6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2881844380403458,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1562945946255360.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|