18068 lines
495 KiB
JSON
18068 lines
495 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.8645533141210374,
|
|
"eval_steps": 3000,
|
|
"global_step": 9000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.7425968170166,
|
|
"epoch": 0.0004803073967339097,
|
|
"grad_norm": 5.0,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7893,
|
|
"mean_token_accuracy": 0.0001694567094091326,
|
|
"num_tokens": 10855.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742561435699463,
|
|
"epoch": 0.0009606147934678194,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.8164,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 24110.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742608547210693,
|
|
"epoch": 0.001440922190201729,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7754,
|
|
"mean_token_accuracy": 6.963788182474673e-05,
|
|
"num_tokens": 35984.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742629623413086,
|
|
"epoch": 0.0019212295869356388,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.7236,
|
|
"mean_token_accuracy": 7.215007208287716e-05,
|
|
"num_tokens": 48152.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.742585182189941,
|
|
"epoch": 0.0024015369836695487,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.6191,
|
|
"mean_token_accuracy": 0.0010923755064141006,
|
|
"num_tokens": 59810.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.74241237640381,
|
|
"epoch": 0.002881844380403458,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.4993,
|
|
"mean_token_accuracy": 0.00965826828032732,
|
|
"num_tokens": 70852.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.74171323776245,
|
|
"epoch": 0.0033621517771373678,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3736,
|
|
"mean_token_accuracy": 0.025041871704161167,
|
|
"num_tokens": 83378.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.74036684036255,
|
|
"epoch": 0.0038424591738712775,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.241,
|
|
"mean_token_accuracy": 0.0312205046415329,
|
|
"num_tokens": 95505.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.738578128814698,
|
|
"epoch": 0.004322766570605188,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.1218,
|
|
"mean_token_accuracy": 0.03706384804099798,
|
|
"num_tokens": 106812.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.737641048431396,
|
|
"epoch": 0.004803073967339097,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.0587,
|
|
"mean_token_accuracy": 0.03593158051371574,
|
|
"num_tokens": 118572.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.737699699401855,
|
|
"epoch": 0.005283381364073006,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.9722,
|
|
"mean_token_accuracy": 0.033468486927449706,
|
|
"num_tokens": 130051.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.737590789794922,
|
|
"epoch": 0.005763688760806916,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.9388,
|
|
"mean_token_accuracy": 0.04036580752581358,
|
|
"num_tokens": 141920.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.736310005187988,
|
|
"epoch": 0.006243996157540826,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.8341,
|
|
"mean_token_accuracy": 0.04443504847586155,
|
|
"num_tokens": 152706.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.733973693847656,
|
|
"epoch": 0.0067243035542747355,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.8099,
|
|
"mean_token_accuracy": 0.04265851955860853,
|
|
"num_tokens": 165253.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.73133602142334,
|
|
"epoch": 0.007204610951008645,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.7265,
|
|
"mean_token_accuracy": 0.04272236041724682,
|
|
"num_tokens": 176708.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.72813663482666,
|
|
"epoch": 0.007684918347742555,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.6935,
|
|
"mean_token_accuracy": 0.04440820924937725,
|
|
"num_tokens": 188240.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.724117946624755,
|
|
"epoch": 0.008165225744476465,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.5348,
|
|
"mean_token_accuracy": 0.04667272008955479,
|
|
"num_tokens": 198355.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.719026947021485,
|
|
"epoch": 0.008645533141210375,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.493,
|
|
"mean_token_accuracy": 0.043789859488606454,
|
|
"num_tokens": 209497.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.712520503997803,
|
|
"epoch": 0.009125840537944284,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.4335,
|
|
"mean_token_accuracy": 0.04756799638271332,
|
|
"num_tokens": 220859.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.70284299850464,
|
|
"epoch": 0.009606147934678195,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.3827,
|
|
"mean_token_accuracy": 0.05129999294877052,
|
|
"num_tokens": 231550.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.686277961730957,
|
|
"epoch": 0.010086455331412104,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2483,
|
|
"mean_token_accuracy": 0.05116281881928444,
|
|
"num_tokens": 244210.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.665186405181885,
|
|
"epoch": 0.010566762728146013,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1189,
|
|
"mean_token_accuracy": 0.058265451714396475,
|
|
"num_tokens": 255745.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.634323501586914,
|
|
"epoch": 0.011047070124879923,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0189,
|
|
"mean_token_accuracy": 0.05389787927269936,
|
|
"num_tokens": 266180.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.591359043121338,
|
|
"epoch": 0.011527377521613832,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8917,
|
|
"mean_token_accuracy": 0.057663530483841895,
|
|
"num_tokens": 277736.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.54497652053833,
|
|
"epoch": 0.012007684918347743,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7685,
|
|
"mean_token_accuracy": 0.061545657366514205,
|
|
"num_tokens": 289069.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.48107271194458,
|
|
"epoch": 0.012487992315081652,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6457,
|
|
"mean_token_accuracy": 0.06588748730719089,
|
|
"num_tokens": 300240.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.40806179046631,
|
|
"epoch": 0.012968299711815562,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.558,
|
|
"mean_token_accuracy": 0.06453255712985992,
|
|
"num_tokens": 311698.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.328728771209716,
|
|
"epoch": 0.013448607108549471,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.4291,
|
|
"mean_token_accuracy": 0.06200851388275623,
|
|
"num_tokens": 322844.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.22898988723755,
|
|
"epoch": 0.013928914505283382,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.3111,
|
|
"mean_token_accuracy": 0.06522167101502419,
|
|
"num_tokens": 335092.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.104230976104736,
|
|
"epoch": 0.01440922190201729,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1711,
|
|
"mean_token_accuracy": 0.06845104768872261,
|
|
"num_tokens": 347033.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.963459777832032,
|
|
"epoch": 0.014889529298751201,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.0479,
|
|
"mean_token_accuracy": 0.06833775304257869,
|
|
"num_tokens": 358696.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.770106410980224,
|
|
"epoch": 0.01536983669548511,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9389,
|
|
"mean_token_accuracy": 0.07227320410311222,
|
|
"num_tokens": 369390.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.595024299621581,
|
|
"epoch": 0.01585014409221902,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.832,
|
|
"mean_token_accuracy": 0.07254205383360386,
|
|
"num_tokens": 380540.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.395240879058838,
|
|
"epoch": 0.01633045148895293,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7561,
|
|
"mean_token_accuracy": 0.07409532256424427,
|
|
"num_tokens": 391243.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.157040977478028,
|
|
"epoch": 0.01681075888568684,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.6871,
|
|
"mean_token_accuracy": 0.07649487368762493,
|
|
"num_tokens": 403336.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.964170169830322,
|
|
"epoch": 0.01729106628242075,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.5772,
|
|
"mean_token_accuracy": 0.07687406204640865,
|
|
"num_tokens": 413886.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.755004787445069,
|
|
"epoch": 0.01777137367915466,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5785,
|
|
"mean_token_accuracy": 0.07747036479413509,
|
|
"num_tokens": 425277.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.616313934326172,
|
|
"epoch": 0.01825168107588857,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.6259,
|
|
"mean_token_accuracy": 0.079135612398386,
|
|
"num_tokens": 436868.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.522105503082276,
|
|
"epoch": 0.018731988472622477,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.4359,
|
|
"mean_token_accuracy": 0.08061296418309212,
|
|
"num_tokens": 448349.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.420132637023926,
|
|
"epoch": 0.01921229586935639,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.4205,
|
|
"mean_token_accuracy": 0.08393056243658066,
|
|
"num_tokens": 459447.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.309343433380127,
|
|
"epoch": 0.0196926032660903,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.3675,
|
|
"mean_token_accuracy": 0.08649685978889465,
|
|
"num_tokens": 470734.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.280020236968994,
|
|
"epoch": 0.020172910662824207,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.4174,
|
|
"mean_token_accuracy": 0.08485044017434121,
|
|
"num_tokens": 482015.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.232032871246338,
|
|
"epoch": 0.020653218059558116,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.3525,
|
|
"mean_token_accuracy": 0.08708564937114716,
|
|
"num_tokens": 493339.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.191392135620116,
|
|
"epoch": 0.021133525456292025,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.289,
|
|
"mean_token_accuracy": 0.0901091642677784,
|
|
"num_tokens": 504924.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.096070671081543,
|
|
"epoch": 0.021613832853025938,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.2659,
|
|
"mean_token_accuracy": 0.08543256968259812,
|
|
"num_tokens": 516603.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.060660076141357,
|
|
"epoch": 0.022094140249759846,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.1691,
|
|
"mean_token_accuracy": 0.09287247136235237,
|
|
"num_tokens": 528347.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.039314794540406,
|
|
"epoch": 0.022574447646493755,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.2454,
|
|
"mean_token_accuracy": 0.09620365053415299,
|
|
"num_tokens": 539328.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.03833818435669,
|
|
"epoch": 0.023054755043227664,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.2157,
|
|
"mean_token_accuracy": 0.10354483127593994,
|
|
"num_tokens": 549297.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.88909420967102,
|
|
"epoch": 0.023535062439961577,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.1749,
|
|
"mean_token_accuracy": 0.09601260498166084,
|
|
"num_tokens": 560306.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.962506532669067,
|
|
"epoch": 0.024015369836695485,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.2445,
|
|
"mean_token_accuracy": 0.0955030769109726,
|
|
"num_tokens": 571972.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.930570125579834,
|
|
"epoch": 0.024495677233429394,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.1279,
|
|
"mean_token_accuracy": 0.10435850247740745,
|
|
"num_tokens": 582962.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.853069543838501,
|
|
"epoch": 0.024975984630163303,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.0975,
|
|
"mean_token_accuracy": 0.0972387246787548,
|
|
"num_tokens": 597193.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.889965534210205,
|
|
"epoch": 0.025456292026897216,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.1716,
|
|
"mean_token_accuracy": 0.10085091665387154,
|
|
"num_tokens": 608982.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.903727865219116,
|
|
"epoch": 0.025936599423631124,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.206,
|
|
"mean_token_accuracy": 0.09627965837717056,
|
|
"num_tokens": 619953.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.821546459197998,
|
|
"epoch": 0.026416906820365033,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.1526,
|
|
"mean_token_accuracy": 0.10060698464512825,
|
|
"num_tokens": 631039.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.850963020324707,
|
|
"epoch": 0.026897214217098942,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.1375,
|
|
"mean_token_accuracy": 0.10203886106610298,
|
|
"num_tokens": 642656.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.698967504501343,
|
|
"epoch": 0.027377521613832854,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.0134,
|
|
"mean_token_accuracy": 0.11590334996581078,
|
|
"num_tokens": 653748.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.7186966896057125,
|
|
"epoch": 0.027857829010566763,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.9933,
|
|
"mean_token_accuracy": 0.10406283661723137,
|
|
"num_tokens": 665618.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.69569730758667,
|
|
"epoch": 0.028338136407300672,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.0226,
|
|
"mean_token_accuracy": 0.10578782483935356,
|
|
"num_tokens": 677329.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.657517051696777,
|
|
"epoch": 0.02881844380403458,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.9769,
|
|
"mean_token_accuracy": 0.10939329639077186,
|
|
"num_tokens": 688278.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.689532470703125,
|
|
"epoch": 0.029298751200768493,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.0338,
|
|
"mean_token_accuracy": 0.10749343782663345,
|
|
"num_tokens": 700739.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.570545291900634,
|
|
"epoch": 0.029779058597502402,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.9673,
|
|
"mean_token_accuracy": 0.10927367061376572,
|
|
"num_tokens": 712527.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.609434270858765,
|
|
"epoch": 0.03025936599423631,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.9962,
|
|
"mean_token_accuracy": 0.10492227971553802,
|
|
"num_tokens": 724514.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.632580757141113,
|
|
"epoch": 0.03073967339097022,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.9339,
|
|
"mean_token_accuracy": 0.11308366954326629,
|
|
"num_tokens": 735679.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.555677700042724,
|
|
"epoch": 0.03121998078770413,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.942,
|
|
"mean_token_accuracy": 0.11490793004631997,
|
|
"num_tokens": 747896.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.581246328353882,
|
|
"epoch": 0.03170028818443804,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.9856,
|
|
"mean_token_accuracy": 0.10933408513665199,
|
|
"num_tokens": 759081.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.607112407684326,
|
|
"epoch": 0.03218059558117195,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.9207,
|
|
"mean_token_accuracy": 0.10591650679707527,
|
|
"num_tokens": 770459.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.448120260238648,
|
|
"epoch": 0.03266090297790586,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.8814,
|
|
"mean_token_accuracy": 0.11157295480370522,
|
|
"num_tokens": 783960.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.518631458282471,
|
|
"epoch": 0.03314121037463977,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.9692,
|
|
"mean_token_accuracy": 0.1153689943253994,
|
|
"num_tokens": 795425.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.512917995452881,
|
|
"epoch": 0.03362151777137368,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.927,
|
|
"mean_token_accuracy": 0.10967304334044456,
|
|
"num_tokens": 807536.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.475287914276123,
|
|
"epoch": 0.034101825168107586,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.9761,
|
|
"mean_token_accuracy": 0.10532209947705269,
|
|
"num_tokens": 818801.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.540158653259278,
|
|
"epoch": 0.0345821325648415,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8451,
|
|
"mean_token_accuracy": 0.11356438398361206,
|
|
"num_tokens": 831497.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.401552820205689,
|
|
"epoch": 0.03506243996157541,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8086,
|
|
"mean_token_accuracy": 0.11573421731591224,
|
|
"num_tokens": 842491.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.4459820747375485,
|
|
"epoch": 0.03554274735830932,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.8907,
|
|
"mean_token_accuracy": 0.10651533678174019,
|
|
"num_tokens": 854560.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.452930879592896,
|
|
"epoch": 0.03602305475504323,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.8048,
|
|
"mean_token_accuracy": 0.12114926502108574,
|
|
"num_tokens": 866688.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.454508543014526,
|
|
"epoch": 0.03650336215177714,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.9043,
|
|
"mean_token_accuracy": 0.10833153203129768,
|
|
"num_tokens": 879484.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.407199048995972,
|
|
"epoch": 0.036983669548511046,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8868,
|
|
"mean_token_accuracy": 0.1142148919403553,
|
|
"num_tokens": 890807.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.467933511734008,
|
|
"epoch": 0.037463976945244955,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.824,
|
|
"mean_token_accuracy": 0.11662854552268982,
|
|
"num_tokens": 901759.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.318777418136596,
|
|
"epoch": 0.037944284341978864,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7487,
|
|
"mean_token_accuracy": 0.1253423847258091,
|
|
"num_tokens": 912212.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.409648275375366,
|
|
"epoch": 0.03842459173871278,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.851,
|
|
"mean_token_accuracy": 0.1168945498764515,
|
|
"num_tokens": 923947.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.329876947402954,
|
|
"epoch": 0.03890489913544669,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.7936,
|
|
"mean_token_accuracy": 0.1201321728527546,
|
|
"num_tokens": 935732.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.254326105117798,
|
|
"epoch": 0.0393852065321806,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7414,
|
|
"mean_token_accuracy": 0.1142658345401287,
|
|
"num_tokens": 948261.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.434876155853272,
|
|
"epoch": 0.039865513928914506,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.8486,
|
|
"mean_token_accuracy": 0.12036997452378273,
|
|
"num_tokens": 959574.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.29233832359314,
|
|
"epoch": 0.040345821325648415,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.9081,
|
|
"mean_token_accuracy": 0.11429130733013153,
|
|
"num_tokens": 970329.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.388989067077636,
|
|
"epoch": 0.040826128722382324,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7648,
|
|
"mean_token_accuracy": 0.12700393423438072,
|
|
"num_tokens": 982037.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.1995869159698485,
|
|
"epoch": 0.04130643611911623,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.7255,
|
|
"mean_token_accuracy": 0.11979713216423989,
|
|
"num_tokens": 994612.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.330949687957764,
|
|
"epoch": 0.04178674351585014,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.8381,
|
|
"mean_token_accuracy": 0.12672944292426108,
|
|
"num_tokens": 1005960.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.2600654602050785,
|
|
"epoch": 0.04226705091258405,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7001,
|
|
"mean_token_accuracy": 0.1206528477370739,
|
|
"num_tokens": 1017618.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.283382511138916,
|
|
"epoch": 0.042747358309317966,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7395,
|
|
"mean_token_accuracy": 0.12196639478206635,
|
|
"num_tokens": 1029307.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.244419002532959,
|
|
"epoch": 0.043227665706051875,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.7559,
|
|
"mean_token_accuracy": 0.11804269179701805,
|
|
"num_tokens": 1042027.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.249811124801636,
|
|
"epoch": 0.043707973102785784,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.7648,
|
|
"mean_token_accuracy": 0.11966601833701133,
|
|
"num_tokens": 1053125.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.156477594375611,
|
|
"epoch": 0.04418828049951969,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7438,
|
|
"mean_token_accuracy": 0.12282297015190125,
|
|
"num_tokens": 1064908.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.249273777008057,
|
|
"epoch": 0.0446685878962536,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.6219,
|
|
"mean_token_accuracy": 0.12831630930304527,
|
|
"num_tokens": 1076328.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.203511905670166,
|
|
"epoch": 0.04514889529298751,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8416,
|
|
"mean_token_accuracy": 0.11294705122709274,
|
|
"num_tokens": 1088469.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.142552328109741,
|
|
"epoch": 0.04562920268972142,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.6489,
|
|
"mean_token_accuracy": 0.12703610360622405,
|
|
"num_tokens": 1099408.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.071178340911866,
|
|
"epoch": 0.04610951008645533,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.5735,
|
|
"mean_token_accuracy": 0.131545989215374,
|
|
"num_tokens": 1111101.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.069411039352417,
|
|
"epoch": 0.046589817483189244,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.5925,
|
|
"mean_token_accuracy": 0.1311088353395462,
|
|
"num_tokens": 1122877.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.144361734390259,
|
|
"epoch": 0.04707012487992315,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.6995,
|
|
"mean_token_accuracy": 0.11579547598958015,
|
|
"num_tokens": 1133956.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.092379188537597,
|
|
"epoch": 0.04755043227665706,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.5997,
|
|
"mean_token_accuracy": 0.12872846126556398,
|
|
"num_tokens": 1146101.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.134016275405884,
|
|
"epoch": 0.04803073967339097,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6909,
|
|
"mean_token_accuracy": 0.1324249878525734,
|
|
"num_tokens": 1157432.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.112411451339722,
|
|
"epoch": 0.04851104707012488,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6805,
|
|
"mean_token_accuracy": 0.12597657218575478,
|
|
"num_tokens": 1167601.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.080900621414185,
|
|
"epoch": 0.04899135446685879,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.5746,
|
|
"mean_token_accuracy": 0.1313086122274399,
|
|
"num_tokens": 1178818.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.224948310852051,
|
|
"epoch": 0.0494716618635927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.8153,
|
|
"mean_token_accuracy": 0.12766674906015396,
|
|
"num_tokens": 1189977.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.031567239761353,
|
|
"epoch": 0.049951969260326606,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6461,
|
|
"mean_token_accuracy": 0.13004279211163522,
|
|
"num_tokens": 1201039.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.180213594436646,
|
|
"epoch": 0.05043227665706052,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6694,
|
|
"mean_token_accuracy": 0.13014231398701667,
|
|
"num_tokens": 1212573.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.090188646316529,
|
|
"epoch": 0.05091258405379443,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6139,
|
|
"mean_token_accuracy": 0.1312407836318016,
|
|
"num_tokens": 1223382.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.126926517486572,
|
|
"epoch": 0.05139289145052834,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6812,
|
|
"mean_token_accuracy": 0.13135352060198785,
|
|
"num_tokens": 1236501.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.070159816741944,
|
|
"epoch": 0.05187319884726225,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6779,
|
|
"mean_token_accuracy": 0.12742857187986373,
|
|
"num_tokens": 1246798.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.063770055770874,
|
|
"epoch": 0.05235350624399616,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.601,
|
|
"mean_token_accuracy": 0.13103493079543113,
|
|
"num_tokens": 1258182.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.035881757736206,
|
|
"epoch": 0.052833813640730067,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.5479,
|
|
"mean_token_accuracy": 0.12442576736211777,
|
|
"num_tokens": 1270273.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.987351989746093,
|
|
"epoch": 0.053314121037463975,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.6115,
|
|
"mean_token_accuracy": 0.1252695493400097,
|
|
"num_tokens": 1281136.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.070683813095092,
|
|
"epoch": 0.053794428434197884,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.5936,
|
|
"mean_token_accuracy": 0.12710341513156892,
|
|
"num_tokens": 1294488.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.9461894035339355,
|
|
"epoch": 0.05427473583093179,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.5271,
|
|
"mean_token_accuracy": 0.12947569712996482,
|
|
"num_tokens": 1304113.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.051584100723266,
|
|
"epoch": 0.05475504322766571,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.5709,
|
|
"mean_token_accuracy": 0.13638901486992835,
|
|
"num_tokens": 1315417.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.921914052963257,
|
|
"epoch": 0.05523535062439962,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.533,
|
|
"mean_token_accuracy": 0.13163114339113235,
|
|
"num_tokens": 1328084.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.019269561767578,
|
|
"epoch": 0.05571565802113353,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.687,
|
|
"mean_token_accuracy": 0.13050052151083946,
|
|
"num_tokens": 1338696.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.040796899795533,
|
|
"epoch": 0.056195965417867436,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6282,
|
|
"mean_token_accuracy": 0.12728999853134154,
|
|
"num_tokens": 1350240.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.014576768875122,
|
|
"epoch": 0.056676272814601344,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.5687,
|
|
"mean_token_accuracy": 0.1278102345764637,
|
|
"num_tokens": 1361720.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.951624011993408,
|
|
"epoch": 0.05715658021133525,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5698,
|
|
"mean_token_accuracy": 0.13706584498286248,
|
|
"num_tokens": 1373286.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.970668458938599,
|
|
"epoch": 0.05763688760806916,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.5226,
|
|
"mean_token_accuracy": 0.12837623208761215,
|
|
"num_tokens": 1384274.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.928129005432129,
|
|
"epoch": 0.05811719500480307,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.5685,
|
|
"mean_token_accuracy": 0.1299145996570587,
|
|
"num_tokens": 1395355.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.85921688079834,
|
|
"epoch": 0.05859750240153699,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.4921,
|
|
"mean_token_accuracy": 0.13815943896770477,
|
|
"num_tokens": 1406664.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.0746745586395265,
|
|
"epoch": 0.059077809798270896,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6592,
|
|
"mean_token_accuracy": 0.12862858772277833,
|
|
"num_tokens": 1418450.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.919266176223755,
|
|
"epoch": 0.059558117195004805,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.5555,
|
|
"mean_token_accuracy": 0.13008297383785247,
|
|
"num_tokens": 1430048.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.971873044967651,
|
|
"epoch": 0.060038424591738714,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5905,
|
|
"mean_token_accuracy": 0.12921996414661407,
|
|
"num_tokens": 1441820.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.887925004959106,
|
|
"epoch": 0.06051873198847262,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.4336,
|
|
"mean_token_accuracy": 0.1331394538283348,
|
|
"num_tokens": 1453209.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.868549394607544,
|
|
"epoch": 0.06099903938520653,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.4539,
|
|
"mean_token_accuracy": 0.1323256403207779,
|
|
"num_tokens": 1465423.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.915077447891235,
|
|
"epoch": 0.06147934678194044,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.4443,
|
|
"mean_token_accuracy": 0.1385464273393154,
|
|
"num_tokens": 1476575.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.748648643493652,
|
|
"epoch": 0.06195965417867435,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.4001,
|
|
"mean_token_accuracy": 0.13120974749326705,
|
|
"num_tokens": 1486932.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.933510446548462,
|
|
"epoch": 0.06243996157540826,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4429,
|
|
"mean_token_accuracy": 0.13331692218780516,
|
|
"num_tokens": 1498494.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.856443071365357,
|
|
"epoch": 0.06292026897214217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.4923,
|
|
"mean_token_accuracy": 0.1305932119488716,
|
|
"num_tokens": 1509937.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.934806203842163,
|
|
"epoch": 0.06340057636887608,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5179,
|
|
"mean_token_accuracy": 0.14017625749111176,
|
|
"num_tokens": 1519823.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.8656535148620605,
|
|
"epoch": 0.06388088376560999,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5463,
|
|
"mean_token_accuracy": 0.1294463723897934,
|
|
"num_tokens": 1529943.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.814459609985351,
|
|
"epoch": 0.0643611911623439,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.3731,
|
|
"mean_token_accuracy": 0.14023564606904984,
|
|
"num_tokens": 1540618.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.802310371398926,
|
|
"epoch": 0.06484149855907781,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.4921,
|
|
"mean_token_accuracy": 0.12996583580970764,
|
|
"num_tokens": 1553208.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.938099765777588,
|
|
"epoch": 0.06532180595581172,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4714,
|
|
"mean_token_accuracy": 0.14118467569351195,
|
|
"num_tokens": 1563975.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.912463045120239,
|
|
"epoch": 0.06580211335254563,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.5185,
|
|
"mean_token_accuracy": 0.13118280842900276,
|
|
"num_tokens": 1575998.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.780094909667969,
|
|
"epoch": 0.06628242074927954,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4184,
|
|
"mean_token_accuracy": 0.14230406507849694,
|
|
"num_tokens": 1586041.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.827849006652832,
|
|
"epoch": 0.06676272814601344,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4684,
|
|
"mean_token_accuracy": 0.13458749651908875,
|
|
"num_tokens": 1597531.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.795176601409912,
|
|
"epoch": 0.06724303554274735,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.4518,
|
|
"mean_token_accuracy": 0.1343138784170151,
|
|
"num_tokens": 1609255.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.759337377548218,
|
|
"epoch": 0.06772334293948126,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4421,
|
|
"mean_token_accuracy": 0.13904302567243576,
|
|
"num_tokens": 1621098.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.774127531051636,
|
|
"epoch": 0.06820365033621517,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.14766101837158202,
|
|
"num_tokens": 1631941.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.74300217628479,
|
|
"epoch": 0.0686839577329491,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.3446,
|
|
"mean_token_accuracy": 0.1429346315562725,
|
|
"num_tokens": 1643117.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.714703035354614,
|
|
"epoch": 0.069164265129683,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.3839,
|
|
"mean_token_accuracy": 0.13676466047763824,
|
|
"num_tokens": 1653595.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.830532836914062,
|
|
"epoch": 0.06964457252641691,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4213,
|
|
"mean_token_accuracy": 0.13829002231359483,
|
|
"num_tokens": 1664495.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.722404527664184,
|
|
"epoch": 0.07012487992315082,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.4066,
|
|
"mean_token_accuracy": 0.13997879922389983,
|
|
"num_tokens": 1674923.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.769494438171387,
|
|
"epoch": 0.07060518731988473,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.2971,
|
|
"mean_token_accuracy": 0.14468497931957244,
|
|
"num_tokens": 1685904.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.729282712936401,
|
|
"epoch": 0.07108549471661864,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5209,
|
|
"mean_token_accuracy": 0.1288589984178543,
|
|
"num_tokens": 1699133.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.7413102149963375,
|
|
"epoch": 0.07156580211335255,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3281,
|
|
"mean_token_accuracy": 0.13741401731967925,
|
|
"num_tokens": 1711559.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.672541761398316,
|
|
"epoch": 0.07204610951008646,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.2503,
|
|
"mean_token_accuracy": 0.1432784304022789,
|
|
"num_tokens": 1722526.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.6785728454589846,
|
|
"epoch": 0.07252641690682037,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.3132,
|
|
"mean_token_accuracy": 0.13960239216685294,
|
|
"num_tokens": 1734261.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.65572600364685,
|
|
"epoch": 0.07300672430355427,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.3011,
|
|
"mean_token_accuracy": 0.14777525439858435,
|
|
"num_tokens": 1745151.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.867705583572388,
|
|
"epoch": 0.07348703170028818,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4582,
|
|
"mean_token_accuracy": 0.14053600579500197,
|
|
"num_tokens": 1755463.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.743470144271851,
|
|
"epoch": 0.07396733909702209,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.4049,
|
|
"mean_token_accuracy": 0.13823116198182106,
|
|
"num_tokens": 1767717.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.601284313201904,
|
|
"epoch": 0.074447646493756,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.2542,
|
|
"mean_token_accuracy": 0.14758941754698754,
|
|
"num_tokens": 1779115.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.523760461807251,
|
|
"epoch": 0.07492795389048991,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.2018,
|
|
"mean_token_accuracy": 0.14831501990556717,
|
|
"num_tokens": 1789644.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.752778768539429,
|
|
"epoch": 0.07540826128722382,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.4227,
|
|
"mean_token_accuracy": 0.14102208092808724,
|
|
"num_tokens": 1800606.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.677890968322754,
|
|
"epoch": 0.07588856868395773,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.4269,
|
|
"mean_token_accuracy": 0.13399276584386827,
|
|
"num_tokens": 1812168.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.844178104400635,
|
|
"epoch": 0.07636887608069164,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.3673,
|
|
"mean_token_accuracy": 0.13583303466439248,
|
|
"num_tokens": 1823830.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.592782688140869,
|
|
"epoch": 0.07684918347742556,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.3581,
|
|
"mean_token_accuracy": 0.14064425751566886,
|
|
"num_tokens": 1835611.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.721078968048095,
|
|
"epoch": 0.07732949087415947,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.4246,
|
|
"mean_token_accuracy": 0.13046615198254585,
|
|
"num_tokens": 1847036.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.640185070037842,
|
|
"epoch": 0.07780979827089338,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3494,
|
|
"mean_token_accuracy": 0.13754188790917396,
|
|
"num_tokens": 1857476.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.721815967559815,
|
|
"epoch": 0.07829010566762729,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.373,
|
|
"mean_token_accuracy": 0.1429060995578766,
|
|
"num_tokens": 1869073.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.464849758148193,
|
|
"epoch": 0.0787704130643612,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.2412,
|
|
"mean_token_accuracy": 0.14811026602983474,
|
|
"num_tokens": 1880439.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.810800933837891,
|
|
"epoch": 0.0792507204610951,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4175,
|
|
"mean_token_accuracy": 0.13784201666712761,
|
|
"num_tokens": 1891600.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.659660720825196,
|
|
"epoch": 0.07973102785782901,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3795,
|
|
"mean_token_accuracy": 0.14037746116518973,
|
|
"num_tokens": 1903126.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.764267301559448,
|
|
"epoch": 0.08021133525456292,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3437,
|
|
"mean_token_accuracy": 0.14527037143707275,
|
|
"num_tokens": 1913913.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.566430568695068,
|
|
"epoch": 0.08069164265129683,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.2667,
|
|
"mean_token_accuracy": 0.14265700429677963,
|
|
"num_tokens": 1924961.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.74987416267395,
|
|
"epoch": 0.08117195004803074,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3443,
|
|
"mean_token_accuracy": 0.13290713876485824,
|
|
"num_tokens": 1936773.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.521253681182861,
|
|
"epoch": 0.08165225744476465,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2669,
|
|
"mean_token_accuracy": 0.14235577881336212,
|
|
"num_tokens": 1948190.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.609525537490844,
|
|
"epoch": 0.08213256484149856,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.2573,
|
|
"mean_token_accuracy": 0.14473007172346114,
|
|
"num_tokens": 1960038.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.668189859390258,
|
|
"epoch": 0.08261287223823247,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.14037344232201576,
|
|
"num_tokens": 1970535.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.6438507556915285,
|
|
"epoch": 0.08309317963496637,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.3179,
|
|
"mean_token_accuracy": 0.1358397677540779,
|
|
"num_tokens": 1981386.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.555328369140625,
|
|
"epoch": 0.08357348703170028,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.14654369950294494,
|
|
"num_tokens": 1993196.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.608275127410889,
|
|
"epoch": 0.08405379442843419,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.2625,
|
|
"mean_token_accuracy": 0.15001987367868425,
|
|
"num_tokens": 2004756.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.563670921325683,
|
|
"epoch": 0.0845341018251681,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2449,
|
|
"mean_token_accuracy": 0.14094123244285583,
|
|
"num_tokens": 2016020.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.522834205627442,
|
|
"epoch": 0.08501440922190202,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.288,
|
|
"mean_token_accuracy": 0.14180351421236992,
|
|
"num_tokens": 2027747.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.644138765335083,
|
|
"epoch": 0.08549471661863593,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.2648,
|
|
"mean_token_accuracy": 0.1389330357313156,
|
|
"num_tokens": 2038841.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.5890850067138675,
|
|
"epoch": 0.08597502401536984,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3071,
|
|
"mean_token_accuracy": 0.13798698037862778,
|
|
"num_tokens": 2049905.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.653052091598511,
|
|
"epoch": 0.08645533141210375,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3869,
|
|
"mean_token_accuracy": 0.13413772657513617,
|
|
"num_tokens": 2062492.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.5456493377685545,
|
|
"epoch": 0.08693563880883766,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.3093,
|
|
"mean_token_accuracy": 0.13950769752264022,
|
|
"num_tokens": 2073840.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.569193363189697,
|
|
"epoch": 0.08741594620557157,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2225,
|
|
"mean_token_accuracy": 0.14058948308229446,
|
|
"num_tokens": 2085720.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.613348484039307,
|
|
"epoch": 0.08789625360230548,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3019,
|
|
"mean_token_accuracy": 0.14243812635540962,
|
|
"num_tokens": 2096649.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.631076240539551,
|
|
"epoch": 0.08837656099903939,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3033,
|
|
"mean_token_accuracy": 0.14374962896108628,
|
|
"num_tokens": 2109030.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.521146059036255,
|
|
"epoch": 0.0888568683957733,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.2097,
|
|
"mean_token_accuracy": 0.14402098059654236,
|
|
"num_tokens": 2121384.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.506090831756592,
|
|
"epoch": 0.0893371757925072,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.1669,
|
|
"mean_token_accuracy": 0.15031797289848328,
|
|
"num_tokens": 2131377.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.554385089874268,
|
|
"epoch": 0.08981748318924111,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.3537,
|
|
"mean_token_accuracy": 0.13973637223243712,
|
|
"num_tokens": 2142364.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.5829205989837645,
|
|
"epoch": 0.09029779058597502,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.14725347831845284,
|
|
"num_tokens": 2153040.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.523045444488526,
|
|
"epoch": 0.09077809798270893,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.2703,
|
|
"mean_token_accuracy": 0.14759753867983819,
|
|
"num_tokens": 2165571.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.537745571136474,
|
|
"epoch": 0.09125840537944284,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2456,
|
|
"mean_token_accuracy": 0.14311620220541954,
|
|
"num_tokens": 2177241.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.572008037567139,
|
|
"epoch": 0.09173871277617675,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2812,
|
|
"mean_token_accuracy": 0.13619020357728004,
|
|
"num_tokens": 2187475.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.5255202293396,
|
|
"epoch": 0.09221902017291066,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3112,
|
|
"mean_token_accuracy": 0.14339686632156373,
|
|
"num_tokens": 2198185.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.506760311126709,
|
|
"epoch": 0.09269932756964457,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2432,
|
|
"mean_token_accuracy": 0.145152947306633,
|
|
"num_tokens": 2210404.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.614426374435425,
|
|
"epoch": 0.09317963496637849,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2227,
|
|
"mean_token_accuracy": 0.1446111634373665,
|
|
"num_tokens": 2222188.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.4725706577301025,
|
|
"epoch": 0.0936599423631124,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.2734,
|
|
"mean_token_accuracy": 0.14453680962324142,
|
|
"num_tokens": 2233418.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.50886721611023,
|
|
"epoch": 0.0941402497598463,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2401,
|
|
"mean_token_accuracy": 0.1501119926571846,
|
|
"num_tokens": 2245053.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.550162982940674,
|
|
"epoch": 0.09462055715658022,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2607,
|
|
"mean_token_accuracy": 0.14686937928199767,
|
|
"num_tokens": 2256375.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.408747339248658,
|
|
"epoch": 0.09510086455331412,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.1015,
|
|
"mean_token_accuracy": 0.14864389300346376,
|
|
"num_tokens": 2267074.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.412355279922485,
|
|
"epoch": 0.09558117195004803,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.1563,
|
|
"mean_token_accuracy": 0.15030216574668884,
|
|
"num_tokens": 2277168.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.463335084915161,
|
|
"epoch": 0.09606147934678194,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.1421,
|
|
"mean_token_accuracy": 0.15055060535669326,
|
|
"num_tokens": 2288178.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.375842523574829,
|
|
"epoch": 0.09654178674351585,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999983283737,
|
|
"loss": 6.1518,
|
|
"mean_token_accuracy": 0.14721509963274002,
|
|
"num_tokens": 2299765.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.613855504989624,
|
|
"epoch": 0.09702209414024976,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999999915373924,
|
|
"loss": 6.2717,
|
|
"mean_token_accuracy": 0.1355791248381138,
|
|
"num_tokens": 2312047.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.423848724365234,
|
|
"epoch": 0.09750240153698367,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999999795225793,
|
|
"loss": 6.2421,
|
|
"mean_token_accuracy": 0.13908444195985795,
|
|
"num_tokens": 2324118.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.541734027862549,
|
|
"epoch": 0.09798270893371758,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999999622839347,
|
|
"loss": 6.2441,
|
|
"mean_token_accuracy": 0.14666304737329483,
|
|
"num_tokens": 2335171.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.506129121780395,
|
|
"epoch": 0.09846301633045149,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999999398214593,
|
|
"loss": 6.1528,
|
|
"mean_token_accuracy": 0.14639462679624557,
|
|
"num_tokens": 2346338.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.4336082458496096,
|
|
"epoch": 0.0989433237271854,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999999121351532,
|
|
"loss": 6.1809,
|
|
"mean_token_accuracy": 0.1509660616517067,
|
|
"num_tokens": 2357185.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.422454690933227,
|
|
"epoch": 0.0994236311239193,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999998792250173,
|
|
"loss": 6.1198,
|
|
"mean_token_accuracy": 0.1525423288345337,
|
|
"num_tokens": 2368494.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.528336238861084,
|
|
"epoch": 0.09990393852065321,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999998410910524,
|
|
"loss": 6.318,
|
|
"mean_token_accuracy": 0.13721144571900368,
|
|
"num_tokens": 2380800.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.4995053768157955,
|
|
"epoch": 0.10038424591738712,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999997977332592,
|
|
"loss": 6.2573,
|
|
"mean_token_accuracy": 0.1406011924147606,
|
|
"num_tokens": 2391753.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.355279207229614,
|
|
"epoch": 0.10086455331412104,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999997491516389,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.14223827719688414,
|
|
"num_tokens": 2403324.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.485898113250732,
|
|
"epoch": 0.10134486071085495,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999996953461925,
|
|
"loss": 6.2381,
|
|
"mean_token_accuracy": 0.14303919151425362,
|
|
"num_tokens": 2414873.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.298157644271851,
|
|
"epoch": 0.10182516810758886,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999996363169212,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.15766309648752214,
|
|
"num_tokens": 2425308.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.33884563446045,
|
|
"epoch": 0.10230547550432277,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999995720638266,
|
|
"loss": 6.0714,
|
|
"mean_token_accuracy": 0.15607305616140366,
|
|
"num_tokens": 2436835.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.4138219356536865,
|
|
"epoch": 0.10278578290105668,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00049999950258691,
|
|
"loss": 6.1795,
|
|
"mean_token_accuracy": 0.14858196377754213,
|
|
"num_tokens": 2446798.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.343221044540405,
|
|
"epoch": 0.10326609029779059,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999994278861731,
|
|
"loss": 6.0823,
|
|
"mean_token_accuracy": 0.1503281533718109,
|
|
"num_tokens": 2457308.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.410136365890503,
|
|
"epoch": 0.1037463976945245,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999993479616175,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.14141261354088783,
|
|
"num_tokens": 2468917.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.4494935989379885,
|
|
"epoch": 0.1042267050912584,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999992628132451,
|
|
"loss": 6.1666,
|
|
"mean_token_accuracy": 0.14505101442337037,
|
|
"num_tokens": 2481363.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.386939859390258,
|
|
"epoch": 0.10470701248799232,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999991724410582,
|
|
"loss": 6.1591,
|
|
"mean_token_accuracy": 0.14499209821224213,
|
|
"num_tokens": 2493082.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.401579475402832,
|
|
"epoch": 0.10518731988472622,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999990768450583,
|
|
"loss": 6.1193,
|
|
"mean_token_accuracy": 0.14764227569103242,
|
|
"num_tokens": 2503849.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.376060819625854,
|
|
"epoch": 0.10566762728146013,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999989760252482,
|
|
"loss": 6.1642,
|
|
"mean_token_accuracy": 0.14896273389458656,
|
|
"num_tokens": 2514528.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.361701393127442,
|
|
"epoch": 0.10614793467819404,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999988699816299,
|
|
"loss": 6.1386,
|
|
"mean_token_accuracy": 0.15386009961366653,
|
|
"num_tokens": 2524971.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.2997602939605715,
|
|
"epoch": 0.10662824207492795,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999987587142058,
|
|
"loss": 6.0389,
|
|
"mean_token_accuracy": 0.1510354369878769,
|
|
"num_tokens": 2535674.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.495864677429199,
|
|
"epoch": 0.10710854947166186,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999986422229789,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.13760789409279822,
|
|
"num_tokens": 2547108.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.3444905281066895,
|
|
"epoch": 0.10758885686839577,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999985205079514,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.14668779224157333,
|
|
"num_tokens": 2559474.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.281940221786499,
|
|
"epoch": 0.10806916426512968,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999983935691265,
|
|
"loss": 5.9473,
|
|
"mean_token_accuracy": 0.16225168406963347,
|
|
"num_tokens": 2571264.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.2712925434112545,
|
|
"epoch": 0.10854947166186359,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499998261406507,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.1521009087562561,
|
|
"num_tokens": 2583731.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.588572835922241,
|
|
"epoch": 0.10902977905859751,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999981240200958,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.1474340245127678,
|
|
"num_tokens": 2595497.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.184768009185791,
|
|
"epoch": 0.10951008645533142,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999979814098966,
|
|
"loss": 6.1175,
|
|
"mean_token_accuracy": 0.15334238335490227,
|
|
"num_tokens": 2607358.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.4007182121276855,
|
|
"epoch": 0.10999039385206533,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999978335759121,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.15680247992277146,
|
|
"num_tokens": 2618936.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.322919797897339,
|
|
"epoch": 0.11047070124879924,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999976805181461,
|
|
"loss": 6.1873,
|
|
"mean_token_accuracy": 0.1458278477191925,
|
|
"num_tokens": 2631840.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.365493202209473,
|
|
"epoch": 0.11095100864553314,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499997522236602,
|
|
"loss": 6.138,
|
|
"mean_token_accuracy": 0.15330254882574082,
|
|
"num_tokens": 2642412.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.349469995498657,
|
|
"epoch": 0.11143131604226705,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999973587312837,
|
|
"loss": 6.1062,
|
|
"mean_token_accuracy": 0.14750108644366264,
|
|
"num_tokens": 2653890.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.458298873901367,
|
|
"epoch": 0.11191162343900096,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999971900021947,
|
|
"loss": 6.1649,
|
|
"mean_token_accuracy": 0.1521790385246277,
|
|
"num_tokens": 2664888.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.242096948623657,
|
|
"epoch": 0.11239193083573487,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999970160493391,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.14765168353915215,
|
|
"num_tokens": 2675550.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.323576927185059,
|
|
"epoch": 0.11287223823246878,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999968368727209,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.15634231716394426,
|
|
"num_tokens": 2688022.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.322928762435913,
|
|
"epoch": 0.11335254562920269,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999966524723442,
|
|
"loss": 6.0667,
|
|
"mean_token_accuracy": 0.15129867494106292,
|
|
"num_tokens": 2698737.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.321136522293091,
|
|
"epoch": 0.1138328530259366,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999964628482135,
|
|
"loss": 6.0445,
|
|
"mean_token_accuracy": 0.15983350723981857,
|
|
"num_tokens": 2709844.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.330933856964111,
|
|
"epoch": 0.1143131604226705,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999962680003328,
|
|
"loss": 6.0873,
|
|
"mean_token_accuracy": 0.1584131069481373,
|
|
"num_tokens": 2720273.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.310527086257935,
|
|
"epoch": 0.11479346781940442,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499996067928707,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.14796678125858306,
|
|
"num_tokens": 2731354.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.2873091220855715,
|
|
"epoch": 0.11527377521613832,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999958626333406,
|
|
"loss": 6.0851,
|
|
"mean_token_accuracy": 0.15372786819934844,
|
|
"num_tokens": 2742966.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.31016173362732,
|
|
"epoch": 0.11575408261287223,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999956521142383,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.1610312283039093,
|
|
"num_tokens": 2755010.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.299917507171631,
|
|
"epoch": 0.11623439000960614,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999954363714051,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.1533173903822899,
|
|
"num_tokens": 2766176.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.396469974517823,
|
|
"epoch": 0.11671469740634005,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999952154048459,
|
|
"loss": 6.1947,
|
|
"mean_token_accuracy": 0.14717967435717583,
|
|
"num_tokens": 2777861.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.267566394805908,
|
|
"epoch": 0.11719500480307397,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499994989214566,
|
|
"loss": 6.0127,
|
|
"mean_token_accuracy": 0.15340577512979509,
|
|
"num_tokens": 2788725.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.235751724243164,
|
|
"epoch": 0.11767531219980788,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999947578005705,
|
|
"loss": 6.0311,
|
|
"mean_token_accuracy": 0.15211454331874846,
|
|
"num_tokens": 2801613.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.352841997146607,
|
|
"epoch": 0.11815561959654179,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999945211628648,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.1481211692094803,
|
|
"num_tokens": 2812474.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.22174391746521,
|
|
"epoch": 0.1186359269932757,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999942793014544,
|
|
"loss": 6.0198,
|
|
"mean_token_accuracy": 0.1554572179913521,
|
|
"num_tokens": 2823178.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.201157283782959,
|
|
"epoch": 0.11911623439000961,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499994032216345,
|
|
"loss": 6.0082,
|
|
"mean_token_accuracy": 0.15631193220615386,
|
|
"num_tokens": 2836486.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.298185110092163,
|
|
"epoch": 0.11959654178674352,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999937799075422,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.15345329195261,
|
|
"num_tokens": 2847902.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.128469324111938,
|
|
"epoch": 0.12007684918347743,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499993522375052,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.15789376199245453,
|
|
"num_tokens": 2859991.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.42838487625122,
|
|
"epoch": 0.12055715658021134,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999932596188802,
|
|
"loss": 6.1567,
|
|
"mean_token_accuracy": 0.14668479561805725,
|
|
"num_tokens": 2870269.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.199470043182373,
|
|
"epoch": 0.12103746397694524,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999929916390331,
|
|
"loss": 6.0278,
|
|
"mean_token_accuracy": 0.15147914439439775,
|
|
"num_tokens": 2882191.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.238399505615234,
|
|
"epoch": 0.12151777137367915,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999927184355169,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.15111806318163873,
|
|
"num_tokens": 2892775.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.218603134155273,
|
|
"epoch": 0.12199807877041306,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999924400083377,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.15733990743756293,
|
|
"num_tokens": 2904750.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.357618188858032,
|
|
"epoch": 0.12247838616714697,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999921563575022,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.1490491099655628,
|
|
"num_tokens": 2916150.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.287556076049805,
|
|
"epoch": 0.12295869356388088,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999918674830169,
|
|
"loss": 6.0557,
|
|
"mean_token_accuracy": 0.15047229453921318,
|
|
"num_tokens": 2928452.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.229531908035279,
|
|
"epoch": 0.12343900096061479,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999915733848886,
|
|
"loss": 6.052,
|
|
"mean_token_accuracy": 0.14816432297229767,
|
|
"num_tokens": 2940577.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.193968200683594,
|
|
"epoch": 0.1239193083573487,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499991274063124,
|
|
"loss": 6.0271,
|
|
"mean_token_accuracy": 0.15466209426522254,
|
|
"num_tokens": 2952302.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.348705244064331,
|
|
"epoch": 0.12439961575408261,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999909695177301,
|
|
"loss": 6.0836,
|
|
"mean_token_accuracy": 0.1576863333582878,
|
|
"num_tokens": 2964611.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.245805740356445,
|
|
"epoch": 0.12487992315081652,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499990659748714,
|
|
"loss": 6.0714,
|
|
"mean_token_accuracy": 0.1507440909743309,
|
|
"num_tokens": 2975668.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.332144260406494,
|
|
"epoch": 0.12536023054755044,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999903447560828,
|
|
"loss": 6.1263,
|
|
"mean_token_accuracy": 0.15026951879262923,
|
|
"num_tokens": 2987303.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.330797815322876,
|
|
"epoch": 0.12584053794428435,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999900245398439,
|
|
"loss": 6.0264,
|
|
"mean_token_accuracy": 0.15367057919502258,
|
|
"num_tokens": 3000400.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.232060718536377,
|
|
"epoch": 0.12632084534101826,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999896991000047,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.1533641867339611,
|
|
"num_tokens": 3012336.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.258577537536621,
|
|
"epoch": 0.12680115273775217,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999893684365729,
|
|
"loss": 6.0286,
|
|
"mean_token_accuracy": 0.152130339294672,
|
|
"num_tokens": 3023004.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.220389127731323,
|
|
"epoch": 0.12728146013448607,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999890325495559,
|
|
"loss": 6.0975,
|
|
"mean_token_accuracy": 0.14989801868796349,
|
|
"num_tokens": 3035147.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.253002405166626,
|
|
"epoch": 0.12776176753121998,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999886914389617,
|
|
"loss": 5.9242,
|
|
"mean_token_accuracy": 0.15818189233541488,
|
|
"num_tokens": 3045611.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.172885894775391,
|
|
"epoch": 0.1282420749279539,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999883451047981,
|
|
"loss": 5.9499,
|
|
"mean_token_accuracy": 0.1549012377858162,
|
|
"num_tokens": 3056420.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.169215822219849,
|
|
"epoch": 0.1287223823246878,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999879935470733,
|
|
"loss": 5.9238,
|
|
"mean_token_accuracy": 0.15970174074172974,
|
|
"num_tokens": 3068770.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.298935747146606,
|
|
"epoch": 0.1292026897214217,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999876367657954,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.14842666387557985,
|
|
"num_tokens": 3080806.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.276106071472168,
|
|
"epoch": 0.12968299711815562,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999872747609725,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.1495455838739872,
|
|
"num_tokens": 3091769.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.219928741455078,
|
|
"epoch": 0.13016330451488953,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999869075326132,
|
|
"loss": 5.9957,
|
|
"mean_token_accuracy": 0.1552440881729126,
|
|
"num_tokens": 3103121.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.204897928237915,
|
|
"epoch": 0.13064361191162344,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499986535080726,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.16277382969856263,
|
|
"num_tokens": 3115606.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.145621061325073,
|
|
"epoch": 0.13112391930835735,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999861574053196,
|
|
"loss": 5.8792,
|
|
"mean_token_accuracy": 0.16227115243673323,
|
|
"num_tokens": 3127961.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.100908708572388,
|
|
"epoch": 0.13160422670509125,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999857745064027,
|
|
"loss": 5.8918,
|
|
"mean_token_accuracy": 0.16080396622419357,
|
|
"num_tokens": 3138316.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.145740222930908,
|
|
"epoch": 0.13208453410182516,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499985386383984,
|
|
"loss": 5.8898,
|
|
"mean_token_accuracy": 0.16010251343250276,
|
|
"num_tokens": 3150818.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.221674299240112,
|
|
"epoch": 0.13256484149855907,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999849930380729,
|
|
"loss": 6.0332,
|
|
"mean_token_accuracy": 0.15478831380605698,
|
|
"num_tokens": 3162066.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.167523431777954,
|
|
"epoch": 0.13304514889529298,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999845944686781,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.1528627470135689,
|
|
"num_tokens": 3172209.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.064603567123413,
|
|
"epoch": 0.1335254562920269,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999841906758093,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.16878736317157744,
|
|
"num_tokens": 3183248.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.167459440231323,
|
|
"epoch": 0.1340057636887608,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999837816594757,
|
|
"loss": 5.9321,
|
|
"mean_token_accuracy": 0.16111771613359452,
|
|
"num_tokens": 3194748.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.154092168807983,
|
|
"epoch": 0.1344860710854947,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999833674196865,
|
|
"loss": 5.8874,
|
|
"mean_token_accuracy": 0.1668296754360199,
|
|
"num_tokens": 3205669.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.156223106384277,
|
|
"epoch": 0.13496637848222862,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999829479564518,
|
|
"loss": 5.989,
|
|
"mean_token_accuracy": 0.15401702225208283,
|
|
"num_tokens": 3216035.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.196358156204224,
|
|
"epoch": 0.13544668587896252,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499982523269781,
|
|
"loss": 5.9783,
|
|
"mean_token_accuracy": 0.15676602721214294,
|
|
"num_tokens": 3227192.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.147973108291626,
|
|
"epoch": 0.13592699327569643,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999820933596842,
|
|
"loss": 6.0023,
|
|
"mean_token_accuracy": 0.15647790133953093,
|
|
"num_tokens": 3240237.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.207319927215576,
|
|
"epoch": 0.13640730067243034,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499981658226171,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.1610751822590828,
|
|
"num_tokens": 3251963.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.076681470870971,
|
|
"epoch": 0.13688760806916425,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499981217869252,
|
|
"loss": 5.9913,
|
|
"mean_token_accuracy": 0.1612226501107216,
|
|
"num_tokens": 3263101.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.216303873062134,
|
|
"epoch": 0.1373679154658982,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499980772288937,
|
|
"loss": 5.8768,
|
|
"mean_token_accuracy": 0.16368011087179185,
|
|
"num_tokens": 3275100.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.141348648071289,
|
|
"epoch": 0.1378482228626321,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999803214852367,
|
|
"loss": 5.9678,
|
|
"mean_token_accuracy": 0.15624959021806717,
|
|
"num_tokens": 3287025.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.223503255844117,
|
|
"epoch": 0.138328530259366,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999798654581613,
|
|
"loss": 5.9712,
|
|
"mean_token_accuracy": 0.1579916626214981,
|
|
"num_tokens": 3299867.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.127595090866089,
|
|
"epoch": 0.13880883765609991,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999794042077214,
|
|
"loss": 5.9159,
|
|
"mean_token_accuracy": 0.1553739383816719,
|
|
"num_tokens": 3311183.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.166766166687012,
|
|
"epoch": 0.13928914505283382,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999789377339279,
|
|
"loss": 5.9827,
|
|
"mean_token_accuracy": 0.15575652718544006,
|
|
"num_tokens": 3322247.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.165034675598145,
|
|
"epoch": 0.13976945244956773,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999784660367915,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.1582799434661865,
|
|
"num_tokens": 3333369.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.110639047622681,
|
|
"epoch": 0.14024975984630164,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999779891163231,
|
|
"loss": 5.9384,
|
|
"mean_token_accuracy": 0.15631188750267028,
|
|
"num_tokens": 3345876.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.116653394699097,
|
|
"epoch": 0.14073006724303555,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999775069725339,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.1637310653924942,
|
|
"num_tokens": 3357323.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.105227518081665,
|
|
"epoch": 0.14121037463976946,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499977019605435,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.160066157579422,
|
|
"num_tokens": 3367689.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.980920314788818,
|
|
"epoch": 0.14169068203650337,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999765270150378,
|
|
"loss": 5.8722,
|
|
"mean_token_accuracy": 0.16156274527311326,
|
|
"num_tokens": 3379472.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.227704000473023,
|
|
"epoch": 0.14217098943323728,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999760292013536,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.15907305255532264,
|
|
"num_tokens": 3390929.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.240896797180175,
|
|
"epoch": 0.14265129682997119,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999755261643941,
|
|
"loss": 5.9174,
|
|
"mean_token_accuracy": 0.16511183232069016,
|
|
"num_tokens": 3401242.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.003513145446777,
|
|
"epoch": 0.1431316042267051,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999750179041709,
|
|
"loss": 5.9087,
|
|
"mean_token_accuracy": 0.15776129364967345,
|
|
"num_tokens": 3411169.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.05569019317627,
|
|
"epoch": 0.143611911623439,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999745044206959,
|
|
"loss": 5.7394,
|
|
"mean_token_accuracy": 0.1670708954334259,
|
|
"num_tokens": 3423265.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.043114852905274,
|
|
"epoch": 0.1440922190201729,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999739857139809,
|
|
"loss": 5.8494,
|
|
"mean_token_accuracy": 0.1674238234758377,
|
|
"num_tokens": 3434793.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.026560688018799,
|
|
"epoch": 0.14457252641690682,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499973461784038,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.1741930678486824,
|
|
"num_tokens": 3445732.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.085477066040039,
|
|
"epoch": 0.14505283381364073,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999729326308792,
|
|
"loss": 5.9612,
|
|
"mean_token_accuracy": 0.15714176446199418,
|
|
"num_tokens": 3457090.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.235566902160644,
|
|
"epoch": 0.14553314121037464,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499972398254517,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.15230439007282257,
|
|
"num_tokens": 3468087.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.1251365661621096,
|
|
"epoch": 0.14601344860710855,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499971858654964,
|
|
"loss": 5.8869,
|
|
"mean_token_accuracy": 0.1600414589047432,
|
|
"num_tokens": 3478820.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.028464698791504,
|
|
"epoch": 0.14649375600384246,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999713138322321,
|
|
"loss": 5.9044,
|
|
"mean_token_accuracy": 0.15837728679180146,
|
|
"num_tokens": 3489878.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.158157634735107,
|
|
"epoch": 0.14697406340057637,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999707637863346,
|
|
"loss": 5.8931,
|
|
"mean_token_accuracy": 0.16006086468696595,
|
|
"num_tokens": 3500944.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.039820289611816,
|
|
"epoch": 0.14745437079731027,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999702085172838,
|
|
"loss": 5.8805,
|
|
"mean_token_accuracy": 0.16458703875541686,
|
|
"num_tokens": 3511383.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.116418266296387,
|
|
"epoch": 0.14793467819404418,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999696480250929,
|
|
"loss": 5.9682,
|
|
"mean_token_accuracy": 0.1588382303714752,
|
|
"num_tokens": 3523300.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.157420682907104,
|
|
"epoch": 0.1484149855907781,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999690823097747,
|
|
"loss": 5.8922,
|
|
"mean_token_accuracy": 0.15603983476758004,
|
|
"num_tokens": 3534371.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.085301923751831,
|
|
"epoch": 0.148895292987512,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999685113713426,
|
|
"loss": 5.8566,
|
|
"mean_token_accuracy": 0.1630222499370575,
|
|
"num_tokens": 3544847.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.091690015792847,
|
|
"epoch": 0.1493756003842459,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999679352098096,
|
|
"loss": 5.8394,
|
|
"mean_token_accuracy": 0.1639106124639511,
|
|
"num_tokens": 3555859.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.032490921020508,
|
|
"epoch": 0.14985590778097982,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999673538251891,
|
|
"loss": 5.8622,
|
|
"mean_token_accuracy": 0.16305326968431472,
|
|
"num_tokens": 3568283.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.074030351638794,
|
|
"epoch": 0.15033621517771373,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999667672174947,
|
|
"loss": 5.9212,
|
|
"mean_token_accuracy": 0.15798406153917313,
|
|
"num_tokens": 3581442.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.221883392333984,
|
|
"epoch": 0.15081652257444764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049996617538674,
|
|
"loss": 5.9677,
|
|
"mean_token_accuracy": 0.15445063039660453,
|
|
"num_tokens": 3594055.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.099120283126831,
|
|
"epoch": 0.15129682997118155,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999655783329386,
|
|
"loss": 5.9341,
|
|
"mean_token_accuracy": 0.1539287731051445,
|
|
"num_tokens": 3605952.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.155495500564575,
|
|
"epoch": 0.15177713736791545,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999649760561046,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.1572701022028923,
|
|
"num_tokens": 3618544.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.109302043914795,
|
|
"epoch": 0.15225744476464936,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999643685562519,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.1646600529551506,
|
|
"num_tokens": 3630445.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.1016254901885985,
|
|
"epoch": 0.15273775216138327,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999637558333945,
|
|
"loss": 5.9039,
|
|
"mean_token_accuracy": 0.16291006058454513,
|
|
"num_tokens": 3642516.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.074013328552246,
|
|
"epoch": 0.15321805955811718,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999631378875467,
|
|
"loss": 5.8209,
|
|
"mean_token_accuracy": 0.16821238100528718,
|
|
"num_tokens": 3654425.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.979668712615966,
|
|
"epoch": 0.15369836695485112,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999625147187228,
|
|
"loss": 5.8486,
|
|
"mean_token_accuracy": 0.1578590378165245,
|
|
"num_tokens": 3666521.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.134301042556762,
|
|
"epoch": 0.15417867435158503,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999618863269373,
|
|
"loss": 5.8947,
|
|
"mean_token_accuracy": 0.15352863371372222,
|
|
"num_tokens": 3679121.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.100239419937134,
|
|
"epoch": 0.15465898174831894,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999612527122049,
|
|
"loss": 5.894,
|
|
"mean_token_accuracy": 0.15724605321884155,
|
|
"num_tokens": 3691095.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.060277366638184,
|
|
"epoch": 0.15513928914505284,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999606138745402,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.1618647649884224,
|
|
"num_tokens": 3703426.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.1450238704681395,
|
|
"epoch": 0.15561959654178675,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999599698139581,
|
|
"loss": 5.9336,
|
|
"mean_token_accuracy": 0.16260550543665886,
|
|
"num_tokens": 3715429.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.146528911590576,
|
|
"epoch": 0.15609990393852066,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999593205304734,
|
|
"loss": 5.9163,
|
|
"mean_token_accuracy": 0.15805355310440064,
|
|
"num_tokens": 3726327.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.100754690170288,
|
|
"epoch": 0.15658021133525457,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999586660241012,
|
|
"loss": 5.8732,
|
|
"mean_token_accuracy": 0.1542663834989071,
|
|
"num_tokens": 3736818.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.088619899749756,
|
|
"epoch": 0.15706051873198848,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999580062948569,
|
|
"loss": 5.8789,
|
|
"mean_token_accuracy": 0.16102785766124725,
|
|
"num_tokens": 3747776.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.949653625488281,
|
|
"epoch": 0.1575408261287224,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999573413427556,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.16540554612874986,
|
|
"num_tokens": 3758990.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.039187049865722,
|
|
"epoch": 0.1580211335254563,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999566711678128,
|
|
"loss": 5.8119,
|
|
"mean_token_accuracy": 0.16214931458234788,
|
|
"num_tokens": 3769686.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.065354490280152,
|
|
"epoch": 0.1585014409221902,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999559957700442,
|
|
"loss": 5.8824,
|
|
"mean_token_accuracy": 0.1635928988456726,
|
|
"num_tokens": 3781815.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.073367595672607,
|
|
"epoch": 0.15898174831892412,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999553151494653,
|
|
"loss": 5.9146,
|
|
"mean_token_accuracy": 0.16144528090953827,
|
|
"num_tokens": 3793392.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.073708391189575,
|
|
"epoch": 0.15946205571565802,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999546293060919,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.1598874419927597,
|
|
"num_tokens": 3804974.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.9182981014251705,
|
|
"epoch": 0.15994236311239193,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049995393823994,
|
|
"loss": 5.7125,
|
|
"mean_token_accuracy": 0.17333305180072783,
|
|
"num_tokens": 3817166.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.048591375350952,
|
|
"epoch": 0.16042267050912584,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999532419510255,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.16252198666334153,
|
|
"num_tokens": 3828151.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.027536058425904,
|
|
"epoch": 0.16090297790585975,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499952540439365,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.16017384976148605,
|
|
"num_tokens": 3839439.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.0826294898986815,
|
|
"epoch": 0.16138328530259366,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999518337049743,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.1598974958062172,
|
|
"num_tokens": 3851694.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.004607820510865,
|
|
"epoch": 0.16186359269932757,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049995112174787,
|
|
"loss": 5.8737,
|
|
"mean_token_accuracy": 0.16189273744821547,
|
|
"num_tokens": 3863593.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.980313777923584,
|
|
"epoch": 0.16234390009606148,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999504045680687,
|
|
"loss": 5.7892,
|
|
"mean_token_accuracy": 0.169136680662632,
|
|
"num_tokens": 3874588.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.042408800125122,
|
|
"epoch": 0.1628242074927954,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999496821655869,
|
|
"loss": 5.8829,
|
|
"mean_token_accuracy": 0.16141626685857774,
|
|
"num_tokens": 3884662.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.158259296417237,
|
|
"epoch": 0.1633045148895293,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999489545404414,
|
|
"loss": 5.9778,
|
|
"mean_token_accuracy": 0.15626356303691863,
|
|
"num_tokens": 3896569.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.13565845489502,
|
|
"epoch": 0.1637848222862632,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999482216926493,
|
|
"loss": 5.8183,
|
|
"mean_token_accuracy": 0.16687567681074142,
|
|
"num_tokens": 3907691.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.031500291824341,
|
|
"epoch": 0.1642651296829971,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999474836222273,
|
|
"loss": 5.8433,
|
|
"mean_token_accuracy": 0.1687850758433342,
|
|
"num_tokens": 3918794.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.0354866027832035,
|
|
"epoch": 0.16474543707973102,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999467403291928,
|
|
"loss": 5.8302,
|
|
"mean_token_accuracy": 0.17379950284957885,
|
|
"num_tokens": 3929773.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.017301607131958,
|
|
"epoch": 0.16522574447646493,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999459918135628,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.16206772923469542,
|
|
"num_tokens": 3940264.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.961511898040771,
|
|
"epoch": 0.16570605187319884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499945238075355,
|
|
"loss": 5.7453,
|
|
"mean_token_accuracy": 0.16794898062944413,
|
|
"num_tokens": 3951500.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.9861691951751705,
|
|
"epoch": 0.16618635926993275,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999444791145865,
|
|
"loss": 5.8345,
|
|
"mean_token_accuracy": 0.16556786149740219,
|
|
"num_tokens": 3963580.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.995738363265991,
|
|
"epoch": 0.16666666666666666,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999437149312754,
|
|
"loss": 5.7682,
|
|
"mean_token_accuracy": 0.17584467083215713,
|
|
"num_tokens": 3975994.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.007660579681397,
|
|
"epoch": 0.16714697406340057,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499942945525439,
|
|
"loss": 5.7844,
|
|
"mean_token_accuracy": 0.1600303217768669,
|
|
"num_tokens": 3987897.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.043190240859985,
|
|
"epoch": 0.16762728146013448,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999421708970954,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.15594586208462716,
|
|
"num_tokens": 3999829.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.972902059555054,
|
|
"epoch": 0.16810758885686838,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999413910462625,
|
|
"loss": 5.7781,
|
|
"mean_token_accuracy": 0.16753159314393998,
|
|
"num_tokens": 4010882.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.9610387802124025,
|
|
"epoch": 0.1685878962536023,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999406059729586,
|
|
"loss": 5.756,
|
|
"mean_token_accuracy": 0.1666981115937233,
|
|
"num_tokens": 4021423.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.116128730773926,
|
|
"epoch": 0.1690682036503362,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999398156772016,
|
|
"loss": 5.894,
|
|
"mean_token_accuracy": 0.15112203359603882,
|
|
"num_tokens": 4033590.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.959614181518555,
|
|
"epoch": 0.16954851104707014,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049993902015901,
|
|
"loss": 5.7608,
|
|
"mean_token_accuracy": 0.17025730162858962,
|
|
"num_tokens": 4043978.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.023910427093506,
|
|
"epoch": 0.17002881844380405,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999382194184023,
|
|
"loss": 5.8956,
|
|
"mean_token_accuracy": 0.1614847645163536,
|
|
"num_tokens": 4054513.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.124105310440063,
|
|
"epoch": 0.17050912584053796,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999374134553972,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.16457433849573136,
|
|
"num_tokens": 4066019.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.968501949310303,
|
|
"epoch": 0.17098943323727187,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999366022700131,
|
|
"loss": 5.7905,
|
|
"mean_token_accuracy": 0.16719537675380708,
|
|
"num_tokens": 4077688.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.039582633972168,
|
|
"epoch": 0.17146974063400577,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999357858622691,
|
|
"loss": 5.8791,
|
|
"mean_token_accuracy": 0.16837128698825837,
|
|
"num_tokens": 4089803.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.028085994720459,
|
|
"epoch": 0.17195004803073968,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999349642321842,
|
|
"loss": 5.8319,
|
|
"mean_token_accuracy": 0.16663650572299957,
|
|
"num_tokens": 4101969.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.029037094116211,
|
|
"epoch": 0.1724303554274736,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999341373797772,
|
|
"loss": 5.808,
|
|
"mean_token_accuracy": 0.1627863183617592,
|
|
"num_tokens": 4113567.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.954306650161743,
|
|
"epoch": 0.1729106628242075,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999333053050675,
|
|
"loss": 5.7683,
|
|
"mean_token_accuracy": 0.16414574086666106,
|
|
"num_tokens": 4125191.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.0340282917022705,
|
|
"epoch": 0.1733909702209414,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999324680080744,
|
|
"loss": 5.8148,
|
|
"mean_token_accuracy": 0.16474771052598952,
|
|
"num_tokens": 4135050.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.960515642166138,
|
|
"epoch": 0.17387127761767532,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999316254888172,
|
|
"loss": 5.8762,
|
|
"mean_token_accuracy": 0.16312166899442673,
|
|
"num_tokens": 4146874.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.994801616668701,
|
|
"epoch": 0.17435158501440923,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999307777473157,
|
|
"loss": 5.7959,
|
|
"mean_token_accuracy": 0.16597876250743865,
|
|
"num_tokens": 4158118.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.025922155380249,
|
|
"epoch": 0.17483189241114314,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999299247835893,
|
|
"loss": 5.778,
|
|
"mean_token_accuracy": 0.17315936088562012,
|
|
"num_tokens": 4169035.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.942285585403442,
|
|
"epoch": 0.17531219980787704,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499929066597658,
|
|
"loss": 5.7655,
|
|
"mean_token_accuracy": 0.17127336263656617,
|
|
"num_tokens": 4180314.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.031781435012817,
|
|
"epoch": 0.17579250720461095,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999282031895418,
|
|
"loss": 5.8419,
|
|
"mean_token_accuracy": 0.16611838191747666,
|
|
"num_tokens": 4192238.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.9649334907531735,
|
|
"epoch": 0.17627281460134486,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999273345592604,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.16682324707508087,
|
|
"num_tokens": 4203346.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.9124401092529295,
|
|
"epoch": 0.17675312199807877,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999264607068343,
|
|
"loss": 5.8301,
|
|
"mean_token_accuracy": 0.16939765363931655,
|
|
"num_tokens": 4213763.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.962861585617065,
|
|
"epoch": 0.17723342939481268,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999255816322837,
|
|
"loss": 5.7927,
|
|
"mean_token_accuracy": 0.16723354011774064,
|
|
"num_tokens": 4225553.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.043817090988159,
|
|
"epoch": 0.1777137367915466,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499924697335629,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.17336428612470628,
|
|
"num_tokens": 4236058.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.887497758865356,
|
|
"epoch": 0.1781940441882805,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999238078168906,
|
|
"loss": 5.7904,
|
|
"mean_token_accuracy": 0.17044568955898284,
|
|
"num_tokens": 4248299.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.978550386428833,
|
|
"epoch": 0.1786743515850144,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999229130760894,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.17197388857603074,
|
|
"num_tokens": 4259704.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.893118095397949,
|
|
"epoch": 0.17915465898174832,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499922013113246,
|
|
"loss": 5.607,
|
|
"mean_token_accuracy": 0.18167430013418198,
|
|
"num_tokens": 4270480.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.973291683197021,
|
|
"epoch": 0.17963496637848222,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999211079283814,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.16774737685918809,
|
|
"num_tokens": 4282104.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.07144513130188,
|
|
"epoch": 0.18011527377521613,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999201975215164,
|
|
"loss": 5.8297,
|
|
"mean_token_accuracy": 0.16095103695988655,
|
|
"num_tokens": 4294251.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.909284830093384,
|
|
"epoch": 0.18059558117195004,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999192818926725,
|
|
"loss": 5.7078,
|
|
"mean_token_accuracy": 0.1667791336774826,
|
|
"num_tokens": 4305569.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.000306129455566,
|
|
"epoch": 0.18107588856868395,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999183610418706,
|
|
"loss": 5.8418,
|
|
"mean_token_accuracy": 0.16189501956105232,
|
|
"num_tokens": 4317845.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.922011661529541,
|
|
"epoch": 0.18155619596541786,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999174349691322,
|
|
"loss": 5.7119,
|
|
"mean_token_accuracy": 0.1709301382303238,
|
|
"num_tokens": 4329987.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.898713827133179,
|
|
"epoch": 0.18203650336215177,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999165036744788,
|
|
"loss": 5.7182,
|
|
"mean_token_accuracy": 0.17281702160835266,
|
|
"num_tokens": 4341628.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.981558704376221,
|
|
"epoch": 0.18251681075888568,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999155671579322,
|
|
"loss": 5.7952,
|
|
"mean_token_accuracy": 0.16310359686613082,
|
|
"num_tokens": 4352379.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.8705666065216064,
|
|
"epoch": 0.1829971181556196,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499914625419514,
|
|
"loss": 5.7502,
|
|
"mean_token_accuracy": 0.16969154328107833,
|
|
"num_tokens": 4364800.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.977327680587768,
|
|
"epoch": 0.1834774255523535,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999136784592459,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.16629694402217865,
|
|
"num_tokens": 4376048.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.91033673286438,
|
|
"epoch": 0.1839577329490874,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999127262771502,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.16977874636650087,
|
|
"num_tokens": 4388072.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.031687164306641,
|
|
"epoch": 0.1844380403458213,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999117688732487,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.16268031895160676,
|
|
"num_tokens": 4399843.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.8528807163238525,
|
|
"epoch": 0.18491834774255522,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999108062475638,
|
|
"loss": 5.6895,
|
|
"mean_token_accuracy": 0.1747806504368782,
|
|
"num_tokens": 4411373.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.9012157917022705,
|
|
"epoch": 0.18539865513928913,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499909838400118,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.17514891028404236,
|
|
"num_tokens": 4421857.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.992180585861206,
|
|
"epoch": 0.18587896253602307,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999088653309334,
|
|
"loss": 5.7655,
|
|
"mean_token_accuracy": 0.17122769355773926,
|
|
"num_tokens": 4432728.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.874881219863892,
|
|
"epoch": 0.18635926993275698,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999078870400329,
|
|
"loss": 5.7109,
|
|
"mean_token_accuracy": 0.1737685203552246,
|
|
"num_tokens": 4444683.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.048246431350708,
|
|
"epoch": 0.18683957732949089,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999069035274391,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.16185275614261627,
|
|
"num_tokens": 4456961.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.890452718734741,
|
|
"epoch": 0.1873198847262248,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999059147931747,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.1743285223841667,
|
|
"num_tokens": 4468424.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.918470287322998,
|
|
"epoch": 0.1878001921229587,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999049208372629,
|
|
"loss": 5.87,
|
|
"mean_token_accuracy": 0.15737151950597764,
|
|
"num_tokens": 4479813.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.117772960662842,
|
|
"epoch": 0.1882804995196926,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999039216597267,
|
|
"loss": 5.8843,
|
|
"mean_token_accuracy": 0.16440917253494264,
|
|
"num_tokens": 4491172.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.863306999206543,
|
|
"epoch": 0.18876080691642652,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999029172605892,
|
|
"loss": 5.7603,
|
|
"mean_token_accuracy": 0.17048608511686325,
|
|
"num_tokens": 4503063.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.016164255142212,
|
|
"epoch": 0.18924111431316043,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999019076398738,
|
|
"loss": 5.8321,
|
|
"mean_token_accuracy": 0.15428075492382048,
|
|
"num_tokens": 4514188.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.956648588180542,
|
|
"epoch": 0.18972142170989434,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499900892797604,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.17256650179624558,
|
|
"num_tokens": 4525293.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.915363073348999,
|
|
"epoch": 0.19020172910662825,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998998727338031,
|
|
"loss": 5.8306,
|
|
"mean_token_accuracy": 0.16908561289310456,
|
|
"num_tokens": 4536589.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.890870523452759,
|
|
"epoch": 0.19068203650336216,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998988474484952,
|
|
"loss": 5.5742,
|
|
"mean_token_accuracy": 0.19122034162282944,
|
|
"num_tokens": 4547594.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.90146050453186,
|
|
"epoch": 0.19116234390009607,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998978169417038,
|
|
"loss": 5.7832,
|
|
"mean_token_accuracy": 0.17002302259206772,
|
|
"num_tokens": 4559850.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.936874294281006,
|
|
"epoch": 0.19164265129682997,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998967812134529,
|
|
"loss": 5.7186,
|
|
"mean_token_accuracy": 0.16649213433265686,
|
|
"num_tokens": 4570727.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.786225271224976,
|
|
"epoch": 0.19212295869356388,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998957402637664,
|
|
"loss": 5.6629,
|
|
"mean_token_accuracy": 0.17317176163196563,
|
|
"num_tokens": 4582248.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.951917409896851,
|
|
"epoch": 0.1926032660902978,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998946940926687,
|
|
"loss": 5.6879,
|
|
"mean_token_accuracy": 0.17081644088029863,
|
|
"num_tokens": 4592604.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.852265024185181,
|
|
"epoch": 0.1930835734870317,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499893642700184,
|
|
"loss": 5.7288,
|
|
"mean_token_accuracy": 0.16796955615282058,
|
|
"num_tokens": 4604398.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.932278966903686,
|
|
"epoch": 0.1935638808837656,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998925860863368,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.16799372732639312,
|
|
"num_tokens": 4616434.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.984751844406128,
|
|
"epoch": 0.19404418828049952,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998915242511516,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.17852777987718582,
|
|
"num_tokens": 4627577.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.979996967315674,
|
|
"epoch": 0.19452449567723343,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998904571946528,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.16536686867475509,
|
|
"num_tokens": 4639698.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.992480897903443,
|
|
"epoch": 0.19500480307396734,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998893849168655,
|
|
"loss": 5.8193,
|
|
"mean_token_accuracy": 0.16457681208848954,
|
|
"num_tokens": 4650643.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.908215618133545,
|
|
"epoch": 0.19548511047070125,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998883074178144,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.16797305792570114,
|
|
"num_tokens": 4662897.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.982371234893799,
|
|
"epoch": 0.19596541786743515,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998872246975247,
|
|
"loss": 5.8354,
|
|
"mean_token_accuracy": 0.17146392464637755,
|
|
"num_tokens": 4673701.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.009561920166016,
|
|
"epoch": 0.19644572526416906,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998861367560213,
|
|
"loss": 5.7898,
|
|
"mean_token_accuracy": 0.16622848212718963,
|
|
"num_tokens": 4685873.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.924004793167114,
|
|
"epoch": 0.19692603266090297,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998850435933296,
|
|
"loss": 5.6709,
|
|
"mean_token_accuracy": 0.1732612207531929,
|
|
"num_tokens": 4697179.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.862003564834595,
|
|
"epoch": 0.19740634005763688,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998839452094749,
|
|
"loss": 5.7114,
|
|
"mean_token_accuracy": 0.17544772624969482,
|
|
"num_tokens": 4707752.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.796081399917602,
|
|
"epoch": 0.1978866474543708,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998828416044829,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.17987633645534515,
|
|
"num_tokens": 4718413.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.9167498588562015,
|
|
"epoch": 0.1983669548511047,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499881732778379,
|
|
"loss": 5.7688,
|
|
"mean_token_accuracy": 0.16329588294029235,
|
|
"num_tokens": 4730033.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.891122531890869,
|
|
"epoch": 0.1988472622478386,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499880618731189,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.17821569591760636,
|
|
"num_tokens": 4742084.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.9228325366973875,
|
|
"epoch": 0.19932756964457252,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998794994629388,
|
|
"loss": 5.8539,
|
|
"mean_token_accuracy": 0.16390760689973832,
|
|
"num_tokens": 4753885.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.88261046409607,
|
|
"epoch": 0.19980787704130643,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998783749736545,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.1716991052031517,
|
|
"num_tokens": 4765686.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.954660081863404,
|
|
"epoch": 0.20028818443804033,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998772452633619,
|
|
"loss": 5.7332,
|
|
"mean_token_accuracy": 0.1718806430697441,
|
|
"num_tokens": 4777157.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.845113325119018,
|
|
"epoch": 0.20076849183477424,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998761103320876,
|
|
"loss": 5.6655,
|
|
"mean_token_accuracy": 0.17630862295627595,
|
|
"num_tokens": 4788583.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.971330165863037,
|
|
"epoch": 0.20124879923150815,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998749701798577,
|
|
"loss": 5.7852,
|
|
"mean_token_accuracy": 0.16313367635011672,
|
|
"num_tokens": 4800749.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.862610292434693,
|
|
"epoch": 0.2017291066282421,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998738248066986,
|
|
"loss": 5.6986,
|
|
"mean_token_accuracy": 0.1719326362013817,
|
|
"num_tokens": 4812488.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.943162345886231,
|
|
"epoch": 0.202209414024976,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998726742126372,
|
|
"loss": 5.6826,
|
|
"mean_token_accuracy": 0.17237975001335143,
|
|
"num_tokens": 4823495.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.845049905776977,
|
|
"epoch": 0.2026897214217099,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998715183976999,
|
|
"loss": 5.7416,
|
|
"mean_token_accuracy": 0.16694231554865838,
|
|
"num_tokens": 4834450.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.872321510314942,
|
|
"epoch": 0.20317002881844382,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998703573619137,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.17984378933906556,
|
|
"num_tokens": 4846826.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.981400775909424,
|
|
"epoch": 0.20365033621517772,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998691911053056,
|
|
"loss": 5.838,
|
|
"mean_token_accuracy": 0.15721772760152816,
|
|
"num_tokens": 4859668.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.889471960067749,
|
|
"epoch": 0.20413064361191163,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998680196279026,
|
|
"loss": 5.7188,
|
|
"mean_token_accuracy": 0.17116449922323226,
|
|
"num_tokens": 4871727.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.965567874908447,
|
|
"epoch": 0.20461095100864554,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998668429297319,
|
|
"loss": 5.7581,
|
|
"mean_token_accuracy": 0.17664661183953284,
|
|
"num_tokens": 4882191.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.91290979385376,
|
|
"epoch": 0.20509125840537945,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998656610108208,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.17135777622461318,
|
|
"num_tokens": 4892416.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.7849208354949955,
|
|
"epoch": 0.20557156580211336,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998644738711969,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.1663479372859001,
|
|
"num_tokens": 4903572.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.012947654724121,
|
|
"epoch": 0.20605187319884727,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998632815108874,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.16735016852617263,
|
|
"num_tokens": 4915417.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.828745889663696,
|
|
"epoch": 0.20653218059558118,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998620839299203,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.1731554314494133,
|
|
"num_tokens": 4926943.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.879217290878296,
|
|
"epoch": 0.2070124879923151,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998608811283233,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.17777990251779557,
|
|
"num_tokens": 4937724.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.948641300201416,
|
|
"epoch": 0.207492795389049,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998596731061244,
|
|
"loss": 5.7627,
|
|
"mean_token_accuracy": 0.16541688293218612,
|
|
"num_tokens": 4949970.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.916024541854858,
|
|
"epoch": 0.2079731027857829,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998584598633516,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.1677638292312622,
|
|
"num_tokens": 4961389.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.9447978973388675,
|
|
"epoch": 0.2084534101825168,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998572414000329,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.16801437735557556,
|
|
"num_tokens": 4973888.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.877821445465088,
|
|
"epoch": 0.20893371757925072,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998560177161969,
|
|
"loss": 5.7626,
|
|
"mean_token_accuracy": 0.15845638066530227,
|
|
"num_tokens": 4985423.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.847891712188721,
|
|
"epoch": 0.20941402497598463,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998547888118718,
|
|
"loss": 5.7327,
|
|
"mean_token_accuracy": 0.1661007210612297,
|
|
"num_tokens": 4997711.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.9377055168151855,
|
|
"epoch": 0.20989433237271854,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998535546870862,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.17071173936128617,
|
|
"num_tokens": 5009633.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.87849235534668,
|
|
"epoch": 0.21037463976945245,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998523153418687,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.17723384648561477,
|
|
"num_tokens": 5021523.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.969219064712524,
|
|
"epoch": 0.21085494716618636,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998510707762481,
|
|
"loss": 5.7792,
|
|
"mean_token_accuracy": 0.1698889523744583,
|
|
"num_tokens": 5033513.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.002408790588379,
|
|
"epoch": 0.21133525456292027,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998498209902533,
|
|
"loss": 5.7803,
|
|
"mean_token_accuracy": 0.16734371781349183,
|
|
"num_tokens": 5047055.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.902544927597046,
|
|
"epoch": 0.21181556195965417,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998485659839134,
|
|
"loss": 5.6634,
|
|
"mean_token_accuracy": 0.171344156563282,
|
|
"num_tokens": 5057613.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.888894319534302,
|
|
"epoch": 0.21229586935638808,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998473057572575,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.16772594749927522,
|
|
"num_tokens": 5068886.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.889117670059204,
|
|
"epoch": 0.212776176753122,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998460403103146,
|
|
"loss": 5.7516,
|
|
"mean_token_accuracy": 0.1667829394340515,
|
|
"num_tokens": 5079978.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.892506170272827,
|
|
"epoch": 0.2132564841498559,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998447696431146,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.1731807380914688,
|
|
"num_tokens": 5091021.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.812002897262573,
|
|
"epoch": 0.2137367915465898,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998434937556865,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.1779699981212616,
|
|
"num_tokens": 5101483.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.916818428039551,
|
|
"epoch": 0.21421709894332372,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998422126480602,
|
|
"loss": 5.7339,
|
|
"mean_token_accuracy": 0.16566304564476014,
|
|
"num_tokens": 5113116.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.918116569519043,
|
|
"epoch": 0.21469740634005763,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998409263202653,
|
|
"loss": 5.6905,
|
|
"mean_token_accuracy": 0.17165909111499786,
|
|
"num_tokens": 5124824.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.821660041809082,
|
|
"epoch": 0.21517771373679154,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998396347723318,
|
|
"loss": 5.6186,
|
|
"mean_token_accuracy": 0.16778021901845933,
|
|
"num_tokens": 5137567.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.834303140640259,
|
|
"epoch": 0.21565802113352545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998383380042895,
|
|
"loss": 5.6873,
|
|
"mean_token_accuracy": 0.1687231481075287,
|
|
"num_tokens": 5149016.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.800395917892456,
|
|
"epoch": 0.21613832853025935,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998370360161688,
|
|
"loss": 5.5679,
|
|
"mean_token_accuracy": 0.177195705473423,
|
|
"num_tokens": 5160356.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.877714490890503,
|
|
"epoch": 0.21661863592699326,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998357288079996,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.1638329356908798,
|
|
"num_tokens": 5172100.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.947152042388916,
|
|
"epoch": 0.21709894332372717,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998344163798125,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.1652805581688881,
|
|
"num_tokens": 5183984.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.8969450950622555,
|
|
"epoch": 0.21757925072046108,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998330987316379,
|
|
"loss": 5.7033,
|
|
"mean_token_accuracy": 0.16846372336149215,
|
|
"num_tokens": 5195853.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.786798810958862,
|
|
"epoch": 0.21805955811719502,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998317758635062,
|
|
"loss": 5.5582,
|
|
"mean_token_accuracy": 0.17903037667274474,
|
|
"num_tokens": 5206995.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.688874101638794,
|
|
"epoch": 0.21853986551392893,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998304477754484,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.1773568794131279,
|
|
"num_tokens": 5219291.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.856671667098999,
|
|
"epoch": 0.21902017291066284,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998291144674952,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.1779756113886833,
|
|
"num_tokens": 5230856.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.781990480422974,
|
|
"epoch": 0.21950048030739674,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998277759396776,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.18482960611581803,
|
|
"num_tokens": 5242871.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.7626872062683105,
|
|
"epoch": 0.21998078770413065,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998264321920265,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.18032118529081345,
|
|
"num_tokens": 5253835.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.782493829727173,
|
|
"epoch": 0.22046109510086456,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998250832245734,
|
|
"loss": 5.6194,
|
|
"mean_token_accuracy": 0.17594331204891206,
|
|
"num_tokens": 5266195.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.801488208770752,
|
|
"epoch": 0.22094140249759847,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998237290373494,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.17856477349996566,
|
|
"num_tokens": 5277499.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.931110095977783,
|
|
"epoch": 0.22142170989433238,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499822369630386,
|
|
"loss": 5.706,
|
|
"mean_token_accuracy": 0.16192054152488708,
|
|
"num_tokens": 5288622.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.866655731201172,
|
|
"epoch": 0.2219020172910663,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998210050037148,
|
|
"loss": 5.7657,
|
|
"mean_token_accuracy": 0.16639903783798218,
|
|
"num_tokens": 5299664.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.874531269073486,
|
|
"epoch": 0.2223823246878002,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998196351573674,
|
|
"loss": 5.6538,
|
|
"mean_token_accuracy": 0.17477090954780578,
|
|
"num_tokens": 5311627.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.721544981002808,
|
|
"epoch": 0.2228626320845341,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998182600913757,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.18625836670398713,
|
|
"num_tokens": 5323000.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.832249641418457,
|
|
"epoch": 0.22334293948126802,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998168798057715,
|
|
"loss": 5.6003,
|
|
"mean_token_accuracy": 0.1812728613615036,
|
|
"num_tokens": 5333811.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.826548004150391,
|
|
"epoch": 0.22382324687800192,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499815494300587,
|
|
"loss": 5.6142,
|
|
"mean_token_accuracy": 0.17571379840373993,
|
|
"num_tokens": 5344762.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.80838451385498,
|
|
"epoch": 0.22430355427473583,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998141035758542,
|
|
"loss": 5.602,
|
|
"mean_token_accuracy": 0.18153773993253708,
|
|
"num_tokens": 5356112.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.876251316070556,
|
|
"epoch": 0.22478386167146974,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998127076316054,
|
|
"loss": 5.7258,
|
|
"mean_token_accuracy": 0.16987995207309722,
|
|
"num_tokens": 5367339.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.799464511871338,
|
|
"epoch": 0.22526416906820365,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998113064678734,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.183486644923687,
|
|
"num_tokens": 5378627.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.8673011302948,
|
|
"epoch": 0.22574447646493756,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998099000846901,
|
|
"loss": 5.6825,
|
|
"mean_token_accuracy": 0.1747091993689537,
|
|
"num_tokens": 5390209.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.885054302215576,
|
|
"epoch": 0.22622478386167147,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998084884820887,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.17270639091730117,
|
|
"num_tokens": 5401578.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.7969471454620365,
|
|
"epoch": 0.22670509125840538,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998070716601016,
|
|
"loss": 5.6028,
|
|
"mean_token_accuracy": 0.17538144290447236,
|
|
"num_tokens": 5413831.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.863705444335937,
|
|
"epoch": 0.2271853986551393,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998056496187618,
|
|
"loss": 5.652,
|
|
"mean_token_accuracy": 0.1691875770688057,
|
|
"num_tokens": 5425430.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.6353754043579105,
|
|
"epoch": 0.2276657060518732,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998042223581025,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.1855420872569084,
|
|
"num_tokens": 5435353.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.862425804138184,
|
|
"epoch": 0.2281460134486071,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998027898781565,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.17443186193704605,
|
|
"num_tokens": 5446925.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.729289484024048,
|
|
"epoch": 0.228626320845341,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998013521789574,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.1821834087371826,
|
|
"num_tokens": 5456613.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.850210475921631,
|
|
"epoch": 0.22910662824207492,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997999092605384,
|
|
"loss": 5.6193,
|
|
"mean_token_accuracy": 0.17688928544521332,
|
|
"num_tokens": 5467790.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.8598381042480465,
|
|
"epoch": 0.22958693563880883,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499798461122933,
|
|
"loss": 5.6118,
|
|
"mean_token_accuracy": 0.1773025169968605,
|
|
"num_tokens": 5479166.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.695592832565308,
|
|
"epoch": 0.23006724303554274,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997970077661748,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.18406546413898467,
|
|
"num_tokens": 5490186.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.785607433319091,
|
|
"epoch": 0.23054755043227665,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997955491902977,
|
|
"loss": 5.5746,
|
|
"mean_token_accuracy": 0.17407838255167007,
|
|
"num_tokens": 5500416.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.80128846168518,
|
|
"epoch": 0.23102785782901056,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997940853953354,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.17734454870223998,
|
|
"num_tokens": 5512189.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.753947496414185,
|
|
"epoch": 0.23150816522574447,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499792616381322,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.1830824211239815,
|
|
"num_tokens": 5523631.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.727394866943359,
|
|
"epoch": 0.23198847262247838,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997911421482914,
|
|
"loss": 5.5761,
|
|
"mean_token_accuracy": 0.17973856627941132,
|
|
"num_tokens": 5535637.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.7857983112335205,
|
|
"epoch": 0.23246878001921228,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499789662696278,
|
|
"loss": 5.5863,
|
|
"mean_token_accuracy": 0.1800864651799202,
|
|
"num_tokens": 5546470.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.888076305389404,
|
|
"epoch": 0.2329490874159462,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997881780253162,
|
|
"loss": 5.7413,
|
|
"mean_token_accuracy": 0.16848194748163223,
|
|
"num_tokens": 5558633.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.80600266456604,
|
|
"epoch": 0.2334293948126801,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997866881354403,
|
|
"loss": 5.6487,
|
|
"mean_token_accuracy": 0.17162267118692398,
|
|
"num_tokens": 5570427.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.762806415557861,
|
|
"epoch": 0.23390970220941404,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499785193026685,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.17541880607604982,
|
|
"num_tokens": 5580991.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.884730529785156,
|
|
"epoch": 0.23439000960614795,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997836926990851,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.17449010610580445,
|
|
"num_tokens": 5592777.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.745317554473877,
|
|
"epoch": 0.23487031700288186,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997821871526752,
|
|
"loss": 5.5765,
|
|
"mean_token_accuracy": 0.18271358013153077,
|
|
"num_tokens": 5603326.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.73594331741333,
|
|
"epoch": 0.23535062439961577,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997806763874905,
|
|
"loss": 5.5693,
|
|
"mean_token_accuracy": 0.18031217455863952,
|
|
"num_tokens": 5614504.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.782830619812012,
|
|
"epoch": 0.23583093179634967,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997791604035659,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.17803447991609572,
|
|
"num_tokens": 5625150.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.804438877105713,
|
|
"epoch": 0.23631123919308358,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997776392009366,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.17143210619688035,
|
|
"num_tokens": 5636815.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.8043129444122314,
|
|
"epoch": 0.2367915465898175,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997761127796381,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.17545064836740493,
|
|
"num_tokens": 5648272.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.757105493545533,
|
|
"epoch": 0.2372718539865514,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997745811397056,
|
|
"loss": 5.5526,
|
|
"mean_token_accuracy": 0.1801515832543373,
|
|
"num_tokens": 5659227.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.795153522491455,
|
|
"epoch": 0.2377521613832853,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997730442811748,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.17654881477355958,
|
|
"num_tokens": 5670411.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.748981523513794,
|
|
"epoch": 0.23823246878001922,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997715022040814,
|
|
"loss": 5.5096,
|
|
"mean_token_accuracy": 0.18419251292943956,
|
|
"num_tokens": 5681570.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.7172455310821535,
|
|
"epoch": 0.23871277617675313,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499769954908461,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.18976044952869414,
|
|
"num_tokens": 5693021.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.727937793731689,
|
|
"epoch": 0.23919308357348704,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997684023943498,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.17496601939201356,
|
|
"num_tokens": 5704043.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.732729482650757,
|
|
"epoch": 0.23967339097022095,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997668446617837,
|
|
"loss": 5.6705,
|
|
"mean_token_accuracy": 0.16925858408212663,
|
|
"num_tokens": 5715735.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.932486486434937,
|
|
"epoch": 0.24015369836695485,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997652817107989,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.17272803783416749,
|
|
"num_tokens": 5725778.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.75950403213501,
|
|
"epoch": 0.24063400576368876,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997637135414315,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.17402508705854416,
|
|
"num_tokens": 5737224.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.841374206542969,
|
|
"epoch": 0.24111431316042267,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997621401537183,
|
|
"loss": 5.6819,
|
|
"mean_token_accuracy": 0.1714730903506279,
|
|
"num_tokens": 5749226.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.859533452987671,
|
|
"epoch": 0.24159462055715658,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997605615476955,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.17602848410606384,
|
|
"num_tokens": 5760282.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.705944013595581,
|
|
"epoch": 0.2420749279538905,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997589777234,
|
|
"loss": 5.5527,
|
|
"mean_token_accuracy": 0.18297999501228332,
|
|
"num_tokens": 5771756.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.783916234970093,
|
|
"epoch": 0.2425552353506244,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997573886808684,
|
|
"loss": 5.5929,
|
|
"mean_token_accuracy": 0.17033566832542418,
|
|
"num_tokens": 5783237.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.766665458679199,
|
|
"epoch": 0.2430355427473583,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997557944201375,
|
|
"loss": 5.6765,
|
|
"mean_token_accuracy": 0.17114062905311583,
|
|
"num_tokens": 5794825.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.83233232498169,
|
|
"epoch": 0.24351585014409222,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997541949412445,
|
|
"loss": 5.5704,
|
|
"mean_token_accuracy": 0.18051684647798538,
|
|
"num_tokens": 5805578.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.825575923919677,
|
|
"epoch": 0.24399615754082613,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997525902442266,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.1699126750230789,
|
|
"num_tokens": 5818201.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.761399126052856,
|
|
"epoch": 0.24447646493756003,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997509803291207,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.17694975286722184,
|
|
"num_tokens": 5830319.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.706338500976562,
|
|
"epoch": 0.24495677233429394,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997493651959647,
|
|
"loss": 5.5395,
|
|
"mean_token_accuracy": 0.1815444216132164,
|
|
"num_tokens": 5840638.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.751677846908569,
|
|
"epoch": 0.24543707973102785,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997477448447955,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.17573375552892684,
|
|
"num_tokens": 5852472.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.835761976242066,
|
|
"epoch": 0.24591738712776176,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997461192756512,
|
|
"loss": 5.6,
|
|
"mean_token_accuracy": 0.17359656244516372,
|
|
"num_tokens": 5863455.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.677509737014771,
|
|
"epoch": 0.24639769452449567,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997444884885694,
|
|
"loss": 5.5109,
|
|
"mean_token_accuracy": 0.18119774758815765,
|
|
"num_tokens": 5873141.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.6975038051605225,
|
|
"epoch": 0.24687800192122958,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997428524835879,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.1763081893324852,
|
|
"num_tokens": 5884363.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.83483624458313,
|
|
"epoch": 0.2473583093179635,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997412112607446,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.17418509721755981,
|
|
"num_tokens": 5895856.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.710783958435059,
|
|
"epoch": 0.2478386167146974,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997395648200778,
|
|
"loss": 5.5001,
|
|
"mean_token_accuracy": 0.18241955786943437,
|
|
"num_tokens": 5906657.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.73748025894165,
|
|
"epoch": 0.2483189241114313,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997379131616257,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.17517986595630647,
|
|
"num_tokens": 5919496.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.801119375228882,
|
|
"epoch": 0.24879923150816521,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997362562854266,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.16362314075231552,
|
|
"num_tokens": 5932593.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.805383825302124,
|
|
"epoch": 0.24927953890489912,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997345941915187,
|
|
"loss": 5.5946,
|
|
"mean_token_accuracy": 0.17460722476243973,
|
|
"num_tokens": 5944080.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.7451694965362545,
|
|
"epoch": 0.24975984630163303,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997329268799412,
|
|
"loss": 5.5769,
|
|
"mean_token_accuracy": 0.18260987102985382,
|
|
"num_tokens": 5955703.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.733469676971436,
|
|
"epoch": 0.25024015369836694,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997312543507322,
|
|
"loss": 5.6574,
|
|
"mean_token_accuracy": 0.1740378275513649,
|
|
"num_tokens": 5966979.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.814836883544922,
|
|
"epoch": 0.2507204610951009,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997295766039309,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.17929624170064926,
|
|
"num_tokens": 5978808.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.754059314727783,
|
|
"epoch": 0.25120076849183476,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997278936395761,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.16822077333927155,
|
|
"num_tokens": 5992145.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.775521326065063,
|
|
"epoch": 0.2516810758885687,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997262054577071,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.1735659971833229,
|
|
"num_tokens": 6003723.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.785316133499146,
|
|
"epoch": 0.2521613832853026,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997245120583627,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.18019691854715347,
|
|
"num_tokens": 6014064.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.703524494171143,
|
|
"epoch": 0.2526416906820365,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997228134415825,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.18180668652057647,
|
|
"num_tokens": 6025455.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.781266164779663,
|
|
"epoch": 0.2531219980787704,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997211096074059,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.1656498432159424,
|
|
"num_tokens": 6037347.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.690671968460083,
|
|
"epoch": 0.25360230547550433,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997194005558722,
|
|
"loss": 5.5216,
|
|
"mean_token_accuracy": 0.1789523884654045,
|
|
"num_tokens": 6049236.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.6680278301239015,
|
|
"epoch": 0.2540826128722382,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997176862870216,
|
|
"loss": 5.538,
|
|
"mean_token_accuracy": 0.17978094518184662,
|
|
"num_tokens": 6060982.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.819158840179443,
|
|
"epoch": 0.25456292026897215,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997159668008933,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.18156028538942337,
|
|
"num_tokens": 6070925.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.680534505844117,
|
|
"epoch": 0.25504322766570603,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997142420975277,
|
|
"loss": 5.487,
|
|
"mean_token_accuracy": 0.18826171904802322,
|
|
"num_tokens": 6081279.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.710468053817749,
|
|
"epoch": 0.25552353506243997,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997125121769647,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.17861386388540268,
|
|
"num_tokens": 6091797.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.825000762939453,
|
|
"epoch": 0.25600384245917385,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997107770392444,
|
|
"loss": 5.6073,
|
|
"mean_token_accuracy": 0.18347439020872117,
|
|
"num_tokens": 6103435.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.79217495918274,
|
|
"epoch": 0.2564841498559078,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499709036684407,
|
|
"loss": 5.6709,
|
|
"mean_token_accuracy": 0.17622565925121308,
|
|
"num_tokens": 6114531.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.653947401046753,
|
|
"epoch": 0.25696445725264166,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997072911124932,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.18308780789375306,
|
|
"num_tokens": 6126110.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.768945932388306,
|
|
"epoch": 0.2574447646493756,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997055403235432,
|
|
"loss": 5.6082,
|
|
"mean_token_accuracy": 0.17530772536993028,
|
|
"num_tokens": 6137114.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.69290862083435,
|
|
"epoch": 0.2579250720461095,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997037843175978,
|
|
"loss": 5.5674,
|
|
"mean_token_accuracy": 0.179079769551754,
|
|
"num_tokens": 6148696.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.712290477752686,
|
|
"epoch": 0.2584053794428434,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997020230946978,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.17987955063581468,
|
|
"num_tokens": 6160235.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.794245862960816,
|
|
"epoch": 0.25888568683957736,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997002566548841,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.17859422713518142,
|
|
"num_tokens": 6172031.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.621943998336792,
|
|
"epoch": 0.25936599423631124,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996984849981976,
|
|
"loss": 5.415,
|
|
"mean_token_accuracy": 0.18926973193883895,
|
|
"num_tokens": 6183547.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.752551746368408,
|
|
"epoch": 0.2598463016330452,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996967081246794,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.17076316028833388,
|
|
"num_tokens": 6194768.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.741240787506103,
|
|
"epoch": 0.26032660902977905,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996949260343711,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.17027782052755355,
|
|
"num_tokens": 6206099.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.780304861068726,
|
|
"epoch": 0.260806916426513,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996931387273137,
|
|
"loss": 5.61,
|
|
"mean_token_accuracy": 0.1808237463235855,
|
|
"num_tokens": 6217530.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.834391117095947,
|
|
"epoch": 0.2612872238232469,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996913462035487,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.17484427392482757,
|
|
"num_tokens": 6228564.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.670606851577759,
|
|
"epoch": 0.2617675312199808,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499689548463118,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.17770184427499772,
|
|
"num_tokens": 6239945.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.735776376724243,
|
|
"epoch": 0.2622478386167147,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996877455060631,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.17381711900234223,
|
|
"num_tokens": 6251829.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.871343946456909,
|
|
"epoch": 0.2627281460134486,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996859373324259,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.16585395336151124,
|
|
"num_tokens": 6264823.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.686900472640991,
|
|
"epoch": 0.2632084534101825,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996841239422485,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.18778327703475953,
|
|
"num_tokens": 6276247.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.597873067855835,
|
|
"epoch": 0.26368876080691644,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996823053355729,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.18251601308584214,
|
|
"num_tokens": 6287593.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.837592267990113,
|
|
"epoch": 0.2641690682036503,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996804815124413,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.1740195035934448,
|
|
"num_tokens": 6299918.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.680815124511719,
|
|
"epoch": 0.26464937560038426,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996786524728962,
|
|
"loss": 5.5247,
|
|
"mean_token_accuracy": 0.18393096774816514,
|
|
"num_tokens": 6311147.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.613561296463013,
|
|
"epoch": 0.26512968299711814,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996768182169797,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.18843217045068741,
|
|
"num_tokens": 6323239.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.7647748470306395,
|
|
"epoch": 0.2656099903938521,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996749787447349,
|
|
"loss": 5.5256,
|
|
"mean_token_accuracy": 0.1798029989004135,
|
|
"num_tokens": 6334625.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.730550050735474,
|
|
"epoch": 0.26609029779058596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499673134056204,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.18138138502836226,
|
|
"num_tokens": 6346068.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.688610410690307,
|
|
"epoch": 0.2665706051873199,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996712841514303,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.18104476630687713,
|
|
"num_tokens": 6357097.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.780763864517212,
|
|
"epoch": 0.2670509125840538,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996694290304563,
|
|
"loss": 5.6012,
|
|
"mean_token_accuracy": 0.1663811519742012,
|
|
"num_tokens": 6367481.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.648175573348999,
|
|
"epoch": 0.2675312199807877,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996675686933255,
|
|
"loss": 5.5164,
|
|
"mean_token_accuracy": 0.1855094313621521,
|
|
"num_tokens": 6378873.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.778855705261231,
|
|
"epoch": 0.2680115273775216,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996657031400807,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.1777387112379074,
|
|
"num_tokens": 6390651.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.656892156600952,
|
|
"epoch": 0.26849183477425553,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996638323707655,
|
|
"loss": 5.4324,
|
|
"mean_token_accuracy": 0.18739653527736663,
|
|
"num_tokens": 6401631.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.608145618438721,
|
|
"epoch": 0.2689721421709894,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996619563854232,
|
|
"loss": 5.5187,
|
|
"mean_token_accuracy": 0.1855126902461052,
|
|
"num_tokens": 6413875.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.782154989242554,
|
|
"epoch": 0.26945244956772335,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996600751840974,
|
|
"loss": 5.5557,
|
|
"mean_token_accuracy": 0.176130411028862,
|
|
"num_tokens": 6425764.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.670776462554931,
|
|
"epoch": 0.26993275696445723,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996581887668317,
|
|
"loss": 5.4646,
|
|
"mean_token_accuracy": 0.18302996158599855,
|
|
"num_tokens": 6437911.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.640679788589478,
|
|
"epoch": 0.27041306436119117,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049965629713367,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.18281519412994385,
|
|
"num_tokens": 6449942.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.719023561477661,
|
|
"epoch": 0.27089337175792505,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996544002846561,
|
|
"loss": 5.5995,
|
|
"mean_token_accuracy": 0.17978287041187285,
|
|
"num_tokens": 6461729.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.751323080062866,
|
|
"epoch": 0.271373679154659,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996524982198343,
|
|
"loss": 5.5719,
|
|
"mean_token_accuracy": 0.18161486983299255,
|
|
"num_tokens": 6472046.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.721522521972656,
|
|
"epoch": 0.27185398655139287,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996505909392485,
|
|
"loss": 5.5477,
|
|
"mean_token_accuracy": 0.1771852806210518,
|
|
"num_tokens": 6483308.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.551406669616699,
|
|
"epoch": 0.2723342939481268,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996486784429429,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.1857747346162796,
|
|
"num_tokens": 6495093.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.71174054145813,
|
|
"epoch": 0.2728146013448607,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996467607309622,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.17964418977499008,
|
|
"num_tokens": 6505933.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.72988600730896,
|
|
"epoch": 0.2732949087415946,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996448378033507,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.17828564196825028,
|
|
"num_tokens": 6517280.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.678931474685669,
|
|
"epoch": 0.2737752161383285,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996429096601532,
|
|
"loss": 5.6158,
|
|
"mean_token_accuracy": 0.17375251650810242,
|
|
"num_tokens": 6528980.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.71303505897522,
|
|
"epoch": 0.27425552353506244,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996409763014144,
|
|
"loss": 5.6106,
|
|
"mean_token_accuracy": 0.1804870694875717,
|
|
"num_tokens": 6540670.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.702807521820068,
|
|
"epoch": 0.2747358309317964,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996390377271791,
|
|
"loss": 5.57,
|
|
"mean_token_accuracy": 0.18366750180721284,
|
|
"num_tokens": 6551302.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.705173969268799,
|
|
"epoch": 0.27521613832853026,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996370939374924,
|
|
"loss": 5.5216,
|
|
"mean_token_accuracy": 0.17237444818019867,
|
|
"num_tokens": 6563177.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.844460535049438,
|
|
"epoch": 0.2756964457252642,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996351449323994,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.1813505157828331,
|
|
"num_tokens": 6573323.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.725948524475098,
|
|
"epoch": 0.2761767531219981,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996331907119455,
|
|
"loss": 5.5713,
|
|
"mean_token_accuracy": 0.1717742770910263,
|
|
"num_tokens": 6585382.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.586256790161133,
|
|
"epoch": 0.276657060518732,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996312312761758,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.1891452044248581,
|
|
"num_tokens": 6596629.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.739269733428955,
|
|
"epoch": 0.2771373679154659,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499629266625136,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.18007983416318893,
|
|
"num_tokens": 6608408.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.759958505630493,
|
|
"epoch": 0.27761767531219983,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996272967588715,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.17467228472232818,
|
|
"num_tokens": 6619375.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.750079774856568,
|
|
"epoch": 0.2780979827089337,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996253216774283,
|
|
"loss": 5.6357,
|
|
"mean_token_accuracy": 0.17795114517211913,
|
|
"num_tokens": 6631317.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.730680131912232,
|
|
"epoch": 0.27857829010566765,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996233413808521,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.18032360523939134,
|
|
"num_tokens": 6642009.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.708155965805053,
|
|
"epoch": 0.27905859750240153,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996213558691889,
|
|
"loss": 5.6328,
|
|
"mean_token_accuracy": 0.1716104194521904,
|
|
"num_tokens": 6654713.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.699761247634887,
|
|
"epoch": 0.27953890489913547,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996193651424848,
|
|
"loss": 5.5966,
|
|
"mean_token_accuracy": 0.1802009731531143,
|
|
"num_tokens": 6667157.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.7038122653961185,
|
|
"epoch": 0.28001921229586935,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499617369200786,
|
|
"loss": 5.5383,
|
|
"mean_token_accuracy": 0.18896565586328506,
|
|
"num_tokens": 6679573.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.7405517578125,
|
|
"epoch": 0.2804995196926033,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996153680441389,
|
|
"loss": 5.6213,
|
|
"mean_token_accuracy": 0.17383338063955306,
|
|
"num_tokens": 6691768.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.770690536499023,
|
|
"epoch": 0.28097982708933716,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049961336167259,
|
|
"loss": 5.5717,
|
|
"mean_token_accuracy": 0.174806410074234,
|
|
"num_tokens": 6701964.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.705366468429565,
|
|
"epoch": 0.2814601344860711,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996113500861857,
|
|
"loss": 5.5588,
|
|
"mean_token_accuracy": 0.18040292710065842,
|
|
"num_tokens": 6713506.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.7421009063720705,
|
|
"epoch": 0.281940441882805,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996093332849729,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.17432304471731186,
|
|
"num_tokens": 6724616.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.721134281158447,
|
|
"epoch": 0.2824207492795389,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996073112689983,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.17643650472164155,
|
|
"num_tokens": 6735054.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.75977578163147,
|
|
"epoch": 0.2829010566762728,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996052840383088,
|
|
"loss": 5.6062,
|
|
"mean_token_accuracy": 0.17887143716216086,
|
|
"num_tokens": 6746756.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.688607835769654,
|
|
"epoch": 0.28338136407300674,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996032515929516,
|
|
"loss": 5.4822,
|
|
"mean_token_accuracy": 0.1823216959834099,
|
|
"num_tokens": 6759566.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.691004610061645,
|
|
"epoch": 0.2838616714697406,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996012139329738,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.17962852418422698,
|
|
"num_tokens": 6771375.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.770864868164063,
|
|
"epoch": 0.28434197886647455,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995991710584228,
|
|
"loss": 5.6127,
|
|
"mean_token_accuracy": 0.17344165444374085,
|
|
"num_tokens": 6783252.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.664705038070679,
|
|
"epoch": 0.28482228626320844,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995971229693459,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.17210681587457657,
|
|
"num_tokens": 6795525.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.780670309066773,
|
|
"epoch": 0.28530259365994237,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995950696657909,
|
|
"loss": 5.5285,
|
|
"mean_token_accuracy": 0.18434083163738252,
|
|
"num_tokens": 6807212.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.617880916595459,
|
|
"epoch": 0.28578290105667625,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995930111478051,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.18253830969333648,
|
|
"num_tokens": 6819367.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.67643985748291,
|
|
"epoch": 0.2862632084534102,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995909474154365,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.18423326760530473,
|
|
"num_tokens": 6830405.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.620176124572754,
|
|
"epoch": 0.28674351585014407,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995888784687331,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.17934491336345673,
|
|
"num_tokens": 6841479.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.667870092391968,
|
|
"epoch": 0.287223823246878,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995868043077428,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.17985389232635499,
|
|
"num_tokens": 6851585.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.701903438568115,
|
|
"epoch": 0.2877041306436119,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995847249325137,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.1836439073085785,
|
|
"num_tokens": 6863176.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.728053426742553,
|
|
"epoch": 0.2881844380403458,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995826403430942,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.1827200844883919,
|
|
"num_tokens": 6874021.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2881844380403458,
|
|
"eval_entropy": 5.467494524030904,
|
|
"eval_loss": 5.550236225128174,
|
|
"eval_mean_token_accuracy": 0.187719893863362,
|
|
"eval_num_tokens": 6874021.0,
|
|
"eval_runtime": 20.6705,
|
|
"eval_samples_per_second": 1587.532,
|
|
"eval_steps_per_second": 198.448,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.704174375534057,
|
|
"epoch": 0.2886647454370797,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995805505395328,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.18029418736696243,
|
|
"num_tokens": 6884999.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.699745559692383,
|
|
"epoch": 0.28914505283381364,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004995784555218778,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.1831611156463623,
|
|
"num_tokens": 6897021.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.637732887268067,
|
|
"epoch": 0.2896253602305475,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995763552901779,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.18181773722171785,
|
|
"num_tokens": 6908320.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.748047924041748,
|
|
"epoch": 0.29010566762728146,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995742498444818,
|
|
"loss": 5.5131,
|
|
"mean_token_accuracy": 0.18566226214170456,
|
|
"num_tokens": 6919957.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.710698127746582,
|
|
"epoch": 0.2905859750240154,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995721391848387,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.17768509238958358,
|
|
"num_tokens": 6930531.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.712391090393067,
|
|
"epoch": 0.2910662824207493,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995700233112972,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.1782066062092781,
|
|
"num_tokens": 6942556.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.708733320236206,
|
|
"epoch": 0.2915465898174832,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995679022239066,
|
|
"loss": 5.5547,
|
|
"mean_token_accuracy": 0.1831905037164688,
|
|
"num_tokens": 6954410.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.706331968307495,
|
|
"epoch": 0.2920268972142171,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995657759227162,
|
|
"loss": 5.5624,
|
|
"mean_token_accuracy": 0.17520011961460114,
|
|
"num_tokens": 6964970.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.6419037818908695,
|
|
"epoch": 0.29250720461095103,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995636444077751,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.18813293129205705,
|
|
"num_tokens": 6976016.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.64836859703064,
|
|
"epoch": 0.2929875120076849,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995615076791333,
|
|
"loss": 5.4822,
|
|
"mean_token_accuracy": 0.18480593264102935,
|
|
"num_tokens": 6987199.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.643376255035401,
|
|
"epoch": 0.29346781940441885,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995593657368399,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.18682510256767274,
|
|
"num_tokens": 6999174.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.666988182067871,
|
|
"epoch": 0.29394812680115273,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499557218580945,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.1785376712679863,
|
|
"num_tokens": 7012148.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.61878514289856,
|
|
"epoch": 0.29442843419788667,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995550662114981,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.18653325736522675,
|
|
"num_tokens": 7023238.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.654002618789673,
|
|
"epoch": 0.29490874159462055,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995529086285495,
|
|
"loss": 5.5267,
|
|
"mean_token_accuracy": 0.1808794245123863,
|
|
"num_tokens": 7034944.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.678547668457031,
|
|
"epoch": 0.2953890489913545,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499550745832149,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.19032707810401917,
|
|
"num_tokens": 7046880.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.637848234176635,
|
|
"epoch": 0.29586935638808837,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995485778223471,
|
|
"loss": 5.4831,
|
|
"mean_token_accuracy": 0.17996930032968522,
|
|
"num_tokens": 7057678.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.570685338973999,
|
|
"epoch": 0.2963496637848223,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995464045991939,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.18621571809053422,
|
|
"num_tokens": 7068336.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.675237321853638,
|
|
"epoch": 0.2968299711815562,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049954422616274,
|
|
"loss": 5.5212,
|
|
"mean_token_accuracy": 0.17852572798728944,
|
|
"num_tokens": 7080341.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.806090068817139,
|
|
"epoch": 0.2973102785782901,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995420425130359,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.17285532206296922,
|
|
"num_tokens": 7090618.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.632469844818115,
|
|
"epoch": 0.297790585975024,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995398536501324,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.18980091959238052,
|
|
"num_tokens": 7101843.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.602583503723144,
|
|
"epoch": 0.29827089337175794,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995376595740801,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.18240708112716675,
|
|
"num_tokens": 7112014.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.6829828262329105,
|
|
"epoch": 0.2987512007684918,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995354602849302,
|
|
"loss": 5.57,
|
|
"mean_token_accuracy": 0.17665938287973404,
|
|
"num_tokens": 7123860.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.68782525062561,
|
|
"epoch": 0.29923150816522576,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995332557827337,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.1798730105161667,
|
|
"num_tokens": 7135901.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.678207349777222,
|
|
"epoch": 0.29971181556195964,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995310460675416,
|
|
"loss": 5.4903,
|
|
"mean_token_accuracy": 0.19226625710725784,
|
|
"num_tokens": 7148743.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.718117713928223,
|
|
"epoch": 0.3001921229586936,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995288311394053,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.18411389291286467,
|
|
"num_tokens": 7160731.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.695175981521606,
|
|
"epoch": 0.30067243035542746,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995266109983764,
|
|
"loss": 5.5379,
|
|
"mean_token_accuracy": 0.18051327168941497,
|
|
"num_tokens": 7172861.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.663706064224243,
|
|
"epoch": 0.3011527377521614,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995243856445062,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.1794595777988434,
|
|
"num_tokens": 7183954.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.54837441444397,
|
|
"epoch": 0.3016330451488953,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995221550778466,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.18403159081935883,
|
|
"num_tokens": 7195466.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.650097274780274,
|
|
"epoch": 0.3021133525456292,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995199192984491,
|
|
"loss": 5.445,
|
|
"mean_token_accuracy": 0.18828442096710205,
|
|
"num_tokens": 7207173.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.701932287216186,
|
|
"epoch": 0.3025936599423631,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995176783063657,
|
|
"loss": 5.5847,
|
|
"mean_token_accuracy": 0.1841903731226921,
|
|
"num_tokens": 7220095.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.633075094223022,
|
|
"epoch": 0.30307396733909703,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995154321016487,
|
|
"loss": 5.5079,
|
|
"mean_token_accuracy": 0.1826324224472046,
|
|
"num_tokens": 7230664.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.709785985946655,
|
|
"epoch": 0.3035542747358309,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995131806843499,
|
|
"loss": 5.4593,
|
|
"mean_token_accuracy": 0.18663873821496962,
|
|
"num_tokens": 7241278.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.560795783996582,
|
|
"epoch": 0.30403458213256485,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995109240545218,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.1759345531463623,
|
|
"num_tokens": 7252999.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.699498128890991,
|
|
"epoch": 0.3045148895292987,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995086622122167,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.1813385471701622,
|
|
"num_tokens": 7263949.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.637405109405518,
|
|
"epoch": 0.30499519692603266,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995063951574871,
|
|
"loss": 5.4896,
|
|
"mean_token_accuracy": 0.18765443116426467,
|
|
"num_tokens": 7275467.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.65950870513916,
|
|
"epoch": 0.30547550432276654,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995041228903856,
|
|
"loss": 5.4633,
|
|
"mean_token_accuracy": 0.19078702926635743,
|
|
"num_tokens": 7285534.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.745648288726807,
|
|
"epoch": 0.3059558117195005,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499501845410965,
|
|
"loss": 5.5733,
|
|
"mean_token_accuracy": 0.1831236869096756,
|
|
"num_tokens": 7297252.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.611358976364135,
|
|
"epoch": 0.30643611911623436,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994995627192781,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.18962527066469193,
|
|
"num_tokens": 7308492.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.604902219772339,
|
|
"epoch": 0.3069164265129683,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994972748153781,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.18148828595876693,
|
|
"num_tokens": 7319703.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.685352182388305,
|
|
"epoch": 0.30739673390970224,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499494981699318,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.19088191539049149,
|
|
"num_tokens": 7331022.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.615092754364014,
|
|
"epoch": 0.3078770413064361,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499492683371151,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.182320274412632,
|
|
"num_tokens": 7342977.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.697661113739014,
|
|
"epoch": 0.30835734870317005,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994903798309306,
|
|
"loss": 5.4744,
|
|
"mean_token_accuracy": 0.18243792206048964,
|
|
"num_tokens": 7353227.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.6787608623504635,
|
|
"epoch": 0.30883765609990393,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994880710787102,
|
|
"loss": 5.5267,
|
|
"mean_token_accuracy": 0.16992310285568238,
|
|
"num_tokens": 7364165.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.5938324451446535,
|
|
"epoch": 0.30931796349663787,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994857571145432,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.1885462373495102,
|
|
"num_tokens": 7374800.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.550031423568726,
|
|
"epoch": 0.30979827089337175,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994834379384837,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.1900305286049843,
|
|
"num_tokens": 7386360.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.643242835998535,
|
|
"epoch": 0.3102785782901057,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994811135505851,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.1852445274591446,
|
|
"num_tokens": 7397066.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.69812912940979,
|
|
"epoch": 0.31075888568683957,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994787839509018,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.1741228461265564,
|
|
"num_tokens": 7408349.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.671992778778076,
|
|
"epoch": 0.3112391930835735,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994764491394876,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.17537114769220352,
|
|
"num_tokens": 7420343.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.708970642089843,
|
|
"epoch": 0.3117195004803074,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994741091163969,
|
|
"loss": 5.4766,
|
|
"mean_token_accuracy": 0.18881572633981705,
|
|
"num_tokens": 7431683.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.49902081489563,
|
|
"epoch": 0.3121998078770413,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499471763881684,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.18738958537578582,
|
|
"num_tokens": 7443327.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.648282718658447,
|
|
"epoch": 0.3126801152737752,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994694134354031,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.18875627666711808,
|
|
"num_tokens": 7454002.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.579559707641602,
|
|
"epoch": 0.31316042267050914,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499467057777609,
|
|
"loss": 5.4831,
|
|
"mean_token_accuracy": 0.1835149794816971,
|
|
"num_tokens": 7464074.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.561008071899414,
|
|
"epoch": 0.313640730067243,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994646969083565,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.19485885351896287,
|
|
"num_tokens": 7475543.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.693277263641358,
|
|
"epoch": 0.31412103746397696,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994623308277002,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.18558466881513597,
|
|
"num_tokens": 7486818.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.665642356872558,
|
|
"epoch": 0.31460134486071084,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499459959535695,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.18450151830911637,
|
|
"num_tokens": 7499046.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.634830045700073,
|
|
"epoch": 0.3150816522574448,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994575830323962,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.17926069498062133,
|
|
"num_tokens": 7509853.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.514278316497803,
|
|
"epoch": 0.31556195965417866,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994552013178586,
|
|
"loss": 5.3046,
|
|
"mean_token_accuracy": 0.19069029539823532,
|
|
"num_tokens": 7521091.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.596073818206787,
|
|
"epoch": 0.3160422670509126,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499452814392138,
|
|
"loss": 5.4375,
|
|
"mean_token_accuracy": 0.19329715222120286,
|
|
"num_tokens": 7531317.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.64233808517456,
|
|
"epoch": 0.3165225744476465,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994504222552894,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.18084498941898347,
|
|
"num_tokens": 7542822.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.722558689117432,
|
|
"epoch": 0.3170028818443804,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994480249073684,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.18076840192079544,
|
|
"num_tokens": 7552434.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.598572635650635,
|
|
"epoch": 0.3174831892411143,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994456223484308,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.1927143394947052,
|
|
"num_tokens": 7563895.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.454520845413208,
|
|
"epoch": 0.31796349663784823,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994432145785323,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.18793661743402482,
|
|
"num_tokens": 7575391.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.677673196792602,
|
|
"epoch": 0.3184438040345821,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994408015977288,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.18976033180952073,
|
|
"num_tokens": 7587119.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.694156169891357,
|
|
"epoch": 0.31892411143131605,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994383834060764,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.17661510556936263,
|
|
"num_tokens": 7598615.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.696703481674194,
|
|
"epoch": 0.31940441882804993,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994359600036311,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.19055715948343277,
|
|
"num_tokens": 7610159.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.683110094070434,
|
|
"epoch": 0.31988472622478387,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994335313904493,
|
|
"loss": 5.4601,
|
|
"mean_token_accuracy": 0.18581361472606658,
|
|
"num_tokens": 7620922.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.582138109207153,
|
|
"epoch": 0.32036503362151775,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994310975665873,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.19046609699726105,
|
|
"num_tokens": 7632343.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.732189750671386,
|
|
"epoch": 0.3208453410182517,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994286585321017,
|
|
"loss": 5.5902,
|
|
"mean_token_accuracy": 0.17252802550792695,
|
|
"num_tokens": 7644748.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.710432291030884,
|
|
"epoch": 0.32132564841498557,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499426214287049,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.19114425033330917,
|
|
"num_tokens": 7655449.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.64078426361084,
|
|
"epoch": 0.3218059558117195,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994237648314862,
|
|
"loss": 5.5035,
|
|
"mean_token_accuracy": 0.18543385416269303,
|
|
"num_tokens": 7665623.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.554352760314941,
|
|
"epoch": 0.3222862632084534,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994213101654697,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.19078583717346193,
|
|
"num_tokens": 7676860.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.686653995513916,
|
|
"epoch": 0.3227665706051873,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499418850289057,
|
|
"loss": 5.5767,
|
|
"mean_token_accuracy": 0.18165411055088043,
|
|
"num_tokens": 7687778.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.667432641983032,
|
|
"epoch": 0.32324687800192126,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994163852023048,
|
|
"loss": 5.4775,
|
|
"mean_token_accuracy": 0.18488942384719848,
|
|
"num_tokens": 7699154.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.591152572631836,
|
|
"epoch": 0.32372718539865514,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994139149052706,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.18603985756635666,
|
|
"num_tokens": 7711010.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.668866777420044,
|
|
"epoch": 0.3242074927953891,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994114393980117,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.18332684338092803,
|
|
"num_tokens": 7721969.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.679357814788818,
|
|
"epoch": 0.32468780019212296,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.1889062002301216,
|
|
"num_tokens": 7733762.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.640239667892456,
|
|
"epoch": 0.3251681075888569,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994064727530496,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.1815125659108162,
|
|
"num_tokens": 7744614.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.564548492431641,
|
|
"epoch": 0.3256484149855908,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994039816154618,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.1951647639274597,
|
|
"num_tokens": 7755799.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.5753570079803465,
|
|
"epoch": 0.3261287223823247,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00049940148526788,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.1877640664577484,
|
|
"num_tokens": 7768140.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.5929913997650145,
|
|
"epoch": 0.3266090297790586,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993989837103618,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.1846913829445839,
|
|
"num_tokens": 7778494.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.708591794967651,
|
|
"epoch": 0.3270893371757925,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993964769429657,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.19035352319478988,
|
|
"num_tokens": 7789234.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.599575138092041,
|
|
"epoch": 0.3275696445725264,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993939649657498,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.1874484598636627,
|
|
"num_tokens": 7800602.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.562217473983765,
|
|
"epoch": 0.32804995196926034,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993914477787721,
|
|
"loss": 5.3376,
|
|
"mean_token_accuracy": 0.19393931627273558,
|
|
"num_tokens": 7812803.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.748968839645386,
|
|
"epoch": 0.3285302593659942,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993889253820915,
|
|
"loss": 5.6342,
|
|
"mean_token_accuracy": 0.1738002836704254,
|
|
"num_tokens": 7825432.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.6201917171478275,
|
|
"epoch": 0.32901056676272816,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993863977757663,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.18626101016998292,
|
|
"num_tokens": 7837258.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.545711612701416,
|
|
"epoch": 0.32949087415946204,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993838649598552,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.1965160608291626,
|
|
"num_tokens": 7847573.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.670653295516968,
|
|
"epoch": 0.329971181556196,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993813269344171,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.18039093613624574,
|
|
"num_tokens": 7857957.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.603359937667847,
|
|
"epoch": 0.33045148895292986,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993787836995108,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.19513991624116897,
|
|
"num_tokens": 7867996.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.527387523651123,
|
|
"epoch": 0.3309317963496638,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993762352551954,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.1835164800286293,
|
|
"num_tokens": 7879245.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.659226322174073,
|
|
"epoch": 0.3314121037463977,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993736816015301,
|
|
"loss": 5.5261,
|
|
"mean_token_accuracy": 0.17599146217107772,
|
|
"num_tokens": 7891186.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.6871460437774655,
|
|
"epoch": 0.3318924111431316,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993711227385742,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.19238765239715577,
|
|
"num_tokens": 7902231.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.626007223129273,
|
|
"epoch": 0.3323727185398655,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993685586663871,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.1862488716840744,
|
|
"num_tokens": 7913364.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.866927194595337,
|
|
"epoch": 0.33285302593659943,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993659893850281,
|
|
"loss": 5.6859,
|
|
"mean_token_accuracy": 0.17142274528741835,
|
|
"num_tokens": 7925217.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.592819738388061,
|
|
"epoch": 0.3333333333333333,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993634148945573,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.17677210867404938,
|
|
"num_tokens": 7937636.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.596171140670776,
|
|
"epoch": 0.33381364073006725,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993608351950341,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.18027846217155458,
|
|
"num_tokens": 7948958.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.671500778198242,
|
|
"epoch": 0.33429394812680113,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993582502865185,
|
|
"loss": 5.4924,
|
|
"mean_token_accuracy": 0.18664607107639314,
|
|
"num_tokens": 7960013.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.620531797409058,
|
|
"epoch": 0.33477425552353507,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993556601690706,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.1812283620238304,
|
|
"num_tokens": 7971041.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.660557413101197,
|
|
"epoch": 0.33525456292026895,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993530648427505,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.18094693422317504,
|
|
"num_tokens": 7982752.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.649030065536499,
|
|
"epoch": 0.3357348703170029,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993504643076184,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.18630249798297882,
|
|
"num_tokens": 7993681.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.596584844589233,
|
|
"epoch": 0.33621517771373677,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993478585637347,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.18762964010238647,
|
|
"num_tokens": 8004727.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.62527117729187,
|
|
"epoch": 0.3366954851104707,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993452476111599,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.19001320451498033,
|
|
"num_tokens": 8015423.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.621340608596801,
|
|
"epoch": 0.3371757925072046,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993426314499546,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.19290892481803895,
|
|
"num_tokens": 8027911.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.620342636108399,
|
|
"epoch": 0.3376560999039385,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993400100801796,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.18564309179782867,
|
|
"num_tokens": 8038831.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.51328182220459,
|
|
"epoch": 0.3381364073006724,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993373835018956,
|
|
"loss": 5.3275,
|
|
"mean_token_accuracy": 0.19699581563472748,
|
|
"num_tokens": 8049906.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.513483619689941,
|
|
"epoch": 0.33861671469740634,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993347517151638,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.18792010992765426,
|
|
"num_tokens": 8061158.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.646618938446045,
|
|
"epoch": 0.3390970220941403,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993321147200452,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.18583539128303528,
|
|
"num_tokens": 8071958.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.588662624359131,
|
|
"epoch": 0.33957732949087416,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499329472516601,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.18485624343156815,
|
|
"num_tokens": 8084068.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.4956859111785885,
|
|
"epoch": 0.3400576368876081,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993268251048925,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.198596853017807,
|
|
"num_tokens": 8096132.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.58132586479187,
|
|
"epoch": 0.340537944284342,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004993241724849814,
|
|
"loss": 5.4759,
|
|
"mean_token_accuracy": 0.1903732657432556,
|
|
"num_tokens": 8107327.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.608106994628907,
|
|
"epoch": 0.3410182516810759,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499321514656929,
|
|
"loss": 5.4608,
|
|
"mean_token_accuracy": 0.18965245932340621,
|
|
"num_tokens": 8118584.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.643239259719849,
|
|
"epoch": 0.3414985590778098,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993188516207972,
|
|
"loss": 5.4951,
|
|
"mean_token_accuracy": 0.18048142790794372,
|
|
"num_tokens": 8130081.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.573701095581055,
|
|
"epoch": 0.34197886647454373,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993161833766478,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.18741901069879532,
|
|
"num_tokens": 8141463.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.632593965530395,
|
|
"epoch": 0.3424591738712776,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993135099245426,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.18373015522956848,
|
|
"num_tokens": 8153863.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.53346095085144,
|
|
"epoch": 0.34293948126801155,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993108312645438,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.18515754789113997,
|
|
"num_tokens": 8165695.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.614653158187866,
|
|
"epoch": 0.34341978866474543,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993081473967135,
|
|
"loss": 5.4701,
|
|
"mean_token_accuracy": 0.1853488028049469,
|
|
"num_tokens": 8176456.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.65216178894043,
|
|
"epoch": 0.34390009606147937,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993054583211143,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.18880873173475266,
|
|
"num_tokens": 8189050.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.548917770385742,
|
|
"epoch": 0.34438040345821325,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993027640378081,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.18787043541669846,
|
|
"num_tokens": 8200011.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.564371919631958,
|
|
"epoch": 0.3448607108549472,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499300064546858,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.19150739163160324,
|
|
"num_tokens": 8211770.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.599589443206787,
|
|
"epoch": 0.34534101825168106,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992973598483264,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.19162243753671646,
|
|
"num_tokens": 8223582.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.68660888671875,
|
|
"epoch": 0.345821325648415,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499294649942276,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.18258577585220337,
|
|
"num_tokens": 8234336.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.620280456542969,
|
|
"epoch": 0.3463016330451489,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992919348287699,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.18839440494775772,
|
|
"num_tokens": 8244605.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.633523941040039,
|
|
"epoch": 0.3467819404418828,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992892145078711,
|
|
"loss": 5.5118,
|
|
"mean_token_accuracy": 0.18184645473957062,
|
|
"num_tokens": 8255876.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.564020156860352,
|
|
"epoch": 0.3472622478386167,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992864889796427,
|
|
"loss": 5.3966,
|
|
"mean_token_accuracy": 0.18950104862451553,
|
|
"num_tokens": 8266602.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.597898054122925,
|
|
"epoch": 0.34774255523535064,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004992837582441481,
|
|
"loss": 5.3843,
|
|
"mean_token_accuracy": 0.19015932381153106,
|
|
"num_tokens": 8279804.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.6535993099212645,
|
|
"epoch": 0.3482228626320845,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992810223014506,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.18701547533273696,
|
|
"num_tokens": 8291020.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.622987365722656,
|
|
"epoch": 0.34870317002881845,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992782811516137,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.19102343469858168,
|
|
"num_tokens": 8302192.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.582995176315308,
|
|
"epoch": 0.34918347742555234,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004992755347947011,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.1902191162109375,
|
|
"num_tokens": 8313649.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.5383587837219235,
|
|
"epoch": 0.34966378482228627,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992727832307766,
|
|
"loss": 5.3974,
|
|
"mean_token_accuracy": 0.18865602910518647,
|
|
"num_tokens": 8324694.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.71724762916565,
|
|
"epoch": 0.35014409221902015,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992700264599039,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.18377173095941543,
|
|
"num_tokens": 8336517.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.599456405639648,
|
|
"epoch": 0.3506243996157541,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004992672644821473,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.18044322580099106,
|
|
"num_tokens": 8349001.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.642662906646729,
|
|
"epoch": 0.35110470701248797,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992644972975707,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.19142407476902007,
|
|
"num_tokens": 8361230.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.532097005844117,
|
|
"epoch": 0.3515850144092219,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992617249062383,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.19701765477657318,
|
|
"num_tokens": 8372159.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.58645806312561,
|
|
"epoch": 0.3520653218059558,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992589473082147,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.18735242784023284,
|
|
"num_tokens": 8383228.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.640217876434326,
|
|
"epoch": 0.3525456292026897,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992561645035641,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.18576795011758804,
|
|
"num_tokens": 8394582.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.58097825050354,
|
|
"epoch": 0.3530259365994236,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992533764923515,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.187009534239769,
|
|
"num_tokens": 8406784.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.567069339752197,
|
|
"epoch": 0.35350624399615754,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992505832746412,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.19539184421300887,
|
|
"num_tokens": 8418405.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.581828355789185,
|
|
"epoch": 0.3539865513928914,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992477848504983,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.19186690151691438,
|
|
"num_tokens": 8430432.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.608822822570801,
|
|
"epoch": 0.35446685878962536,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992449812199877,
|
|
"loss": 5.5098,
|
|
"mean_token_accuracy": 0.18246612846851348,
|
|
"num_tokens": 8442423.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.603720855712891,
|
|
"epoch": 0.3549471661863593,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992421723831745,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.1835420086979866,
|
|
"num_tokens": 8454951.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.596175956726074,
|
|
"epoch": 0.3554274735830932,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992393583401239,
|
|
"loss": 5.368,
|
|
"mean_token_accuracy": 0.19326992928981782,
|
|
"num_tokens": 8467758.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.587682628631592,
|
|
"epoch": 0.3559077809798271,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992365390909014,
|
|
"loss": 5.4549,
|
|
"mean_token_accuracy": 0.18845424950122833,
|
|
"num_tokens": 8479728.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.616272878646851,
|
|
"epoch": 0.356388088376561,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992337146355721,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.18585399091243743,
|
|
"num_tokens": 8492099.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.6486982822418215,
|
|
"epoch": 0.35686839577329493,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992308849742019,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.17614103853702545,
|
|
"num_tokens": 8504657.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.613508033752441,
|
|
"epoch": 0.3573487031700288,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992280501068563,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.19100760966539382,
|
|
"num_tokens": 8514728.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.631121015548706,
|
|
"epoch": 0.35782901056676275,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992252100336012,
|
|
"loss": 5.5379,
|
|
"mean_token_accuracy": 0.1856612503528595,
|
|
"num_tokens": 8525588.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.616485548019409,
|
|
"epoch": 0.35830931796349663,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992223647545027,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.18350607752799988,
|
|
"num_tokens": 8537468.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.631916236877442,
|
|
"epoch": 0.35878962536023057,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992195142696266,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.1893299102783203,
|
|
"num_tokens": 8548598.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.418419742584229,
|
|
"epoch": 0.35926993275696445,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992166585790391,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.20219719260931016,
|
|
"num_tokens": 8560301.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.572213268280029,
|
|
"epoch": 0.3597502401536984,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992137976828067,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.19558291882276535,
|
|
"num_tokens": 8571186.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.578411054611206,
|
|
"epoch": 0.36023054755043227,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992109315809955,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.1940329760313034,
|
|
"num_tokens": 8580725.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.555987167358398,
|
|
"epoch": 0.3607108549471662,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004992080602736725,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.180860997736454,
|
|
"num_tokens": 8594598.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.739662742614746,
|
|
"epoch": 0.3611911623439001,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992051837609039,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.18189345002174379,
|
|
"num_tokens": 8606733.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.661942768096924,
|
|
"epoch": 0.361671469740634,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992023020427568,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.19026065915822982,
|
|
"num_tokens": 8618863.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.462978744506836,
|
|
"epoch": 0.3621517771373679,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991994151192979,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.19249616265296937,
|
|
"num_tokens": 8629270.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.561847591400147,
|
|
"epoch": 0.36263208453410184,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991965229905943,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.1881070166826248,
|
|
"num_tokens": 8641363.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.688853645324707,
|
|
"epoch": 0.3631123919308357,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991936256567133,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.18743191063404083,
|
|
"num_tokens": 8653233.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.547352027893067,
|
|
"epoch": 0.36359269932756966,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499190723117722,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.1837211713194847,
|
|
"num_tokens": 8665192.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.648187112808228,
|
|
"epoch": 0.36407300672430354,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991878153736877,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.17802536785602568,
|
|
"num_tokens": 8677669.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.492604207992554,
|
|
"epoch": 0.3645533141210375,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991849024246781,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.1957615062594414,
|
|
"num_tokens": 8688002.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.566503572463989,
|
|
"epoch": 0.36503362151777136,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991819842707608,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.19245349913835524,
|
|
"num_tokens": 8698396.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.637855195999146,
|
|
"epoch": 0.3655139289145053,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991790609120035,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.18937206119298935,
|
|
"num_tokens": 8711135.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.548817920684814,
|
|
"epoch": 0.3659942363112392,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499176132348474,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.19292772859334945,
|
|
"num_tokens": 8723707.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.611570119857788,
|
|
"epoch": 0.3664745437079731,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991731985802405,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.194192536175251,
|
|
"num_tokens": 8734193.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.5339254379272464,
|
|
"epoch": 0.366954851104707,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991702596073708,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.18580521792173385,
|
|
"num_tokens": 8745619.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.510940504074097,
|
|
"epoch": 0.36743515850144093,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991673154299335,
|
|
"loss": 5.368,
|
|
"mean_token_accuracy": 0.1902906373143196,
|
|
"num_tokens": 8757331.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.5497801303863525,
|
|
"epoch": 0.3679154658981748,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991643660479967,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.19248363822698594,
|
|
"num_tokens": 8768840.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.608413505554199,
|
|
"epoch": 0.36839577329490875,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991614114616289,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.19261340647935868,
|
|
"num_tokens": 8781214.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.616617870330811,
|
|
"epoch": 0.3688760806916426,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991584516708988,
|
|
"loss": 5.4095,
|
|
"mean_token_accuracy": 0.18974703997373582,
|
|
"num_tokens": 8791645.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.630726337432861,
|
|
"epoch": 0.36935638808837656,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991554866758751,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.18070310354232788,
|
|
"num_tokens": 8803286.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.639148473739624,
|
|
"epoch": 0.36983669548511044,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991525164766265,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.18947552740573884,
|
|
"num_tokens": 8814207.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.567518186569214,
|
|
"epoch": 0.3703170028818444,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991495410732222,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.18093401342630386,
|
|
"num_tokens": 8825540.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.613472604751587,
|
|
"epoch": 0.37079731027857826,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991465604657311,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.1754475399851799,
|
|
"num_tokens": 8838182.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.599302816390991,
|
|
"epoch": 0.3712776176753122,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991435746542224,
|
|
"loss": 5.4306,
|
|
"mean_token_accuracy": 0.19523921459913254,
|
|
"num_tokens": 8850211.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.560464334487915,
|
|
"epoch": 0.37175792507204614,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991405836387655,
|
|
"loss": 5.4749,
|
|
"mean_token_accuracy": 0.1841433361172676,
|
|
"num_tokens": 8862804.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.578405046463013,
|
|
"epoch": 0.37223823246878,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991375874194298,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.18286560624837875,
|
|
"num_tokens": 8874112.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.550269412994385,
|
|
"epoch": 0.37271853986551395,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499134585996285,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.19159672558307647,
|
|
"num_tokens": 8885114.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.586460971832276,
|
|
"epoch": 0.37319884726224783,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991315793694004,
|
|
"loss": 5.3307,
|
|
"mean_token_accuracy": 0.192276206612587,
|
|
"num_tokens": 8895555.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.524693441390991,
|
|
"epoch": 0.37367915465898177,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991285675388463,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.20285780131816863,
|
|
"num_tokens": 8906073.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.544021129608154,
|
|
"epoch": 0.37415946205571565,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991255505046922,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.18590356409549713,
|
|
"num_tokens": 8916587.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.61430516242981,
|
|
"epoch": 0.3746397694524496,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991225282670083,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.18587377518415452,
|
|
"num_tokens": 8927923.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.538893175125122,
|
|
"epoch": 0.37512007684918347,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499119500825865,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.19215198904275893,
|
|
"num_tokens": 8939939.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.523986291885376,
|
|
"epoch": 0.3756003842459174,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991164681813323,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.19619202464818955,
|
|
"num_tokens": 8951748.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.533074951171875,
|
|
"epoch": 0.3760806916426513,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991134303334807,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.19790138006210328,
|
|
"num_tokens": 8962922.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.467417430877686,
|
|
"epoch": 0.3765609990393852,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991103872823807,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.19722643196582795,
|
|
"num_tokens": 8974013.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.515323543548584,
|
|
"epoch": 0.3770413064361191,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499107339028103,
|
|
"loss": 5.3855,
|
|
"mean_token_accuracy": 0.1921772316098213,
|
|
"num_tokens": 8986032.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.610967826843262,
|
|
"epoch": 0.37752161383285304,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004991042855707184,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.1876501262187958,
|
|
"num_tokens": 8996889.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.524027967453003,
|
|
"epoch": 0.3780019212295869,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991012269102977,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.18921342343091965,
|
|
"num_tokens": 9007594.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.449644565582275,
|
|
"epoch": 0.37848222862632086,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990981630469119,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.19195079207420349,
|
|
"num_tokens": 9018097.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.576449728012085,
|
|
"epoch": 0.37896253602305474,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990950939806323,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.18259283453226088,
|
|
"num_tokens": 9029554.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.5739020824432375,
|
|
"epoch": 0.3794428434197887,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049909201971153,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.1885339617729187,
|
|
"num_tokens": 9042518.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.542482852935791,
|
|
"epoch": 0.37992315081652256,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990889402396763,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.19385820478200913,
|
|
"num_tokens": 9054524.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.561400604248047,
|
|
"epoch": 0.3804034582132565,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004990858555651431,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.1895818293094635,
|
|
"num_tokens": 9065375.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.515637397766113,
|
|
"epoch": 0.3808837656099904,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990827656880015,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.1950634926557541,
|
|
"num_tokens": 9076338.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.506933546066284,
|
|
"epoch": 0.3813640730067243,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990796706083235,
|
|
"loss": 5.3694,
|
|
"mean_token_accuracy": 0.188057541847229,
|
|
"num_tokens": 9088407.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.518592023849488,
|
|
"epoch": 0.3818443804034582,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990765703261809,
|
|
"loss": 5.3255,
|
|
"mean_token_accuracy": 0.19157813787460326,
|
|
"num_tokens": 9099833.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.4132482528686525,
|
|
"epoch": 0.38232468780019213,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990734648416458,
|
|
"loss": 5.2993,
|
|
"mean_token_accuracy": 0.19470689445734024,
|
|
"num_tokens": 9111126.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.551502323150634,
|
|
"epoch": 0.382804995196926,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990703541547901,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.19405279755592347,
|
|
"num_tokens": 9121979.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.61278281211853,
|
|
"epoch": 0.38328530259365995,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990672382656863,
|
|
"loss": 5.4075,
|
|
"mean_token_accuracy": 0.1920866474509239,
|
|
"num_tokens": 9132929.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.5851963520050045,
|
|
"epoch": 0.38376560999039383,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990641171744064,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.19273888766765596,
|
|
"num_tokens": 9143903.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.577231502532959,
|
|
"epoch": 0.38424591738712777,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990609908810231,
|
|
"loss": 5.4469,
|
|
"mean_token_accuracy": 0.18918763995170593,
|
|
"num_tokens": 9154416.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.5459951877594,
|
|
"epoch": 0.38472622478386165,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990578593856089,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.18706282377243041,
|
|
"num_tokens": 9165613.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.517359685897827,
|
|
"epoch": 0.3852065321805956,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990547226882366,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.19604209959506988,
|
|
"num_tokens": 9177884.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.608504676818848,
|
|
"epoch": 0.38568683957732947,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990515807889788,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.18097308576107024,
|
|
"num_tokens": 9190041.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.668904542922974,
|
|
"epoch": 0.3861671469740634,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990484336879087,
|
|
"loss": 5.4049,
|
|
"mean_token_accuracy": 0.19387364238500596,
|
|
"num_tokens": 9202390.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.502331256866455,
|
|
"epoch": 0.3866474543707973,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990452813850992,
|
|
"loss": 5.4057,
|
|
"mean_token_accuracy": 0.18983091711997985,
|
|
"num_tokens": 9213437.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.569727373123169,
|
|
"epoch": 0.3871277617675312,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004990421238806236,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.1795946553349495,
|
|
"num_tokens": 9226310.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.586350727081299,
|
|
"epoch": 0.38760806916426516,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990389611745551,
|
|
"loss": 5.3893,
|
|
"mean_token_accuracy": 0.19350333213806153,
|
|
"num_tokens": 9236271.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.618629360198975,
|
|
"epoch": 0.38808837656099904,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990357932669672,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.1930390328168869,
|
|
"num_tokens": 9247755.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.52394847869873,
|
|
"epoch": 0.388568683957733,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990326201579335,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.2017490491271019,
|
|
"num_tokens": 9259821.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.552427816390991,
|
|
"epoch": 0.38904899135446686,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990294418475274,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.1905425786972046,
|
|
"num_tokens": 9270663.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.550879764556885,
|
|
"epoch": 0.3895292987512008,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004990262583358231,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.1851213574409485,
|
|
"num_tokens": 9282588.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.5647125244140625,
|
|
"epoch": 0.3900096061479347,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990230696228943,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.18009695112705232,
|
|
"num_tokens": 9293368.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.598783493041992,
|
|
"epoch": 0.3904899135446686,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990198757088149,
|
|
"loss": 5.4702,
|
|
"mean_token_accuracy": 0.18485325574874878,
|
|
"num_tokens": 9305962.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.559340906143189,
|
|
"epoch": 0.3909702209414025,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990166765936593,
|
|
"loss": 5.3495,
|
|
"mean_token_accuracy": 0.1973833203315735,
|
|
"num_tokens": 9317955.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.53150486946106,
|
|
"epoch": 0.3914505283381364,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990134722775016,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.19113391786813735,
|
|
"num_tokens": 9329491.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.537538051605225,
|
|
"epoch": 0.3919308357348703,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990102627604162,
|
|
"loss": 5.483,
|
|
"mean_token_accuracy": 0.19353909343481063,
|
|
"num_tokens": 9341612.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.59714822769165,
|
|
"epoch": 0.39241114313160425,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990070480424778,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.18844473958015442,
|
|
"num_tokens": 9352302.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.568612432479858,
|
|
"epoch": 0.3928914505283381,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990038281237608,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.1887407511472702,
|
|
"num_tokens": 9363303.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.498561525344849,
|
|
"epoch": 0.39337175792507206,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990006030043401,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.18864162415266036,
|
|
"num_tokens": 9375878.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.547961282730102,
|
|
"epoch": 0.39385206532180594,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989973726842906,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.18958245515823363,
|
|
"num_tokens": 9388342.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.48880181312561,
|
|
"epoch": 0.3943323727185399,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989941371636872,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.19420120269060134,
|
|
"num_tokens": 9399047.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.567055034637451,
|
|
"epoch": 0.39481268011527376,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989908964426051,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.19254230260848998,
|
|
"num_tokens": 9410172.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.607863855361939,
|
|
"epoch": 0.3952929875120077,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989876505211194,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.18579558283090591,
|
|
"num_tokens": 9422287.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.619776344299316,
|
|
"epoch": 0.3957732949087416,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989843993993056,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.19312429577112197,
|
|
"num_tokens": 9433709.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.447456026077271,
|
|
"epoch": 0.3962536023054755,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989811430772392,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.19651771783828736,
|
|
"num_tokens": 9445138.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.522433710098267,
|
|
"epoch": 0.3967339097022094,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989778815549957,
|
|
"loss": 5.4104,
|
|
"mean_token_accuracy": 0.19089603275060654,
|
|
"num_tokens": 9455263.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.561570167541504,
|
|
"epoch": 0.39721421709894333,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989746148326508,
|
|
"loss": 5.3728,
|
|
"mean_token_accuracy": 0.18802272528409958,
|
|
"num_tokens": 9465491.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.456939458847046,
|
|
"epoch": 0.3976945244956772,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004989713429102805,
|
|
"loss": 5.3368,
|
|
"mean_token_accuracy": 0.18885795921087264,
|
|
"num_tokens": 9477601.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.559215688705445,
|
|
"epoch": 0.39817483189241115,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989680657879607,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.1909678354859352,
|
|
"num_tokens": 9489385.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.4989770412445065,
|
|
"epoch": 0.39865513928914503,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004989647834657675,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.20021265596151352,
|
|
"num_tokens": 9501131.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.475941276550293,
|
|
"epoch": 0.39913544668587897,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000498961495943777,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.19261130541563035,
|
|
"num_tokens": 9513094.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.646708154678345,
|
|
"epoch": 0.39961575408261285,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989582032220656,
|
|
"loss": 5.5307,
|
|
"mean_token_accuracy": 0.18555604368448259,
|
|
"num_tokens": 9524538.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.593398761749268,
|
|
"epoch": 0.4000960614793468,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989549053007096,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.19916174411773682,
|
|
"num_tokens": 9535284.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.515568971633911,
|
|
"epoch": 0.40057636887608067,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004989516021797858,
|
|
"loss": 5.4242,
|
|
"mean_token_accuracy": 0.1882516548037529,
|
|
"num_tokens": 9546472.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.554485511779785,
|
|
"epoch": 0.4010566762728146,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498948293859371,
|
|
"loss": 5.4202,
|
|
"mean_token_accuracy": 0.18679715245962142,
|
|
"num_tokens": 9558358.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.641470861434937,
|
|
"epoch": 0.4015369836695485,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004989449803395415,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.19269262552261351,
|
|
"num_tokens": 9570653.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.546628665924072,
|
|
"epoch": 0.4020172910662824,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004989416616203747,
|
|
"loss": 5.3869,
|
|
"mean_token_accuracy": 0.1908806025981903,
|
|
"num_tokens": 9582150.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.560229682922364,
|
|
"epoch": 0.4024975984630163,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989383377019476,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.19352059811353683,
|
|
"num_tokens": 9592462.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.506600999832154,
|
|
"epoch": 0.40297790585975024,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989350085843371,
|
|
"loss": 5.3262,
|
|
"mean_token_accuracy": 0.19509673863649368,
|
|
"num_tokens": 9604027.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.445934009552002,
|
|
"epoch": 0.4034582132564842,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004989316742676207,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.19528971016407012,
|
|
"num_tokens": 9616325.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.4403135776519775,
|
|
"epoch": 0.40393852065321806,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989283347518757,
|
|
"loss": 5.2888,
|
|
"mean_token_accuracy": 0.19427725523710251,
|
|
"num_tokens": 9628133.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.6427380561828615,
|
|
"epoch": 0.404418828049952,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989249900371797,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.1834379181265831,
|
|
"num_tokens": 9639686.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.576334476470947,
|
|
"epoch": 0.4048991354466859,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989216401236103,
|
|
"loss": 5.3872,
|
|
"mean_token_accuracy": 0.19191829711198807,
|
|
"num_tokens": 9650222.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.450829315185547,
|
|
"epoch": 0.4053794428434198,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989182850112455,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.2054572194814682,
|
|
"num_tokens": 9661792.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.533667945861817,
|
|
"epoch": 0.4058597502401537,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989149247001629,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.18864203095436097,
|
|
"num_tokens": 9673000.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.57403678894043,
|
|
"epoch": 0.40634005763688763,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989115591904407,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.19470216035842897,
|
|
"num_tokens": 9685253.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.4957459449768065,
|
|
"epoch": 0.4068203650336215,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004989081884821569,
|
|
"loss": 5.3394,
|
|
"mean_token_accuracy": 0.18996310979127884,
|
|
"num_tokens": 9697245.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.490689039230347,
|
|
"epoch": 0.40730067243035545,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989048125753899,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.19019463509321213,
|
|
"num_tokens": 9710095.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.472829914093017,
|
|
"epoch": 0.40778097982708933,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000498901431470218,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.20080252438783647,
|
|
"num_tokens": 9721488.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.3933182716369625,
|
|
"epoch": 0.40826128722382327,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988980451667198,
|
|
"loss": 5.2043,
|
|
"mean_token_accuracy": 0.1991969019174576,
|
|
"num_tokens": 9733280.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.4942357540130615,
|
|
"epoch": 0.40874159462055715,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988946536649737,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.18908474445343018,
|
|
"num_tokens": 9744514.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.509702730178833,
|
|
"epoch": 0.4092219020172911,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988912569650585,
|
|
"loss": 5.3416,
|
|
"mean_token_accuracy": 0.19426414370536804,
|
|
"num_tokens": 9754931.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.42921404838562,
|
|
"epoch": 0.40970220941402496,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004988878550670533,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.19834061712026596,
|
|
"num_tokens": 9765635.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.563821077346802,
|
|
"epoch": 0.4101825168107589,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988844479710369,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.18279904276132583,
|
|
"num_tokens": 9777512.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.6497407913208,
|
|
"epoch": 0.4106628242074928,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004988810356770884,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.17943356335163116,
|
|
"num_tokens": 9790128.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.516012334823609,
|
|
"epoch": 0.4111431316042267,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498877618185287,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.19427798241376876,
|
|
"num_tokens": 9802549.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.486606025695801,
|
|
"epoch": 0.4116234390009606,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988741954957121,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.19245170205831527,
|
|
"num_tokens": 9813736.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.4289391040802,
|
|
"epoch": 0.41210374639769454,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988707676084432,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.20583047419786454,
|
|
"num_tokens": 9823785.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.480359363555908,
|
|
"epoch": 0.4125840537944284,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988673345235597,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.1970909520983696,
|
|
"num_tokens": 9834910.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.525894498825073,
|
|
"epoch": 0.41306436119116235,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988638962411416,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.19386228919029236,
|
|
"num_tokens": 9845593.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.436275625228882,
|
|
"epoch": 0.41354466858789624,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988604527612685,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.20476569086313248,
|
|
"num_tokens": 9856763.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.573514127731324,
|
|
"epoch": 0.4140249759846302,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988570040840205,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.18456612378358841,
|
|
"num_tokens": 9869528.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.480060815811157,
|
|
"epoch": 0.41450528338136405,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988535502094774,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.19747838228940964,
|
|
"num_tokens": 9881170.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.5313794136047365,
|
|
"epoch": 0.414985590778098,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988500911377198,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.1888141453266144,
|
|
"num_tokens": 9893119.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.4053281307220455,
|
|
"epoch": 0.41546589817483187,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004988466268688276,
|
|
"loss": 5.2654,
|
|
"mean_token_accuracy": 0.20344866067171097,
|
|
"num_tokens": 9905339.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.571810483932495,
|
|
"epoch": 0.4159462055715658,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004988431574028814,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.19604763239622117,
|
|
"num_tokens": 9917500.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.524722290039063,
|
|
"epoch": 0.4164265129682997,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988396827399618,
|
|
"loss": 5.4356,
|
|
"mean_token_accuracy": 0.18719332963228225,
|
|
"num_tokens": 9929667.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.520600318908691,
|
|
"epoch": 0.4169068203650336,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004988362028801495,
|
|
"loss": 5.3503,
|
|
"mean_token_accuracy": 0.19482496231794358,
|
|
"num_tokens": 9941102.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.45862774848938,
|
|
"epoch": 0.4173871277617675,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988327178235253,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.2036656454205513,
|
|
"num_tokens": 9951986.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.434820699691772,
|
|
"epoch": 0.41786743515850144,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004988292275701699,
|
|
"loss": 5.2608,
|
|
"mean_token_accuracy": 0.19801096320152284,
|
|
"num_tokens": 9964486.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.481801605224609,
|
|
"epoch": 0.4183477425552353,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988257321201646,
|
|
"loss": 5.3643,
|
|
"mean_token_accuracy": 0.19375134259462357,
|
|
"num_tokens": 9975909.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.512979364395141,
|
|
"epoch": 0.41882804995196926,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988222314735902,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.19729440063238143,
|
|
"num_tokens": 9986951.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.606730222702026,
|
|
"epoch": 0.41930835734870314,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988187256305284,
|
|
"loss": 5.4677,
|
|
"mean_token_accuracy": 0.1853739634156227,
|
|
"num_tokens": 9999234.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.498926258087158,
|
|
"epoch": 0.4197886647454371,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988152145910603,
|
|
"loss": 5.3337,
|
|
"mean_token_accuracy": 0.20228377282619475,
|
|
"num_tokens": 10010178.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.419414520263672,
|
|
"epoch": 0.420268972142171,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988116983552675,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.194709937274456,
|
|
"num_tokens": 10021183.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.632723474502564,
|
|
"epoch": 0.4207492795389049,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988081769232317,
|
|
"loss": 5.5847,
|
|
"mean_token_accuracy": 0.1804965242743492,
|
|
"num_tokens": 10033686.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.490194416046142,
|
|
"epoch": 0.42122958693563883,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988046502950346,
|
|
"loss": 5.2806,
|
|
"mean_token_accuracy": 0.19382549822330475,
|
|
"num_tokens": 10045923.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.338625478744507,
|
|
"epoch": 0.4217098943323727,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000498801118470758,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.20119253993034364,
|
|
"num_tokens": 10057196.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.4828390121459964,
|
|
"epoch": 0.42219020172910665,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498797581450484,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.19160341322422028,
|
|
"num_tokens": 10069655.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.533946561813354,
|
|
"epoch": 0.42267050912584053,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987940392342948,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.19662789553403853,
|
|
"num_tokens": 10080876.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.507131290435791,
|
|
"epoch": 0.42315081652257447,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987904918222726,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.19040922522544862,
|
|
"num_tokens": 10091986.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.542103242874146,
|
|
"epoch": 0.42363112391930835,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987869392144996,
|
|
"loss": 5.4415,
|
|
"mean_token_accuracy": 0.19244588911533356,
|
|
"num_tokens": 10104027.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.522120523452759,
|
|
"epoch": 0.4241114313160423,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987833814110584,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.19760800004005433,
|
|
"num_tokens": 10114665.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.473827123641968,
|
|
"epoch": 0.42459173871277617,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987798184120316,
|
|
"loss": 5.3303,
|
|
"mean_token_accuracy": 0.19874691665172578,
|
|
"num_tokens": 10126032.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.56437931060791,
|
|
"epoch": 0.4250720461095101,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987762502175018,
|
|
"loss": 5.3934,
|
|
"mean_token_accuracy": 0.18887989372015,
|
|
"num_tokens": 10137256.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.421947860717774,
|
|
"epoch": 0.425552353506244,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498772676827552,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.19916727691888808,
|
|
"num_tokens": 10149445.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.51547532081604,
|
|
"epoch": 0.4260326609029779,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004987690982422652,
|
|
"loss": 5.3958,
|
|
"mean_token_accuracy": 0.1895904004573822,
|
|
"num_tokens": 10161607.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.549444389343262,
|
|
"epoch": 0.4265129682997118,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987655144617243,
|
|
"loss": 5.4129,
|
|
"mean_token_accuracy": 0.19335524141788482,
|
|
"num_tokens": 10173184.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.520701122283936,
|
|
"epoch": 0.42699327569644574,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987619254860126,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.20056545436382295,
|
|
"num_tokens": 10184617.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.515553379058838,
|
|
"epoch": 0.4274735830931796,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987583313152134,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.19518428593873977,
|
|
"num_tokens": 10195608.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.488814115524292,
|
|
"epoch": 0.42795389048991356,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987547319494104,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.19026617109775543,
|
|
"num_tokens": 10206763.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.541830825805664,
|
|
"epoch": 0.42843419788664744,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004987511273886867,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.19727638810873033,
|
|
"num_tokens": 10218714.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.502747392654419,
|
|
"epoch": 0.4289145052833814,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004987475176331263,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.18761258721351623,
|
|
"num_tokens": 10229902.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.464094400405884,
|
|
"epoch": 0.42939481268011526,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004987439026828129,
|
|
"loss": 5.2389,
|
|
"mean_token_accuracy": 0.1978443130850792,
|
|
"num_tokens": 10241578.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.39894585609436,
|
|
"epoch": 0.4298751200768492,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987402825378305,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.2003094583749771,
|
|
"num_tokens": 10252109.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.5236156463623045,
|
|
"epoch": 0.4303554274735831,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987366571982631,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.1925773411989212,
|
|
"num_tokens": 10263357.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.555547142028809,
|
|
"epoch": 0.430835734870317,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987330266641948,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.18810010105371475,
|
|
"num_tokens": 10275536.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.5469659805297855,
|
|
"epoch": 0.4313160422670509,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004987293909357101,
|
|
"loss": 5.3566,
|
|
"mean_token_accuracy": 0.19789600372314453,
|
|
"num_tokens": 10286901.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.410230827331543,
|
|
"epoch": 0.43179634966378483,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987257500128933,
|
|
"loss": 5.2626,
|
|
"mean_token_accuracy": 0.1930641770362854,
|
|
"num_tokens": 10298961.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.526727294921875,
|
|
"epoch": 0.4322766570605187,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004987221038958288,
|
|
"loss": 5.3875,
|
|
"mean_token_accuracy": 0.19502759724855423,
|
|
"num_tokens": 10310911.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.566359043121338,
|
|
"epoch": 0.43275696445725265,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987184525846015,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.18737707734107972,
|
|
"num_tokens": 10322267.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.477842903137207,
|
|
"epoch": 0.4332372718539865,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987147960792958,
|
|
"loss": 5.4036,
|
|
"mean_token_accuracy": 0.19320885390043258,
|
|
"num_tokens": 10335111.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.582201528549194,
|
|
"epoch": 0.43371757925072046,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987111343799971,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.19570576399564743,
|
|
"num_tokens": 10345672.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.567843389511109,
|
|
"epoch": 0.43419788664745435,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00049870746748679,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.19766930043697356,
|
|
"num_tokens": 10357369.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.494852113723755,
|
|
"epoch": 0.4346781940441883,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987037953997598,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.19237277954816817,
|
|
"num_tokens": 10368842.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.473773574829101,
|
|
"epoch": 0.43515850144092216,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987001181189918,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.19634409248828888,
|
|
"num_tokens": 10380096.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.398287105560303,
|
|
"epoch": 0.4356388088376561,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986964356445713,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.1937148690223694,
|
|
"num_tokens": 10391996.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.496431159973144,
|
|
"epoch": 0.43611911623439004,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986927479765837,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.1934656947851181,
|
|
"num_tokens": 10403607.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.511260318756103,
|
|
"epoch": 0.4365994236311239,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986890551151148,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.1925230547785759,
|
|
"num_tokens": 10413580.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.47296986579895,
|
|
"epoch": 0.43707973102785785,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986853570602503,
|
|
"loss": 5.3258,
|
|
"mean_token_accuracy": 0.19467985332012178,
|
|
"num_tokens": 10426456.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.578516864776612,
|
|
"epoch": 0.43756003842459174,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004986816538120758,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.18571384996175766,
|
|
"num_tokens": 10438869.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.476364612579346,
|
|
"epoch": 0.43804034582132567,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004986779453706778,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.18391507416963576,
|
|
"num_tokens": 10450672.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.489961862564087,
|
|
"epoch": 0.43852065321805955,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986742317361419,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.20194608271121978,
|
|
"num_tokens": 10461890.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.555417490005493,
|
|
"epoch": 0.4390009606147935,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986705129085546,
|
|
"loss": 5.4116,
|
|
"mean_token_accuracy": 0.18422490060329438,
|
|
"num_tokens": 10473866.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.551934766769409,
|
|
"epoch": 0.43948126801152737,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004986667888880021,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.19357246905565262,
|
|
"num_tokens": 10484889.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.465532112121582,
|
|
"epoch": 0.4399615754082613,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004986630596745709,
|
|
"loss": 5.355,
|
|
"mean_token_accuracy": 0.19461666494607927,
|
|
"num_tokens": 10496108.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.503142023086548,
|
|
"epoch": 0.4404418828049952,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986593252683477,
|
|
"loss": 5.3168,
|
|
"mean_token_accuracy": 0.19193545132875442,
|
|
"num_tokens": 10505472.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.371403980255127,
|
|
"epoch": 0.4409221902017291,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986555856694191,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.2004853069782257,
|
|
"num_tokens": 10516954.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.551608276367188,
|
|
"epoch": 0.441402497598463,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986518408778718,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.19154966324567796,
|
|
"num_tokens": 10528166.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.461075639724731,
|
|
"epoch": 0.44188280499519694,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986480908937929,
|
|
"loss": 5.2563,
|
|
"mean_token_accuracy": 0.19935419112443925,
|
|
"num_tokens": 10538112.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.530212450027466,
|
|
"epoch": 0.4423631123919308,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986443357172695,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.19479911625385285,
|
|
"num_tokens": 10549888.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.653611516952514,
|
|
"epoch": 0.44284341978866476,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004986405753483887,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.1801862746477127,
|
|
"num_tokens": 10561710.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.439924049377441,
|
|
"epoch": 0.44332372718539864,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004986368097872377,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.1889050930738449,
|
|
"num_tokens": 10574564.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.5105362892150875,
|
|
"epoch": 0.4438040345821326,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004986330390339042,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.19357553124427795,
|
|
"num_tokens": 10586639.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.502204561233521,
|
|
"epoch": 0.44428434197886646,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986292630884755,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.1955375999212265,
|
|
"num_tokens": 10598730.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.417471694946289,
|
|
"epoch": 0.4447646493756004,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986254819510393,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.20689018219709396,
|
|
"num_tokens": 10610352.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.460666942596435,
|
|
"epoch": 0.4452449567723343,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986216956216835,
|
|
"loss": 5.3129,
|
|
"mean_token_accuracy": 0.1962559252977371,
|
|
"num_tokens": 10621951.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.489536237716675,
|
|
"epoch": 0.4457252641690682,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000498617904100496,
|
|
"loss": 5.2536,
|
|
"mean_token_accuracy": 0.1979408711194992,
|
|
"num_tokens": 10633207.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.551165294647217,
|
|
"epoch": 0.4462055715658021,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986141073875646,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.186821448802948,
|
|
"num_tokens": 10645853.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.432143926620483,
|
|
"epoch": 0.44668587896253603,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004986103054829779,
|
|
"loss": 5.27,
|
|
"mean_token_accuracy": 0.19958215057849885,
|
|
"num_tokens": 10656892.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.428584432601928,
|
|
"epoch": 0.4471661863592699,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004986064983868237,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.19150467962026596,
|
|
"num_tokens": 10670110.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.511739206314087,
|
|
"epoch": 0.44764649375600385,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986026860991906,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.19259512722492217,
|
|
"num_tokens": 10681255.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.514628124237061,
|
|
"epoch": 0.44812680115273773,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985988686201672,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.19111472219228745,
|
|
"num_tokens": 10692631.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.506016063690185,
|
|
"epoch": 0.44860710854947167,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004985950459498419,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.19589586406946183,
|
|
"num_tokens": 10704880.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.485089635848999,
|
|
"epoch": 0.44908741594620555,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004985912180883037,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.20430310666561127,
|
|
"num_tokens": 10715561.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.413974857330322,
|
|
"epoch": 0.4495677233429395,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985873850356411,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.19555141776800156,
|
|
"num_tokens": 10727232.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.413888311386108,
|
|
"epoch": 0.45004803073967337,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985835467919436,
|
|
"loss": 5.2991,
|
|
"mean_token_accuracy": 0.20086562782526016,
|
|
"num_tokens": 10739404.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.5062575340271,
|
|
"epoch": 0.4505283381364073,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985797033572999,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.19117717891931535,
|
|
"num_tokens": 10751948.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.458573246002198,
|
|
"epoch": 0.4510086455331412,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985758547317994,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.19499971568584443,
|
|
"num_tokens": 10764611.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.518351459503174,
|
|
"epoch": 0.4514889529298751,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004985720009155315,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.19280190467834474,
|
|
"num_tokens": 10775954.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.475862789154053,
|
|
"epoch": 0.45196926032660906,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985681419085856,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.18717591017484664,
|
|
"num_tokens": 10788723.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.48907470703125,
|
|
"epoch": 0.45244956772334294,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985642777110513,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.19800368696451187,
|
|
"num_tokens": 10799879.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.421358299255371,
|
|
"epoch": 0.4529298751200769,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004985604083230183,
|
|
"loss": 5.2791,
|
|
"mean_token_accuracy": 0.19696285873651503,
|
|
"num_tokens": 10811838.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.494543981552124,
|
|
"epoch": 0.45341018251681076,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985565337445765,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.19829083234071732,
|
|
"num_tokens": 10822910.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.533810424804687,
|
|
"epoch": 0.4538904899135447,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004985526539758158,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.19275055080652237,
|
|
"num_tokens": 10835344.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.468215227127075,
|
|
"epoch": 0.4543707973102786,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004985487690168263,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.19680845141410827,
|
|
"num_tokens": 10846043.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.478121185302735,
|
|
"epoch": 0.4548511047070125,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000498544878867698,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.20072862654924392,
|
|
"num_tokens": 10857783.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.474717378616333,
|
|
"epoch": 0.4553314121037464,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985409835285215,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.19704768657684327,
|
|
"num_tokens": 10870527.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.464604425430298,
|
|
"epoch": 0.45581171950048033,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004985370829993873,
|
|
"loss": 5.304,
|
|
"mean_token_accuracy": 0.20295322835445403,
|
|
"num_tokens": 10882285.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.4915252208709715,
|
|
"epoch": 0.4562920268972142,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004985331772803857,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.1975204363465309,
|
|
"num_tokens": 10895319.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.524920082092285,
|
|
"epoch": 0.45677233429394815,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004985292663716074,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.1974620059132576,
|
|
"num_tokens": 10906253.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.351269483566284,
|
|
"epoch": 0.457252641690682,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004985253502731435,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.2055060312151909,
|
|
"num_tokens": 10918197.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.476984643936158,
|
|
"epoch": 0.45773294908741596,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004985214289850845,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.19004748165607452,
|
|
"num_tokens": 10930771.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.489283180236816,
|
|
"epoch": 0.45821325648414984,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004985175025075217,
|
|
"loss": 5.2985,
|
|
"mean_token_accuracy": 0.19462554901838303,
|
|
"num_tokens": 10942759.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.6803840637207035,
|
|
"epoch": 0.4586935638808838,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985135708405462,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.18637332171201706,
|
|
"num_tokens": 10953557.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.436570262908935,
|
|
"epoch": 0.45917387127761766,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004985096339842493,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.20460412800312042,
|
|
"num_tokens": 10963142.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.396737003326416,
|
|
"epoch": 0.4596541786743516,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985056919387224,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.202386274933815,
|
|
"num_tokens": 10974321.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.550132369995117,
|
|
"epoch": 0.4601344860710855,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985017447040569,
|
|
"loss": 5.43,
|
|
"mean_token_accuracy": 0.19050837010145188,
|
|
"num_tokens": 10985524.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.525373315811157,
|
|
"epoch": 0.4606147934678194,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004984977922803447,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.19777408093214036,
|
|
"num_tokens": 10997606.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.440893602371216,
|
|
"epoch": 0.4610951008645533,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004984938346676772,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.1897636130452156,
|
|
"num_tokens": 11010692.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.451299047470092,
|
|
"epoch": 0.46157540826128723,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984898718661468,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.20564369410276412,
|
|
"num_tokens": 11022517.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.449737644195556,
|
|
"epoch": 0.4620557156580211,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984859038758451,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.20158778578042985,
|
|
"num_tokens": 11033141.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.4242347240447994,
|
|
"epoch": 0.46253602305475505,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004984819306968642,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.19843853563070296,
|
|
"num_tokens": 11044619.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.555520963668823,
|
|
"epoch": 0.46301633045148893,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004984779523292966,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.19956816583871842,
|
|
"num_tokens": 11055934.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.463156366348267,
|
|
"epoch": 0.46349663784822287,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984739687732345,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.2006239727139473,
|
|
"num_tokens": 11066203.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.269961309432984,
|
|
"epoch": 0.46397694524495675,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004984699800287705,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.2056365504860878,
|
|
"num_tokens": 11079664.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.376195335388184,
|
|
"epoch": 0.4644572526416907,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000498465986095997,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.2033955082297325,
|
|
"num_tokens": 11091186.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.497678804397583,
|
|
"epoch": 0.46493756003842457,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984619869750069,
|
|
"loss": 5.3304,
|
|
"mean_token_accuracy": 0.18890146911144257,
|
|
"num_tokens": 11102710.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.408234453201294,
|
|
"epoch": 0.4654178674351585,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498457982665893,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.2038560301065445,
|
|
"num_tokens": 11114746.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.460979413986206,
|
|
"epoch": 0.4658981748318924,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984539731687483,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.195130418241024,
|
|
"num_tokens": 11126572.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.4305055141448975,
|
|
"epoch": 0.4663784822286263,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004984499584836659,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.20321067571640014,
|
|
"num_tokens": 11137830.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.377715015411377,
|
|
"epoch": 0.4668587896253602,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498445938610739,
|
|
"loss": 5.2293,
|
|
"mean_token_accuracy": 0.2016708493232727,
|
|
"num_tokens": 11148860.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.479203367233277,
|
|
"epoch": 0.46733909702209414,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004984419135500608,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.18884660452604293,
|
|
"num_tokens": 11161311.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.443951034545899,
|
|
"epoch": 0.4678194044188281,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984378833017249,
|
|
"loss": 5.2379,
|
|
"mean_token_accuracy": 0.19662537276744843,
|
|
"num_tokens": 11173124.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.412505626678467,
|
|
"epoch": 0.46829971181556196,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984338478658248,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.19596934467554092,
|
|
"num_tokens": 11184879.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.530852127075195,
|
|
"epoch": 0.4687800192122959,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004984298072424542,
|
|
"loss": 5.3221,
|
|
"mean_token_accuracy": 0.19306136071681976,
|
|
"num_tokens": 11196243.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.437544488906861,
|
|
"epoch": 0.4692603266090298,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000498425761431707,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.20993078351020814,
|
|
"num_tokens": 11207485.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.378513956069947,
|
|
"epoch": 0.4697406340057637,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000498421710433677,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.19690736532211303,
|
|
"num_tokens": 11219891.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.515623712539673,
|
|
"epoch": 0.4702209414024976,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004984176542484584,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.19684761762619019,
|
|
"num_tokens": 11231329.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.420218229293823,
|
|
"epoch": 0.47070124879923153,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984135928761452,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.20384916067123413,
|
|
"num_tokens": 11241367.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.4436530590057375,
|
|
"epoch": 0.4711815561959654,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004984095263168317,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.19205039143562316,
|
|
"num_tokens": 11254532.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.55198187828064,
|
|
"epoch": 0.47166186359269935,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984054545706124,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.18903273940086365,
|
|
"num_tokens": 11265223.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.435238647460937,
|
|
"epoch": 0.47214217098943323,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000498401377637582,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.19942667335271835,
|
|
"num_tokens": 11278228.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.531127023696899,
|
|
"epoch": 0.47262247838616717,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000498397295517835,
|
|
"loss": 5.4152,
|
|
"mean_token_accuracy": 0.1892762526869774,
|
|
"num_tokens": 11289654.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.441771411895752,
|
|
"epoch": 0.47310278578290105,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004983932082114659,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.20304778963327408,
|
|
"num_tokens": 11301911.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.547307014465332,
|
|
"epoch": 0.473583093179635,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004983891157185699,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.19476744085550307,
|
|
"num_tokens": 11312945.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.594564008712768,
|
|
"epoch": 0.47406340057636887,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983850180392421,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.186136656999588,
|
|
"num_tokens": 11324126.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.489442443847656,
|
|
"epoch": 0.4745437079731028,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983809151735775,
|
|
"loss": 5.345,
|
|
"mean_token_accuracy": 0.19110574275255204,
|
|
"num_tokens": 11336395.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.506710433959961,
|
|
"epoch": 0.4750240153698367,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004983768071216713,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.1983468234539032,
|
|
"num_tokens": 11347387.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.399397993087769,
|
|
"epoch": 0.4755043227665706,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004983726938836189,
|
|
"loss": 5.2472,
|
|
"mean_token_accuracy": 0.20188201814889908,
|
|
"num_tokens": 11358467.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.4775426387786865,
|
|
"epoch": 0.4759846301633045,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983685754595159,
|
|
"loss": 5.4131,
|
|
"mean_token_accuracy": 0.18820505440235138,
|
|
"num_tokens": 11370322.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.378913688659668,
|
|
"epoch": 0.47646493756003844,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004983644518494578,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.20417440831661224,
|
|
"num_tokens": 11381719.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.415813398361206,
|
|
"epoch": 0.4769452449567723,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004983603230535403,
|
|
"loss": 5.2357,
|
|
"mean_token_accuracy": 0.19860472083091735,
|
|
"num_tokens": 11393561.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.506166219711304,
|
|
"epoch": 0.47742555235350626,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004983561890718594,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.19491951316595077,
|
|
"num_tokens": 11405411.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.578386402130127,
|
|
"epoch": 0.47790585975024014,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498352049904511,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.1887726828455925,
|
|
"num_tokens": 11417419.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.438750505447388,
|
|
"epoch": 0.4783861671469741,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983479055515914,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.19747813940048217,
|
|
"num_tokens": 11428145.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.37105541229248,
|
|
"epoch": 0.47886647454370795,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983437560131964,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.20008998066186906,
|
|
"num_tokens": 11439224.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.454404306411743,
|
|
"epoch": 0.4793467819404419,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983396012894228,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.1926464319229126,
|
|
"num_tokens": 11451731.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.503137922286987,
|
|
"epoch": 0.47982708933717577,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983354413803666,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.20034031867980956,
|
|
"num_tokens": 11463058.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.568387126922607,
|
|
"epoch": 0.4803073967339097,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983312762861248,
|
|
"loss": 5.3678,
|
|
"mean_token_accuracy": 0.19228482842445374,
|
|
"num_tokens": 11472618.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.427599239349365,
|
|
"epoch": 0.4807877041306436,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983271060067939,
|
|
"loss": 5.2494,
|
|
"mean_token_accuracy": 0.19887056648731233,
|
|
"num_tokens": 11483114.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.37850604057312,
|
|
"epoch": 0.4812680115273775,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983229305424707,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.20153291821479796,
|
|
"num_tokens": 11494281.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.467651128768921,
|
|
"epoch": 0.4817483189241114,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004983187498932522,
|
|
"loss": 5.3153,
|
|
"mean_token_accuracy": 0.19636951982975007,
|
|
"num_tokens": 11505962.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.497737312316895,
|
|
"epoch": 0.48222862632084534,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004983145640592354,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.19193184673786162,
|
|
"num_tokens": 11517558.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.4847935199737545,
|
|
"epoch": 0.4827089337175792,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004983103730405176,
|
|
"loss": 5.3696,
|
|
"mean_token_accuracy": 0.19255296885967255,
|
|
"num_tokens": 11529184.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.436256265640258,
|
|
"epoch": 0.48318924111431316,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498306176837196,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.19038698375225066,
|
|
"num_tokens": 11540727.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.436978578567505,
|
|
"epoch": 0.48366954851104704,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004983019754493681,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.20015370547771455,
|
|
"num_tokens": 11551510.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.481416273117065,
|
|
"epoch": 0.484149855907781,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004982977688771314,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.19754620641469955,
|
|
"num_tokens": 11563203.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.4130464553833,
|
|
"epoch": 0.4846301633045149,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004982935571205835,
|
|
"loss": 5.2229,
|
|
"mean_token_accuracy": 0.20334694683551788,
|
|
"num_tokens": 11576013.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.343645143508911,
|
|
"epoch": 0.4851104707012488,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004982893401798223,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.21171488612890244,
|
|
"num_tokens": 11587535.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.405810928344726,
|
|
"epoch": 0.48559077809798273,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004982851180549456,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.20077610909938812,
|
|
"num_tokens": 11598487.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.349521541595459,
|
|
"epoch": 0.4860710854947166,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004982808907460515,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.22083092629909515,
|
|
"num_tokens": 11609457.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.382025146484375,
|
|
"epoch": 0.48655139289145055,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004982766582532382,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.20699179470539092,
|
|
"num_tokens": 11620251.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.375451374053955,
|
|
"epoch": 0.48703170028818443,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004982724205766038,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.20996559262275696,
|
|
"num_tokens": 11630956.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.420528221130371,
|
|
"epoch": 0.48751200768491837,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004982681777162468,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.20217099487781526,
|
|
"num_tokens": 11642560.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.33175368309021,
|
|
"epoch": 0.48799231508165225,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982639296722657,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.20277092307806016,
|
|
"num_tokens": 11654050.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.378251647949218,
|
|
"epoch": 0.4884726224783862,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004982596764447591,
|
|
"loss": 5.3346,
|
|
"mean_token_accuracy": 0.20321715325117112,
|
|
"num_tokens": 11664947.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.449995803833008,
|
|
"epoch": 0.48895292987512007,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982554180338258,
|
|
"loss": 5.2456,
|
|
"mean_token_accuracy": 0.19882605373859405,
|
|
"num_tokens": 11676927.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.577300882339477,
|
|
"epoch": 0.489433237271854,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004982511544395646,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.18948118835687638,
|
|
"num_tokens": 11688573.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.363681936264038,
|
|
"epoch": 0.4899135446685879,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982468856620745,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.19672578871250151,
|
|
"num_tokens": 11698704.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.34480619430542,
|
|
"epoch": 0.4903938520653218,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004982426117014545,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.20228682458400726,
|
|
"num_tokens": 11709466.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.421897935867309,
|
|
"epoch": 0.4908741594620557,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004982383325578041,
|
|
"loss": 5.2921,
|
|
"mean_token_accuracy": 0.19451844096183776,
|
|
"num_tokens": 11721120.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.504036855697632,
|
|
"epoch": 0.49135446685878964,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982340482312226,
|
|
"loss": 5.2679,
|
|
"mean_token_accuracy": 0.1939774975180626,
|
|
"num_tokens": 11732120.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.4026013851165775,
|
|
"epoch": 0.4918347742555235,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004982297587218092,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.20662265568971633,
|
|
"num_tokens": 11743501.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.384142446517944,
|
|
"epoch": 0.49231508165225746,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982254640296637,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.20638473331928253,
|
|
"num_tokens": 11755051.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.443932723999024,
|
|
"epoch": 0.49279538904899134,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004982211641548857,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.1939889207482338,
|
|
"num_tokens": 11767663.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.499396657943725,
|
|
"epoch": 0.4932756964457253,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982168590975752,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.20122796595096587,
|
|
"num_tokens": 11778828.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.513611745834351,
|
|
"epoch": 0.49375600384245916,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004982125488578321,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.19013044238090515,
|
|
"num_tokens": 11790654.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.448870611190796,
|
|
"epoch": 0.4942363112391931,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004982082334357563,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.1969570130109787,
|
|
"num_tokens": 11801489.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.391196393966675,
|
|
"epoch": 0.494716618635927,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982039128314481,
|
|
"loss": 5.2229,
|
|
"mean_token_accuracy": 0.19950801879167557,
|
|
"num_tokens": 11813818.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.391459226608276,
|
|
"epoch": 0.4951969260326609,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004981995870450079,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.1980131134390831,
|
|
"num_tokens": 11824814.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.479894018173217,
|
|
"epoch": 0.4956772334293948,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981952560765361,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.19537818133831025,
|
|
"num_tokens": 11836252.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.3897405624389645,
|
|
"epoch": 0.49615754082612873,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004981909199261331,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.1983597010374069,
|
|
"num_tokens": 11847715.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.345670604705811,
|
|
"epoch": 0.4966378482228626,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981865785938998,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.2015163406729698,
|
|
"num_tokens": 11860309.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.3873132228851315,
|
|
"epoch": 0.49711815561959655,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004981822320799367,
|
|
"loss": 5.2035,
|
|
"mean_token_accuracy": 0.19946749955415727,
|
|
"num_tokens": 11872569.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.385909605026245,
|
|
"epoch": 0.49759846301633043,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004981778803843449,
|
|
"loss": 5.1969,
|
|
"mean_token_accuracy": 0.2004099726676941,
|
|
"num_tokens": 11884778.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.452798223495483,
|
|
"epoch": 0.49807877041306436,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004981735235072256,
|
|
"loss": 5.277,
|
|
"mean_token_accuracy": 0.2006050869822502,
|
|
"num_tokens": 11897324.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.475766944885254,
|
|
"epoch": 0.49855907780979825,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004981691614486796,
|
|
"loss": 5.3007,
|
|
"mean_token_accuracy": 0.19719384908676146,
|
|
"num_tokens": 11909145.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.360778284072876,
|
|
"epoch": 0.4990393852065322,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004981647942088084,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.2016976147890091,
|
|
"num_tokens": 11921021.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.543325519561767,
|
|
"epoch": 0.49951969260326606,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004981604217877135,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.19207874685525894,
|
|
"num_tokens": 11932565.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.409695863723755,
|
|
"epoch": 0.5,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498156044185496,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.19969164580106735,
|
|
"num_tokens": 11943225.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.400139284133911,
|
|
"epoch": 0.5004803073967339,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004981516614022579,
|
|
"loss": 5.2701,
|
|
"mean_token_accuracy": 0.20002519637346267,
|
|
"num_tokens": 11954821.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.445433759689331,
|
|
"epoch": 0.5009606147934679,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981472734381008,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.20269747227430343,
|
|
"num_tokens": 11966090.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.445778322219849,
|
|
"epoch": 0.5014409221902018,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004981428802931267,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.20094207674264908,
|
|
"num_tokens": 11977410.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.433689832687378,
|
|
"epoch": 0.5019212295869356,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004981384819674375,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.19651618897914885,
|
|
"num_tokens": 11989119.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.504806232452393,
|
|
"epoch": 0.5024015369836695,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004981340784611354,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.19821322858333587,
|
|
"num_tokens": 12000165.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.426196527481079,
|
|
"epoch": 0.5028818443804035,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981296697743224,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.1921847268939018,
|
|
"num_tokens": 12012118.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.454052591323853,
|
|
"epoch": 0.5033621517771374,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981252559071012,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.19141038358211518,
|
|
"num_tokens": 12023432.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.45819616317749,
|
|
"epoch": 0.5038424591738713,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004981208368595739,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.20807536840438842,
|
|
"num_tokens": 12034323.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.384243202209473,
|
|
"epoch": 0.5043227665706052,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981164126318435,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.19932233542203903,
|
|
"num_tokens": 12045532.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.437687397003174,
|
|
"epoch": 0.5048030739673391,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004981119832240124,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.20076098144054413,
|
|
"num_tokens": 12057346.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.396479225158691,
|
|
"epoch": 0.505283381364073,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004981075486361837,
|
|
"loss": 5.2005,
|
|
"mean_token_accuracy": 0.2075444668531418,
|
|
"num_tokens": 12068670.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.467753219604492,
|
|
"epoch": 0.5057636887608069,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981031088684601,
|
|
"loss": 5.3338,
|
|
"mean_token_accuracy": 0.19293148219585418,
|
|
"num_tokens": 12079664.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.470578527450561,
|
|
"epoch": 0.5062439961575408,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004980986639209448,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.20865996778011323,
|
|
"num_tokens": 12089984.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.336924886703491,
|
|
"epoch": 0.5067243035542748,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000498094213793741,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.20369258522987366,
|
|
"num_tokens": 12101182.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.461707401275635,
|
|
"epoch": 0.5072046109510087,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498089758486952,
|
|
"loss": 5.2908,
|
|
"mean_token_accuracy": 0.19222524017095566,
|
|
"num_tokens": 12112002.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.52132477760315,
|
|
"epoch": 0.5076849183477425,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004980852980006812,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.18709225356578826,
|
|
"num_tokens": 12124194.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.383759450912476,
|
|
"epoch": 0.5081652257444764,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004980808323350323,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.2057688355445862,
|
|
"num_tokens": 12133966.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.434381294250488,
|
|
"epoch": 0.5086455331412104,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004980763614901089,
|
|
"loss": 5.2242,
|
|
"mean_token_accuracy": 0.20607974529266357,
|
|
"num_tokens": 12145643.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.415269994735718,
|
|
"epoch": 0.5091258405379443,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004980718854660146,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.19458574503660203,
|
|
"num_tokens": 12156804.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.415568923950195,
|
|
"epoch": 0.5096061479346782,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004980674042628537,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.1962417483329773,
|
|
"num_tokens": 12168700.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.462696838378906,
|
|
"epoch": 0.5100864553314121,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00049806291788073,
|
|
"loss": 5.2451,
|
|
"mean_token_accuracy": 0.19924858808517457,
|
|
"num_tokens": 12181050.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.497040414810181,
|
|
"epoch": 0.510566762728146,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980584263197477,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.1936553090810776,
|
|
"num_tokens": 12192001.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.576595830917358,
|
|
"epoch": 0.5110470701248799,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980539295800111,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.19061971008777617,
|
|
"num_tokens": 12202436.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.417716455459595,
|
|
"epoch": 0.5115273775216138,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980494276616246,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.2038380205631256,
|
|
"num_tokens": 12214454.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.4226940155029295,
|
|
"epoch": 0.5120076849183477,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004980449205646926,
|
|
"loss": 5.2415,
|
|
"mean_token_accuracy": 0.20273517370223998,
|
|
"num_tokens": 12225924.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.481082773208618,
|
|
"epoch": 0.5124879923150817,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049804040828932,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.2039707839488983,
|
|
"num_tokens": 12236456.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.45840368270874,
|
|
"epoch": 0.5129682997118156,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980358908356113,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.2003647953271866,
|
|
"num_tokens": 12247719.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.392190551757812,
|
|
"epoch": 0.5134486071085494,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004980313682036717,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.2013251528143883,
|
|
"num_tokens": 12259141.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.524492168426514,
|
|
"epoch": 0.5139289145052833,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980268403936058,
|
|
"loss": 5.365,
|
|
"mean_token_accuracy": 0.1915614753961563,
|
|
"num_tokens": 12269748.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.469030904769897,
|
|
"epoch": 0.5144092219020173,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004980223074055189,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.199795925617218,
|
|
"num_tokens": 12281456.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.447213125228882,
|
|
"epoch": 0.5148895292987512,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980177692395164,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.19139748066663742,
|
|
"num_tokens": 12293763.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.445377683639526,
|
|
"epoch": 0.5153698366954851,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004980132258957035,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.20402918457984925,
|
|
"num_tokens": 12305398.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.37006196975708,
|
|
"epoch": 0.515850144092219,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004980086773741856,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.19856112748384475,
|
|
"num_tokens": 12316582.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.4883135795593265,
|
|
"epoch": 0.516330451488953,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004980041236750685,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.19816807955503463,
|
|
"num_tokens": 12328463.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.471945953369141,
|
|
"epoch": 0.5168107588856868,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979995647984577,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.2046574831008911,
|
|
"num_tokens": 12341040.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.377148008346557,
|
|
"epoch": 0.5172910662824207,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004979950007444593,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.20244609713554382,
|
|
"num_tokens": 12353024.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.388622713088989,
|
|
"epoch": 0.5177713736791547,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004979904315131792,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.20672389566898347,
|
|
"num_tokens": 12366100.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.371060800552368,
|
|
"epoch": 0.5182516810758886,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979858571047233,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.20542769879102707,
|
|
"num_tokens": 12377829.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.531446743011474,
|
|
"epoch": 0.5187319884726225,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004979812775191979,
|
|
"loss": 5.3243,
|
|
"mean_token_accuracy": 0.19638566672801971,
|
|
"num_tokens": 12390830.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.379356050491333,
|
|
"epoch": 0.5192122958693564,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004979766927567094,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.20557043850421905,
|
|
"num_tokens": 12401642.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.416276645660401,
|
|
"epoch": 0.5196926032660903,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004979721028173643,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.19905493408441544,
|
|
"num_tokens": 12411653.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.433461380004883,
|
|
"epoch": 0.5201729106628242,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497967507701269,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.2078799471259117,
|
|
"num_tokens": 12422891.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.475499200820923,
|
|
"epoch": 0.5206532180595581,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004979629074085303,
|
|
"loss": 5.2669,
|
|
"mean_token_accuracy": 0.19606062769889832,
|
|
"num_tokens": 12434190.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.457970666885376,
|
|
"epoch": 0.521133525456292,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004979583019392548,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.19612389653921128,
|
|
"num_tokens": 12445796.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.535390472412109,
|
|
"epoch": 0.521613832853026,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004979536912935497,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.1937570571899414,
|
|
"num_tokens": 12456212.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.380803632736206,
|
|
"epoch": 0.5220941402497599,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000497949075471522,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.2022882655262947,
|
|
"num_tokens": 12467871.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.396414804458618,
|
|
"epoch": 0.5225744476464937,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979444544732786,
|
|
"loss": 5.221,
|
|
"mean_token_accuracy": 0.1953339844942093,
|
|
"num_tokens": 12478626.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.4133953094482425,
|
|
"epoch": 0.5230547550432276,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000497939828298927,
|
|
"loss": 5.304,
|
|
"mean_token_accuracy": 0.19671797156333923,
|
|
"num_tokens": 12491487.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.487530469894409,
|
|
"epoch": 0.5235350624399616,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004979351969485747,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.19640773683786392,
|
|
"num_tokens": 12503240.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.477804231643677,
|
|
"epoch": 0.5240153698366955,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979305604223291,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.19627538919448853,
|
|
"num_tokens": 12513860.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.403817749023437,
|
|
"epoch": 0.5244956772334294,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004979259187202978,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.19977164268493652,
|
|
"num_tokens": 12525884.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.434985589981079,
|
|
"epoch": 0.5249759846301633,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004979212718425887,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.19778544455766678,
|
|
"num_tokens": 12536709.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.4217602729797365,
|
|
"epoch": 0.5254562920268973,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004979166197893096,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.2063028946518898,
|
|
"num_tokens": 12549727.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.387630319595337,
|
|
"epoch": 0.5259365994236311,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004979119625605683,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.19354690313339235,
|
|
"num_tokens": 12562053.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.365799236297607,
|
|
"epoch": 0.526416906820365,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004979073001564734,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.20725233256816863,
|
|
"num_tokens": 12574096.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.444792222976685,
|
|
"epoch": 0.5268972142170989,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004979026325771328,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.19553550630807875,
|
|
"num_tokens": 12585416.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.421392726898193,
|
|
"epoch": 0.5273775216138329,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004978979598226549,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.20420124977827073,
|
|
"num_tokens": 12596861.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.3878334045410154,
|
|
"epoch": 0.5278578290105668,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978932818931483,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.20604118704795837,
|
|
"num_tokens": 12607761.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.473101997375489,
|
|
"epoch": 0.5283381364073007,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004978885987887216,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.19876412749290467,
|
|
"num_tokens": 12619889.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.52455768585205,
|
|
"epoch": 0.5288184438040345,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004978839105094833,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.2017087683081627,
|
|
"num_tokens": 12630604.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.3455263614654545,
|
|
"epoch": 0.5292987512007685,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004978792170555426,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.2012774810194969,
|
|
"num_tokens": 12641172.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.3482582569122314,
|
|
"epoch": 0.5297790585975024,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004978745184270083,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.21653910875320434,
|
|
"num_tokens": 12651731.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.3865655899047855,
|
|
"epoch": 0.5302593659942363,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004978698146239893,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.20066481977701187,
|
|
"num_tokens": 12663050.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.507231616973877,
|
|
"epoch": 0.5307396733909702,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004978651056465952,
|
|
"loss": 5.3351,
|
|
"mean_token_accuracy": 0.19464969784021377,
|
|
"num_tokens": 12674732.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.335496616363526,
|
|
"epoch": 0.5312199807877042,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000497860391494935,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.2027897372841835,
|
|
"num_tokens": 12685981.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.45561728477478,
|
|
"epoch": 0.531700288184438,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004978556721691183,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.19806865006685256,
|
|
"num_tokens": 12697139.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.408766794204712,
|
|
"epoch": 0.5321805955811719,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978509476692547,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.1951587051153183,
|
|
"num_tokens": 12708268.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.4117907047271725,
|
|
"epoch": 0.5326609029779059,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004978462179954538,
|
|
"loss": 5.2159,
|
|
"mean_token_accuracy": 0.20486142337322236,
|
|
"num_tokens": 12720715.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.401797723770142,
|
|
"epoch": 0.5331412103746398,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004978414831478253,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.20377576798200608,
|
|
"num_tokens": 12732409.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.3635334968566895,
|
|
"epoch": 0.5336215177713737,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004978367431264794,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.19053958356380463,
|
|
"num_tokens": 12745174.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.448608493804931,
|
|
"epoch": 0.5341018251681076,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004978319979315261,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.20215798765420914,
|
|
"num_tokens": 12756116.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.492583560943603,
|
|
"epoch": 0.5345821325648416,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978272475630752,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.20121425837278367,
|
|
"num_tokens": 12768183.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.337130117416382,
|
|
"epoch": 0.5350624399615754,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004978224920212374,
|
|
"loss": 5.2125,
|
|
"mean_token_accuracy": 0.20143257826566696,
|
|
"num_tokens": 12778537.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.33579421043396,
|
|
"epoch": 0.5355427473583093,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004978177313061232,
|
|
"loss": 5.2536,
|
|
"mean_token_accuracy": 0.19911010861396788,
|
|
"num_tokens": 12789691.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.470923042297363,
|
|
"epoch": 0.5360230547550432,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004978129654178426,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.19690274745225905,
|
|
"num_tokens": 12801438.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.426489925384521,
|
|
"epoch": 0.5365033621517772,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004978081943565067,
|
|
"loss": 5.238,
|
|
"mean_token_accuracy": 0.1983571782708168,
|
|
"num_tokens": 12812425.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.3816330909729,
|
|
"epoch": 0.5369836695485111,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004978034181222261,
|
|
"loss": 5.2057,
|
|
"mean_token_accuracy": 0.19511340707540512,
|
|
"num_tokens": 12824735.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.472543573379516,
|
|
"epoch": 0.537463976945245,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004977986367151119,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.20105631202459334,
|
|
"num_tokens": 12835454.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.470243644714356,
|
|
"epoch": 0.5379442843419788,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004977938501352747,
|
|
"loss": 5.3567,
|
|
"mean_token_accuracy": 0.19113609939813614,
|
|
"num_tokens": 12847086.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.43897271156311,
|
|
"epoch": 0.5384245917387128,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004977890583828259,
|
|
"loss": 5.2946,
|
|
"mean_token_accuracy": 0.1976897582411766,
|
|
"num_tokens": 12857713.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.3829254627227785,
|
|
"epoch": 0.5389048991354467,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004977842614578768,
|
|
"loss": 5.2637,
|
|
"mean_token_accuracy": 0.19672221690416336,
|
|
"num_tokens": 12869967.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.49492883682251,
|
|
"epoch": 0.5393852065321806,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004977794593605386,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.19768787920475006,
|
|
"num_tokens": 12881230.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.434672880172729,
|
|
"epoch": 0.5398655139289145,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497774652090923,
|
|
"loss": 5.2561,
|
|
"mean_token_accuracy": 0.19740487784147262,
|
|
"num_tokens": 12892376.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.423199844360352,
|
|
"epoch": 0.5403458213256485,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004977698396491414,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.2015289470553398,
|
|
"num_tokens": 12903709.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.338968229293823,
|
|
"epoch": 0.5408261287223823,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004977650220353055,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.20367807447910308,
|
|
"num_tokens": 12914958.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.394136428833008,
|
|
"epoch": 0.5413064361191162,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004977601992495274,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.20167420655488968,
|
|
"num_tokens": 12927418.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.442663192749023,
|
|
"epoch": 0.5417867435158501,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004977553712919189,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.20043358504772185,
|
|
"num_tokens": 12939874.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.459798288345337,
|
|
"epoch": 0.5422670509125841,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004977505381625921,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.1963661327958107,
|
|
"num_tokens": 12951113.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.350559663772583,
|
|
"epoch": 0.542747358309318,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004977456998616593,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.20273139774799348,
|
|
"num_tokens": 12961940.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.300940227508545,
|
|
"epoch": 0.5432276657060519,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004977408563892327,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.20215410143136978,
|
|
"num_tokens": 12973938.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.438532543182373,
|
|
"epoch": 0.5437079731027857,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004977360077454249,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.20405146181583406,
|
|
"num_tokens": 12985400.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.416611433029175,
|
|
"epoch": 0.5441882804995197,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004977311539303483,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.20964492708444596,
|
|
"num_tokens": 12996402.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.33284559249878,
|
|
"epoch": 0.5446685878962536,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004977262949441158,
|
|
"loss": 5.1338,
|
|
"mean_token_accuracy": 0.207969768345356,
|
|
"num_tokens": 13006991.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.431616878509521,
|
|
"epoch": 0.5451488952929875,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977214307868399,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.20395167768001557,
|
|
"num_tokens": 13016969.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.395513486862183,
|
|
"epoch": 0.5456292026897214,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497716561458634,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.20513697415590287,
|
|
"num_tokens": 13027759.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.496779155731201,
|
|
"epoch": 0.5461095100864554,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004977116869596107,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.1954101249575615,
|
|
"num_tokens": 13039881.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.441585397720337,
|
|
"epoch": 0.5465898174831892,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977068072898834,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.2028578534722328,
|
|
"num_tokens": 13051443.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.487551069259643,
|
|
"epoch": 0.5470701248799231,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004977019224495652,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.1925104007124901,
|
|
"num_tokens": 13063474.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.36223611831665,
|
|
"epoch": 0.547550432276657,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976970324387698,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.21396491527557374,
|
|
"num_tokens": 13074365.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.3667303085327145,
|
|
"epoch": 0.548030739673391,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976921372576104,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.20565143525600432,
|
|
"num_tokens": 13087354.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.39310245513916,
|
|
"epoch": 0.5485110470701249,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004976872369062011,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.20052028000354766,
|
|
"num_tokens": 13099306.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.456270217895508,
|
|
"epoch": 0.5489913544668588,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976823313846552,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.1909172460436821,
|
|
"num_tokens": 13111259.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.505323982238769,
|
|
"epoch": 0.5494716618635928,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004976774206930869,
|
|
"loss": 5.2629,
|
|
"mean_token_accuracy": 0.19202751219272612,
|
|
"num_tokens": 13123589.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.3730621337890625,
|
|
"epoch": 0.5499519692603266,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976725048316101,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.20131368041038514,
|
|
"num_tokens": 13136485.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.442380285263061,
|
|
"epoch": 0.5504322766570605,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004976675838003388,
|
|
"loss": 5.2377,
|
|
"mean_token_accuracy": 0.19371712058782578,
|
|
"num_tokens": 13148067.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.425840091705322,
|
|
"epoch": 0.5509125840537944,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004976626575993877,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.19743252247571946,
|
|
"num_tokens": 13159813.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.4400359153747555,
|
|
"epoch": 0.5513928914505284,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004976577262288705,
|
|
"loss": 5.2761,
|
|
"mean_token_accuracy": 0.19976773113012314,
|
|
"num_tokens": 13170828.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.354959201812744,
|
|
"epoch": 0.5518731988472623,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976527896889023,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.2092746376991272,
|
|
"num_tokens": 13181883.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.348735427856445,
|
|
"epoch": 0.5523535062439962,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004976478479795974,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.20560824871063232,
|
|
"num_tokens": 13193530.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.479697370529175,
|
|
"epoch": 0.55283381364073,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004976429011010706,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.1900714859366417,
|
|
"num_tokens": 13205822.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.410556364059448,
|
|
"epoch": 0.553314121037464,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004976379490534366,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.20924041867256166,
|
|
"num_tokens": 13216698.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.373366641998291,
|
|
"epoch": 0.5537944284341979,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004976329918368107,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.19905991554260255,
|
|
"num_tokens": 13228389.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.449615812301635,
|
|
"epoch": 0.5542747358309318,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004976280294513079,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.18989023566246033,
|
|
"num_tokens": 13239628.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.44436993598938,
|
|
"epoch": 0.5547550432276657,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004976230618970431,
|
|
"loss": 5.2859,
|
|
"mean_token_accuracy": 0.2014923021197319,
|
|
"num_tokens": 13251149.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.518587255477906,
|
|
"epoch": 0.5552353506243997,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000497618089174132,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.1971034973859787,
|
|
"num_tokens": 13264846.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.339368152618408,
|
|
"epoch": 0.5557156580211335,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004976131112826898,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.21116390824317932,
|
|
"num_tokens": 13275409.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.2891651630401615,
|
|
"epoch": 0.5561959654178674,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004976081282228323,
|
|
"loss": 5.0913,
|
|
"mean_token_accuracy": 0.21006590127944946,
|
|
"num_tokens": 13287173.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.436860179901123,
|
|
"epoch": 0.5566762728146013,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000497603139994675,
|
|
"loss": 5.1804,
|
|
"mean_token_accuracy": 0.20149831473827362,
|
|
"num_tokens": 13298225.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.383152008056641,
|
|
"epoch": 0.5571565802113353,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975981465983338,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.20298803150653838,
|
|
"num_tokens": 13309685.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.355784368515015,
|
|
"epoch": 0.5576368876080692,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004975931480339246,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.20758654028177262,
|
|
"num_tokens": 13320837.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.400020551681519,
|
|
"epoch": 0.5581171950048031,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004975881443015635,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.1994555786252022,
|
|
"num_tokens": 13333512.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.499358034133911,
|
|
"epoch": 0.5585975024015369,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004975831354013667,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.19726525396108627,
|
|
"num_tokens": 13345189.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.400446796417237,
|
|
"epoch": 0.5590778097982709,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004975781213334503,
|
|
"loss": 5.1814,
|
|
"mean_token_accuracy": 0.20379290580749512,
|
|
"num_tokens": 13356123.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.37984790802002,
|
|
"epoch": 0.5595581171950048,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004975731020979309,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.19814090579748153,
|
|
"num_tokens": 13366902.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.458560657501221,
|
|
"epoch": 0.5600384245917387,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004975680776949249,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.1988992065191269,
|
|
"num_tokens": 13377567.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.446119594573974,
|
|
"epoch": 0.5605187319884726,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004975630481245492,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.21275554597377777,
|
|
"num_tokens": 13387297.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.448615026473999,
|
|
"epoch": 0.5609990393852066,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004975580133869202,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.203067584335804,
|
|
"num_tokens": 13397723.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.4316037654876705,
|
|
"epoch": 0.5614793467819404,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004975529734821552,
|
|
"loss": 5.302,
|
|
"mean_token_accuracy": 0.19728813618421553,
|
|
"num_tokens": 13409875.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.390988826751709,
|
|
"epoch": 0.5619596541786743,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004975479284103708,
|
|
"loss": 5.2099,
|
|
"mean_token_accuracy": 0.20556127578020095,
|
|
"num_tokens": 13421338.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.444341087341309,
|
|
"epoch": 0.5624399615754082,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975428781716845,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.20571468025445938,
|
|
"num_tokens": 13431373.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.428695297241211,
|
|
"epoch": 0.5629202689721422,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004975378227662134,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.20486005395650864,
|
|
"num_tokens": 13443158.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.476019096374512,
|
|
"epoch": 0.5634005763688761,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004975327621940746,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.19317104965448378,
|
|
"num_tokens": 13454559.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.550100421905517,
|
|
"epoch": 0.56388088376561,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004975276964553861,
|
|
"loss": 5.387,
|
|
"mean_token_accuracy": 0.19499229043722152,
|
|
"num_tokens": 13466934.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.421635150909424,
|
|
"epoch": 0.5643611911623438,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004975226255502651,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.21336206346750258,
|
|
"num_tokens": 13477770.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.469849634170532,
|
|
"epoch": 0.5648414985590778,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004975175494788297,
|
|
"loss": 5.3372,
|
|
"mean_token_accuracy": 0.194351489841938,
|
|
"num_tokens": 13490093.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.486195516586304,
|
|
"epoch": 0.5653218059558117,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004975124682411974,
|
|
"loss": 5.2018,
|
|
"mean_token_accuracy": 0.2025473579764366,
|
|
"num_tokens": 13500663.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.460525321960449,
|
|
"epoch": 0.5658021133525456,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004975073818374863,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.19814062863588333,
|
|
"num_tokens": 13512369.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.4164266109466555,
|
|
"epoch": 0.5662824207492796,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004975022902678145,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.20385072082281114,
|
|
"num_tokens": 13523181.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.385796976089478,
|
|
"epoch": 0.5667627281460135,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004974971935323003,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.20066388696432114,
|
|
"num_tokens": 13534113.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.329702281951905,
|
|
"epoch": 0.5672430355427474,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004974920916310619,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.20250354558229447,
|
|
"num_tokens": 13545037.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.408524751663208,
|
|
"epoch": 0.5677233429394812,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004974869845642178,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.20249072313308716,
|
|
"num_tokens": 13555541.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.388197135925293,
|
|
"epoch": 0.5682036503362152,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004974818723318866,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.2064737856388092,
|
|
"num_tokens": 13566951.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.446853971481323,
|
|
"epoch": 0.5686839577329491,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004974767549341868,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.19983698725700377,
|
|
"num_tokens": 13578492.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.443757009506226,
|
|
"epoch": 0.569164265129683,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974716323712376,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.20955992639064788,
|
|
"num_tokens": 13589183.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.421390628814697,
|
|
"epoch": 0.5696445725264169,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004974665046431576,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.19809137284755707,
|
|
"num_tokens": 13600588.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.376427507400512,
|
|
"epoch": 0.5701248799231509,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004974613717500659,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.20923979729413986,
|
|
"num_tokens": 13612107.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.5154797554016115,
|
|
"epoch": 0.5706051873198847,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004974562336920818,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.19478144943714143,
|
|
"num_tokens": 13623973.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.39094648361206,
|
|
"epoch": 0.5710854947166186,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004974510904693245,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.20794936567544936,
|
|
"num_tokens": 13634994.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.455427503585815,
|
|
"epoch": 0.5715658021133525,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004974459420819134,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.19929085075855255,
|
|
"num_tokens": 13646361.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.420032691955567,
|
|
"epoch": 0.5720461095100865,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000497440788529968,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.20158523619174956,
|
|
"num_tokens": 13656975.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.401870012283325,
|
|
"epoch": 0.5725264169068204,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004974356298136081,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.20242744088172912,
|
|
"num_tokens": 13668434.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.414079713821411,
|
|
"epoch": 0.5730067243035543,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974304659329533,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.2013985440135002,
|
|
"num_tokens": 13679266.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.358348417282104,
|
|
"epoch": 0.5734870317002881,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004974252968881236,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.19810654670000077,
|
|
"num_tokens": 13690921.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.451554870605468,
|
|
"epoch": 0.5739673390970221,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000497420122679239,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.2040702223777771,
|
|
"num_tokens": 13702329.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.353938722610474,
|
|
"epoch": 0.574447646493756,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004974149433064196,
|
|
"loss": 5.1619,
|
|
"mean_token_accuracy": 0.20967793166637422,
|
|
"num_tokens": 13713356.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.297184705734253,
|
|
"epoch": 0.5749279538904899,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004974097587697856,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.19970266073942183,
|
|
"num_tokens": 13724718.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.3087554454803465,
|
|
"epoch": 0.5754082612872238,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004974045690694575,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.20804403126239776,
|
|
"num_tokens": 13736113.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.485042858123779,
|
|
"epoch": 0.5758885686839578,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004973993742055557,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.20523133128881454,
|
|
"num_tokens": 13748322.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.351669263839722,
|
|
"epoch": 0.5763688760806917,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973941741782007,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.19881592094898223,
|
|
"num_tokens": 13759433.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5763688760806917,
|
|
"eval_entropy": 5.173574446934365,
|
|
"eval_loss": 5.231561183929443,
|
|
"eval_mean_token_accuracy": 0.20952744792778133,
|
|
"eval_num_tokens": 13759433.0,
|
|
"eval_runtime": 20.3933,
|
|
"eval_samples_per_second": 1609.104,
|
|
"eval_steps_per_second": 201.144,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.317676401138305,
|
|
"epoch": 0.5768491834774255,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004973889689875135,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.20577383935451507,
|
|
"num_tokens": 13770181.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.34284462928772,
|
|
"epoch": 0.5773294908741594,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004973837586336147,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.2017221912741661,
|
|
"num_tokens": 13781792.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.397495365142822,
|
|
"epoch": 0.5778097982708934,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004973785431166254,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.19736747443675995,
|
|
"num_tokens": 13792101.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.408102750778198,
|
|
"epoch": 0.5782901056676273,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004973733224366666,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.20430949330329895,
|
|
"num_tokens": 13803640.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.417121553421021,
|
|
"epoch": 0.5787704130643612,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004973680965938597,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.20893548280000687,
|
|
"num_tokens": 13815017.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.47672209739685,
|
|
"epoch": 0.579250720461095,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004973628655883258,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.19625595062971116,
|
|
"num_tokens": 13826119.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.360985326766968,
|
|
"epoch": 0.579731027857829,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004973576294201865,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.20206461399793624,
|
|
"num_tokens": 13837869.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.567944145202636,
|
|
"epoch": 0.5802113352545629,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004973523880895633,
|
|
"loss": 5.3422,
|
|
"mean_token_accuracy": 0.1880539357662201,
|
|
"num_tokens": 13849333.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.459596252441406,
|
|
"epoch": 0.5806916426512968,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004973471415965779,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.20356349796056747,
|
|
"num_tokens": 13860648.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.490988540649414,
|
|
"epoch": 0.5811719500480308,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000497341889941352,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.1951858326792717,
|
|
"num_tokens": 13872979.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.409925270080566,
|
|
"epoch": 0.5816522574447647,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004973366331240078,
|
|
"loss": 5.2426,
|
|
"mean_token_accuracy": 0.19907674342393875,
|
|
"num_tokens": 13884363.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.414319229125977,
|
|
"epoch": 0.5821325648414986,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000497331371144667,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.1978744849562645,
|
|
"num_tokens": 13895424.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.446793508529663,
|
|
"epoch": 0.5826128722382324,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004973261040034521,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.1934633269906044,
|
|
"num_tokens": 13907319.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.335920190811157,
|
|
"epoch": 0.5830931796349664,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004973208317004852,
|
|
"loss": 5.168,
|
|
"mean_token_accuracy": 0.20753708779811858,
|
|
"num_tokens": 13920013.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.3865642070770265,
|
|
"epoch": 0.5835734870317003,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004973155542358889,
|
|
"loss": 5.138,
|
|
"mean_token_accuracy": 0.20259324014186858,
|
|
"num_tokens": 13932033.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.333774566650391,
|
|
"epoch": 0.5840537944284342,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004973102716097853,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.2091463476419449,
|
|
"num_tokens": 13943324.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.408417177200318,
|
|
"epoch": 0.5845341018251681,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973049838222973,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.21122615337371825,
|
|
"num_tokens": 13954291.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.465994453430175,
|
|
"epoch": 0.5850144092219021,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004972996908735479,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.19264212399721145,
|
|
"num_tokens": 13966264.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.490592527389526,
|
|
"epoch": 0.585494716618636,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004972943927636597,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.19654978811740875,
|
|
"num_tokens": 13977785.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.3439209938049315,
|
|
"epoch": 0.5859750240153698,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004972890894927558,
|
|
"loss": 5.2046,
|
|
"mean_token_accuracy": 0.20348718762397766,
|
|
"num_tokens": 13989704.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.414724111557007,
|
|
"epoch": 0.5864553314121037,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004972837810609592,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.2061559408903122,
|
|
"num_tokens": 14000565.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.300512218475342,
|
|
"epoch": 0.5869356388088377,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004972784674683933,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.21265693455934526,
|
|
"num_tokens": 14011521.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.342484712600708,
|
|
"epoch": 0.5874159462055716,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004972731487151815,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.20898157060146333,
|
|
"num_tokens": 14022966.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.496384477615356,
|
|
"epoch": 0.5878962536023055,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004972678248014471,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.20139852464199065,
|
|
"num_tokens": 14034905.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.296892976760864,
|
|
"epoch": 0.5883765609990393,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004972624957273139,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.20901353806257247,
|
|
"num_tokens": 14045816.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.331165027618408,
|
|
"epoch": 0.5888568683957733,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004972571614929055,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20691063702106477,
|
|
"num_tokens": 14057316.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.4494264125823975,
|
|
"epoch": 0.5893371757925072,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972518220983457,
|
|
"loss": 5.2315,
|
|
"mean_token_accuracy": 0.194955912232399,
|
|
"num_tokens": 14067542.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.300818586349488,
|
|
"epoch": 0.5898174831892411,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004972464775437586,
|
|
"loss": 5.1082,
|
|
"mean_token_accuracy": 0.2038309842348099,
|
|
"num_tokens": 14079467.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.322385835647583,
|
|
"epoch": 0.590297790585975,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004972411278292683,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.20967037081718445,
|
|
"num_tokens": 14090695.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.365872621536255,
|
|
"epoch": 0.590778097982709,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004972357729549988,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.21425690948963166,
|
|
"num_tokens": 14101380.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.316104984283447,
|
|
"epoch": 0.5912584053794429,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004972304129210746,
|
|
"loss": 5.158,
|
|
"mean_token_accuracy": 0.20969926416873932,
|
|
"num_tokens": 14112265.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.376876020431519,
|
|
"epoch": 0.5917387127761767,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004972250477276202,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.20484964549541473,
|
|
"num_tokens": 14124294.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.383788347244263,
|
|
"epoch": 0.5922190201729106,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004972196773747599,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.2072070226073265,
|
|
"num_tokens": 14135230.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.435587596893311,
|
|
"epoch": 0.5926993275696446,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004972143018626186,
|
|
"loss": 5.2706,
|
|
"mean_token_accuracy": 0.199320986866951,
|
|
"num_tokens": 14147576.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.357582330703735,
|
|
"epoch": 0.5931796349663785,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004972089211913211,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.20706107169389726,
|
|
"num_tokens": 14158834.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.406814289093018,
|
|
"epoch": 0.5936599423631124,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004972035353609923,
|
|
"loss": 5.284,
|
|
"mean_token_accuracy": 0.1946965351700783,
|
|
"num_tokens": 14170694.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.382691860198975,
|
|
"epoch": 0.5941402497598463,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004971981443717572,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.20373794585466384,
|
|
"num_tokens": 14183184.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.499075698852539,
|
|
"epoch": 0.5946205571565802,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004971927482237409,
|
|
"loss": 5.2727,
|
|
"mean_token_accuracy": 0.19923094511032105,
|
|
"num_tokens": 14194761.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.346008777618408,
|
|
"epoch": 0.5951008645533141,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004971873469170689,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.2069292798638344,
|
|
"num_tokens": 14205820.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.285473346710205,
|
|
"epoch": 0.595581171950048,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004971819404518664,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.2080278217792511,
|
|
"num_tokens": 14217826.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.355868816375732,
|
|
"epoch": 0.5960614793467819,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497176528828259,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.2167549431324005,
|
|
"num_tokens": 14228632.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.407436847686768,
|
|
"epoch": 0.5965417867435159,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004971711120463722,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.19621515572071074,
|
|
"num_tokens": 14240231.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.441270589828491,
|
|
"epoch": 0.5970220941402498,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000497165690106332,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.20620052814483641,
|
|
"num_tokens": 14251718.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.402524423599243,
|
|
"epoch": 0.5975024015369836,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004971602630082642,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.21023498028516768,
|
|
"num_tokens": 14263129.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.316794395446777,
|
|
"epoch": 0.5979827089337176,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004971548307522947,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.20603148490190507,
|
|
"num_tokens": 14274465.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.442112064361572,
|
|
"epoch": 0.5984630163304515,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004971493933385498,
|
|
"loss": 5.2854,
|
|
"mean_token_accuracy": 0.20513668954372405,
|
|
"num_tokens": 14286190.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.433134078979492,
|
|
"epoch": 0.5989433237271854,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004971439507671556,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.2017318844795227,
|
|
"num_tokens": 14297638.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.346106767654419,
|
|
"epoch": 0.5994236311239193,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004971385030382384,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.20881230533123016,
|
|
"num_tokens": 14309773.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.369094181060791,
|
|
"epoch": 0.5999039385206533,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004971330501519248,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.2099878966808319,
|
|
"num_tokens": 14320543.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.409315919876098,
|
|
"epoch": 0.6003842459173871,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971275921083414,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.19912684857845306,
|
|
"num_tokens": 14332076.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.338934898376465,
|
|
"epoch": 0.600864553314121,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497122128907615,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.20467256158590316,
|
|
"num_tokens": 14343768.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.336265516281128,
|
|
"epoch": 0.6013448607108549,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004971166605498722,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.20175106227397918,
|
|
"num_tokens": 14357051.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.380846071243286,
|
|
"epoch": 0.6018251681075889,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004971111870352401,
|
|
"loss": 5.2108,
|
|
"mean_token_accuracy": 0.19954999536275864,
|
|
"num_tokens": 14368800.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.387369632720947,
|
|
"epoch": 0.6023054755043228,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004971057083638458,
|
|
"loss": 5.1885,
|
|
"mean_token_accuracy": 0.21062051504850388,
|
|
"num_tokens": 14379617.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.346527814865112,
|
|
"epoch": 0.6027857829010567,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004971002245358166,
|
|
"loss": 5.1559,
|
|
"mean_token_accuracy": 0.21145128458738327,
|
|
"num_tokens": 14391454.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.3886960506439205,
|
|
"epoch": 0.6032660902977905,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004970947355512795,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.2130463242530823,
|
|
"num_tokens": 14402379.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.3505042552947994,
|
|
"epoch": 0.6037463976945245,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004970892414103622,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.20644438415765762,
|
|
"num_tokens": 14415040.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.376429271697998,
|
|
"epoch": 0.6042267050912584,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004970837421131921,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.19653793871402742,
|
|
"num_tokens": 14426677.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.396064376831054,
|
|
"epoch": 0.6047070124879923,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004970782376598972,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.20533006340265275,
|
|
"num_tokens": 14436676.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.392739105224609,
|
|
"epoch": 0.6051873198847262,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004970727280506048,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.19733990132808685,
|
|
"num_tokens": 14448294.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.315736722946167,
|
|
"epoch": 0.6056676272814602,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004970672132854431,
|
|
"loss": 5.1622,
|
|
"mean_token_accuracy": 0.20562706589698793,
|
|
"num_tokens": 14460642.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.338218450546265,
|
|
"epoch": 0.6061479346781941,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004970616933645403,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.21485713571310044,
|
|
"num_tokens": 14471370.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.4621439456939695,
|
|
"epoch": 0.6066282420749279,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004970561682880242,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.20577811002731322,
|
|
"num_tokens": 14482358.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.4311422348022464,
|
|
"epoch": 0.6071085494716618,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004970506380560233,
|
|
"loss": 5.2623,
|
|
"mean_token_accuracy": 0.20287067741155623,
|
|
"num_tokens": 14494413.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.398257827758789,
|
|
"epoch": 0.6075888568683958,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004970451026686659,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.21675312221050264,
|
|
"num_tokens": 14506370.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.395339870452881,
|
|
"epoch": 0.6080691642651297,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004970395621260806,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.2110365942120552,
|
|
"num_tokens": 14517198.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.46751856803894,
|
|
"epoch": 0.6085494716618636,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000497034016428396,
|
|
"loss": 5.2693,
|
|
"mean_token_accuracy": 0.19731477200984954,
|
|
"num_tokens": 14529434.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.328270530700683,
|
|
"epoch": 0.6090297790585975,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970284655757409,
|
|
"loss": 5.1596,
|
|
"mean_token_accuracy": 0.2077682361006737,
|
|
"num_tokens": 14540857.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.332006740570068,
|
|
"epoch": 0.6095100864553314,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004970229095682439,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.20433960258960723,
|
|
"num_tokens": 14552594.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.420663452148437,
|
|
"epoch": 0.6099903938520653,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004970173484060344,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.20081303864717484,
|
|
"num_tokens": 14563599.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.411350440979004,
|
|
"epoch": 0.6104707012487992,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004970117820892414,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.20423975884914397,
|
|
"num_tokens": 14575905.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.417771673202514,
|
|
"epoch": 0.6109510086455331,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004970062106179939,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.2102581739425659,
|
|
"num_tokens": 14587800.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.382213973999024,
|
|
"epoch": 0.6114313160422671,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004970006339924214,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.2105979710817337,
|
|
"num_tokens": 14600654.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.389059114456177,
|
|
"epoch": 0.611911623439001,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969950522126534,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.2078918397426605,
|
|
"num_tokens": 14611985.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.326954650878906,
|
|
"epoch": 0.6123919308357348,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004969894652788196,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.20942535400390624,
|
|
"num_tokens": 14625004.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.39363808631897,
|
|
"epoch": 0.6128722382324687,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004969838731910494,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.20212942659854888,
|
|
"num_tokens": 14635381.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.327234983444214,
|
|
"epoch": 0.6133525456292027,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004969782759494729,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.211282180249691,
|
|
"num_tokens": 14646582.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.334175634384155,
|
|
"epoch": 0.6138328530259366,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049697267355422,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.20744510143995284,
|
|
"num_tokens": 14658024.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.537168884277344,
|
|
"epoch": 0.6143131604226705,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004969670660054208,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.1993764966726303,
|
|
"num_tokens": 14669933.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.426605176925659,
|
|
"epoch": 0.6147934678194045,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004969614533032054,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.2035425618290901,
|
|
"num_tokens": 14681331.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.25716814994812,
|
|
"epoch": 0.6152737752161384,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004969558354477041,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.21936360746622086,
|
|
"num_tokens": 14691361.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.337737512588501,
|
|
"epoch": 0.6157540826128722,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004969502124390474,
|
|
"loss": 5.1451,
|
|
"mean_token_accuracy": 0.2076416000723839,
|
|
"num_tokens": 14701791.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.4165130138397215,
|
|
"epoch": 0.6162343900096061,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004969445842773658,
|
|
"loss": 5.2218,
|
|
"mean_token_accuracy": 0.20131406635046006,
|
|
"num_tokens": 14713672.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.3496606826782225,
|
|
"epoch": 0.6167146974063401,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00049693895096279,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.2134489744901657,
|
|
"num_tokens": 14724789.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.311793231964112,
|
|
"epoch": 0.617195004803074,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004969333124954508,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.20452271401882172,
|
|
"num_tokens": 14737212.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.303396415710449,
|
|
"epoch": 0.6176753121998079,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004969276688754791,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.20288337469100953,
|
|
"num_tokens": 14748387.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.390523481369018,
|
|
"epoch": 0.6181556195965417,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004969220201030059,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.20002119094133378,
|
|
"num_tokens": 14758477.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.424677038192749,
|
|
"epoch": 0.6186359269932757,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969163661781624,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.2052892789244652,
|
|
"num_tokens": 14769650.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.289681673049927,
|
|
"epoch": 0.6191162343900096,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969107071010798,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.20910587459802626,
|
|
"num_tokens": 14780988.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.361701822280883,
|
|
"epoch": 0.6195965417867435,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004969050428718895,
|
|
"loss": 5.1561,
|
|
"mean_token_accuracy": 0.20649783462285995,
|
|
"num_tokens": 14792458.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.406031084060669,
|
|
"epoch": 0.6200768491834774,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000496899373490723,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.20498424172401428,
|
|
"num_tokens": 14804772.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.400968217849732,
|
|
"epoch": 0.6205571565802114,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000496893698957712,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.2003758192062378,
|
|
"num_tokens": 14816126.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.400296592712403,
|
|
"epoch": 0.6210374639769453,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968880192729882,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.1981361836194992,
|
|
"num_tokens": 14829376.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.335179996490479,
|
|
"epoch": 0.6215177713736791,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004968823344366835,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.21548613011837006,
|
|
"num_tokens": 14841098.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.350776815414429,
|
|
"epoch": 0.621998078770413,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968766444489298,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.2144631862640381,
|
|
"num_tokens": 14852690.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.3790772438049315,
|
|
"epoch": 0.622478386167147,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004968709493098593,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.2103243201971054,
|
|
"num_tokens": 14863327.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.40360050201416,
|
|
"epoch": 0.6229586935638809,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968652490196041,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.20150311589241027,
|
|
"num_tokens": 14875213.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.375523424148559,
|
|
"epoch": 0.6234390009606148,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004968595435782967,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.21407082676887512,
|
|
"num_tokens": 14886129.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.438185405731201,
|
|
"epoch": 0.6239193083573487,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004968538329860695,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.19463388323783876,
|
|
"num_tokens": 14897217.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.393808460235595,
|
|
"epoch": 0.6243996157540826,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004968481172430549,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.20633927583694459,
|
|
"num_tokens": 14908438.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.309189128875732,
|
|
"epoch": 0.6248799231508165,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000496842396349386,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.21646459102630616,
|
|
"num_tokens": 14920472.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.331929683685303,
|
|
"epoch": 0.6253602305475504,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004968366703051952,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.20861062556505203,
|
|
"num_tokens": 14932075.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.352813959121704,
|
|
"epoch": 0.6258405379442843,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004968309391106157,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.2066570281982422,
|
|
"num_tokens": 14942971.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.33895583152771,
|
|
"epoch": 0.6263208453410183,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004968252027657806,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.21391605734825134,
|
|
"num_tokens": 14954288.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.299142169952392,
|
|
"epoch": 0.6268011527377522,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004968194612708229,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.20947352200746536,
|
|
"num_tokens": 14966017.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.404318571090698,
|
|
"epoch": 0.627281460134486,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004968137146258759,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.20726121813058854,
|
|
"num_tokens": 14978022.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.298225545883179,
|
|
"epoch": 0.6277617675312199,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004968079628310732,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.213259819149971,
|
|
"num_tokens": 14990370.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.273942232131958,
|
|
"epoch": 0.6282420749279539,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004968022058865482,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.21425193250179292,
|
|
"num_tokens": 15001535.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.437747240066528,
|
|
"epoch": 0.6287223823246878,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967964437924346,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.210428886115551,
|
|
"num_tokens": 15012560.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.273789119720459,
|
|
"epoch": 0.6292026897214217,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004967906765488662,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.21402514725923538,
|
|
"num_tokens": 15024594.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.3567702293396,
|
|
"epoch": 0.6296829971181557,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004967849041559769,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.207964426279068,
|
|
"num_tokens": 15034735.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.427696561813354,
|
|
"epoch": 0.6301633045148896,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004967791266139006,
|
|
"loss": 5.2278,
|
|
"mean_token_accuracy": 0.2034089207649231,
|
|
"num_tokens": 15046955.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.351802921295166,
|
|
"epoch": 0.6306436119116234,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004967733439227716,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.2113296240568161,
|
|
"num_tokens": 15058250.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.387771797180176,
|
|
"epoch": 0.6311239193083573,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000496767556082724,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.20387782156467438,
|
|
"num_tokens": 15069451.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.345231580734253,
|
|
"epoch": 0.6316042267050913,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004967617630938924,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.21100624650716782,
|
|
"num_tokens": 15080920.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.305248832702636,
|
|
"epoch": 0.6320845341018252,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000496755964956411,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.20580895841121674,
|
|
"num_tokens": 15091579.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.3537815570831295,
|
|
"epoch": 0.6325648414985591,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004967501616704147,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.20618314743041993,
|
|
"num_tokens": 15103097.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.358901882171631,
|
|
"epoch": 0.633045148895293,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000496744353236038,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.20893874168395996,
|
|
"num_tokens": 15114646.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.435190343856812,
|
|
"epoch": 0.633525456292027,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000496738539653416,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.2017595499753952,
|
|
"num_tokens": 15126019.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.388354825973511,
|
|
"epoch": 0.6340057636887608,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004967327209226835,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.20799960643053056,
|
|
"num_tokens": 15136132.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.357957077026367,
|
|
"epoch": 0.6344860710854947,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004967268970439755,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.20312527120113372,
|
|
"num_tokens": 15149016.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.4254063129425045,
|
|
"epoch": 0.6349663784822286,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004967210680174274,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.21304135918617248,
|
|
"num_tokens": 15160302.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.364810657501221,
|
|
"epoch": 0.6354466858789626,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004967152338431745,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.205369770526886,
|
|
"num_tokens": 15171770.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.3285229206085205,
|
|
"epoch": 0.6359269932756965,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967093945213523,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.2132847711443901,
|
|
"num_tokens": 15182283.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.329556131362915,
|
|
"epoch": 0.6364073006724303,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004967035500520962,
|
|
"loss": 5.1796,
|
|
"mean_token_accuracy": 0.20531734675168992,
|
|
"num_tokens": 15193917.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.485039520263672,
|
|
"epoch": 0.6368876080691642,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004966977004355421,
|
|
"loss": 5.2488,
|
|
"mean_token_accuracy": 0.20010878443717955,
|
|
"num_tokens": 15205854.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.307362651824951,
|
|
"epoch": 0.6373679154658982,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004966918456718256,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.2113931208848953,
|
|
"num_tokens": 15217884.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.3968860626220705,
|
|
"epoch": 0.6378482228626321,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004966859857610828,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.19845329076051713,
|
|
"num_tokens": 15229493.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.36131911277771,
|
|
"epoch": 0.638328530259366,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004966801207034497,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.20187900811433793,
|
|
"num_tokens": 15241402.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.421045923233033,
|
|
"epoch": 0.6388088376560999,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004966742504990624,
|
|
"loss": 5.1971,
|
|
"mean_token_accuracy": 0.2028847262263298,
|
|
"num_tokens": 15252981.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.372963190078735,
|
|
"epoch": 0.6392891450528339,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004966683751480572,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.21094227433204651,
|
|
"num_tokens": 15264171.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.313787841796875,
|
|
"epoch": 0.6397694524495677,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004966624946505706,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.20988318622112273,
|
|
"num_tokens": 15275595.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.406278848648071,
|
|
"epoch": 0.6402497598463016,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004966566090067391,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.20010184794664382,
|
|
"num_tokens": 15286074.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.420538902282715,
|
|
"epoch": 0.6407300672430355,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004966507182166993,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.20725206285715103,
|
|
"num_tokens": 15296230.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.338460397720337,
|
|
"epoch": 0.6412103746397695,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000496644822280588,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.2085949957370758,
|
|
"num_tokens": 15307428.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.454903888702392,
|
|
"epoch": 0.6416906820365034,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000496638921198542,
|
|
"loss": 5.2716,
|
|
"mean_token_accuracy": 0.19481648355722428,
|
|
"num_tokens": 15318796.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.352904796600342,
|
|
"epoch": 0.6421709894332372,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004966330149706984,
|
|
"loss": 5.163,
|
|
"mean_token_accuracy": 0.2108139529824257,
|
|
"num_tokens": 15330914.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.312903547286988,
|
|
"epoch": 0.6426512968299711,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004966271035971944,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.2060234397649765,
|
|
"num_tokens": 15341756.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.429139471054077,
|
|
"epoch": 0.6431316042267051,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004966211870781671,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.20073795765638353,
|
|
"num_tokens": 15353217.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.409663105010987,
|
|
"epoch": 0.643611911623439,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000496615265413754,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.2033244863152504,
|
|
"num_tokens": 15363813.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.33024377822876,
|
|
"epoch": 0.6440922190201729,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966093386040923,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.20895603746175767,
|
|
"num_tokens": 15375223.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.3554637908935545,
|
|
"epoch": 0.6445725264169068,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049660340664932,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.20896363705396653,
|
|
"num_tokens": 15385523.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.4246556758880615,
|
|
"epoch": 0.6450528338136408,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004965974695495746,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.20112065821886063,
|
|
"num_tokens": 15397262.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.298054838180542,
|
|
"epoch": 0.6455331412103746,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004965915273049938,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20933966040611268,
|
|
"num_tokens": 15409043.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.3289378643035885,
|
|
"epoch": 0.6460134486071085,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965855799157158,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.2075978308916092,
|
|
"num_tokens": 15420859.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.38963098526001,
|
|
"epoch": 0.6464937560038425,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004965796273818787,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.2000960275530815,
|
|
"num_tokens": 15433650.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.307419919967652,
|
|
"epoch": 0.6469740634005764,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004965736697036206,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.21013231873512267,
|
|
"num_tokens": 15445158.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.410332536697387,
|
|
"epoch": 0.6474543707973103,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004965677068810798,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.19520421028137208,
|
|
"num_tokens": 15456974.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.460703659057617,
|
|
"epoch": 0.6479346781940442,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965617389143947,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.20826771557331086,
|
|
"num_tokens": 15467395.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.342369890213012,
|
|
"epoch": 0.6484149855907781,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000496555765803704,
|
|
"loss": 5.2001,
|
|
"mean_token_accuracy": 0.20690712183713914,
|
|
"num_tokens": 15479396.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.332846927642822,
|
|
"epoch": 0.648895292987512,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004965497875491462,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.21249084174633026,
|
|
"num_tokens": 15490992.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.493760395050049,
|
|
"epoch": 0.6493756003842459,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004965438041508604,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.1961396560072899,
|
|
"num_tokens": 15502413.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.415083122253418,
|
|
"epoch": 0.6498559077809798,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965378156089851,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.1977938786149025,
|
|
"num_tokens": 15512588.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.344873046875,
|
|
"epoch": 0.6503362151777138,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004965318219236597,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.20562929958105086,
|
|
"num_tokens": 15523252.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.317601299285888,
|
|
"epoch": 0.6508165225744477,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004965258230950232,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.2040314793586731,
|
|
"num_tokens": 15534975.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.35293869972229,
|
|
"epoch": 0.6512968299711815,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965198191232148,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.2115544080734253,
|
|
"num_tokens": 15545709.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.400387811660766,
|
|
"epoch": 0.6517771373679154,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000496513810008374,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.21018994152545928,
|
|
"num_tokens": 15557270.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.407934236526489,
|
|
"epoch": 0.6522574447646494,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004965077957506403,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.20628803521394729,
|
|
"num_tokens": 15569156.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.340046644210815,
|
|
"epoch": 0.6527377521613833,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004965017763501533,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.20741754472255708,
|
|
"num_tokens": 15579270.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.257709932327271,
|
|
"epoch": 0.6532180595581172,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004964957518070529,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.21847713738679886,
|
|
"num_tokens": 15589912.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.367315435409546,
|
|
"epoch": 0.6536983669548511,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004964897221214788,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.20783090144395827,
|
|
"num_tokens": 15601088.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.432088708877563,
|
|
"epoch": 0.654178674351585,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000496483687293571,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.20100946724414825,
|
|
"num_tokens": 15612520.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.322639274597168,
|
|
"epoch": 0.6546589817483189,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004964776473234696,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.21446669548749925,
|
|
"num_tokens": 15623991.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.256708145141602,
|
|
"epoch": 0.6551392891450528,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000496471602211315,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.21122566908597945,
|
|
"num_tokens": 15635389.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.375541400909424,
|
|
"epoch": 0.6556195965417867,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004964655519572475,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.21136708408594132,
|
|
"num_tokens": 15646427.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.289290475845337,
|
|
"epoch": 0.6560999039385207,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004964594965614072,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.20655087977647782,
|
|
"num_tokens": 15657518.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.3904680728912355,
|
|
"epoch": 0.6565802113352546,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004964534360239353,
|
|
"loss": 5.1551,
|
|
"mean_token_accuracy": 0.19926086515188218,
|
|
"num_tokens": 15669775.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.3419993877410885,
|
|
"epoch": 0.6570605187319885,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000496447370344972,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.19673027694225312,
|
|
"num_tokens": 15682566.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.310968637466431,
|
|
"epoch": 0.6575408261287223,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004964412995246584,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.21229192465543748,
|
|
"num_tokens": 15693168.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.342676162719727,
|
|
"epoch": 0.6580211335254563,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964352235631354,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.20767595022916793,
|
|
"num_tokens": 15703879.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.394798994064331,
|
|
"epoch": 0.6585014409221902,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496429142460544,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.2011292904615402,
|
|
"num_tokens": 15716015.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.4194292545318605,
|
|
"epoch": 0.6589817483189241,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004964230562170254,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.20597222745418547,
|
|
"num_tokens": 15728254.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.352735090255737,
|
|
"epoch": 0.659462055715658,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004964169648327209,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.20761849135160446,
|
|
"num_tokens": 15738778.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.39863657951355,
|
|
"epoch": 0.659942363112392,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000496410868307772,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.20410102009773254,
|
|
"num_tokens": 15750305.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.380156660079956,
|
|
"epoch": 0.6604226705091258,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004964047666423203,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.2071267694234848,
|
|
"num_tokens": 15761303.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.327047538757324,
|
|
"epoch": 0.6609029779058597,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004963986598365072,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.21683207303285598,
|
|
"num_tokens": 15773095.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.38857135772705,
|
|
"epoch": 0.6613832853025937,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004963925478904746,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.2092995211482048,
|
|
"num_tokens": 15784405.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.2769053936004635,
|
|
"epoch": 0.6618635926993276,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004963864308043645,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.2081150382757187,
|
|
"num_tokens": 15795178.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.344074344635009,
|
|
"epoch": 0.6623439000960615,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004963803085783189,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.20570641607046128,
|
|
"num_tokens": 15806205.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.331649971008301,
|
|
"epoch": 0.6628242074927954,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004963741812124799,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.21467693150043488,
|
|
"num_tokens": 15817474.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.301028442382813,
|
|
"epoch": 0.6633045148895294,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004963680487069898,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.20411243587732314,
|
|
"num_tokens": 15829728.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.446570825576782,
|
|
"epoch": 0.6637848222862632,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004963619110619908,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.20543691217899324,
|
|
"num_tokens": 15840082.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.397112512588501,
|
|
"epoch": 0.6642651296829971,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004963557682776256,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.20543725341558455,
|
|
"num_tokens": 15851450.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.375704574584961,
|
|
"epoch": 0.664745437079731,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004963496203540368,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.19991056323051454,
|
|
"num_tokens": 15864168.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.405896139144898,
|
|
"epoch": 0.665225744476465,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004963434672913671,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.20860163271427154,
|
|
"num_tokens": 15875634.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.489336633682251,
|
|
"epoch": 0.6657060518731989,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004963373090897592,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.19939687252044677,
|
|
"num_tokens": 15888411.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.367930603027344,
|
|
"epoch": 0.6661863592699327,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004963311457493563,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.20343247950077056,
|
|
"num_tokens": 15901084.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.468456649780274,
|
|
"epoch": 0.6666666666666666,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004963249772703015,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.20327554941177367,
|
|
"num_tokens": 15912061.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.43146448135376,
|
|
"epoch": 0.6671469740634006,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004963188036527378,
|
|
"loss": 5.2862,
|
|
"mean_token_accuracy": 0.20486033260822295,
|
|
"num_tokens": 15925439.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.288822364807129,
|
|
"epoch": 0.6676272814601345,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004963126248968087,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.2155329942703247,
|
|
"num_tokens": 15937762.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.24741907119751,
|
|
"epoch": 0.6681075888568684,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004963064410026577,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.21581644266843797,
|
|
"num_tokens": 15948656.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.389021873474121,
|
|
"epoch": 0.6685878962536023,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004963002519704281,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.20223325192928315,
|
|
"num_tokens": 15960376.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.403183937072754,
|
|
"epoch": 0.6690682036503363,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000496294057800264,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.20470741689205169,
|
|
"num_tokens": 15971913.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.385066366195678,
|
|
"epoch": 0.6695485110470701,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004962878584923089,
|
|
"loss": 5.2015,
|
|
"mean_token_accuracy": 0.20076711922883989,
|
|
"num_tokens": 15984775.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.373220205307007,
|
|
"epoch": 0.670028818443804,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004962816540467068,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.20235749930143357,
|
|
"num_tokens": 15996717.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.352170085906982,
|
|
"epoch": 0.6705091258405379,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004962754444636017,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.21042097061872483,
|
|
"num_tokens": 16007964.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.3342327117919925,
|
|
"epoch": 0.6709894332372719,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000496269229743138,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.2070094719529152,
|
|
"num_tokens": 16019185.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.382532596588135,
|
|
"epoch": 0.6714697406340058,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004962630098854597,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.21081747412681578,
|
|
"num_tokens": 16029983.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.362025403976441,
|
|
"epoch": 0.6719500480307397,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004962567848907113,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.20711022466421128,
|
|
"num_tokens": 16040574.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.39690465927124,
|
|
"epoch": 0.6724303554274735,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004962505547590374,
|
|
"loss": 5.2372,
|
|
"mean_token_accuracy": 0.20249408334493638,
|
|
"num_tokens": 16052037.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.408071565628052,
|
|
"epoch": 0.6729106628242075,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004962443194905826,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.20055394023656845,
|
|
"num_tokens": 16063413.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.406305170059204,
|
|
"epoch": 0.6733909702209414,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004962380790854916,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.20647710859775542,
|
|
"num_tokens": 16074373.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.407031011581421,
|
|
"epoch": 0.6738712776176753,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004962318335439094,
|
|
"loss": 5.2426,
|
|
"mean_token_accuracy": 0.20001827776432038,
|
|
"num_tokens": 16086575.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.355895090103149,
|
|
"epoch": 0.6743515850144092,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004962255828659809,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.20987340211868286,
|
|
"num_tokens": 16098529.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.3135683059692385,
|
|
"epoch": 0.6748318924111432,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004962193270518513,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.2066950723528862,
|
|
"num_tokens": 16110085.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.3063897609710695,
|
|
"epoch": 0.675312199807877,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004962130661016659,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.2101002663373947,
|
|
"num_tokens": 16120249.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.438611888885498,
|
|
"epoch": 0.6757925072046109,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004962068000155699,
|
|
"loss": 5.3008,
|
|
"mean_token_accuracy": 0.1928768277168274,
|
|
"num_tokens": 16132645.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.368090295791626,
|
|
"epoch": 0.6762728146013448,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004962005287937088,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.20920299738645554,
|
|
"num_tokens": 16143808.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.340124797821045,
|
|
"epoch": 0.6767531219980788,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004961942524362283,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.21055777072906495,
|
|
"num_tokens": 16154309.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.3663732528686525,
|
|
"epoch": 0.6772334293948127,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004961879709432741,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.20459160655736924,
|
|
"num_tokens": 16164654.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.417678356170654,
|
|
"epoch": 0.6777137367915466,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000496181684314992,
|
|
"loss": 5.1882,
|
|
"mean_token_accuracy": 0.20391224175691605,
|
|
"num_tokens": 16177837.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.296876859664917,
|
|
"epoch": 0.6781940441882806,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004961753925515279,
|
|
"loss": 5.067,
|
|
"mean_token_accuracy": 0.21334256529808043,
|
|
"num_tokens": 16189073.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.4126255989074705,
|
|
"epoch": 0.6786743515850144,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496169095653028,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.20514075458049774,
|
|
"num_tokens": 16200371.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.371976518630982,
|
|
"epoch": 0.6791546589817483,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004961627936196384,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.21760908663272857,
|
|
"num_tokens": 16210526.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.340885639190674,
|
|
"epoch": 0.6796349663784822,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004961564864515055,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.20996493846178055,
|
|
"num_tokens": 16221687.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.24901442527771,
|
|
"epoch": 0.6801152737752162,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004961501741487757,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.21863269060850143,
|
|
"num_tokens": 16233828.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.31521201133728,
|
|
"epoch": 0.6805955811719501,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004961438567115955,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.2200038269162178,
|
|
"num_tokens": 16243900.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.282388162612915,
|
|
"epoch": 0.681075888568684,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004961375341401116,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.21111399531364441,
|
|
"num_tokens": 16256347.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.329246616363525,
|
|
"epoch": 0.6815561959654178,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004961312064344708,
|
|
"loss": 5.0302,
|
|
"mean_token_accuracy": 0.2127418264746666,
|
|
"num_tokens": 16267743.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.278157663345337,
|
|
"epoch": 0.6820365033621518,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049612487359482,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.21328497529029847,
|
|
"num_tokens": 16278280.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.223898696899414,
|
|
"epoch": 0.6825168107588857,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004961185356213062,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.21954626590013504,
|
|
"num_tokens": 16288568.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.3232855796813965,
|
|
"epoch": 0.6829971181556196,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004961121925140767,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.21324246376752853,
|
|
"num_tokens": 16300730.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.363188552856445,
|
|
"epoch": 0.6834774255523535,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004961058442732786,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.20338241755962372,
|
|
"num_tokens": 16311789.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.308821392059326,
|
|
"epoch": 0.6839577329490875,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004960994908990594,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.20517774373292924,
|
|
"num_tokens": 16324439.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.404965448379516,
|
|
"epoch": 0.6844380403458213,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004960931323915665,
|
|
"loss": 5.2544,
|
|
"mean_token_accuracy": 0.21529368460178375,
|
|
"num_tokens": 16335344.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.350891351699829,
|
|
"epoch": 0.6849183477425552,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004960867687509475,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.21074139922857285,
|
|
"num_tokens": 16349018.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.351697254180908,
|
|
"epoch": 0.6853986551392891,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004960803999773504,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.20665929168462754,
|
|
"num_tokens": 16360137.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.396191358566284,
|
|
"epoch": 0.6858789625360231,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004960740260709228,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.20857713222503663,
|
|
"num_tokens": 16372277.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.390155935287476,
|
|
"epoch": 0.686359269932757,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004960676470318128,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.20712728649377823,
|
|
"num_tokens": 16383440.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.3785594463348385,
|
|
"epoch": 0.6868395773294909,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004960612628601683,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.20781178623437882,
|
|
"num_tokens": 16394330.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.285098600387573,
|
|
"epoch": 0.6873198847262247,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004960548735561379,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.21686847060918807,
|
|
"num_tokens": 16405734.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.334474325180054,
|
|
"epoch": 0.6878001921229587,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004960484791198697,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.2046303242444992,
|
|
"num_tokens": 16416025.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.311826276779175,
|
|
"epoch": 0.6882804995196926,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004960420795515121,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.20956576615571976,
|
|
"num_tokens": 16427416.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.333488845825196,
|
|
"epoch": 0.6887608069164265,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004960356748512138,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.21433757096529008,
|
|
"num_tokens": 16438073.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.313464593887329,
|
|
"epoch": 0.6892411143131604,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004960292650191236,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.2105144217610359,
|
|
"num_tokens": 16449994.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.303148984909058,
|
|
"epoch": 0.6897214217098944,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004960228500553899,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.21942657977342606,
|
|
"num_tokens": 16460355.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.391108226776123,
|
|
"epoch": 0.6902017291066282,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004960164299601623,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.20661765486001968,
|
|
"num_tokens": 16472274.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.407241725921631,
|
|
"epoch": 0.6906820365033621,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004960100047335892,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.20781127214431763,
|
|
"num_tokens": 16482959.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.370867395401001,
|
|
"epoch": 0.691162343900096,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004960035743758202,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.20494930148124696,
|
|
"num_tokens": 16494533.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.2687249183654785,
|
|
"epoch": 0.69164265129683,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004959971388870044,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.21412606686353683,
|
|
"num_tokens": 16506124.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.32615475654602,
|
|
"epoch": 0.6921229586935639,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004959906982672912,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.20936821401119232,
|
|
"num_tokens": 16517867.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.248544454574585,
|
|
"epoch": 0.6926032660902978,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004959842525168302,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.21626189798116685,
|
|
"num_tokens": 16529075.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.336199426651001,
|
|
"epoch": 0.6930835734870316,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004959778016357712,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.2134622648358345,
|
|
"num_tokens": 16540326.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.347323656082153,
|
|
"epoch": 0.6935638808837656,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004959713456242637,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.21234775632619857,
|
|
"num_tokens": 16551570.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.4202698230743405,
|
|
"epoch": 0.6940441882804995,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004959648844824576,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.2128515362739563,
|
|
"num_tokens": 16562636.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.355170202255249,
|
|
"epoch": 0.6945244956772334,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004959584182105032,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.21433595418930054,
|
|
"num_tokens": 16573867.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.254151916503906,
|
|
"epoch": 0.6950048030739674,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004959519468085504,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.21470070779323577,
|
|
"num_tokens": 16584533.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.303434753417969,
|
|
"epoch": 0.6954851104707013,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004959454702767494,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.21080477982759477,
|
|
"num_tokens": 16596562.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.348945045471192,
|
|
"epoch": 0.6959654178674352,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004959389886152507,
|
|
"loss": 5.0921,
|
|
"mean_token_accuracy": 0.21597741097211837,
|
|
"num_tokens": 16607508.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.36681900024414,
|
|
"epoch": 0.696445725264169,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004959325018242048,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.20786135047674179,
|
|
"num_tokens": 16617737.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.389381217956543,
|
|
"epoch": 0.696926032660903,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004959260099037622,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.20632247775793075,
|
|
"num_tokens": 16628518.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.329285192489624,
|
|
"epoch": 0.6974063400576369,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004959195128540737,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.2045375347137451,
|
|
"num_tokens": 16639644.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.452426290512085,
|
|
"epoch": 0.6978866474543708,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049591301067529,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.19840320199728012,
|
|
"num_tokens": 16650882.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.395485305786133,
|
|
"epoch": 0.6983669548511047,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004959065033675623,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.20692969709634781,
|
|
"num_tokens": 16662464.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.353216886520386,
|
|
"epoch": 0.6988472622478387,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004958999909310414,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.19958139210939407,
|
|
"num_tokens": 16673718.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.310863065719604,
|
|
"epoch": 0.6993275696445725,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004958934733658788,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.20269549638032913,
|
|
"num_tokens": 16684957.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.392301034927368,
|
|
"epoch": 0.6998078770413064,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004958869506722256,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.20818491131067277,
|
|
"num_tokens": 16695782.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.30381064414978,
|
|
"epoch": 0.7002881844380403,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004958804228502332,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.21515030711889266,
|
|
"num_tokens": 16707448.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.25730562210083,
|
|
"epoch": 0.7007684918347743,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004958738899000534,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.20368140041828156,
|
|
"num_tokens": 16718074.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.325642538070679,
|
|
"epoch": 0.7012487992315082,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004958673518218377,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.2102039560675621,
|
|
"num_tokens": 16728656.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.346181964874267,
|
|
"epoch": 0.7017291066282421,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004958608086157379,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.21052978038787842,
|
|
"num_tokens": 16740703.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.34031572341919,
|
|
"epoch": 0.7022094140249759,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000495854260281906,
|
|
"loss": 5.0407,
|
|
"mean_token_accuracy": 0.22064048647880555,
|
|
"num_tokens": 16753320.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.238544130325318,
|
|
"epoch": 0.7026897214217099,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004958477068204941,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.21317285746335984,
|
|
"num_tokens": 16764889.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.404721593856811,
|
|
"epoch": 0.7031700288184438,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000495841148231654,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.21132533699274064,
|
|
"num_tokens": 16776301.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.378520059585571,
|
|
"epoch": 0.7036503362151777,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004958345845155383,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.21723831295967103,
|
|
"num_tokens": 16786935.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.313399696350098,
|
|
"epoch": 0.7041306436119116,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004958280156722992,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.20934344679117203,
|
|
"num_tokens": 16799335.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.243146371841431,
|
|
"epoch": 0.7046109510086456,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004958214417020894,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.2091888189315796,
|
|
"num_tokens": 16811376.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.403880453109741,
|
|
"epoch": 0.7050912584053795,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004958148626050614,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.2032211810350418,
|
|
"num_tokens": 16822859.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.329212093353272,
|
|
"epoch": 0.7055715658021133,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000495808278381368,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.2076030045747757,
|
|
"num_tokens": 16833831.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.315768384933472,
|
|
"epoch": 0.7060518731988472,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000495801689031162,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.20439638048410416,
|
|
"num_tokens": 16846827.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.369126892089843,
|
|
"epoch": 0.7065321805955812,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004957950945545965,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.2099258854985237,
|
|
"num_tokens": 16858166.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.3943541049957275,
|
|
"epoch": 0.7070124879923151,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004957884949518246,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.1968243569135666,
|
|
"num_tokens": 16870201.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.387752628326416,
|
|
"epoch": 0.707492795389049,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004957818902229992,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.2092154875397682,
|
|
"num_tokens": 16880891.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.3780457973480225,
|
|
"epoch": 0.7079731027857828,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004957752803682741,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.19942378848791123,
|
|
"num_tokens": 16893498.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.40191125869751,
|
|
"epoch": 0.7084534101825168,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004957686653878024,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.20957574099302292,
|
|
"num_tokens": 16904959.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.427788352966308,
|
|
"epoch": 0.7089337175792507,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000495762045281738,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.20638214647769929,
|
|
"num_tokens": 16916547.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.316069078445435,
|
|
"epoch": 0.7094140249759846,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004957554200502344,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.2140609458088875,
|
|
"num_tokens": 16928580.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.35137710571289,
|
|
"epoch": 0.7098943323727186,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004957487896934454,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.20508789867162705,
|
|
"num_tokens": 16941247.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.423005771636963,
|
|
"epoch": 0.7103746397694525,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000495742154211525,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.2094101682305336,
|
|
"num_tokens": 16951119.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.3181304931640625,
|
|
"epoch": 0.7108549471661864,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004957355136046272,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.21093301326036454,
|
|
"num_tokens": 16962608.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.309222221374512,
|
|
"epoch": 0.7113352545629202,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004957288678729064,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.20930130630731583,
|
|
"num_tokens": 16973291.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.401194095611572,
|
|
"epoch": 0.7118155619596542,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004957222170165166,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.20743726789951325,
|
|
"num_tokens": 16984895.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.386478519439697,
|
|
"epoch": 0.7122958693563881,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004957155610356124,
|
|
"loss": 5.169,
|
|
"mean_token_accuracy": 0.20269262194633483,
|
|
"num_tokens": 16997109.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.32469916343689,
|
|
"epoch": 0.712776176753122,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004957088999303481,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.2049662411212921,
|
|
"num_tokens": 17008640.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.332112789154053,
|
|
"epoch": 0.7132564841498559,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004957022337008787,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.21241938471794128,
|
|
"num_tokens": 17018924.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.315089893341065,
|
|
"epoch": 0.7137367915465899,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004956955623473587,
|
|
"loss": 5.0955,
|
|
"mean_token_accuracy": 0.21295803785324097,
|
|
"num_tokens": 17029932.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.348790550231934,
|
|
"epoch": 0.7142170989433237,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000495688885869943,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.20275085419416428,
|
|
"num_tokens": 17042164.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.391345739364624,
|
|
"epoch": 0.7146974063400576,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004956822042687868,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.1998043403029442,
|
|
"num_tokens": 17054729.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.29535026550293,
|
|
"epoch": 0.7151777137367915,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004956755175440451,
|
|
"loss": 5.039,
|
|
"mean_token_accuracy": 0.2244885817170143,
|
|
"num_tokens": 17066537.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.314731502532959,
|
|
"epoch": 0.7156580211335255,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004956688256958731,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.21349663585424422,
|
|
"num_tokens": 17077787.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.293307971954346,
|
|
"epoch": 0.7161383285302594,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004956621287244262,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.20553401112556458,
|
|
"num_tokens": 17089555.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.377112102508545,
|
|
"epoch": 0.7166186359269933,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004956554266298599,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.21415567249059678,
|
|
"num_tokens": 17099911.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.296390771865845,
|
|
"epoch": 0.7170989433237271,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956487194123298,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.21108074188232423,
|
|
"num_tokens": 17110880.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.301234579086303,
|
|
"epoch": 0.7175792507204611,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004956420070719918,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.2123343512415886,
|
|
"num_tokens": 17122272.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.330184984207153,
|
|
"epoch": 0.718059558117195,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004956352896090014,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.2031962588429451,
|
|
"num_tokens": 17133995.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.359682512283325,
|
|
"epoch": 0.7185398655139289,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956285670235147,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.2137000471353531,
|
|
"num_tokens": 17145970.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.412320518493653,
|
|
"epoch": 0.7190201729106628,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004956218393156879,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.19951253086328508,
|
|
"num_tokens": 17157747.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.321125650405884,
|
|
"epoch": 0.7195004803073968,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004956151064856772,
|
|
"loss": 5.1911,
|
|
"mean_token_accuracy": 0.21149196475744247,
|
|
"num_tokens": 17168357.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.360573768615723,
|
|
"epoch": 0.7199807877041307,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004956083685336386,
|
|
"loss": 5.1275,
|
|
"mean_token_accuracy": 0.21438027173280716,
|
|
"num_tokens": 17179871.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.362541389465332,
|
|
"epoch": 0.7204610951008645,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004956016254597289,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.21592396199703218,
|
|
"num_tokens": 17190456.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.316376209259033,
|
|
"epoch": 0.7209414024975984,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004955948772641044,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.2022445410490036,
|
|
"num_tokens": 17201623.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.289179086685181,
|
|
"epoch": 0.7214217098943324,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000495588123946922,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.2154449552297592,
|
|
"num_tokens": 17212891.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.3309040546417235,
|
|
"epoch": 0.7219020172910663,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004955813655083384,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.20933630019426347,
|
|
"num_tokens": 17223983.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.364512252807617,
|
|
"epoch": 0.7223823246878002,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004955746019485104,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.21106259077787398,
|
|
"num_tokens": 17233701.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.334096384048462,
|
|
"epoch": 0.722862632084534,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000495567833267595,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.20766069740056992,
|
|
"num_tokens": 17245958.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.422809076309204,
|
|
"epoch": 0.723342939481268,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004955610594657496,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.19982282370328902,
|
|
"num_tokens": 17257687.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.387662744522094,
|
|
"epoch": 0.7238232468780019,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004955542805431313,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.20973837822675706,
|
|
"num_tokens": 17270247.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.3202332019805905,
|
|
"epoch": 0.7243035542747358,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004955474964998976,
|
|
"loss": 5.1216,
|
|
"mean_token_accuracy": 0.21431013494729995,
|
|
"num_tokens": 17281920.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.414140367507935,
|
|
"epoch": 0.7247838616714697,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004955407073362058,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.19534719735383987,
|
|
"num_tokens": 17293602.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.420685434341431,
|
|
"epoch": 0.7252641690682037,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004955339130522136,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.2121052160859108,
|
|
"num_tokens": 17304484.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.2246194839477536,
|
|
"epoch": 0.7257444764649376,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000495527113648079,
|
|
"loss": 5.0059,
|
|
"mean_token_accuracy": 0.21230011135339738,
|
|
"num_tokens": 17314953.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.308328247070312,
|
|
"epoch": 0.7262247838616714,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004955203091239596,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.2041084423661232,
|
|
"num_tokens": 17326813.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.433790779113769,
|
|
"epoch": 0.7267050912584054,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004955134994800134,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.1998712569475174,
|
|
"num_tokens": 17337968.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.352131271362305,
|
|
"epoch": 0.7271853986551393,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004955066847163984,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.20739677548408508,
|
|
"num_tokens": 17350406.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.270753717422485,
|
|
"epoch": 0.7276657060518732,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004954998648332731,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.2157138392329216,
|
|
"num_tokens": 17361888.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.341862487792969,
|
|
"epoch": 0.7281460134486071,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004954930398307956,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.20940286815166473,
|
|
"num_tokens": 17374047.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.3741772174835205,
|
|
"epoch": 0.7286263208453411,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004954862097091245,
|
|
"loss": 5.1396,
|
|
"mean_token_accuracy": 0.20097160637378692,
|
|
"num_tokens": 17386175.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.308564138412476,
|
|
"epoch": 0.729106628242075,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004954793744684184,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.21635485887527467,
|
|
"num_tokens": 17398168.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.309036827087402,
|
|
"epoch": 0.7295869356388088,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004954725341088358,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.21216989010572435,
|
|
"num_tokens": 17408825.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.309152460098266,
|
|
"epoch": 0.7300672430355427,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004954656886305356,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.21166825592517852,
|
|
"num_tokens": 17419813.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.38578987121582,
|
|
"epoch": 0.7305475504322767,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004954588380336768,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.20159507989883424,
|
|
"num_tokens": 17431134.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.311600255966186,
|
|
"epoch": 0.7310278578290106,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004954519823184184,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.21454625129699706,
|
|
"num_tokens": 17442614.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.34098448753357,
|
|
"epoch": 0.7315081652257445,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004954451214849196,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.21475362479686738,
|
|
"num_tokens": 17454615.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.360263872146606,
|
|
"epoch": 0.7319884726224783,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004954382555333397,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.21009002029895782,
|
|
"num_tokens": 17467025.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.301818799972534,
|
|
"epoch": 0.7324687800192123,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000495431384463838,
|
|
"loss": 5.0963,
|
|
"mean_token_accuracy": 0.21603968143463134,
|
|
"num_tokens": 17477681.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.361507606506348,
|
|
"epoch": 0.7329490874159462,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004954245082765741,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.21298671513795853,
|
|
"num_tokens": 17489814.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.368234872817993,
|
|
"epoch": 0.7334293948126801,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004954176269717077,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.2104403242468834,
|
|
"num_tokens": 17501701.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.3271644115448,
|
|
"epoch": 0.733909702209414,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004954107405493984,
|
|
"loss": 5.0356,
|
|
"mean_token_accuracy": 0.2159121409058571,
|
|
"num_tokens": 17513585.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.358423662185669,
|
|
"epoch": 0.734390009606148,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004954038490098064,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.21037847995758058,
|
|
"num_tokens": 17525557.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.293937301635742,
|
|
"epoch": 0.7348703170028819,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004953969523530914,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.20951283425092698,
|
|
"num_tokens": 17538312.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.427788209915161,
|
|
"epoch": 0.7353506243996157,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004953900505794136,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.20821893364191055,
|
|
"num_tokens": 17550248.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.321779489517212,
|
|
"epoch": 0.7358309317963496,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004953831436889332,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.21040415316820144,
|
|
"num_tokens": 17560624.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.344732618331909,
|
|
"epoch": 0.7363112391930836,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004953762316818106,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.20328582674264908,
|
|
"num_tokens": 17572439.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.398155641555786,
|
|
"epoch": 0.7367915465898175,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004953693145582064,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.20126384794712066,
|
|
"num_tokens": 17583120.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.239375448226928,
|
|
"epoch": 0.7372718539865514,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000495362392318281,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.21710849404335023,
|
|
"num_tokens": 17593677.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.31401481628418,
|
|
"epoch": 0.7377521613832853,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004953554649621951,
|
|
"loss": 5.1353,
|
|
"mean_token_accuracy": 0.2044165164232254,
|
|
"num_tokens": 17605180.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.387196826934814,
|
|
"epoch": 0.7382324687800192,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004953485324901098,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.2123894587159157,
|
|
"num_tokens": 17617459.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.339674425125122,
|
|
"epoch": 0.7387127761767531,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004953415949021857,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.2147862806916237,
|
|
"num_tokens": 17628024.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.280680418014526,
|
|
"epoch": 0.739193083573487,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004953346521985843,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.21122694313526152,
|
|
"num_tokens": 17639833.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.383000087738037,
|
|
"epoch": 0.7396733909702209,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004953277043794663,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.19969362765550613,
|
|
"num_tokens": 17651057.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.367031621932983,
|
|
"epoch": 0.7401536983669549,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004953207514449933,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.215635746717453,
|
|
"num_tokens": 17662288.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.322967958450318,
|
|
"epoch": 0.7406340057636888,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004953137933953267,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.2102230355143547,
|
|
"num_tokens": 17673885.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.322059631347656,
|
|
"epoch": 0.7411143131604226,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000495306830230628,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.20912605226039888,
|
|
"num_tokens": 17685030.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.315001726150513,
|
|
"epoch": 0.7415946205571565,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004952998619510589,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.21422436237335205,
|
|
"num_tokens": 17696624.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.3054591655731205,
|
|
"epoch": 0.7420749279538905,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004952928885567811,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.20987910330295562,
|
|
"num_tokens": 17707386.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.447640895843506,
|
|
"epoch": 0.7425552353506244,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004952859100479566,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.20340465903282165,
|
|
"num_tokens": 17718605.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.337006759643555,
|
|
"epoch": 0.7430355427473583,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004952789264247474,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.2116430938243866,
|
|
"num_tokens": 17730275.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.415854597091675,
|
|
"epoch": 0.7435158501440923,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004952719376873156,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.204722361266613,
|
|
"num_tokens": 17741390.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.36515965461731,
|
|
"epoch": 0.7439961575408262,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004952649438358234,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.21425745487213135,
|
|
"num_tokens": 17752354.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.360581254959106,
|
|
"epoch": 0.74447646493756,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952579448704334,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.21331725269556046,
|
|
"num_tokens": 17762839.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.340327024459839,
|
|
"epoch": 0.7449567723342939,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000495250940791308,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.2019715890288353,
|
|
"num_tokens": 17775800.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.336835718154907,
|
|
"epoch": 0.7454370797310279,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004952439315986096,
|
|
"loss": 5.0913,
|
|
"mean_token_accuracy": 0.21300239115953445,
|
|
"num_tokens": 17787804.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.420383405685425,
|
|
"epoch": 0.7459173871277618,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004952369172925012,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.21128985583782195,
|
|
"num_tokens": 17800291.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.346131610870361,
|
|
"epoch": 0.7463976945244957,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952298978731454,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.2144858330488205,
|
|
"num_tokens": 17811548.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.319376707077026,
|
|
"epoch": 0.7468780019212296,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004952228733407055,
|
|
"loss": 5.0082,
|
|
"mean_token_accuracy": 0.21832434386014937,
|
|
"num_tokens": 17822589.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.246201896667481,
|
|
"epoch": 0.7473583093179635,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004952158436953444,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.2151762828230858,
|
|
"num_tokens": 17834203.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.329451227188111,
|
|
"epoch": 0.7478386167146974,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004952088089372252,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.2087213635444641,
|
|
"num_tokens": 17846238.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.339178371429443,
|
|
"epoch": 0.7483189241114313,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004952017690665114,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.2133630856871605,
|
|
"num_tokens": 17857640.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.300387716293335,
|
|
"epoch": 0.7487992315081652,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004951947240833664,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.212492036819458,
|
|
"num_tokens": 17868755.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.285845375061035,
|
|
"epoch": 0.7492795389048992,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004951876739879537,
|
|
"loss": 5.1171,
|
|
"mean_token_accuracy": 0.20655798763036728,
|
|
"num_tokens": 17881078.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.276634550094604,
|
|
"epoch": 0.7497598463016331,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004951806187804371,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.21204878985881806,
|
|
"num_tokens": 17893888.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.35845980644226,
|
|
"epoch": 0.7502401536983669,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004951735584609804,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.205987349152565,
|
|
"num_tokens": 17904443.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.3006621360778805,
|
|
"epoch": 0.7507204610951008,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004951664930297474,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.2139347091317177,
|
|
"num_tokens": 17918090.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.254575872421265,
|
|
"epoch": 0.7512007684918348,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000495159422486902,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.21954036206007005,
|
|
"num_tokens": 17929233.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.316081428527832,
|
|
"epoch": 0.7516810758885687,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004951523468326088,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.2085426151752472,
|
|
"num_tokens": 17940580.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.377710056304932,
|
|
"epoch": 0.7521613832853026,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004951452660670317,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.20402376651763915,
|
|
"num_tokens": 17953993.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.318881797790527,
|
|
"epoch": 0.7526416906820365,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004951381801903352,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.21420904248952866,
|
|
"num_tokens": 17966033.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.1989460468292235,
|
|
"epoch": 0.7531219980787704,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004951310892026839,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.22273213565349578,
|
|
"num_tokens": 17977943.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.31523871421814,
|
|
"epoch": 0.7536023054755043,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004951239931042424,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.2181277170777321,
|
|
"num_tokens": 17990135.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.287261819839477,
|
|
"epoch": 0.7540826128722382,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004951168918951753,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.21650127023458482,
|
|
"num_tokens": 18002126.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.2205640316009525,
|
|
"epoch": 0.7545629202689721,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004951097855756476,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.21751293540000916,
|
|
"num_tokens": 18013147.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.362655401229858,
|
|
"epoch": 0.7550432276657061,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004951026741458243,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.21097714751958846,
|
|
"num_tokens": 18025146.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.297344970703125,
|
|
"epoch": 0.75552353506244,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004950955576058705,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.20839287489652633,
|
|
"num_tokens": 18036412.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.333431053161621,
|
|
"epoch": 0.7560038424591738,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004950884359559513,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.21789794266223908,
|
|
"num_tokens": 18048041.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.348143005371094,
|
|
"epoch": 0.7564841498559077,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004950813091962324,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.20152033120393753,
|
|
"num_tokens": 18060163.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.341336822509765,
|
|
"epoch": 0.7569644572526417,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004950741773268788,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.2069680780172348,
|
|
"num_tokens": 18071628.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.24476900100708,
|
|
"epoch": 0.7574447646493756,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004950670403480562,
|
|
"loss": 5.0129,
|
|
"mean_token_accuracy": 0.2150563642382622,
|
|
"num_tokens": 18082979.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.306754159927368,
|
|
"epoch": 0.7579250720461095,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004950598982599306,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.21355952471494674,
|
|
"num_tokens": 18093889.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.303635692596435,
|
|
"epoch": 0.7584053794428435,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004950527510626675,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.21013883501291275,
|
|
"num_tokens": 18105559.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.3475329875946045,
|
|
"epoch": 0.7588856868395774,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004950455987564329,
|
|
"loss": 5.1876,
|
|
"mean_token_accuracy": 0.20690033286809922,
|
|
"num_tokens": 18116316.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.367655611038208,
|
|
"epoch": 0.7593659942363112,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004950384413413931,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.21405460834503173,
|
|
"num_tokens": 18126851.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.409810495376587,
|
|
"epoch": 0.7598463016330451,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004950312788177139,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.20579453110694884,
|
|
"num_tokens": 18139571.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.401680421829224,
|
|
"epoch": 0.7603266090297791,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004950241111855618,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.2073150560259819,
|
|
"num_tokens": 18150680.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.349238586425781,
|
|
"epoch": 0.760806916426513,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004950169384451031,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.21686834394931792,
|
|
"num_tokens": 18161911.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.322481346130371,
|
|
"epoch": 0.7612872238232469,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004950097605965045,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.21482323259115219,
|
|
"num_tokens": 18172714.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.340502977371216,
|
|
"epoch": 0.7617675312199808,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004950025776399326,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.21751550883054732,
|
|
"num_tokens": 18184250.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.416499662399292,
|
|
"epoch": 0.7622478386167147,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000494995389575554,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.20439111143350602,
|
|
"num_tokens": 18195299.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.417877340316773,
|
|
"epoch": 0.7627281460134486,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004949881964035357,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.20470178574323655,
|
|
"num_tokens": 18206863.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.378323221206665,
|
|
"epoch": 0.7632084534101825,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004949809981240448,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.2075530543923378,
|
|
"num_tokens": 18219643.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.325662612915039,
|
|
"epoch": 0.7636887608069164,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004949737947372483,
|
|
"loss": 5.0208,
|
|
"mean_token_accuracy": 0.21761458963155747,
|
|
"num_tokens": 18230461.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.356977033615112,
|
|
"epoch": 0.7641690682036504,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004949665862433134,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.2047246813774109,
|
|
"num_tokens": 18243768.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.338019752502442,
|
|
"epoch": 0.7646493756003843,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004949593726424077,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.21247661113739014,
|
|
"num_tokens": 18255322.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.326325607299805,
|
|
"epoch": 0.7651296829971181,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004949521539346985,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.21496090292930603,
|
|
"num_tokens": 18267262.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.325637435913086,
|
|
"epoch": 0.765609990393852,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004949449301203533,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.2124694988131523,
|
|
"num_tokens": 18277332.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.328628253936768,
|
|
"epoch": 0.766090297790586,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004949377011995399,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.2142286017537117,
|
|
"num_tokens": 18289547.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.334627962112426,
|
|
"epoch": 0.7665706051873199,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004949304671724263,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.21425910890102387,
|
|
"num_tokens": 18302097.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.358500671386719,
|
|
"epoch": 0.7670509125840538,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004949232280391802,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.20893050283193587,
|
|
"num_tokens": 18314151.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.300828313827514,
|
|
"epoch": 0.7675312199807877,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004949159837999698,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.2079789936542511,
|
|
"num_tokens": 18326085.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.332225370407104,
|
|
"epoch": 0.7680115273775217,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004949087344549633,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.2095819741487503,
|
|
"num_tokens": 18338158.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.340604019165039,
|
|
"epoch": 0.7684918347742555,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000494901480004329,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.21303831338882445,
|
|
"num_tokens": 18349418.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.335345029830933,
|
|
"epoch": 0.7689721421709894,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004948942204482351,
|
|
"loss": 5.0913,
|
|
"mean_token_accuracy": 0.21118417233228684,
|
|
"num_tokens": 18361964.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.2611064434051515,
|
|
"epoch": 0.7694524495677233,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004948869557868506,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.22380157858133315,
|
|
"num_tokens": 18373108.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.20665922164917,
|
|
"epoch": 0.7699327569644573,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004948796860203439,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.21662286221981047,
|
|
"num_tokens": 18385310.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.35377984046936,
|
|
"epoch": 0.7704130643611912,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004948724111488838,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.20525239855051042,
|
|
"num_tokens": 18396132.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.476380968093872,
|
|
"epoch": 0.770893371757925,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004948651311726391,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.2004573792219162,
|
|
"num_tokens": 18409930.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.424106931686401,
|
|
"epoch": 0.7713736791546589,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004948578460917789,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.20446532666683198,
|
|
"num_tokens": 18421204.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.346558856964111,
|
|
"epoch": 0.7718539865513929,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004948505559064725,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.2158183068037033,
|
|
"num_tokens": 18433194.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.272424125671387,
|
|
"epoch": 0.7723342939481268,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004948432606168889,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.21654528975486756,
|
|
"num_tokens": 18445282.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.305673980712891,
|
|
"epoch": 0.7728146013448607,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004948359602231976,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.21816591918468475,
|
|
"num_tokens": 18456264.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.286828231811524,
|
|
"epoch": 0.7732949087415946,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004948286547255681,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.21798124611377717,
|
|
"num_tokens": 18467573.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.309575033187866,
|
|
"epoch": 0.7737752161383286,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049482134412417,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.2214351251721382,
|
|
"num_tokens": 18478333.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.313509607315064,
|
|
"epoch": 0.7742555235350624,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000494814028419173,
|
|
"loss": 5.0132,
|
|
"mean_token_accuracy": 0.21748400628566741,
|
|
"num_tokens": 18489106.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.337710571289063,
|
|
"epoch": 0.7747358309317963,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000494806707610747,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.20957866162061692,
|
|
"num_tokens": 18500090.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.376635408401489,
|
|
"epoch": 0.7752161383285303,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000494799381699062,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.21432682424783706,
|
|
"num_tokens": 18510305.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.354851531982422,
|
|
"epoch": 0.7756964457252642,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004947920506842879,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.20744638592004777,
|
|
"num_tokens": 18523048.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.252260065078735,
|
|
"epoch": 0.7761767531219981,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004947847145665951,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.21565694659948348,
|
|
"num_tokens": 18534145.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.320717811584473,
|
|
"epoch": 0.776657060518732,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004947773733461539,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.21510692089796066,
|
|
"num_tokens": 18545045.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.335205030441284,
|
|
"epoch": 0.777137367915466,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004947700270231347,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.21586762219667435,
|
|
"num_tokens": 18557531.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.325165128707885,
|
|
"epoch": 0.7776176753121998,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004947626755977079,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.21161842197179795,
|
|
"num_tokens": 18569127.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.3843793869018555,
|
|
"epoch": 0.7780979827089337,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004947553190700444,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.21503574401140213,
|
|
"num_tokens": 18580606.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.438429355621338,
|
|
"epoch": 0.7785782901056676,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000494747957440315,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.20055583566427232,
|
|
"num_tokens": 18592330.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.394421195983886,
|
|
"epoch": 0.7790585975024016,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004947405907086905,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.20635333955287932,
|
|
"num_tokens": 18604721.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.3272958278656,
|
|
"epoch": 0.7795389048991355,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004947332188753419,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.2168866366147995,
|
|
"num_tokens": 18616814.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.369074058532715,
|
|
"epoch": 0.7800192122958693,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004947258419404405,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.21367238312959672,
|
|
"num_tokens": 18628224.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.341666793823242,
|
|
"epoch": 0.7804995196926032,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004947184599041576,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.2109402135014534,
|
|
"num_tokens": 18639777.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.262123155593872,
|
|
"epoch": 0.7809798270893372,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004947110727666644,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.20775717198848725,
|
|
"num_tokens": 18651044.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.378970146179199,
|
|
"epoch": 0.7814601344860711,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004947036805281325,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.21273023933172225,
|
|
"num_tokens": 18663142.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.46126880645752,
|
|
"epoch": 0.781940441882805,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946962831887336,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.20995586663484572,
|
|
"num_tokens": 18674079.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.357724142074585,
|
|
"epoch": 0.7824207492795389,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004946888807486393,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.20491517782211305,
|
|
"num_tokens": 18685744.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.25427393913269,
|
|
"epoch": 0.7829010566762729,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946814732080214,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.21469540596008302,
|
|
"num_tokens": 18697049.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.287244415283203,
|
|
"epoch": 0.7833813640730067,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004946740605670523,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.2153855100274086,
|
|
"num_tokens": 18708765.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.338965272903442,
|
|
"epoch": 0.7838616714697406,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004946666428259037,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.21777086108922958,
|
|
"num_tokens": 18719819.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.383521318435669,
|
|
"epoch": 0.7843419788664745,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004946592199847478,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.20879859924316407,
|
|
"num_tokens": 18730668.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.223228931427002,
|
|
"epoch": 0.7848222862632085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946517920437571,
|
|
"loss": 4.9226,
|
|
"mean_token_accuracy": 0.21504913419485092,
|
|
"num_tokens": 18741991.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.29312801361084,
|
|
"epoch": 0.7853025936599424,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004946443590031041,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.2096063584089279,
|
|
"num_tokens": 18753919.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.399734401702881,
|
|
"epoch": 0.7857829010566763,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004946369208629613,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.22159929424524308,
|
|
"num_tokens": 18764342.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.25146107673645,
|
|
"epoch": 0.7862632084534101,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004946294776235013,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.20978716462850572,
|
|
"num_tokens": 18776044.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.380789184570313,
|
|
"epoch": 0.7867435158501441,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004946220292848971,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.21196742206811905,
|
|
"num_tokens": 18787354.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.347150278091431,
|
|
"epoch": 0.787223823246878,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004946145758473214,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.20693592727184296,
|
|
"num_tokens": 18797845.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.370972061157227,
|
|
"epoch": 0.7877041306436119,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004946071173109475,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.20758142024278642,
|
|
"num_tokens": 18809253.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.293522930145263,
|
|
"epoch": 0.7881844380403458,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004945996536759484,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.22032079249620437,
|
|
"num_tokens": 18819768.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.395445680618286,
|
|
"epoch": 0.7886647454370798,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945921849424974,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.20500316172838212,
|
|
"num_tokens": 18831151.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.31566424369812,
|
|
"epoch": 0.7891450528338136,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004945847111107679,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.21720090508460999,
|
|
"num_tokens": 18842133.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.346229505538941,
|
|
"epoch": 0.7896253602305475,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004945772321809334,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.2060374140739441,
|
|
"num_tokens": 18853295.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.3284361362457275,
|
|
"epoch": 0.7901056676272814,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004945697481531677,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.21173674166202544,
|
|
"num_tokens": 18865802.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.311218690872193,
|
|
"epoch": 0.7905859750240154,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004945622590276443,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.21996215879917144,
|
|
"num_tokens": 18877693.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.346083736419677,
|
|
"epoch": 0.7910662824207493,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004945547648045373,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.2140740066766739,
|
|
"num_tokens": 18888549.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.291837453842163,
|
|
"epoch": 0.7915465898174832,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004945472654840206,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.2168283298611641,
|
|
"num_tokens": 18899132.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.2041699409484865,
|
|
"epoch": 0.7920268972142172,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004945397610662683,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.20819741487503052,
|
|
"num_tokens": 18911774.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.378843021392822,
|
|
"epoch": 0.792507204610951,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945322515514547,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.21274399608373643,
|
|
"num_tokens": 18922806.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.363301086425781,
|
|
"epoch": 0.7929875120076849,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000494524736939754,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.22166195064783095,
|
|
"num_tokens": 18934861.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.319985294342041,
|
|
"epoch": 0.7934678194044188,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004945172172313408,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.21769434064626694,
|
|
"num_tokens": 18944269.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.335051441192627,
|
|
"epoch": 0.7939481268011528,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004945096924263896,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.21137671172618866,
|
|
"num_tokens": 18957197.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.365131044387818,
|
|
"epoch": 0.7944284341978867,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004945021625250753,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.2078988566994667,
|
|
"num_tokens": 18968254.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.2728620052337645,
|
|
"epoch": 0.7949087415946205,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004944946275275724,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.22354944944381713,
|
|
"num_tokens": 18979372.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.305412864685058,
|
|
"epoch": 0.7953890489913544,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004944870874340561,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.21727642118930818,
|
|
"num_tokens": 18991075.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.239272832870483,
|
|
"epoch": 0.7958693563880884,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004944795422447013,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.21712242513895036,
|
|
"num_tokens": 19002324.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.36112904548645,
|
|
"epoch": 0.7963496637848223,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004944719919596835,
|
|
"loss": 5.1357,
|
|
"mean_token_accuracy": 0.2119611993432045,
|
|
"num_tokens": 19014406.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.266506242752075,
|
|
"epoch": 0.7968299711815562,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004944644365791776,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.21952706724405288,
|
|
"num_tokens": 19025984.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.356861162185669,
|
|
"epoch": 0.7973102785782901,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000494456876103359,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.21321585327386855,
|
|
"num_tokens": 19036189.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.349044847488403,
|
|
"epoch": 0.7977905859750241,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004944493105324035,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.2092265710234642,
|
|
"num_tokens": 19047587.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.368412446975708,
|
|
"epoch": 0.7982708933717579,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004944417398664866,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.2098768413066864,
|
|
"num_tokens": 19058467.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.319743537902832,
|
|
"epoch": 0.7987512007684918,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004944341641057843,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.20655251890420914,
|
|
"num_tokens": 19070235.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.373353815078735,
|
|
"epoch": 0.7992315081652257,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004944265832504721,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.21016550213098525,
|
|
"num_tokens": 19082005.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.381409645080566,
|
|
"epoch": 0.7997118155619597,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004944189973007262,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.20851912647485732,
|
|
"num_tokens": 19092922.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.331025552749634,
|
|
"epoch": 0.8001921229586936,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004944114062567229,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.2098314180970192,
|
|
"num_tokens": 19104832.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.350796508789062,
|
|
"epoch": 0.8006724303554275,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004944038101186381,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.21115050017833709,
|
|
"num_tokens": 19116261.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.384184217453003,
|
|
"epoch": 0.8011527377521613,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004943962088866483,
|
|
"loss": 5.1275,
|
|
"mean_token_accuracy": 0.2100977197289467,
|
|
"num_tokens": 19127195.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.3867803573608395,
|
|
"epoch": 0.8016330451488953,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004943886025609301,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.20455964505672455,
|
|
"num_tokens": 19138164.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.335765314102173,
|
|
"epoch": 0.8021133525456292,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049438099114166,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.20542529970407486,
|
|
"num_tokens": 19149153.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.36065936088562,
|
|
"epoch": 0.8025936599423631,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004943733746290147,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.2054949954152107,
|
|
"num_tokens": 19161023.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.297316360473633,
|
|
"epoch": 0.803073967339097,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000494365753023171,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.22194321006536483,
|
|
"num_tokens": 19172466.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.355871915817261,
|
|
"epoch": 0.803554274735831,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004943581263243059,
|
|
"loss": 5.0845,
|
|
"mean_token_accuracy": 0.21780402660369874,
|
|
"num_tokens": 19183684.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.277257871627808,
|
|
"epoch": 0.8040345821325648,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004943504945325965,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.221344518661499,
|
|
"num_tokens": 19194479.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.368801832199097,
|
|
"epoch": 0.8045148895292987,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004943428576482198,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.20726759284734725,
|
|
"num_tokens": 19206323.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.389929342269897,
|
|
"epoch": 0.8049951969260326,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004943352156713535,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.20489852130413055,
|
|
"num_tokens": 19218849.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.280133438110352,
|
|
"epoch": 0.8054755043227666,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004943275686021747,
|
|
"loss": 4.975,
|
|
"mean_token_accuracy": 0.21554317623376845,
|
|
"num_tokens": 19229603.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.354938077926636,
|
|
"epoch": 0.8059558117195005,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000494319916440861,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.20746131092309952,
|
|
"num_tokens": 19241318.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.339200258255005,
|
|
"epoch": 0.8064361191162344,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004943122591875901,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.21261312961578369,
|
|
"num_tokens": 19252640.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.28208646774292,
|
|
"epoch": 0.8069164265129684,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004943045968425398,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.2161882311105728,
|
|
"num_tokens": 19262971.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.335348129272461,
|
|
"epoch": 0.8073967339097022,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004942969294058878,
|
|
"loss": 5.1338,
|
|
"mean_token_accuracy": 0.21078867763280867,
|
|
"num_tokens": 19274426.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.329405164718628,
|
|
"epoch": 0.8078770413064361,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004942892568778125,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.2150216817855835,
|
|
"num_tokens": 19286806.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.294596529006958,
|
|
"epoch": 0.80835734870317,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004942815792584917,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.21479784101247787,
|
|
"num_tokens": 19297997.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.298877191543579,
|
|
"epoch": 0.808837656099904,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004942738965481038,
|
|
"loss": 5.0407,
|
|
"mean_token_accuracy": 0.2120647981762886,
|
|
"num_tokens": 19309789.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.310087585449219,
|
|
"epoch": 0.8093179634966379,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004942662087468272,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.2190921738743782,
|
|
"num_tokens": 19320688.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.300725936889648,
|
|
"epoch": 0.8097982708933718,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004942585158548402,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.21266603618860244,
|
|
"num_tokens": 19331670.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.353588581085205,
|
|
"epoch": 0.8102785782901056,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004942508178723214,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.2116592988371849,
|
|
"num_tokens": 19343578.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.35286431312561,
|
|
"epoch": 0.8107588856868396,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004942431147994499,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.21038884222507476,
|
|
"num_tokens": 19354875.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.294489812850952,
|
|
"epoch": 0.8112391930835735,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004942354066364042,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.21754383891820908,
|
|
"num_tokens": 19366353.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.222540330886841,
|
|
"epoch": 0.8117195004803074,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004942276933833634,
|
|
"loss": 4.9713,
|
|
"mean_token_accuracy": 0.22078879177570343,
|
|
"num_tokens": 19377534.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.311097049713135,
|
|
"epoch": 0.8121998078770413,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004942199750405064,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.20324969440698623,
|
|
"num_tokens": 19388188.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.2128173828125,
|
|
"epoch": 0.8126801152737753,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004942122516080127,
|
|
"loss": 4.9474,
|
|
"mean_token_accuracy": 0.22659370303153992,
|
|
"num_tokens": 19399910.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.347034454345703,
|
|
"epoch": 0.8131604226705091,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004942045230860614,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.2169678568840027,
|
|
"num_tokens": 19411715.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.397089576721191,
|
|
"epoch": 0.813640730067243,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004941967894748319,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.20122881829738617,
|
|
"num_tokens": 19423275.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.352301979064942,
|
|
"epoch": 0.8141210374639769,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004941890507745039,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.2074746236205101,
|
|
"num_tokens": 19436035.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.256072378158569,
|
|
"epoch": 0.8146013448607109,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004941813069852569,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.208758844435215,
|
|
"num_tokens": 19447755.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.34722113609314,
|
|
"epoch": 0.8150816522574448,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004941735581072708,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.21877842992544175,
|
|
"num_tokens": 19459044.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.319392919540405,
|
|
"epoch": 0.8155619596541787,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004941658041407255,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.21560748517513276,
|
|
"num_tokens": 19471486.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.23969407081604,
|
|
"epoch": 0.8160422670509125,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000494158045085801,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.22304799407720566,
|
|
"num_tokens": 19482428.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.298281669616699,
|
|
"epoch": 0.8165225744476465,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004941502809426776,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.21189234107732774,
|
|
"num_tokens": 19494616.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.322142028808594,
|
|
"epoch": 0.8170028818443804,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004941425117115354,
|
|
"loss": 5.0279,
|
|
"mean_token_accuracy": 0.21516261249780655,
|
|
"num_tokens": 19504953.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.344069623947144,
|
|
"epoch": 0.8174831892411143,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004941347373925547,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.2153186947107315,
|
|
"num_tokens": 19517408.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.260396909713745,
|
|
"epoch": 0.8179634966378482,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004941269579859161,
|
|
"loss": 5.0485,
|
|
"mean_token_accuracy": 0.22386470288038254,
|
|
"num_tokens": 19529190.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.295646095275879,
|
|
"epoch": 0.8184438040345822,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004941191734918002,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.21131166815757751,
|
|
"num_tokens": 19540278.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.2985352039337155,
|
|
"epoch": 0.818924111431316,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000494111383910388,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.21477940827608108,
|
|
"num_tokens": 19551224.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.413621044158935,
|
|
"epoch": 0.8194044188280499,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004941035892418597,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.21000590771436692,
|
|
"num_tokens": 19564386.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.35599045753479,
|
|
"epoch": 0.8198847262247838,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004940957894863968,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.2179810106754303,
|
|
"num_tokens": 19576170.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.303261089324951,
|
|
"epoch": 0.8203650336215178,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004940879846441804,
|
|
"loss": 5.0672,
|
|
"mean_token_accuracy": 0.21418049484491347,
|
|
"num_tokens": 19587220.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.311101293563842,
|
|
"epoch": 0.8208453410182517,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004940801747153914,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.2150135889649391,
|
|
"num_tokens": 19598649.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.326148223876953,
|
|
"epoch": 0.8213256484149856,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004940723597002113,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.21055997759103776,
|
|
"num_tokens": 19610243.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.339675760269165,
|
|
"epoch": 0.8218059558117194,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004940645395988216,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.20540111064910888,
|
|
"num_tokens": 19621467.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.43748722076416,
|
|
"epoch": 0.8222862632084534,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004940567144114036,
|
|
"loss": 5.1911,
|
|
"mean_token_accuracy": 0.20521468967199324,
|
|
"num_tokens": 19633367.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.280074691772461,
|
|
"epoch": 0.8227665706051873,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004940488841381393,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.21650393456220626,
|
|
"num_tokens": 19643144.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.322038555145264,
|
|
"epoch": 0.8232468780019212,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004940410487792103,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.21338038444519042,
|
|
"num_tokens": 19654501.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.361709308624268,
|
|
"epoch": 0.8237271853986552,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004940332083347986,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.20908380001783372,
|
|
"num_tokens": 19665382.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.306746339797973,
|
|
"epoch": 0.8242074927953891,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004940253628050861,
|
|
"loss": 4.936,
|
|
"mean_token_accuracy": 0.22473569065332413,
|
|
"num_tokens": 19677222.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.251218366622925,
|
|
"epoch": 0.824687800192123,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004940175121902552,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.21675127148628234,
|
|
"num_tokens": 19688550.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.372262859344483,
|
|
"epoch": 0.8251681075888568,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000494009656490488,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.2072849303483963,
|
|
"num_tokens": 19700125.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.377041482925415,
|
|
"epoch": 0.8256484149855908,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004940017957059668,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.20963060855865479,
|
|
"num_tokens": 19711969.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.31815013885498,
|
|
"epoch": 0.8261287223823247,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004939939298368742,
|
|
"loss": 5.0993,
|
|
"mean_token_accuracy": 0.21465936601161956,
|
|
"num_tokens": 19723813.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.344383239746094,
|
|
"epoch": 0.8266090297790586,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004939860588833929,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.20407067835330964,
|
|
"num_tokens": 19735539.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.457013177871704,
|
|
"epoch": 0.8270893371757925,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004939781828457055,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.207156802713871,
|
|
"num_tokens": 19747106.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.327617025375366,
|
|
"epoch": 0.8275696445725265,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000493970301723995,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.22132242172956468,
|
|
"num_tokens": 19760156.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.2592857837677,
|
|
"epoch": 0.8280499519692603,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004939624155184443,
|
|
"loss": 4.9854,
|
|
"mean_token_accuracy": 0.2137436553835869,
|
|
"num_tokens": 19771256.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.317019081115722,
|
|
"epoch": 0.8285302593659942,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004939545242292365,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.21734109967947007,
|
|
"num_tokens": 19781332.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.366267538070678,
|
|
"epoch": 0.8290105667627281,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004939466278565547,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.2046363517642021,
|
|
"num_tokens": 19793573.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.300094032287598,
|
|
"epoch": 0.8294908741594621,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004939387264005825,
|
|
"loss": 5.0553,
|
|
"mean_token_accuracy": 0.22160843908786773,
|
|
"num_tokens": 19803421.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.274855470657348,
|
|
"epoch": 0.829971181556196,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004939308198615031,
|
|
"loss": 4.9411,
|
|
"mean_token_accuracy": 0.22383784204721452,
|
|
"num_tokens": 19814440.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.291015243530273,
|
|
"epoch": 0.8304514889529299,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004939229082395001,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.21296679377555847,
|
|
"num_tokens": 19825721.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.294602918624878,
|
|
"epoch": 0.8309317963496637,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004939149915347573,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.22048348635435105,
|
|
"num_tokens": 19837273.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.322047472000122,
|
|
"epoch": 0.8314121037463977,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004939070697474585,
|
|
"loss": 5.0627,
|
|
"mean_token_accuracy": 0.2189880520105362,
|
|
"num_tokens": 19849436.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.262040901184082,
|
|
"epoch": 0.8318924111431316,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004938991428777875,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.2296365961432457,
|
|
"num_tokens": 19860222.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.303294992446899,
|
|
"epoch": 0.8323727185398655,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004938912109259284,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.22054938077926636,
|
|
"num_tokens": 19870934.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.334577989578247,
|
|
"epoch": 0.8328530259365994,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004938832738920654,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.20727307349443436,
|
|
"num_tokens": 19882149.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.352105045318604,
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004938753317763826,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.2173917070031166,
|
|
"num_tokens": 19893276.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.369452667236328,
|
|
"epoch": 0.8338136407300673,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004938673845790646,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.20366691648960114,
|
|
"num_tokens": 19904723.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.336636304855347,
|
|
"epoch": 0.8342939481268011,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004938594323002957,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.21069223880767823,
|
|
"num_tokens": 19915226.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.302987289428711,
|
|
"epoch": 0.834774255523535,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004938514749402609,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.2127903327345848,
|
|
"num_tokens": 19927911.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.342841100692749,
|
|
"epoch": 0.835254562920269,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004938435124991447,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.21555902510881425,
|
|
"num_tokens": 19940356.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.369471168518066,
|
|
"epoch": 0.8357348703170029,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004938355449771318,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.20579011142253875,
|
|
"num_tokens": 19951108.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.26868748664856,
|
|
"epoch": 0.8362151777137368,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004938275723744075,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.21689395755529403,
|
|
"num_tokens": 19962427.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.396554660797119,
|
|
"epoch": 0.8366954851104706,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004938195946911567,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.20994247645139694,
|
|
"num_tokens": 19973476.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.3372321128845215,
|
|
"epoch": 0.8371757925072046,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004938116119275645,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.21437105536460876,
|
|
"num_tokens": 19984034.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.349392986297607,
|
|
"epoch": 0.8376560999039385,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004938036240838166,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.21108293831348418,
|
|
"num_tokens": 19996035.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.351335144042968,
|
|
"epoch": 0.8381364073006724,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004937956311600983,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.21916403919458388,
|
|
"num_tokens": 20007259.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.320114088058472,
|
|
"epoch": 0.8386167146974063,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004937876331565951,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.2123742774128914,
|
|
"num_tokens": 20018673.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.293909978866577,
|
|
"epoch": 0.8390970220941403,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004937796300734926,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.21447703391313552,
|
|
"num_tokens": 20030767.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.374973201751709,
|
|
"epoch": 0.8395773294908742,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004937716219109769,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.2089406043291092,
|
|
"num_tokens": 20041268.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.292406320571899,
|
|
"epoch": 0.840057636887608,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004937636086692336,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.2205505609512329,
|
|
"num_tokens": 20052285.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.37066388130188,
|
|
"epoch": 0.840537944284342,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000493755590348449,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.20929153263568878,
|
|
"num_tokens": 20065113.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.455632162094116,
|
|
"epoch": 0.8410182516810759,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004937475669488091,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.21504518389701843,
|
|
"num_tokens": 20076151.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.304359483718872,
|
|
"epoch": 0.8414985590778098,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004937395384705004,
|
|
"loss": 5.0843,
|
|
"mean_token_accuracy": 0.21089454740285873,
|
|
"num_tokens": 20088195.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.246131372451782,
|
|
"epoch": 0.8419788664745437,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004937315049137089,
|
|
"loss": 4.9576,
|
|
"mean_token_accuracy": 0.22410656064748763,
|
|
"num_tokens": 20098576.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.392441177368164,
|
|
"epoch": 0.8424591738712777,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004937234662786216,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.20310539305210112,
|
|
"num_tokens": 20110176.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.37788577079773,
|
|
"epoch": 0.8429394812680115,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004937154225654246,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.21563199907541275,
|
|
"num_tokens": 20121713.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.409587812423706,
|
|
"epoch": 0.8434197886647454,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004937073737743051,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.20503998696804046,
|
|
"num_tokens": 20134126.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.296372509002685,
|
|
"epoch": 0.8439000960614793,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004936993199054499,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.21902117878198624,
|
|
"num_tokens": 20144791.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.379805946350098,
|
|
"epoch": 0.8443804034582133,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004936912609590458,
|
|
"loss": 5.2054,
|
|
"mean_token_accuracy": 0.21019366681575774,
|
|
"num_tokens": 20157214.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.450400161743164,
|
|
"epoch": 0.8448607108549472,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00049368319693528,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.19938351958990097,
|
|
"num_tokens": 20168952.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.350177001953125,
|
|
"epoch": 0.8453410182516811,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004936751278343397,
|
|
"loss": 5.0845,
|
|
"mean_token_accuracy": 0.21037333756685256,
|
|
"num_tokens": 20181829.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.387225246429443,
|
|
"epoch": 0.845821325648415,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004936670536564123,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.19706704914569856,
|
|
"num_tokens": 20193362.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.338515043258667,
|
|
"epoch": 0.8463016330451489,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004936589744016853,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.2130685493350029,
|
|
"num_tokens": 20205159.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.326151418685913,
|
|
"epoch": 0.8467819404418828,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000493650890070346,
|
|
"loss": 5.0295,
|
|
"mean_token_accuracy": 0.22603174149990082,
|
|
"num_tokens": 20217075.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.335449981689453,
|
|
"epoch": 0.8472622478386167,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004936428006625824,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.2198606699705124,
|
|
"num_tokens": 20227901.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.347858715057373,
|
|
"epoch": 0.8477425552353506,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004936347061785823,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.21948010176420213,
|
|
"num_tokens": 20239945.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.393839931488037,
|
|
"epoch": 0.8482228626320846,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004936266066185334,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.20632718950510026,
|
|
"num_tokens": 20251503.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.29513463973999,
|
|
"epoch": 0.8487031700288185,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004936185019826239,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.2160756379365921,
|
|
"num_tokens": 20263044.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.344191026687622,
|
|
"epoch": 0.8491834774255523,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004936103922710419,
|
|
"loss": 5.0376,
|
|
"mean_token_accuracy": 0.2183619663119316,
|
|
"num_tokens": 20273563.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.333452129364014,
|
|
"epoch": 0.8496637848222862,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004936022774839759,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.21377312242984772,
|
|
"num_tokens": 20285482.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.443333387374878,
|
|
"epoch": 0.8501440922190202,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004935941576216141,
|
|
"loss": 5.268,
|
|
"mean_token_accuracy": 0.20341867357492446,
|
|
"num_tokens": 20296666.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.22430272102356,
|
|
"epoch": 0.8506243996157541,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000493586032684145,
|
|
"loss": 4.9551,
|
|
"mean_token_accuracy": 0.22342516332864762,
|
|
"num_tokens": 20308978.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.261478471755981,
|
|
"epoch": 0.851104707012488,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004935779026717573,
|
|
"loss": 5.0398,
|
|
"mean_token_accuracy": 0.21408196687698364,
|
|
"num_tokens": 20321488.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.2735799789428714,
|
|
"epoch": 0.8515850144092219,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004935697675846396,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.23052898645401002,
|
|
"num_tokens": 20332938.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.272325849533081,
|
|
"epoch": 0.8520653218059558,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004935616274229811,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.22203793078660966,
|
|
"num_tokens": 20342986.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.300751733779907,
|
|
"epoch": 0.8525456292026897,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004935534821869705,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.2123943343758583,
|
|
"num_tokens": 20355791.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.233129358291626,
|
|
"epoch": 0.8530259365994236,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004935453318767971,
|
|
"loss": 4.9309,
|
|
"mean_token_accuracy": 0.22178226709365845,
|
|
"num_tokens": 20367080.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.330565071105957,
|
|
"epoch": 0.8535062439961575,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049353717649265,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.22484754920005798,
|
|
"num_tokens": 20376697.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.3550821304321286,
|
|
"epoch": 0.8539865513928915,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004935290160347185,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.21934617012739183,
|
|
"num_tokens": 20387430.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.3011399269104,
|
|
"epoch": 0.8544668587896254,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004935208505031922,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.21876584887504577,
|
|
"num_tokens": 20398488.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.251365756988525,
|
|
"epoch": 0.8549471661863592,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004935126798982606,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.21767811328172684,
|
|
"num_tokens": 20410316.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.318483972549439,
|
|
"epoch": 0.8554274735830932,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004935045042201135,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.2249806195497513,
|
|
"num_tokens": 20421645.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.3637378215789795,
|
|
"epoch": 0.8559077809798271,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004934963234689407,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.2078435719013214,
|
|
"num_tokens": 20433397.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.272715377807617,
|
|
"epoch": 0.856388088376561,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000493488137644932,
|
|
"loss": 5.0126,
|
|
"mean_token_accuracy": 0.22031760662794114,
|
|
"num_tokens": 20446218.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.3629358291625975,
|
|
"epoch": 0.8568683957732949,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004934799467482774,
|
|
"loss": 5.1104,
|
|
"mean_token_accuracy": 0.2142086386680603,
|
|
"num_tokens": 20457265.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.325270271301269,
|
|
"epoch": 0.8573487031700289,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004934717507791673,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.2102256551384926,
|
|
"num_tokens": 20468748.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.350523042678833,
|
|
"epoch": 0.8578290105667628,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004934635497377919,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.21354436427354812,
|
|
"num_tokens": 20481416.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.272500276565552,
|
|
"epoch": 0.8583093179634966,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004934553436243415,
|
|
"loss": 5.0154,
|
|
"mean_token_accuracy": 0.2177797794342041,
|
|
"num_tokens": 20493063.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.249647235870361,
|
|
"epoch": 0.8587896253602305,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004934471324390067,
|
|
"loss": 5.0015,
|
|
"mean_token_accuracy": 0.2156543180346489,
|
|
"num_tokens": 20504000.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.33812108039856,
|
|
"epoch": 0.8592699327569645,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004934389161819783,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.21617372930049897,
|
|
"num_tokens": 20516419.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.331470489501953,
|
|
"epoch": 0.8597502401536984,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004934306948534467,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.2139761984348297,
|
|
"num_tokens": 20527385.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.33019003868103,
|
|
"epoch": 0.8602305475504323,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004934224684536031,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.21539317667484284,
|
|
"num_tokens": 20538051.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.3348424434661865,
|
|
"epoch": 0.8607108549471661,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004934142369826382,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.2150691881775856,
|
|
"num_tokens": 20550321.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.349039459228516,
|
|
"epoch": 0.8611911623439001,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004934060004407434,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.2163606807589531,
|
|
"num_tokens": 20561229.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.298765516281128,
|
|
"epoch": 0.861671469740634,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004933977588281099,
|
|
"loss": 5.0059,
|
|
"mean_token_accuracy": 0.21803612411022186,
|
|
"num_tokens": 20572040.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.263881349563599,
|
|
"epoch": 0.8621517771373679,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004933895121449288,
|
|
"loss": 5.0304,
|
|
"mean_token_accuracy": 0.22013145685195923,
|
|
"num_tokens": 20583110.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.310286951065064,
|
|
"epoch": 0.8626320845341018,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004933812603913917,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.2132230743765831,
|
|
"num_tokens": 20593647.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.244890308380127,
|
|
"epoch": 0.8631123919308358,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004933730035676903,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.2285411074757576,
|
|
"num_tokens": 20604428.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.208324146270752,
|
|
"epoch": 0.8635926993275697,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004933647416740161,
|
|
"loss": 4.9729,
|
|
"mean_token_accuracy": 0.22819437831640244,
|
|
"num_tokens": 20615811.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.338266658782959,
|
|
"epoch": 0.8640730067243035,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000493356474710561,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.21221038401126863,
|
|
"num_tokens": 20627679.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.377738285064697,
|
|
"epoch": 0.8645533141210374,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000493348202677517,
|
|
"loss": 5.0993,
|
|
"mean_token_accuracy": 0.21800316274166107,
|
|
"num_tokens": 20638879.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.8645533141210374,
|
|
"eval_entropy": 5.128290109318213,
|
|
"eval_loss": 5.07960844039917,
|
|
"eval_mean_token_accuracy": 0.22225927816443272,
|
|
"eval_num_tokens": 20638879.0,
|
|
"eval_runtime": 20.6364,
|
|
"eval_samples_per_second": 1590.153,
|
|
"eval_steps_per_second": 198.775,
|
|
"step": 9000
|
|
}
|
|
],
|
|
"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": 4682294471393280.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|