12057 lines
329 KiB
JSON
12057 lines
329 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.5763688760806917,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 2.1108419647488e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|