,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047926290497393714,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.21110281348228455,
|
|
"num_tokens": 34854448.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.367152118682862,
|
|
"epoch": 1.4606147934678195,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004792485265726036,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.19694704115390776,
|
|
"num_tokens": 34866492.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.31414532661438,
|
|
"epoch": 1.4610951008645534,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004792341434292257,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.20230041146278382,
|
|
"num_tokens": 34876869.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.270202922821045,
|
|
"epoch": 1.4615754082612873,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004792197555441374,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.21500990837812423,
|
|
"num_tokens": 34888449.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.257145929336548,
|
|
"epoch": 1.4620557156580212,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004792053629176729,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.21283208578824997,
|
|
"num_tokens": 34898124.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.318220901489258,
|
|
"epoch": 1.462536023054755,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004791909655501662,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.2157799333333969,
|
|
"num_tokens": 34909128.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.237135410308838,
|
|
"epoch": 1.463016330451489,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004791765634419516,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.2060834914445877,
|
|
"num_tokens": 34920541.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.200583410263062,
|
|
"epoch": 1.4634966378482228,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047916215659336343,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.21248252242803572,
|
|
"num_tokens": 34931605.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.294836902618409,
|
|
"epoch": 1.4639769452449567,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004791477450047363,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.20895520895719527,
|
|
"num_tokens": 34943057.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.380582189559936,
|
|
"epoch": 1.4644572526416906,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047913332867640464,
|
|
"loss": 5.2088,
|
|
"mean_token_accuracy": 0.19861086308956147,
|
|
"num_tokens": 34954386.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.279351615905762,
|
|
"epoch": 1.4649375600384245,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004791189076087033,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.20733903646469115,
|
|
"num_tokens": 34965874.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.321742820739746,
|
|
"epoch": 1.4654178674351586,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047910448180196703,
|
|
"loss": 5.1559,
|
|
"mean_token_accuracy": 0.20079931765794753,
|
|
"num_tokens": 34977408.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.356105470657349,
|
|
"epoch": 1.4658981748318924,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004790900512565307,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.21514576226472854,
|
|
"num_tokens": 34987788.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.400559806823731,
|
|
"epoch": 1.4663784822286263,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004790756159727294,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.20402260720729828,
|
|
"num_tokens": 35001051.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.314635801315307,
|
|
"epoch": 1.4668587896253602,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047906117595089835,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.20797006636857987,
|
|
"num_tokens": 35012621.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.2586164474487305,
|
|
"epoch": 1.467339097022094,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004790467311913727,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.1996197894215584,
|
|
"num_tokens": 35023789.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.296824264526367,
|
|
"epoch": 1.4678194044188282,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004790322816944879,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.20858755856752395,
|
|
"num_tokens": 35035839.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.42156867980957,
|
|
"epoch": 1.468299711815562,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004790178274605793,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.20070536136627198,
|
|
"num_tokens": 35047823.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.345474433898926,
|
|
"epoch": 1.468780019212296,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047900336848998254,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.19949516355991365,
|
|
"num_tokens": 35058597.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.1826671123504635,
|
|
"epoch": 1.4692603266090298,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004789889047830334,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.20832534581422807,
|
|
"num_tokens": 35069822.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.323334980010986,
|
|
"epoch": 1.4697406340057637,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047897443634006766,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.20681535303592682,
|
|
"num_tokens": 35081423.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.378560495376587,
|
|
"epoch": 1.4702209414024976,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004789599631614211,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.1998908057808876,
|
|
"num_tokens": 35092565.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.321041774749756,
|
|
"epoch": 1.4707012487992315,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004789454852474298,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.20908844321966172,
|
|
"num_tokens": 35103811.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.351989507675171,
|
|
"epoch": 1.4711815561959654,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004789310025984299,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.19863588809967042,
|
|
"num_tokens": 35115516.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.353603744506836,
|
|
"epoch": 1.4716618635926992,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047891651521475776,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.20425378233194352,
|
|
"num_tokens": 35127285.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.286849927902222,
|
|
"epoch": 1.4721421709894331,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00047890202309674963,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.20781433433294297,
|
|
"num_tokens": 35137884.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.349787378311158,
|
|
"epoch": 1.4726224783861672,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047888752624474195,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.19240061193704605,
|
|
"num_tokens": 35149935.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.366101360321045,
|
|
"epoch": 1.473102785782901,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004788730246590714,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.2034175753593445,
|
|
"num_tokens": 35162610.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.347180652618408,
|
|
"epoch": 1.473583093179635,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047885851834007456,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.2044341966509819,
|
|
"num_tokens": 35174799.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.282588148117066,
|
|
"epoch": 1.4740634005763689,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047884400728808824,
|
|
"loss": 5.0485,
|
|
"mean_token_accuracy": 0.2085613191127777,
|
|
"num_tokens": 35186004.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.295201778411865,
|
|
"epoch": 1.4745437079731027,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004788294915034494,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.20752790123224257,
|
|
"num_tokens": 35197310.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.235984992980957,
|
|
"epoch": 1.4750240153698366,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000478814970986495,
|
|
"loss": 5.0361,
|
|
"mean_token_accuracy": 0.21387367695569992,
|
|
"num_tokens": 35208703.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.3001384258270265,
|
|
"epoch": 1.4755043227665707,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047880044573756213,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.21141816824674606,
|
|
"num_tokens": 35219927.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.257389640808105,
|
|
"epoch": 1.4759846301633046,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00047878591575698816,
|
|
"loss": 5.0467,
|
|
"mean_token_accuracy": 0.20929306149482726,
|
|
"num_tokens": 35231077.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.319155550003051,
|
|
"epoch": 1.4764649375600385,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004787713810451103,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.20051585435867308,
|
|
"num_tokens": 35241984.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.307653141021729,
|
|
"epoch": 1.4769452449567724,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047875684160226606,
|
|
"loss": 5.0663,
|
|
"mean_token_accuracy": 0.21470328867435456,
|
|
"num_tokens": 35252717.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.33350715637207,
|
|
"epoch": 1.4774255523535063,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000478742297428793,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.2025059938430786,
|
|
"num_tokens": 35263916.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.2697181224823,
|
|
"epoch": 1.4779058597502401,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047872774852502877,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.20859434604644775,
|
|
"num_tokens": 35274772.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.248328971862793,
|
|
"epoch": 1.478386167146974,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004787131948913112,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.21042598634958268,
|
|
"num_tokens": 35287150.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.306303882598877,
|
|
"epoch": 1.478866474543708,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00047869863652797806,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.21301501840353013,
|
|
"num_tokens": 35298538.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.273547124862671,
|
|
"epoch": 1.4793467819404418,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004786840734353675,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.2041073977947235,
|
|
"num_tokens": 35309395.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.301401138305664,
|
|
"epoch": 1.4798270893371757,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047866950561381756,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.2057197406888008,
|
|
"num_tokens": 35320741.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.449479770660401,
|
|
"epoch": 1.4803073967339098,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004786549330636665,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.20050628185272218,
|
|
"num_tokens": 35331895.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.26626877784729,
|
|
"epoch": 1.4807877041306436,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047864035578525256,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.21885530948638915,
|
|
"num_tokens": 35343775.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.271960592269897,
|
|
"epoch": 1.4812680115273775,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004786257737789143,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.2045095905661583,
|
|
"num_tokens": 35355043.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.3856017112731935,
|
|
"epoch": 1.4817483189241114,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004786111870449902,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.20090538561344146,
|
|
"num_tokens": 35365387.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.334269666671753,
|
|
"epoch": 1.4822286263208453,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047859659558381894,
|
|
"loss": 5.0663,
|
|
"mean_token_accuracy": 0.21309885382652283,
|
|
"num_tokens": 35376400.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.308069801330566,
|
|
"epoch": 1.4827089337175792,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047858199939573935,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.20392912924289702,
|
|
"num_tokens": 35387315.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.330906963348388,
|
|
"epoch": 1.4831892411143133,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047856739848109014,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.20855657309293746,
|
|
"num_tokens": 35398666.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.345583438873291,
|
|
"epoch": 1.4836695485110472,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047855279284021046,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.20909199118614197,
|
|
"num_tokens": 35409192.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.354464673995972,
|
|
"epoch": 1.484149855907781,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.00047853818247343933,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.19404848366975785,
|
|
"num_tokens": 35419812.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.361686944961548,
|
|
"epoch": 1.484630163304515,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047852356738111606,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.2162793144583702,
|
|
"num_tokens": 35430875.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.309618377685547,
|
|
"epoch": 1.4851104707012488,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004785089475635799,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.21001715511083602,
|
|
"num_tokens": 35441065.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.279362344741822,
|
|
"epoch": 1.4855907780979827,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047849432302117024,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.2084777310490608,
|
|
"num_tokens": 35452164.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.3433736801147464,
|
|
"epoch": 1.4860710854947166,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047847969375422656,
|
|
"loss": 5.1931,
|
|
"mean_token_accuracy": 0.19705236554145814,
|
|
"num_tokens": 35463158.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.291674613952637,
|
|
"epoch": 1.4865513928914504,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004784650597630887,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.217717182636261,
|
|
"num_tokens": 35474153.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.365289688110352,
|
|
"epoch": 1.4870317002881843,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00047845042104809635,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.20578911453485488,
|
|
"num_tokens": 35485680.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.385678005218506,
|
|
"epoch": 1.4875120076849184,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004784357776095892,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.21110421866178514,
|
|
"num_tokens": 35497271.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.326588344573975,
|
|
"epoch": 1.4879923150816523,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004784211294479075,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.21188997775316237,
|
|
"num_tokens": 35509166.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.304242753982544,
|
|
"epoch": 1.4884726224783862,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004784064765633912,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.21132884323596954,
|
|
"num_tokens": 35521289.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.308375310897827,
|
|
"epoch": 1.48895292987512,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047839181895638057,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.21322586089372636,
|
|
"num_tokens": 35532179.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.407812023162842,
|
|
"epoch": 1.489433237271854,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00047837715662721575,
|
|
"loss": 5.2607,
|
|
"mean_token_accuracy": 0.19944295883178711,
|
|
"num_tokens": 35544703.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.4146356105804445,
|
|
"epoch": 1.4899135446685878,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004783624895762372,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.18990132659673692,
|
|
"num_tokens": 35557853.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.329196262359619,
|
|
"epoch": 1.490393852065322,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047834781780378563,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.21543993502855302,
|
|
"num_tokens": 35570340.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.3557289123535154,
|
|
"epoch": 1.4908741594620558,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004783331413102015,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.20626865476369857,
|
|
"num_tokens": 35582387.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.35982666015625,
|
|
"epoch": 1.4913544668587897,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00047831846009582557,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.19724981784820556,
|
|
"num_tokens": 35595105.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.316178655624389,
|
|
"epoch": 1.4918347742555236,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004783037741609988,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.19946703165769578,
|
|
"num_tokens": 35607160.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.360345888137817,
|
|
"epoch": 1.4923150816522575,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004782890835060621,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.20727163404226304,
|
|
"num_tokens": 35619097.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.229111957550049,
|
|
"epoch": 1.4927953890489913,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004782743881313564,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.21602532118558884,
|
|
"num_tokens": 35629868.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.288349533081055,
|
|
"epoch": 1.4932756964457252,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047825968803722315,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.2062566488981247,
|
|
"num_tokens": 35640622.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.304030323028565,
|
|
"epoch": 1.493756003842459,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004782449832240035,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.20271336734294892,
|
|
"num_tokens": 35652383.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.269534587860107,
|
|
"epoch": 1.494236311239193,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004782302736920387,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.2073517695069313,
|
|
"num_tokens": 35663838.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.360981607437134,
|
|
"epoch": 1.4947166186359269,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004782155594416705,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.205577252805233,
|
|
"num_tokens": 35674564.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.359388303756714,
|
|
"epoch": 1.495196926032661,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047820084047324045,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.20440198630094528,
|
|
"num_tokens": 35685518.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.395944309234619,
|
|
"epoch": 1.4956772334293948,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047818611678709027,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.20773788988590242,
|
|
"num_tokens": 35696597.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.298573637008667,
|
|
"epoch": 1.4961575408261287,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004781713883835618,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.21191534548997878,
|
|
"num_tokens": 35707229.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.302655506134033,
|
|
"epoch": 1.4966378482228626,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047815665526299695,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.20392076224088668,
|
|
"num_tokens": 35719440.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.340134191513061,
|
|
"epoch": 1.4971181556195965,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004781419174257378,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.19822956770658492,
|
|
"num_tokens": 35731611.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.296953344345093,
|
|
"epoch": 1.4975984630163304,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004781271748721266,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.20230129957199097,
|
|
"num_tokens": 35743047.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.340254592895508,
|
|
"epoch": 1.4980787704130645,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004781124276025055,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.2194366693496704,
|
|
"num_tokens": 35753499.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.311364316940308,
|
|
"epoch": 1.4985590778097984,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000478097675617217,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.19941366612911224,
|
|
"num_tokens": 35764682.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.363536357879639,
|
|
"epoch": 1.4990393852065322,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047808291891660357,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.21302209198474883,
|
|
"num_tokens": 35775160.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.336853265762329,
|
|
"epoch": 1.4995196926032661,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047806815750100774,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.20398466289043427,
|
|
"num_tokens": 35786089.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.311153602600098,
|
|
"epoch": 1.5,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004780533913707723,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.20666101723909377,
|
|
"num_tokens": 35796851.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.366311883926391,
|
|
"epoch": 1.5004803073967339,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047803862052624006,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.2006330281496048,
|
|
"num_tokens": 35808553.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.432717657089233,
|
|
"epoch": 1.5009606147934678,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047802384496775397,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.1999915733933449,
|
|
"num_tokens": 35820108.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.299103689193726,
|
|
"epoch": 1.5014409221902016,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004780090646956571,
|
|
"loss": 5.01,
|
|
"mean_token_accuracy": 0.2171195477247238,
|
|
"num_tokens": 35831672.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.428519678115845,
|
|
"epoch": 1.5019212295869355,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047799427971029245,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.20507666021585463,
|
|
"num_tokens": 35843164.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.408617973327637,
|
|
"epoch": 1.5024015369836694,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004779794900120034,
|
|
"loss": 5.2047,
|
|
"mean_token_accuracy": 0.197944013774395,
|
|
"num_tokens": 35854677.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.334943008422852,
|
|
"epoch": 1.5028818443804035,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004779646956011334,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.20981245189905168,
|
|
"num_tokens": 35865956.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.306821680068969,
|
|
"epoch": 1.5033621517771374,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047794989647802574,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.2063814952969551,
|
|
"num_tokens": 35877451.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.312264823913575,
|
|
"epoch": 1.5038424591738713,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047793509264302424,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.20705510377883912,
|
|
"num_tokens": 35888436.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.294168853759766,
|
|
"epoch": 1.5043227665706052,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047792028409647237,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.2032469779253006,
|
|
"num_tokens": 35901010.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.332839822769165,
|
|
"epoch": 1.5048030739673393,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047790547083871414,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.2054579511284828,
|
|
"num_tokens": 35912697.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.278722333908081,
|
|
"epoch": 1.5052833813640731,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047789065287009335,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.20874810814857483,
|
|
"num_tokens": 35924614.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.3735551834106445,
|
|
"epoch": 1.505763688760807,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004778758301909542,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.20480876863002778,
|
|
"num_tokens": 35935492.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.254597187042236,
|
|
"epoch": 1.506243996157541,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004778610028016405,
|
|
"loss": 5.1223,
|
|
"mean_token_accuracy": 0.20884814411401748,
|
|
"num_tokens": 35947901.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.276274919509888,
|
|
"epoch": 1.5067243035542748,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004778461707024967,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.2152129143476486,
|
|
"num_tokens": 35959690.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.32186713218689,
|
|
"epoch": 1.5072046109510087,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004778313338938672,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.21040457785129546,
|
|
"num_tokens": 35971209.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.261551237106323,
|
|
"epoch": 1.5076849183477425,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047781649237609643,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.21217665523290635,
|
|
"num_tokens": 35981795.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.250638771057129,
|
|
"epoch": 1.5081652257444764,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004778016461495289,
|
|
"loss": 5.0921,
|
|
"mean_token_accuracy": 0.20595138967037202,
|
|
"num_tokens": 35993358.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.320055437088013,
|
|
"epoch": 1.5086455331412103,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004777867952145094,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.2048203930258751,
|
|
"num_tokens": 36005353.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.395911455154419,
|
|
"epoch": 1.5091258405379442,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004777719395713826,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.20254443734884262,
|
|
"num_tokens": 36017510.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.3143385887146,
|
|
"epoch": 1.509606147934678,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047775707922049354,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.20757827013731003,
|
|
"num_tokens": 36028687.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.241795063018799,
|
|
"epoch": 1.510086455331412,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004777422141621871,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.212799534201622,
|
|
"num_tokens": 36039851.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.315477895736694,
|
|
"epoch": 1.510566762728146,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004777273443968085,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.20391366630792618,
|
|
"num_tokens": 36050776.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.2399825096130375,
|
|
"epoch": 1.51104707012488,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004777124699247029,
|
|
"loss": 5.002,
|
|
"mean_token_accuracy": 0.21141346246004106,
|
|
"num_tokens": 36062151.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.289028310775757,
|
|
"epoch": 1.5115273775216138,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004776975907462157,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.21216995716094972,
|
|
"num_tokens": 36074601.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.316258144378662,
|
|
"epoch": 1.5120076849183477,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004776827068616924,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.21564974039793014,
|
|
"num_tokens": 36085436.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.396112775802612,
|
|
"epoch": 1.5124879923150818,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004776678182714785,
|
|
"loss": 5.2029,
|
|
"mean_token_accuracy": 0.19518298655748367,
|
|
"num_tokens": 36097589.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.27427077293396,
|
|
"epoch": 1.5129682997118157,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047765292497591955,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.20454778373241425,
|
|
"num_tokens": 36109993.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.336736965179443,
|
|
"epoch": 1.5134486071085496,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047763802697536146,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.20808484852313996,
|
|
"num_tokens": 36122439.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.384919452667236,
|
|
"epoch": 1.5139289145052834,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047762312427015015,
|
|
"loss": 5.0925,
|
|
"mean_token_accuracy": 0.20157887488603593,
|
|
"num_tokens": 36133867.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.3454266548156735,
|
|
"epoch": 1.5144092219020173,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047760821686063153,
|
|
"loss": 5.1705,
|
|
"mean_token_accuracy": 0.20314918458461761,
|
|
"num_tokens": 36144202.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.309101009368897,
|
|
"epoch": 1.5148895292987512,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047759330474715173,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.20690389573574067,
|
|
"num_tokens": 36154863.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.3638499736785885,
|
|
"epoch": 1.515369836695485,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047757838793005704,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.20113610327243805,
|
|
"num_tokens": 36166360.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.286581325531006,
|
|
"epoch": 1.515850144092219,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047756346640969366,
|
|
"loss": 4.9915,
|
|
"mean_token_accuracy": 0.22013422548770906,
|
|
"num_tokens": 36177477.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.359613561630249,
|
|
"epoch": 1.5163304514889528,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047754854018640803,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.20612413734197615,
|
|
"num_tokens": 36188510.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.285648202896118,
|
|
"epoch": 1.5168107588856867,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047753360926054684,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.20978983491659164,
|
|
"num_tokens": 36199084.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.242048931121826,
|
|
"epoch": 1.5172910662824206,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047751867363245653,
|
|
"loss": 5.0407,
|
|
"mean_token_accuracy": 0.20474733114242555,
|
|
"num_tokens": 36211265.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.413763999938965,
|
|
"epoch": 1.5177713736791547,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004775037333024841,
|
|
"loss": 5.2203,
|
|
"mean_token_accuracy": 0.1955953672528267,
|
|
"num_tokens": 36223070.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.35607500076294,
|
|
"epoch": 1.5182516810758886,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004774887882709762,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.20588915646076203,
|
|
"num_tokens": 36235021.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.32380256652832,
|
|
"epoch": 1.5187319884726225,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047747383853827995,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.2045574888586998,
|
|
"num_tokens": 36245647.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.366781091690063,
|
|
"epoch": 1.5192122958693564,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004774588841047424,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.20063382685184478,
|
|
"num_tokens": 36257470.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.280811500549317,
|
|
"epoch": 1.5196926032660905,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004774439249707108,
|
|
"loss": 5.0337,
|
|
"mean_token_accuracy": 0.20682831406593322,
|
|
"num_tokens": 36268839.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.30407977104187,
|
|
"epoch": 1.5201729106628243,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004774289611365323,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.2052461698651314,
|
|
"num_tokens": 36280624.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.339308977127075,
|
|
"epoch": 1.5206532180595582,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047741399260255434,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.20912803560495377,
|
|
"num_tokens": 36292696.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.319470691680908,
|
|
"epoch": 1.521133525456292,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047739901936912467,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.21092095524072646,
|
|
"num_tokens": 36303612.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.260247373580933,
|
|
"epoch": 1.521613832853026,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004773840414365907,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.20907704532146454,
|
|
"num_tokens": 36314511.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.407761335372925,
|
|
"epoch": 1.5220941402497599,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047736905880530026,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.19968598634004592,
|
|
"num_tokens": 36327276.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.343130683898925,
|
|
"epoch": 1.5225744476464937,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004773540714756012,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.20651497095823287,
|
|
"num_tokens": 36339373.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.366746664047241,
|
|
"epoch": 1.5230547550432276,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047733907944784144,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.19529192596673967,
|
|
"num_tokens": 36351863.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.313302707672119,
|
|
"epoch": 1.5235350624399615,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004773240827223691,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.2140681564807892,
|
|
"num_tokens": 36363961.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.290032052993775,
|
|
"epoch": 1.5240153698366954,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004773090812995323,
|
|
"loss": 5.0553,
|
|
"mean_token_accuracy": 0.21352988630533218,
|
|
"num_tokens": 36374738.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.288148260116577,
|
|
"epoch": 1.5244956772334293,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047729407517967945,
|
|
"loss": 4.9981,
|
|
"mean_token_accuracy": 0.20865701735019684,
|
|
"num_tokens": 36386472.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.274398899078369,
|
|
"epoch": 1.5249759846301632,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047727906436315884,
|
|
"loss": 5.0748,
|
|
"mean_token_accuracy": 0.21495105624198912,
|
|
"num_tokens": 36397042.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.267912578582764,
|
|
"epoch": 1.5254562920268973,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00047726404885031895,
|
|
"loss": 5.0485,
|
|
"mean_token_accuracy": 0.2101367309689522,
|
|
"num_tokens": 36408720.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.316926765441894,
|
|
"epoch": 1.5259365994236311,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00047724902864150845,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.20312738418579102,
|
|
"num_tokens": 36420885.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.3592804908752445,
|
|
"epoch": 1.526416906820365,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047723400373707607,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.19705341905355453,
|
|
"num_tokens": 36433678.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.335611629486084,
|
|
"epoch": 1.526897214217099,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004772189741373707,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.20681924372911453,
|
|
"num_tokens": 36445143.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.244937229156494,
|
|
"epoch": 1.527377521613833,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047720393984274117,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.20840252488851546,
|
|
"num_tokens": 36456214.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.380179166793823,
|
|
"epoch": 1.5278578290105669,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047718890085353654,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.2093242660164833,
|
|
"num_tokens": 36466767.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.350666904449463,
|
|
"epoch": 1.5283381364073008,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000477173857170106,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.20472349524497985,
|
|
"num_tokens": 36478150.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.32206654548645,
|
|
"epoch": 1.5288184438040346,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047715880879279894,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.202899369597435,
|
|
"num_tokens": 36488280.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.345649147033692,
|
|
"epoch": 1.5292987512007685,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004771437557219646,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.2041873589158058,
|
|
"num_tokens": 36498505.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.246016931533814,
|
|
"epoch": 1.5297790585975024,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004771286979579524,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.20406609922647476,
|
|
"num_tokens": 36509271.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.325800991058349,
|
|
"epoch": 1.5302593659942363,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004771136355011121,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.2036772608757019,
|
|
"num_tokens": 36520022.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.364723157882691,
|
|
"epoch": 1.5307396733909702,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047709856835179333,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.20681098252534866,
|
|
"num_tokens": 36532769.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.386866331100464,
|
|
"epoch": 1.531219980787704,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00047708349651034586,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.2103017359972,
|
|
"num_tokens": 36544454.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.312154150009155,
|
|
"epoch": 1.531700288184438,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047706841997711974,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.20436654537916182,
|
|
"num_tokens": 36555916.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.287511253356934,
|
|
"epoch": 1.5321805955811718,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047705333875246495,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.20432552993297576,
|
|
"num_tokens": 36567829.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.347614765167236,
|
|
"epoch": 1.532660902977906,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047703825283673153,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.20314279198646545,
|
|
"num_tokens": 36578216.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.379737710952758,
|
|
"epoch": 1.5331412103746398,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004770231622302699,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.20881457775831222,
|
|
"num_tokens": 36589945.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.3987956047058105,
|
|
"epoch": 1.5336215177713737,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047700806693343016,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.20783490240573882,
|
|
"num_tokens": 36600724.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.197413301467895,
|
|
"epoch": 1.5341018251681076,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047699296694656316,
|
|
"loss": 4.9376,
|
|
"mean_token_accuracy": 0.21987202316522597,
|
|
"num_tokens": 36611154.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.250714826583862,
|
|
"epoch": 1.5345821325648417,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004769778622700192,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.21001372039318084,
|
|
"num_tokens": 36621750.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.33173942565918,
|
|
"epoch": 1.5350624399615755,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047696275290414885,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.20733319073915482,
|
|
"num_tokens": 36633294.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.293679332733154,
|
|
"epoch": 1.5355427473583094,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047694763884930324,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.20775003135204315,
|
|
"num_tokens": 36646377.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.238643550872803,
|
|
"epoch": 1.5360230547550433,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047693252010583314,
|
|
"loss": 4.9768,
|
|
"mean_token_accuracy": 0.21326316893100739,
|
|
"num_tokens": 36656159.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.264440393447876,
|
|
"epoch": 1.5365033621517772,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004769173966740895,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.2029369831085205,
|
|
"num_tokens": 36667522.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.371861457824707,
|
|
"epoch": 1.536983669548511,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047690226855442346,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.20143139660358428,
|
|
"num_tokens": 36678662.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.331053924560547,
|
|
"epoch": 1.537463976945245,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004768871357471863,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.20494483262300492,
|
|
"num_tokens": 36689876.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.313150787353516,
|
|
"epoch": 1.5379442843419788,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047687199825272936,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.21088340729475022,
|
|
"num_tokens": 36701140.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.337675762176514,
|
|
"epoch": 1.5384245917387127,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047685685607140403,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.20031316876411437,
|
|
"num_tokens": 36711077.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.380051326751709,
|
|
"epoch": 1.5389048991354466,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047684170920356185,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.2096099153161049,
|
|
"num_tokens": 36722705.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.258144426345825,
|
|
"epoch": 1.5393852065321805,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004768265576495546,
|
|
"loss": 5.0264,
|
|
"mean_token_accuracy": 0.2080724373459816,
|
|
"num_tokens": 36733446.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.208423233032226,
|
|
"epoch": 1.5398655139289144,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047681140140973396,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.21060321778059005,
|
|
"num_tokens": 36744529.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.2020933628082275,
|
|
"epoch": 1.5403458213256485,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004767962404844517,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.2145044758915901,
|
|
"num_tokens": 36756248.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.410145330429077,
|
|
"epoch": 1.5408261287223823,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047678107487406015,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.20492404997348784,
|
|
"num_tokens": 36768097.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.30552830696106,
|
|
"epoch": 1.5413064361191162,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047676590457891116,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.20460336059331893,
|
|
"num_tokens": 36780395.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.286385822296142,
|
|
"epoch": 1.54178674351585,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004767507295993569,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.20367637723684312,
|
|
"num_tokens": 36791897.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.303220462799072,
|
|
"epoch": 1.5422670509125842,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004767355499357498,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.21287268549203872,
|
|
"num_tokens": 36802716.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.264397525787354,
|
|
"epoch": 1.542747358309318,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004767203655884423,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.20670515298843384,
|
|
"num_tokens": 36814471.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.2660047054290775,
|
|
"epoch": 1.543227665706052,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004767051765577869,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.2141999587416649,
|
|
"num_tokens": 36825975.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.355614042282104,
|
|
"epoch": 1.5437079731027858,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00047668998284413624,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.19436067193746567,
|
|
"num_tokens": 36837990.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.32629427909851,
|
|
"epoch": 1.5441882804995197,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047667478444784306,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.20309953391551971,
|
|
"num_tokens": 36849115.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.326242733001709,
|
|
"epoch": 1.5446685878962536,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004766595813692602,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.205696402490139,
|
|
"num_tokens": 36860626.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.327420282363891,
|
|
"epoch": 1.5451488952929875,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047664437360874076,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.1991450548171997,
|
|
"num_tokens": 36871926.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.302243614196778,
|
|
"epoch": 1.5456292026897214,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047662916116663766,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.21172798573970794,
|
|
"num_tokens": 36883511.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.376856565475464,
|
|
"epoch": 1.5461095100864553,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047661394404330417,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.205851012468338,
|
|
"num_tokens": 36895468.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.3078149318695065,
|
|
"epoch": 1.5465898174831891,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047659872223909357,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.20445011109113692,
|
|
"num_tokens": 36906957.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.2808784484863285,
|
|
"epoch": 1.547070124879923,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004765834957543592,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.2067875385284424,
|
|
"num_tokens": 36916495.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.224740266799927,
|
|
"epoch": 1.547550432276657,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047656826458945475,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.20315874516963958,
|
|
"num_tokens": 36927301.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.30440583229065,
|
|
"epoch": 1.548030739673391,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047655302874473365,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.21257056146860123,
|
|
"num_tokens": 36938116.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.372204113006592,
|
|
"epoch": 1.5485110470701249,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004765377882205498,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.20569490790367126,
|
|
"num_tokens": 36950292.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.247190713882446,
|
|
"epoch": 1.5489913544668588,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004765225430172568,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.21092472225427628,
|
|
"num_tokens": 36962017.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.321947622299194,
|
|
"epoch": 1.5494716618635929,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004765072931352089,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.20113423764705657,
|
|
"num_tokens": 36972831.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.305951309204102,
|
|
"epoch": 1.5499519692603267,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047649203857476,
|
|
"loss": 4.9986,
|
|
"mean_token_accuracy": 0.2097838193178177,
|
|
"num_tokens": 36983324.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.287349843978882,
|
|
"epoch": 1.5504322766570606,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047647677933626423,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.1902223527431488,
|
|
"num_tokens": 36996093.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.314684057235718,
|
|
"epoch": 1.5509125840537945,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047646151542007583,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.20901332944631576,
|
|
"num_tokens": 37006548.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.352572441101074,
|
|
"epoch": 1.5513928914505284,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004764462468265494,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.20277443081140517,
|
|
"num_tokens": 37019181.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.3795534610748295,
|
|
"epoch": 1.5518731988472623,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047643097355603913,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.20563308000564576,
|
|
"num_tokens": 37029808.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.252798223495484,
|
|
"epoch": 1.5523535062439962,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004764156956088999,
|
|
"loss": 5.0767,
|
|
"mean_token_accuracy": 0.20489506125450135,
|
|
"num_tokens": 37040352.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.252407026290894,
|
|
"epoch": 1.55283381364073,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004764004129854863,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.21205128431320192,
|
|
"num_tokens": 37050780.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.360000562667847,
|
|
"epoch": 1.553314121037464,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047638512568615307,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.20500940084457397,
|
|
"num_tokens": 37062608.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.337680625915527,
|
|
"epoch": 1.5537944284341978,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004763698337112553,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.20206108391284944,
|
|
"num_tokens": 37074578.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.338007307052612,
|
|
"epoch": 1.5542747358309317,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004763545370611479,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.2063354328274727,
|
|
"num_tokens": 37086487.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.324742460250855,
|
|
"epoch": 1.5547550432276656,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047633923573618605,
|
|
"loss": 5.0488,
|
|
"mean_token_accuracy": 0.21600349247455597,
|
|
"num_tokens": 37097249.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.378001594543457,
|
|
"epoch": 1.5552353506243997,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000476323929736725,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.1934942424297333,
|
|
"num_tokens": 37109274.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.328637599945068,
|
|
"epoch": 1.5557156580211335,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047630861906312004,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.21147672981023788,
|
|
"num_tokens": 37120100.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.330235242843628,
|
|
"epoch": 1.5561959654178674,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004762933037157268,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.20328413248062133,
|
|
"num_tokens": 37131889.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.232202005386353,
|
|
"epoch": 1.5566762728146013,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047627798369490076,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.21751004904508592,
|
|
"num_tokens": 37142538.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.346778011322021,
|
|
"epoch": 1.5571565802113354,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047626265900099757,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.1980739265680313,
|
|
"num_tokens": 37153639.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.3209999084472654,
|
|
"epoch": 1.5576368876080693,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047624732963437314,
|
|
"loss": 5.1205,
|
|
"mean_token_accuracy": 0.20385928601026534,
|
|
"num_tokens": 37164029.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.326368188858032,
|
|
"epoch": 1.5581171950048032,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047623199559538324,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.20345907509326935,
|
|
"num_tokens": 37175880.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.356235361099243,
|
|
"epoch": 1.558597502401537,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000476216656884384,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.20511586368083953,
|
|
"num_tokens": 37187483.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.317887449264527,
|
|
"epoch": 1.559077809798271,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047620131350173135,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.2087674543261528,
|
|
"num_tokens": 37198978.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.409282302856445,
|
|
"epoch": 1.5595581171950048,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004761859654477817,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.1950107529759407,
|
|
"num_tokens": 37210054.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.3338957786560055,
|
|
"epoch": 1.5600384245917387,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004761706127228914,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.20824625641107558,
|
|
"num_tokens": 37221744.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.289117670059204,
|
|
"epoch": 1.5605187319884726,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004761552553274168,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.2053858682513237,
|
|
"num_tokens": 37234629.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.419245386123658,
|
|
"epoch": 1.5609990393852065,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004761398932617144,
|
|
"loss": 5.2029,
|
|
"mean_token_accuracy": 0.19704837203025818,
|
|
"num_tokens": 37246960.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.3095728874206545,
|
|
"epoch": 1.5614793467819403,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000476124526526141,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.2067649245262146,
|
|
"num_tokens": 37259326.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.2240049839019775,
|
|
"epoch": 1.5619596541786742,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047610915512105327,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.20569961667060851,
|
|
"num_tokens": 37271436.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.342802858352661,
|
|
"epoch": 1.562439961575408,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004760937790468082,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.19820557832717894,
|
|
"num_tokens": 37283230.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.313557863235474,
|
|
"epoch": 1.5629202689721422,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004760783983037627,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.21025891304016114,
|
|
"num_tokens": 37295185.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.318403434753418,
|
|
"epoch": 1.563400576368876,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004760630128922738,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.20383380055427552,
|
|
"num_tokens": 37307573.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.407955884933472,
|
|
"epoch": 1.56388088376561,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004760476228126989,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.2005763530731201,
|
|
"num_tokens": 37319084.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.217340707778931,
|
|
"epoch": 1.5643611911623438,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004760322280653951,
|
|
"loss": 5.0527,
|
|
"mean_token_accuracy": 0.2088148295879364,
|
|
"num_tokens": 37330447.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.2852246284484865,
|
|
"epoch": 1.564841498559078,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004760168286507199,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.20959784239530563,
|
|
"num_tokens": 37341184.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.358658266067505,
|
|
"epoch": 1.5653218059558118,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047600142456903085,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.2059228852391243,
|
|
"num_tokens": 37352712.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.331033372879029,
|
|
"epoch": 1.5658021133525457,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047598601582068555,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.19939152747392655,
|
|
"num_tokens": 37365001.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.408932209014893,
|
|
"epoch": 1.5662824207492796,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004759706024060418,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.20051614195108414,
|
|
"num_tokens": 37377005.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.329226875305176,
|
|
"epoch": 1.5667627281460135,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004759551843254575,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.20561263412237168,
|
|
"num_tokens": 37387329.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.3877098083496096,
|
|
"epoch": 1.5672430355427474,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047593976157929034,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.20687068849802018,
|
|
"num_tokens": 37398894.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.334888696670532,
|
|
"epoch": 1.5677233429394812,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004759243341678987,
|
|
"loss": 5.0744,
|
|
"mean_token_accuracy": 0.20718985795974731,
|
|
"num_tokens": 37409913.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.370473003387451,
|
|
"epoch": 1.5682036503362151,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004759089020916407,
|
|
"loss": 5.0373,
|
|
"mean_token_accuracy": 0.2055622547864914,
|
|
"num_tokens": 37421859.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.319072675704956,
|
|
"epoch": 1.568683957732949,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047589346535087444,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.20059471279382707,
|
|
"num_tokens": 37432827.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.325724935531616,
|
|
"epoch": 1.5691642651296829,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004758780239459586,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.21531772762537002,
|
|
"num_tokens": 37444171.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.300668668746948,
|
|
"epoch": 1.5696445725264168,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004758625778772514,
|
|
"loss": 5.0553,
|
|
"mean_token_accuracy": 0.20189524292945862,
|
|
"num_tokens": 37455194.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.2150195121765135,
|
|
"epoch": 1.5701248799231509,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047584712714511166,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.21618202924728394,
|
|
"num_tokens": 37465839.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.292907047271728,
|
|
"epoch": 1.5706051873198847,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047583167174989797,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.20999283492565154,
|
|
"num_tokens": 37476948.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.319771718978882,
|
|
"epoch": 1.5710854947166186,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004758162116919692,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.20959147810935974,
|
|
"num_tokens": 37487382.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.218329524993896,
|
|
"epoch": 1.5715658021133525,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047580074697168434,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.2157032608985901,
|
|
"num_tokens": 37498347.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.27532730102539,
|
|
"epoch": 1.5720461095100866,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047578527758940236,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.20023149400949478,
|
|
"num_tokens": 37509620.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.339815950393676,
|
|
"epoch": 1.5725264169068205,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004757698035454825,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.2164599522948265,
|
|
"num_tokens": 37519768.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.292916250228882,
|
|
"epoch": 1.5730067243035544,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004757543248402839,
|
|
"loss": 5.0067,
|
|
"mean_token_accuracy": 0.21136390268802643,
|
|
"num_tokens": 37530476.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.278514432907104,
|
|
"epoch": 1.5734870317002883,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047573884147416597,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.20470152646303177,
|
|
"num_tokens": 37541702.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.350610876083374,
|
|
"epoch": 1.5739673390970221,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004757233534474883,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.204076412320137,
|
|
"num_tokens": 37553323.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.308850860595703,
|
|
"epoch": 1.574447646493756,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004757078607606103,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.2035911574959755,
|
|
"num_tokens": 37564882.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.289526844024659,
|
|
"epoch": 1.57492795389049,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004756923634138918,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.20710788816213607,
|
|
"num_tokens": 37575612.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.323983430862427,
|
|
"epoch": 1.5754082612872238,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047567686140769264,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.20723945647478104,
|
|
"num_tokens": 37587089.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.309318923950196,
|
|
"epoch": 1.5758885686839577,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047566135474237247,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.20703659653663636,
|
|
"num_tokens": 37598429.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.352410411834716,
|
|
"epoch": 1.5763688760806915,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047564584341829166,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.1978172853589058,
|
|
"num_tokens": 37609769.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.392447996139526,
|
|
"epoch": 1.5768491834774254,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047563032743581,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.1976489692926407,
|
|
"num_tokens": 37622425.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.336363935470581,
|
|
"epoch": 1.5773294908741593,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047561480679528804,
|
|
"loss": 5.1098,
|
|
"mean_token_accuracy": 0.20966575294733047,
|
|
"num_tokens": 37634819.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.287162971496582,
|
|
"epoch": 1.5778097982708934,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004755992814970859,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.21380167752504348,
|
|
"num_tokens": 37645531.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.264857530593872,
|
|
"epoch": 1.5782901056676273,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000475583751541564,
|
|
"loss": 5.0541,
|
|
"mean_token_accuracy": 0.2077256828546524,
|
|
"num_tokens": 37657243.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.348211622238159,
|
|
"epoch": 1.5787704130643612,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047556821692908315,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.20734720528125763,
|
|
"num_tokens": 37668218.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.304349088668824,
|
|
"epoch": 1.579250720461095,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004755526776600038,
|
|
"loss": 5.0642,
|
|
"mean_token_accuracy": 0.20846139937639235,
|
|
"num_tokens": 37680173.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.295353841781616,
|
|
"epoch": 1.5797310278578292,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047553713373468684,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.20295505225658417,
|
|
"num_tokens": 37691281.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.30849871635437,
|
|
"epoch": 1.580211335254563,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047552158515349306,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.19835709631443024,
|
|
"num_tokens": 37702320.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.324478483200073,
|
|
"epoch": 1.580691642651297,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047550603191678356,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.2047861099243164,
|
|
"num_tokens": 37713724.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.33772120475769,
|
|
"epoch": 1.5811719500480308,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004754904740249194,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.21046376079320908,
|
|
"num_tokens": 37724532.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.288224744796753,
|
|
"epoch": 1.5816522574447647,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047547491147826156,
|
|
"loss": 5.0219,
|
|
"mean_token_accuracy": 0.21071733236312867,
|
|
"num_tokens": 37735174.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.317471885681153,
|
|
"epoch": 1.5821325648414986,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004754593442771718,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.20063369870185851,
|
|
"num_tokens": 37746981.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.316577196121216,
|
|
"epoch": 1.5826128722382324,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047544377242201115,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.20548705160617828,
|
|
"num_tokens": 37757576.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.345623540878296,
|
|
"epoch": 1.5830931796349663,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047542819591314136,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.2013881415128708,
|
|
"num_tokens": 37769053.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.401471471786499,
|
|
"epoch": 1.5835734870317002,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004754126147509241,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.20709681808948516,
|
|
"num_tokens": 37780517.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.40665283203125,
|
|
"epoch": 1.584053794428434,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047539702893572086,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.19753515869379043,
|
|
"num_tokens": 37791333.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.229759550094604,
|
|
"epoch": 1.584534101825168,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047538143846789376,
|
|
"loss": 5.0349,
|
|
"mean_token_accuracy": 0.21178653389215468,
|
|
"num_tokens": 37802635.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.209204959869385,
|
|
"epoch": 1.585014409221902,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004753658433478047,
|
|
"loss": 4.9504,
|
|
"mean_token_accuracy": 0.21672283858060837,
|
|
"num_tokens": 37814788.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.298788738250733,
|
|
"epoch": 1.585494716618636,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047535024357581564,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.20592179000377656,
|
|
"num_tokens": 37826650.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.345539903640747,
|
|
"epoch": 1.5859750240153698,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004753346391522889,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.20050072818994522,
|
|
"num_tokens": 37839362.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.35245943069458,
|
|
"epoch": 1.5864553314121037,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047531903007758667,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.20345453917980194,
|
|
"num_tokens": 37851057.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.277271413803101,
|
|
"epoch": 1.5869356388088378,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004753034163520714,
|
|
"loss": 5.0281,
|
|
"mean_token_accuracy": 0.21871261596679686,
|
|
"num_tokens": 37863507.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.314554977416992,
|
|
"epoch": 1.5874159462055717,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047528779797610557,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.20298245102167128,
|
|
"num_tokens": 37874439.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.353095960617066,
|
|
"epoch": 1.5878962536023056,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047527217495005184,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.2087333008646965,
|
|
"num_tokens": 37886720.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.3201192855834964,
|
|
"epoch": 1.5883765609990395,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047525654727427285,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.2047535702586174,
|
|
"num_tokens": 37897919.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.363012838363647,
|
|
"epoch": 1.5888568683957733,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004752409149491315,
|
|
"loss": 5.1797,
|
|
"mean_token_accuracy": 0.20494158565998077,
|
|
"num_tokens": 37911061.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.343307542800903,
|
|
"epoch": 1.5893371757925072,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047522527797499075,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.2006249099969864,
|
|
"num_tokens": 37922677.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.203279590606689,
|
|
"epoch": 1.589817483189241,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004752096363522135,
|
|
"loss": 4.922,
|
|
"mean_token_accuracy": 0.21460891216993333,
|
|
"num_tokens": 37932802.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.271373987197876,
|
|
"epoch": 1.590297790585975,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047519399008116305,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.20479289144277574,
|
|
"num_tokens": 37944782.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.339709043502808,
|
|
"epoch": 1.5907780979827089,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004751783391622026,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.20663870573043824,
|
|
"num_tokens": 37956577.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.3375811100006105,
|
|
"epoch": 1.5912584053794427,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004751626835956955,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.20496171116828918,
|
|
"num_tokens": 37967937.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.236937761306763,
|
|
"epoch": 1.5917387127761766,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004751470233820053,
|
|
"loss": 5.0682,
|
|
"mean_token_accuracy": 0.2186117634177208,
|
|
"num_tokens": 37978113.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.26765513420105,
|
|
"epoch": 1.5922190201729105,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004751313585214955,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.2111627146601677,
|
|
"num_tokens": 37988852.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.335949420928955,
|
|
"epoch": 1.5926993275696446,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004751156890145298,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.20724963545799255,
|
|
"num_tokens": 38000531.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.255350732803345,
|
|
"epoch": 1.5931796349663785,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000475100014861472,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.21324245631694794,
|
|
"num_tokens": 38011818.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.330066347122193,
|
|
"epoch": 1.5936599423631124,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004750843360626861,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.2115153968334198,
|
|
"num_tokens": 38022455.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.304638671875,
|
|
"epoch": 1.5941402497598463,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004750686526185359,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.21499674618244172,
|
|
"num_tokens": 38033126.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.2155012607574465,
|
|
"epoch": 1.5946205571565804,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047505296452938584,
|
|
"loss": 4.9958,
|
|
"mean_token_accuracy": 0.2102390244603157,
|
|
"num_tokens": 38044935.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.323942947387695,
|
|
"epoch": 1.5951008645533142,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047503727179559995,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.2054184541106224,
|
|
"num_tokens": 38056080.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.328876495361328,
|
|
"epoch": 1.5955811719500481,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047502157441754256,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.20428294390439988,
|
|
"num_tokens": 38066788.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.375869417190552,
|
|
"epoch": 1.596061479346782,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004750058723955781,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.20579786151647567,
|
|
"num_tokens": 38079529.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.30080213546753,
|
|
"epoch": 1.5965417867435159,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004749901657300713,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.20463573336601257,
|
|
"num_tokens": 38091484.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.3224687576293945,
|
|
"epoch": 1.5970220941402498,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.00047497445442138667,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.2094428986310959,
|
|
"num_tokens": 38103102.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.362610769271851,
|
|
"epoch": 1.5975024015369836,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047495873846988896,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.19787125587463378,
|
|
"num_tokens": 38115565.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.292722463607788,
|
|
"epoch": 1.5979827089337175,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004749430178759431,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.2077077865600586,
|
|
"num_tokens": 38126741.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.267918729782105,
|
|
"epoch": 1.5984630163304514,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.00047492729263991413,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.20735271275043488,
|
|
"num_tokens": 38137149.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.275971412658691,
|
|
"epoch": 1.5989433237271853,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047491156276216695,
|
|
"loss": 5.0209,
|
|
"mean_token_accuracy": 0.21761179566383362,
|
|
"num_tokens": 38148537.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.283541202545166,
|
|
"epoch": 1.5994236311239192,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047489582824306704,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.20780387669801711,
|
|
"num_tokens": 38159097.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.257484436035156,
|
|
"epoch": 1.5999039385206533,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047488008908297955,
|
|
"loss": 5.0376,
|
|
"mean_token_accuracy": 0.21827599704265593,
|
|
"num_tokens": 38171400.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.420404481887817,
|
|
"epoch": 1.6003842459173871,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004748643452822699,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.20902111977338791,
|
|
"num_tokens": 38181876.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.340447187423706,
|
|
"epoch": 1.600864553314121,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004748485968413036,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.21367233246564865,
|
|
"num_tokens": 38193680.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.178025817871093,
|
|
"epoch": 1.601344860710855,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047483284376044634,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.21309840381145478,
|
|
"num_tokens": 38204944.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.284568119049072,
|
|
"epoch": 1.601825168107589,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004748170860400638,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.2130626395344734,
|
|
"num_tokens": 38216381.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.302024173736572,
|
|
"epoch": 1.602305475504323,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00047480132368052185,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.21649913340806962,
|
|
"num_tokens": 38227420.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.307836961746216,
|
|
"epoch": 1.6027857829010568,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047478555668218643,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.2094103068113327,
|
|
"num_tokens": 38237869.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.298277235031128,
|
|
"epoch": 1.6032660902977907,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004747697850454237,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.20520910769701003,
|
|
"num_tokens": 38250362.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.435504817962647,
|
|
"epoch": 1.6037463976945245,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004747540087705997,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.1993291437625885,
|
|
"num_tokens": 38262887.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.321794605255127,
|
|
"epoch": 1.6042267050912584,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004747382278580808,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.21518548280000688,
|
|
"num_tokens": 38273206.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.287866878509521,
|
|
"epoch": 1.6047070124879923,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004747224423082333,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.2104703366756439,
|
|
"num_tokens": 38283307.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.364654493331909,
|
|
"epoch": 1.6051873198847262,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047470665212142384,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.2066923663020134,
|
|
"num_tokens": 38293830.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.336060047149658,
|
|
"epoch": 1.60566762728146,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047469085729801887,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.21079878956079484,
|
|
"num_tokens": 38306523.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.314435291290283,
|
|
"epoch": 1.606147934678194,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047467505783838515,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.21338141411542894,
|
|
"num_tokens": 38318468.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.342729902267456,
|
|
"epoch": 1.6066282420749278,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004746592537428895,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.2130373403429985,
|
|
"num_tokens": 38329852.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.221718978881836,
|
|
"epoch": 1.6071085494716617,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047464344501189877,
|
|
"loss": 4.9683,
|
|
"mean_token_accuracy": 0.22213088423013688,
|
|
"num_tokens": 38340951.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.357579088211059,
|
|
"epoch": 1.6075888568683958,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047462763164578015,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.20352368503808976,
|
|
"num_tokens": 38351490.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.338244676589966,
|
|
"epoch": 1.6080691642651297,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004746118136449007,
|
|
"loss": 5.0639,
|
|
"mean_token_accuracy": 0.2047002837061882,
|
|
"num_tokens": 38362364.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.304887914657593,
|
|
"epoch": 1.6085494716618636,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004745959910096276,
|
|
"loss": 5.1316,
|
|
"mean_token_accuracy": 0.21248288154602052,
|
|
"num_tokens": 38374132.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.331747674942017,
|
|
"epoch": 1.6090297790585975,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047458016374032837,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.2035684570670128,
|
|
"num_tokens": 38384608.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.353367948532105,
|
|
"epoch": 1.6095100864553316,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004745643318373703,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.20489526838064193,
|
|
"num_tokens": 38396639.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.321113872528076,
|
|
"epoch": 1.6099903938520654,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047454849530112106,
|
|
"loss": 5.1098,
|
|
"mean_token_accuracy": 0.20117121636867524,
|
|
"num_tokens": 38407954.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.3794433116912845,
|
|
"epoch": 1.6104707012487993,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047453265413194826,
|
|
"loss": 5.0774,
|
|
"mean_token_accuracy": 0.2087887316942215,
|
|
"num_tokens": 38418939.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.346958637237549,
|
|
"epoch": 1.6109510086455332,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047451680833021973,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.2052266851067543,
|
|
"num_tokens": 38429717.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.216208600997925,
|
|
"epoch": 1.611431316042267,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004745009578963034,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.21313693672418593,
|
|
"num_tokens": 38441054.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.194230270385742,
|
|
"epoch": 1.611911623439001,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047448510283056716,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.21272834092378617,
|
|
"num_tokens": 38451329.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.337768697738648,
|
|
"epoch": 1.6123919308357348,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047446924313337925,
|
|
"loss": 5.1185,
|
|
"mean_token_accuracy": 0.20390904694795609,
|
|
"num_tokens": 38462118.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.276772737503052,
|
|
"epoch": 1.6128722382324687,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047445337880510773,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.2156524583697319,
|
|
"num_tokens": 38472642.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.226366376876831,
|
|
"epoch": 1.6133525456292026,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004744375098461211,
|
|
"loss": 4.993,
|
|
"mean_token_accuracy": 0.21407995373010635,
|
|
"num_tokens": 38483866.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.300112915039063,
|
|
"epoch": 1.6138328530259365,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004744216362567876,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.21433386355638503,
|
|
"num_tokens": 38494164.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.364255142211914,
|
|
"epoch": 1.6143131604226704,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047440575803747595,
|
|
"loss": 5.221,
|
|
"mean_token_accuracy": 0.1988980606198311,
|
|
"num_tokens": 38505340.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.444919490814209,
|
|
"epoch": 1.6147934678194045,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047438987518855463,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.20270504653453827,
|
|
"num_tokens": 38516164.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.3805742263793945,
|
|
"epoch": 1.6152737752161384,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004743739877103926,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.2102931931614876,
|
|
"num_tokens": 38526545.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.256982660293579,
|
|
"epoch": 1.6157540826128722,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004743580956033585,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.20837611854076385,
|
|
"num_tokens": 38538102.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.3354181289672855,
|
|
"epoch": 1.6162343900096061,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047434219886782135,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.20118009001016618,
|
|
"num_tokens": 38550594.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.338464164733887,
|
|
"epoch": 1.6167146974063402,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004743262975041504,
|
|
"loss": 5.0281,
|
|
"mean_token_accuracy": 0.21206241697072983,
|
|
"num_tokens": 38561666.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.272887277603149,
|
|
"epoch": 1.617195004803074,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004743103915127146,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.215212582051754,
|
|
"num_tokens": 38572923.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.244351816177368,
|
|
"epoch": 1.617675312199808,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00047429448089388336,
|
|
"loss": 5.0458,
|
|
"mean_token_accuracy": 0.21278014034032822,
|
|
"num_tokens": 38584108.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.380122184753418,
|
|
"epoch": 1.6181556195965419,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047427856564802605,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.19814595133066176,
|
|
"num_tokens": 38594974.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.383210611343384,
|
|
"epoch": 1.6186359269932757,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004742626457755122,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.2052934557199478,
|
|
"num_tokens": 38606436.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.271665096282959,
|
|
"epoch": 1.6191162343900096,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004742467212767114,
|
|
"loss": 5.0154,
|
|
"mean_token_accuracy": 0.2066379740834236,
|
|
"num_tokens": 38618760.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.237734603881836,
|
|
"epoch": 1.6195965417867435,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004742307921519933,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.2161208212375641,
|
|
"num_tokens": 38629901.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.378278017044067,
|
|
"epoch": 1.6200768491834774,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047421485840172794,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.19535476416349412,
|
|
"num_tokens": 38640798.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.360268926620483,
|
|
"epoch": 1.6205571565802113,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004741989200262851,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.20457079708576204,
|
|
"num_tokens": 38653048.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.349793338775635,
|
|
"epoch": 1.6210374639769451,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004741829770260347,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.20303380042314528,
|
|
"num_tokens": 38666219.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.331890010833741,
|
|
"epoch": 1.621517771373679,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047416702940134714,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.20845467746257781,
|
|
"num_tokens": 38678584.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.297105884552002,
|
|
"epoch": 1.621998078770413,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047415107715259255,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.2050744116306305,
|
|
"num_tokens": 38690164.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.31823992729187,
|
|
"epoch": 1.622478386167147,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047413512028014125,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.2097344547510147,
|
|
"num_tokens": 38702035.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.38923020362854,
|
|
"epoch": 1.622958693563881,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004741191587843638,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.20405492037534714,
|
|
"num_tokens": 38713802.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.329560375213623,
|
|
"epoch": 1.6234390009606148,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004741031926656308,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.21811476796865464,
|
|
"num_tokens": 38725682.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.270963048934936,
|
|
"epoch": 1.6239193083573487,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004740872219243128,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.2113190323114395,
|
|
"num_tokens": 38737897.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.37080397605896,
|
|
"epoch": 1.6243996157540828,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004740712465607807,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.20485543757677077,
|
|
"num_tokens": 38749446.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.354019117355347,
|
|
"epoch": 1.6248799231508166,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004740552665754054,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.20189750492572783,
|
|
"num_tokens": 38761406.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.323232984542846,
|
|
"epoch": 1.6253602305475505,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047403928196855776,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.21115460991859436,
|
|
"num_tokens": 38772574.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.271060466766357,
|
|
"epoch": 1.6258405379442844,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047402329274060916,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.21697424501180648,
|
|
"num_tokens": 38782932.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.346034002304077,
|
|
"epoch": 1.6263208453410183,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004740072988919306,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.20802369266748427,
|
|
"num_tokens": 38793799.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.2508063316345215,
|
|
"epoch": 1.6268011527377522,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004739913004228936,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.21558031141757966,
|
|
"num_tokens": 38804899.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.300131797790527,
|
|
"epoch": 1.627281460134486,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004739752973338694,
|
|
"loss": 5.1523,
|
|
"mean_token_accuracy": 0.19897391200065612,
|
|
"num_tokens": 38816455.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.352627754211426,
|
|
"epoch": 1.62776176753122,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047395928962522965,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.21070034801959991,
|
|
"num_tokens": 38827735.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.2939005374908445,
|
|
"epoch": 1.6282420749279538,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00047394327729734595,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.20251616537570954,
|
|
"num_tokens": 38838536.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.3701070785522464,
|
|
"epoch": 1.6287223823246877,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004739272603505901,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.20897049456834793,
|
|
"num_tokens": 38849577.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.430567693710327,
|
|
"epoch": 1.6292026897214216,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000473911238785334,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.20393307954072953,
|
|
"num_tokens": 38861370.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.288699054718018,
|
|
"epoch": 1.6296829971181557,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004738952126019496,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.20892221182584764,
|
|
"num_tokens": 38872885.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.270905685424805,
|
|
"epoch": 1.6301633045148896,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004738791818008089,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.20901542156934738,
|
|
"num_tokens": 38885440.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.3410890102386475,
|
|
"epoch": 1.6306436119116234,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004738631463822841,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.21156086325645446,
|
|
"num_tokens": 38897108.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.2630445003509525,
|
|
"epoch": 1.6311239193083573,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047384710634674766,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.20535554438829423,
|
|
"num_tokens": 38908020.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.297327613830566,
|
|
"epoch": 1.6316042267050914,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047383106169457184,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.20820825546979904,
|
|
"num_tokens": 38919558.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.339403820037842,
|
|
"epoch": 1.6320845341018253,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004738150124261292,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.21037687361240387,
|
|
"num_tokens": 38931008.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.251557397842407,
|
|
"epoch": 1.6325648414985592,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047379895854179226,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.21601705998182297,
|
|
"num_tokens": 38943474.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.335887098312378,
|
|
"epoch": 1.633045148895293,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004737829000419338,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.20185681134462358,
|
|
"num_tokens": 38954592.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.314235258102417,
|
|
"epoch": 1.633525456292027,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047376683692692666,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.2123204916715622,
|
|
"num_tokens": 38965627.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.23765001296997,
|
|
"epoch": 1.6340057636887608,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004737507691971439,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.21367433816194534,
|
|
"num_tokens": 38975731.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.272068071365356,
|
|
"epoch": 1.6344860710854947,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047373469685295833,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.21641003340482712,
|
|
"num_tokens": 38987101.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.288151502609253,
|
|
"epoch": 1.6349663784822286,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047371861989474326,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.2125428155064583,
|
|
"num_tokens": 38999584.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.2543353080749515,
|
|
"epoch": 1.6354466858789625,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004737025383228719,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.21478338092565535,
|
|
"num_tokens": 39012025.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.205795860290527,
|
|
"epoch": 1.6359269932756964,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047368645213771764,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.21672004014253615,
|
|
"num_tokens": 39024102.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.325501537322998,
|
|
"epoch": 1.6364073006724302,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000473670361339654,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.2032487526535988,
|
|
"num_tokens": 39035295.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.275527429580689,
|
|
"epoch": 1.6368876080691641,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004736542659290544,
|
|
"loss": 4.9821,
|
|
"mean_token_accuracy": 0.20851410627365113,
|
|
"num_tokens": 39046493.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.282931566238403,
|
|
"epoch": 1.6373679154658982,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004736381659062927,
|
|
"loss": 5.0246,
|
|
"mean_token_accuracy": 0.21455830633640288,
|
|
"num_tokens": 39056746.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.320876264572144,
|
|
"epoch": 1.637848222862632,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047362206127174255,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.20003198087215424,
|
|
"num_tokens": 39068263.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.324578714370728,
|
|
"epoch": 1.638328530259366,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047360595202577786,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.20833728909492494,
|
|
"num_tokens": 39080666.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.24551043510437,
|
|
"epoch": 1.6388088376560999,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047358983816877284,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.2035980835556984,
|
|
"num_tokens": 39091851.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.372729396820068,
|
|
"epoch": 1.639289145052834,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004735737197011015,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.20821507424116134,
|
|
"num_tokens": 39102893.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.2619948387146,
|
|
"epoch": 1.6397694524495678,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047355759662313793,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.2105441525578499,
|
|
"num_tokens": 39113582.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.346616315841675,
|
|
"epoch": 1.6402497598463017,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004735414689352566,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.2009565606713295,
|
|
"num_tokens": 39124616.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.200970554351807,
|
|
"epoch": 1.6407300672430356,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004735253366378318,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.2147371932864189,
|
|
"num_tokens": 39135537.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.328286457061767,
|
|
"epoch": 1.6412103746397695,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004735091997312383,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.21201014071702956,
|
|
"num_tokens": 39146363.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.296258020401001,
|
|
"epoch": 1.6416906820365034,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047349305821585067,
|
|
"loss": 5.0345,
|
|
"mean_token_accuracy": 0.2155297428369522,
|
|
"num_tokens": 39157319.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.270400762557983,
|
|
"epoch": 1.6421709894332372,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004734769120920435,
|
|
"loss": 5.0376,
|
|
"mean_token_accuracy": 0.21263784915208817,
|
|
"num_tokens": 39169352.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.359902954101562,
|
|
"epoch": 1.6426512968299711,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004734607613601919,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.20997129529714584,
|
|
"num_tokens": 39180989.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.3101013660430905,
|
|
"epoch": 1.643131604226705,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047344460602067077,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.20525191426277162,
|
|
"num_tokens": 39192309.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.1833415031433105,
|
|
"epoch": 1.643611911623439,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000473428446073855,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.21010292023420335,
|
|
"num_tokens": 39203586.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.259043598175049,
|
|
"epoch": 1.6440922190201728,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047341228152012003,
|
|
"loss": 5.0588,
|
|
"mean_token_accuracy": 0.20251668393611907,
|
|
"num_tokens": 39216248.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.310799407958984,
|
|
"epoch": 1.6445725264169067,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000473396112359841,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.20936723351478576,
|
|
"num_tokens": 39227244.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.301188707351685,
|
|
"epoch": 1.6450528338136408,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047337993859339334,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.21474155634641648,
|
|
"num_tokens": 39238769.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.283073377609253,
|
|
"epoch": 1.6455331412103746,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047336376022115255,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.20849765837192535,
|
|
"num_tokens": 39251424.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.231944799423218,
|
|
"epoch": 1.6460134486071085,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047334757724349437,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.2130365788936615,
|
|
"num_tokens": 39262451.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.268719053268432,
|
|
"epoch": 1.6464937560038426,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004733313896607943,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.2091429904103279,
|
|
"num_tokens": 39275129.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.375137281417847,
|
|
"epoch": 1.6469740634005765,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004733151974734284,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.20444968044757844,
|
|
"num_tokens": 39287399.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.308919858932495,
|
|
"epoch": 1.6474543707973104,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047329900068177245,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.2114996552467346,
|
|
"num_tokens": 39297755.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.353009843826294,
|
|
"epoch": 1.6479346781940443,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00047328279928620244,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.20128021091222764,
|
|
"num_tokens": 39311012.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.361724185943603,
|
|
"epoch": 1.6484149855907781,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004732665932870947,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.20949484556913375,
|
|
"num_tokens": 39321797.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.3296154022216795,
|
|
"epoch": 1.648895292987512,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047325038268482544,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.2176440954208374,
|
|
"num_tokens": 39333598.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.33280348777771,
|
|
"epoch": 1.649375600384246,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004732341674797709,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.20241859704256057,
|
|
"num_tokens": 39345578.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.220914316177368,
|
|
"epoch": 1.6498559077809798,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047321794767230766,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.21593749672174453,
|
|
"num_tokens": 39356744.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.340908575057983,
|
|
"epoch": 1.6503362151777137,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047320172326281224,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.2064099445939064,
|
|
"num_tokens": 39368138.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.266617774963379,
|
|
"epoch": 1.6508165225744476,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047318549425166134,
|
|
"loss": 4.9539,
|
|
"mean_token_accuracy": 0.21723274886608124,
|
|
"num_tokens": 39380117.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.250093841552735,
|
|
"epoch": 1.6512968299711814,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004731692606392318,
|
|
"loss": 5.026,
|
|
"mean_token_accuracy": 0.20863229781389236,
|
|
"num_tokens": 39390913.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.333778238296508,
|
|
"epoch": 1.6517771373679153,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004731530224259004,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.19636747986078262,
|
|
"num_tokens": 39401001.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.265682697296143,
|
|
"epoch": 1.6522574447646494,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004731367796120442,
|
|
"loss": 5.0488,
|
|
"mean_token_accuracy": 0.21238905787467957,
|
|
"num_tokens": 39411982.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.366572427749634,
|
|
"epoch": 1.6527377521613833,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004731205321980404,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.20713277906179428,
|
|
"num_tokens": 39423363.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.328851747512817,
|
|
"epoch": 1.6532180595581172,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047310428018426616,
|
|
"loss": 5.1255,
|
|
"mean_token_accuracy": 0.2098961666226387,
|
|
"num_tokens": 39434002.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.2321693897247314,
|
|
"epoch": 1.653698366954851,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004730880235710987,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.21095893681049346,
|
|
"num_tokens": 39444629.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.295881748199463,
|
|
"epoch": 1.6541786743515852,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004730717623589155,
|
|
"loss": 4.9683,
|
|
"mean_token_accuracy": 0.21932769566774368,
|
|
"num_tokens": 39454803.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.300078248977661,
|
|
"epoch": 1.654658981748319,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004730554965480942,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.20776157975196838,
|
|
"num_tokens": 39466931.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.266944217681885,
|
|
"epoch": 1.655139289145053,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004730392261390124,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.20985424816608428,
|
|
"num_tokens": 39478127.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.321455717086792,
|
|
"epoch": 1.6556195965417868,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004730229511320478,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.20590091347694398,
|
|
"num_tokens": 39488188.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.333714866638184,
|
|
"epoch": 1.6560999039385207,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047300667152757827,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.20882366150617598,
|
|
"num_tokens": 39500035.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.311215782165528,
|
|
"epoch": 1.6565802113352546,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047299038732598184,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.206865993142128,
|
|
"num_tokens": 39510922.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.258708667755127,
|
|
"epoch": 1.6570605187319885,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047297409852763644,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.2120583698153496,
|
|
"num_tokens": 39521319.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.32377405166626,
|
|
"epoch": 1.6575408261287223,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004729578051329204,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.20981634855270387,
|
|
"num_tokens": 39532408.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.370115947723389,
|
|
"epoch": 1.6580211335254562,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047294150714221185,
|
|
"loss": 5.1298,
|
|
"mean_token_accuracy": 0.20058363676071167,
|
|
"num_tokens": 39543323.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.349912643432617,
|
|
"epoch": 1.65850144092219,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004729252045558894,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.20597438365221024,
|
|
"num_tokens": 39554133.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.25756459236145,
|
|
"epoch": 1.658981748318924,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047290889737433133,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.21188713610172272,
|
|
"num_tokens": 39565990.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.325252389907837,
|
|
"epoch": 1.6594620557156579,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047289258559791633,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.2111702486872673,
|
|
"num_tokens": 39577591.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.339227104187012,
|
|
"epoch": 1.659942363112392,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047287626922702317,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.20843616873025894,
|
|
"num_tokens": 39589922.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.2627747535705565,
|
|
"epoch": 1.6604226705091258,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047285994826203054,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.21190861910581588,
|
|
"num_tokens": 39602183.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.328217697143555,
|
|
"epoch": 1.6609029779058597,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004728436227033175,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.20965490788221358,
|
|
"num_tokens": 39612922.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.377883958816528,
|
|
"epoch": 1.6613832853025938,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047282729255126294,
|
|
"loss": 5.067,
|
|
"mean_token_accuracy": 0.20851318687200546,
|
|
"num_tokens": 39624475.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.198849391937256,
|
|
"epoch": 1.6618635926993277,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004728109578062461,
|
|
"loss": 4.9289,
|
|
"mean_token_accuracy": 0.21803170591592788,
|
|
"num_tokens": 39635230.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.221282052993774,
|
|
"epoch": 1.6623439000960616,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047279461846864626,
|
|
"loss": 5.0349,
|
|
"mean_token_accuracy": 0.20978556275367738,
|
|
"num_tokens": 39646788.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.276208305358887,
|
|
"epoch": 1.6628242074927955,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047277827453884265,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.2114986553788185,
|
|
"num_tokens": 39657531.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.418065309524536,
|
|
"epoch": 1.6633045148895294,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047276192601721477,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.19723718464374543,
|
|
"num_tokens": 39669008.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.321707916259766,
|
|
"epoch": 1.6637848222862632,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004727455729041422,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.20875480473041536,
|
|
"num_tokens": 39680772.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.4002601146698,
|
|
"epoch": 1.6642651296829971,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047272921520000465,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.19823125153779983,
|
|
"num_tokens": 39694107.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.260912990570068,
|
|
"epoch": 1.664745437079731,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004727128529051819,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.20769205689430237,
|
|
"num_tokens": 39705440.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.25518045425415,
|
|
"epoch": 1.6652257444764649,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004726964860200537,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.2112964853644371,
|
|
"num_tokens": 39716246.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.335805940628052,
|
|
"epoch": 1.6657060518731988,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004726801145450002,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.20471725314855577,
|
|
"num_tokens": 39727233.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.34052004814148,
|
|
"epoch": 1.6661863592699326,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004726637384804014,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.2087594136595726,
|
|
"num_tokens": 39738929.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.283181619644165,
|
|
"epoch": 1.6666666666666665,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004726473578266375,
|
|
"loss": 5.0588,
|
|
"mean_token_accuracy": 0.20847259759902953,
|
|
"num_tokens": 39750714.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.276309061050415,
|
|
"epoch": 1.6671469740634006,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00047263097258408893,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.20803593546152116,
|
|
"num_tokens": 39762810.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.35517692565918,
|
|
"epoch": 1.6676272814601345,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004726145827531359,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.2026548683643341,
|
|
"num_tokens": 39774611.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.247454214096069,
|
|
"epoch": 1.6681075888568684,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047259818833415916,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.21626731604337693,
|
|
"num_tokens": 39784900.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.386185932159424,
|
|
"epoch": 1.6685878962536023,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047258178932753917,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.21031530648469926,
|
|
"num_tokens": 39794805.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.355830335617066,
|
|
"epoch": 1.6690682036503364,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00047256538573365675,
|
|
"loss": 5.1067,
|
|
"mean_token_accuracy": 0.20283535420894622,
|
|
"num_tokens": 39806444.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.427976131439209,
|
|
"epoch": 1.6695485110470702,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004725489775528928,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.19671351462602615,
|
|
"num_tokens": 39817724.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.281654310226441,
|
|
"epoch": 1.6700288184438041,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00047253256478562805,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.2050136774778366,
|
|
"num_tokens": 39828944.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.273978042602539,
|
|
"epoch": 1.670509125840538,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00047251614743224374,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.21034155786037445,
|
|
"num_tokens": 39839978.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.31033411026001,
|
|
"epoch": 1.670989433237272,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047249972549312107,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.21320640295743942,
|
|
"num_tokens": 39850787.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.366944789886475,
|
|
"epoch": 1.6714697406340058,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004724832989686411,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.21022327989339828,
|
|
"num_tokens": 39862245.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.271491813659668,
|
|
"epoch": 1.6719500480307397,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047246686785918545,
|
|
"loss": 5.0268,
|
|
"mean_token_accuracy": 0.21342124193906784,
|
|
"num_tokens": 39872295.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.236797618865967,
|
|
"epoch": 1.6724303554274735,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047245043216513546,
|
|
"loss": 4.9847,
|
|
"mean_token_accuracy": 0.20913004726171494,
|
|
"num_tokens": 39882839.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.237705039978027,
|
|
"epoch": 1.6729106628242074,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004724339918868727,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.21181651055812836,
|
|
"num_tokens": 39894767.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.34732837677002,
|
|
"epoch": 1.6733909702209413,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000472417547024779,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.1986520081758499,
|
|
"num_tokens": 39907492.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.210131549835205,
|
|
"epoch": 1.6738712776176752,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047240109757923593,
|
|
"loss": 4.9323,
|
|
"mean_token_accuracy": 0.2148791030049324,
|
|
"num_tokens": 39919005.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.2489905834198,
|
|
"epoch": 1.674351585014409,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004723846435506256,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.21284741014242173,
|
|
"num_tokens": 39930417.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.24761266708374,
|
|
"epoch": 1.6748318924111432,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047236818493932994,
|
|
"loss": 5.0552,
|
|
"mean_token_accuracy": 0.2102885976433754,
|
|
"num_tokens": 39941873.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.343794679641723,
|
|
"epoch": 1.675312199807877,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004723517217457311,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.2048580005764961,
|
|
"num_tokens": 39953280.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.4011180877685545,
|
|
"epoch": 1.675792507204611,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004723352539702113,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.2031763970851898,
|
|
"num_tokens": 39964898.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.3044677734375,
|
|
"epoch": 1.6762728146013448,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004723187816131529,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.21282412111759186,
|
|
"num_tokens": 39976945.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.351509284973145,
|
|
"epoch": 1.676753121998079,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004723023046749383,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.20709767639636995,
|
|
"num_tokens": 39987760.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.253203821182251,
|
|
"epoch": 1.6772334293948128,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047228582315595,
|
|
"loss": 4.9116,
|
|
"mean_token_accuracy": 0.22218418419361113,
|
|
"num_tokens": 39998171.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.267012691497802,
|
|
"epoch": 1.6777137367915467,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004722693370565708,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.2085336983203888,
|
|
"num_tokens": 40010124.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.281265687942505,
|
|
"epoch": 1.6781940441882806,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00047225284637718323,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.20429042726755142,
|
|
"num_tokens": 40022599.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.315108728408814,
|
|
"epoch": 1.6786743515850144,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004722363511181703,
|
|
"loss": 5.0043,
|
|
"mean_token_accuracy": 0.2191181093454361,
|
|
"num_tokens": 40033738.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.320285844802856,
|
|
"epoch": 1.6791546589817483,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000472219851279915,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.21348150968551635,
|
|
"num_tokens": 40044148.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.328495693206787,
|
|
"epoch": 1.6796349663784822,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004722033468628004,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.21177013367414474,
|
|
"num_tokens": 40055430.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.259841823577881,
|
|
"epoch": 1.680115273775216,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004721868378672098,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.21214968860149383,
|
|
"num_tokens": 40066147.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.311545372009277,
|
|
"epoch": 1.68059558117195,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004721703242935261,
|
|
"loss": 5.0307,
|
|
"mean_token_accuracy": 0.21098269075155257,
|
|
"num_tokens": 40077567.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.362444448471069,
|
|
"epoch": 1.6810758885686838,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004721538061421331,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.2048191487789154,
|
|
"num_tokens": 40089544.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.203444719314575,
|
|
"epoch": 1.6815561959654177,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047213728341341407,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.22030575424432755,
|
|
"num_tokens": 40100557.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.327872848510742,
|
|
"epoch": 1.6820365033621518,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004721207561077527,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.20620910674333573,
|
|
"num_tokens": 40112052.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.497119283676147,
|
|
"epoch": 1.6825168107588857,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004721042242255327,
|
|
"loss": 5.2469,
|
|
"mean_token_accuracy": 0.19710370451211928,
|
|
"num_tokens": 40123830.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.34385085105896,
|
|
"epoch": 1.6829971181556196,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00047208768776713805,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.2112124189734459,
|
|
"num_tokens": 40134222.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.276069402694702,
|
|
"epoch": 1.6834774255523535,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004720711467329523,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.21251606345176696,
|
|
"num_tokens": 40145552.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.253878927230835,
|
|
"epoch": 1.6839577329490876,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004720546011233599,
|
|
"loss": 4.9403,
|
|
"mean_token_accuracy": 0.21546922773122787,
|
|
"num_tokens": 40156615.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.269441413879394,
|
|
"epoch": 1.6844380403458215,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004720380509387446,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.2120695471763611,
|
|
"num_tokens": 40168825.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.293647956848145,
|
|
"epoch": 1.6849183477425553,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000472021496179491,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.21115250438451766,
|
|
"num_tokens": 40179523.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.28689227104187,
|
|
"epoch": 1.6853986551392892,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047200493684598316,
|
|
"loss": 5.003,
|
|
"mean_token_accuracy": 0.21079657971858978,
|
|
"num_tokens": 40191362.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.298970031738281,
|
|
"epoch": 1.685878962536023,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047198837293860573,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.2081828936934471,
|
|
"num_tokens": 40202274.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.3592640399932865,
|
|
"epoch": 1.686359269932757,
|
|
"grad_norm": 7.3125,
|
|
"learning_rate": 0.0004719718044577432,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.20209406763315202,
|
|
"num_tokens": 40213907.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.254560089111328,
|
|
"epoch": 1.6868395773294909,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047195523140378034,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.20776725560426712,
|
|
"num_tokens": 40225300.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.220425033569336,
|
|
"epoch": 1.6873198847262247,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047193865377710177,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.21640539765357972,
|
|
"num_tokens": 40236197.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.412212085723877,
|
|
"epoch": 1.6878001921229586,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047192207157809246,
|
|
"loss": 5.1685,
|
|
"mean_token_accuracy": 0.20226399302482606,
|
|
"num_tokens": 40247887.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.39486026763916,
|
|
"epoch": 1.6882804995196925,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047190548480713736,
|
|
"loss": 5.0184,
|
|
"mean_token_accuracy": 0.2094702437520027,
|
|
"num_tokens": 40258262.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.320482540130615,
|
|
"epoch": 1.6887608069164264,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047188889346462163,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.2039002388715744,
|
|
"num_tokens": 40268735.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.339608573913575,
|
|
"epoch": 1.6892411143131603,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047187229755093037,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.19981771856546401,
|
|
"num_tokens": 40279905.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.331702947616577,
|
|
"epoch": 1.6897214217098944,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000471855697066449,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.2088620826601982,
|
|
"num_tokens": 40290580.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.3216057300567625,
|
|
"epoch": 1.6902017291066282,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047183909201156297,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.20497860312461852,
|
|
"num_tokens": 40302472.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.374712514877319,
|
|
"epoch": 1.6906820365033621,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004718224823866576,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.20098289400339125,
|
|
"num_tokens": 40314238.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.249492549896241,
|
|
"epoch": 1.691162343900096,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004718058681921186,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.2114214763045311,
|
|
"num_tokens": 40326147.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.337893533706665,
|
|
"epoch": 1.6916426512968301,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047178924942833185,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.21324871331453324,
|
|
"num_tokens": 40338210.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.27638521194458,
|
|
"epoch": 1.692122958693564,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004717726260956831,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.21868437975645066,
|
|
"num_tokens": 40349293.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.275179481506347,
|
|
"epoch": 1.6926032660902979,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004717559981945581,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.20724861919879914,
|
|
"num_tokens": 40360916.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.301390361785889,
|
|
"epoch": 1.6930835734870318,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004717393657253432,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.20472198873758315,
|
|
"num_tokens": 40373525.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.329948759078979,
|
|
"epoch": 1.6935638808837656,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004717227286884243,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.20501853823661803,
|
|
"num_tokens": 40385286.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.321048307418823,
|
|
"epoch": 1.6940441882804995,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004717060870841879,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.20899488776922226,
|
|
"num_tokens": 40396371.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.3167863368988035,
|
|
"epoch": 1.6945244956772334,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004716894409130202,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.20931693613529206,
|
|
"num_tokens": 40407304.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.277111482620239,
|
|
"epoch": 1.6950048030739673,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004716727901753078,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.20877570509910584,
|
|
"num_tokens": 40418384.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.371481895446777,
|
|
"epoch": 1.6954851104707012,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004716561348714371,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.20625497698783873,
|
|
"num_tokens": 40430603.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.292591905593872,
|
|
"epoch": 1.695965417867435,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047163947500179494,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.21318791061639786,
|
|
"num_tokens": 40442597.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.200218677520752,
|
|
"epoch": 1.696445725264169,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004716228105667681,
|
|
"loss": 4.9453,
|
|
"mean_token_accuracy": 0.2173769325017929,
|
|
"num_tokens": 40454078.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.251240396499634,
|
|
"epoch": 1.696926032660903,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004716061415667435,
|
|
"loss": 5.0006,
|
|
"mean_token_accuracy": 0.21560627222061157,
|
|
"num_tokens": 40465561.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.358589029312133,
|
|
"epoch": 1.697406340057637,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000471589468002108,
|
|
"loss": 5.1027,
|
|
"mean_token_accuracy": 0.20977002382278442,
|
|
"num_tokens": 40476883.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.315391540527344,
|
|
"epoch": 1.6978866474543708,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004715727898732488,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.21534698754549025,
|
|
"num_tokens": 40488139.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.285712099075317,
|
|
"epoch": 1.6983669548511047,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047155610718055315,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.21187641024589537,
|
|
"num_tokens": 40499367.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.247774076461792,
|
|
"epoch": 1.6988472622478388,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047153941992440833,
|
|
"loss": 5.0243,
|
|
"mean_token_accuracy": 0.20232046842575074,
|
|
"num_tokens": 40510628.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.217894601821899,
|
|
"epoch": 1.6993275696445727,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004715227281052018,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.21723879724740983,
|
|
"num_tokens": 40522680.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.197141647338867,
|
|
"epoch": 1.6998078770413065,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004715060317233211,
|
|
"loss": 4.9394,
|
|
"mean_token_accuracy": 0.22519012838602065,
|
|
"num_tokens": 40533139.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.3428487300872805,
|
|
"epoch": 1.7002881844380404,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004714893307791538,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.21122673898935318,
|
|
"num_tokens": 40544578.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.394808721542359,
|
|
"epoch": 1.7007684918347743,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047147262527308766,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.21298388838768006,
|
|
"num_tokens": 40555667.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.284377813339233,
|
|
"epoch": 1.7012487992315082,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004714559152055106,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.2143390506505966,
|
|
"num_tokens": 40567123.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.3383238315582275,
|
|
"epoch": 1.701729106628242,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004714392005768106,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.20940806865692138,
|
|
"num_tokens": 40579692.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.302740907669067,
|
|
"epoch": 1.702209414024976,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004714224813873756,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.21735740453004837,
|
|
"num_tokens": 40590989.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.224558162689209,
|
|
"epoch": 1.7026897214217098,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047140575763759393,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.21485394835472107,
|
|
"num_tokens": 40602050.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.275645923614502,
|
|
"epoch": 1.7031700288184437,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00047138902932785363,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.20955518782138824,
|
|
"num_tokens": 40614552.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.331122303009034,
|
|
"epoch": 1.7036503362151776,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047137229645854333,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.2187611937522888,
|
|
"num_tokens": 40625903.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.308680725097656,
|
|
"epoch": 1.7041306436119115,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004713555590300513,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.20957717448472976,
|
|
"num_tokens": 40638634.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.340577602386475,
|
|
"epoch": 1.7046109510086456,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004713388170427664,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.20562972724437714,
|
|
"num_tokens": 40651279.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.33116192817688,
|
|
"epoch": 1.7050912584053795,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004713220704970771,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.2098960041999817,
|
|
"num_tokens": 40662306.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.170094060897827,
|
|
"epoch": 1.7055715658021133,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047130531939337236,
|
|
"loss": 4.9018,
|
|
"mean_token_accuracy": 0.22068019211292267,
|
|
"num_tokens": 40672290.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.24260950088501,
|
|
"epoch": 1.7060518731988472,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047128856373204086,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.2107086092233658,
|
|
"num_tokens": 40683447.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.457520294189453,
|
|
"epoch": 1.7065321805955813,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047127180351347184,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.1984176442027092,
|
|
"num_tokens": 40695230.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.33763108253479,
|
|
"epoch": 1.7070124879923152,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004712550387380544,
|
|
"loss": 5.0304,
|
|
"mean_token_accuracy": 0.20985168665647508,
|
|
"num_tokens": 40707311.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.309390830993652,
|
|
"epoch": 1.707492795389049,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004712382694061776,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.21062377691268921,
|
|
"num_tokens": 40717928.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.300785398483276,
|
|
"epoch": 1.707973102785783,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047122149551823096,
|
|
"loss": 5.0682,
|
|
"mean_token_accuracy": 0.20144151002168656,
|
|
"num_tokens": 40730355.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.355575275421143,
|
|
"epoch": 1.7084534101825168,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004712047170746039,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.20955101996660233,
|
|
"num_tokens": 40741412.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.3769913673400875,
|
|
"epoch": 1.7089337175792507,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00047118793407568586,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.21362569332122802,
|
|
"num_tokens": 40753491.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.2515708923339846,
|
|
"epoch": 1.7094140249759846,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047117114652186657,
|
|
"loss": 4.9912,
|
|
"mean_token_accuracy": 0.21644763499498368,
|
|
"num_tokens": 40765209.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.252030992507935,
|
|
"epoch": 1.7098943323727185,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047115435441353573,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.20952441841363906,
|
|
"num_tokens": 40778065.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.353886270523072,
|
|
"epoch": 1.7103746397694524,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00047113755775108333,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.21040690839290618,
|
|
"num_tokens": 40789149.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.30014181137085,
|
|
"epoch": 1.7108549471661862,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047112075653489913,
|
|
"loss": 5.0337,
|
|
"mean_token_accuracy": 0.2195592150092125,
|
|
"num_tokens": 40800340.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.276033687591553,
|
|
"epoch": 1.7113352545629201,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004711039507653734,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.21037130802869797,
|
|
"num_tokens": 40811866.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.319614839553833,
|
|
"epoch": 1.7118155619596542,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004710871404428961,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.20272798836231232,
|
|
"num_tokens": 40825850.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.388823843002319,
|
|
"epoch": 1.7122958693563881,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047107032556785786,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.21079877465963365,
|
|
"num_tokens": 40836688.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.314892911911011,
|
|
"epoch": 1.712776176753122,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047105350614064874,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.20946250706911088,
|
|
"num_tokens": 40847803.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.348804378509522,
|
|
"epoch": 1.7132564841498559,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047103668216165944,
|
|
"loss": 5.0993,
|
|
"mean_token_accuracy": 0.20611426830291749,
|
|
"num_tokens": 40859099.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.240990447998047,
|
|
"epoch": 1.71373679154659,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047101985363128045,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.21787478178739547,
|
|
"num_tokens": 40870440.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.398545837402343,
|
|
"epoch": 1.7142170989433239,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047100302054990255,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.20021020174026488,
|
|
"num_tokens": 40882329.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.376252508163452,
|
|
"epoch": 1.7146974063400577,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004709861829179165,
|
|
"loss": 5.1507,
|
|
"mean_token_accuracy": 0.20237011313438416,
|
|
"num_tokens": 40893458.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.239268016815186,
|
|
"epoch": 1.7151777137367916,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047096934073571325,
|
|
"loss": 4.9659,
|
|
"mean_token_accuracy": 0.21936981827020646,
|
|
"num_tokens": 40904626.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.256492948532104,
|
|
"epoch": 1.7156580211335255,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047095249400368384,
|
|
"loss": 4.9682,
|
|
"mean_token_accuracy": 0.22320087105035782,
|
|
"num_tokens": 40916005.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.246867561340332,
|
|
"epoch": 1.7161383285302594,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047093564272221927,
|
|
"loss": 4.9523,
|
|
"mean_token_accuracy": 0.2178478643298149,
|
|
"num_tokens": 40927470.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.340414381027221,
|
|
"epoch": 1.7166186359269933,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047091878689171105,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.2127180889248848,
|
|
"num_tokens": 40938968.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.237211275100708,
|
|
"epoch": 1.7170989433237271,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004709019265125502,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.22003840059041976,
|
|
"num_tokens": 40952636.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.33972487449646,
|
|
"epoch": 1.717579250720461,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047088506158512837,
|
|
"loss": 5.0955,
|
|
"mean_token_accuracy": 0.21384502202272415,
|
|
"num_tokens": 40964816.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.328907537460327,
|
|
"epoch": 1.718059558117195,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047086819210983714,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.2067756712436676,
|
|
"num_tokens": 40977152.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.2519862174987795,
|
|
"epoch": 1.7185398655139288,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047085131808706813,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.21158942431211472,
|
|
"num_tokens": 40987506.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.362021493911743,
|
|
"epoch": 1.7190201729106627,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004708344395172129,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.21249691098928453,
|
|
"num_tokens": 40998598.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.307884216308594,
|
|
"epoch": 1.7195004803073968,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004708175564006636,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.20432443767786027,
|
|
"num_tokens": 41009644.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.246445989608764,
|
|
"epoch": 1.7199807877041307,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004708006687378121,
|
|
"loss": 4.9685,
|
|
"mean_token_accuracy": 0.21385153383016586,
|
|
"num_tokens": 41021816.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.268310499191284,
|
|
"epoch": 1.7204610951008645,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004707837765290505,
|
|
"loss": 5.0082,
|
|
"mean_token_accuracy": 0.21102462708950043,
|
|
"num_tokens": 41033482.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.271789646148681,
|
|
"epoch": 1.7209414024975984,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004707668797747709,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.21951788812875747,
|
|
"num_tokens": 41043854.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.297924327850342,
|
|
"epoch": 1.7214217098943325,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004707499784753657,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.20410621613264085,
|
|
"num_tokens": 41056956.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.4226751804351805,
|
|
"epoch": 1.7219020172910664,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004707330726312273,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.20128053426742554,
|
|
"num_tokens": 41068170.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.298157453536987,
|
|
"epoch": 1.7223823246878003,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047071616224274803,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.20986811071634293,
|
|
"num_tokens": 41079149.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.342500066757202,
|
|
"epoch": 1.7228626320845342,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004706992473103207,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.2040976107120514,
|
|
"num_tokens": 41091039.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.3082208156585695,
|
|
"epoch": 1.723342939481268,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047068232783433806,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.21285650730133057,
|
|
"num_tokens": 41103318.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.28608808517456,
|
|
"epoch": 1.723823246878002,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004706654038151927,
|
|
"loss": 4.9799,
|
|
"mean_token_accuracy": 0.21823993027210237,
|
|
"num_tokens": 41114235.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.230897426605225,
|
|
"epoch": 1.7243035542747358,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004706484752532777,
|
|
"loss": 5.0511,
|
|
"mean_token_accuracy": 0.21588950157165526,
|
|
"num_tokens": 41126008.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.236124897003174,
|
|
"epoch": 1.7247838616714697,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004706315421489861,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.20848289728164673,
|
|
"num_tokens": 41138819.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.336418771743775,
|
|
"epoch": 1.7252641690682036,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004706146045027109,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.21666808277368546,
|
|
"num_tokens": 41149389.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.287679672241211,
|
|
"epoch": 1.7257444764649374,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004705976623148455,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.20809733867645264,
|
|
"num_tokens": 41161810.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.266623401641846,
|
|
"epoch": 1.7262247838616713,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047058071558578324,
|
|
"loss": 5.0259,
|
|
"mean_token_accuracy": 0.21060358434915544,
|
|
"num_tokens": 41172903.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.306065797805786,
|
|
"epoch": 1.7267050912584054,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004705637643159175,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.21487960517406463,
|
|
"num_tokens": 41183905.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.294497346878051,
|
|
"epoch": 1.7271853986551393,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047054680850564185,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.2092100277543068,
|
|
"num_tokens": 41195921.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.218858146667481,
|
|
"epoch": 1.7276657060518732,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004705298481553499,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.21826158016920089,
|
|
"num_tokens": 41208287.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.304620409011841,
|
|
"epoch": 1.728146013448607,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047051288326543553,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.20336541682481765,
|
|
"num_tokens": 41219864.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.272913599014283,
|
|
"epoch": 1.7286263208453412,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047049591383629247,
|
|
"loss": 5.0177,
|
|
"mean_token_accuracy": 0.21219969540834427,
|
|
"num_tokens": 41230640.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.305487012863159,
|
|
"epoch": 1.729106628242075,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047047893986831493,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.21337115168571472,
|
|
"num_tokens": 41242413.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.729106628242075,
|
|
"eval_entropy": 5.155172023117571,
|
|
"eval_loss": 5.130072116851807,
|
|
"eval_mean_token_accuracy": 0.21423444137166095,
|
|
"eval_num_tokens": 41242413.0,
|
|
"eval_runtime": 26.8082,
|
|
"eval_samples_per_second": 1224.067,
|
|
"eval_steps_per_second": 153.013,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.359158372879028,
|
|
"epoch": 1.729586935638809,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047046196136189686,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.20067351907491685,
|
|
"num_tokens": 41254400.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.279945611953735,
|
|
"epoch": 1.7300672430355428,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004704449783174323,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.21057355999946595,
|
|
"num_tokens": 41266849.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.313865661621094,
|
|
"epoch": 1.7305475504322767,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004704279907353158,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.20442575067281724,
|
|
"num_tokens": 41278179.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.30363917350769,
|
|
"epoch": 1.7310278578290106,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047041099861594167,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.21792377531528473,
|
|
"num_tokens": 41289904.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.434446382522583,
|
|
"epoch": 1.7315081652257445,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004703940019597044,
|
|
"loss": 5.1962,
|
|
"mean_token_accuracy": 0.20008488595485688,
|
|
"num_tokens": 41301861.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.312793254852295,
|
|
"epoch": 1.7319884726224783,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047037700076699857,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.21193612962961197,
|
|
"num_tokens": 41312420.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.287335157394409,
|
|
"epoch": 1.7324687800192122,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000470359995038219,
|
|
"loss": 5.0315,
|
|
"mean_token_accuracy": 0.21608101725578308,
|
|
"num_tokens": 41323264.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.321090650558472,
|
|
"epoch": 1.732949087415946,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004703429847737604,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.20688869059085846,
|
|
"num_tokens": 41335438.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.3426838397979735,
|
|
"epoch": 1.73342939481268,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004703259699740177,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.19895274043083191,
|
|
"num_tokens": 41347295.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.340757751464844,
|
|
"epoch": 1.7339097022094139,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047030895063938607,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.2027134194970131,
|
|
"num_tokens": 41358886.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.289423942565918,
|
|
"epoch": 1.734390009606148,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047029192677026043,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.22134024053812026,
|
|
"num_tokens": 41369402.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.360753011703491,
|
|
"epoch": 1.7348703170028819,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004702748983670363,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.20410456508398056,
|
|
"num_tokens": 41379772.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.347270154953003,
|
|
"epoch": 1.7353506243996157,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004702578654301088,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.2068547412753105,
|
|
"num_tokens": 41389776.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.199202299118042,
|
|
"epoch": 1.7358309317963496,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004702408279598734,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.20837776958942414,
|
|
"num_tokens": 41400640.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.245973777770996,
|
|
"epoch": 1.7363112391930837,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004702237859567258,
|
|
"loss": 4.9922,
|
|
"mean_token_accuracy": 0.21093752533197402,
|
|
"num_tokens": 41412653.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.417133092880249,
|
|
"epoch": 1.7367915465898176,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004702067394210616,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.203184013068676,
|
|
"num_tokens": 41423815.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.325295495986938,
|
|
"epoch": 1.7372718539865515,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047018968835327643,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.2048053190112114,
|
|
"num_tokens": 41436016.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.223222494125366,
|
|
"epoch": 1.7377521613832854,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004701726327537664,
|
|
"loss": 5.01,
|
|
"mean_token_accuracy": 0.2154722958803177,
|
|
"num_tokens": 41447837.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.338507270812988,
|
|
"epoch": 1.7382324687800192,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004701555726229274,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.2118996948003769,
|
|
"num_tokens": 41459816.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.3357385158538815,
|
|
"epoch": 1.7387127761767531,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004701385079611555,
|
|
"loss": 5.0005,
|
|
"mean_token_accuracy": 0.20757359117269517,
|
|
"num_tokens": 41471461.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.250492906570434,
|
|
"epoch": 1.739193083573487,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047012143876884677,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.21634634137153624,
|
|
"num_tokens": 41481886.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.215898227691651,
|
|
"epoch": 1.739673390970221,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004701043650463977,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.20985569059848785,
|
|
"num_tokens": 41493698.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.2768017768859865,
|
|
"epoch": 1.7401536983669548,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004700872867942046,
|
|
"loss": 5.0019,
|
|
"mean_token_accuracy": 0.21895111352205276,
|
|
"num_tokens": 41504744.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.341749811172486,
|
|
"epoch": 1.7406340057636887,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000470070204012664,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.21321367621421813,
|
|
"num_tokens": 41517129.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.347299289703369,
|
|
"epoch": 1.7411143131604225,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047005311670217256,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.20233103185892104,
|
|
"num_tokens": 41529969.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.28585295677185,
|
|
"epoch": 1.7415946205571564,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047003602486312687,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.21380268335342406,
|
|
"num_tokens": 41541515.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.243846464157104,
|
|
"epoch": 1.7420749279538905,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004700189284959238,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.21098914742469788,
|
|
"num_tokens": 41553045.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.338457107543945,
|
|
"epoch": 1.7425552353506244,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047000182760096037,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.2072700247168541,
|
|
"num_tokens": 41565376.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.2746326446533205,
|
|
"epoch": 1.7430355427473583,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004699847221786335,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.20339891463518142,
|
|
"num_tokens": 41577515.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.213727331161499,
|
|
"epoch": 1.7435158501440924,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004699676122293403,
|
|
"loss": 4.9657,
|
|
"mean_token_accuracy": 0.21493878215551376,
|
|
"num_tokens": 41588589.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.339514684677124,
|
|
"epoch": 1.7439961575408263,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004699504977534782,
|
|
"loss": 5.1172,
|
|
"mean_token_accuracy": 0.20244111567735673,
|
|
"num_tokens": 41600727.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.328644561767578,
|
|
"epoch": 1.7444764649375601,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004699333787514444,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.21113107949495316,
|
|
"num_tokens": 41612177.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.314232969284058,
|
|
"epoch": 1.744956772334294,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004699162552236363,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.2121845602989197,
|
|
"num_tokens": 41623749.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.356080818176269,
|
|
"epoch": 1.745437079731028,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046989912717045165,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.20939796268939972,
|
|
"num_tokens": 41635549.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.308680677413941,
|
|
"epoch": 1.7459173871277618,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046988199459228793,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.2075299382209778,
|
|
"num_tokens": 41647219.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.39847731590271,
|
|
"epoch": 1.7463976945244957,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004698648574895429,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.2058700680732727,
|
|
"num_tokens": 41658850.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.390297555923462,
|
|
"epoch": 1.7468780019212296,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046984771586261465,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.2029770791530609,
|
|
"num_tokens": 41669304.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.325394201278686,
|
|
"epoch": 1.7473583093179634,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000469830569711901,
|
|
"loss": 5.1275,
|
|
"mean_token_accuracy": 0.21497109085321425,
|
|
"num_tokens": 41681652.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.339619731903076,
|
|
"epoch": 1.7478386167146973,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004698134190377999,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.2000415712594986,
|
|
"num_tokens": 41692548.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.283330011367798,
|
|
"epoch": 1.7483189241114312,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046979626384070983,
|
|
"loss": 5.0276,
|
|
"mean_token_accuracy": 0.20697579085826873,
|
|
"num_tokens": 41704528.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.290766811370849,
|
|
"epoch": 1.748799231508165,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000469779104121029,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.21106507927179335,
|
|
"num_tokens": 41717314.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.397818374633789,
|
|
"epoch": 1.7492795389048992,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046976193987915553,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.20856433510780334,
|
|
"num_tokens": 41729193.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.3164609432220455,
|
|
"epoch": 1.749759846301633,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004697447711154883,
|
|
"loss": 4.9993,
|
|
"mean_token_accuracy": 0.21473176628351212,
|
|
"num_tokens": 41741208.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.271097135543823,
|
|
"epoch": 1.750240153698367,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046972759783042576,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.21172467470169068,
|
|
"num_tokens": 41752792.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.329588556289673,
|
|
"epoch": 1.7507204610951008,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004697104200243666,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.21389222741127015,
|
|
"num_tokens": 41763629.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.212681531906128,
|
|
"epoch": 1.751200768491835,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004696932376977096,
|
|
"loss": 4.9839,
|
|
"mean_token_accuracy": 0.21984031796455383,
|
|
"num_tokens": 41774502.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.2775777816772464,
|
|
"epoch": 1.7516810758885688,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004696760508508538,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.20408624410629272,
|
|
"num_tokens": 41785700.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.24399766921997,
|
|
"epoch": 1.7521613832853027,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046965885948419814,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.20771894007921218,
|
|
"num_tokens": 41797347.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.251304769515992,
|
|
"epoch": 1.7526416906820366,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004696416635981418,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.20964408218860625,
|
|
"num_tokens": 41810866.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.337221956253051,
|
|
"epoch": 1.7531219980787704,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000469624463193084,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.2092787966132164,
|
|
"num_tokens": 41821786.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.3241219997406,
|
|
"epoch": 1.7536023054755043,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000469607258269424,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.20477483570575714,
|
|
"num_tokens": 41833591.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.2503228187561035,
|
|
"epoch": 1.7540826128722382,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004695900488275614,
|
|
"loss": 4.9761,
|
|
"mean_token_accuracy": 0.21733361780643462,
|
|
"num_tokens": 41844659.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.262905025482178,
|
|
"epoch": 1.754562920268972,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004695728348678957,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.21085489988327027,
|
|
"num_tokens": 41856378.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.25796685218811,
|
|
"epoch": 1.755043227665706,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004695556163908265,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.20598994195461273,
|
|
"num_tokens": 41867624.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.306719350814819,
|
|
"epoch": 1.7555235350624399,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004695383933967536,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.21959179490804673,
|
|
"num_tokens": 41879250.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.2858093738555905,
|
|
"epoch": 1.7560038424591737,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046952116588607694,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.20796082466840743,
|
|
"num_tokens": 41890713.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.346621751785278,
|
|
"epoch": 1.7564841498559076,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004695039338591963,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.20969011038541793,
|
|
"num_tokens": 41902924.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.3813560009002686,
|
|
"epoch": 1.7569644572526417,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000469486697316512,
|
|
"loss": 5.0921,
|
|
"mean_token_accuracy": 0.21072899103164672,
|
|
"num_tokens": 41914498.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.27591462135315,
|
|
"epoch": 1.7574447646493756,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000469469456258424,
|
|
"loss": 5.008,
|
|
"mean_token_accuracy": 0.21331811547279358,
|
|
"num_tokens": 41925258.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.235059499740601,
|
|
"epoch": 1.7579250720461095,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004694522106853327,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.20887383669614792,
|
|
"num_tokens": 41938176.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.301186037063599,
|
|
"epoch": 1.7584053794428436,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046943496059763845,
|
|
"loss": 4.9204,
|
|
"mean_token_accuracy": 0.21976470649242402,
|
|
"num_tokens": 41949160.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.30994815826416,
|
|
"epoch": 1.7588856868395775,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046941770599574176,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.20536702424287795,
|
|
"num_tokens": 41960981.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.2084917545318605,
|
|
"epoch": 1.7593659942363113,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004694004468800433,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.20575557351112367,
|
|
"num_tokens": 41971755.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.269831800460816,
|
|
"epoch": 1.7598463016330452,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004693831832509437,
|
|
"loss": 5.0195,
|
|
"mean_token_accuracy": 0.21528498381376265,
|
|
"num_tokens": 41984337.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.289263582229614,
|
|
"epoch": 1.760326609029779,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046936591510884375,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.21349796205759047,
|
|
"num_tokens": 41995648.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.227924633026123,
|
|
"epoch": 1.760806916426513,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046934864245414443,
|
|
"loss": 4.9847,
|
|
"mean_token_accuracy": 0.21549142450094222,
|
|
"num_tokens": 42006995.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.328451776504517,
|
|
"epoch": 1.7612872238232469,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046933136528724676,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.20300369262695311,
|
|
"num_tokens": 42020074.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.2883837699890135,
|
|
"epoch": 1.7617675312199808,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004693140836085518,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.21964470148086548,
|
|
"num_tokens": 42032053.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.222679328918457,
|
|
"epoch": 1.7622478386167146,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046929679741846076,
|
|
"loss": 4.992,
|
|
"mean_token_accuracy": 0.2165501594543457,
|
|
"num_tokens": 42042223.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.241136789321899,
|
|
"epoch": 1.7627281460134485,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046927950671737505,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.22104030400514602,
|
|
"num_tokens": 42053988.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.209686994552612,
|
|
"epoch": 1.7632084534101824,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046926221150569617,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.22487284988164902,
|
|
"num_tokens": 42064451.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.303736448287964,
|
|
"epoch": 1.7636887608069163,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004692449117838255,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.20346187353134154,
|
|
"num_tokens": 42076503.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.322427892684937,
|
|
"epoch": 1.7641690682036504,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004692276075521648,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.20268558114767074,
|
|
"num_tokens": 42088341.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.2834454536437985,
|
|
"epoch": 1.7646493756003843,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004692102988111158,
|
|
"loss": 5.0044,
|
|
"mean_token_accuracy": 0.21396459341049195,
|
|
"num_tokens": 42099862.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.330893611907959,
|
|
"epoch": 1.7651296829971181,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046919298556108023,
|
|
"loss": 5.1304,
|
|
"mean_token_accuracy": 0.2064095452427864,
|
|
"num_tokens": 42112117.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.3361430168151855,
|
|
"epoch": 1.765609990393852,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046917566780246036,
|
|
"loss": 5.0456,
|
|
"mean_token_accuracy": 0.20987981408834458,
|
|
"num_tokens": 42123093.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.319780969619751,
|
|
"epoch": 1.7660902977905861,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046915834553565793,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.20977818369865417,
|
|
"num_tokens": 42135266.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.423206043243408,
|
|
"epoch": 1.76657060518732,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004691410187610753,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.20398397147655487,
|
|
"num_tokens": 42145743.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.266022348403931,
|
|
"epoch": 1.767050912584054,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00046912368747911465,
|
|
"loss": 4.9603,
|
|
"mean_token_accuracy": 0.21562689393758774,
|
|
"num_tokens": 42157604.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.246299409866333,
|
|
"epoch": 1.7675312199807878,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046910635169017845,
|
|
"loss": 4.9848,
|
|
"mean_token_accuracy": 0.21592072248458863,
|
|
"num_tokens": 42168738.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.327320861816406,
|
|
"epoch": 1.7680115273775217,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004690890113946691,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.2032323122024536,
|
|
"num_tokens": 42179699.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.290639781951905,
|
|
"epoch": 1.7684918347742555,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004690716665929893,
|
|
"loss": 5.0349,
|
|
"mean_token_accuracy": 0.20555274188518524,
|
|
"num_tokens": 42190512.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.353878450393677,
|
|
"epoch": 1.7689721421709894,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046905431728554164,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.20623240172863005,
|
|
"num_tokens": 42200996.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.237537574768067,
|
|
"epoch": 1.7694524495677233,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00046903696347272894,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.2195417433977127,
|
|
"num_tokens": 42213032.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.268774747848511,
|
|
"epoch": 1.7699327569644572,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046901960515495413,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.20236818641424179,
|
|
"num_tokens": 42224366.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.246276473999023,
|
|
"epoch": 1.770413064361191,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004690022423326202,
|
|
"loss": 4.9426,
|
|
"mean_token_accuracy": 0.22171082496643066,
|
|
"num_tokens": 42235540.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.227318954467774,
|
|
"epoch": 1.770893371757925,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004689848750061303,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.21774039268493653,
|
|
"num_tokens": 42246755.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.2519713878631595,
|
|
"epoch": 1.7713736791546588,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004689675031758876,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.2086520954966545,
|
|
"num_tokens": 42259536.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.265620326995849,
|
|
"epoch": 1.771853986551393,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004689501268422954,
|
|
"loss": 5.0018,
|
|
"mean_token_accuracy": 0.21309262961149217,
|
|
"num_tokens": 42270813.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.4291352272033695,
|
|
"epoch": 1.7723342939481268,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046893274600575725,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.20688621699810028,
|
|
"num_tokens": 42281953.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.3555103778839115,
|
|
"epoch": 1.7728146013448607,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004689153606666765,
|
|
"loss": 5.1671,
|
|
"mean_token_accuracy": 0.20102828592061997,
|
|
"num_tokens": 42294041.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.3062074184417725,
|
|
"epoch": 1.7732949087415946,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000468897970825457,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.21212381571531297,
|
|
"num_tokens": 42305812.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.242274236679077,
|
|
"epoch": 1.7737752161383287,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046888057648250233,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.21752597093582154,
|
|
"num_tokens": 42317585.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.289505672454834,
|
|
"epoch": 1.7742555235350626,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004688631776382164,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.20872523933649062,
|
|
"num_tokens": 42328723.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.298673343658447,
|
|
"epoch": 1.7747358309317964,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046884577429300305,
|
|
"loss": 5.0315,
|
|
"mean_token_accuracy": 0.21802302896976472,
|
|
"num_tokens": 42340741.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.337715339660645,
|
|
"epoch": 1.7752161383285303,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004688283664472665,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.21372077763080596,
|
|
"num_tokens": 42351504.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.298803091049194,
|
|
"epoch": 1.7756964457252642,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046881095410141084,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.21036599278450013,
|
|
"num_tokens": 42362920.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.235004472732544,
|
|
"epoch": 1.776176753121998,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046879353725584036,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.214657324552536,
|
|
"num_tokens": 42374523.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.318952417373657,
|
|
"epoch": 1.776657060518732,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046877611591095923,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.20923085808753966,
|
|
"num_tokens": 42384988.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.188015174865723,
|
|
"epoch": 1.7771373679154658,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046875869006717224,
|
|
"loss": 4.9683,
|
|
"mean_token_accuracy": 0.21809540092945098,
|
|
"num_tokens": 42396503.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.34822187423706,
|
|
"epoch": 1.7776176753121997,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046874125972488375,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.20592930167913437,
|
|
"num_tokens": 42406877.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.2847075939178465,
|
|
"epoch": 1.7780979827089336,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046872382488449853,
|
|
"loss": 5.0045,
|
|
"mean_token_accuracy": 0.21339936852455138,
|
|
"num_tokens": 42418010.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.278915119171143,
|
|
"epoch": 1.7785782901056675,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046870638554642133,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.21521574556827544,
|
|
"num_tokens": 42429056.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.1981254577636715,
|
|
"epoch": 1.7790585975024016,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046868894171105704,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.2182863846421242,
|
|
"num_tokens": 42442294.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.312037134170533,
|
|
"epoch": 1.7795389048991355,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004686714933788107,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.20568554252386093,
|
|
"num_tokens": 42454064.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.262416028976441,
|
|
"epoch": 1.7800192122958693,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004686540405500873,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.22254208624362945,
|
|
"num_tokens": 42465289.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.196308517456055,
|
|
"epoch": 1.7804995196926032,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004686365832252922,
|
|
"loss": 4.9558,
|
|
"mean_token_accuracy": 0.21787980943918228,
|
|
"num_tokens": 42476662.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.272400331497193,
|
|
"epoch": 1.7809798270893373,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046861912140483056,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.20990404039621352,
|
|
"num_tokens": 42486893.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.25569486618042,
|
|
"epoch": 1.7814601344860712,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046860165508910787,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.2137012392282486,
|
|
"num_tokens": 42498202.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.20408935546875,
|
|
"epoch": 1.781940441882805,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004685841842785296,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.22130123376846314,
|
|
"num_tokens": 42509378.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.278441333770752,
|
|
"epoch": 1.782420749279539,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004685667089735014,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.2135585516691208,
|
|
"num_tokens": 42519955.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.339098310470581,
|
|
"epoch": 1.7829010566762729,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046854922917442907,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.2042855978012085,
|
|
"num_tokens": 42531896.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.287368059158325,
|
|
"epoch": 1.7833813640730067,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004685317448817182,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.2154393747448921,
|
|
"num_tokens": 42542123.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.265484142303467,
|
|
"epoch": 1.7838616714697406,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004685142560957751,
|
|
"loss": 5.0267,
|
|
"mean_token_accuracy": 0.20920644849538803,
|
|
"num_tokens": 42554034.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.213453340530395,
|
|
"epoch": 1.7843419788664745,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004684967628170054,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.2161969870328903,
|
|
"num_tokens": 42564532.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.252641820907593,
|
|
"epoch": 1.7848222862632084,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046847926504581553,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.20888954699039458,
|
|
"num_tokens": 42576864.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.220727872848511,
|
|
"epoch": 1.7853025936599423,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004684617627826116,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.21723691672086715,
|
|
"num_tokens": 42588571.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.28783655166626,
|
|
"epoch": 1.7857829010566761,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004684442560278001,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.20396023243665695,
|
|
"num_tokens": 42600912.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.3420875549316404,
|
|
"epoch": 1.78626320845341,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046842674478178727,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.21310542821884154,
|
|
"num_tokens": 42612929.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.271707010269165,
|
|
"epoch": 1.7867435158501441,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004684092290449798,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.21643836200237274,
|
|
"num_tokens": 42623688.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.30314040184021,
|
|
"epoch": 1.787223823246878,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004683917088177844,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.20017116963863374,
|
|
"num_tokens": 42635773.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.335175085067749,
|
|
"epoch": 1.7877041306436119,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004683741841006077,
|
|
"loss": 5.0116,
|
|
"mean_token_accuracy": 0.2126285418868065,
|
|
"num_tokens": 42647210.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.302445983886718,
|
|
"epoch": 1.7881844380403458,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004683566548938567,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.2100044533610344,
|
|
"num_tokens": 42658029.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.244175386428833,
|
|
"epoch": 1.7886647454370799,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004683391211979383,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.2126620218157768,
|
|
"num_tokens": 42669327.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.318448734283447,
|
|
"epoch": 1.7891450528338138,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004683215830132597,
|
|
"loss": 4.978,
|
|
"mean_token_accuracy": 0.21849014163017272,
|
|
"num_tokens": 42679794.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.2540802478790285,
|
|
"epoch": 1.7896253602305476,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046830404034022786,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.21587754786014557,
|
|
"num_tokens": 42689838.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.244184827804565,
|
|
"epoch": 1.7901056676272815,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004682864931792502,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.2088169500231743,
|
|
"num_tokens": 42700935.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.3687248706817625,
|
|
"epoch": 1.7905859750240154,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004682689415307342,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.2058991253376007,
|
|
"num_tokens": 42712533.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.323299503326416,
|
|
"epoch": 1.7910662824207493,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004682513853950872,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.2164225161075592,
|
|
"num_tokens": 42723604.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.295904636383057,
|
|
"epoch": 1.7915465898174832,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000468233824772717,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.21704533249139785,
|
|
"num_tokens": 42735957.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.31956639289856,
|
|
"epoch": 1.792026897214217,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000468216259664031,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.20795589536428452,
|
|
"num_tokens": 42747287.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.25225305557251,
|
|
"epoch": 1.792507204610951,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046819869006943727,
|
|
"loss": 5.0214,
|
|
"mean_token_accuracy": 0.21288145780563356,
|
|
"num_tokens": 42759270.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.2126421451568605,
|
|
"epoch": 1.7929875120076848,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004681811159893436,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.21643001288175584,
|
|
"num_tokens": 42771955.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.379230213165283,
|
|
"epoch": 1.7934678194044187,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046816353742415814,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.20377400517463684,
|
|
"num_tokens": 42784610.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.329622888565064,
|
|
"epoch": 1.7939481268011528,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046814595437428885,
|
|
"loss": 5.0131,
|
|
"mean_token_accuracy": 0.21334183663129808,
|
|
"num_tokens": 42795221.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.202362680435181,
|
|
"epoch": 1.7944284341978867,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000468128366840144,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.2136797621846199,
|
|
"num_tokens": 42807475.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.285220813751221,
|
|
"epoch": 1.7949087415946205,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000468110774822132,
|
|
"loss": 5.0247,
|
|
"mean_token_accuracy": 0.2099965825676918,
|
|
"num_tokens": 42819193.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.358534240722657,
|
|
"epoch": 1.7953890489913544,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004680931783206612,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.20857750475406647,
|
|
"num_tokens": 42831267.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.341310977935791,
|
|
"epoch": 1.7958693563880885,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046807557733614014,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.21137182265520096,
|
|
"num_tokens": 42843066.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.23621973991394,
|
|
"epoch": 1.7963496637848224,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046805797186897757,
|
|
"loss": 4.9839,
|
|
"mean_token_accuracy": 0.21609312891960145,
|
|
"num_tokens": 42854630.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.344387006759644,
|
|
"epoch": 1.7968299711815563,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046804036191958206,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.20598830431699752,
|
|
"num_tokens": 42865986.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.385649871826172,
|
|
"epoch": 1.7973102785782902,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046802274748836267,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.2113535687327385,
|
|
"num_tokens": 42877533.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.264233493804932,
|
|
"epoch": 1.797790585975024,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004680051285757281,
|
|
"loss": 4.9622,
|
|
"mean_token_accuracy": 0.21787598580121995,
|
|
"num_tokens": 42889114.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.339657306671143,
|
|
"epoch": 1.798270893371758,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004679875051820877,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.20209333896636963,
|
|
"num_tokens": 42899483.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.265343427658081,
|
|
"epoch": 1.7987512007684918,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004679698773078503,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.21470368504524232,
|
|
"num_tokens": 42910267.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.229344463348388,
|
|
"epoch": 1.7992315081652257,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046795224495342554,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.21523467749357222,
|
|
"num_tokens": 42922440.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.26675820350647,
|
|
"epoch": 1.7997118155619596,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046793460811922255,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.21941274106502534,
|
|
"num_tokens": 42933967.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.325247478485108,
|
|
"epoch": 1.8001921229586935,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046791696680565075,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.21752756983041763,
|
|
"num_tokens": 42945049.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.357015180587768,
|
|
"epoch": 1.8006724303554273,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046789932101312003,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.209684094786644,
|
|
"num_tokens": 42956062.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.316752099990845,
|
|
"epoch": 1.8011527377521612,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004678816707420397,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.20755847543478012,
|
|
"num_tokens": 42967687.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.374838733673096,
|
|
"epoch": 1.8016330451488953,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004678640159928198,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.2041533976793289,
|
|
"num_tokens": 42979916.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.376203107833862,
|
|
"epoch": 1.8021133525456292,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004678463567658701,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.20571846514940262,
|
|
"num_tokens": 42991639.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.295275259017944,
|
|
"epoch": 1.802593659942363,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004678286930616006,
|
|
"loss": 5.0304,
|
|
"mean_token_accuracy": 0.2202141121029854,
|
|
"num_tokens": 43001843.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.199962472915649,
|
|
"epoch": 1.803073967339097,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004678110248804215,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.20934677869081497,
|
|
"num_tokens": 43013249.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.25519380569458,
|
|
"epoch": 1.803554274735831,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046779335222274293,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.2141787514090538,
|
|
"num_tokens": 43025867.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.354210567474365,
|
|
"epoch": 1.804034582132565,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046777567508897515,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.20677855163812636,
|
|
"num_tokens": 43037530.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.30510630607605,
|
|
"epoch": 1.8045148895292988,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00046775799347952864,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.20953916907310485,
|
|
"num_tokens": 43048675.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.334172582626342,
|
|
"epoch": 1.8049951969260327,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004677403073948139,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.21350647658109664,
|
|
"num_tokens": 43059592.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.204934883117676,
|
|
"epoch": 1.8054755043227666,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004677226168352416,
|
|
"loss": 4.9055,
|
|
"mean_token_accuracy": 0.21881050765514373,
|
|
"num_tokens": 43071755.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.30055422782898,
|
|
"epoch": 1.8059558117195005,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004677049218012223,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.20856136530637742,
|
|
"num_tokens": 43081801.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.28363676071167,
|
|
"epoch": 1.8064361191162344,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000467687222293167,
|
|
"loss": 4.9865,
|
|
"mean_token_accuracy": 0.21563947796821595,
|
|
"num_tokens": 43094160.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.245216512680054,
|
|
"epoch": 1.8069164265129682,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004676695183114866,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.21113639771938325,
|
|
"num_tokens": 43106082.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.289541482925415,
|
|
"epoch": 1.8073967339097021,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000467651809856592,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.21034857034683227,
|
|
"num_tokens": 43117215.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.3805536270141605,
|
|
"epoch": 1.807877041306436,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046763409692889446,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.1985493093729019,
|
|
"num_tokens": 43127858.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.3331808090209964,
|
|
"epoch": 1.8083573487031699,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046761637952880516,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.2098263457417488,
|
|
"num_tokens": 43139952.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.222054100036621,
|
|
"epoch": 1.808837656099904,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046759865765673555,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.21680815070867537,
|
|
"num_tokens": 43150900.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.250592851638794,
|
|
"epoch": 1.8093179634966379,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000467580931313097,
|
|
"loss": 4.9961,
|
|
"mean_token_accuracy": 0.21610429286956787,
|
|
"num_tokens": 43163199.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.26975908279419,
|
|
"epoch": 1.8097982708933718,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046756320049830106,
|
|
"loss": 4.9713,
|
|
"mean_token_accuracy": 0.21149453967809678,
|
|
"num_tokens": 43174147.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.21594090461731,
|
|
"epoch": 1.8102785782901056,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004675454652127594,
|
|
"loss": 4.9574,
|
|
"mean_token_accuracy": 0.2148670420050621,
|
|
"num_tokens": 43186191.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.332516765594482,
|
|
"epoch": 1.8107588856868397,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046752772545688377,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.20392100960016252,
|
|
"num_tokens": 43197541.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.357608366012573,
|
|
"epoch": 1.8112391930835736,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004675099812310861,
|
|
"loss": 5.0393,
|
|
"mean_token_accuracy": 0.2057356894016266,
|
|
"num_tokens": 43208792.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.341261863708496,
|
|
"epoch": 1.8117195004803075,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004674922325357782,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.20795847922563554,
|
|
"num_tokens": 43219914.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.265428829193115,
|
|
"epoch": 1.8121998078770414,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046747447937137235,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.21839789152145386,
|
|
"num_tokens": 43232179.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.284711074829102,
|
|
"epoch": 1.8126801152737753,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046745672173828057,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.20690246820449829,
|
|
"num_tokens": 43243196.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.3317663192749025,
|
|
"epoch": 1.8131604226705091,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004674389596369151,
|
|
"loss": 5.061,
|
|
"mean_token_accuracy": 0.2074489712715149,
|
|
"num_tokens": 43255573.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.269362545013427,
|
|
"epoch": 1.813640730067243,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00046742119306768855,
|
|
"loss": 5.0112,
|
|
"mean_token_accuracy": 0.2068965658545494,
|
|
"num_tokens": 43267679.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.371166372299195,
|
|
"epoch": 1.814121037463977,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004674034220310132,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.20389920175075532,
|
|
"num_tokens": 43278857.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.315099573135376,
|
|
"epoch": 1.8146013448607108,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046738564652730176,
|
|
"loss": 5.0402,
|
|
"mean_token_accuracy": 0.2159240111708641,
|
|
"num_tokens": 43291099.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.344594144821167,
|
|
"epoch": 1.8150816522574447,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004673678665569669,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.20903838574886321,
|
|
"num_tokens": 43302863.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.268089008331299,
|
|
"epoch": 1.8155619596541785,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004673500821204213,
|
|
"loss": 4.993,
|
|
"mean_token_accuracy": 0.2161931425333023,
|
|
"num_tokens": 43314673.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.2688511371612545,
|
|
"epoch": 1.8160422670509124,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000467332293218078,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.2204125016927719,
|
|
"num_tokens": 43325927.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.26735200881958,
|
|
"epoch": 1.8165225744476465,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046731449985035,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.21368924230337144,
|
|
"num_tokens": 43337615.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.318307256698608,
|
|
"epoch": 1.8170028818443804,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00046729670201765036,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20909264981746672,
|
|
"num_tokens": 43349195.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.348115921020508,
|
|
"epoch": 1.8174831892411143,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00046727889972039227,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.2128039926290512,
|
|
"num_tokens": 43361274.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.277438163757324,
|
|
"epoch": 1.8179634966378482,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046726109295898904,
|
|
"loss": 5.0246,
|
|
"mean_token_accuracy": 0.21475251168012618,
|
|
"num_tokens": 43372843.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.289341068267822,
|
|
"epoch": 1.8184438040345823,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004672432817338542,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.21477254182100297,
|
|
"num_tokens": 43383492.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.301332139968872,
|
|
"epoch": 1.8189241114313162,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046722546604540115,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.20793161690235137,
|
|
"num_tokens": 43395669.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.2153009414672855,
|
|
"epoch": 1.81940441882805,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004672076458940436,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.2199820727109909,
|
|
"num_tokens": 43407340.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.245261144638062,
|
|
"epoch": 1.819884726224784,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046718982128019534,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.21321489661931992,
|
|
"num_tokens": 43418607.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.384263229370117,
|
|
"epoch": 1.8203650336215178,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046717199220427003,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.20619122684001923,
|
|
"num_tokens": 43429286.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.248145866394043,
|
|
"epoch": 1.8208453410182517,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046715415866668163,
|
|
"loss": 5.0015,
|
|
"mean_token_accuracy": 0.21345564723014832,
|
|
"num_tokens": 43440794.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.2673125743865965,
|
|
"epoch": 1.8213256484149856,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004671363206678443,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.21078508347272873,
|
|
"num_tokens": 43452184.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.221431255340576,
|
|
"epoch": 1.8218059558117194,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046711847820817215,
|
|
"loss": 5.0174,
|
|
"mean_token_accuracy": 0.21327925324440003,
|
|
"num_tokens": 43463361.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.303540515899658,
|
|
"epoch": 1.8222862632084533,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004671006312880794,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.21002405285835266,
|
|
"num_tokens": 43474802.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.292356014251709,
|
|
"epoch": 1.8227665706051872,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004670827799079805,
|
|
"loss": 4.9953,
|
|
"mean_token_accuracy": 0.21283789873123168,
|
|
"num_tokens": 43486962.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.30965223312378,
|
|
"epoch": 1.823246878001921,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00046706492406828966,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.211692875623703,
|
|
"num_tokens": 43498761.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.277971649169922,
|
|
"epoch": 1.8237271853986552,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004670470637694217,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.21012924909591674,
|
|
"num_tokens": 43511294.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.292625045776367,
|
|
"epoch": 1.824207492795389,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004670291990117912,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.22180955111980438,
|
|
"num_tokens": 43522858.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.327417802810669,
|
|
"epoch": 1.824687800192123,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004670113297958128,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.2080127403140068,
|
|
"num_tokens": 43533453.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.286314535140991,
|
|
"epoch": 1.8251681075888568,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046699345612190155,
|
|
"loss": 4.9852,
|
|
"mean_token_accuracy": 0.21814341247081756,
|
|
"num_tokens": 43543889.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.170576810836792,
|
|
"epoch": 1.825648414985591,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046697557799047233,
|
|
"loss": 4.9515,
|
|
"mean_token_accuracy": 0.22128957360982895,
|
|
"num_tokens": 43554815.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.194893789291382,
|
|
"epoch": 1.8261287223823248,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004669576954019403,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.22137105762958526,
|
|
"num_tokens": 43565258.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.317008399963379,
|
|
"epoch": 1.8266090297790587,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004669398083567205,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.20849737972021104,
|
|
"num_tokens": 43576710.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.291316509246826,
|
|
"epoch": 1.8270893371757926,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004669219168552284,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.20931296944618225,
|
|
"num_tokens": 43587590.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.239701843261718,
|
|
"epoch": 1.8275696445725265,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046690402089787916,
|
|
"loss": 5.0685,
|
|
"mean_token_accuracy": 0.21393070369958878,
|
|
"num_tokens": 43599675.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.217621850967407,
|
|
"epoch": 1.8280499519692603,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004668861204850884,
|
|
"loss": 4.9112,
|
|
"mean_token_accuracy": 0.22566640079021455,
|
|
"num_tokens": 43612369.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.229228782653808,
|
|
"epoch": 1.8285302593659942,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046686821561727176,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.22551157623529433,
|
|
"num_tokens": 43624807.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.240088605880738,
|
|
"epoch": 1.829010566762728,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004668503062948449,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.21810400485992432,
|
|
"num_tokens": 43635389.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.289660787582397,
|
|
"epoch": 1.829490874159462,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004668323925182236,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.21172595620155335,
|
|
"num_tokens": 43646807.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.31950101852417,
|
|
"epoch": 1.8299711815561959,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046681447428782377,
|
|
"loss": 5.0554,
|
|
"mean_token_accuracy": 0.20691585391759873,
|
|
"num_tokens": 43657910.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.241174936294556,
|
|
"epoch": 1.8304514889529298,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004667965516040613,
|
|
"loss": 4.9931,
|
|
"mean_token_accuracy": 0.22097569406032563,
|
|
"num_tokens": 43669376.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.213934659957886,
|
|
"epoch": 1.8309317963496636,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004667786244673526,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.21567879170179366,
|
|
"num_tokens": 43681702.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.331620121002198,
|
|
"epoch": 1.8314121037463977,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046676069287811365,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.21479692310094833,
|
|
"num_tokens": 43694795.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.410304307937622,
|
|
"epoch": 1.8318924111431316,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004667427568367607,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.2122415065765381,
|
|
"num_tokens": 43707197.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.353474140167236,
|
|
"epoch": 1.8323727185398655,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046672481634371047,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.20369820594787597,
|
|
"num_tokens": 43719066.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.2937578678131105,
|
|
"epoch": 1.8328530259365994,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046670687139937925,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.21501201391220093,
|
|
"num_tokens": 43731080.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.311443519592285,
|
|
"epoch": 1.8333333333333335,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004666889220041837,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.21123168468475342,
|
|
"num_tokens": 43743048.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.260170412063599,
|
|
"epoch": 1.8338136407300674,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00046667096815854056,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.2065480977296829,
|
|
"num_tokens": 43754701.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.298238039016724,
|
|
"epoch": 1.8342939481268012,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004666530098628667,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.21224534660577773,
|
|
"num_tokens": 43765696.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.335970115661621,
|
|
"epoch": 1.8347742555235351,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004666350471175791,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.20418452620506286,
|
|
"num_tokens": 43777162.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.310415887832642,
|
|
"epoch": 1.835254562920269,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004666170799230947,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.20815580934286118,
|
|
"num_tokens": 43789340.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.250678586959839,
|
|
"epoch": 1.8357348703170029,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004665991082798307,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.22449758201837539,
|
|
"num_tokens": 43800098.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.291762208938598,
|
|
"epoch": 1.8362151777137368,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004665811321882043,
|
|
"loss": 5.0115,
|
|
"mean_token_accuracy": 0.21538132280111313,
|
|
"num_tokens": 43811403.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.35831298828125,
|
|
"epoch": 1.8366954851104706,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046656315164863297,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.21247103959321975,
|
|
"num_tokens": 43821946.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.203867626190186,
|
|
"epoch": 1.8371757925072045,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046654516666153403,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.21651494652032852,
|
|
"num_tokens": 43832638.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.244303607940674,
|
|
"epoch": 1.8376560999039384,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004665271772273251,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.21210751086473464,
|
|
"num_tokens": 43843616.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.363058376312256,
|
|
"epoch": 1.8381364073006723,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004665091833464239,
|
|
"loss": 5.0054,
|
|
"mean_token_accuracy": 0.2123182535171509,
|
|
"num_tokens": 43854680.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.251821422576905,
|
|
"epoch": 1.8386167146974062,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046649118501924805,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.21571109145879747,
|
|
"num_tokens": 43866683.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.287014532089233,
|
|
"epoch": 1.8390970220941403,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004664731822462154,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.20670593529939651,
|
|
"num_tokens": 43878080.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.367952489852906,
|
|
"epoch": 1.8395773294908742,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046645517502774415,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.21339842975139617,
|
|
"num_tokens": 43888633.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.377101421356201,
|
|
"epoch": 1.840057636887608,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046643716336425224,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.20850269943475724,
|
|
"num_tokens": 43899678.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.275916528701782,
|
|
"epoch": 1.8405379442843421,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004664191472561578,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.2170855864882469,
|
|
"num_tokens": 43910744.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.29974946975708,
|
|
"epoch": 1.841018251681076,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004664011267038792,
|
|
"loss": 5.1067,
|
|
"mean_token_accuracy": 0.21274504363536834,
|
|
"num_tokens": 43922467.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.282487392425537,
|
|
"epoch": 1.84149855907781,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046638310170783476,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.21923004537820817,
|
|
"num_tokens": 43934919.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.334354019165039,
|
|
"epoch": 1.8419788664745438,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000466365072268443,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.21065457165241241,
|
|
"num_tokens": 43947737.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.214226627349854,
|
|
"epoch": 1.8424591738712777,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004663470383861225,
|
|
"loss": 4.9734,
|
|
"mean_token_accuracy": 0.21505632102489472,
|
|
"num_tokens": 43959656.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.2418756008148195,
|
|
"epoch": 1.8429394812680115,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000466329000061292,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.21279378831386567,
|
|
"num_tokens": 43970732.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.315751695632935,
|
|
"epoch": 1.8434197886647454,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004663109572943702,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.2092084750533104,
|
|
"num_tokens": 43982369.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.365240144729614,
|
|
"epoch": 1.8439000960614793,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000466292910085776,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.2108530357480049,
|
|
"num_tokens": 43993751.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.2352635860443115,
|
|
"epoch": 1.8443804034582132,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046627485843592854,
|
|
"loss": 4.9838,
|
|
"mean_token_accuracy": 0.20953248739242553,
|
|
"num_tokens": 44005021.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.24734845161438,
|
|
"epoch": 1.844860710854947,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046625680234524674,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.21830109655857086,
|
|
"num_tokens": 44015571.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.285162925720215,
|
|
"epoch": 1.845341018251681,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046623874181414993,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.21147332340478897,
|
|
"num_tokens": 44026363.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.237609004974365,
|
|
"epoch": 1.8458213256484148,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004662206768430574,
|
|
"loss": 4.9569,
|
|
"mean_token_accuracy": 0.21987491250038146,
|
|
"num_tokens": 44038042.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.295706081390381,
|
|
"epoch": 1.846301633045149,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004662026074323886,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.20177761167287828,
|
|
"num_tokens": 44049086.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.303319215774536,
|
|
"epoch": 1.8467819404418828,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046618453358256303,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.2137199118733406,
|
|
"num_tokens": 44060816.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.18802924156189,
|
|
"epoch": 1.8472622478386167,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046616645529400026,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.2169766440987587,
|
|
"num_tokens": 44071877.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.244649982452392,
|
|
"epoch": 1.8477425552353506,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004661483725671201,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.2118618443608284,
|
|
"num_tokens": 44082618.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.285070610046387,
|
|
"epoch": 1.8482228626320847,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046613028540234226,
|
|
"loss": 4.9725,
|
|
"mean_token_accuracy": 0.21849899739027023,
|
|
"num_tokens": 44093411.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.214768934249878,
|
|
"epoch": 1.8487031700288186,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004661121938000867,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.22752974927425385,
|
|
"num_tokens": 44103595.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.208281755447388,
|
|
"epoch": 1.8491834774255524,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004660940977607736,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.22332675755023956,
|
|
"num_tokens": 44114740.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.2180708885192875,
|
|
"epoch": 1.8496637848222863,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046607599728482285,
|
|
"loss": 4.9495,
|
|
"mean_token_accuracy": 0.22409942895174026,
|
|
"num_tokens": 44125415.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.220376014709473,
|
|
"epoch": 1.8501440922190202,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046605789237265496,
|
|
"loss": 5.0068,
|
|
"mean_token_accuracy": 0.2163587838411331,
|
|
"num_tokens": 44137399.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.227117300033569,
|
|
"epoch": 1.850624399615754,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046603978302469,
|
|
"loss": 4.9237,
|
|
"mean_token_accuracy": 0.21382114738225938,
|
|
"num_tokens": 44148354.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.212729787826538,
|
|
"epoch": 1.851104707012488,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004660216692413486,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.21948872953653337,
|
|
"num_tokens": 44160496.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.2633284568786625,
|
|
"epoch": 1.8515850144092219,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004660035510230513,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.2135166957974434,
|
|
"num_tokens": 44171832.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.300767040252685,
|
|
"epoch": 1.8520653218059557,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004659854283702186,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.21029375046491622,
|
|
"num_tokens": 44182850.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.288577699661255,
|
|
"epoch": 1.8525456292026896,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004659673012832715,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.21106387227773665,
|
|
"num_tokens": 44194343.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.322905445098877,
|
|
"epoch": 1.8530259365994235,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004659491697626306,
|
|
"loss": 5.1259,
|
|
"mean_token_accuracy": 0.20601016730070115,
|
|
"num_tokens": 44206294.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.3181358814239506,
|
|
"epoch": 1.8535062439961574,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046593103380871705,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.21062656342983246,
|
|
"num_tokens": 44218576.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.270628929138184,
|
|
"epoch": 1.8539865513928915,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046591289342195184,
|
|
"loss": 5.0279,
|
|
"mean_token_accuracy": 0.20980951935052872,
|
|
"num_tokens": 44230480.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.235353803634643,
|
|
"epoch": 1.8544668587896254,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004658947486027562,
|
|
"loss": 4.921,
|
|
"mean_token_accuracy": 0.21621815711259842,
|
|
"num_tokens": 44240907.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.309948444366455,
|
|
"epoch": 1.8549471661863592,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046587659935155124,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.2057477906346321,
|
|
"num_tokens": 44251469.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.41249270439148,
|
|
"epoch": 1.8554274735830933,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046585844566875845,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.2095566987991333,
|
|
"num_tokens": 44263875.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.32013463973999,
|
|
"epoch": 1.8559077809798272,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004658402875547993,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.2086760252714157,
|
|
"num_tokens": 44276163.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.2659906387329105,
|
|
"epoch": 1.856388088376561,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046582212501009533,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.21217812448740006,
|
|
"num_tokens": 44287985.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.3223100185394285,
|
|
"epoch": 1.856868395773295,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046580395803506825,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.2092093899846077,
|
|
"num_tokens": 44299360.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.280294752120971,
|
|
"epoch": 1.8573487031700289,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004657857866301399,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.22109387964010238,
|
|
"num_tokens": 44310459.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.39028844833374,
|
|
"epoch": 1.8578290105667628,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00046576761079573204,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.20455761402845382,
|
|
"num_tokens": 44321832.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.3569207191467285,
|
|
"epoch": 1.8583093179634966,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004657494305322667,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.20953987985849382,
|
|
"num_tokens": 44332829.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.3238747119903564,
|
|
"epoch": 1.8587896253602305,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004657312458401661,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.2116164669394493,
|
|
"num_tokens": 44344321.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.382580137252807,
|
|
"epoch": 1.8592699327569644,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004657130567198522,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.2033289387822151,
|
|
"num_tokens": 44357183.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.3526993751525875,
|
|
"epoch": 1.8597502401536983,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046569486317174746,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.2113606885075569,
|
|
"num_tokens": 44367118.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.346012783050537,
|
|
"epoch": 1.8602305475504322,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004656766651962742,
|
|
"loss": 5.0925,
|
|
"mean_token_accuracy": 0.21126640886068343,
|
|
"num_tokens": 44377699.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.291727113723755,
|
|
"epoch": 1.860710854947166,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004656584627938551,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.20558258146047592,
|
|
"num_tokens": 44389457.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.238782072067261,
|
|
"epoch": 1.8611911623439001,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046564025596491254,
|
|
"loss": 4.9537,
|
|
"mean_token_accuracy": 0.21766353398561478,
|
|
"num_tokens": 44400140.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.2655538558959964,
|
|
"epoch": 1.861671469740634,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004656220447098693,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.22367118746042253,
|
|
"num_tokens": 44411088.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.288393354415893,
|
|
"epoch": 1.862151777137368,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004656038290291483,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.21385680735111237,
|
|
"num_tokens": 44422515.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.213572978973389,
|
|
"epoch": 1.8626320845341018,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004655856089231723,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.2174661710858345,
|
|
"num_tokens": 44433711.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.329999113082886,
|
|
"epoch": 1.8631123919308359,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004655673843923644,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.21358466595411302,
|
|
"num_tokens": 44446157.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.3997903823852536,
|
|
"epoch": 1.8635926993275698,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004655491554371477,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.20192237347364425,
|
|
"num_tokens": 44457506.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.311753797531128,
|
|
"epoch": 1.8640730067243036,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046553092205794543,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.200942662358284,
|
|
"num_tokens": 44469572.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.3078405380249025,
|
|
"epoch": 1.8645533141210375,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046551268425518096,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.2128366455435753,
|
|
"num_tokens": 44481932.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.288011884689331,
|
|
"epoch": 1.8650336215177714,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004654944420292776,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.21143432706594467,
|
|
"num_tokens": 44493081.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.328649282455444,
|
|
"epoch": 1.8655139289145053,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000465476195380659,
|
|
"loss": 5.0276,
|
|
"mean_token_accuracy": 0.21368955671787263,
|
|
"num_tokens": 44503919.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.275989580154419,
|
|
"epoch": 1.8659942363112392,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004654579443097487,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.2178771361708641,
|
|
"num_tokens": 44515493.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.35762300491333,
|
|
"epoch": 1.866474543707973,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004654396888169705,
|
|
"loss": 5.0635,
|
|
"mean_token_accuracy": 0.20458602011203766,
|
|
"num_tokens": 44527432.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.306378555297852,
|
|
"epoch": 1.866954851104707,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046542142890274816,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.21261765956878662,
|
|
"num_tokens": 44537634.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.258159351348877,
|
|
"epoch": 1.8674351585014408,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004654031645675057,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.210937063395977,
|
|
"num_tokens": 44549856.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.24801344871521,
|
|
"epoch": 1.8679154658981747,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004653848958116672,
|
|
"loss": 4.9828,
|
|
"mean_token_accuracy": 0.21108436733484268,
|
|
"num_tokens": 44563214.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.252404975891113,
|
|
"epoch": 1.8683957732949086,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046536662263565667,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.2040380761027336,
|
|
"num_tokens": 44572982.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.289970541000367,
|
|
"epoch": 1.8688760806916427,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004653483450398985,
|
|
"loss": 4.9546,
|
|
"mean_token_accuracy": 0.2206380233168602,
|
|
"num_tokens": 44583664.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.234703636169433,
|
|
"epoch": 1.8693563880883766,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046533006302481694,
|
|
"loss": 4.875,
|
|
"mean_token_accuracy": 0.22452741414308547,
|
|
"num_tokens": 44594987.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.245051097869873,
|
|
"epoch": 1.8698366954851104,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004653117765908365,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.21386986523866652,
|
|
"num_tokens": 44607123.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.276066160202026,
|
|
"epoch": 1.8703170028818443,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004652934857383816,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.21181312650442125,
|
|
"num_tokens": 44618736.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.232456636428833,
|
|
"epoch": 1.8707973102785784,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004652751904678772,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.22400026619434357,
|
|
"num_tokens": 44630681.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.273044061660767,
|
|
"epoch": 1.8712776176753123,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046525689077974775,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.2172794371843338,
|
|
"num_tokens": 44641641.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.269042682647705,
|
|
"epoch": 1.8717579250720462,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046523858667441834,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.21485141813755035,
|
|
"num_tokens": 44652489.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.276655197143555,
|
|
"epoch": 1.87223823246878,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004652202781523138,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.21070256382226943,
|
|
"num_tokens": 44665659.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.309630441665649,
|
|
"epoch": 1.872718539865514,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004652019652138592,
|
|
"loss": 4.9734,
|
|
"mean_token_accuracy": 0.2207336023449898,
|
|
"num_tokens": 44677300.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.270104837417603,
|
|
"epoch": 1.8731988472622478,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004651836478594798,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.2061604827642441,
|
|
"num_tokens": 44690084.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.26462607383728,
|
|
"epoch": 1.8736791546589817,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004651653260896008,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.22041265964508056,
|
|
"num_tokens": 44701208.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.387423086166382,
|
|
"epoch": 1.8741594620557156,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046514699990464763,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.2044372022151947,
|
|
"num_tokens": 44713546.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.493787384033203,
|
|
"epoch": 1.8746397694524495,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004651286693050458,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.1938343808054924,
|
|
"num_tokens": 44724802.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.269013166427612,
|
|
"epoch": 1.8751200768491834,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004651103342912207,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.21562180370092393,
|
|
"num_tokens": 44736625.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.228459119796753,
|
|
"epoch": 1.8756003842459172,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046509199486359824,
|
|
"loss": 4.9907,
|
|
"mean_token_accuracy": 0.20765036940574647,
|
|
"num_tokens": 44750451.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.249907398223877,
|
|
"epoch": 1.8760806916426513,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046507365102260403,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.21662263721227645,
|
|
"num_tokens": 44762043.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.329118442535401,
|
|
"epoch": 1.8765609990393852,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046505530276866417,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.20628708004951476,
|
|
"num_tokens": 44774329.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.356129550933838,
|
|
"epoch": 1.877041306436119,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046503695010220443,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.21316770762205123,
|
|
"num_tokens": 44786352.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.232901334762573,
|
|
"epoch": 1.877521613832853,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000465018593023651,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.2236788883805275,
|
|
"num_tokens": 44796829.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.31919641494751,
|
|
"epoch": 1.878001921229587,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004650002315334302,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.20649721324443818,
|
|
"num_tokens": 44808900.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.237712049484253,
|
|
"epoch": 1.878482228626321,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000464981865631968,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.21684545576572417,
|
|
"num_tokens": 44820638.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.2202623844146725,
|
|
"epoch": 1.8789625360230549,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004649634953196912,
|
|
"loss": 4.9853,
|
|
"mean_token_accuracy": 0.21510301381349564,
|
|
"num_tokens": 44833370.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.249262046813965,
|
|
"epoch": 1.8794428434197887,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046494512059702605,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.20902179181575775,
|
|
"num_tokens": 44844291.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.292049312591553,
|
|
"epoch": 1.8799231508165226,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004649267414643992,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.22034831643104552,
|
|
"num_tokens": 44855303.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.214948654174805,
|
|
"epoch": 1.8804034582132565,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004649083579222374,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.2198813810944557,
|
|
"num_tokens": 44866593.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.232288980484009,
|
|
"epoch": 1.8808837656099904,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046488996997096744,
|
|
"loss": 5.0022,
|
|
"mean_token_accuracy": 0.2162306621670723,
|
|
"num_tokens": 44879124.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.26952018737793,
|
|
"epoch": 1.8813640730067243,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004648715776110162,
|
|
"loss": 4.962,
|
|
"mean_token_accuracy": 0.22770543545484542,
|
|
"num_tokens": 44889942.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.2399139404296875,
|
|
"epoch": 1.8818443804034581,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004648531808428108,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.22301126569509505,
|
|
"num_tokens": 44901002.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.3148565769195555,
|
|
"epoch": 1.882324687800192,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004648347796667782,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.20749584436416627,
|
|
"num_tokens": 44913495.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.2737291812896725,
|
|
"epoch": 1.882804995196926,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004648163740833458,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.21020472198724746,
|
|
"num_tokens": 44924624.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.313634872436523,
|
|
"epoch": 1.8832853025936598,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046479796409294076,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.21518365144729615,
|
|
"num_tokens": 44935539.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.2407920360565186,
|
|
"epoch": 1.8837656099903939,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004647795496959907,
|
|
"loss": 4.9676,
|
|
"mean_token_accuracy": 0.22084807455539704,
|
|
"num_tokens": 44945979.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.250488758087158,
|
|
"epoch": 1.8842459173871278,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046476113089292286,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.2077271655201912,
|
|
"num_tokens": 44958294.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.362096452713013,
|
|
"epoch": 1.8847262247838616,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004647427076841651,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.20957524329423904,
|
|
"num_tokens": 44970261.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.32420163154602,
|
|
"epoch": 1.8852065321805955,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046472428007014515,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.21345267295837403,
|
|
"num_tokens": 44981515.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.22032675743103,
|
|
"epoch": 1.8856868395773296,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004647058480512907,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.21882299035787584,
|
|
"num_tokens": 44992473.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.35247950553894,
|
|
"epoch": 1.8861671469740635,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046468741162802987,
|
|
"loss": 5.0963,
|
|
"mean_token_accuracy": 0.20549307465553285,
|
|
"num_tokens": 45004264.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.269802570343018,
|
|
"epoch": 1.8866474543707974,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004646689708007905,
|
|
"loss": 4.9447,
|
|
"mean_token_accuracy": 0.22094198018312455,
|
|
"num_tokens": 45015601.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.344634342193603,
|
|
"epoch": 1.8871277617675313,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046465052557000087,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.21282566636800765,
|
|
"num_tokens": 45028044.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.337531805038452,
|
|
"epoch": 1.8876080691642652,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046463207593608916,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.21318864375352858,
|
|
"num_tokens": 45040144.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.368450593948364,
|
|
"epoch": 1.888088376560999,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004646136218994837,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.19907456934452056,
|
|
"num_tokens": 45051844.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.342854738235474,
|
|
"epoch": 1.888568683957733,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046459516346061304,
|
|
"loss": 5.0907,
|
|
"mean_token_accuracy": 0.210019987821579,
|
|
"num_tokens": 45062684.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.264765739440918,
|
|
"epoch": 1.8890489913544668,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046457670061990564,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.21809170693159102,
|
|
"num_tokens": 45073327.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.259234857559204,
|
|
"epoch": 1.8895292987512007,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046455823337779024,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.2089684545993805,
|
|
"num_tokens": 45085309.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.435636949539185,
|
|
"epoch": 1.8900096061479346,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004645397617346954,
|
|
"loss": 5.0866,
|
|
"mean_token_accuracy": 0.2088565081357956,
|
|
"num_tokens": 45095934.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.283352375030518,
|
|
"epoch": 1.8904899135446684,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004645212856910502,
|
|
"loss": 4.9931,
|
|
"mean_token_accuracy": 0.22000974118709565,
|
|
"num_tokens": 45106220.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.20910005569458,
|
|
"epoch": 1.8909702209414025,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004645028052472835,
|
|
"loss": 4.9719,
|
|
"mean_token_accuracy": 0.2118960812687874,
|
|
"num_tokens": 45117861.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.251631402969361,
|
|
"epoch": 1.8914505283381364,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046448432040382444,
|
|
"loss": 4.9782,
|
|
"mean_token_accuracy": 0.21902803480625152,
|
|
"num_tokens": 45129248.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.335808372497558,
|
|
"epoch": 1.8919308357348703,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000464465831161102,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.20699119120836257,
|
|
"num_tokens": 45140610.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.27377290725708,
|
|
"epoch": 1.8924111431316042,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004644473375195456,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.21669483929872513,
|
|
"num_tokens": 45150697.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.303275871276855,
|
|
"epoch": 1.8928914505283383,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046442883947958466,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.21175060272216797,
|
|
"num_tokens": 45162627.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.186190986633301,
|
|
"epoch": 1.8933717579250722,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046441033704164845,
|
|
"loss": 4.815,
|
|
"mean_token_accuracy": 0.23236378133296967,
|
|
"num_tokens": 45173030.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.271634101867676,
|
|
"epoch": 1.893852065321806,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004643918302061666,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.21142958104610443,
|
|
"num_tokens": 45183588.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.308107948303222,
|
|
"epoch": 1.89433237271854,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004643733189735689,
|
|
"loss": 5.0261,
|
|
"mean_token_accuracy": 0.2083171308040619,
|
|
"num_tokens": 45195289.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.313886499404907,
|
|
"epoch": 1.8948126801152738,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000464354803344285,
|
|
"loss": 5.0006,
|
|
"mean_token_accuracy": 0.21571817398071289,
|
|
"num_tokens": 45207001.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.222890424728393,
|
|
"epoch": 1.8952929875120077,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046433628331874496,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.2150554597377777,
|
|
"num_tokens": 45217447.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.290614080429077,
|
|
"epoch": 1.8957732949087416,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004643177588973785,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.21388696730136872,
|
|
"num_tokens": 45227588.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.282289457321167,
|
|
"epoch": 1.8962536023054755,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004642992300806159,
|
|
"loss": 5.016,
|
|
"mean_token_accuracy": 0.2184993401169777,
|
|
"num_tokens": 45239969.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.298550462722778,
|
|
"epoch": 1.8967339097022093,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004642806968688873,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.2119063526391983,
|
|
"num_tokens": 45250877.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.340607452392578,
|
|
"epoch": 1.8972142170989432,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046426215926262295,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.21566742062568664,
|
|
"num_tokens": 45262846.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.209905576705933,
|
|
"epoch": 1.897694524495677,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004642436172622532,
|
|
"loss": 4.979,
|
|
"mean_token_accuracy": 0.21812470108270646,
|
|
"num_tokens": 45274198.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.2204046726226805,
|
|
"epoch": 1.898174831892411,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004642250708682086,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.21467911899089814,
|
|
"num_tokens": 45285803.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.369857549667358,
|
|
"epoch": 1.898655139289145,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046420652008091984,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.2124742791056633,
|
|
"num_tokens": 45298242.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.2806648254394535,
|
|
"epoch": 1.899135446685879,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004641879649008174,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.21825421899557113,
|
|
"num_tokens": 45309567.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.328894376754761,
|
|
"epoch": 1.8996157540826129,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004641694053283323,
|
|
"loss": 5.0973,
|
|
"mean_token_accuracy": 0.2127980574965477,
|
|
"num_tokens": 45321693.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.350430536270141,
|
|
"epoch": 1.9000960614793467,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046415084136389525,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.20960698127746583,
|
|
"num_tokens": 45333094.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.23296275138855,
|
|
"epoch": 1.9005763688760808,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004641322730079374,
|
|
"loss": 4.9774,
|
|
"mean_token_accuracy": 0.21763262003660203,
|
|
"num_tokens": 45344549.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.305110216140747,
|
|
"epoch": 1.9010566762728147,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004641137002608897,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.2089278593659401,
|
|
"num_tokens": 45356433.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.309568929672241,
|
|
"epoch": 1.9015369836695486,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046409512312318345,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.21319393664598466,
|
|
"num_tokens": 45368224.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.191646242141724,
|
|
"epoch": 1.9020172910662825,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046407654159524994,
|
|
"loss": 4.9416,
|
|
"mean_token_accuracy": 0.21909800320863723,
|
|
"num_tokens": 45379673.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.372690010070801,
|
|
"epoch": 1.9024975984630164,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046405795567752055,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.20601453334093095,
|
|
"num_tokens": 45391613.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.327785778045654,
|
|
"epoch": 1.9029779058597502,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00046403936537042686,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.21072492152452468,
|
|
"num_tokens": 45403693.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.280022001266479,
|
|
"epoch": 1.9034582132564841,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046402077067440043,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.21396971493959427,
|
|
"num_tokens": 45416151.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.337584161758423,
|
|
"epoch": 1.903938520653218,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046400217158987293,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.2099314421415329,
|
|
"num_tokens": 45428276.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.255852174758911,
|
|
"epoch": 1.9044188280499519,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046398356811727626,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.21713652163743974,
|
|
"num_tokens": 45439877.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.307520818710327,
|
|
"epoch": 1.9048991354466858,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004639649602570423,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.21774634569883347,
|
|
"num_tokens": 45451459.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.178621530532837,
|
|
"epoch": 1.9053794428434196,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046394634800960314,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.21638017147779465,
|
|
"num_tokens": 45463341.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.299449634552002,
|
|
"epoch": 1.9058597502401537,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046392773137539074,
|
|
"loss": 5.017,
|
|
"mean_token_accuracy": 0.21333562284708024,
|
|
"num_tokens": 45475585.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.315364789962769,
|
|
"epoch": 1.9063400576368876,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00046390911035483744,
|
|
"loss": 5.0085,
|
|
"mean_token_accuracy": 0.21654972285032273,
|
|
"num_tokens": 45487178.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.337924003601074,
|
|
"epoch": 1.9068203650336215,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004638904849483756,
|
|
"loss": 5.0806,
|
|
"mean_token_accuracy": 0.2103333979845047,
|
|
"num_tokens": 45498832.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.263652229309082,
|
|
"epoch": 1.9073006724303554,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046387185515643756,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.20707266479730607,
|
|
"num_tokens": 45511549.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.285342073440551,
|
|
"epoch": 1.9077809798270895,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004638532209794559,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.21112990826368333,
|
|
"num_tokens": 45523421.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.3521665096282955,
|
|
"epoch": 1.9082612872238234,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004638345824178631,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.21261093467473985,
|
|
"num_tokens": 45535247.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.212268543243408,
|
|
"epoch": 1.9087415946205573,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046381593947209215,
|
|
"loss": 4.8907,
|
|
"mean_token_accuracy": 0.2225550338625908,
|
|
"num_tokens": 45546296.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.255787563323975,
|
|
"epoch": 1.9092219020172911,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004637972921425757,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.21263747066259384,
|
|
"num_tokens": 45557360.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.260379314422607,
|
|
"epoch": 1.909702209414025,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046377864042974675,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.2211372435092926,
|
|
"num_tokens": 45568500.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.314268445968628,
|
|
"epoch": 1.910182516810759,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004637599843340384,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.2052885726094246,
|
|
"num_tokens": 45579513.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.271269369125366,
|
|
"epoch": 1.9106628242074928,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00046374132385588356,
|
|
"loss": 4.9745,
|
|
"mean_token_accuracy": 0.22036373019218444,
|
|
"num_tokens": 45591144.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.294055509567261,
|
|
"epoch": 1.9111431316042267,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046372265899571576,
|
|
"loss": 5.026,
|
|
"mean_token_accuracy": 0.21274459809064866,
|
|
"num_tokens": 45602487.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.336878681182862,
|
|
"epoch": 1.9116234390009605,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046370398975396817,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.20567838847637177,
|
|
"num_tokens": 45614448.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.289744710922241,
|
|
"epoch": 1.9121037463976944,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004636853161310743,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.20937449783086776,
|
|
"num_tokens": 45625660.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.182929468154907,
|
|
"epoch": 1.9125840537944283,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046366663812746764,
|
|
"loss": 4.922,
|
|
"mean_token_accuracy": 0.2227497309446335,
|
|
"num_tokens": 45638602.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.192956161499024,
|
|
"epoch": 1.9130643611911622,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004636479557435818,
|
|
"loss": 4.9062,
|
|
"mean_token_accuracy": 0.22652638256549834,
|
|
"num_tokens": 45649460.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.147806978225708,
|
|
"epoch": 1.9135446685878963,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046362926897985067,
|
|
"loss": 4.8963,
|
|
"mean_token_accuracy": 0.22723331451416015,
|
|
"num_tokens": 45659995.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.218676948547364,
|
|
"epoch": 1.9140249759846302,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000463610577836708,
|
|
"loss": 4.9849,
|
|
"mean_token_accuracy": 0.2133773848414421,
|
|
"num_tokens": 45672262.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.286187076568604,
|
|
"epoch": 1.914505283381364,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046359188231458783,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.21478935033082963,
|
|
"num_tokens": 45685210.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.2673930644989015,
|
|
"epoch": 1.914985590778098,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046357318241392414,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.21094246953725815,
|
|
"num_tokens": 45696418.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.296578645706177,
|
|
"epoch": 1.915465898174832,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000463554478135151,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.2069357603788376,
|
|
"num_tokens": 45708393.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.3399721622467045,
|
|
"epoch": 1.915946205571566,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004635357694787029,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.20556865632534027,
|
|
"num_tokens": 45721287.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.222489881515503,
|
|
"epoch": 1.9164265129682998,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000463517056445014,
|
|
"loss": 4.8899,
|
|
"mean_token_accuracy": 0.2254376530647278,
|
|
"num_tokens": 45732846.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.288328409194946,
|
|
"epoch": 1.9169068203650337,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046349833903451884,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.20381149649620056,
|
|
"num_tokens": 45743931.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.330214929580689,
|
|
"epoch": 1.9173871277617676,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046347961724765196,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.21698636263608934,
|
|
"num_tokens": 45755512.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.253272676467896,
|
|
"epoch": 1.9178674351585014,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046346089108484806,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.21686626374721527,
|
|
"num_tokens": 45766793.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.288983583450317,
|
|
"epoch": 1.9183477425552353,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046344216054654193,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.21284249126911164,
|
|
"num_tokens": 45778214.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.41779351234436,
|
|
"epoch": 1.9188280499519692,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00046342342563316833,
|
|
"loss": 5.2223,
|
|
"mean_token_accuracy": 0.1990813434123993,
|
|
"num_tokens": 45791255.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.383186769485474,
|
|
"epoch": 1.919308357348703,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046340468634516223,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.20328861027956008,
|
|
"num_tokens": 45803351.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.256784582138062,
|
|
"epoch": 1.919788664745437,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046338594268295884,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.2210489481687546,
|
|
"num_tokens": 45814986.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.209194564819336,
|
|
"epoch": 1.9202689721421708,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004633671946469933,
|
|
"loss": 4.9879,
|
|
"mean_token_accuracy": 0.21612702310085297,
|
|
"num_tokens": 45827073.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.291515350341797,
|
|
"epoch": 1.920749279538905,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046334844223770076,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.22064218968153,
|
|
"num_tokens": 45837808.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.265262937545776,
|
|
"epoch": 1.9212295869356388,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046332968545551674,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.21589585691690444,
|
|
"num_tokens": 45849932.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.248825740814209,
|
|
"epoch": 1.9217098943323727,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004633109243008765,
|
|
"loss": 4.9964,
|
|
"mean_token_accuracy": 0.2118769183754921,
|
|
"num_tokens": 45860961.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.217818355560302,
|
|
"epoch": 1.9221902017291066,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004632921587742159,
|
|
"loss": 4.9359,
|
|
"mean_token_accuracy": 0.21958125233650208,
|
|
"num_tokens": 45872251.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.406523895263672,
|
|
"epoch": 1.9226705091258407,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046327338887597043,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.20970683842897414,
|
|
"num_tokens": 45883234.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.27851505279541,
|
|
"epoch": 1.9231508165225746,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000463254614606576,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.21865278780460357,
|
|
"num_tokens": 45894003.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.179859018325805,
|
|
"epoch": 1.9236311239193085,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004632358359664683,
|
|
"loss": 4.928,
|
|
"mean_token_accuracy": 0.22051313817501067,
|
|
"num_tokens": 45906109.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.30111927986145,
|
|
"epoch": 1.9241114313160423,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046321705295608356,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.21212252974510193,
|
|
"num_tokens": 45918372.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.345204162597656,
|
|
"epoch": 1.9245917387127762,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046319826557585764,
|
|
"loss": 5.0933,
|
|
"mean_token_accuracy": 0.21073244661092758,
|
|
"num_tokens": 45928750.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.3735614776611325,
|
|
"epoch": 1.92507204610951,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004631794738262269,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.21703273206949233,
|
|
"num_tokens": 45939297.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.292479944229126,
|
|
"epoch": 1.925552353506244,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004631606777076275,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.21720093190670015,
|
|
"num_tokens": 45949986.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.249690580368042,
|
|
"epoch": 1.9260326609029779,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046314187722049587,
|
|
"loss": 5.0268,
|
|
"mean_token_accuracy": 0.21340579092502593,
|
|
"num_tokens": 45960747.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.317514848709107,
|
|
"epoch": 1.9265129682997117,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046312307236526863,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.2125207483768463,
|
|
"num_tokens": 45972260.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.2846907615661625,
|
|
"epoch": 1.9269932756964456,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046310426314238217,
|
|
"loss": 4.9378,
|
|
"mean_token_accuracy": 0.2200598895549774,
|
|
"num_tokens": 45983589.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.178891563415528,
|
|
"epoch": 1.9274735830931795,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004630854495522733,
|
|
"loss": 4.9592,
|
|
"mean_token_accuracy": 0.2201237589120865,
|
|
"num_tokens": 45994776.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.316916608810425,
|
|
"epoch": 1.9279538904899134,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046306663159537874,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.21023641228675843,
|
|
"num_tokens": 46005530.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.313195991516113,
|
|
"epoch": 1.9284341978866475,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046304780927213554,
|
|
"loss": 4.9885,
|
|
"mean_token_accuracy": 0.2169075131416321,
|
|
"num_tokens": 46017538.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.276975154876709,
|
|
"epoch": 1.9289145052833814,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046302898258298046,
|
|
"loss": 4.9546,
|
|
"mean_token_accuracy": 0.2144000843167305,
|
|
"num_tokens": 46029011.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.224739217758179,
|
|
"epoch": 1.9293948126801153,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004630101515283509,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.22066741585731506,
|
|
"num_tokens": 46040354.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.236617946624756,
|
|
"epoch": 1.9298751200768491,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046299131610868377,
|
|
"loss": 4.972,
|
|
"mean_token_accuracy": 0.21499887406826018,
|
|
"num_tokens": 46051127.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.254773759841919,
|
|
"epoch": 1.9303554274735832,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004629724763244165,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.21948280334472656,
|
|
"num_tokens": 46062343.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.21448974609375,
|
|
"epoch": 1.9308357348703171,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004629536321759866,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.2166683316230774,
|
|
"num_tokens": 46074193.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.327248859405517,
|
|
"epoch": 1.931316042267051,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046293478366383133,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.22512240409851075,
|
|
"num_tokens": 46085930.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.339855003356933,
|
|
"epoch": 1.9317963496637849,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004629159307883885,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.2070867598056793,
|
|
"num_tokens": 46099759.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.3838738918304445,
|
|
"epoch": 1.9322766570605188,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004628970735500958,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.19904268980026246,
|
|
"num_tokens": 46110907.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.304093837738037,
|
|
"epoch": 1.9327569644572526,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046287821194939094,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.2147204965353012,
|
|
"num_tokens": 46122167.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.3268876552581785,
|
|
"epoch": 1.9332372718539865,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046285934598671186,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.2045973137021065,
|
|
"num_tokens": 46132948.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.324710512161255,
|
|
"epoch": 1.9337175792507204,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046284047566249665,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.21387228071689607,
|
|
"num_tokens": 46144275.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.239879751205445,
|
|
"epoch": 1.9341978866474543,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046282160097718336,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.2173812732100487,
|
|
"num_tokens": 46156138.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.324907207489014,
|
|
"epoch": 1.9346781940441882,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004628027219312102,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.20814938694238663,
|
|
"num_tokens": 46169437.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.295951890945434,
|
|
"epoch": 1.935158501440922,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004627838385250155,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.2192991405725479,
|
|
"num_tokens": 46182150.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.271713542938232,
|
|
"epoch": 1.9356388088376562,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046276495075903764,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.21614630967378617,
|
|
"num_tokens": 46193945.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.321183776855468,
|
|
"epoch": 1.93611911623439,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046274605863371517,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.2088358461856842,
|
|
"num_tokens": 46206130.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.207763051986694,
|
|
"epoch": 1.936599423631124,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004627271621494868,
|
|
"loss": 4.9572,
|
|
"mean_token_accuracy": 0.22250524312257766,
|
|
"num_tokens": 46217284.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.254165840148926,
|
|
"epoch": 1.9370797310278578,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000462708261306791,
|
|
"loss": 4.9988,
|
|
"mean_token_accuracy": 0.21670543253421784,
|
|
"num_tokens": 46227949.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.267551565170288,
|
|
"epoch": 1.937560038424592,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004626893561060669,
|
|
"loss": 4.9784,
|
|
"mean_token_accuracy": 0.21249676644802093,
|
|
"num_tokens": 46239101.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.343110132217407,
|
|
"epoch": 1.9380403458213258,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046267044654775324,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.20847206562757492,
|
|
"num_tokens": 46251272.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.318415117263794,
|
|
"epoch": 1.9385206532180597,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000462651532632289,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.20931880474090575,
|
|
"num_tokens": 46262603.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.329028367996216,
|
|
"epoch": 1.9390009606147935,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046263261436011344,
|
|
"loss": 5.0044,
|
|
"mean_token_accuracy": 0.21436837762594224,
|
|
"num_tokens": 46275142.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.2780944347381595,
|
|
"epoch": 1.9394812680115274,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004626136917316657,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.21261966228485107,
|
|
"num_tokens": 46286339.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.23852276802063,
|
|
"epoch": 1.9399615754082613,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046259476474738514,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.2121097594499588,
|
|
"num_tokens": 46297514.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.213236904144287,
|
|
"epoch": 1.9404418828049952,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046257583340771123,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.2214983358979225,
|
|
"num_tokens": 46309249.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.248092174530029,
|
|
"epoch": 1.940922190201729,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004625568977130835,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.2075631946325302,
|
|
"num_tokens": 46320759.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.372489929199219,
|
|
"epoch": 1.941402497598463,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004625379576639414,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.21001186221837997,
|
|
"num_tokens": 46332113.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.302760648727417,
|
|
"epoch": 1.9418828049951968,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046251901326072487,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.21828533411026002,
|
|
"num_tokens": 46342648.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.248122358322144,
|
|
"epoch": 1.9423631123919307,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046250006450387367,
|
|
"loss": 4.9561,
|
|
"mean_token_accuracy": 0.21959200203418733,
|
|
"num_tokens": 46354066.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.319426441192627,
|
|
"epoch": 1.9428434197886646,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004624811113938277,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.20509544610977173,
|
|
"num_tokens": 46366586.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.319909381866455,
|
|
"epoch": 1.9433237271853987,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004624621539310271,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.21691519170999526,
|
|
"num_tokens": 46378155.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.2960865020751955,
|
|
"epoch": 1.9438040345821326,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046244319211591193,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.20682416409254073,
|
|
"num_tokens": 46389631.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.353441667556763,
|
|
"epoch": 1.9442843419788665,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004624242259489223,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.2033352717757225,
|
|
"num_tokens": 46401915.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.358703994750977,
|
|
"epoch": 1.9447646493756003,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046240525543049884,
|
|
"loss": 5.0177,
|
|
"mean_token_accuracy": 0.21519384384155274,
|
|
"num_tokens": 46412396.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.212532377243042,
|
|
"epoch": 1.9452449567723344,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00046238628056108176,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.21879893243312837,
|
|
"num_tokens": 46423089.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.310611915588379,
|
|
"epoch": 1.9457252641690683,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00046236730134111166,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.20935657620429993,
|
|
"num_tokens": 46434858.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.201248598098755,
|
|
"epoch": 1.9462055715658022,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004623483177710291,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.22264298051595688,
|
|
"num_tokens": 46445628.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.238271808624267,
|
|
"epoch": 1.946685878962536,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004623293298512751,
|
|
"loss": 4.9739,
|
|
"mean_token_accuracy": 0.21631351858377457,
|
|
"num_tokens": 46457382.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.302374172210693,
|
|
"epoch": 1.94716618635927,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046231033758229026,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.2078896403312683,
|
|
"num_tokens": 46469765.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.393563556671142,
|
|
"epoch": 1.9476464937560038,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004622913409645154,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.21063573360443116,
|
|
"num_tokens": 46481451.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.294204330444336,
|
|
"epoch": 1.9481268011527377,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004622723399983919,
|
|
"loss": 4.8986,
|
|
"mean_token_accuracy": 0.22292485535144807,
|
|
"num_tokens": 46491585.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.283259391784668,
|
|
"epoch": 1.9486071085494716,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046225333468436077,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.20558424592018126,
|
|
"num_tokens": 46503789.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.342193078994751,
|
|
"epoch": 1.9490874159462055,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00046223432502286323,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.20954610854387284,
|
|
"num_tokens": 46516647.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.330379962921143,
|
|
"epoch": 1.9495677233429394,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046221531101434056,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.2077916905283928,
|
|
"num_tokens": 46527432.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.333846807479858,
|
|
"epoch": 1.9500480307396733,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004621962926592343,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.2121288448572159,
|
|
"num_tokens": 46538990.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.274318838119507,
|
|
"epoch": 1.9505283381364071,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000462177269957986,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.21003809571266174,
|
|
"num_tokens": 46551291.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.273636341094971,
|
|
"epoch": 1.9510086455331412,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004621582429110373,
|
|
"loss": 4.9705,
|
|
"mean_token_accuracy": 0.21971399784088136,
|
|
"num_tokens": 46562415.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.317828369140625,
|
|
"epoch": 1.9514889529298751,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046213921151883,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.22107682079076768,
|
|
"num_tokens": 46572544.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.281886291503906,
|
|
"epoch": 1.951969260326609,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004621201757818059,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.21738390475511551,
|
|
"num_tokens": 46584694.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.279499626159668,
|
|
"epoch": 1.952449567723343,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046210113570040683,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.21724555194377898,
|
|
"num_tokens": 46595086.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.317991638183594,
|
|
"epoch": 1.952929875120077,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000462082091275075,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.2108807697892189,
|
|
"num_tokens": 46606627.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.340487718582153,
|
|
"epoch": 1.9534101825168109,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004620630425062526,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.20705530941486358,
|
|
"num_tokens": 46618560.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.294549131393433,
|
|
"epoch": 1.9538904899135447,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004620439893943817,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.210959030687809,
|
|
"num_tokens": 46630109.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.280263948440552,
|
|
"epoch": 1.9543707973102786,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004620249319399049,
|
|
"loss": 4.9951,
|
|
"mean_token_accuracy": 0.2180105060338974,
|
|
"num_tokens": 46642247.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.368070507049561,
|
|
"epoch": 1.9548511047070125,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046200587014326455,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.21291210502386093,
|
|
"num_tokens": 46653119.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.218988561630249,
|
|
"epoch": 1.9553314121037464,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004619868040049031,
|
|
"loss": 4.9868,
|
|
"mean_token_accuracy": 0.21985072642564774,
|
|
"num_tokens": 46664392.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.220429182052612,
|
|
"epoch": 1.9558117195004803,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004619677335252633,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.2219279333949089,
|
|
"num_tokens": 46674981.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.31857442855835,
|
|
"epoch": 1.9562920268972142,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046194865870478793,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.20428954362869262,
|
|
"num_tokens": 46688692.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.189849233627319,
|
|
"epoch": 1.956772334293948,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046192957954391983,
|
|
"loss": 4.9016,
|
|
"mean_token_accuracy": 0.22908854633569717,
|
|
"num_tokens": 46699799.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.2713587284088135,
|
|
"epoch": 1.957252641690682,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000461910496043102,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.21134653240442275,
|
|
"num_tokens": 46711994.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.27680344581604,
|
|
"epoch": 1.9577329490874158,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004618914082027773,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.21466514468193054,
|
|
"num_tokens": 46723247.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.372175216674805,
|
|
"epoch": 1.95821325648415,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046187231602338926,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.20462281554937362,
|
|
"num_tokens": 46732824.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.2614501953125,
|
|
"epoch": 1.9586935638808838,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046185321950538086,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.21830960363149643,
|
|
"num_tokens": 46744640.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.233187532424926,
|
|
"epoch": 1.9591738712776177,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004618341186491955,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.21613709330558778,
|
|
"num_tokens": 46757513.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.261158895492554,
|
|
"epoch": 1.9596541786743515,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004618150134552768,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.21977288872003556,
|
|
"num_tokens": 46769021.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.237416982650757,
|
|
"epoch": 1.9601344860710856,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000461795903924068,
|
|
"loss": 4.9211,
|
|
"mean_token_accuracy": 0.21619904786348343,
|
|
"num_tokens": 46781175.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.231151485443116,
|
|
"epoch": 1.9606147934678195,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046177679005601313,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.2152673751115799,
|
|
"num_tokens": 46792256.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.180067443847657,
|
|
"epoch": 1.9610951008645534,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004617576718515558,
|
|
"loss": 4.9095,
|
|
"mean_token_accuracy": 0.22252859324216842,
|
|
"num_tokens": 46803215.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.325067234039307,
|
|
"epoch": 1.9615754082612873,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004617385493111399,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.2187580242753029,
|
|
"num_tokens": 46813770.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.2910933017730715,
|
|
"epoch": 1.9620557156580212,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004617194224352093,
|
|
"loss": 5.0541,
|
|
"mean_token_accuracy": 0.21663111597299575,
|
|
"num_tokens": 46826923.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.227443361282349,
|
|
"epoch": 1.962536023054755,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004617002912242083,
|
|
"loss": 4.9523,
|
|
"mean_token_accuracy": 0.21961165517568587,
|
|
"num_tokens": 46837761.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.267227697372436,
|
|
"epoch": 1.963016330451489,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046168115567858084,
|
|
"loss": 5.0176,
|
|
"mean_token_accuracy": 0.21460486501455306,
|
|
"num_tokens": 46848190.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.19956374168396,
|
|
"epoch": 1.9634966378482228,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046166201579877125,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.22261028587818146,
|
|
"num_tokens": 46858643.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.235478734970092,
|
|
"epoch": 1.9639769452449567,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004616428715852239,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.21382445245981216,
|
|
"num_tokens": 46868711.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.287342214584351,
|
|
"epoch": 1.9644572526416906,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004616237230383833,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.21296110600233079,
|
|
"num_tokens": 46880045.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.246248531341553,
|
|
"epoch": 1.9649375600384245,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00046160457015869414,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.21423857361078263,
|
|
"num_tokens": 46890680.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.253405141830444,
|
|
"epoch": 1.9654178674351583,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046158541294660083,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.21291701048612593,
|
|
"num_tokens": 46904807.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.307267808914185,
|
|
"epoch": 1.9658981748318924,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004615662514025483,
|
|
"loss": 4.981,
|
|
"mean_token_accuracy": 0.21761256754398345,
|
|
"num_tokens": 46916039.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.269694519042969,
|
|
"epoch": 1.9663784822286263,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046154708552698147,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.21115701496601105,
|
|
"num_tokens": 46927175.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.184688138961792,
|
|
"epoch": 1.9668587896253602,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046152791532034517,
|
|
"loss": 4.8842,
|
|
"mean_token_accuracy": 0.22842337042093278,
|
|
"num_tokens": 46938711.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.232572269439697,
|
|
"epoch": 1.967339097022094,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046150874078308463,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.2101133167743683,
|
|
"num_tokens": 46951002.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.373419141769409,
|
|
"epoch": 1.9678194044188282,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004614895619156449,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.2113277405500412,
|
|
"num_tokens": 46962673.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.270331859588623,
|
|
"epoch": 1.968299711815562,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046147037871847125,
|
|
"loss": 4.9835,
|
|
"mean_token_accuracy": 0.21468617916107177,
|
|
"num_tokens": 46973955.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.264113092422486,
|
|
"epoch": 1.968780019212296,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004614511911920092,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.20566287636756897,
|
|
"num_tokens": 46985791.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.432606554031372,
|
|
"epoch": 1.9692603266090298,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046143199933670404,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.20247029811143874,
|
|
"num_tokens": 46998437.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.29546012878418,
|
|
"epoch": 1.9697406340057637,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004614128031530015,
|
|
"loss": 4.9662,
|
|
"mean_token_accuracy": 0.2105017974972725,
|
|
"num_tokens": 47009666.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.312030935287476,
|
|
"epoch": 1.9702209414024976,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046139360264134724,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.20746953934431075,
|
|
"num_tokens": 47021170.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.31428484916687,
|
|
"epoch": 1.9707012487992315,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004613743978021869,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.21696943938732147,
|
|
"num_tokens": 47033077.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.339881563186646,
|
|
"epoch": 1.9711815561959654,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046135518863596654,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.20911260396242143,
|
|
"num_tokens": 47044858.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.323528003692627,
|
|
"epoch": 1.9716618635926992,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046133597514313204,
|
|
"loss": 5.1148,
|
|
"mean_token_accuracy": 0.2039257436990738,
|
|
"num_tokens": 47057587.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.318865489959717,
|
|
"epoch": 1.9721421709894331,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004613167573241295,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.20321835428476334,
|
|
"num_tokens": 47068690.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.303210639953614,
|
|
"epoch": 1.972622478386167,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004612975351794051,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.21286789923906327,
|
|
"num_tokens": 47081279.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.314201736450196,
|
|
"epoch": 1.973102785782901,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004612783087094051,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.2106296792626381,
|
|
"num_tokens": 47093372.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.3587483882904055,
|
|
"epoch": 1.973583093179635,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046125907791457594,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.19956330209970474,
|
|
"num_tokens": 47104332.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.3330153465271,
|
|
"epoch": 1.9740634005763689,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046123984279536405,
|
|
"loss": 5.0277,
|
|
"mean_token_accuracy": 0.21092136055231095,
|
|
"num_tokens": 47116941.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.361131858825684,
|
|
"epoch": 1.9745437079731027,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046122060335221604,
|
|
"loss": 5.0748,
|
|
"mean_token_accuracy": 0.2092033788561821,
|
|
"num_tokens": 47128473.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.240169620513916,
|
|
"epoch": 1.9750240153698368,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046120135958557855,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.2075726345181465,
|
|
"num_tokens": 47140586.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.20444974899292,
|
|
"epoch": 1.9755043227665707,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046118211149589843,
|
|
"loss": 4.9605,
|
|
"mean_token_accuracy": 0.22434598356485366,
|
|
"num_tokens": 47150875.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.2706891059875485,
|
|
"epoch": 1.9759846301633046,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004611628590836225,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.22923311442136765,
|
|
"num_tokens": 47162074.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.222149324417114,
|
|
"epoch": 1.9764649375600385,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004611436023491979,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.21839731484651564,
|
|
"num_tokens": 47174544.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.3230393409729,
|
|
"epoch": 1.9769452449567724,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004611243412930714,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.21177063435316085,
|
|
"num_tokens": 47186260.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.2830664157867435,
|
|
"epoch": 1.9774255523535063,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046110507591569047,
|
|
"loss": 4.9809,
|
|
"mean_token_accuracy": 0.2132396712899208,
|
|
"num_tokens": 47198059.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.212104797363281,
|
|
"epoch": 1.9779058597502401,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004610858062175023,
|
|
"loss": 4.94,
|
|
"mean_token_accuracy": 0.2211351662874222,
|
|
"num_tokens": 47208300.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.237720775604248,
|
|
"epoch": 1.978386167146974,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046106653219895417,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.2177065685391426,
|
|
"num_tokens": 47220135.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.3905106544494625,
|
|
"epoch": 1.978866474543708,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004610472538604938,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.20639235228300096,
|
|
"num_tokens": 47230385.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.1854071617126465,
|
|
"epoch": 1.9793467819404418,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046102797120256854,
|
|
"loss": 4.9119,
|
|
"mean_token_accuracy": 0.2193854421377182,
|
|
"num_tokens": 47242593.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.330305099487305,
|
|
"epoch": 1.9798270893371757,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004610086842256262,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.21453961730003357,
|
|
"num_tokens": 47254223.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.303645610809326,
|
|
"epoch": 1.9803073967339095,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004609893929301146,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.21432540267705918,
|
|
"num_tokens": 47266559.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.299778842926026,
|
|
"epoch": 1.9807877041306436,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004609700973164816,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.2149021878838539,
|
|
"num_tokens": 47276438.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.24346513748169,
|
|
"epoch": 1.9812680115273775,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004609507973851751,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.2101423427462578,
|
|
"num_tokens": 47287791.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.254670143127441,
|
|
"epoch": 1.9817483189241114,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046093149313664316,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.21622006148099898,
|
|
"num_tokens": 47300282.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.395428037643432,
|
|
"epoch": 1.9822286263208453,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004609121845713342,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.21435018628835678,
|
|
"num_tokens": 47310473.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.257578897476196,
|
|
"epoch": 1.9827089337175794,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004608928716896963,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.21473112553358079,
|
|
"num_tokens": 47322245.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.302432870864868,
|
|
"epoch": 1.9831892411143133,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004608735544921778,
|
|
"loss": 5.0248,
|
|
"mean_token_accuracy": 0.21750623285770415,
|
|
"num_tokens": 47334316.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.348230075836182,
|
|
"epoch": 1.9836695485110472,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046085423297922745,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.20937004834413528,
|
|
"num_tokens": 47344909.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.231410980224609,
|
|
"epoch": 1.984149855907781,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00046083490715129367,
|
|
"loss": 4.9311,
|
|
"mean_token_accuracy": 0.22692679315805436,
|
|
"num_tokens": 47356682.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.236084079742431,
|
|
"epoch": 1.984630163304515,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004608155770088251,
|
|
"loss": 4.8891,
|
|
"mean_token_accuracy": 0.22552646249532698,
|
|
"num_tokens": 47368362.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.32037353515625,
|
|
"epoch": 1.9851104707012488,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046079624255227066,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.21459729820489884,
|
|
"num_tokens": 47379932.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.2608959674835205,
|
|
"epoch": 1.9855907780979827,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004607769037820791,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.206511253118515,
|
|
"num_tokens": 47391244.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.318761014938355,
|
|
"epoch": 1.9860710854947166,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004607575606986995,
|
|
"loss": 5.0242,
|
|
"mean_token_accuracy": 0.2130133777856827,
|
|
"num_tokens": 47404005.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.188485145568848,
|
|
"epoch": 1.9865513928914504,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004607382133025809,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.21952994167804718,
|
|
"num_tokens": 47414555.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.270067739486694,
|
|
"epoch": 1.9870317002881843,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046071886159417257,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.21426478773355484,
|
|
"num_tokens": 47425902.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.160845136642456,
|
|
"epoch": 1.9875120076849182,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004606995055739238,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.22313574999570845,
|
|
"num_tokens": 47438068.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.3258349895477295,
|
|
"epoch": 1.9879923150816523,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046068014524228374,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.2105170413851738,
|
|
"num_tokens": 47450322.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.2598789691925045,
|
|
"epoch": 1.9884726224783862,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046066078059970217,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.21418765634298326,
|
|
"num_tokens": 47462615.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.2725849628448485,
|
|
"epoch": 1.98895292987512,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004606414116466286,
|
|
"loss": 4.9602,
|
|
"mean_token_accuracy": 0.21760379076004027,
|
|
"num_tokens": 47472530.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.234996032714844,
|
|
"epoch": 1.989433237271854,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046062203838351267,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.21864081174135208,
|
|
"num_tokens": 47484217.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.341804170608521,
|
|
"epoch": 1.989913544668588,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046060266081080414,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.21228740662336348,
|
|
"num_tokens": 47496365.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.288717651367188,
|
|
"epoch": 1.990393852065322,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004605832789289531,
|
|
"loss": 5.031,
|
|
"mean_token_accuracy": 0.22136366963386536,
|
|
"num_tokens": 47509437.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.324091577529908,
|
|
"epoch": 1.9908741594620558,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004605638927384093,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.20378996729850768,
|
|
"num_tokens": 47520913.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.33263578414917,
|
|
"epoch": 1.9913544668587897,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.00046054450223962284,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.2074803128838539,
|
|
"num_tokens": 47532015.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.377984476089478,
|
|
"epoch": 1.9918347742555236,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046052510743304405,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.20272771269083023,
|
|
"num_tokens": 47543675.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.286761093139648,
|
|
"epoch": 1.9923150816522575,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004605057083191232,
|
|
"loss": 4.9965,
|
|
"mean_token_accuracy": 0.21486834585666656,
|
|
"num_tokens": 47555757.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.341885042190552,
|
|
"epoch": 1.9927953890489913,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004604863048983106,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.2108628645539284,
|
|
"num_tokens": 47568043.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.244656753540039,
|
|
"epoch": 1.9932756964457252,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004604668971710568,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.21564851850271224,
|
|
"num_tokens": 47577811.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.378100395202637,
|
|
"epoch": 1.993756003842459,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004604474851378124,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.20760051608085633,
|
|
"num_tokens": 47588309.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.4479766368865965,
|
|
"epoch": 1.994236311239193,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046042806879902803,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.20232975631952285,
|
|
"num_tokens": 47599814.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.378687953948974,
|
|
"epoch": 1.9947166186359269,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004604086481551546,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.21041362285614013,
|
|
"num_tokens": 47611851.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.242335176467895,
|
|
"epoch": 1.9951969260326607,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004603892232066428,
|
|
"loss": 4.9354,
|
|
"mean_token_accuracy": 0.2179631844162941,
|
|
"num_tokens": 47624056.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.249002170562744,
|
|
"epoch": 1.9956772334293948,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046036979395394374,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.21273429691791534,
|
|
"num_tokens": 47637214.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.321302366256714,
|
|
"epoch": 1.9961575408261287,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004603503603975085,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.21624971479177474,
|
|
"num_tokens": 47647498.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.283480167388916,
|
|
"epoch": 1.9966378482228626,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004603309225377883,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.21645567566156387,
|
|
"num_tokens": 47659576.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.319673776626587,
|
|
"epoch": 1.9971181556195965,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004603114803752344,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.21627725958824157,
|
|
"num_tokens": 47670631.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.262354850769043,
|
|
"epoch": 1.9975984630163306,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00046029203391029813,
|
|
"loss": 4.9352,
|
|
"mean_token_accuracy": 0.21583732813596726,
|
|
"num_tokens": 47681647.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.304576063156128,
|
|
"epoch": 1.9980787704130645,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046027258314343107,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.2177200511097908,
|
|
"num_tokens": 47694386.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.305324649810791,
|
|
"epoch": 1.9985590778097984,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046025312807508487,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.21233405023813248,
|
|
"num_tokens": 47704897.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.259843206405639,
|
|
"epoch": 1.9990393852065322,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046023366870571097,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.21114459931850432,
|
|
"num_tokens": 47715771.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.347751903533935,
|
|
"epoch": 1.9995196926032661,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046021420503576145,
|
|
"loss": 4.9502,
|
|
"mean_token_accuracy": 0.2207678884267807,
|
|
"num_tokens": 47726295.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.200345993041992,
|
|
"epoch": 2.0,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004601947370656879,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.20830153524875641,
|
|
"num_tokens": 47737072.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.292755889892578,
|
|
"epoch": 2.000480307396734,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004601752647959426,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.2101481720805168,
|
|
"num_tokens": 47750379.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.390938663482666,
|
|
"epoch": 2.0009606147934678,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004601557882269775,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.20955608338117598,
|
|
"num_tokens": 47763059.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.287863063812256,
|
|
"epoch": 2.0014409221902016,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004601363073592447,
|
|
"loss": 4.9365,
|
|
"mean_token_accuracy": 0.21765465587377547,
|
|
"num_tokens": 47775513.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.210210800170898,
|
|
"epoch": 2.0019212295869355,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004601168221931967,
|
|
"loss": 4.8692,
|
|
"mean_token_accuracy": 0.2205789491534233,
|
|
"num_tokens": 47786215.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.2372801303863525,
|
|
"epoch": 2.0024015369836694,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004600973327292857,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.21732470989227295,
|
|
"num_tokens": 47796894.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.2534534454345705,
|
|
"epoch": 2.0028818443804033,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046007783896796436,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.21410460770130157,
|
|
"num_tokens": 47808505.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.264333772659302,
|
|
"epoch": 2.003362151777137,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004600583409096851,
|
|
"loss": 4.8573,
|
|
"mean_token_accuracy": 0.22370079457759856,
|
|
"num_tokens": 47819617.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.214208936691284,
|
|
"epoch": 2.0038424591738715,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046003883855490066,
|
|
"loss": 4.905,
|
|
"mean_token_accuracy": 0.2269794002175331,
|
|
"num_tokens": 47830655.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.194448089599609,
|
|
"epoch": 2.0043227665706054,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004600193319040638,
|
|
"loss": 4.8556,
|
|
"mean_token_accuracy": 0.22256429493427277,
|
|
"num_tokens": 47842439.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.165983724594116,
|
|
"epoch": 2.0048030739673393,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045999982095762756,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.22932244688272477,
|
|
"num_tokens": 47853327.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.308304214477539,
|
|
"epoch": 2.005283381364073,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00045998030571604473,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.21660917848348618,
|
|
"num_tokens": 47867155.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.287899541854858,
|
|
"epoch": 2.005763688760807,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004599607861797685,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.21699809432029724,
|
|
"num_tokens": 47879641.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.277233648300171,
|
|
"epoch": 2.006243996157541,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00045994126234925203,
|
|
"loss": 4.9833,
|
|
"mean_token_accuracy": 0.2095753639936447,
|
|
"num_tokens": 47890512.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.280686092376709,
|
|
"epoch": 2.006724303554275,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00045992173422494865,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.20959788262844087,
|
|
"num_tokens": 47902575.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.265145778656006,
|
|
"epoch": 2.0072046109510087,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004599022018073117,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.2257157489657402,
|
|
"num_tokens": 47915447.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.240523910522461,
|
|
"epoch": 2.0076849183477425,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004598826650967946,
|
|
"loss": 4.9371,
|
|
"mean_token_accuracy": 0.2157982900738716,
|
|
"num_tokens": 47925702.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.236347818374634,
|
|
"epoch": 2.0081652257444764,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045986312409385105,
|
|
"loss": 4.9144,
|
|
"mean_token_accuracy": 0.2237488090991974,
|
|
"num_tokens": 47936621.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.212708377838135,
|
|
"epoch": 2.0086455331412103,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004598435787989347,
|
|
"loss": 4.8761,
|
|
"mean_token_accuracy": 0.2239510416984558,
|
|
"num_tokens": 47948026.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.329348611831665,
|
|
"epoch": 2.009125840537944,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00045982402921249934,
|
|
"loss": 4.9837,
|
|
"mean_token_accuracy": 0.2158149227499962,
|
|
"num_tokens": 47959976.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.312648868560791,
|
|
"epoch": 2.009606147934678,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004598044753349988,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.20889578759670258,
|
|
"num_tokens": 47972071.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.238373470306397,
|
|
"epoch": 2.010086455331412,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045978491716688706,
|
|
"loss": 4.9172,
|
|
"mean_token_accuracy": 0.22420759946107865,
|
|
"num_tokens": 47984789.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.232894659042358,
|
|
"epoch": 2.010566762728146,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004597653547086184,
|
|
"loss": 4.9088,
|
|
"mean_token_accuracy": 0.22079799622297286,
|
|
"num_tokens": 47995661.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.314253568649292,
|
|
"epoch": 2.0110470701248797,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004597457879606467,
|
|
"loss": 4.9916,
|
|
"mean_token_accuracy": 0.21548200249671937,
|
|
"num_tokens": 48006043.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.266390228271485,
|
|
"epoch": 2.011527377521614,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045972621692342636,
|
|
"loss": 5.0328,
|
|
"mean_token_accuracy": 0.21404333263635636,
|
|
"num_tokens": 48016904.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.308969593048095,
|
|
"epoch": 2.012007684918348,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045970664159741186,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.2208836108446121,
|
|
"num_tokens": 48026533.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.2323424339294435,
|
|
"epoch": 2.012487992315082,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045968706198305765,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.2262360244989395,
|
|
"num_tokens": 48038280.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.174136066436768,
|
|
"epoch": 2.0129682997118157,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045966747808081824,
|
|
"loss": 4.862,
|
|
"mean_token_accuracy": 0.22376373857259751,
|
|
"num_tokens": 48049663.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.2826111793518065,
|
|
"epoch": 2.0134486071085496,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004596478898911483,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.21532391905784606,
|
|
"num_tokens": 48059826.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.22762098312378,
|
|
"epoch": 2.0139289145052834,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045962829741450265,
|
|
"loss": 4.8589,
|
|
"mean_token_accuracy": 0.2246117651462555,
|
|
"num_tokens": 48071097.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.259641313552857,
|
|
"epoch": 2.0144092219020173,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004596087006513361,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.22035930603742598,
|
|
"num_tokens": 48082297.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.174351978302002,
|
|
"epoch": 2.014889529298751,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045958909960210385,
|
|
"loss": 4.8461,
|
|
"mean_token_accuracy": 0.2262355774641037,
|
|
"num_tokens": 48092946.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.159037113189697,
|
|
"epoch": 2.015369836695485,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045956949426726075,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.22461183220148087,
|
|
"num_tokens": 48105000.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.225910949707031,
|
|
"epoch": 2.015850144092219,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045954988464726203,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.21950788646936417,
|
|
"num_tokens": 48117513.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.3533014297485355,
|
|
"epoch": 2.016330451488953,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000459530270742563,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.199098339676857,
|
|
"num_tokens": 48130895.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.299352312088013,
|
|
"epoch": 2.0168107588856867,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045951065255361905,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.21402945071458818,
|
|
"num_tokens": 48143348.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.244781351089477,
|
|
"epoch": 2.0172910662824206,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004594910300808856,
|
|
"loss": 4.9354,
|
|
"mean_token_accuracy": 0.2209245190024376,
|
|
"num_tokens": 48154959.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.0172910662824206,
|
|
"eval_entropy": 5.057286840715041,
|
|
"eval_loss": 5.076265335083008,
|
|
"eval_mean_token_accuracy": 0.2192253630811749,
|
|
"eval_num_tokens": 48154959.0,
|
|
"eval_runtime": 26.6798,
|
|
"eval_samples_per_second": 1229.957,
|
|
"eval_steps_per_second": 153.749,
|
|
"step": 21000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 104090,
|
|
"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": 7.3624264022016e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|