0c7ef51387
Model: fpadovani/hin-deva-100mb-after-ppt-Dp-100mb-ckpt500_seed455 Source: Original Platform
24079 lines
660 KiB
JSON
24079 lines
660 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.1527377521613833,
|
|
"eval_steps": 3000,
|
|
"global_step": 12000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 6.845805501937866,
|
|
"epoch": 0.0004803073967339097,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.6326,
|
|
"mean_token_accuracy": 0.12870624884963036,
|
|
"num_tokens": 10821.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 6.8324442386627195,
|
|
"epoch": 0.0009606147934678194,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.5613,
|
|
"mean_token_accuracy": 0.13194445222616197,
|
|
"num_tokens": 21838.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 6.819680023193359,
|
|
"epoch": 0.001440922190201729,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.593,
|
|
"mean_token_accuracy": 0.12538625448942184,
|
|
"num_tokens": 33483.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 6.857285118103027,
|
|
"epoch": 0.0019212295869356388,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.6862,
|
|
"mean_token_accuracy": 0.1256486490368843,
|
|
"num_tokens": 45150.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.892150020599365,
|
|
"epoch": 0.0024015369836695487,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.5826,
|
|
"mean_token_accuracy": 0.12348027229309082,
|
|
"num_tokens": 55862.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 6.904298925399781,
|
|
"epoch": 0.002881844380403458,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.6976,
|
|
"mean_token_accuracy": 0.12837719544768333,
|
|
"num_tokens": 66766.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.884329032897949,
|
|
"epoch": 0.0033621517771373678,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.4329,
|
|
"mean_token_accuracy": 0.13798720836639405,
|
|
"num_tokens": 77012.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 6.914054870605469,
|
|
"epoch": 0.0038424591738712775,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.6479,
|
|
"mean_token_accuracy": 0.12707344740629195,
|
|
"num_tokens": 89034.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 6.835504341125488,
|
|
"epoch": 0.004322766570605188,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.5321,
|
|
"mean_token_accuracy": 0.13442391008138657,
|
|
"num_tokens": 100341.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 6.8050981044769285,
|
|
"epoch": 0.004803073967339097,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.4944,
|
|
"mean_token_accuracy": 0.1337900787591934,
|
|
"num_tokens": 111997.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 6.8239950180053714,
|
|
"epoch": 0.005283381364073006,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.5452,
|
|
"mean_token_accuracy": 0.12953593134880065,
|
|
"num_tokens": 123705.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 6.816039228439331,
|
|
"epoch": 0.005763688760806916,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.4881,
|
|
"mean_token_accuracy": 0.13681765496730805,
|
|
"num_tokens": 134091.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 6.790379428863526,
|
|
"epoch": 0.006243996157540826,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.5926,
|
|
"mean_token_accuracy": 0.13416145518422126,
|
|
"num_tokens": 145731.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 6.8630434513092045,
|
|
"epoch": 0.0067243035542747355,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.51,
|
|
"mean_token_accuracy": 0.1349278561770916,
|
|
"num_tokens": 156979.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 6.868352890014648,
|
|
"epoch": 0.007204610951008645,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.4964,
|
|
"mean_token_accuracy": 0.1383296526968479,
|
|
"num_tokens": 167021.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 6.792302656173706,
|
|
"epoch": 0.007684918347742555,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.5049,
|
|
"mean_token_accuracy": 0.13316406682133675,
|
|
"num_tokens": 179269.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 6.745629453659058,
|
|
"epoch": 0.008165225744476465,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.4804,
|
|
"mean_token_accuracy": 0.1358616307377815,
|
|
"num_tokens": 190328.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 6.760327434539795,
|
|
"epoch": 0.008645533141210375,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.3536,
|
|
"mean_token_accuracy": 0.139989273250103,
|
|
"num_tokens": 201522.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 6.793478059768677,
|
|
"epoch": 0.009125840537944284,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.4743,
|
|
"mean_token_accuracy": 0.14095518440008165,
|
|
"num_tokens": 212963.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 6.847437191009521,
|
|
"epoch": 0.009606147934678195,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.6791,
|
|
"mean_token_accuracy": 0.12346139177680016,
|
|
"num_tokens": 224446.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 6.894752740859985,
|
|
"epoch": 0.010086455331412104,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.5087,
|
|
"mean_token_accuracy": 0.13819111213088037,
|
|
"num_tokens": 235334.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 6.9679093837738035,
|
|
"epoch": 0.010566762728146013,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.5823,
|
|
"mean_token_accuracy": 0.12812134698033334,
|
|
"num_tokens": 247024.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 6.816913843154907,
|
|
"epoch": 0.011047070124879923,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.4988,
|
|
"mean_token_accuracy": 0.1326398141682148,
|
|
"num_tokens": 258354.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 6.757030248641968,
|
|
"epoch": 0.011527377521613832,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.5505,
|
|
"mean_token_accuracy": 0.13475370407104492,
|
|
"num_tokens": 271202.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 6.8415162563323975,
|
|
"epoch": 0.012007684918347743,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.5545,
|
|
"mean_token_accuracy": 0.12843683063983918,
|
|
"num_tokens": 282405.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 6.810266208648682,
|
|
"epoch": 0.012487992315081652,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.5196,
|
|
"mean_token_accuracy": 0.1312414713203907,
|
|
"num_tokens": 294211.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 6.916629600524902,
|
|
"epoch": 0.012968299711815562,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.5531,
|
|
"mean_token_accuracy": 0.12653037831187247,
|
|
"num_tokens": 305420.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 6.8390460968017575,
|
|
"epoch": 0.013448607108549471,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.4628,
|
|
"mean_token_accuracy": 0.1347823828458786,
|
|
"num_tokens": 316430.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 6.7258693218231205,
|
|
"epoch": 0.013928914505283382,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.4777,
|
|
"mean_token_accuracy": 0.13652994483709335,
|
|
"num_tokens": 328406.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 6.8050377368927,
|
|
"epoch": 0.01440922190201729,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.4622,
|
|
"mean_token_accuracy": 0.13485521599650382,
|
|
"num_tokens": 339051.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 6.775390768051148,
|
|
"epoch": 0.014889529298751201,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.4295,
|
|
"mean_token_accuracy": 0.13496242091059685,
|
|
"num_tokens": 350308.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 6.888868618011474,
|
|
"epoch": 0.01536983669548511,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.466,
|
|
"mean_token_accuracy": 0.1328311488032341,
|
|
"num_tokens": 362159.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 6.7834686756134035,
|
|
"epoch": 0.01585014409221902,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.5197,
|
|
"mean_token_accuracy": 0.1340256117284298,
|
|
"num_tokens": 375157.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 6.732735347747803,
|
|
"epoch": 0.01633045148895293,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.3494,
|
|
"mean_token_accuracy": 0.1391011193394661,
|
|
"num_tokens": 387318.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 6.73529953956604,
|
|
"epoch": 0.01681075888568684,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.4332,
|
|
"mean_token_accuracy": 0.140291528403759,
|
|
"num_tokens": 398933.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 6.753161287307739,
|
|
"epoch": 0.01729106628242075,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.4212,
|
|
"mean_token_accuracy": 0.14206939190626144,
|
|
"num_tokens": 410460.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 6.807398653030395,
|
|
"epoch": 0.01777137367915466,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.4542,
|
|
"mean_token_accuracy": 0.13703907132148743,
|
|
"num_tokens": 421894.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 6.740799045562744,
|
|
"epoch": 0.01825168107588857,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.4923,
|
|
"mean_token_accuracy": 0.13176504224538804,
|
|
"num_tokens": 432976.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 6.845755910873413,
|
|
"epoch": 0.018731988472622477,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.5375,
|
|
"mean_token_accuracy": 0.1358255296945572,
|
|
"num_tokens": 444859.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 6.780419158935547,
|
|
"epoch": 0.01921229586935639,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.4609,
|
|
"mean_token_accuracy": 0.1418136939406395,
|
|
"num_tokens": 456508.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 6.7831775665283205,
|
|
"epoch": 0.0196926032660903,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.4672,
|
|
"mean_token_accuracy": 0.1363604933023453,
|
|
"num_tokens": 469064.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 6.7620916843414305,
|
|
"epoch": 0.020172910662824207,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.4243,
|
|
"mean_token_accuracy": 0.14104704037308693,
|
|
"num_tokens": 480743.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 6.745031690597534,
|
|
"epoch": 0.020653218059558116,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.4653,
|
|
"mean_token_accuracy": 0.13698699995875357,
|
|
"num_tokens": 493378.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 6.814111566543579,
|
|
"epoch": 0.021133525456292025,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.4723,
|
|
"mean_token_accuracy": 0.1333048313856125,
|
|
"num_tokens": 505641.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 6.795113658905029,
|
|
"epoch": 0.021613832853025938,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.5338,
|
|
"mean_token_accuracy": 0.13384313508868217,
|
|
"num_tokens": 517783.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 6.722929668426514,
|
|
"epoch": 0.022094140249759846,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.3621,
|
|
"mean_token_accuracy": 0.1424078032374382,
|
|
"num_tokens": 528407.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 6.831379413604736,
|
|
"epoch": 0.022574447646493755,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.5324,
|
|
"mean_token_accuracy": 0.1359228663146496,
|
|
"num_tokens": 539974.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 6.731849145889282,
|
|
"epoch": 0.023054755043227664,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.3723,
|
|
"mean_token_accuracy": 0.1379515901207924,
|
|
"num_tokens": 551127.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 6.754569816589355,
|
|
"epoch": 0.023535062439961577,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.4283,
|
|
"mean_token_accuracy": 0.14257267117500305,
|
|
"num_tokens": 561980.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 6.748660755157471,
|
|
"epoch": 0.024015369836695485,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.4724,
|
|
"mean_token_accuracy": 0.13603295460343362,
|
|
"num_tokens": 573840.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 6.679523086547851,
|
|
"epoch": 0.024495677233429394,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.4282,
|
|
"mean_token_accuracy": 0.1383022792637348,
|
|
"num_tokens": 585110.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 6.642319250106811,
|
|
"epoch": 0.024975984630163303,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.3071,
|
|
"mean_token_accuracy": 0.1404804766178131,
|
|
"num_tokens": 596902.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 6.77508692741394,
|
|
"epoch": 0.025456292026897216,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.4858,
|
|
"mean_token_accuracy": 0.13461525812745095,
|
|
"num_tokens": 608738.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 6.804401445388794,
|
|
"epoch": 0.025936599423631124,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.4096,
|
|
"mean_token_accuracy": 0.13826687932014464,
|
|
"num_tokens": 621078.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 6.799535465240479,
|
|
"epoch": 0.026416906820365033,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.5096,
|
|
"mean_token_accuracy": 0.13709565252065659,
|
|
"num_tokens": 632333.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 6.714285564422608,
|
|
"epoch": 0.026897214217098942,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.3294,
|
|
"mean_token_accuracy": 0.13480642214417457,
|
|
"num_tokens": 644474.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 6.669364023208618,
|
|
"epoch": 0.027377521613832854,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.4381,
|
|
"mean_token_accuracy": 0.13586120754480363,
|
|
"num_tokens": 655608.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 6.735668182373047,
|
|
"epoch": 0.027857829010566763,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.4302,
|
|
"mean_token_accuracy": 0.13791066855192186,
|
|
"num_tokens": 667371.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 6.750858640670776,
|
|
"epoch": 0.028338136407300672,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.4653,
|
|
"mean_token_accuracy": 0.1322570785880089,
|
|
"num_tokens": 679152.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.662555599212647,
|
|
"epoch": 0.02881844380403458,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.3797,
|
|
"mean_token_accuracy": 0.14153480380773545,
|
|
"num_tokens": 690359.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.780093812942505,
|
|
"epoch": 0.029298751200768493,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.3685,
|
|
"mean_token_accuracy": 0.13668907657265664,
|
|
"num_tokens": 701819.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 6.678733968734742,
|
|
"epoch": 0.029779058597502402,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.3892,
|
|
"mean_token_accuracy": 0.13896276280283928,
|
|
"num_tokens": 711048.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.702047061920166,
|
|
"epoch": 0.03025936599423631,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.3094,
|
|
"mean_token_accuracy": 0.144956311583519,
|
|
"num_tokens": 721399.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 6.66398663520813,
|
|
"epoch": 0.03073967339097022,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.323,
|
|
"mean_token_accuracy": 0.14815439581871032,
|
|
"num_tokens": 732144.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 6.663816642761231,
|
|
"epoch": 0.03121998078770413,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.14062243029475213,
|
|
"num_tokens": 743962.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 6.774586772918701,
|
|
"epoch": 0.03170028818443804,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.4838,
|
|
"mean_token_accuracy": 0.134712003916502,
|
|
"num_tokens": 755641.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 6.539123487472534,
|
|
"epoch": 0.03218059558117195,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.3358,
|
|
"mean_token_accuracy": 0.14351314306259155,
|
|
"num_tokens": 766798.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.761009979248047,
|
|
"epoch": 0.03266090297790586,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.4273,
|
|
"mean_token_accuracy": 0.14208256751298903,
|
|
"num_tokens": 778097.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.617664432525634,
|
|
"epoch": 0.03314121037463977,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.3365,
|
|
"mean_token_accuracy": 0.14357409998774529,
|
|
"num_tokens": 789775.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 6.800221252441406,
|
|
"epoch": 0.03362151777137368,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.4119,
|
|
"mean_token_accuracy": 0.1336173504590988,
|
|
"num_tokens": 800155.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.688700437545776,
|
|
"epoch": 0.034101825168107586,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.4309,
|
|
"mean_token_accuracy": 0.14149890020489692,
|
|
"num_tokens": 811213.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 6.706441020965576,
|
|
"epoch": 0.0345821325648415,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.4167,
|
|
"mean_token_accuracy": 0.13566643744707108,
|
|
"num_tokens": 822832.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 6.64611029624939,
|
|
"epoch": 0.03506243996157541,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.4001,
|
|
"mean_token_accuracy": 0.14356471225619316,
|
|
"num_tokens": 834824.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 6.767692947387696,
|
|
"epoch": 0.03554274735830932,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.4247,
|
|
"mean_token_accuracy": 0.13687072023749353,
|
|
"num_tokens": 846969.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.731805896759033,
|
|
"epoch": 0.03602305475504323,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.5275,
|
|
"mean_token_accuracy": 0.1303038403391838,
|
|
"num_tokens": 859271.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.70332555770874,
|
|
"epoch": 0.03650336215177714,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.397,
|
|
"mean_token_accuracy": 0.13794534802436828,
|
|
"num_tokens": 869754.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.676585054397583,
|
|
"epoch": 0.036983669548511046,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.3553,
|
|
"mean_token_accuracy": 0.14230940788984298,
|
|
"num_tokens": 880519.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 6.566428184509277,
|
|
"epoch": 0.037463976945244955,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.3207,
|
|
"mean_token_accuracy": 0.13795292973518372,
|
|
"num_tokens": 890765.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.678460311889649,
|
|
"epoch": 0.037944284341978864,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.3213,
|
|
"mean_token_accuracy": 0.13789281025528907,
|
|
"num_tokens": 901717.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.771489000320434,
|
|
"epoch": 0.03842459173871278,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.4173,
|
|
"mean_token_accuracy": 0.13703501969575882,
|
|
"num_tokens": 913334.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.673534536361695,
|
|
"epoch": 0.03890489913544669,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.4358,
|
|
"mean_token_accuracy": 0.13748908787965775,
|
|
"num_tokens": 924753.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.69045729637146,
|
|
"epoch": 0.0393852065321806,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.3857,
|
|
"mean_token_accuracy": 0.13825666159391403,
|
|
"num_tokens": 935692.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.684324502944946,
|
|
"epoch": 0.039865513928914506,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.4318,
|
|
"mean_token_accuracy": 0.13761915788054466,
|
|
"num_tokens": 947902.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.693652248382568,
|
|
"epoch": 0.040345821325648415,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.4061,
|
|
"mean_token_accuracy": 0.14424072802066804,
|
|
"num_tokens": 959437.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.5537275791168215,
|
|
"epoch": 0.040826128722382324,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.1485251747071743,
|
|
"num_tokens": 970191.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.59421329498291,
|
|
"epoch": 0.04130643611911623,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.349,
|
|
"mean_token_accuracy": 0.14038845673203468,
|
|
"num_tokens": 981811.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.6880528926849365,
|
|
"epoch": 0.04178674351585014,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.4534,
|
|
"mean_token_accuracy": 0.13162965103983879,
|
|
"num_tokens": 994034.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.761573839187622,
|
|
"epoch": 0.04226705091258405,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.4095,
|
|
"mean_token_accuracy": 0.13384866043925286,
|
|
"num_tokens": 1005506.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.527941131591797,
|
|
"epoch": 0.042747358309317966,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.3822,
|
|
"mean_token_accuracy": 0.13079070374369622,
|
|
"num_tokens": 1017103.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.732952213287353,
|
|
"epoch": 0.043227665706051875,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.4624,
|
|
"mean_token_accuracy": 0.13197413310408593,
|
|
"num_tokens": 1029606.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.717301893234253,
|
|
"epoch": 0.043707973102785784,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.4124,
|
|
"mean_token_accuracy": 0.13508057743310928,
|
|
"num_tokens": 1041899.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.644534492492676,
|
|
"epoch": 0.04418828049951969,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.3181,
|
|
"mean_token_accuracy": 0.14683899581432341,
|
|
"num_tokens": 1053577.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.72195086479187,
|
|
"epoch": 0.0446685878962536,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.3696,
|
|
"mean_token_accuracy": 0.1393313579261303,
|
|
"num_tokens": 1065541.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.632449531555176,
|
|
"epoch": 0.04514889529298751,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.13726358041167258,
|
|
"num_tokens": 1076138.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.624440240859985,
|
|
"epoch": 0.04562920268972142,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.4125,
|
|
"mean_token_accuracy": 0.138886184245348,
|
|
"num_tokens": 1087620.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.616486501693726,
|
|
"epoch": 0.04610951008645533,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.14400001466274262,
|
|
"num_tokens": 1099493.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.6268257141113285,
|
|
"epoch": 0.046589817483189244,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.3667,
|
|
"mean_token_accuracy": 0.1370286226272583,
|
|
"num_tokens": 1110559.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.628957080841064,
|
|
"epoch": 0.04707012487992315,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.3286,
|
|
"mean_token_accuracy": 0.1350909538567066,
|
|
"num_tokens": 1121051.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.550091123580932,
|
|
"epoch": 0.04755043227665706,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.2996,
|
|
"mean_token_accuracy": 0.14171547815203667,
|
|
"num_tokens": 1132305.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.606603384017944,
|
|
"epoch": 0.04803073967339097,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.308,
|
|
"mean_token_accuracy": 0.1442063570022583,
|
|
"num_tokens": 1142979.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.564784145355224,
|
|
"epoch": 0.04851104707012488,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.3125,
|
|
"mean_token_accuracy": 0.14522673487663268,
|
|
"num_tokens": 1153889.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.613766813278199,
|
|
"epoch": 0.04899135446685879,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.3265,
|
|
"mean_token_accuracy": 0.13703470006585122,
|
|
"num_tokens": 1166030.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.763839912414551,
|
|
"epoch": 0.0494716618635927,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.5003,
|
|
"mean_token_accuracy": 0.13086057305336,
|
|
"num_tokens": 1177545.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.6000009059906,
|
|
"epoch": 0.049951969260326606,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.3245,
|
|
"mean_token_accuracy": 0.14302466735243796,
|
|
"num_tokens": 1188944.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.479497623443604,
|
|
"epoch": 0.05043227665706052,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.3873,
|
|
"mean_token_accuracy": 0.13586132526397704,
|
|
"num_tokens": 1199517.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.65042929649353,
|
|
"epoch": 0.05091258405379443,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.3071,
|
|
"mean_token_accuracy": 0.1335797443985939,
|
|
"num_tokens": 1211536.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.517299795150757,
|
|
"epoch": 0.05139289145052834,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.2241,
|
|
"mean_token_accuracy": 0.1449120409786701,
|
|
"num_tokens": 1224159.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.549662160873413,
|
|
"epoch": 0.05187319884726225,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.3091,
|
|
"mean_token_accuracy": 0.15078746303915977,
|
|
"num_tokens": 1235226.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.471032619476318,
|
|
"epoch": 0.05235350624399616,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.2327,
|
|
"mean_token_accuracy": 0.1502161517739296,
|
|
"num_tokens": 1245862.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.543156433105469,
|
|
"epoch": 0.052833813640730067,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.14741843491792678,
|
|
"num_tokens": 1257512.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.532389879226685,
|
|
"epoch": 0.053314121037463975,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.3629,
|
|
"mean_token_accuracy": 0.1384106993675232,
|
|
"num_tokens": 1269317.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.504622459411621,
|
|
"epoch": 0.053794428434197884,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.2464,
|
|
"mean_token_accuracy": 0.13634237721562387,
|
|
"num_tokens": 1281878.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.503180837631225,
|
|
"epoch": 0.05427473583093179,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.257,
|
|
"mean_token_accuracy": 0.14371064007282258,
|
|
"num_tokens": 1293178.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.489447402954101,
|
|
"epoch": 0.05475504322766571,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.2417,
|
|
"mean_token_accuracy": 0.14116708934307098,
|
|
"num_tokens": 1304969.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.604181814193725,
|
|
"epoch": 0.05523535062439962,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.2788,
|
|
"mean_token_accuracy": 0.14233512282371522,
|
|
"num_tokens": 1317301.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.477435731887818,
|
|
"epoch": 0.05571565802113353,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.265,
|
|
"mean_token_accuracy": 0.1436339274048805,
|
|
"num_tokens": 1327688.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.550082349777222,
|
|
"epoch": 0.056195965417867436,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.2146,
|
|
"mean_token_accuracy": 0.1425333023071289,
|
|
"num_tokens": 1338750.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.4750957012176515,
|
|
"epoch": 0.056676272814601344,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.3745,
|
|
"mean_token_accuracy": 0.12992137521505356,
|
|
"num_tokens": 1350899.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.533016681671143,
|
|
"epoch": 0.05715658021133525,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.2198,
|
|
"mean_token_accuracy": 0.14716191366314887,
|
|
"num_tokens": 1363184.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.425290632247925,
|
|
"epoch": 0.05763688760806916,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.1448550522327423,
|
|
"num_tokens": 1374192.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.497121429443359,
|
|
"epoch": 0.05811719500480307,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.2521,
|
|
"mean_token_accuracy": 0.13990678563714026,
|
|
"num_tokens": 1384888.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.52073392868042,
|
|
"epoch": 0.05859750240153699,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.3405,
|
|
"mean_token_accuracy": 0.14426726028323172,
|
|
"num_tokens": 1395139.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.423754501342773,
|
|
"epoch": 0.059077809798270896,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.1441607266664505,
|
|
"num_tokens": 1407219.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.469784259796143,
|
|
"epoch": 0.059558117195004805,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.2751,
|
|
"mean_token_accuracy": 0.13724448457360267,
|
|
"num_tokens": 1418917.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.500107717514038,
|
|
"epoch": 0.060038424591738714,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.2195,
|
|
"mean_token_accuracy": 0.14356782287359238,
|
|
"num_tokens": 1430792.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.331269454956055,
|
|
"epoch": 0.06051873198847262,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.229,
|
|
"mean_token_accuracy": 0.14871832877397537,
|
|
"num_tokens": 1442825.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.626306200027466,
|
|
"epoch": 0.06099903938520653,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.3337,
|
|
"mean_token_accuracy": 0.14251203015446662,
|
|
"num_tokens": 1454078.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.469714879989624,
|
|
"epoch": 0.06147934678194044,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.2641,
|
|
"mean_token_accuracy": 0.14170267581939697,
|
|
"num_tokens": 1465164.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.445518112182617,
|
|
"epoch": 0.06195965417867435,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.2758,
|
|
"mean_token_accuracy": 0.1456916779279709,
|
|
"num_tokens": 1476813.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.426507139205933,
|
|
"epoch": 0.06243996157540826,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.2858,
|
|
"mean_token_accuracy": 0.14199284166097642,
|
|
"num_tokens": 1488547.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.549951553344727,
|
|
"epoch": 0.06292026897214217,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.2862,
|
|
"mean_token_accuracy": 0.13861191645264626,
|
|
"num_tokens": 1500714.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.4686461925506595,
|
|
"epoch": 0.06340057636887608,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.271,
|
|
"mean_token_accuracy": 0.14288542419672012,
|
|
"num_tokens": 1512212.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.412826299667358,
|
|
"epoch": 0.06388088376560999,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.2458,
|
|
"mean_token_accuracy": 0.14411089718341827,
|
|
"num_tokens": 1523610.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.428916597366333,
|
|
"epoch": 0.0643611911623439,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.207,
|
|
"mean_token_accuracy": 0.14545318782329558,
|
|
"num_tokens": 1535543.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.586844778060913,
|
|
"epoch": 0.06484149855907781,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.4396,
|
|
"mean_token_accuracy": 0.1306020125746727,
|
|
"num_tokens": 1547183.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.379982614517212,
|
|
"epoch": 0.06532180595581172,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.201,
|
|
"mean_token_accuracy": 0.1453273430466652,
|
|
"num_tokens": 1559265.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.4871210098266605,
|
|
"epoch": 0.06580211335254563,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.2149,
|
|
"mean_token_accuracy": 0.1423127330839634,
|
|
"num_tokens": 1569774.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.295485496520996,
|
|
"epoch": 0.06628242074927954,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.1273,
|
|
"mean_token_accuracy": 0.14571069031953812,
|
|
"num_tokens": 1579408.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.419068622589111,
|
|
"epoch": 0.06676272814601344,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.2013,
|
|
"mean_token_accuracy": 0.14634275287389756,
|
|
"num_tokens": 1591849.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.380165672302246,
|
|
"epoch": 0.06724303554274735,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.2564,
|
|
"mean_token_accuracy": 0.1449852168560028,
|
|
"num_tokens": 1603269.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.5532173156738285,
|
|
"epoch": 0.06772334293948126,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.2875,
|
|
"mean_token_accuracy": 0.14029174968600272,
|
|
"num_tokens": 1613639.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.4776379585266115,
|
|
"epoch": 0.06820365033621517,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.3104,
|
|
"mean_token_accuracy": 0.13592585399746895,
|
|
"num_tokens": 1625393.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.359980726242066,
|
|
"epoch": 0.0686839577329491,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.14281153082847595,
|
|
"num_tokens": 1636355.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.46089243888855,
|
|
"epoch": 0.069164265129683,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.2008,
|
|
"mean_token_accuracy": 0.14487438052892684,
|
|
"num_tokens": 1646157.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.30911774635315,
|
|
"epoch": 0.06964457252641691,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.1967,
|
|
"mean_token_accuracy": 0.1431838683784008,
|
|
"num_tokens": 1657827.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.406947374343872,
|
|
"epoch": 0.07012487992315082,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.2665,
|
|
"mean_token_accuracy": 0.14254478514194488,
|
|
"num_tokens": 1669023.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.439149236679077,
|
|
"epoch": 0.07060518731988473,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.2449,
|
|
"mean_token_accuracy": 0.1420585885643959,
|
|
"num_tokens": 1680048.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.492261695861816,
|
|
"epoch": 0.07108549471661864,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4099,
|
|
"mean_token_accuracy": 0.13245131075382233,
|
|
"num_tokens": 1690907.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.504529047012329,
|
|
"epoch": 0.07156580211335255,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.2452,
|
|
"mean_token_accuracy": 0.14205930680036544,
|
|
"num_tokens": 1702337.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.37948842048645,
|
|
"epoch": 0.07204610951008646,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.1913,
|
|
"mean_token_accuracy": 0.14261919558048247,
|
|
"num_tokens": 1713242.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.319987010955811,
|
|
"epoch": 0.07252641690682037,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.1894,
|
|
"mean_token_accuracy": 0.14029277563095094,
|
|
"num_tokens": 1724939.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.339571523666382,
|
|
"epoch": 0.07300672430355427,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.1217,
|
|
"mean_token_accuracy": 0.15060591399669648,
|
|
"num_tokens": 1737311.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.433168601989746,
|
|
"epoch": 0.07348703170028818,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.2744,
|
|
"mean_token_accuracy": 0.14171026945114135,
|
|
"num_tokens": 1749528.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.279998445510865,
|
|
"epoch": 0.07396733909702209,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.1478,
|
|
"mean_token_accuracy": 0.14513302072882653,
|
|
"num_tokens": 1760304.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.366886043548584,
|
|
"epoch": 0.074447646493756,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.1265,
|
|
"mean_token_accuracy": 0.14714072048664092,
|
|
"num_tokens": 1772014.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.309161758422851,
|
|
"epoch": 0.07492795389048991,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.1815,
|
|
"mean_token_accuracy": 0.13897588327527047,
|
|
"num_tokens": 1784585.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.3078656673431395,
|
|
"epoch": 0.07540826128722382,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.14889669567346572,
|
|
"num_tokens": 1795246.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.25552887916565,
|
|
"epoch": 0.07588856868395773,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.1005,
|
|
"mean_token_accuracy": 0.15239656567573548,
|
|
"num_tokens": 1806826.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.338869380950928,
|
|
"epoch": 0.07636887608069164,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.2446,
|
|
"mean_token_accuracy": 0.14244618490338326,
|
|
"num_tokens": 1818766.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.325174713134766,
|
|
"epoch": 0.07684918347742556,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.1009,
|
|
"mean_token_accuracy": 0.155482742190361,
|
|
"num_tokens": 1830824.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.289180946350098,
|
|
"epoch": 0.07732949087415947,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.1829,
|
|
"mean_token_accuracy": 0.14374645203351974,
|
|
"num_tokens": 1841792.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.302430200576782,
|
|
"epoch": 0.07780979827089338,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.1559,
|
|
"mean_token_accuracy": 0.14021549075841905,
|
|
"num_tokens": 1854683.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.337079668045044,
|
|
"epoch": 0.07829010566762729,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2478,
|
|
"mean_token_accuracy": 0.14183034971356392,
|
|
"num_tokens": 1865826.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.36335711479187,
|
|
"epoch": 0.0787704130643612,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.1493820831179619,
|
|
"num_tokens": 1876759.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.290498876571656,
|
|
"epoch": 0.0792507204610951,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.222,
|
|
"mean_token_accuracy": 0.14272527173161506,
|
|
"num_tokens": 1888013.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.415748977661133,
|
|
"epoch": 0.07973102785782901,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.14676567614078523,
|
|
"num_tokens": 1898964.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.28214316368103,
|
|
"epoch": 0.08021133525456292,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.149,
|
|
"mean_token_accuracy": 0.1509616807103157,
|
|
"num_tokens": 1909728.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.214513111114502,
|
|
"epoch": 0.08069164265129683,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.0757,
|
|
"mean_token_accuracy": 0.15560405552387238,
|
|
"num_tokens": 1919895.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.2361761093139645,
|
|
"epoch": 0.08117195004803074,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.0097,
|
|
"mean_token_accuracy": 0.1526105895638466,
|
|
"num_tokens": 1930839.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.217610692977905,
|
|
"epoch": 0.08165225744476465,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2137,
|
|
"mean_token_accuracy": 0.14339369758963585,
|
|
"num_tokens": 1942605.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.317978858947754,
|
|
"epoch": 0.08213256484149856,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.13737519904971124,
|
|
"num_tokens": 1954863.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.382518625259399,
|
|
"epoch": 0.08261287223823247,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.2852,
|
|
"mean_token_accuracy": 0.1441127136349678,
|
|
"num_tokens": 1966088.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.296528148651123,
|
|
"epoch": 0.08309317963496637,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.1112,
|
|
"mean_token_accuracy": 0.14490053951740264,
|
|
"num_tokens": 1978081.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.272141361236573,
|
|
"epoch": 0.08357348703170028,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.1827,
|
|
"mean_token_accuracy": 0.13639964535832405,
|
|
"num_tokens": 1991212.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.341372632980347,
|
|
"epoch": 0.08405379442843419,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.14349714294075966,
|
|
"num_tokens": 2002074.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.2472961902618405,
|
|
"epoch": 0.0845341018251681,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.0965,
|
|
"mean_token_accuracy": 0.15204162746667862,
|
|
"num_tokens": 2013039.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.304888582229614,
|
|
"epoch": 0.08501440922190202,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.2385,
|
|
"mean_token_accuracy": 0.1450421005487442,
|
|
"num_tokens": 2024744.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.2084990501403805,
|
|
"epoch": 0.08549471661863593,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.15128371939063073,
|
|
"num_tokens": 2035587.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.304928970336914,
|
|
"epoch": 0.08597502401536984,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.1802,
|
|
"mean_token_accuracy": 0.14263538867235184,
|
|
"num_tokens": 2047924.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.22371997833252,
|
|
"epoch": 0.08645533141210375,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.126,
|
|
"mean_token_accuracy": 0.14922973960638047,
|
|
"num_tokens": 2060161.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.24933967590332,
|
|
"epoch": 0.08693563880883766,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.1122,
|
|
"mean_token_accuracy": 0.14982035011053085,
|
|
"num_tokens": 2071674.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.230753231048584,
|
|
"epoch": 0.08741594620557157,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2656,
|
|
"mean_token_accuracy": 0.14044685065746307,
|
|
"num_tokens": 2084025.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.335498666763305,
|
|
"epoch": 0.08789625360230548,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2135,
|
|
"mean_token_accuracy": 0.14406091794371606,
|
|
"num_tokens": 2094501.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.295937156677246,
|
|
"epoch": 0.08837656099903939,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.1786,
|
|
"mean_token_accuracy": 0.15006129145622255,
|
|
"num_tokens": 2106207.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.271474409103393,
|
|
"epoch": 0.0888568683957733,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.0837,
|
|
"mean_token_accuracy": 0.15673873275518418,
|
|
"num_tokens": 2116879.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.162377500534058,
|
|
"epoch": 0.0893371757925072,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.14606007188558578,
|
|
"num_tokens": 2128884.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.210721969604492,
|
|
"epoch": 0.08981748318924111,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.14014682546257973,
|
|
"num_tokens": 2140810.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.217668056488037,
|
|
"epoch": 0.09029779058597502,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.141,
|
|
"mean_token_accuracy": 0.14254814609885216,
|
|
"num_tokens": 2152312.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.211342811584473,
|
|
"epoch": 0.09077809798270893,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.0985,
|
|
"mean_token_accuracy": 0.144034481048584,
|
|
"num_tokens": 2164408.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.172352027893067,
|
|
"epoch": 0.09125840537944284,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.1289,
|
|
"mean_token_accuracy": 0.1452830523252487,
|
|
"num_tokens": 2176050.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.114393424987793,
|
|
"epoch": 0.09173871277617675,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.15028768330812453,
|
|
"num_tokens": 2187354.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.046187686920166,
|
|
"epoch": 0.09221902017291066,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.0429,
|
|
"mean_token_accuracy": 0.14834860116243362,
|
|
"num_tokens": 2198686.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.162608814239502,
|
|
"epoch": 0.09269932756964457,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.15012447834014891,
|
|
"num_tokens": 2209780.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.187800312042237,
|
|
"epoch": 0.09317963496637849,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.1874,
|
|
"mean_token_accuracy": 0.1498972252011299,
|
|
"num_tokens": 2221760.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.147322368621826,
|
|
"epoch": 0.0936599423631124,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.1852,
|
|
"mean_token_accuracy": 0.14224128648638726,
|
|
"num_tokens": 2233767.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.226958322525024,
|
|
"epoch": 0.0941402497598463,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.0957,
|
|
"mean_token_accuracy": 0.14374661892652513,
|
|
"num_tokens": 2244841.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.09796028137207,
|
|
"epoch": 0.09462055715658022,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 5.9658,
|
|
"mean_token_accuracy": 0.1552761510014534,
|
|
"num_tokens": 2255620.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.203439474105835,
|
|
"epoch": 0.09510086455331412,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.1626,
|
|
"mean_token_accuracy": 0.14942158684134482,
|
|
"num_tokens": 2266345.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.17238416671753,
|
|
"epoch": 0.09558117195004803,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.15113430023193358,
|
|
"num_tokens": 2277190.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.099387550354004,
|
|
"epoch": 0.09606147934678194,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 5.9749,
|
|
"mean_token_accuracy": 0.15104159116744995,
|
|
"num_tokens": 2288241.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.172607707977295,
|
|
"epoch": 0.09654178674351585,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999999983283737,
|
|
"loss": 6.1383,
|
|
"mean_token_accuracy": 0.14582284688949584,
|
|
"num_tokens": 2301092.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.113104200363159,
|
|
"epoch": 0.09702209414024976,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999915373924,
|
|
"loss": 6.0215,
|
|
"mean_token_accuracy": 0.1486254870891571,
|
|
"num_tokens": 2313622.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.008445453643799,
|
|
"epoch": 0.09750240153698367,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999795225793,
|
|
"loss": 5.9944,
|
|
"mean_token_accuracy": 0.1521578386425972,
|
|
"num_tokens": 2325699.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.20647497177124,
|
|
"epoch": 0.09798270893371758,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999999622839347,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.15288252979516984,
|
|
"num_tokens": 2337816.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.215051984786987,
|
|
"epoch": 0.09846301633045149,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999999398214593,
|
|
"loss": 6.1867,
|
|
"mean_token_accuracy": 0.14325481206178664,
|
|
"num_tokens": 2348793.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.149576854705811,
|
|
"epoch": 0.0989433237271854,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999999121351532,
|
|
"loss": 6.1092,
|
|
"mean_token_accuracy": 0.1484948292374611,
|
|
"num_tokens": 2360209.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.243153047561646,
|
|
"epoch": 0.0994236311239193,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999998792250173,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.14303301200270652,
|
|
"num_tokens": 2370597.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.169728374481201,
|
|
"epoch": 0.09990393852065321,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999998410910524,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.14206091016530992,
|
|
"num_tokens": 2381466.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.2217827320098875,
|
|
"epoch": 0.10038424591738712,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999997977332592,
|
|
"loss": 6.2478,
|
|
"mean_token_accuracy": 0.1373165175318718,
|
|
"num_tokens": 2394507.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.160476970672607,
|
|
"epoch": 0.10086455331412104,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999997491516389,
|
|
"loss": 6.0899,
|
|
"mean_token_accuracy": 0.1465790644288063,
|
|
"num_tokens": 2406367.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.151379632949829,
|
|
"epoch": 0.10134486071085495,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999996953461925,
|
|
"loss": 6.0559,
|
|
"mean_token_accuracy": 0.1507312148809433,
|
|
"num_tokens": 2416962.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.161687278747559,
|
|
"epoch": 0.10182516810758886,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999996363169212,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.14120108187198638,
|
|
"num_tokens": 2429441.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.095824718475342,
|
|
"epoch": 0.10230547550432277,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999995720638266,
|
|
"loss": 6.0097,
|
|
"mean_token_accuracy": 0.15365689769387245,
|
|
"num_tokens": 2441360.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.10391526222229,
|
|
"epoch": 0.10278578290105668,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049999950258691,
|
|
"loss": 6.0177,
|
|
"mean_token_accuracy": 0.14536169916391373,
|
|
"num_tokens": 2452928.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.02531418800354,
|
|
"epoch": 0.10326609029779059,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999994278861731,
|
|
"loss": 5.9698,
|
|
"mean_token_accuracy": 0.14933416843414307,
|
|
"num_tokens": 2464218.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.104892635345459,
|
|
"epoch": 0.1037463976945245,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999993479616175,
|
|
"loss": 6.0582,
|
|
"mean_token_accuracy": 0.15327436327934266,
|
|
"num_tokens": 2475084.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.1318131446838375,
|
|
"epoch": 0.1042267050912584,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999992628132451,
|
|
"loss": 6.0505,
|
|
"mean_token_accuracy": 0.1454383134841919,
|
|
"num_tokens": 2486845.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.044811820983886,
|
|
"epoch": 0.10470701248799232,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999991724410582,
|
|
"loss": 6.1225,
|
|
"mean_token_accuracy": 0.14644298553466797,
|
|
"num_tokens": 2498049.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.118540906906128,
|
|
"epoch": 0.10518731988472622,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999990768450583,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.14827468991279602,
|
|
"num_tokens": 2509511.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.200696563720703,
|
|
"epoch": 0.10566762728146013,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999989760252482,
|
|
"loss": 6.0115,
|
|
"mean_token_accuracy": 0.15714994966983795,
|
|
"num_tokens": 2521518.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 5.881813478469849,
|
|
"epoch": 0.10614793467819404,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999988699816299,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.15803790241479873,
|
|
"num_tokens": 2533141.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 5.976910018920899,
|
|
"epoch": 0.10662824207492795,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999987587142058,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.15562851428985597,
|
|
"num_tokens": 2542907.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.015887451171875,
|
|
"epoch": 0.10710854947166186,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999986422229789,
|
|
"loss": 6.0172,
|
|
"mean_token_accuracy": 0.1435399830341339,
|
|
"num_tokens": 2554497.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.222254037857056,
|
|
"epoch": 0.10758885686839577,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999985205079514,
|
|
"loss": 6.1419,
|
|
"mean_token_accuracy": 0.15260767042636872,
|
|
"num_tokens": 2567035.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 5.941625452041626,
|
|
"epoch": 0.10806916426512968,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999983935691265,
|
|
"loss": 5.9125,
|
|
"mean_token_accuracy": 0.16007250249385835,
|
|
"num_tokens": 2578003.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.222092819213867,
|
|
"epoch": 0.10854947166186359,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499998261406507,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.14466361775994302,
|
|
"num_tokens": 2590272.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 5.978817510604858,
|
|
"epoch": 0.10902977905859751,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999981240200958,
|
|
"loss": 6.0431,
|
|
"mean_token_accuracy": 0.14697342813014985,
|
|
"num_tokens": 2602874.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.120553874969483,
|
|
"epoch": 0.10951008645533142,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999979814098966,
|
|
"loss": 5.9901,
|
|
"mean_token_accuracy": 0.15932974964380264,
|
|
"num_tokens": 2613835.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.091197299957275,
|
|
"epoch": 0.10999039385206533,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999978335759121,
|
|
"loss": 6.1007,
|
|
"mean_token_accuracy": 0.14361643120646478,
|
|
"num_tokens": 2624986.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.129514551162719,
|
|
"epoch": 0.11047070124879924,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999976805181461,
|
|
"loss": 6.1063,
|
|
"mean_token_accuracy": 0.14257665798068048,
|
|
"num_tokens": 2637654.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.070494890213013,
|
|
"epoch": 0.11095100864553314,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499997522236602,
|
|
"loss": 6.0191,
|
|
"mean_token_accuracy": 0.14936878979206086,
|
|
"num_tokens": 2648947.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.050145816802979,
|
|
"epoch": 0.11143131604226705,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999973587312837,
|
|
"loss": 6.0003,
|
|
"mean_token_accuracy": 0.15421223491430283,
|
|
"num_tokens": 2659573.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 5.9971983432769775,
|
|
"epoch": 0.11191162343900096,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999971900021947,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.1543707251548767,
|
|
"num_tokens": 2671491.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.009974718093872,
|
|
"epoch": 0.11239193083573487,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999970160493391,
|
|
"loss": 5.9746,
|
|
"mean_token_accuracy": 0.1493075892329216,
|
|
"num_tokens": 2682705.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 5.976160669326783,
|
|
"epoch": 0.11287223823246878,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999968368727209,
|
|
"loss": 5.9202,
|
|
"mean_token_accuracy": 0.15478333532810212,
|
|
"num_tokens": 2693539.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.010011291503906,
|
|
"epoch": 0.11335254562920269,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999966524723442,
|
|
"loss": 5.9729,
|
|
"mean_token_accuracy": 0.15669194161891936,
|
|
"num_tokens": 2705403.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.115589570999146,
|
|
"epoch": 0.1138328530259366,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999964628482135,
|
|
"loss": 6.0684,
|
|
"mean_token_accuracy": 0.14865557104349136,
|
|
"num_tokens": 2717320.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.025648975372315,
|
|
"epoch": 0.1143131604226705,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999962680003328,
|
|
"loss": 6.0295,
|
|
"mean_token_accuracy": 0.14510569497942924,
|
|
"num_tokens": 2730056.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.009522199630737,
|
|
"epoch": 0.11479346781940442,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499996067928707,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.15695455223321914,
|
|
"num_tokens": 2741399.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.138769435882568,
|
|
"epoch": 0.11527377521613832,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999958626333406,
|
|
"loss": 6.1321,
|
|
"mean_token_accuracy": 0.14366149455308913,
|
|
"num_tokens": 2752277.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.120853424072266,
|
|
"epoch": 0.11575408261287223,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999956521142383,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.14938354790210723,
|
|
"num_tokens": 2763172.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.033753395080566,
|
|
"epoch": 0.11623439000960614,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999954363714051,
|
|
"loss": 6.0339,
|
|
"mean_token_accuracy": 0.1517849951982498,
|
|
"num_tokens": 2775096.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.113629102706909,
|
|
"epoch": 0.11671469740634005,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999952154048459,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.14458551853895188,
|
|
"num_tokens": 2786007.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.020708131790161,
|
|
"epoch": 0.11719500480307397,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499994989214566,
|
|
"loss": 5.93,
|
|
"mean_token_accuracy": 0.15760562121868132,
|
|
"num_tokens": 2797265.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.061748027801514,
|
|
"epoch": 0.11767531219980788,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999947578005705,
|
|
"loss": 6.079,
|
|
"mean_token_accuracy": 0.15117940902709961,
|
|
"num_tokens": 2809427.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.040156745910645,
|
|
"epoch": 0.11815561959654179,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999945211628648,
|
|
"loss": 6.0195,
|
|
"mean_token_accuracy": 0.15237225145101546,
|
|
"num_tokens": 2822880.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.100583505630493,
|
|
"epoch": 0.1186359269932757,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999942793014544,
|
|
"loss": 6.0854,
|
|
"mean_token_accuracy": 0.14831554368138314,
|
|
"num_tokens": 2834760.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.070679807662964,
|
|
"epoch": 0.11911623439000961,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499994032216345,
|
|
"loss": 6.0407,
|
|
"mean_token_accuracy": 0.1506760910153389,
|
|
"num_tokens": 2846517.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 5.970952844619751,
|
|
"epoch": 0.11959654178674352,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999937799075422,
|
|
"loss": 5.918,
|
|
"mean_token_accuracy": 0.15903548300266265,
|
|
"num_tokens": 2857280.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.055624532699585,
|
|
"epoch": 0.12007684918347743,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499993522375052,
|
|
"loss": 5.9884,
|
|
"mean_token_accuracy": 0.15432048588991165,
|
|
"num_tokens": 2869735.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 5.979946804046631,
|
|
"epoch": 0.12055715658021134,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999932596188802,
|
|
"loss": 5.9782,
|
|
"mean_token_accuracy": 0.1547883614897728,
|
|
"num_tokens": 2881681.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 5.934148931503296,
|
|
"epoch": 0.12103746397694524,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999929916390331,
|
|
"loss": 5.9816,
|
|
"mean_token_accuracy": 0.15643564164638518,
|
|
"num_tokens": 2893828.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 5.921392345428467,
|
|
"epoch": 0.12151777137367915,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999927184355169,
|
|
"loss": 5.9543,
|
|
"mean_token_accuracy": 0.15064309760928155,
|
|
"num_tokens": 2905804.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.214194297790527,
|
|
"epoch": 0.12199807877041306,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999924400083377,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.1528476931154728,
|
|
"num_tokens": 2918709.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.012447738647461,
|
|
"epoch": 0.12247838616714697,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999921563575022,
|
|
"loss": 5.9939,
|
|
"mean_token_accuracy": 0.15287727490067482,
|
|
"num_tokens": 2930589.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.041652250289917,
|
|
"epoch": 0.12295869356388088,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999918674830169,
|
|
"loss": 6.0472,
|
|
"mean_token_accuracy": 0.15353401154279708,
|
|
"num_tokens": 2940635.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 5.93117880821228,
|
|
"epoch": 0.12343900096061479,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999915733848886,
|
|
"loss": 5.9315,
|
|
"mean_token_accuracy": 0.15750601142644882,
|
|
"num_tokens": 2952731.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 5.993732738494873,
|
|
"epoch": 0.1239193083573487,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499991274063124,
|
|
"loss": 5.9264,
|
|
"mean_token_accuracy": 0.15445593893527984,
|
|
"num_tokens": 2964544.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 5.881064367294312,
|
|
"epoch": 0.12439961575408261,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999909695177301,
|
|
"loss": 5.8655,
|
|
"mean_token_accuracy": 0.15871210992336274,
|
|
"num_tokens": 2974996.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 5.977795648574829,
|
|
"epoch": 0.12487992315081652,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499990659748714,
|
|
"loss": 5.8809,
|
|
"mean_token_accuracy": 0.15484783351421355,
|
|
"num_tokens": 2986496.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 5.925467538833618,
|
|
"epoch": 0.12536023054755044,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999903447560828,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.15500155389308928,
|
|
"num_tokens": 2997693.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 5.94029974937439,
|
|
"epoch": 0.12584053794428435,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999900245398439,
|
|
"loss": 5.9248,
|
|
"mean_token_accuracy": 0.15493305549025535,
|
|
"num_tokens": 3009155.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 5.945185422897339,
|
|
"epoch": 0.12632084534101826,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999896991000047,
|
|
"loss": 5.8471,
|
|
"mean_token_accuracy": 0.16124534010887145,
|
|
"num_tokens": 3020944.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 5.93646125793457,
|
|
"epoch": 0.12680115273775217,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999893684365729,
|
|
"loss": 5.9099,
|
|
"mean_token_accuracy": 0.15695340186357498,
|
|
"num_tokens": 3032893.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 5.944838190078736,
|
|
"epoch": 0.12728146013448607,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999890325495559,
|
|
"loss": 5.9864,
|
|
"mean_token_accuracy": 0.15219316333532334,
|
|
"num_tokens": 3044937.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 5.944310712814331,
|
|
"epoch": 0.12776176753121998,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999886914389617,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.1587807759642601,
|
|
"num_tokens": 3056071.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 5.932201910018921,
|
|
"epoch": 0.1282420749279539,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004999883451047981,
|
|
"loss": 6.0432,
|
|
"mean_token_accuracy": 0.15118279233574866,
|
|
"num_tokens": 3067724.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.02701096534729,
|
|
"epoch": 0.1287223823246878,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999879935470733,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.158474200963974,
|
|
"num_tokens": 3080779.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.9539937496185305,
|
|
"epoch": 0.1292026897214217,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999876367657954,
|
|
"loss": 5.9255,
|
|
"mean_token_accuracy": 0.15368285030126572,
|
|
"num_tokens": 3091991.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 5.926160478591919,
|
|
"epoch": 0.12968299711815562,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999872747609725,
|
|
"loss": 5.9166,
|
|
"mean_token_accuracy": 0.15522892773151398,
|
|
"num_tokens": 3103713.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 5.925470161437988,
|
|
"epoch": 0.13016330451488953,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999869075326132,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.1540072813630104,
|
|
"num_tokens": 3115891.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 5.85691990852356,
|
|
"epoch": 0.13064361191162344,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499986535080726,
|
|
"loss": 5.8039,
|
|
"mean_token_accuracy": 0.16470443606376647,
|
|
"num_tokens": 3126223.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.008657360076905,
|
|
"epoch": 0.13112391930835735,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999861574053196,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.151066617667675,
|
|
"num_tokens": 3137537.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.027498769760132,
|
|
"epoch": 0.13160422670509125,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999857745064027,
|
|
"loss": 5.9965,
|
|
"mean_token_accuracy": 0.15381778329610823,
|
|
"num_tokens": 3150126.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 5.952863073348999,
|
|
"epoch": 0.13208453410182516,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499985386383984,
|
|
"loss": 5.9663,
|
|
"mean_token_accuracy": 0.1613561525940895,
|
|
"num_tokens": 3161684.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 5.872996187210083,
|
|
"epoch": 0.13256484149855907,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999849930380729,
|
|
"loss": 5.8446,
|
|
"mean_token_accuracy": 0.1591193348169327,
|
|
"num_tokens": 3172342.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.032765531539917,
|
|
"epoch": 0.13304514889529298,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999845944686781,
|
|
"loss": 5.983,
|
|
"mean_token_accuracy": 0.16015656739473344,
|
|
"num_tokens": 3183681.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 5.799786615371704,
|
|
"epoch": 0.1335254562920269,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999841906758093,
|
|
"loss": 5.7942,
|
|
"mean_token_accuracy": 0.16851347237825393,
|
|
"num_tokens": 3194122.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.937053966522217,
|
|
"epoch": 0.1340057636887608,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999837816594757,
|
|
"loss": 5.8463,
|
|
"mean_token_accuracy": 0.16169387549161912,
|
|
"num_tokens": 3205719.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.814732265472412,
|
|
"epoch": 0.1344860710854947,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999833674196865,
|
|
"loss": 5.8652,
|
|
"mean_token_accuracy": 0.15869019478559493,
|
|
"num_tokens": 3216262.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.002225685119629,
|
|
"epoch": 0.13496637848222862,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999829479564518,
|
|
"loss": 5.9264,
|
|
"mean_token_accuracy": 0.14966704398393632,
|
|
"num_tokens": 3228035.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 5.857042741775513,
|
|
"epoch": 0.13544668587896252,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499982523269781,
|
|
"loss": 5.8011,
|
|
"mean_token_accuracy": 0.16352371722459794,
|
|
"num_tokens": 3239643.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 5.89963698387146,
|
|
"epoch": 0.13592699327569643,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999820933596842,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.159575891494751,
|
|
"num_tokens": 3250293.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 5.967745113372803,
|
|
"epoch": 0.13640730067243034,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499981658226171,
|
|
"loss": 6.0057,
|
|
"mean_token_accuracy": 0.14675760343670846,
|
|
"num_tokens": 3262448.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 5.867046260833741,
|
|
"epoch": 0.13688760806916425,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499981217869252,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.1589981123805046,
|
|
"num_tokens": 3274041.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 5.931325817108155,
|
|
"epoch": 0.1373679154658982,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499980772288937,
|
|
"loss": 5.9072,
|
|
"mean_token_accuracy": 0.15695446729660034,
|
|
"num_tokens": 3285063.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 5.940659904479981,
|
|
"epoch": 0.1378482228626321,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999803214852367,
|
|
"loss": 5.9238,
|
|
"mean_token_accuracy": 0.15722591131925584,
|
|
"num_tokens": 3297031.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 5.956357479095459,
|
|
"epoch": 0.138328530259366,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999798654581613,
|
|
"loss": 5.9031,
|
|
"mean_token_accuracy": 0.1554128795862198,
|
|
"num_tokens": 3308187.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 5.911098432540894,
|
|
"epoch": 0.13880883765609991,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999794042077214,
|
|
"loss": 5.9062,
|
|
"mean_token_accuracy": 0.15348758697509765,
|
|
"num_tokens": 3319439.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.934011363983155,
|
|
"epoch": 0.13928914505283382,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999789377339279,
|
|
"loss": 5.8996,
|
|
"mean_token_accuracy": 0.15216536745429038,
|
|
"num_tokens": 3331715.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.9182721138000485,
|
|
"epoch": 0.13976945244956773,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999784660367915,
|
|
"loss": 5.8609,
|
|
"mean_token_accuracy": 0.16844206303358078,
|
|
"num_tokens": 3342281.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.01653094291687,
|
|
"epoch": 0.14024975984630164,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999779891163231,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.15272812992334367,
|
|
"num_tokens": 3353530.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 5.90668683052063,
|
|
"epoch": 0.14073006724303555,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999775069725339,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.1540558233857155,
|
|
"num_tokens": 3365083.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.972508382797241,
|
|
"epoch": 0.14121037463976946,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499977019605435,
|
|
"loss": 5.9154,
|
|
"mean_token_accuracy": 0.15416828840970992,
|
|
"num_tokens": 3378143.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.9383855819702145,
|
|
"epoch": 0.14169068203650337,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999765270150378,
|
|
"loss": 5.882,
|
|
"mean_token_accuracy": 0.1628871500492096,
|
|
"num_tokens": 3388438.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.881742811203003,
|
|
"epoch": 0.14217098943323728,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999760292013536,
|
|
"loss": 5.8832,
|
|
"mean_token_accuracy": 0.15267159640789033,
|
|
"num_tokens": 3400150.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 5.778295660018921,
|
|
"epoch": 0.14265129682997119,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999755261643941,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.16744979172945024,
|
|
"num_tokens": 3411073.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.8690554141998295,
|
|
"epoch": 0.1431316042267051,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999750179041709,
|
|
"loss": 5.8341,
|
|
"mean_token_accuracy": 0.1667776271700859,
|
|
"num_tokens": 3422196.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.88673849105835,
|
|
"epoch": 0.143611911623439,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999745044206959,
|
|
"loss": 5.8586,
|
|
"mean_token_accuracy": 0.15091366693377495,
|
|
"num_tokens": 3432568.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.872237205505371,
|
|
"epoch": 0.1440922190201729,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999739857139809,
|
|
"loss": 5.8889,
|
|
"mean_token_accuracy": 0.15535980463027954,
|
|
"num_tokens": 3444096.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 5.795199871063232,
|
|
"epoch": 0.14457252641690682,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499973461784038,
|
|
"loss": 5.7672,
|
|
"mean_token_accuracy": 0.1684318333864212,
|
|
"num_tokens": 3455502.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.938459205627441,
|
|
"epoch": 0.14505283381364073,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999729326308792,
|
|
"loss": 5.9119,
|
|
"mean_token_accuracy": 0.15085936039686204,
|
|
"num_tokens": 3467753.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.837009334564209,
|
|
"epoch": 0.14553314121037464,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499972398254517,
|
|
"loss": 5.7789,
|
|
"mean_token_accuracy": 0.1624188169836998,
|
|
"num_tokens": 3479206.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.872801876068115,
|
|
"epoch": 0.14601344860710855,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499971858654964,
|
|
"loss": 5.8213,
|
|
"mean_token_accuracy": 0.1598054826259613,
|
|
"num_tokens": 3490914.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.859324884414673,
|
|
"epoch": 0.14649375600384246,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999713138322321,
|
|
"loss": 5.8751,
|
|
"mean_token_accuracy": 0.15338242948055267,
|
|
"num_tokens": 3502932.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.787054777145386,
|
|
"epoch": 0.14697406340057637,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999707637863346,
|
|
"loss": 5.7941,
|
|
"mean_token_accuracy": 0.16474374681711196,
|
|
"num_tokens": 3515071.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.964262914657593,
|
|
"epoch": 0.14745437079731027,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999702085172838,
|
|
"loss": 5.9125,
|
|
"mean_token_accuracy": 0.15990954861044884,
|
|
"num_tokens": 3526845.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.844745063781739,
|
|
"epoch": 0.14793467819404418,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999696480250929,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.15008662939071654,
|
|
"num_tokens": 3538810.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.913762807846069,
|
|
"epoch": 0.1484149855907781,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999690823097747,
|
|
"loss": 5.8619,
|
|
"mean_token_accuracy": 0.168930259346962,
|
|
"num_tokens": 3549570.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.6661440372467045,
|
|
"epoch": 0.148895292987512,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999685113713426,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.16731411069631577,
|
|
"num_tokens": 3560937.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.910660028457642,
|
|
"epoch": 0.1493756003842459,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999679352098096,
|
|
"loss": 5.8428,
|
|
"mean_token_accuracy": 0.15711865276098252,
|
|
"num_tokens": 3573603.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.797772836685181,
|
|
"epoch": 0.14985590778097982,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999673538251891,
|
|
"loss": 5.8481,
|
|
"mean_token_accuracy": 0.15457407534122466,
|
|
"num_tokens": 3586034.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.83761682510376,
|
|
"epoch": 0.15033621517771373,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999667672174947,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.16625763177871705,
|
|
"num_tokens": 3597305.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.9048542976379395,
|
|
"epoch": 0.15081652257444764,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049996617538674,
|
|
"loss": 5.9291,
|
|
"mean_token_accuracy": 0.1503527745604515,
|
|
"num_tokens": 3608758.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.960012817382813,
|
|
"epoch": 0.15129682997118155,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999655783329386,
|
|
"loss": 5.9154,
|
|
"mean_token_accuracy": 0.15208876878023148,
|
|
"num_tokens": 3621508.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.895190334320068,
|
|
"epoch": 0.15177713736791545,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999649760561046,
|
|
"loss": 5.8637,
|
|
"mean_token_accuracy": 0.1636648565530777,
|
|
"num_tokens": 3634826.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.734798717498779,
|
|
"epoch": 0.15225744476464936,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999643685562519,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.18017627894878388,
|
|
"num_tokens": 3646427.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.792345857620239,
|
|
"epoch": 0.15273775216138327,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999637558333945,
|
|
"loss": 5.833,
|
|
"mean_token_accuracy": 0.16134492605924605,
|
|
"num_tokens": 3658157.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.953826999664306,
|
|
"epoch": 0.15321805955811718,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999631378875467,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.1592890664935112,
|
|
"num_tokens": 3670695.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.788533782958984,
|
|
"epoch": 0.15369836695485112,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999625147187228,
|
|
"loss": 5.8006,
|
|
"mean_token_accuracy": 0.15868576020002365,
|
|
"num_tokens": 3683379.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.749165391921997,
|
|
"epoch": 0.15417867435158503,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999618863269373,
|
|
"loss": 5.6955,
|
|
"mean_token_accuracy": 0.17023993730545045,
|
|
"num_tokens": 3694411.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.775392723083496,
|
|
"epoch": 0.15465898174831894,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999612527122049,
|
|
"loss": 5.7396,
|
|
"mean_token_accuracy": 0.16863008290529252,
|
|
"num_tokens": 3703833.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.853102731704712,
|
|
"epoch": 0.15513928914505284,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999606138745402,
|
|
"loss": 5.8203,
|
|
"mean_token_accuracy": 0.1702694848179817,
|
|
"num_tokens": 3714702.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.865390205383301,
|
|
"epoch": 0.15561959654178675,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999599698139581,
|
|
"loss": 5.9266,
|
|
"mean_token_accuracy": 0.16280574798583985,
|
|
"num_tokens": 3726000.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.882253932952881,
|
|
"epoch": 0.15609990393852066,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999593205304734,
|
|
"loss": 5.8091,
|
|
"mean_token_accuracy": 0.15844953060150146,
|
|
"num_tokens": 3737681.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.8566688060760494,
|
|
"epoch": 0.15658021133525457,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999586660241012,
|
|
"loss": 5.9001,
|
|
"mean_token_accuracy": 0.15781862735748292,
|
|
"num_tokens": 3749477.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 5.952614831924438,
|
|
"epoch": 0.15706051873198848,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999580062948569,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.16022729724645615,
|
|
"num_tokens": 3759946.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.780766010284424,
|
|
"epoch": 0.1575408261287224,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999573413427556,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.16178222000598907,
|
|
"num_tokens": 3770147.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.765101289749145,
|
|
"epoch": 0.1580211335254563,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999566711678128,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.17101316899061203,
|
|
"num_tokens": 3781028.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.815601539611817,
|
|
"epoch": 0.1585014409221902,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999559957700442,
|
|
"loss": 5.817,
|
|
"mean_token_accuracy": 0.1586659610271454,
|
|
"num_tokens": 3792529.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.89880256652832,
|
|
"epoch": 0.15898174831892412,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999553151494653,
|
|
"loss": 5.9256,
|
|
"mean_token_accuracy": 0.16100257486104966,
|
|
"num_tokens": 3804630.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.736216402053833,
|
|
"epoch": 0.15946205571565802,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999546293060919,
|
|
"loss": 5.6871,
|
|
"mean_token_accuracy": 0.1763335272669792,
|
|
"num_tokens": 3815019.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.719022655487061,
|
|
"epoch": 0.15994236311239193,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049995393823994,
|
|
"loss": 5.7902,
|
|
"mean_token_accuracy": 0.15792783051729203,
|
|
"num_tokens": 3825648.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.86321792602539,
|
|
"epoch": 0.16042267050912584,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999532419510255,
|
|
"loss": 5.7728,
|
|
"mean_token_accuracy": 0.16869686394929886,
|
|
"num_tokens": 3836779.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.7344707489013675,
|
|
"epoch": 0.16090297790585975,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499952540439365,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.16161244064569474,
|
|
"num_tokens": 3848350.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.933605194091797,
|
|
"epoch": 0.16138328530259366,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999518337049743,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.16452196836471558,
|
|
"num_tokens": 3859792.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.732853984832763,
|
|
"epoch": 0.16186359269932757,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049995112174787,
|
|
"loss": 5.7598,
|
|
"mean_token_accuracy": 0.16248514652252197,
|
|
"num_tokens": 3871539.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.743935489654541,
|
|
"epoch": 0.16234390009606148,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999504045680687,
|
|
"loss": 5.8142,
|
|
"mean_token_accuracy": 0.1657908469438553,
|
|
"num_tokens": 3885025.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.881377410888672,
|
|
"epoch": 0.1628242074927954,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999496821655869,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.15664341002702714,
|
|
"num_tokens": 3896519.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.774726724624633,
|
|
"epoch": 0.1633045148895293,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999489545404414,
|
|
"loss": 5.6679,
|
|
"mean_token_accuracy": 0.16605159938335418,
|
|
"num_tokens": 3907636.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.7758361339569095,
|
|
"epoch": 0.1637848222862632,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999482216926493,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.16288612633943558,
|
|
"num_tokens": 3917746.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.775166130065918,
|
|
"epoch": 0.1642651296829971,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999474836222273,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.17258119732141494,
|
|
"num_tokens": 3928901.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.706221103668213,
|
|
"epoch": 0.16474543707973102,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999467403291928,
|
|
"loss": 5.8489,
|
|
"mean_token_accuracy": 0.16663677543401717,
|
|
"num_tokens": 3940094.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.823417139053345,
|
|
"epoch": 0.16522574447646493,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999459918135628,
|
|
"loss": 5.7544,
|
|
"mean_token_accuracy": 0.16869125217199327,
|
|
"num_tokens": 3952714.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.729210901260376,
|
|
"epoch": 0.16570605187319884,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499945238075355,
|
|
"loss": 5.7318,
|
|
"mean_token_accuracy": 0.1667981579899788,
|
|
"num_tokens": 3963107.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.833112668991089,
|
|
"epoch": 0.16618635926993275,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999444791145865,
|
|
"loss": 5.6788,
|
|
"mean_token_accuracy": 0.16824763119220734,
|
|
"num_tokens": 3973454.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.756386947631836,
|
|
"epoch": 0.16666666666666666,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999437149312754,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.1626473069190979,
|
|
"num_tokens": 3985352.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.8663242816925045,
|
|
"epoch": 0.16714697406340057,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499942945525439,
|
|
"loss": 5.7607,
|
|
"mean_token_accuracy": 0.16653031706809998,
|
|
"num_tokens": 3997088.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.762393426895142,
|
|
"epoch": 0.16762728146013448,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999421708970954,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.17101218104362487,
|
|
"num_tokens": 4008551.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.807009887695313,
|
|
"epoch": 0.16810758885686838,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999413910462625,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.16373823583126068,
|
|
"num_tokens": 4020886.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.802869558334351,
|
|
"epoch": 0.1685878962536023,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999406059729586,
|
|
"loss": 5.7631,
|
|
"mean_token_accuracy": 0.1604061797261238,
|
|
"num_tokens": 4032811.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.792250299453736,
|
|
"epoch": 0.1690682036503362,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999398156772016,
|
|
"loss": 5.7608,
|
|
"mean_token_accuracy": 0.16829253733158112,
|
|
"num_tokens": 4044102.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.774747133255005,
|
|
"epoch": 0.16954851104707014,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049993902015901,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.16452797800302504,
|
|
"num_tokens": 4056849.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.772494602203369,
|
|
"epoch": 0.17002881844380405,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999382194184023,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.16248029321432114,
|
|
"num_tokens": 4068392.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.777360963821411,
|
|
"epoch": 0.17050912584053796,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999374134553972,
|
|
"loss": 5.646,
|
|
"mean_token_accuracy": 0.17268918007612227,
|
|
"num_tokens": 4078949.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.744507360458374,
|
|
"epoch": 0.17098943323727187,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999366022700131,
|
|
"loss": 5.8057,
|
|
"mean_token_accuracy": 0.1625596508383751,
|
|
"num_tokens": 4091432.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.717019987106323,
|
|
"epoch": 0.17146974063400577,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999357858622691,
|
|
"loss": 5.6587,
|
|
"mean_token_accuracy": 0.171124404668808,
|
|
"num_tokens": 4103001.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.755549430847168,
|
|
"epoch": 0.17195004803073968,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999349642321842,
|
|
"loss": 5.7557,
|
|
"mean_token_accuracy": 0.16994501501321793,
|
|
"num_tokens": 4113570.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.760085391998291,
|
|
"epoch": 0.1724303554274736,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999341373797772,
|
|
"loss": 5.8149,
|
|
"mean_token_accuracy": 0.15936170816421508,
|
|
"num_tokens": 4125658.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.720655012130737,
|
|
"epoch": 0.1729106628242075,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999333053050675,
|
|
"loss": 5.7078,
|
|
"mean_token_accuracy": 0.16616615355014802,
|
|
"num_tokens": 4137424.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.744824743270874,
|
|
"epoch": 0.1733909702209414,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999324680080744,
|
|
"loss": 5.7518,
|
|
"mean_token_accuracy": 0.16471749246120454,
|
|
"num_tokens": 4149772.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.733233070373535,
|
|
"epoch": 0.17387127761767532,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999316254888172,
|
|
"loss": 5.7438,
|
|
"mean_token_accuracy": 0.16947544515132903,
|
|
"num_tokens": 4162246.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.736325740814209,
|
|
"epoch": 0.17435158501440923,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999307777473157,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.174015836417675,
|
|
"num_tokens": 4173449.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.735329103469849,
|
|
"epoch": 0.17483189241114314,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999299247835893,
|
|
"loss": 5.7338,
|
|
"mean_token_accuracy": 0.16482603400945664,
|
|
"num_tokens": 4185560.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.752186679840088,
|
|
"epoch": 0.17531219980787704,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499929066597658,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.15707085877656937,
|
|
"num_tokens": 4197843.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.825539398193359,
|
|
"epoch": 0.17579250720461095,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999282031895418,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.16972217261791228,
|
|
"num_tokens": 4210009.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.74087233543396,
|
|
"epoch": 0.17627281460134486,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999273345592604,
|
|
"loss": 5.9079,
|
|
"mean_token_accuracy": 0.15466363951563836,
|
|
"num_tokens": 4222213.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.786208820343018,
|
|
"epoch": 0.17675312199807877,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999264607068343,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.16184426844120026,
|
|
"num_tokens": 4234159.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.770721483230591,
|
|
"epoch": 0.17723342939481268,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999255816322837,
|
|
"loss": 5.8244,
|
|
"mean_token_accuracy": 0.15809911489486694,
|
|
"num_tokens": 4246358.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.925276517868042,
|
|
"epoch": 0.1777137367915466,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499924697335629,
|
|
"loss": 5.8836,
|
|
"mean_token_accuracy": 0.1607755497097969,
|
|
"num_tokens": 4256698.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.714931774139404,
|
|
"epoch": 0.1781940441882805,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999238078168906,
|
|
"loss": 5.6716,
|
|
"mean_token_accuracy": 0.1786502331495285,
|
|
"num_tokens": 4268007.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.753628253936768,
|
|
"epoch": 0.1786743515850144,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999229130760894,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.16579428613185881,
|
|
"num_tokens": 4278583.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.856677532196045,
|
|
"epoch": 0.17915465898174832,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499922013113246,
|
|
"loss": 5.7914,
|
|
"mean_token_accuracy": 0.16347781121730803,
|
|
"num_tokens": 4290267.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.739168548583985,
|
|
"epoch": 0.17963496637848222,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999211079283814,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.16955134123563767,
|
|
"num_tokens": 4302177.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.694641065597534,
|
|
"epoch": 0.18011527377521613,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999201975215164,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.16879584789276122,
|
|
"num_tokens": 4312420.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.815468692779541,
|
|
"epoch": 0.18059558117195004,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999192818926725,
|
|
"loss": 5.8052,
|
|
"mean_token_accuracy": 0.15983834564685823,
|
|
"num_tokens": 4324050.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.708034896850586,
|
|
"epoch": 0.18107588856868395,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999183610418706,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.16869973838329316,
|
|
"num_tokens": 4335336.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.616009616851807,
|
|
"epoch": 0.18155619596541786,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999174349691322,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.17169511318206787,
|
|
"num_tokens": 4346239.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.76420841217041,
|
|
"epoch": 0.18203650336215177,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999165036744788,
|
|
"loss": 5.7368,
|
|
"mean_token_accuracy": 0.16637959629297255,
|
|
"num_tokens": 4357195.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.639016723632812,
|
|
"epoch": 0.18251681075888568,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999155671579322,
|
|
"loss": 5.6806,
|
|
"mean_token_accuracy": 0.17036481946706772,
|
|
"num_tokens": 4368905.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.747797107696533,
|
|
"epoch": 0.1829971181556196,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499914625419514,
|
|
"loss": 5.7451,
|
|
"mean_token_accuracy": 0.16570276916027069,
|
|
"num_tokens": 4381708.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.6733973026275635,
|
|
"epoch": 0.1834774255523535,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999136784592459,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.18222368210554124,
|
|
"num_tokens": 4393199.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.731898021697998,
|
|
"epoch": 0.1839577329490874,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999127262771502,
|
|
"loss": 5.8355,
|
|
"mean_token_accuracy": 0.15900960564613342,
|
|
"num_tokens": 4403986.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.8278138637542725,
|
|
"epoch": 0.1844380403458213,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999117688732487,
|
|
"loss": 5.6824,
|
|
"mean_token_accuracy": 0.16800769567489623,
|
|
"num_tokens": 4415574.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.6885899066925045,
|
|
"epoch": 0.18491834774255522,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999108062475638,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.1703812912106514,
|
|
"num_tokens": 4427579.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.7626372337341305,
|
|
"epoch": 0.18539865513928913,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499909838400118,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.16777720302343369,
|
|
"num_tokens": 4440045.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.7155296325683596,
|
|
"epoch": 0.18587896253602307,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999088653309334,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.16413577646017075,
|
|
"num_tokens": 4450129.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.716533088684082,
|
|
"epoch": 0.18635926993275698,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999078870400329,
|
|
"loss": 5.6497,
|
|
"mean_token_accuracy": 0.17000699192285537,
|
|
"num_tokens": 4461378.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.688685703277588,
|
|
"epoch": 0.18683957732949089,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999069035274391,
|
|
"loss": 5.7,
|
|
"mean_token_accuracy": 0.17359329164028167,
|
|
"num_tokens": 4472249.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.717999982833862,
|
|
"epoch": 0.1873198847262248,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999059147931747,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.166311414539814,
|
|
"num_tokens": 4484243.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.771619606018066,
|
|
"epoch": 0.1878001921229587,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999049208372629,
|
|
"loss": 5.6593,
|
|
"mean_token_accuracy": 0.16572581231594086,
|
|
"num_tokens": 4495776.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.670734643936157,
|
|
"epoch": 0.1882804995196926,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999039216597267,
|
|
"loss": 5.7501,
|
|
"mean_token_accuracy": 0.16451041847467424,
|
|
"num_tokens": 4508581.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.775052642822265,
|
|
"epoch": 0.18876080691642652,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999029172605892,
|
|
"loss": 5.6696,
|
|
"mean_token_accuracy": 0.16900223344564438,
|
|
"num_tokens": 4519753.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.719663810729981,
|
|
"epoch": 0.18924111431316043,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999019076398738,
|
|
"loss": 5.75,
|
|
"mean_token_accuracy": 0.17347084879875183,
|
|
"num_tokens": 4529957.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.759815454483032,
|
|
"epoch": 0.18972142170989434,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499900892797604,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.16766101717948914,
|
|
"num_tokens": 4541181.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.702226018905639,
|
|
"epoch": 0.19020172910662825,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998998727338031,
|
|
"loss": 5.6776,
|
|
"mean_token_accuracy": 0.173050557076931,
|
|
"num_tokens": 4552235.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.690057182312012,
|
|
"epoch": 0.19068203650336216,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998988474484952,
|
|
"loss": 5.6913,
|
|
"mean_token_accuracy": 0.17268367409706115,
|
|
"num_tokens": 4564045.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.639818572998047,
|
|
"epoch": 0.19116234390009607,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998978169417038,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.17723700404167175,
|
|
"num_tokens": 4575141.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.673330593109131,
|
|
"epoch": 0.19164265129682997,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998967812134529,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.1675497755408287,
|
|
"num_tokens": 4586491.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.74068775177002,
|
|
"epoch": 0.19212295869356388,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998957402637664,
|
|
"loss": 5.697,
|
|
"mean_token_accuracy": 0.16967157423496246,
|
|
"num_tokens": 4598421.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.713365173339843,
|
|
"epoch": 0.1926032660902978,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998946940926687,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.18232411295175552,
|
|
"num_tokens": 4609688.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.647695112228393,
|
|
"epoch": 0.1930835734870317,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499893642700184,
|
|
"loss": 5.7603,
|
|
"mean_token_accuracy": 0.16484474539756774,
|
|
"num_tokens": 4621169.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.75804328918457,
|
|
"epoch": 0.1935638808837656,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998925860863368,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.16970116794109344,
|
|
"num_tokens": 4632512.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.767560434341431,
|
|
"epoch": 0.19404418828049952,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998915242511516,
|
|
"loss": 5.763,
|
|
"mean_token_accuracy": 0.16098930090665817,
|
|
"num_tokens": 4644356.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.748520946502685,
|
|
"epoch": 0.19452449567723343,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998904571946528,
|
|
"loss": 5.7372,
|
|
"mean_token_accuracy": 0.16949849873781203,
|
|
"num_tokens": 4655601.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.7134335994720455,
|
|
"epoch": 0.19500480307396734,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998893849168655,
|
|
"loss": 5.7485,
|
|
"mean_token_accuracy": 0.16730379909276963,
|
|
"num_tokens": 4666813.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.751007986068726,
|
|
"epoch": 0.19548511047070125,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998883074178144,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.16477151960134506,
|
|
"num_tokens": 4679123.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.712923908233643,
|
|
"epoch": 0.19596541786743515,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998872246975247,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.17063149064779282,
|
|
"num_tokens": 4690485.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.578420925140381,
|
|
"epoch": 0.19644572526416906,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998861367560213,
|
|
"loss": 5.6523,
|
|
"mean_token_accuracy": 0.17362430989742278,
|
|
"num_tokens": 4702573.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.7771985054016115,
|
|
"epoch": 0.19692603266090297,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998850435933296,
|
|
"loss": 5.7034,
|
|
"mean_token_accuracy": 0.16219049245119094,
|
|
"num_tokens": 4715653.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.648106813430786,
|
|
"epoch": 0.19740634005763688,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998839452094749,
|
|
"loss": 5.6953,
|
|
"mean_token_accuracy": 0.1705027177929878,
|
|
"num_tokens": 4726051.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.749042558670044,
|
|
"epoch": 0.1978866474543708,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998828416044829,
|
|
"loss": 5.8326,
|
|
"mean_token_accuracy": 0.16298552751541137,
|
|
"num_tokens": 4738176.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.764062976837158,
|
|
"epoch": 0.1983669548511047,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499881732778379,
|
|
"loss": 5.7244,
|
|
"mean_token_accuracy": 0.16867188662290572,
|
|
"num_tokens": 4749547.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.670080184936523,
|
|
"epoch": 0.1988472622478386,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499880618731189,
|
|
"loss": 5.6588,
|
|
"mean_token_accuracy": 0.1658295750617981,
|
|
"num_tokens": 4761967.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.638352346420288,
|
|
"epoch": 0.19932756964457252,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998794994629388,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.17256570607423782,
|
|
"num_tokens": 4772847.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.743561458587647,
|
|
"epoch": 0.19980787704130643,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998783749736545,
|
|
"loss": 5.7147,
|
|
"mean_token_accuracy": 0.16527553051710128,
|
|
"num_tokens": 4785049.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.694084978103637,
|
|
"epoch": 0.20028818443804033,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998772452633619,
|
|
"loss": 5.7413,
|
|
"mean_token_accuracy": 0.16240385919809341,
|
|
"num_tokens": 4797484.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.689326190948487,
|
|
"epoch": 0.20076849183477424,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998761103320876,
|
|
"loss": 5.6549,
|
|
"mean_token_accuracy": 0.1645843580365181,
|
|
"num_tokens": 4809422.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.750069236755371,
|
|
"epoch": 0.20124879923150815,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998749701798577,
|
|
"loss": 5.8479,
|
|
"mean_token_accuracy": 0.16339512243866922,
|
|
"num_tokens": 4822340.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.713565874099731,
|
|
"epoch": 0.2017291066282421,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998738248066986,
|
|
"loss": 5.6261,
|
|
"mean_token_accuracy": 0.17067924439907073,
|
|
"num_tokens": 4833382.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.642834043502807,
|
|
"epoch": 0.202209414024976,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998726742126372,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.179599392414093,
|
|
"num_tokens": 4843916.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.686129951477051,
|
|
"epoch": 0.2026897214217099,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998715183976999,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.17115692496299745,
|
|
"num_tokens": 4855420.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.717159843444824,
|
|
"epoch": 0.20317002881844382,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998703573619137,
|
|
"loss": 5.7091,
|
|
"mean_token_accuracy": 0.16790662705898285,
|
|
"num_tokens": 4866540.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.737949991226197,
|
|
"epoch": 0.20365033621517772,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998691911053056,
|
|
"loss": 5.6503,
|
|
"mean_token_accuracy": 0.1651172399520874,
|
|
"num_tokens": 4878860.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.814427518844605,
|
|
"epoch": 0.20413064361191163,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998680196279026,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.1618766739964485,
|
|
"num_tokens": 4889692.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.733552122116089,
|
|
"epoch": 0.20461095100864554,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998668429297319,
|
|
"loss": 5.7168,
|
|
"mean_token_accuracy": 0.1730179101228714,
|
|
"num_tokens": 4901337.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.628330326080322,
|
|
"epoch": 0.20509125840537945,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998656610108208,
|
|
"loss": 5.6162,
|
|
"mean_token_accuracy": 0.1758786827325821,
|
|
"num_tokens": 4912340.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.650088310241699,
|
|
"epoch": 0.20557156580211336,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998644738711969,
|
|
"loss": 5.6037,
|
|
"mean_token_accuracy": 0.18037814944982528,
|
|
"num_tokens": 4923429.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.692839908599853,
|
|
"epoch": 0.20605187319884727,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998632815108874,
|
|
"loss": 5.672,
|
|
"mean_token_accuracy": 0.1628017544746399,
|
|
"num_tokens": 4934826.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.705739879608155,
|
|
"epoch": 0.20653218059558118,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998620839299203,
|
|
"loss": 5.7485,
|
|
"mean_token_accuracy": 0.1703076645731926,
|
|
"num_tokens": 4945189.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.772362995147705,
|
|
"epoch": 0.2070124879923151,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998608811283233,
|
|
"loss": 5.6281,
|
|
"mean_token_accuracy": 0.17795057147741317,
|
|
"num_tokens": 4956060.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.667694616317749,
|
|
"epoch": 0.207492795389049,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998596731061244,
|
|
"loss": 5.6475,
|
|
"mean_token_accuracy": 0.17147868126630783,
|
|
"num_tokens": 4967710.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.711640691757202,
|
|
"epoch": 0.2079731027857829,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998584598633516,
|
|
"loss": 5.675,
|
|
"mean_token_accuracy": 0.1658002734184265,
|
|
"num_tokens": 4978716.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.694676256179809,
|
|
"epoch": 0.2084534101825168,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998572414000329,
|
|
"loss": 5.7477,
|
|
"mean_token_accuracy": 0.16772115379571914,
|
|
"num_tokens": 4990742.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.771293210983276,
|
|
"epoch": 0.20893371757925072,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998560177161969,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.17304315716028212,
|
|
"num_tokens": 5001217.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.671742153167725,
|
|
"epoch": 0.20941402497598463,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998547888118718,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.16428728848695756,
|
|
"num_tokens": 5012750.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.71360969543457,
|
|
"epoch": 0.20989433237271854,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998535546870862,
|
|
"loss": 5.6916,
|
|
"mean_token_accuracy": 0.17811540961265565,
|
|
"num_tokens": 5023818.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.748793077468872,
|
|
"epoch": 0.21037463976945245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998523153418687,
|
|
"loss": 5.7013,
|
|
"mean_token_accuracy": 0.16991553604602813,
|
|
"num_tokens": 5035060.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.751564168930054,
|
|
"epoch": 0.21085494716618636,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998510707762481,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.15955581441521643,
|
|
"num_tokens": 5046780.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.7015965461730955,
|
|
"epoch": 0.21133525456292027,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998498209902533,
|
|
"loss": 5.7148,
|
|
"mean_token_accuracy": 0.16586878895759583,
|
|
"num_tokens": 5059152.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.687603616714478,
|
|
"epoch": 0.21181556195965417,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998485659839134,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.1731492057442665,
|
|
"num_tokens": 5069971.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.678986549377441,
|
|
"epoch": 0.21229586935638808,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998473057572575,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.17143055498600007,
|
|
"num_tokens": 5080640.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.662276315689087,
|
|
"epoch": 0.212776176753122,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998460403103146,
|
|
"loss": 5.6432,
|
|
"mean_token_accuracy": 0.1736779436469078,
|
|
"num_tokens": 5091240.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.623275947570801,
|
|
"epoch": 0.2132564841498559,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998447696431146,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.16834193468093872,
|
|
"num_tokens": 5102920.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.729692602157593,
|
|
"epoch": 0.2137367915465898,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998434937556865,
|
|
"loss": 5.6973,
|
|
"mean_token_accuracy": 0.1643601253628731,
|
|
"num_tokens": 5114240.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.849734830856323,
|
|
"epoch": 0.21421709894332372,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998422126480602,
|
|
"loss": 5.916,
|
|
"mean_token_accuracy": 0.1578417658805847,
|
|
"num_tokens": 5126653.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.786351490020752,
|
|
"epoch": 0.21469740634005763,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998409263202653,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.1627764031291008,
|
|
"num_tokens": 5138778.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.689749240875244,
|
|
"epoch": 0.21517771373679154,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998396347723318,
|
|
"loss": 5.613,
|
|
"mean_token_accuracy": 0.17623931765556336,
|
|
"num_tokens": 5148670.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.536856698989868,
|
|
"epoch": 0.21565802113352545,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998383380042895,
|
|
"loss": 5.6654,
|
|
"mean_token_accuracy": 0.16913559436798095,
|
|
"num_tokens": 5159617.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.721935510635376,
|
|
"epoch": 0.21613832853025935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998370360161688,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.1725509762763977,
|
|
"num_tokens": 5171225.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.699740695953369,
|
|
"epoch": 0.21661863592699326,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998357288079996,
|
|
"loss": 5.7162,
|
|
"mean_token_accuracy": 0.16764118522405624,
|
|
"num_tokens": 5184586.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.628728437423706,
|
|
"epoch": 0.21709894332372717,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998344163798125,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.16584176570177078,
|
|
"num_tokens": 5196089.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.7385218143463135,
|
|
"epoch": 0.21757925072046108,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998330987316379,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.16616473644971846,
|
|
"num_tokens": 5207581.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.65544490814209,
|
|
"epoch": 0.21805955811719502,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998317758635062,
|
|
"loss": 5.668,
|
|
"mean_token_accuracy": 0.1719151794910431,
|
|
"num_tokens": 5219108.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.698003768920898,
|
|
"epoch": 0.21853986551392893,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998304477754484,
|
|
"loss": 5.6096,
|
|
"mean_token_accuracy": 0.17026123851537706,
|
|
"num_tokens": 5231137.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.793634605407715,
|
|
"epoch": 0.21902017291066284,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998291144674952,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.17130818516016005,
|
|
"num_tokens": 5243528.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.544963455200195,
|
|
"epoch": 0.21950048030739674,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998277759396776,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.17359607815742492,
|
|
"num_tokens": 5254869.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.613512754440308,
|
|
"epoch": 0.21998078770413065,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998264321920265,
|
|
"loss": 5.6196,
|
|
"mean_token_accuracy": 0.17148103266954423,
|
|
"num_tokens": 5265370.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.6785135746002195,
|
|
"epoch": 0.22046109510086456,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998250832245734,
|
|
"loss": 5.5957,
|
|
"mean_token_accuracy": 0.17259823232889177,
|
|
"num_tokens": 5277812.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.57698540687561,
|
|
"epoch": 0.22094140249759847,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998237290373494,
|
|
"loss": 5.5758,
|
|
"mean_token_accuracy": 0.1758878469467163,
|
|
"num_tokens": 5289107.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.679394817352295,
|
|
"epoch": 0.22142170989433238,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499822369630386,
|
|
"loss": 5.6315,
|
|
"mean_token_accuracy": 0.16491704434156418,
|
|
"num_tokens": 5301489.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.549877023696899,
|
|
"epoch": 0.2219020172910663,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998210050037148,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.17484947741031648,
|
|
"num_tokens": 5313273.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.7064066410064695,
|
|
"epoch": 0.2223823246878002,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998196351573674,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.17079515755176544,
|
|
"num_tokens": 5324227.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.61033296585083,
|
|
"epoch": 0.2228626320845341,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998182600913757,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.17890511006116866,
|
|
"num_tokens": 5335138.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.5808428764343265,
|
|
"epoch": 0.22334293948126802,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998168798057715,
|
|
"loss": 5.6627,
|
|
"mean_token_accuracy": 0.1708785980939865,
|
|
"num_tokens": 5345652.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.7352948665618895,
|
|
"epoch": 0.22382324687800192,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499815494300587,
|
|
"loss": 5.749,
|
|
"mean_token_accuracy": 0.16825126260519027,
|
|
"num_tokens": 5357999.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.732254123687744,
|
|
"epoch": 0.22430355427473583,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998141035758542,
|
|
"loss": 5.645,
|
|
"mean_token_accuracy": 0.1687160015106201,
|
|
"num_tokens": 5369032.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.6413782119750975,
|
|
"epoch": 0.22478386167146974,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998127076316054,
|
|
"loss": 5.5879,
|
|
"mean_token_accuracy": 0.17352873533964158,
|
|
"num_tokens": 5380692.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.730327844619751,
|
|
"epoch": 0.22526416906820365,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998113064678734,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.16110651195049286,
|
|
"num_tokens": 5392320.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.694684886932373,
|
|
"epoch": 0.22574447646493756,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998099000846901,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.170077383518219,
|
|
"num_tokens": 5404374.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.719666624069214,
|
|
"epoch": 0.22622478386167147,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998084884820887,
|
|
"loss": 5.6904,
|
|
"mean_token_accuracy": 0.17066318392753602,
|
|
"num_tokens": 5415471.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.532975578308106,
|
|
"epoch": 0.22670509125840538,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998070716601016,
|
|
"loss": 5.5269,
|
|
"mean_token_accuracy": 0.1728779211640358,
|
|
"num_tokens": 5425971.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.670989894866944,
|
|
"epoch": 0.2271853986551393,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998056496187618,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.17769685834646226,
|
|
"num_tokens": 5437638.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.6903704643249515,
|
|
"epoch": 0.2276657060518732,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998042223581025,
|
|
"loss": 5.6898,
|
|
"mean_token_accuracy": 0.1719474747776985,
|
|
"num_tokens": 5449463.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.664535570144653,
|
|
"epoch": 0.2281460134486071,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998027898781565,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.1684306815266609,
|
|
"num_tokens": 5460972.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.866941213607788,
|
|
"epoch": 0.228626320845341,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998013521789574,
|
|
"loss": 5.7553,
|
|
"mean_token_accuracy": 0.15989520251750947,
|
|
"num_tokens": 5471575.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.589054918289184,
|
|
"epoch": 0.22910662824207492,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997999092605384,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.17029613703489305,
|
|
"num_tokens": 5483041.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.63406343460083,
|
|
"epoch": 0.22958693563880883,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499798461122933,
|
|
"loss": 5.6321,
|
|
"mean_token_accuracy": 0.1724291518330574,
|
|
"num_tokens": 5494040.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.6091015338897705,
|
|
"epoch": 0.23006724303554274,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997970077661748,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.1848677799105644,
|
|
"num_tokens": 5504217.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.669242858886719,
|
|
"epoch": 0.23054755043227665,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997955491902977,
|
|
"loss": 5.6951,
|
|
"mean_token_accuracy": 0.16823576092720033,
|
|
"num_tokens": 5517180.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.640048980712891,
|
|
"epoch": 0.23102785782901056,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997940853953354,
|
|
"loss": 5.5985,
|
|
"mean_token_accuracy": 0.16914743930101395,
|
|
"num_tokens": 5529626.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.701624059677124,
|
|
"epoch": 0.23150816522574447,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499792616381322,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.17812359482049941,
|
|
"num_tokens": 5540844.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.684215545654297,
|
|
"epoch": 0.23198847262247838,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997911421482914,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.17999959141016006,
|
|
"num_tokens": 5551732.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.6654558181762695,
|
|
"epoch": 0.23246878001921228,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499789662696278,
|
|
"loss": 5.7098,
|
|
"mean_token_accuracy": 0.17055163383483887,
|
|
"num_tokens": 5562692.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.7184652328491214,
|
|
"epoch": 0.2329490874159462,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997881780253162,
|
|
"loss": 5.6944,
|
|
"mean_token_accuracy": 0.1724271610379219,
|
|
"num_tokens": 5574884.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.526378154754639,
|
|
"epoch": 0.2334293948126801,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997866881354403,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.17680294513702394,
|
|
"num_tokens": 5585335.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.715866374969482,
|
|
"epoch": 0.23390970220941404,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499785193026685,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.16400452703237534,
|
|
"num_tokens": 5597621.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.559733724594116,
|
|
"epoch": 0.23439000960614795,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997836926990851,
|
|
"loss": 5.5486,
|
|
"mean_token_accuracy": 0.17132115513086318,
|
|
"num_tokens": 5609795.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.626978397369385,
|
|
"epoch": 0.23487031700288186,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997821871526752,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.16910365521907805,
|
|
"num_tokens": 5621473.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.741739797592163,
|
|
"epoch": 0.23535062439961577,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997806763874905,
|
|
"loss": 5.7391,
|
|
"mean_token_accuracy": 0.16913674920797347,
|
|
"num_tokens": 5635064.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.771869468688965,
|
|
"epoch": 0.23583093179634967,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997791604035659,
|
|
"loss": 5.7399,
|
|
"mean_token_accuracy": 0.16541620939970017,
|
|
"num_tokens": 5647382.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.632869815826416,
|
|
"epoch": 0.23631123919308358,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997776392009366,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.17495698034763335,
|
|
"num_tokens": 5658417.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.617389917373657,
|
|
"epoch": 0.2367915465898175,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997761127796381,
|
|
"loss": 5.5897,
|
|
"mean_token_accuracy": 0.174434295296669,
|
|
"num_tokens": 5672190.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.6352379322052,
|
|
"epoch": 0.2372718539865514,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997745811397056,
|
|
"loss": 5.6077,
|
|
"mean_token_accuracy": 0.1803595706820488,
|
|
"num_tokens": 5684259.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.635552072525025,
|
|
"epoch": 0.2377521613832853,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997730442811748,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.1712580442428589,
|
|
"num_tokens": 5696505.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.591545057296753,
|
|
"epoch": 0.23823246878001922,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997715022040814,
|
|
"loss": 5.546,
|
|
"mean_token_accuracy": 0.17534102201461793,
|
|
"num_tokens": 5707638.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.5858382225036625,
|
|
"epoch": 0.23871277617675313,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499769954908461,
|
|
"loss": 5.532,
|
|
"mean_token_accuracy": 0.181480710208416,
|
|
"num_tokens": 5719098.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.7313658714294435,
|
|
"epoch": 0.23919308357348704,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997684023943498,
|
|
"loss": 5.7639,
|
|
"mean_token_accuracy": 0.15622588247060776,
|
|
"num_tokens": 5731345.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.546728086471558,
|
|
"epoch": 0.23967339097022095,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997668446617837,
|
|
"loss": 5.5085,
|
|
"mean_token_accuracy": 0.17273759096860886,
|
|
"num_tokens": 5742604.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.542533683776855,
|
|
"epoch": 0.24015369836695485,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997652817107989,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.17851854413747786,
|
|
"num_tokens": 5754620.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.704870271682739,
|
|
"epoch": 0.24063400576368876,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997637135414315,
|
|
"loss": 5.6163,
|
|
"mean_token_accuracy": 0.17889242321252824,
|
|
"num_tokens": 5764764.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.53765640258789,
|
|
"epoch": 0.24111431316042267,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997621401537183,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.18003057241439818,
|
|
"num_tokens": 5776341.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.672939825057983,
|
|
"epoch": 0.24159462055715658,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997605615476955,
|
|
"loss": 5.743,
|
|
"mean_token_accuracy": 0.16112136393785476,
|
|
"num_tokens": 5788604.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.670176792144775,
|
|
"epoch": 0.2420749279538905,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997589777234,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.17324668765068055,
|
|
"num_tokens": 5800194.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.625196886062622,
|
|
"epoch": 0.2425552353506244,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997573886808684,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.17728133350610734,
|
|
"num_tokens": 5812978.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.587188100814819,
|
|
"epoch": 0.2430355427473583,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997557944201375,
|
|
"loss": 5.5326,
|
|
"mean_token_accuracy": 0.18073128014802933,
|
|
"num_tokens": 5824591.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.583196496963501,
|
|
"epoch": 0.24351585014409222,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997541949412445,
|
|
"loss": 5.6288,
|
|
"mean_token_accuracy": 0.1718851387500763,
|
|
"num_tokens": 5835970.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.70057430267334,
|
|
"epoch": 0.24399615754082613,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997525902442266,
|
|
"loss": 5.6803,
|
|
"mean_token_accuracy": 0.1663990870118141,
|
|
"num_tokens": 5848687.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.654277038574219,
|
|
"epoch": 0.24447646493756003,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997509803291207,
|
|
"loss": 5.6426,
|
|
"mean_token_accuracy": 0.1717447817325592,
|
|
"num_tokens": 5860820.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.606211185455322,
|
|
"epoch": 0.24495677233429394,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997493651959647,
|
|
"loss": 5.579,
|
|
"mean_token_accuracy": 0.1743954598903656,
|
|
"num_tokens": 5872172.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.641741323471069,
|
|
"epoch": 0.24543707973102785,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997477448447955,
|
|
"loss": 5.6171,
|
|
"mean_token_accuracy": 0.17213639616966248,
|
|
"num_tokens": 5883574.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.679425430297852,
|
|
"epoch": 0.24591738712776176,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997461192756512,
|
|
"loss": 5.7187,
|
|
"mean_token_accuracy": 0.1697825610637665,
|
|
"num_tokens": 5895223.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.592727375030518,
|
|
"epoch": 0.24639769452449567,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997444884885694,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.17672908753156663,
|
|
"num_tokens": 5907448.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.6109534740448,
|
|
"epoch": 0.24687800192122958,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997428524835879,
|
|
"loss": 5.6404,
|
|
"mean_token_accuracy": 0.17392444908618926,
|
|
"num_tokens": 5918906.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.628335285186767,
|
|
"epoch": 0.2473583093179635,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997412112607446,
|
|
"loss": 5.515,
|
|
"mean_token_accuracy": 0.18007228374481202,
|
|
"num_tokens": 5930619.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.718863439559937,
|
|
"epoch": 0.2478386167146974,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997395648200778,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.16648458540439606,
|
|
"num_tokens": 5941554.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.687685155868531,
|
|
"epoch": 0.2483189241114313,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997379131616257,
|
|
"loss": 5.6831,
|
|
"mean_token_accuracy": 0.17195172160863875,
|
|
"num_tokens": 5953309.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.610647296905517,
|
|
"epoch": 0.24879923150816521,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004997362562854266,
|
|
"loss": 5.6294,
|
|
"mean_token_accuracy": 0.17338041216135025,
|
|
"num_tokens": 5965286.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.6528027057647705,
|
|
"epoch": 0.24927953890489912,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997345941915187,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.17616538554430008,
|
|
"num_tokens": 5976558.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.646711730957032,
|
|
"epoch": 0.24975984630163303,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997329268799412,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.16481584012508393,
|
|
"num_tokens": 5988793.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.680540704727173,
|
|
"epoch": 0.25024015369836694,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997312543507322,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.16258761882781983,
|
|
"num_tokens": 5999825.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.660827779769898,
|
|
"epoch": 0.2507204610951009,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997295766039309,
|
|
"loss": 5.6168,
|
|
"mean_token_accuracy": 0.1700749561190605,
|
|
"num_tokens": 6010408.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.694224882125854,
|
|
"epoch": 0.25120076849183476,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997278936395761,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.1695483595132828,
|
|
"num_tokens": 6021161.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.579520511627197,
|
|
"epoch": 0.2516810758885687,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997262054577071,
|
|
"loss": 5.4949,
|
|
"mean_token_accuracy": 0.1799078106880188,
|
|
"num_tokens": 6032646.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.61772780418396,
|
|
"epoch": 0.2521613832853026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997245120583627,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.17070280015468597,
|
|
"num_tokens": 6045019.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.547396659851074,
|
|
"epoch": 0.2526416906820365,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997228134415825,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.17881007641553878,
|
|
"num_tokens": 6055644.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.676703310012817,
|
|
"epoch": 0.2531219980787704,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997211096074059,
|
|
"loss": 5.5686,
|
|
"mean_token_accuracy": 0.1793759658932686,
|
|
"num_tokens": 6066488.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.61687445640564,
|
|
"epoch": 0.25360230547550433,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997194005558722,
|
|
"loss": 5.6107,
|
|
"mean_token_accuracy": 0.17230986505746843,
|
|
"num_tokens": 6078300.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.612687253952027,
|
|
"epoch": 0.2540826128722382,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997176862870216,
|
|
"loss": 5.5767,
|
|
"mean_token_accuracy": 0.17045443654060363,
|
|
"num_tokens": 6089180.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.659189224243164,
|
|
"epoch": 0.25456292026897215,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997159668008933,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.18232642710208893,
|
|
"num_tokens": 6099093.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.612885761260986,
|
|
"epoch": 0.25504322766570603,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997142420975277,
|
|
"loss": 5.6459,
|
|
"mean_token_accuracy": 0.1759412705898285,
|
|
"num_tokens": 6109161.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.7561407566070555,
|
|
"epoch": 0.25552353506243997,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997125121769647,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.16455692201852798,
|
|
"num_tokens": 6120031.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.593028593063354,
|
|
"epoch": 0.25600384245917385,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997107770392444,
|
|
"loss": 5.6017,
|
|
"mean_token_accuracy": 0.17366934418678284,
|
|
"num_tokens": 6132398.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.646261167526245,
|
|
"epoch": 0.2564841498559078,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499709036684407,
|
|
"loss": 5.5896,
|
|
"mean_token_accuracy": 0.16633834168314934,
|
|
"num_tokens": 6143099.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.615106105804443,
|
|
"epoch": 0.25696445725264166,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997072911124932,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.17667461335659027,
|
|
"num_tokens": 6154815.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.633945465087891,
|
|
"epoch": 0.2574447646493756,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997055403235432,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.17703237533569335,
|
|
"num_tokens": 6165696.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.583321189880371,
|
|
"epoch": 0.2579250720461095,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997037843175978,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.1697259709239006,
|
|
"num_tokens": 6177042.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.723847389221191,
|
|
"epoch": 0.2584053794428434,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997020230946978,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.1708068698644638,
|
|
"num_tokens": 6188691.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.480944967269897,
|
|
"epoch": 0.25888568683957736,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997002566548841,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.18257904648780823,
|
|
"num_tokens": 6199931.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.554953145980835,
|
|
"epoch": 0.25936599423631124,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996984849981976,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.18077756613492965,
|
|
"num_tokens": 6211493.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.7185674667358395,
|
|
"epoch": 0.2598463016330452,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996967081246794,
|
|
"loss": 5.5288,
|
|
"mean_token_accuracy": 0.17527295053005218,
|
|
"num_tokens": 6221505.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.5221052169799805,
|
|
"epoch": 0.26032660902977905,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996949260343711,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.1818551629781723,
|
|
"num_tokens": 6233058.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.628518390655517,
|
|
"epoch": 0.260806916426513,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996931387273137,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.17151581346988679,
|
|
"num_tokens": 6244713.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.612377023696899,
|
|
"epoch": 0.2612872238232469,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996913462035487,
|
|
"loss": 5.6046,
|
|
"mean_token_accuracy": 0.16954844444990158,
|
|
"num_tokens": 6256624.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.582393217086792,
|
|
"epoch": 0.2617675312199808,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499689548463118,
|
|
"loss": 5.6041,
|
|
"mean_token_accuracy": 0.16892476230859757,
|
|
"num_tokens": 6271134.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.718617343902588,
|
|
"epoch": 0.2622478386167147,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996877455060631,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.17103526890277862,
|
|
"num_tokens": 6282082.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.666055965423584,
|
|
"epoch": 0.2627281460134486,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996859373324259,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.17113145142793657,
|
|
"num_tokens": 6293869.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.63692798614502,
|
|
"epoch": 0.2632084534101825,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996841239422485,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.16283004432916642,
|
|
"num_tokens": 6304858.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.64309549331665,
|
|
"epoch": 0.26368876080691644,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996823053355729,
|
|
"loss": 5.5963,
|
|
"mean_token_accuracy": 0.17556946128606796,
|
|
"num_tokens": 6316738.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.568399381637573,
|
|
"epoch": 0.2641690682036503,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996804815124413,
|
|
"loss": 5.556,
|
|
"mean_token_accuracy": 0.17209173142910003,
|
|
"num_tokens": 6327691.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.66407265663147,
|
|
"epoch": 0.26464937560038426,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996786524728962,
|
|
"loss": 5.5718,
|
|
"mean_token_accuracy": 0.16894693523645402,
|
|
"num_tokens": 6337964.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.56714882850647,
|
|
"epoch": 0.26512968299711814,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996768182169797,
|
|
"loss": 5.6163,
|
|
"mean_token_accuracy": 0.17449129968881608,
|
|
"num_tokens": 6349764.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.662902736663819,
|
|
"epoch": 0.2656099903938521,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996749787447349,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.17478797137737273,
|
|
"num_tokens": 6360538.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.595956087112427,
|
|
"epoch": 0.26609029779058596,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499673134056204,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.17373100519180298,
|
|
"num_tokens": 6372489.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.443460750579834,
|
|
"epoch": 0.2665706051873199,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996712841514303,
|
|
"loss": 5.4845,
|
|
"mean_token_accuracy": 0.1831083118915558,
|
|
"num_tokens": 6383080.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.692691278457642,
|
|
"epoch": 0.2670509125840538,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996694290304563,
|
|
"loss": 5.6041,
|
|
"mean_token_accuracy": 0.17385849058628083,
|
|
"num_tokens": 6394033.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.572810697555542,
|
|
"epoch": 0.2675312199807877,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996675686933255,
|
|
"loss": 5.611,
|
|
"mean_token_accuracy": 0.17484720796346664,
|
|
"num_tokens": 6404990.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.576703500747681,
|
|
"epoch": 0.2680115273775216,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996657031400807,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.181576107442379,
|
|
"num_tokens": 6416337.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.643291425704956,
|
|
"epoch": 0.26849183477425553,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996638323707655,
|
|
"loss": 5.6961,
|
|
"mean_token_accuracy": 0.17010248452425003,
|
|
"num_tokens": 6427892.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.650494956970215,
|
|
"epoch": 0.2689721421709894,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996619563854232,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.1760585606098175,
|
|
"num_tokens": 6440300.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.595854425430298,
|
|
"epoch": 0.26945244956772335,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996600751840974,
|
|
"loss": 5.4853,
|
|
"mean_token_accuracy": 0.17765479534864426,
|
|
"num_tokens": 6451499.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.594804906845093,
|
|
"epoch": 0.26993275696445723,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996581887668317,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.17601191103458405,
|
|
"num_tokens": 6462882.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.572175931930542,
|
|
"epoch": 0.27041306436119117,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00049965629713367,
|
|
"loss": 5.5569,
|
|
"mean_token_accuracy": 0.17694126069545746,
|
|
"num_tokens": 6475042.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.570115184783935,
|
|
"epoch": 0.27089337175792505,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996544002846561,
|
|
"loss": 5.5648,
|
|
"mean_token_accuracy": 0.17592734843492508,
|
|
"num_tokens": 6486245.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.579746532440185,
|
|
"epoch": 0.271373679154659,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996524982198343,
|
|
"loss": 5.4745,
|
|
"mean_token_accuracy": 0.178873273730278,
|
|
"num_tokens": 6497705.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.532494258880615,
|
|
"epoch": 0.27185398655139287,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996505909392485,
|
|
"loss": 5.5101,
|
|
"mean_token_accuracy": 0.18047289401292801,
|
|
"num_tokens": 6508193.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.649497365951538,
|
|
"epoch": 0.2723342939481268,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996486784429429,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.17633747458457946,
|
|
"num_tokens": 6519228.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.627618598937988,
|
|
"epoch": 0.2728146013448607,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004996467607309622,
|
|
"loss": 5.587,
|
|
"mean_token_accuracy": 0.1716805502772331,
|
|
"num_tokens": 6530743.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.575333595275879,
|
|
"epoch": 0.2732949087415946,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996448378033507,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.17245458513498307,
|
|
"num_tokens": 6542588.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.695534610748291,
|
|
"epoch": 0.2737752161383285,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996429096601532,
|
|
"loss": 5.674,
|
|
"mean_token_accuracy": 0.16420495510101318,
|
|
"num_tokens": 6554002.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.686659669876098,
|
|
"epoch": 0.27425552353506244,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996409763014144,
|
|
"loss": 5.6925,
|
|
"mean_token_accuracy": 0.1730800151824951,
|
|
"num_tokens": 6563358.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.598821449279785,
|
|
"epoch": 0.2747358309317964,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996390377271791,
|
|
"loss": 5.5962,
|
|
"mean_token_accuracy": 0.16940404772758483,
|
|
"num_tokens": 6574986.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.531180191040039,
|
|
"epoch": 0.27521613832853026,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996370939374924,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.17848169654607773,
|
|
"num_tokens": 6587407.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.562257719039917,
|
|
"epoch": 0.2756964457252642,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996351449323994,
|
|
"loss": 5.5087,
|
|
"mean_token_accuracy": 0.18236653059720992,
|
|
"num_tokens": 6598483.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.533087635040284,
|
|
"epoch": 0.2761767531219981,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996331907119455,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.1755070611834526,
|
|
"num_tokens": 6610749.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.659117031097412,
|
|
"epoch": 0.276657060518732,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996312312761758,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.17036049515008928,
|
|
"num_tokens": 6621762.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.612740898132325,
|
|
"epoch": 0.2771373679154659,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000499629266625136,
|
|
"loss": 5.6441,
|
|
"mean_token_accuracy": 0.17175253927707673,
|
|
"num_tokens": 6632296.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.629729986190796,
|
|
"epoch": 0.27761767531219983,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996272967588715,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.17308499813079833,
|
|
"num_tokens": 6644413.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.616733264923096,
|
|
"epoch": 0.2780979827089337,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996253216774283,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.17536325752735138,
|
|
"num_tokens": 6655634.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.566686773300171,
|
|
"epoch": 0.27857829010566765,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996233413808521,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.18005252480506898,
|
|
"num_tokens": 6665977.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.589098834991455,
|
|
"epoch": 0.27905859750240153,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996213558691889,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.16986947655677795,
|
|
"num_tokens": 6677165.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.5928606510162355,
|
|
"epoch": 0.27953890489913547,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996193651424848,
|
|
"loss": 5.6578,
|
|
"mean_token_accuracy": 0.17219153493642808,
|
|
"num_tokens": 6688182.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.562531757354736,
|
|
"epoch": 0.28001921229586935,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499617369200786,
|
|
"loss": 5.5547,
|
|
"mean_token_accuracy": 0.17558752298355101,
|
|
"num_tokens": 6699259.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.630407905578613,
|
|
"epoch": 0.2804995196926033,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996153680441389,
|
|
"loss": 5.5647,
|
|
"mean_token_accuracy": 0.17240963131189346,
|
|
"num_tokens": 6710071.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.601401424407959,
|
|
"epoch": 0.28097982708933716,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049961336167259,
|
|
"loss": 5.61,
|
|
"mean_token_accuracy": 0.17204567939043044,
|
|
"num_tokens": 6720267.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.683440780639648,
|
|
"epoch": 0.2814601344860711,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996113500861857,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.16914477646350862,
|
|
"num_tokens": 6730919.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.553895092010498,
|
|
"epoch": 0.281940441882805,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996093332849729,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.17506259977817534,
|
|
"num_tokens": 6741480.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.604211473464966,
|
|
"epoch": 0.2824207492795389,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996073112689983,
|
|
"loss": 5.5304,
|
|
"mean_token_accuracy": 0.1787044510245323,
|
|
"num_tokens": 6751816.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.535765361785889,
|
|
"epoch": 0.2829010566762728,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996052840383088,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.17378600239753722,
|
|
"num_tokens": 6763645.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.56224799156189,
|
|
"epoch": 0.28338136407300674,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996032515929516,
|
|
"loss": 5.5275,
|
|
"mean_token_accuracy": 0.17407883554697037,
|
|
"num_tokens": 6774795.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.566365337371826,
|
|
"epoch": 0.2838616714697406,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996012139329738,
|
|
"loss": 5.4567,
|
|
"mean_token_accuracy": 0.18206687271595,
|
|
"num_tokens": 6786833.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.460562705993652,
|
|
"epoch": 0.28434197886647455,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995991710584228,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.17664896845817565,
|
|
"num_tokens": 6798134.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.614284372329712,
|
|
"epoch": 0.28482228626320844,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995971229693459,
|
|
"loss": 5.5657,
|
|
"mean_token_accuracy": 0.1824972078204155,
|
|
"num_tokens": 6807918.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.6419624328613285,
|
|
"epoch": 0.28530259365994237,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995950696657909,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.17275601327419282,
|
|
"num_tokens": 6818689.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.5683265209198,
|
|
"epoch": 0.28578290105667625,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004995930111478051,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.17747195959091186,
|
|
"num_tokens": 6830871.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.584042739868164,
|
|
"epoch": 0.2862632084534102,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995909474154365,
|
|
"loss": 5.5118,
|
|
"mean_token_accuracy": 0.18256898522377013,
|
|
"num_tokens": 6842857.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.512867593765259,
|
|
"epoch": 0.28674351585014407,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995888784687331,
|
|
"loss": 5.5396,
|
|
"mean_token_accuracy": 0.1776072397828102,
|
|
"num_tokens": 6853727.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.5820722579956055,
|
|
"epoch": 0.287223823246878,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995868043077428,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.17571521997451783,
|
|
"num_tokens": 6864728.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.627726793289185,
|
|
"epoch": 0.2877041306436119,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995847249325137,
|
|
"loss": 5.6271,
|
|
"mean_token_accuracy": 0.17045981287956238,
|
|
"num_tokens": 6875001.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.526087427139283,
|
|
"epoch": 0.2881844380403458,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995826403430942,
|
|
"loss": 5.5175,
|
|
"mean_token_accuracy": 0.18246698677539824,
|
|
"num_tokens": 6887026.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2881844380403458,
|
|
"eval_entropy": 5.487682455286986,
|
|
"eval_loss": 5.587414264678955,
|
|
"eval_mean_token_accuracy": 0.18148705224778552,
|
|
"eval_num_tokens": 6887026.0,
|
|
"eval_runtime": 27.0434,
|
|
"eval_samples_per_second": 1213.422,
|
|
"eval_steps_per_second": 151.682,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.784534358978272,
|
|
"epoch": 0.2886647454370797,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995805505395328,
|
|
"loss": 5.634,
|
|
"mean_token_accuracy": 0.17297943606972693,
|
|
"num_tokens": 6900118.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.592379331588745,
|
|
"epoch": 0.28914505283381364,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995784555218778,
|
|
"loss": 5.5457,
|
|
"mean_token_accuracy": 0.177190899848938,
|
|
"num_tokens": 6912135.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.497978210449219,
|
|
"epoch": 0.2896253602305475,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004995763552901779,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.1853455811738968,
|
|
"num_tokens": 6923781.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.664725828170776,
|
|
"epoch": 0.29010566762728146,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995742498444818,
|
|
"loss": 5.5343,
|
|
"mean_token_accuracy": 0.17282128781080247,
|
|
"num_tokens": 6935804.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.571994972229004,
|
|
"epoch": 0.2905859750240154,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995721391848387,
|
|
"loss": 5.5897,
|
|
"mean_token_accuracy": 0.17708188891410828,
|
|
"num_tokens": 6948289.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.632468414306641,
|
|
"epoch": 0.2910662824207493,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995700233112972,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.1799446865916252,
|
|
"num_tokens": 6958719.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.5489743709564205,
|
|
"epoch": 0.2915465898174832,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995679022239066,
|
|
"loss": 5.5794,
|
|
"mean_token_accuracy": 0.18038478195667268,
|
|
"num_tokens": 6969041.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.5848000049591064,
|
|
"epoch": 0.2920268972142171,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995657759227162,
|
|
"loss": 5.6493,
|
|
"mean_token_accuracy": 0.17737395614385604,
|
|
"num_tokens": 6981206.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.696254730224609,
|
|
"epoch": 0.29250720461095103,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995636444077751,
|
|
"loss": 5.538,
|
|
"mean_token_accuracy": 0.1819950446486473,
|
|
"num_tokens": 6993169.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.5612489700317385,
|
|
"epoch": 0.2929875120076849,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995615076791333,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.17608709931373595,
|
|
"num_tokens": 7005175.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.648107385635376,
|
|
"epoch": 0.29346781940441885,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995593657368399,
|
|
"loss": 5.6127,
|
|
"mean_token_accuracy": 0.17430707216262817,
|
|
"num_tokens": 7016738.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.608227968215942,
|
|
"epoch": 0.29394812680115273,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499557218580945,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.18451340198516847,
|
|
"num_tokens": 7028399.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.553318691253662,
|
|
"epoch": 0.29442843419788667,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995550662114981,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.17278157025575638,
|
|
"num_tokens": 7039528.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.479732799530029,
|
|
"epoch": 0.29490874159462055,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995529086285495,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.18942976742982864,
|
|
"num_tokens": 7051399.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.4366058826446535,
|
|
"epoch": 0.2953890489913545,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000499550745832149,
|
|
"loss": 5.4343,
|
|
"mean_token_accuracy": 0.18675332069396972,
|
|
"num_tokens": 7062452.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.553073835372925,
|
|
"epoch": 0.29586935638808837,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004995485778223471,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.17742615193128586,
|
|
"num_tokens": 7074052.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.721508979797363,
|
|
"epoch": 0.2963496637848223,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004995464045991939,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.17061588913202286,
|
|
"num_tokens": 7086692.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.601110982894897,
|
|
"epoch": 0.2968299711815562,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00049954422616274,
|
|
"loss": 5.5736,
|
|
"mean_token_accuracy": 0.1758839413523674,
|
|
"num_tokens": 7098221.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.455524539947509,
|
|
"epoch": 0.2973102785782901,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004995420425130359,
|
|
"loss": 5.5355,
|
|
"mean_token_accuracy": 0.182497076690197,
|
|
"num_tokens": 7110129.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.684749460220337,
|
|
"epoch": 0.297790585975024,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004995398536501324,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.17379121631383895,
|
|
"num_tokens": 7121523.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.6178731441497805,
|
|
"epoch": 0.29827089337175794,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995376595740801,
|
|
"loss": 5.543,
|
|
"mean_token_accuracy": 0.18315426707267762,
|
|
"num_tokens": 7133482.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.5218054294586185,
|
|
"epoch": 0.2987512007684918,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995354602849302,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.18059220016002656,
|
|
"num_tokens": 7144031.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.6512165546417235,
|
|
"epoch": 0.29923150816522576,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995332557827337,
|
|
"loss": 5.6016,
|
|
"mean_token_accuracy": 0.1730698049068451,
|
|
"num_tokens": 7155469.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.630453109741211,
|
|
"epoch": 0.29971181556195964,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995310460675416,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.1743144854903221,
|
|
"num_tokens": 7167077.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.560130977630616,
|
|
"epoch": 0.3001921229586936,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995288311394053,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.1782015010714531,
|
|
"num_tokens": 7178917.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.596506404876709,
|
|
"epoch": 0.30067243035542746,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995266109983764,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.176068215072155,
|
|
"num_tokens": 7190284.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.533182668685913,
|
|
"epoch": 0.3011527377521614,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995243856445062,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.1797621876001358,
|
|
"num_tokens": 7202391.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.574808263778687,
|
|
"epoch": 0.3016330451488953,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995221550778466,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.18022829294204712,
|
|
"num_tokens": 7212882.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.509401130676269,
|
|
"epoch": 0.3021133525456292,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995199192984491,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.18269667625427247,
|
|
"num_tokens": 7224102.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.554200077056885,
|
|
"epoch": 0.3025936599423631,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995176783063657,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.17980438470840454,
|
|
"num_tokens": 7234579.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.574840784072876,
|
|
"epoch": 0.30307396733909703,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004995154321016487,
|
|
"loss": 5.5879,
|
|
"mean_token_accuracy": 0.17145463675260544,
|
|
"num_tokens": 7246065.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.650038957595825,
|
|
"epoch": 0.3035542747358309,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995131806843499,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.16908762753009796,
|
|
"num_tokens": 7258899.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.630798196792602,
|
|
"epoch": 0.30403458213256485,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995109240545218,
|
|
"loss": 5.6372,
|
|
"mean_token_accuracy": 0.15845271199941635,
|
|
"num_tokens": 7271887.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.6133870601654055,
|
|
"epoch": 0.3045148895292987,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995086622122167,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.17348585575819014,
|
|
"num_tokens": 7282773.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.527261400222779,
|
|
"epoch": 0.30499519692603266,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995063951574871,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.18299773186445237,
|
|
"num_tokens": 7294460.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.462077379226685,
|
|
"epoch": 0.30547550432276654,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995041228903856,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.18556461483240128,
|
|
"num_tokens": 7305125.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.476806926727295,
|
|
"epoch": 0.3059558117195005,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499501845410965,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.17339503020048141,
|
|
"num_tokens": 7317738.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.590009593963623,
|
|
"epoch": 0.30643611911623436,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994995627192781,
|
|
"loss": 5.4933,
|
|
"mean_token_accuracy": 0.18183531910181044,
|
|
"num_tokens": 7329820.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.583674764633178,
|
|
"epoch": 0.3069164265129683,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994972748153781,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.1705733358860016,
|
|
"num_tokens": 7341471.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.594673109054566,
|
|
"epoch": 0.30739673390970224,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499494981699318,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.1798601508140564,
|
|
"num_tokens": 7352459.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.549898624420166,
|
|
"epoch": 0.3078770413064361,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499492683371151,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.18590417206287385,
|
|
"num_tokens": 7363129.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.5865977764129635,
|
|
"epoch": 0.30835734870317005,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994903798309306,
|
|
"loss": 5.5361,
|
|
"mean_token_accuracy": 0.17652668207883834,
|
|
"num_tokens": 7373726.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.575078392028809,
|
|
"epoch": 0.30883765609990393,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004994880710787102,
|
|
"loss": 5.5808,
|
|
"mean_token_accuracy": 0.17862567454576492,
|
|
"num_tokens": 7383847.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.550208473205567,
|
|
"epoch": 0.30931796349663787,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994857571145432,
|
|
"loss": 5.5744,
|
|
"mean_token_accuracy": 0.1706383302807808,
|
|
"num_tokens": 7396425.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.712774705886841,
|
|
"epoch": 0.30979827089337175,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994834379384837,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.1724379241466522,
|
|
"num_tokens": 7407591.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.496092796325684,
|
|
"epoch": 0.3102785782901057,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994811135505851,
|
|
"loss": 5.4903,
|
|
"mean_token_accuracy": 0.17818500250577926,
|
|
"num_tokens": 7419668.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.6027021408081055,
|
|
"epoch": 0.31075888568683957,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994787839509018,
|
|
"loss": 5.6,
|
|
"mean_token_accuracy": 0.1715978592634201,
|
|
"num_tokens": 7431969.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.718282890319824,
|
|
"epoch": 0.3112391930835735,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994764491394876,
|
|
"loss": 5.6002,
|
|
"mean_token_accuracy": 0.16918736100196838,
|
|
"num_tokens": 7443467.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.618907451629639,
|
|
"epoch": 0.3117195004803074,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994741091163969,
|
|
"loss": 5.5802,
|
|
"mean_token_accuracy": 0.18071286231279374,
|
|
"num_tokens": 7455220.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.535886287689209,
|
|
"epoch": 0.3121998078770413,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499471763881684,
|
|
"loss": 5.4891,
|
|
"mean_token_accuracy": 0.17951259315013884,
|
|
"num_tokens": 7466452.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.520643424987793,
|
|
"epoch": 0.3126801152737752,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994694134354031,
|
|
"loss": 5.5523,
|
|
"mean_token_accuracy": 0.18383537232875824,
|
|
"num_tokens": 7478798.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.656300401687622,
|
|
"epoch": 0.31316042267050914,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000499467057777609,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.17627301812171936,
|
|
"num_tokens": 7491039.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.56907434463501,
|
|
"epoch": 0.313640730067243,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004994646969083565,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.18003961741924285,
|
|
"num_tokens": 7501455.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.550380516052246,
|
|
"epoch": 0.31412103746397696,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994623308277002,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.17807594686746597,
|
|
"num_tokens": 7513484.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.624225521087647,
|
|
"epoch": 0.31460134486071084,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499459959535695,
|
|
"loss": 5.5295,
|
|
"mean_token_accuracy": 0.17495962828397751,
|
|
"num_tokens": 7524868.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.458921718597412,
|
|
"epoch": 0.3150816522574448,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004994575830323962,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.18480057418346404,
|
|
"num_tokens": 7536290.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.473631525039673,
|
|
"epoch": 0.31556195965417866,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994552013178586,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.18113575130701065,
|
|
"num_tokens": 7546994.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.576454162597656,
|
|
"epoch": 0.3160422670509126,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499452814392138,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.1771087422966957,
|
|
"num_tokens": 7559231.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.5458738803863525,
|
|
"epoch": 0.3165225744476465,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994504222552894,
|
|
"loss": 5.4728,
|
|
"mean_token_accuracy": 0.18084817826747895,
|
|
"num_tokens": 7570894.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.593354415893555,
|
|
"epoch": 0.3170028818443804,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994480249073684,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.17107368111610413,
|
|
"num_tokens": 7581765.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.584808492660523,
|
|
"epoch": 0.3174831892411143,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994456223484308,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.1847134992480278,
|
|
"num_tokens": 7591828.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.496738052368164,
|
|
"epoch": 0.31796349663784823,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994432145785323,
|
|
"loss": 5.5205,
|
|
"mean_token_accuracy": 0.17210932746529578,
|
|
"num_tokens": 7604230.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.508804702758789,
|
|
"epoch": 0.3184438040345821,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994408015977288,
|
|
"loss": 5.4806,
|
|
"mean_token_accuracy": 0.17956049144268035,
|
|
"num_tokens": 7615780.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.559992456436158,
|
|
"epoch": 0.31892411143131605,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994383834060764,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.18018749207258225,
|
|
"num_tokens": 7627633.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.54780011177063,
|
|
"epoch": 0.31940441882804993,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994359600036311,
|
|
"loss": 5.5638,
|
|
"mean_token_accuracy": 0.17372141033411026,
|
|
"num_tokens": 7639487.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.53131685256958,
|
|
"epoch": 0.31988472622478387,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994335313904493,
|
|
"loss": 5.4787,
|
|
"mean_token_accuracy": 0.18689664602279663,
|
|
"num_tokens": 7649976.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.652995538711548,
|
|
"epoch": 0.32036503362151775,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004994310975665873,
|
|
"loss": 5.6624,
|
|
"mean_token_accuracy": 0.17187715470790862,
|
|
"num_tokens": 7662555.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.516408157348633,
|
|
"epoch": 0.3208453410182517,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994286585321017,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.18426660150289537,
|
|
"num_tokens": 7673869.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.440064382553101,
|
|
"epoch": 0.32132564841498557,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499426214287049,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.1737172707915306,
|
|
"num_tokens": 7687149.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.638825702667236,
|
|
"epoch": 0.3218059558117195,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994237648314862,
|
|
"loss": 5.5771,
|
|
"mean_token_accuracy": 0.172631074488163,
|
|
"num_tokens": 7698352.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.527461862564087,
|
|
"epoch": 0.3222862632084534,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994213101654697,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.18670456856489182,
|
|
"num_tokens": 7709117.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.505496597290039,
|
|
"epoch": 0.3227665706051873,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499418850289057,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.18491367399692535,
|
|
"num_tokens": 7721731.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.465352964401245,
|
|
"epoch": 0.32324687800192126,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004994163852023048,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.1779892385005951,
|
|
"num_tokens": 7733010.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.502725553512573,
|
|
"epoch": 0.32372718539865514,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994139149052706,
|
|
"loss": 5.4128,
|
|
"mean_token_accuracy": 0.1885485202074051,
|
|
"num_tokens": 7743905.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.549247980117798,
|
|
"epoch": 0.3242074927953891,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994114393980117,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.1853503555059433,
|
|
"num_tokens": 7754891.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.602116250991822,
|
|
"epoch": 0.32468780019212296,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.1704148158431053,
|
|
"num_tokens": 7766831.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.567165756225586,
|
|
"epoch": 0.3251681075888569,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994064727530496,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.17241787314414977,
|
|
"num_tokens": 7778239.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.570478391647339,
|
|
"epoch": 0.3256484149855908,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994039816154618,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.18829160332679748,
|
|
"num_tokens": 7789449.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.566330051422119,
|
|
"epoch": 0.3261287223823247,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00049940148526788,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.17587794810533525,
|
|
"num_tokens": 7799507.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.594382429122925,
|
|
"epoch": 0.3266090297790586,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993989837103618,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.1818511962890625,
|
|
"num_tokens": 7811730.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.5170355319976805,
|
|
"epoch": 0.3270893371757925,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993964769429657,
|
|
"loss": 5.3913,
|
|
"mean_token_accuracy": 0.19005172401666642,
|
|
"num_tokens": 7823108.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.479337692260742,
|
|
"epoch": 0.3275696445725264,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993939649657498,
|
|
"loss": 5.4954,
|
|
"mean_token_accuracy": 0.18005067110061646,
|
|
"num_tokens": 7835384.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.633117008209228,
|
|
"epoch": 0.32804995196926034,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993914477787721,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.18406772017478942,
|
|
"num_tokens": 7845860.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.571261167526245,
|
|
"epoch": 0.3285302593659942,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004993889253820915,
|
|
"loss": 5.5867,
|
|
"mean_token_accuracy": 0.17345319539308549,
|
|
"num_tokens": 7856861.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.547126531600952,
|
|
"epoch": 0.32901056676272816,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004993863977757663,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.1789025694131851,
|
|
"num_tokens": 7868902.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.592067241668701,
|
|
"epoch": 0.32949087415946204,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993838649598552,
|
|
"loss": 5.5241,
|
|
"mean_token_accuracy": 0.17713177651166917,
|
|
"num_tokens": 7880369.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.600041341781616,
|
|
"epoch": 0.329971181556196,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993813269344171,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.1734185978770256,
|
|
"num_tokens": 7892041.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.557718801498413,
|
|
"epoch": 0.33045148895292986,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004993787836995108,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.18128235787153243,
|
|
"num_tokens": 7903644.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.55188684463501,
|
|
"epoch": 0.3309317963496638,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993762352551954,
|
|
"loss": 5.5356,
|
|
"mean_token_accuracy": 0.17435626536607743,
|
|
"num_tokens": 7915679.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.591059875488281,
|
|
"epoch": 0.3314121037463977,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993736816015301,
|
|
"loss": 5.5674,
|
|
"mean_token_accuracy": 0.1774520233273506,
|
|
"num_tokens": 7928020.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.646395540237426,
|
|
"epoch": 0.3318924111431316,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993711227385742,
|
|
"loss": 5.6181,
|
|
"mean_token_accuracy": 0.17499688863754273,
|
|
"num_tokens": 7940521.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.59263768196106,
|
|
"epoch": 0.3323727185398655,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993685586663871,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.17106352746486664,
|
|
"num_tokens": 7952234.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.6110433578491214,
|
|
"epoch": 0.33285302593659943,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993659893850281,
|
|
"loss": 5.6388,
|
|
"mean_token_accuracy": 0.17529400438070297,
|
|
"num_tokens": 7964900.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.642898845672607,
|
|
"epoch": 0.3333333333333333,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004993634148945573,
|
|
"loss": 5.63,
|
|
"mean_token_accuracy": 0.17343595176935195,
|
|
"num_tokens": 7976661.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.529425048828125,
|
|
"epoch": 0.33381364073006725,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004993608351950341,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.18070945143699646,
|
|
"num_tokens": 7987605.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.487625551223755,
|
|
"epoch": 0.33429394812680113,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004993582502865185,
|
|
"loss": 5.5197,
|
|
"mean_token_accuracy": 0.17941949963569642,
|
|
"num_tokens": 7998879.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.516484785079956,
|
|
"epoch": 0.33477425552353507,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993556601690706,
|
|
"loss": 5.5174,
|
|
"mean_token_accuracy": 0.1826210230588913,
|
|
"num_tokens": 8010634.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.6183764934539795,
|
|
"epoch": 0.33525456292026895,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993530648427505,
|
|
"loss": 5.5108,
|
|
"mean_token_accuracy": 0.17249346971511842,
|
|
"num_tokens": 8022134.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.5445984363555905,
|
|
"epoch": 0.3357348703170029,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993504643076184,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.17687141448259353,
|
|
"num_tokens": 8034454.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.613416385650635,
|
|
"epoch": 0.33621517771373677,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004993478585637347,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.17275482267141343,
|
|
"num_tokens": 8046175.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.645603847503662,
|
|
"epoch": 0.3366954851104707,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004993452476111599,
|
|
"loss": 5.5959,
|
|
"mean_token_accuracy": 0.1748912051320076,
|
|
"num_tokens": 8057335.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.4952959537506105,
|
|
"epoch": 0.3371757925072046,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993426314499546,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.1863348513841629,
|
|
"num_tokens": 8068860.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.541372632980346,
|
|
"epoch": 0.3376560999039385,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993400100801796,
|
|
"loss": 5.4994,
|
|
"mean_token_accuracy": 0.18107041716575623,
|
|
"num_tokens": 8078957.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.620969152450561,
|
|
"epoch": 0.3381364073006724,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993373835018956,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.1709742322564125,
|
|
"num_tokens": 8090143.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.475292491912842,
|
|
"epoch": 0.33861671469740634,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993347517151638,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.1815132901072502,
|
|
"num_tokens": 8101961.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.399444246292115,
|
|
"epoch": 0.3390970220941403,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004993321147200452,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.1859508275985718,
|
|
"num_tokens": 8112635.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.527603101730347,
|
|
"epoch": 0.33957732949087416,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000499329472516601,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.17721263766288758,
|
|
"num_tokens": 8123730.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.588210105895996,
|
|
"epoch": 0.3400576368876081,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004993268251048925,
|
|
"loss": 5.5535,
|
|
"mean_token_accuracy": 0.17419885396957396,
|
|
"num_tokens": 8135258.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.5484428882598875,
|
|
"epoch": 0.340537944284342,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004993241724849814,
|
|
"loss": 5.4141,
|
|
"mean_token_accuracy": 0.18497108668088913,
|
|
"num_tokens": 8145946.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.568217039108276,
|
|
"epoch": 0.3410182516810759,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499321514656929,
|
|
"loss": 5.6227,
|
|
"mean_token_accuracy": 0.17725986391305923,
|
|
"num_tokens": 8158422.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.59538516998291,
|
|
"epoch": 0.3414985590778098,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004993188516207972,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.16808454543352128,
|
|
"num_tokens": 8170849.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.472879934310913,
|
|
"epoch": 0.34197886647454373,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993161833766478,
|
|
"loss": 5.4718,
|
|
"mean_token_accuracy": 0.17750526070594788,
|
|
"num_tokens": 8180907.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.5876367568969725,
|
|
"epoch": 0.3424591738712776,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004993135099245426,
|
|
"loss": 5.5691,
|
|
"mean_token_accuracy": 0.17272659689188002,
|
|
"num_tokens": 8193418.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.638572835922242,
|
|
"epoch": 0.34293948126801155,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004993108312645438,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.17432851642370223,
|
|
"num_tokens": 8203873.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.689888572692871,
|
|
"epoch": 0.34341978866474543,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004993081473967135,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.1738373428583145,
|
|
"num_tokens": 8215150.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.633081579208374,
|
|
"epoch": 0.34390009606147937,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004993054583211143,
|
|
"loss": 5.5772,
|
|
"mean_token_accuracy": 0.17401220202445983,
|
|
"num_tokens": 8225732.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.580939245223999,
|
|
"epoch": 0.34438040345821325,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993027640378081,
|
|
"loss": 5.5413,
|
|
"mean_token_accuracy": 0.17461099326610566,
|
|
"num_tokens": 8237523.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.578071880340576,
|
|
"epoch": 0.3448607108549472,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000499300064546858,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.18483215868473052,
|
|
"num_tokens": 8249660.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.528390693664551,
|
|
"epoch": 0.34534101825168106,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004992973598483264,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.18607661873102188,
|
|
"num_tokens": 8261224.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.4553515911102295,
|
|
"epoch": 0.345821325648415,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000499294649942276,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.17476649433374405,
|
|
"num_tokens": 8272177.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.509897232055664,
|
|
"epoch": 0.3463016330451489,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992919348287699,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.17783477455377578,
|
|
"num_tokens": 8284449.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.580263137817383,
|
|
"epoch": 0.3467819404418828,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004992892145078711,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.18046885281801223,
|
|
"num_tokens": 8297028.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.550862407684326,
|
|
"epoch": 0.3472622478386167,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004992864889796427,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.1867825835943222,
|
|
"num_tokens": 8308348.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.5030101299285885,
|
|
"epoch": 0.34774255523535064,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004992837582441481,
|
|
"loss": 5.4419,
|
|
"mean_token_accuracy": 0.18680350333452225,
|
|
"num_tokens": 8318951.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.570378112792969,
|
|
"epoch": 0.3482228626320845,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004992810223014506,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.1736852467060089,
|
|
"num_tokens": 8329979.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.6074597358703615,
|
|
"epoch": 0.34870317002881845,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004992782811516137,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.18209828138351442,
|
|
"num_tokens": 8340332.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.504545783996582,
|
|
"epoch": 0.34918347742555234,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004992755347947011,
|
|
"loss": 5.5036,
|
|
"mean_token_accuracy": 0.17444830089807511,
|
|
"num_tokens": 8350376.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.5022422790527346,
|
|
"epoch": 0.34966378482228627,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992727832307766,
|
|
"loss": 5.447,
|
|
"mean_token_accuracy": 0.1850413426756859,
|
|
"num_tokens": 8361884.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.412858676910401,
|
|
"epoch": 0.35014409221902015,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992700264599039,
|
|
"loss": 5.3681,
|
|
"mean_token_accuracy": 0.1885715678334236,
|
|
"num_tokens": 8372914.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.607450914382935,
|
|
"epoch": 0.3506243996157541,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992672644821473,
|
|
"loss": 5.541,
|
|
"mean_token_accuracy": 0.17206971049308778,
|
|
"num_tokens": 8385800.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.460282897949218,
|
|
"epoch": 0.35110470701248797,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992644972975707,
|
|
"loss": 5.4328,
|
|
"mean_token_accuracy": 0.18788817524909973,
|
|
"num_tokens": 8397783.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.495180940628051,
|
|
"epoch": 0.3515850144092219,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992617249062383,
|
|
"loss": 5.4815,
|
|
"mean_token_accuracy": 0.1792609453201294,
|
|
"num_tokens": 8409096.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.487185144424439,
|
|
"epoch": 0.3520653218059558,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004992589473082147,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.18282747715711595,
|
|
"num_tokens": 8420833.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.518129491806031,
|
|
"epoch": 0.3525456292026897,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992561645035641,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.1755655437707901,
|
|
"num_tokens": 8431848.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.674550867080688,
|
|
"epoch": 0.3530259365994236,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004992533764923515,
|
|
"loss": 5.581,
|
|
"mean_token_accuracy": 0.17016951739788055,
|
|
"num_tokens": 8443620.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.523875331878662,
|
|
"epoch": 0.35350624399615754,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004992505832746412,
|
|
"loss": 5.5753,
|
|
"mean_token_accuracy": 0.17916093170642852,
|
|
"num_tokens": 8455339.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.41377534866333,
|
|
"epoch": 0.3539865513928914,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992477848504983,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.1903923347592354,
|
|
"num_tokens": 8466342.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.558801507949829,
|
|
"epoch": 0.35446685878962536,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992449812199877,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.18054721355438233,
|
|
"num_tokens": 8476955.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.4651518821716305,
|
|
"epoch": 0.3549471661863593,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004992421723831745,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.18249859064817428,
|
|
"num_tokens": 8488148.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.50803542137146,
|
|
"epoch": 0.3554274735830932,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004992393583401239,
|
|
"loss": 5.44,
|
|
"mean_token_accuracy": 0.1850776731967926,
|
|
"num_tokens": 8499014.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.592900276184082,
|
|
"epoch": 0.3559077809798271,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004992365390909014,
|
|
"loss": 5.5041,
|
|
"mean_token_accuracy": 0.1760295107960701,
|
|
"num_tokens": 8510191.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.4998047828674315,
|
|
"epoch": 0.356388088376561,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004992337146355721,
|
|
"loss": 5.382,
|
|
"mean_token_accuracy": 0.19070065915584564,
|
|
"num_tokens": 8522368.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.478042936325073,
|
|
"epoch": 0.35686839577329493,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004992308849742019,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.18542258441448212,
|
|
"num_tokens": 8533692.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.532752656936646,
|
|
"epoch": 0.3573487031700288,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004992280501068563,
|
|
"loss": 5.4923,
|
|
"mean_token_accuracy": 0.18073118031024932,
|
|
"num_tokens": 8545283.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.548139572143555,
|
|
"epoch": 0.35782901056676275,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004992252100336012,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.18284210115671157,
|
|
"num_tokens": 8555094.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.493295383453369,
|
|
"epoch": 0.35830931796349663,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992223647545027,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.17202253490686417,
|
|
"num_tokens": 8565179.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.458832216262818,
|
|
"epoch": 0.35878962536023057,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992195142696266,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.17971008121967316,
|
|
"num_tokens": 8575764.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.402663707733154,
|
|
"epoch": 0.35926993275696445,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004992166585790391,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.1906619504094124,
|
|
"num_tokens": 8586052.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.586157178878784,
|
|
"epoch": 0.3597502401536984,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004992137976828067,
|
|
"loss": 5.5437,
|
|
"mean_token_accuracy": 0.1729776903986931,
|
|
"num_tokens": 8597832.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.630362415313721,
|
|
"epoch": 0.36023054755043227,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004992109315809955,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.1815161645412445,
|
|
"num_tokens": 8609917.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.622105073928833,
|
|
"epoch": 0.3607108549471662,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004992080602736725,
|
|
"loss": 5.531,
|
|
"mean_token_accuracy": 0.17484886199235916,
|
|
"num_tokens": 8620137.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.485766124725342,
|
|
"epoch": 0.3611911623439001,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004992051837609039,
|
|
"loss": 5.5359,
|
|
"mean_token_accuracy": 0.17977116703987123,
|
|
"num_tokens": 8630620.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.506924819946289,
|
|
"epoch": 0.361671469740634,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004992023020427568,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.186400842666626,
|
|
"num_tokens": 8642820.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.526337003707885,
|
|
"epoch": 0.3621517771373679,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004991994151192979,
|
|
"loss": 5.4057,
|
|
"mean_token_accuracy": 0.18802926689386368,
|
|
"num_tokens": 8654081.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.496154022216797,
|
|
"epoch": 0.36263208453410184,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991965229905943,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.18222517222166063,
|
|
"num_tokens": 8665097.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.496727418899536,
|
|
"epoch": 0.3631123919308357,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991936256567133,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.18645656406879424,
|
|
"num_tokens": 8676576.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.522012424468994,
|
|
"epoch": 0.36359269932756966,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000499190723117722,
|
|
"loss": 5.4352,
|
|
"mean_token_accuracy": 0.1772135764360428,
|
|
"num_tokens": 8689217.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.579939079284668,
|
|
"epoch": 0.36407300672430354,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004991878153736877,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.17048364728689194,
|
|
"num_tokens": 8701101.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.5359409809112545,
|
|
"epoch": 0.3645533141210375,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004991849024246781,
|
|
"loss": 5.4834,
|
|
"mean_token_accuracy": 0.1785448133945465,
|
|
"num_tokens": 8712769.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.5004900932312015,
|
|
"epoch": 0.36503362151777136,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991819842707608,
|
|
"loss": 5.4207,
|
|
"mean_token_accuracy": 0.18760534077882768,
|
|
"num_tokens": 8724691.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.416055679321289,
|
|
"epoch": 0.3655139289145053,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004991790609120035,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.18623173832893372,
|
|
"num_tokens": 8738008.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.621143198013305,
|
|
"epoch": 0.3659942363112392,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000499176132348474,
|
|
"loss": 5.5939,
|
|
"mean_token_accuracy": 0.17312756925821304,
|
|
"num_tokens": 8750353.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.495223045349121,
|
|
"epoch": 0.3664745437079731,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004991731985802405,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.1862175390124321,
|
|
"num_tokens": 8761319.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.491991853713989,
|
|
"epoch": 0.366954851104707,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991702596073708,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.18171467781066894,
|
|
"num_tokens": 8772722.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.680236911773681,
|
|
"epoch": 0.36743515850144093,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004991673154299335,
|
|
"loss": 5.5401,
|
|
"mean_token_accuracy": 0.17654287219047546,
|
|
"num_tokens": 8783886.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.507202577590943,
|
|
"epoch": 0.3679154658981748,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004991643660479967,
|
|
"loss": 5.4677,
|
|
"mean_token_accuracy": 0.182183638215065,
|
|
"num_tokens": 8795161.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.455057001113891,
|
|
"epoch": 0.36839577329490875,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004991614114616289,
|
|
"loss": 5.4381,
|
|
"mean_token_accuracy": 0.18425257205963136,
|
|
"num_tokens": 8805417.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.536152696609497,
|
|
"epoch": 0.3688760806916426,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004991584516708988,
|
|
"loss": 5.5076,
|
|
"mean_token_accuracy": 0.17491607666015624,
|
|
"num_tokens": 8817980.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.479372930526734,
|
|
"epoch": 0.36935638808837656,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004991554866758751,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.19501214772462844,
|
|
"num_tokens": 8829814.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.439425039291382,
|
|
"epoch": 0.36983669548511044,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991525164766265,
|
|
"loss": 5.4003,
|
|
"mean_token_accuracy": 0.1816820025444031,
|
|
"num_tokens": 8840220.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.535809803009033,
|
|
"epoch": 0.3703170028818444,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004991495410732222,
|
|
"loss": 5.544,
|
|
"mean_token_accuracy": 0.17503760904073715,
|
|
"num_tokens": 8852156.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.564910411834717,
|
|
"epoch": 0.37079731027857826,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004991465604657311,
|
|
"loss": 5.4649,
|
|
"mean_token_accuracy": 0.1742330566048622,
|
|
"num_tokens": 8863362.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.473694896697998,
|
|
"epoch": 0.3712776176753122,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004991435746542224,
|
|
"loss": 5.4766,
|
|
"mean_token_accuracy": 0.1813788130879402,
|
|
"num_tokens": 8874957.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.491585159301758,
|
|
"epoch": 0.37175792507204614,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991405836387655,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.19009595215320588,
|
|
"num_tokens": 8886171.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.552527809143067,
|
|
"epoch": 0.37223823246878,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991375874194298,
|
|
"loss": 5.5307,
|
|
"mean_token_accuracy": 0.18047902584075928,
|
|
"num_tokens": 8898103.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.532804012298584,
|
|
"epoch": 0.37271853986551395,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000499134585996285,
|
|
"loss": 5.4914,
|
|
"mean_token_accuracy": 0.17974178791046141,
|
|
"num_tokens": 8910195.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.467819118499756,
|
|
"epoch": 0.37319884726224783,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991315793694004,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.18020269870758057,
|
|
"num_tokens": 8922865.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.512961053848267,
|
|
"epoch": 0.37367915465898177,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991285675388463,
|
|
"loss": 5.4669,
|
|
"mean_token_accuracy": 0.18156256675720214,
|
|
"num_tokens": 8933913.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.496314191818238,
|
|
"epoch": 0.37415946205571565,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991255505046922,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.17870626449584961,
|
|
"num_tokens": 8945749.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.534526300430298,
|
|
"epoch": 0.3746397694524496,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004991225282670083,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.1765512451529503,
|
|
"num_tokens": 8957454.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.525162124633789,
|
|
"epoch": 0.37512007684918347,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499119500825865,
|
|
"loss": 5.474,
|
|
"mean_token_accuracy": 0.1824617013335228,
|
|
"num_tokens": 8968173.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.45548300743103,
|
|
"epoch": 0.3756003842459174,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004991164681813323,
|
|
"loss": 5.4823,
|
|
"mean_token_accuracy": 0.18043213784694673,
|
|
"num_tokens": 8979187.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.501256608963013,
|
|
"epoch": 0.3760806916426513,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004991134303334807,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.19173142462968826,
|
|
"num_tokens": 8990007.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.502903604507447,
|
|
"epoch": 0.3765609990393852,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004991103872823807,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.17736413031816484,
|
|
"num_tokens": 9001108.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.58303918838501,
|
|
"epoch": 0.3770413064361191,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000499107339028103,
|
|
"loss": 5.5154,
|
|
"mean_token_accuracy": 0.1774510145187378,
|
|
"num_tokens": 9012704.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.534247255325317,
|
|
"epoch": 0.37752161383285304,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991042855707184,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.18156566768884658,
|
|
"num_tokens": 9024351.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.403720951080322,
|
|
"epoch": 0.3780019212295869,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004991012269102977,
|
|
"loss": 5.3985,
|
|
"mean_token_accuracy": 0.18490844815969468,
|
|
"num_tokens": 9035099.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.571021938323975,
|
|
"epoch": 0.37848222862632086,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004990981630469119,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.18070338517427445,
|
|
"num_tokens": 9045675.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.531776332855225,
|
|
"epoch": 0.37896253602305474,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004990950939806323,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.18625857383012773,
|
|
"num_tokens": 9057133.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.4402061939239506,
|
|
"epoch": 0.3794428434197887,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00049909201971153,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.18193181306123735,
|
|
"num_tokens": 9067806.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.379292678833008,
|
|
"epoch": 0.37992315081652256,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990889402396763,
|
|
"loss": 5.4337,
|
|
"mean_token_accuracy": 0.17841372936964034,
|
|
"num_tokens": 9079893.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.518050765991211,
|
|
"epoch": 0.3804034582132565,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004990858555651431,
|
|
"loss": 5.4534,
|
|
"mean_token_accuracy": 0.1778656631708145,
|
|
"num_tokens": 9091583.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.542593479156494,
|
|
"epoch": 0.3808837656099904,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004990827656880015,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.18845251202583313,
|
|
"num_tokens": 9102919.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.516092967987061,
|
|
"epoch": 0.3813640730067243,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990796706083235,
|
|
"loss": 5.4236,
|
|
"mean_token_accuracy": 0.18649644553661346,
|
|
"num_tokens": 9113876.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.600319576263428,
|
|
"epoch": 0.3818443804034582,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004990765703261809,
|
|
"loss": 5.5733,
|
|
"mean_token_accuracy": 0.1720522865653038,
|
|
"num_tokens": 9125630.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.546241998672485,
|
|
"epoch": 0.38232468780019213,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990734648416458,
|
|
"loss": 5.4872,
|
|
"mean_token_accuracy": 0.18249279856681824,
|
|
"num_tokens": 9137302.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.517662239074707,
|
|
"epoch": 0.382804995196926,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004990703541547901,
|
|
"loss": 5.4385,
|
|
"mean_token_accuracy": 0.19126711189746856,
|
|
"num_tokens": 9148048.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.575773859024048,
|
|
"epoch": 0.38328530259365995,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990672382656863,
|
|
"loss": 5.5034,
|
|
"mean_token_accuracy": 0.17943598479032516,
|
|
"num_tokens": 9158656.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.525322914123535,
|
|
"epoch": 0.38376560999039383,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004990641171744064,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.1827353596687317,
|
|
"num_tokens": 9169324.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.381278705596924,
|
|
"epoch": 0.38424591738712777,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990609908810231,
|
|
"loss": 5.3556,
|
|
"mean_token_accuracy": 0.18749811947345735,
|
|
"num_tokens": 9180238.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.343673324584961,
|
|
"epoch": 0.38472622478386165,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990578593856089,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.1928326591849327,
|
|
"num_tokens": 9190766.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.380656909942627,
|
|
"epoch": 0.3852065321805956,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990547226882366,
|
|
"loss": 5.3859,
|
|
"mean_token_accuracy": 0.18694805949926377,
|
|
"num_tokens": 9202445.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.476647901535034,
|
|
"epoch": 0.38568683957732947,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990515807889788,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.1870392620563507,
|
|
"num_tokens": 9212383.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.44529356956482,
|
|
"epoch": 0.3861671469740634,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990484336879087,
|
|
"loss": 5.349,
|
|
"mean_token_accuracy": 0.1862738847732544,
|
|
"num_tokens": 9223619.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.496671152114868,
|
|
"epoch": 0.3866474543707973,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004990452813850992,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.17846391946077347,
|
|
"num_tokens": 9234137.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.539433526992798,
|
|
"epoch": 0.3871277617675312,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004990421238806236,
|
|
"loss": 5.4297,
|
|
"mean_token_accuracy": 0.18255595862865448,
|
|
"num_tokens": 9246093.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.590913152694702,
|
|
"epoch": 0.38760806916426516,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004990389611745551,
|
|
"loss": 5.5424,
|
|
"mean_token_accuracy": 0.16726417541503907,
|
|
"num_tokens": 9258021.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.551828765869141,
|
|
"epoch": 0.38808837656099904,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990357932669672,
|
|
"loss": 5.5542,
|
|
"mean_token_accuracy": 0.18153435066342355,
|
|
"num_tokens": 9267668.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.57155327796936,
|
|
"epoch": 0.388568683957733,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990326201579335,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.17921186834573746,
|
|
"num_tokens": 9279381.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.574979829788208,
|
|
"epoch": 0.38904899135446686,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004990294418475274,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.1721788078546524,
|
|
"num_tokens": 9292578.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.47789044380188,
|
|
"epoch": 0.3895292987512008,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990262583358231,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.18749912977218627,
|
|
"num_tokens": 9304116.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.588890504837036,
|
|
"epoch": 0.3900096061479347,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990230696228943,
|
|
"loss": 5.5638,
|
|
"mean_token_accuracy": 0.18039464950561523,
|
|
"num_tokens": 9315877.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.451913595199585,
|
|
"epoch": 0.3904899135446686,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004990198757088149,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.18427368402481079,
|
|
"num_tokens": 9326859.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.570649194717407,
|
|
"epoch": 0.3909702209414025,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004990166765936593,
|
|
"loss": 5.5218,
|
|
"mean_token_accuracy": 0.17401764392852784,
|
|
"num_tokens": 9338067.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.551594066619873,
|
|
"epoch": 0.3914505283381364,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004990134722775016,
|
|
"loss": 5.5548,
|
|
"mean_token_accuracy": 0.17771293371915817,
|
|
"num_tokens": 9349564.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.384429550170898,
|
|
"epoch": 0.3919308357348703,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004990102627604162,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.18717946261167526,
|
|
"num_tokens": 9359962.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.442182159423828,
|
|
"epoch": 0.39241114313160425,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004990070480424778,
|
|
"loss": 5.3492,
|
|
"mean_token_accuracy": 0.18788860142230987,
|
|
"num_tokens": 9370251.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.529190635681152,
|
|
"epoch": 0.3928914505283381,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004990038281237608,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.1772561714053154,
|
|
"num_tokens": 9381848.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.45083270072937,
|
|
"epoch": 0.39337175792507206,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004990006030043401,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.18683607429265975,
|
|
"num_tokens": 9392475.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.5099693775177006,
|
|
"epoch": 0.39385206532180594,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004989973726842906,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.1804587125778198,
|
|
"num_tokens": 9404014.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.522710990905762,
|
|
"epoch": 0.3943323727185399,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989941371636872,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.18026885092258454,
|
|
"num_tokens": 9415590.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.573627662658692,
|
|
"epoch": 0.39481268011527376,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004989908964426051,
|
|
"loss": 5.5684,
|
|
"mean_token_accuracy": 0.17600324302911757,
|
|
"num_tokens": 9427486.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.538381767272949,
|
|
"epoch": 0.3952929875120077,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989876505211194,
|
|
"loss": 5.4647,
|
|
"mean_token_accuracy": 0.18080680817365646,
|
|
"num_tokens": 9438212.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.513815832138062,
|
|
"epoch": 0.3957732949087416,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989843993993056,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.1923951029777527,
|
|
"num_tokens": 9450922.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.414572429656983,
|
|
"epoch": 0.3962536023054755,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989811430772392,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.18224074989557265,
|
|
"num_tokens": 9461676.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.351324844360351,
|
|
"epoch": 0.3967339097022094,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004989778815549957,
|
|
"loss": 5.3505,
|
|
"mean_token_accuracy": 0.19106744974851608,
|
|
"num_tokens": 9473517.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.60519814491272,
|
|
"epoch": 0.39721421709894333,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989746148326508,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.17537111341953276,
|
|
"num_tokens": 9485660.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.52572922706604,
|
|
"epoch": 0.3976945244956772,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004989713429102805,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.17903834730386733,
|
|
"num_tokens": 9495983.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.47251706123352,
|
|
"epoch": 0.39817483189241115,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004989680657879607,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.17506579160690308,
|
|
"num_tokens": 9507438.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.406937599182129,
|
|
"epoch": 0.39865513928914503,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989647834657675,
|
|
"loss": 5.3427,
|
|
"mean_token_accuracy": 0.1858995169401169,
|
|
"num_tokens": 9517508.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.3676002502441404,
|
|
"epoch": 0.39913544668587897,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000498961495943777,
|
|
"loss": 5.3493,
|
|
"mean_token_accuracy": 0.18892575353384017,
|
|
"num_tokens": 9527641.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.528365707397461,
|
|
"epoch": 0.39961575408261285,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989582032220656,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.18333982080221176,
|
|
"num_tokens": 9538762.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.53466567993164,
|
|
"epoch": 0.4000960614793468,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989549053007096,
|
|
"loss": 5.5004,
|
|
"mean_token_accuracy": 0.17668719887733458,
|
|
"num_tokens": 9550246.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.489660739898682,
|
|
"epoch": 0.40057636887608067,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989516021797858,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.18076204359531403,
|
|
"num_tokens": 9562341.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.557612943649292,
|
|
"epoch": 0.4010566762728146,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000498948293859371,
|
|
"loss": 5.4992,
|
|
"mean_token_accuracy": 0.1803925946354866,
|
|
"num_tokens": 9574484.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.492554616928101,
|
|
"epoch": 0.4015369836695485,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004989449803395415,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.18405203372240067,
|
|
"num_tokens": 9585241.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.530519580841064,
|
|
"epoch": 0.4020172910662824,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004989416616203747,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.1819280803203583,
|
|
"num_tokens": 9598683.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.520482158660888,
|
|
"epoch": 0.4024975984630163,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004989383377019476,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.18044654726982118,
|
|
"num_tokens": 9610127.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.494972562789917,
|
|
"epoch": 0.40297790585975024,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004989350085843371,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.18540242165327073,
|
|
"num_tokens": 9620009.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.463833379745483,
|
|
"epoch": 0.4034582132564842,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004989316742676207,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.18554787784814836,
|
|
"num_tokens": 9632479.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.529710388183593,
|
|
"epoch": 0.40393852065321806,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989283347518757,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.18498131781816482,
|
|
"num_tokens": 9644447.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.508409833908081,
|
|
"epoch": 0.404418828049952,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004989249900371797,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.175240458548069,
|
|
"num_tokens": 9656886.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.514116859436035,
|
|
"epoch": 0.4048991354466859,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004989216401236103,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.18342093825340272,
|
|
"num_tokens": 9667079.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.546218204498291,
|
|
"epoch": 0.4053794428434198,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004989182850112455,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.18024542927742004,
|
|
"num_tokens": 9678237.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.479090642929077,
|
|
"epoch": 0.4058597502401537,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989149247001629,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.18879555612802507,
|
|
"num_tokens": 9688809.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.506127262115479,
|
|
"epoch": 0.40634005763688763,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004989115591904407,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.18512516021728515,
|
|
"num_tokens": 9700460.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.435467624664307,
|
|
"epoch": 0.4068203650336215,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989081884821569,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.17947154939174653,
|
|
"num_tokens": 9711379.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.446878910064697,
|
|
"epoch": 0.40730067243035545,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989048125753899,
|
|
"loss": 5.3581,
|
|
"mean_token_accuracy": 0.18849164247512817,
|
|
"num_tokens": 9722792.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.467892980575561,
|
|
"epoch": 0.40778097982708933,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000498901431470218,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.18827234208583832,
|
|
"num_tokens": 9733524.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.494660711288452,
|
|
"epoch": 0.40826128722382327,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004988980451667198,
|
|
"loss": 5.4705,
|
|
"mean_token_accuracy": 0.18629121035337448,
|
|
"num_tokens": 9745430.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.445364713668823,
|
|
"epoch": 0.40874159462055715,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004988946536649737,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.1829912081360817,
|
|
"num_tokens": 9756927.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.457226800918579,
|
|
"epoch": 0.4092219020172911,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004988912569650585,
|
|
"loss": 5.4165,
|
|
"mean_token_accuracy": 0.1858849585056305,
|
|
"num_tokens": 9768350.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.430975008010864,
|
|
"epoch": 0.40970220941402496,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004988878550670533,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.19087884128093718,
|
|
"num_tokens": 9779238.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.543310165405273,
|
|
"epoch": 0.4101825168107589,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004988844479710369,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.17559687942266464,
|
|
"num_tokens": 9789262.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.603669548034668,
|
|
"epoch": 0.4106628242074928,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988810356770884,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.1808350995182991,
|
|
"num_tokens": 9800909.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.541848754882812,
|
|
"epoch": 0.4111431316042267,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000498877618185287,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.18005858659744262,
|
|
"num_tokens": 9812538.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.481583595275879,
|
|
"epoch": 0.4116234390009606,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004988741954957121,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.18316709250211716,
|
|
"num_tokens": 9824071.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.616250133514404,
|
|
"epoch": 0.41210374639769454,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004988707676084432,
|
|
"loss": 5.5597,
|
|
"mean_token_accuracy": 0.17763041853904724,
|
|
"num_tokens": 9836713.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.45892858505249,
|
|
"epoch": 0.4125840537944284,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988673345235597,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.18704597353935243,
|
|
"num_tokens": 9847336.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.399388790130615,
|
|
"epoch": 0.41306436119116235,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004988638962411416,
|
|
"loss": 5.3885,
|
|
"mean_token_accuracy": 0.1803923949599266,
|
|
"num_tokens": 9858567.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.568233394622803,
|
|
"epoch": 0.41354466858789624,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004988604527612685,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.17673510760068895,
|
|
"num_tokens": 9869254.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.464548826217651,
|
|
"epoch": 0.4140249759846302,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004988570040840205,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.18541614562273026,
|
|
"num_tokens": 9879635.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.507536220550537,
|
|
"epoch": 0.41450528338136405,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004988535502094774,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.18638484328985214,
|
|
"num_tokens": 9891728.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.462026214599609,
|
|
"epoch": 0.414985590778098,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004988500911377198,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.19292479157447814,
|
|
"num_tokens": 9903140.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.489208745956421,
|
|
"epoch": 0.41546589817483187,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004988466268688276,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.18310181945562362,
|
|
"num_tokens": 9915562.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.399180269241333,
|
|
"epoch": 0.4159462055715658,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004988431574028814,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.17812881022691726,
|
|
"num_tokens": 9925720.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.475612354278565,
|
|
"epoch": 0.4164265129682997,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988396827399618,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.1799673169851303,
|
|
"num_tokens": 9936492.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.476762056350708,
|
|
"epoch": 0.4169068203650336,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004988362028801495,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.18283660858869552,
|
|
"num_tokens": 9948658.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.3699225902557375,
|
|
"epoch": 0.4173871277617675,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988327178235253,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.1888917088508606,
|
|
"num_tokens": 9959710.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.422818231582641,
|
|
"epoch": 0.41786743515850144,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004988292275701699,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.19038798660039902,
|
|
"num_tokens": 9970302.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.4733960151672365,
|
|
"epoch": 0.4183477425552353,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004988257321201646,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.18172130286693572,
|
|
"num_tokens": 9981776.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.54775071144104,
|
|
"epoch": 0.41882804995196926,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004988222314735902,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.17825412899255752,
|
|
"num_tokens": 9993471.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.511180019378662,
|
|
"epoch": 0.41930835734870314,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004988187256305284,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.18433743417263032,
|
|
"num_tokens": 10003818.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.520654535293579,
|
|
"epoch": 0.4197886647454371,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988152145910603,
|
|
"loss": 5.5325,
|
|
"mean_token_accuracy": 0.1697872295975685,
|
|
"num_tokens": 10015507.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.494216966629028,
|
|
"epoch": 0.420268972142171,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004988116983552675,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.18661011159420013,
|
|
"num_tokens": 10026994.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.556194162368774,
|
|
"epoch": 0.4207492795389049,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988081769232317,
|
|
"loss": 5.4865,
|
|
"mean_token_accuracy": 0.17480666041374207,
|
|
"num_tokens": 10039547.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.5414666652679445,
|
|
"epoch": 0.42122958693563883,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004988046502950346,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.17513879239559174,
|
|
"num_tokens": 10050568.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.501482439041138,
|
|
"epoch": 0.4217098943323727,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000498801118470758,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.1797420412302017,
|
|
"num_tokens": 10061780.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.416441011428833,
|
|
"epoch": 0.42219020172910665,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000498797581450484,
|
|
"loss": 5.3911,
|
|
"mean_token_accuracy": 0.18381205797195435,
|
|
"num_tokens": 10073101.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.427166414260864,
|
|
"epoch": 0.42267050912584053,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004987940392342948,
|
|
"loss": 5.3394,
|
|
"mean_token_accuracy": 0.19149589389562607,
|
|
"num_tokens": 10084397.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.497838401794434,
|
|
"epoch": 0.42315081652257447,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004987904918222726,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.1842352643609047,
|
|
"num_tokens": 10095635.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.48901333808899,
|
|
"epoch": 0.42363112391930835,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004987869392144996,
|
|
"loss": 5.4793,
|
|
"mean_token_accuracy": 0.1816812828183174,
|
|
"num_tokens": 10107744.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.496208906173706,
|
|
"epoch": 0.4241114313160423,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004987833814110584,
|
|
"loss": 5.3851,
|
|
"mean_token_accuracy": 0.1842407152056694,
|
|
"num_tokens": 10118552.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.532422399520874,
|
|
"epoch": 0.42459173871277617,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004987798184120316,
|
|
"loss": 5.5252,
|
|
"mean_token_accuracy": 0.17265765517950057,
|
|
"num_tokens": 10130813.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.524330091476441,
|
|
"epoch": 0.4250720461095101,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004987762502175018,
|
|
"loss": 5.547,
|
|
"mean_token_accuracy": 0.1797323852777481,
|
|
"num_tokens": 10142196.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.455458688735962,
|
|
"epoch": 0.425552353506244,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498772676827552,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.18626082092523574,
|
|
"num_tokens": 10155012.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.562879610061645,
|
|
"epoch": 0.4260326609029779,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004987690982422652,
|
|
"loss": 5.5231,
|
|
"mean_token_accuracy": 0.17669414579868317,
|
|
"num_tokens": 10166160.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.5610884666442875,
|
|
"epoch": 0.4265129682997118,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004987655144617243,
|
|
"loss": 5.3167,
|
|
"mean_token_accuracy": 0.1907524585723877,
|
|
"num_tokens": 10177663.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.389883518218994,
|
|
"epoch": 0.42699327569644574,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004987619254860126,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.18991009294986724,
|
|
"num_tokens": 10189127.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.544426345825196,
|
|
"epoch": 0.4274735830931796,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004987583313152134,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.17470676451921463,
|
|
"num_tokens": 10200765.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.571499347686768,
|
|
"epoch": 0.42795389048991356,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004987547319494104,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.18762336522340775,
|
|
"num_tokens": 10213047.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.486662864685059,
|
|
"epoch": 0.42843419788664744,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004987511273886867,
|
|
"loss": 5.3762,
|
|
"mean_token_accuracy": 0.18954455107450485,
|
|
"num_tokens": 10223790.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.417471694946289,
|
|
"epoch": 0.4289145052833814,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004987475176331263,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.18484554588794708,
|
|
"num_tokens": 10235077.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.510037088394165,
|
|
"epoch": 0.42939481268011526,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004987439026828129,
|
|
"loss": 5.4662,
|
|
"mean_token_accuracy": 0.16899558305740356,
|
|
"num_tokens": 10248844.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.493098974227905,
|
|
"epoch": 0.4298751200768492,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004987402825378305,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.19217505306005478,
|
|
"num_tokens": 10259013.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.4027419090271,
|
|
"epoch": 0.4303554274735831,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004987366571982631,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.1829615756869316,
|
|
"num_tokens": 10271415.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.373300838470459,
|
|
"epoch": 0.430835734870317,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004987330266641948,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.18090762794017792,
|
|
"num_tokens": 10283204.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.555873060226441,
|
|
"epoch": 0.4313160422670509,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004987293909357101,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.17647680789232253,
|
|
"num_tokens": 10294111.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.61440486907959,
|
|
"epoch": 0.43179634966378483,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004987257500128933,
|
|
"loss": 5.4548,
|
|
"mean_token_accuracy": 0.17417747229337693,
|
|
"num_tokens": 10305417.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.414704751968384,
|
|
"epoch": 0.4322766570605187,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004987221038958288,
|
|
"loss": 5.3509,
|
|
"mean_token_accuracy": 0.18823618143796922,
|
|
"num_tokens": 10316416.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.453503274917603,
|
|
"epoch": 0.43275696445725265,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004987184525846015,
|
|
"loss": 5.5101,
|
|
"mean_token_accuracy": 0.1855538010597229,
|
|
"num_tokens": 10328251.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.528881454467774,
|
|
"epoch": 0.4332372718539865,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004987147960792958,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.190151546895504,
|
|
"num_tokens": 10340189.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.532504892349243,
|
|
"epoch": 0.43371757925072046,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004987111343799971,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.18358281552791594,
|
|
"num_tokens": 10351660.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.500876617431641,
|
|
"epoch": 0.43419788664745435,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00049870746748679,
|
|
"loss": 5.4477,
|
|
"mean_token_accuracy": 0.18505928963422774,
|
|
"num_tokens": 10362240.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.549033355712891,
|
|
"epoch": 0.4346781940441883,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004987037953997598,
|
|
"loss": 5.4865,
|
|
"mean_token_accuracy": 0.18396148830652237,
|
|
"num_tokens": 10373646.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.519213771820068,
|
|
"epoch": 0.43515850144092216,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004987001181189918,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.1776837483048439,
|
|
"num_tokens": 10385540.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.514508628845215,
|
|
"epoch": 0.4356388088376561,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004986964356445713,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.17722374349832534,
|
|
"num_tokens": 10396641.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.542151689529419,
|
|
"epoch": 0.43611911623439004,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004986927479765837,
|
|
"loss": 5.4703,
|
|
"mean_token_accuracy": 0.17439449429512024,
|
|
"num_tokens": 10408165.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.431505870819092,
|
|
"epoch": 0.4365994236311239,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004986890551151148,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.18728436678647994,
|
|
"num_tokens": 10419646.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.512647581100464,
|
|
"epoch": 0.43707973102785785,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004986853570602503,
|
|
"loss": 5.4426,
|
|
"mean_token_accuracy": 0.17937116622924804,
|
|
"num_tokens": 10431051.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.559714508056641,
|
|
"epoch": 0.43756003842459174,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004986816538120758,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.1776018351316452,
|
|
"num_tokens": 10441833.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.498169469833374,
|
|
"epoch": 0.43804034582132567,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004986779453706778,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.18185556530952454,
|
|
"num_tokens": 10453544.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.486437511444092,
|
|
"epoch": 0.43852065321805955,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004986742317361419,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.1900118961930275,
|
|
"num_tokens": 10464140.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.3946116924285885,
|
|
"epoch": 0.4390009606147935,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004986705129085546,
|
|
"loss": 5.3682,
|
|
"mean_token_accuracy": 0.18866920918226243,
|
|
"num_tokens": 10475739.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.333141279220581,
|
|
"epoch": 0.43948126801152737,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004986667888880021,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.18941385596990584,
|
|
"num_tokens": 10487451.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.512581920623779,
|
|
"epoch": 0.4399615754082613,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004986630596745709,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.17348228245973588,
|
|
"num_tokens": 10499367.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.495959854125976,
|
|
"epoch": 0.4404418828049952,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986593252683477,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.19116291105747224,
|
|
"num_tokens": 10511192.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.356853771209717,
|
|
"epoch": 0.4409221902017291,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004986555856694191,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.18143054395914077,
|
|
"num_tokens": 10522754.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.471630573272705,
|
|
"epoch": 0.441402497598463,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004986518408778718,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.18229032605886458,
|
|
"num_tokens": 10533439.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.552867031097412,
|
|
"epoch": 0.44188280499519694,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986480908937929,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.1835053011775017,
|
|
"num_tokens": 10543654.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.414029836654663,
|
|
"epoch": 0.4423631123919308,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004986443357172695,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.18729309886693954,
|
|
"num_tokens": 10554936.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.4253771781921385,
|
|
"epoch": 0.44284341978866476,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004986405753483887,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.1833935260772705,
|
|
"num_tokens": 10566410.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.47337064743042,
|
|
"epoch": 0.44332372718539864,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004986368097872377,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.19434593766927719,
|
|
"num_tokens": 10577258.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.524574089050293,
|
|
"epoch": 0.4438040345821326,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004986330390339042,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.178845639526844,
|
|
"num_tokens": 10588783.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.466887617111206,
|
|
"epoch": 0.44428434197886646,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004986292630884755,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.18453073799610137,
|
|
"num_tokens": 10599778.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.5022495746612545,
|
|
"epoch": 0.4447646493756004,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004986254819510393,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.1926836684346199,
|
|
"num_tokens": 10611211.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.36075005531311,
|
|
"epoch": 0.4452449567723343,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004986216956216835,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.1826932579278946,
|
|
"num_tokens": 10624535.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.4547281742095945,
|
|
"epoch": 0.4457252641690682,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000498617904100496,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.1895545944571495,
|
|
"num_tokens": 10635206.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.505380582809448,
|
|
"epoch": 0.4462055715658021,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004986141073875646,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.19218022376298904,
|
|
"num_tokens": 10646993.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.473623847961425,
|
|
"epoch": 0.44668587896253603,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004986103054829779,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.18942495286464692,
|
|
"num_tokens": 10657262.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.44066014289856,
|
|
"epoch": 0.4471661863592699,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004986064983868237,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.18157739341259002,
|
|
"num_tokens": 10668962.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.504913854598999,
|
|
"epoch": 0.44764649375600385,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004986026860991906,
|
|
"loss": 5.408,
|
|
"mean_token_accuracy": 0.19493381828069686,
|
|
"num_tokens": 10680183.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.470511531829834,
|
|
"epoch": 0.44812680115273773,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004985988686201672,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.19322926551103592,
|
|
"num_tokens": 10691221.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.445162010192871,
|
|
"epoch": 0.44860710854947167,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004985950459498419,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.185987688601017,
|
|
"num_tokens": 10703462.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.462856149673462,
|
|
"epoch": 0.44908741594620555,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004985912180883037,
|
|
"loss": 5.3566,
|
|
"mean_token_accuracy": 0.1904120072722435,
|
|
"num_tokens": 10713774.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.575588703155518,
|
|
"epoch": 0.4495677233429395,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004985873850356411,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.17069013193249702,
|
|
"num_tokens": 10725109.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.450364017486573,
|
|
"epoch": 0.45004803073967337,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004985835467919436,
|
|
"loss": 5.3791,
|
|
"mean_token_accuracy": 0.1900913417339325,
|
|
"num_tokens": 10735695.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.5042625904083256,
|
|
"epoch": 0.4505283381364073,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004985797033572999,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.18182757198810579,
|
|
"num_tokens": 10747554.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.534461879730225,
|
|
"epoch": 0.4510086455331412,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004985758547317994,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.18399068862199783,
|
|
"num_tokens": 10759175.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.468274736404419,
|
|
"epoch": 0.4514889529298751,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004985720009155315,
|
|
"loss": 5.3448,
|
|
"mean_token_accuracy": 0.18884512335062026,
|
|
"num_tokens": 10770365.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.475963687896728,
|
|
"epoch": 0.45196926032660906,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004985681419085856,
|
|
"loss": 5.4411,
|
|
"mean_token_accuracy": 0.178588305413723,
|
|
"num_tokens": 10783096.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.567919683456421,
|
|
"epoch": 0.45244956772334294,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004985642777110513,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.17430274039506913,
|
|
"num_tokens": 10795312.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.490743017196655,
|
|
"epoch": 0.4529298751200769,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004985604083230183,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.1856426477432251,
|
|
"num_tokens": 10806451.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.524587106704712,
|
|
"epoch": 0.45341018251681076,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004985565337445765,
|
|
"loss": 5.5086,
|
|
"mean_token_accuracy": 0.18065753430128098,
|
|
"num_tokens": 10818185.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.481802463531494,
|
|
"epoch": 0.4538904899135447,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004985526539758158,
|
|
"loss": 5.37,
|
|
"mean_token_accuracy": 0.18981760442256929,
|
|
"num_tokens": 10830203.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.455829095840454,
|
|
"epoch": 0.4543707973102786,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004985487690168263,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.17300689220428467,
|
|
"num_tokens": 10842953.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.5628132820129395,
|
|
"epoch": 0.4548511047070125,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000498544878867698,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.17378109693527222,
|
|
"num_tokens": 10853322.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.536968040466308,
|
|
"epoch": 0.4553314121037464,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985409835285215,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.17889120429754257,
|
|
"num_tokens": 10865480.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.435639333724976,
|
|
"epoch": 0.45581171950048033,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004985370829993873,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.19336266964673995,
|
|
"num_tokens": 10875700.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.419657135009766,
|
|
"epoch": 0.4562920268972142,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004985331772803857,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.1836688607931137,
|
|
"num_tokens": 10887350.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.450266981124878,
|
|
"epoch": 0.45677233429394815,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985292663716074,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.18904644697904588,
|
|
"num_tokens": 10899355.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.427554178237915,
|
|
"epoch": 0.457252641690682,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004985253502731435,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.18772731721401215,
|
|
"num_tokens": 10911521.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.424086999893189,
|
|
"epoch": 0.45773294908741596,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004985214289850845,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.1889353096485138,
|
|
"num_tokens": 10923363.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.470712327957154,
|
|
"epoch": 0.45821325648414984,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004985175025075217,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.1832897409796715,
|
|
"num_tokens": 10934965.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.458177661895752,
|
|
"epoch": 0.4586935638808838,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004985135708405462,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.17735306471586226,
|
|
"num_tokens": 10946126.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.489032363891601,
|
|
"epoch": 0.45917387127761766,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004985096339842493,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.17940519899129867,
|
|
"num_tokens": 10957667.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.597390937805176,
|
|
"epoch": 0.4596541786743516,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004985056919387224,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.17519876211881638,
|
|
"num_tokens": 10969999.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.3790318965911865,
|
|
"epoch": 0.4601344860710855,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004985017447040569,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.19265517294406892,
|
|
"num_tokens": 10980672.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.436908149719239,
|
|
"epoch": 0.4606147934678194,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004984977922803447,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.18623633831739425,
|
|
"num_tokens": 10991471.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.489195775985718,
|
|
"epoch": 0.4610951008645533,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004984938346676772,
|
|
"loss": 5.4822,
|
|
"mean_token_accuracy": 0.18003522753715515,
|
|
"num_tokens": 11001960.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.520635604858398,
|
|
"epoch": 0.46157540826128723,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984898718661468,
|
|
"loss": 5.3385,
|
|
"mean_token_accuracy": 0.1887583240866661,
|
|
"num_tokens": 11013274.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.454546737670898,
|
|
"epoch": 0.4620557156580211,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004984859038758451,
|
|
"loss": 5.3459,
|
|
"mean_token_accuracy": 0.195092011988163,
|
|
"num_tokens": 11024635.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.409391307830811,
|
|
"epoch": 0.46253602305475505,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004984819306968642,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.18462751805782318,
|
|
"num_tokens": 11036317.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.492571496963501,
|
|
"epoch": 0.46301633045148893,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004984779523292966,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.1878635674715042,
|
|
"num_tokens": 11047776.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.451682281494141,
|
|
"epoch": 0.46349663784822287,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004984739687732345,
|
|
"loss": 5.4143,
|
|
"mean_token_accuracy": 0.18734978139400482,
|
|
"num_tokens": 11058746.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.479636383056641,
|
|
"epoch": 0.46397694524495675,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004984699800287705,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.18848110288381575,
|
|
"num_tokens": 11068892.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.451904296875,
|
|
"epoch": 0.4644572526416907,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000498465986095997,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.18504210859537124,
|
|
"num_tokens": 11080038.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.445950746536255,
|
|
"epoch": 0.46493756003842457,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004984619869750069,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.1845824599266052,
|
|
"num_tokens": 11091261.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.3959002017974855,
|
|
"epoch": 0.4654178674351585,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498457982665893,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.19228337705135345,
|
|
"num_tokens": 11103015.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.444662761688233,
|
|
"epoch": 0.4658981748318924,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004984539731687483,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.19602457731962203,
|
|
"num_tokens": 11115075.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.461604499816895,
|
|
"epoch": 0.4663784822286263,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004984499584836659,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.1870917484164238,
|
|
"num_tokens": 11125937.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.425907611846924,
|
|
"epoch": 0.4668587896253602,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000498445938610739,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.1811567708849907,
|
|
"num_tokens": 11136863.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.509153938293457,
|
|
"epoch": 0.46733909702209414,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004984419135500608,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.18005056977272033,
|
|
"num_tokens": 11149934.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.434760904312133,
|
|
"epoch": 0.4678194044188281,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984378833017249,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.18313904404640197,
|
|
"num_tokens": 11162208.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.437519550323486,
|
|
"epoch": 0.46829971181556196,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004984338478658248,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.1863478258252144,
|
|
"num_tokens": 11172892.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.48405089378357,
|
|
"epoch": 0.4687800192122959,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004984298072424542,
|
|
"loss": 5.3743,
|
|
"mean_token_accuracy": 0.19089971333742142,
|
|
"num_tokens": 11184339.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.48475399017334,
|
|
"epoch": 0.4692603266090298,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000498425761431707,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.18189417570829391,
|
|
"num_tokens": 11195681.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.503478860855102,
|
|
"epoch": 0.4697406340057637,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000498421710433677,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.17995550185441972,
|
|
"num_tokens": 11207982.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.480038022994995,
|
|
"epoch": 0.4702209414024976,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004984176542484584,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.18344718217849731,
|
|
"num_tokens": 11218901.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.442627573013306,
|
|
"epoch": 0.47070124879923153,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004984135928761452,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.18672479391098024,
|
|
"num_tokens": 11230764.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.4512451648712155,
|
|
"epoch": 0.4711815561959654,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004984095263168317,
|
|
"loss": 5.3338,
|
|
"mean_token_accuracy": 0.18761596381664275,
|
|
"num_tokens": 11241489.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.341250276565551,
|
|
"epoch": 0.47166186359269935,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004984054545706124,
|
|
"loss": 5.3221,
|
|
"mean_token_accuracy": 0.19300410151481628,
|
|
"num_tokens": 11254500.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.531213903427124,
|
|
"epoch": 0.47214217098943323,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000498401377637582,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.18692879676818847,
|
|
"num_tokens": 11266235.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.517435598373413,
|
|
"epoch": 0.47262247838616717,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000498397295517835,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.19072997123003005,
|
|
"num_tokens": 11277471.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.325749921798706,
|
|
"epoch": 0.47310278578290105,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004983932082114659,
|
|
"loss": 5.3297,
|
|
"mean_token_accuracy": 0.1865825429558754,
|
|
"num_tokens": 11290501.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.427298593521118,
|
|
"epoch": 0.473583093179635,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004983891157185699,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.1869247242808342,
|
|
"num_tokens": 11301933.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.552150440216065,
|
|
"epoch": 0.47406340057636887,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004983850180392421,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.18141084909439087,
|
|
"num_tokens": 11314539.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.398589944839477,
|
|
"epoch": 0.4745437079731028,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004983809151735775,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.1900244951248169,
|
|
"num_tokens": 11326641.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.445167350769043,
|
|
"epoch": 0.4750240153698367,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004983768071216713,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.1810634598135948,
|
|
"num_tokens": 11337214.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.495223093032837,
|
|
"epoch": 0.4755043227665706,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004983726938836189,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.18667189180850982,
|
|
"num_tokens": 11349540.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.492793083190918,
|
|
"epoch": 0.4759846301633045,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004983685754595159,
|
|
"loss": 5.3723,
|
|
"mean_token_accuracy": 0.18532039523124694,
|
|
"num_tokens": 11359817.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.462947273254395,
|
|
"epoch": 0.47646493756003844,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004983644518494578,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.1787272647023201,
|
|
"num_tokens": 11371120.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.430369329452515,
|
|
"epoch": 0.4769452449567723,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004983603230535403,
|
|
"loss": 5.4297,
|
|
"mean_token_accuracy": 0.17996030002832414,
|
|
"num_tokens": 11382071.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.5358741760253904,
|
|
"epoch": 0.47742555235350626,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004983561890718594,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.1795857608318329,
|
|
"num_tokens": 11392938.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.482577991485596,
|
|
"epoch": 0.47790585975024014,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498352049904511,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.18274903744459153,
|
|
"num_tokens": 11405416.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.488064527511597,
|
|
"epoch": 0.4783861671469741,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004983479055515914,
|
|
"loss": 5.4351,
|
|
"mean_token_accuracy": 0.18943743258714676,
|
|
"num_tokens": 11417008.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.544620180130005,
|
|
"epoch": 0.47886647454370795,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004983437560131964,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.1895648792386055,
|
|
"num_tokens": 11428154.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.487364006042481,
|
|
"epoch": 0.4793467819404419,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004983396012894228,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.18201917707920073,
|
|
"num_tokens": 11438559.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.533839893341065,
|
|
"epoch": 0.47982708933717577,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004983354413803666,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.18239017128944396,
|
|
"num_tokens": 11449501.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.43055911064148,
|
|
"epoch": 0.4803073967339097,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004983312762861248,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.17930015325546264,
|
|
"num_tokens": 11461841.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.444394779205322,
|
|
"epoch": 0.4807877041306436,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004983271060067939,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.18473062217235564,
|
|
"num_tokens": 11472876.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.47320032119751,
|
|
"epoch": 0.4812680115273775,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004983229305424707,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.18353282213211058,
|
|
"num_tokens": 11484541.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.386233186721801,
|
|
"epoch": 0.4817483189241114,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004983187498932522,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.18736893236637114,
|
|
"num_tokens": 11496071.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.441421842575073,
|
|
"epoch": 0.48222862632084534,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004983145640592354,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.1883857563138008,
|
|
"num_tokens": 11507574.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.440950775146485,
|
|
"epoch": 0.4827089337175792,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004983103730405176,
|
|
"loss": 5.4095,
|
|
"mean_token_accuracy": 0.18637361377477646,
|
|
"num_tokens": 11519738.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.465356111526489,
|
|
"epoch": 0.48318924111431316,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000498306176837196,
|
|
"loss": 5.4131,
|
|
"mean_token_accuracy": 0.1857826292514801,
|
|
"num_tokens": 11530669.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.364138412475586,
|
|
"epoch": 0.48366954851104704,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004983019754493681,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.1915925696492195,
|
|
"num_tokens": 11541680.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.434883451461792,
|
|
"epoch": 0.484149855907781,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004982977688771314,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.18698243647813798,
|
|
"num_tokens": 11553204.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.494551324844361,
|
|
"epoch": 0.4846301633045149,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004982935571205835,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.17969363927841187,
|
|
"num_tokens": 11564841.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.432051181793213,
|
|
"epoch": 0.4851104707012488,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004982893401798223,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.18372393250465394,
|
|
"num_tokens": 11576723.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.507033395767212,
|
|
"epoch": 0.48559077809798273,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004982851180549456,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.18664456009864808,
|
|
"num_tokens": 11587727.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.383077955245971,
|
|
"epoch": 0.4860710854947166,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004982808907460515,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.1817546159029007,
|
|
"num_tokens": 11598508.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.344477891921997,
|
|
"epoch": 0.48655139289145055,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004982766582532382,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.19086076617240905,
|
|
"num_tokens": 11609684.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.481044912338257,
|
|
"epoch": 0.48703170028818443,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004982724205766038,
|
|
"loss": 5.4351,
|
|
"mean_token_accuracy": 0.17675031274557113,
|
|
"num_tokens": 11621642.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.466136455535889,
|
|
"epoch": 0.48751200768491837,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004982681777162468,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.18459942936897278,
|
|
"num_tokens": 11632778.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.385703611373901,
|
|
"epoch": 0.48799231508165225,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004982639296722657,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.19703588932752608,
|
|
"num_tokens": 11643581.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.552964448928833,
|
|
"epoch": 0.4884726224783862,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004982596764447591,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.17867382615804672,
|
|
"num_tokens": 11656126.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.5898202419281,
|
|
"epoch": 0.48895292987512007,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004982554180338258,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.1850968047976494,
|
|
"num_tokens": 11667765.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.511855411529541,
|
|
"epoch": 0.489433237271854,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004982511544395646,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.17825420945882797,
|
|
"num_tokens": 11679268.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.415318298339844,
|
|
"epoch": 0.4899135446685879,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004982468856620745,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.1884788230061531,
|
|
"num_tokens": 11690049.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.434323644638061,
|
|
"epoch": 0.4903938520653218,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004982426117014545,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.1916387513279915,
|
|
"num_tokens": 11701782.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.389872455596924,
|
|
"epoch": 0.4908741594620557,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004982383325578041,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.1935378208756447,
|
|
"num_tokens": 11712488.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.478123521804809,
|
|
"epoch": 0.49135446685878964,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004982340482312226,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.18805212676525115,
|
|
"num_tokens": 11724036.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.4282684326171875,
|
|
"epoch": 0.4918347742555235,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004982297587218092,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.18427670001983643,
|
|
"num_tokens": 11736461.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.36871337890625,
|
|
"epoch": 0.49231508165225746,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004982254640296637,
|
|
"loss": 5.3203,
|
|
"mean_token_accuracy": 0.18877253979444503,
|
|
"num_tokens": 11747549.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.520420217514038,
|
|
"epoch": 0.49279538904899134,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004982211641548857,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.1765229657292366,
|
|
"num_tokens": 11759012.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.555425024032592,
|
|
"epoch": 0.4932756964457253,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004982168590975752,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.18458688855171204,
|
|
"num_tokens": 11770535.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.475128078460694,
|
|
"epoch": 0.49375600384245916,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004982125488578321,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.18305824548006058,
|
|
"num_tokens": 11783708.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.444312715530396,
|
|
"epoch": 0.4942363112391931,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004982082334357563,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.18637588024139404,
|
|
"num_tokens": 11794565.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.5029500961303714,
|
|
"epoch": 0.494716618635927,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004982039128314481,
|
|
"loss": 5.3979,
|
|
"mean_token_accuracy": 0.18649012595415115,
|
|
"num_tokens": 11805631.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.515172100067138,
|
|
"epoch": 0.4951969260326609,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004981995870450079,
|
|
"loss": 5.4343,
|
|
"mean_token_accuracy": 0.18024242222309111,
|
|
"num_tokens": 11817041.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.471421098709106,
|
|
"epoch": 0.4956772334293948,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004981952560765361,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.1874469444155693,
|
|
"num_tokens": 11829090.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.560026025772094,
|
|
"epoch": 0.49615754082612873,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004981909199261331,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.17861385643482208,
|
|
"num_tokens": 11839980.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.473791790008545,
|
|
"epoch": 0.4966378482228626,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004981865785938998,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.18403689414262772,
|
|
"num_tokens": 11851217.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.435330820083618,
|
|
"epoch": 0.49711815561959655,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004981822320799367,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.1848284050822258,
|
|
"num_tokens": 11862506.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.511408042907715,
|
|
"epoch": 0.49759846301633043,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004981778803843449,
|
|
"loss": 5.4551,
|
|
"mean_token_accuracy": 0.17914380580186845,
|
|
"num_tokens": 11874844.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.420107173919678,
|
|
"epoch": 0.49807877041306436,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004981735235072256,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.19396358132362365,
|
|
"num_tokens": 11885231.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.479499053955078,
|
|
"epoch": 0.49855907780979825,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004981691614486796,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.18174998164176942,
|
|
"num_tokens": 11897222.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.432892322540283,
|
|
"epoch": 0.4990393852065322,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004981647942088084,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.18804378658533097,
|
|
"num_tokens": 11909493.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.518645811080932,
|
|
"epoch": 0.49951969260326606,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004981604217877135,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.18577739745378494,
|
|
"num_tokens": 11920833.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.396304130554199,
|
|
"epoch": 0.5,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000498156044185496,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.19440183341503142,
|
|
"num_tokens": 11932910.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.468098115921021,
|
|
"epoch": 0.5004803073967339,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004981516614022579,
|
|
"loss": 5.3945,
|
|
"mean_token_accuracy": 0.19133666008710862,
|
|
"num_tokens": 11944536.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.420602512359619,
|
|
"epoch": 0.5009606147934679,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004981472734381008,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.1924171507358551,
|
|
"num_tokens": 11955724.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.436355924606323,
|
|
"epoch": 0.5014409221902018,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004981428802931267,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.18886628448963166,
|
|
"num_tokens": 11965921.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.398175191879273,
|
|
"epoch": 0.5019212295869356,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004981384819674375,
|
|
"loss": 5.3237,
|
|
"mean_token_accuracy": 0.19049944132566451,
|
|
"num_tokens": 11976356.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.450118923187256,
|
|
"epoch": 0.5024015369836695,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004981340784611354,
|
|
"loss": 5.382,
|
|
"mean_token_accuracy": 0.18158023357391356,
|
|
"num_tokens": 11987959.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.474130916595459,
|
|
"epoch": 0.5028818443804035,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004981296697743224,
|
|
"loss": 5.3966,
|
|
"mean_token_accuracy": 0.18466383665800096,
|
|
"num_tokens": 12000089.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.477195882797242,
|
|
"epoch": 0.5033621517771374,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004981252559071012,
|
|
"loss": 5.4641,
|
|
"mean_token_accuracy": 0.18619239926338196,
|
|
"num_tokens": 12011286.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.401328229904175,
|
|
"epoch": 0.5038424591738713,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004981208368595739,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.18776115477085115,
|
|
"num_tokens": 12022809.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.441013193130493,
|
|
"epoch": 0.5043227665706052,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004981164126318435,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.1900719553232193,
|
|
"num_tokens": 12034311.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.412341165542602,
|
|
"epoch": 0.5048030739673391,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004981119832240124,
|
|
"loss": 5.3303,
|
|
"mean_token_accuracy": 0.19273549765348436,
|
|
"num_tokens": 12046405.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.427926826477051,
|
|
"epoch": 0.505283381364073,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004981075486361837,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.18678055107593536,
|
|
"num_tokens": 12059022.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.438950443267823,
|
|
"epoch": 0.5057636887608069,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004981031088684601,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.1849857747554779,
|
|
"num_tokens": 12070666.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.455779361724853,
|
|
"epoch": 0.5062439961575408,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004980986639209448,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.18551258444786073,
|
|
"num_tokens": 12082702.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.457168388366699,
|
|
"epoch": 0.5067243035542748,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000498094213793741,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.18254365026950836,
|
|
"num_tokens": 12094034.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.502580165863037,
|
|
"epoch": 0.5072046109510087,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000498089758486952,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.17486527115106582,
|
|
"num_tokens": 12104597.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.479168128967285,
|
|
"epoch": 0.5076849183477425,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004980852980006812,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.18257687538862227,
|
|
"num_tokens": 12116577.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.413305711746216,
|
|
"epoch": 0.5081652257444764,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004980808323350323,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.18752931505441667,
|
|
"num_tokens": 12128005.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.475668621063233,
|
|
"epoch": 0.5086455331412104,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004980763614901089,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.18278273642063142,
|
|
"num_tokens": 12138591.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.431951951980591,
|
|
"epoch": 0.5091258405379443,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004980718854660146,
|
|
"loss": 5.4224,
|
|
"mean_token_accuracy": 0.18703065663576127,
|
|
"num_tokens": 12150010.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.493814706802368,
|
|
"epoch": 0.5096061479346782,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004980674042628537,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.17938946783542634,
|
|
"num_tokens": 12161268.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.451682090759277,
|
|
"epoch": 0.5100864553314121,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00049806291788073,
|
|
"loss": 5.345,
|
|
"mean_token_accuracy": 0.1900179147720337,
|
|
"num_tokens": 12172647.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.397039413452148,
|
|
"epoch": 0.510566762728146,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004980584263197477,
|
|
"loss": 5.4469,
|
|
"mean_token_accuracy": 0.1861713707447052,
|
|
"num_tokens": 12183521.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.595460653305054,
|
|
"epoch": 0.5110470701248799,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004980539295800111,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.177712544798851,
|
|
"num_tokens": 12193616.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.457161283493042,
|
|
"epoch": 0.5115273775216138,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004980494276616246,
|
|
"loss": 5.3989,
|
|
"mean_token_accuracy": 0.18704742044210435,
|
|
"num_tokens": 12204817.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.471468687057495,
|
|
"epoch": 0.5120076849183477,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004980449205646926,
|
|
"loss": 5.4626,
|
|
"mean_token_accuracy": 0.17779629975557326,
|
|
"num_tokens": 12217281.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.4687206745147705,
|
|
"epoch": 0.5124879923150817,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00049804040828932,
|
|
"loss": 5.3687,
|
|
"mean_token_accuracy": 0.1845517635345459,
|
|
"num_tokens": 12228705.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.50502576828003,
|
|
"epoch": 0.5129682997118156,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004980358908356113,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.17887165397405624,
|
|
"num_tokens": 12240010.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.492001867294311,
|
|
"epoch": 0.5134486071085494,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004980313682036717,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.17649380415678023,
|
|
"num_tokens": 12251384.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.450707054138183,
|
|
"epoch": 0.5139289145052833,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004980268403936058,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.18193223625421523,
|
|
"num_tokens": 12262548.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.434090042114258,
|
|
"epoch": 0.5144092219020173,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004980223074055189,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.19134428352117538,
|
|
"num_tokens": 12274022.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.3991340637207035,
|
|
"epoch": 0.5148895292987512,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004980177692395164,
|
|
"loss": 5.2867,
|
|
"mean_token_accuracy": 0.18951193541288375,
|
|
"num_tokens": 12285000.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.338136863708496,
|
|
"epoch": 0.5153698366954851,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004980132258957035,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.19007130116224288,
|
|
"num_tokens": 12297472.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.503325796127319,
|
|
"epoch": 0.515850144092219,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004980086773741856,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.18749501258134843,
|
|
"num_tokens": 12309310.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.525248384475708,
|
|
"epoch": 0.516330451488953,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004980041236750685,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.18202975690364837,
|
|
"num_tokens": 12321897.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.373438596725464,
|
|
"epoch": 0.5168107588856868,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004979995647984577,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.19803487062454223,
|
|
"num_tokens": 12333484.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.407309484481812,
|
|
"epoch": 0.5172910662824207,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004979950007444593,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.18875620067119597,
|
|
"num_tokens": 12345154.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.531070184707642,
|
|
"epoch": 0.5177713736791547,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004979904315131792,
|
|
"loss": 5.3985,
|
|
"mean_token_accuracy": 0.18682202696800232,
|
|
"num_tokens": 12354934.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.580181455612182,
|
|
"epoch": 0.5182516810758886,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004979858571047233,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.17747551798820496,
|
|
"num_tokens": 12367729.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.537011623382568,
|
|
"epoch": 0.5187319884726225,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004979812775191979,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.18911508321762086,
|
|
"num_tokens": 12380366.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.4212806224823,
|
|
"epoch": 0.5192122958693564,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004979766927567094,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.185391803085804,
|
|
"num_tokens": 12392338.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.411877775192261,
|
|
"epoch": 0.5196926032660903,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004979721028173643,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.19052527099847794,
|
|
"num_tokens": 12403280.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.428349351882934,
|
|
"epoch": 0.5201729106628242,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000497967507701269,
|
|
"loss": 5.339,
|
|
"mean_token_accuracy": 0.19180969446897506,
|
|
"num_tokens": 12414279.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.369792318344116,
|
|
"epoch": 0.5206532180595581,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004979629074085303,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.19326327443122865,
|
|
"num_tokens": 12425486.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.429877424240113,
|
|
"epoch": 0.521133525456292,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004979583019392548,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.18277973234653472,
|
|
"num_tokens": 12437295.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.488057661056518,
|
|
"epoch": 0.521613832853026,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004979536912935497,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.19044878631830214,
|
|
"num_tokens": 12448684.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.416075134277344,
|
|
"epoch": 0.5220941402497599,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000497949075471522,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.1959683492779732,
|
|
"num_tokens": 12461209.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.439440536499023,
|
|
"epoch": 0.5225744476464937,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004979444544732786,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.18593170940876008,
|
|
"num_tokens": 12472863.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.487802410125733,
|
|
"epoch": 0.5230547550432276,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000497939828298927,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.18451804667711258,
|
|
"num_tokens": 12483510.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.566813945770264,
|
|
"epoch": 0.5235350624399616,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004979351969485747,
|
|
"loss": 5.4393,
|
|
"mean_token_accuracy": 0.1832005724310875,
|
|
"num_tokens": 12495532.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.328968048095703,
|
|
"epoch": 0.5240153698366955,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004979305604223291,
|
|
"loss": 5.3321,
|
|
"mean_token_accuracy": 0.18730416595935823,
|
|
"num_tokens": 12508413.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.472768878936767,
|
|
"epoch": 0.5244956772334294,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004979259187202978,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.18066055029630662,
|
|
"num_tokens": 12520705.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.515762042999268,
|
|
"epoch": 0.5249759846301633,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004979212718425887,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.1898324728012085,
|
|
"num_tokens": 12531560.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.4374120235443115,
|
|
"epoch": 0.5254562920268973,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004979166197893096,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.1806342676281929,
|
|
"num_tokens": 12542539.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.494349431991577,
|
|
"epoch": 0.5259365994236311,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004979119625605683,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.17977063953876496,
|
|
"num_tokens": 12555228.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.515709638595581,
|
|
"epoch": 0.526416906820365,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004979073001564734,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.19102157950401305,
|
|
"num_tokens": 12565715.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.459074687957764,
|
|
"epoch": 0.5268972142170989,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004979026325771328,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.18871578127145766,
|
|
"num_tokens": 12576896.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.411230421066284,
|
|
"epoch": 0.5273775216138329,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004978979598226549,
|
|
"loss": 5.3653,
|
|
"mean_token_accuracy": 0.1876650035381317,
|
|
"num_tokens": 12588117.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.381819152832032,
|
|
"epoch": 0.5278578290105668,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004978932818931483,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.18598207086324692,
|
|
"num_tokens": 12599987.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.484870481491089,
|
|
"epoch": 0.5283381364073007,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004978885987887216,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.18079727739095688,
|
|
"num_tokens": 12611453.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.549768304824829,
|
|
"epoch": 0.5288184438040345,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004978839105094833,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.1803484871983528,
|
|
"num_tokens": 12623068.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.487051725387573,
|
|
"epoch": 0.5292987512007685,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004978792170555426,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.18667725324630738,
|
|
"num_tokens": 12634952.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.45725793838501,
|
|
"epoch": 0.5297790585975024,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004978745184270083,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.18108554929494858,
|
|
"num_tokens": 12647027.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.370086240768432,
|
|
"epoch": 0.5302593659942363,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004978698146239893,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.19929148703813554,
|
|
"num_tokens": 12657249.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.405987405776978,
|
|
"epoch": 0.5307396733909702,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004978651056465952,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.19359083771705626,
|
|
"num_tokens": 12666714.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.4099356174469,
|
|
"epoch": 0.5312199807877042,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000497860391494935,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.18576207011938095,
|
|
"num_tokens": 12678627.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.4683794498443605,
|
|
"epoch": 0.531700288184438,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004978556721691183,
|
|
"loss": 5.4143,
|
|
"mean_token_accuracy": 0.18748129159212112,
|
|
"num_tokens": 12691009.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.4890233993530275,
|
|
"epoch": 0.5321805955811719,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004978509476692547,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.1840150013566017,
|
|
"num_tokens": 12702503.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.5058454990386965,
|
|
"epoch": 0.5326609029779059,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004978462179954538,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.1805101990699768,
|
|
"num_tokens": 12714018.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.499725580215454,
|
|
"epoch": 0.5331412103746398,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004978414831478253,
|
|
"loss": 5.5094,
|
|
"mean_token_accuracy": 0.18239614218473435,
|
|
"num_tokens": 12726726.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.421793651580811,
|
|
"epoch": 0.5336215177713737,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004978367431264794,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.18756531327962875,
|
|
"num_tokens": 12737790.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.4131616115570065,
|
|
"epoch": 0.5341018251681076,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004978319979315261,
|
|
"loss": 5.255,
|
|
"mean_token_accuracy": 0.19221504777669907,
|
|
"num_tokens": 12749473.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.403030204772949,
|
|
"epoch": 0.5345821325648416,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004978272475630752,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.18725448250770568,
|
|
"num_tokens": 12762220.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.306041097640991,
|
|
"epoch": 0.5350624399615754,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004978224920212374,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.19876040071249007,
|
|
"num_tokens": 12772788.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.314635419845581,
|
|
"epoch": 0.5355427473583093,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004978177313061232,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.18902058899402618,
|
|
"num_tokens": 12784552.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.4929139614105225,
|
|
"epoch": 0.5360230547550432,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004978129654178426,
|
|
"loss": 5.3497,
|
|
"mean_token_accuracy": 0.19190627783536912,
|
|
"num_tokens": 12797618.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.396257305145264,
|
|
"epoch": 0.5365033621517772,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004978081943565067,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.18863389194011687,
|
|
"num_tokens": 12807789.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.415760183334351,
|
|
"epoch": 0.5369836695485111,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004978034181222261,
|
|
"loss": 5.4194,
|
|
"mean_token_accuracy": 0.18857093751430512,
|
|
"num_tokens": 12819020.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.4485376358032225,
|
|
"epoch": 0.537463976945245,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977986367151119,
|
|
"loss": 5.3736,
|
|
"mean_token_accuracy": 0.18792831897735596,
|
|
"num_tokens": 12829527.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.476880073547363,
|
|
"epoch": 0.5379442843419788,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977938501352747,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.18210554718971253,
|
|
"num_tokens": 12840821.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.4507091522216795,
|
|
"epoch": 0.5384245917387128,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004977890583828259,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.1881468653678894,
|
|
"num_tokens": 12853314.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.414139366149902,
|
|
"epoch": 0.5389048991354467,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004977842614578768,
|
|
"loss": 5.349,
|
|
"mean_token_accuracy": 0.18417798578739167,
|
|
"num_tokens": 12863507.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.472694253921508,
|
|
"epoch": 0.5393852065321806,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004977794593605386,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.18529417961835862,
|
|
"num_tokens": 12874142.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.480929613113403,
|
|
"epoch": 0.5398655139289145,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000497774652090923,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.19421031028032304,
|
|
"num_tokens": 12884548.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.420640277862549,
|
|
"epoch": 0.5403458213256485,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004977698396491414,
|
|
"loss": 5.3841,
|
|
"mean_token_accuracy": 0.1893293485045433,
|
|
"num_tokens": 12895562.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.396530723571777,
|
|
"epoch": 0.5408261287223823,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977650220353055,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.195559298992157,
|
|
"num_tokens": 12905308.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.4512217998504635,
|
|
"epoch": 0.5413064361191162,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004977601992495274,
|
|
"loss": 5.3962,
|
|
"mean_token_accuracy": 0.18294627964496613,
|
|
"num_tokens": 12916731.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.576397562026978,
|
|
"epoch": 0.5417867435158501,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004977553712919189,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.18038235157728194,
|
|
"num_tokens": 12927609.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.500153350830078,
|
|
"epoch": 0.5422670509125841,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004977505381625921,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.1856964871287346,
|
|
"num_tokens": 12939445.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.358836555480957,
|
|
"epoch": 0.542747358309318,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004977456998616593,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.18769825100898743,
|
|
"num_tokens": 12951638.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.491495943069458,
|
|
"epoch": 0.5432276657060519,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977408563892327,
|
|
"loss": 5.3537,
|
|
"mean_token_accuracy": 0.1883303478360176,
|
|
"num_tokens": 12963157.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.459182405471802,
|
|
"epoch": 0.5437079731027857,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004977360077454249,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.1848008930683136,
|
|
"num_tokens": 12974187.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.447499179840088,
|
|
"epoch": 0.5441882804995197,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004977311539303483,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.1852130800485611,
|
|
"num_tokens": 12986612.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.509026002883911,
|
|
"epoch": 0.5446685878962536,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004977262949441158,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.1818256512284279,
|
|
"num_tokens": 12998343.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.432409858703613,
|
|
"epoch": 0.5451488952929875,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004977214307868399,
|
|
"loss": 5.3914,
|
|
"mean_token_accuracy": 0.18320675790309907,
|
|
"num_tokens": 13009272.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.472721290588379,
|
|
"epoch": 0.5456292026897214,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000497716561458634,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.19270115345716476,
|
|
"num_tokens": 13019961.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.409308815002442,
|
|
"epoch": 0.5461095100864554,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977116869596107,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.19604558497667313,
|
|
"num_tokens": 13030827.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.545911836624145,
|
|
"epoch": 0.5465898174831892,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004977068072898834,
|
|
"loss": 5.5615,
|
|
"mean_token_accuracy": 0.174258317053318,
|
|
"num_tokens": 13043702.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.371285057067871,
|
|
"epoch": 0.5470701248799231,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004977019224495652,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.20260500013828278,
|
|
"num_tokens": 13054474.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.458423662185669,
|
|
"epoch": 0.547550432276657,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004976970324387698,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.181874817609787,
|
|
"num_tokens": 13064920.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.489721298217773,
|
|
"epoch": 0.548030739673391,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004976921372576104,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.18271468281745912,
|
|
"num_tokens": 13077214.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.496641778945923,
|
|
"epoch": 0.5485110470701249,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004976872369062011,
|
|
"loss": 5.3489,
|
|
"mean_token_accuracy": 0.18365099430084228,
|
|
"num_tokens": 13089472.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.43571252822876,
|
|
"epoch": 0.5489913544668588,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004976823313846552,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.19171821922063828,
|
|
"num_tokens": 13100369.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.434876585006714,
|
|
"epoch": 0.5494716618635928,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004976774206930869,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.17715881168842315,
|
|
"num_tokens": 13110813.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.465077877044678,
|
|
"epoch": 0.5499519692603266,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004976725048316101,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.19080623835325242,
|
|
"num_tokens": 13121946.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.418812561035156,
|
|
"epoch": 0.5504322766570605,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004976675838003388,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.19176877588033675,
|
|
"num_tokens": 13133286.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.352372169494629,
|
|
"epoch": 0.5509125840537944,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004976626575993877,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.19047755151987075,
|
|
"num_tokens": 13145023.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.429314851760864,
|
|
"epoch": 0.5513928914505284,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004976577262288705,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.19412717819213868,
|
|
"num_tokens": 13156379.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.361028480529785,
|
|
"epoch": 0.5518731988472623,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004976527896889023,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.19664226770401,
|
|
"num_tokens": 13166313.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.473565244674683,
|
|
"epoch": 0.5523535062439962,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004976478479795974,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.18206481039524078,
|
|
"num_tokens": 13177968.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.48589334487915,
|
|
"epoch": 0.55283381364073,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004976429011010706,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.1862631544470787,
|
|
"num_tokens": 13189464.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.4495502471923825,
|
|
"epoch": 0.553314121037464,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004976379490534366,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.17927081435918807,
|
|
"num_tokens": 13201716.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.356699466705322,
|
|
"epoch": 0.5537944284341979,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004976329918368107,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.18967038840055467,
|
|
"num_tokens": 13212976.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.342360019683838,
|
|
"epoch": 0.5542747358309318,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004976280294513079,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.20202525407075883,
|
|
"num_tokens": 13225265.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.567855405807495,
|
|
"epoch": 0.5547550432276657,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004976230618970431,
|
|
"loss": 5.5457,
|
|
"mean_token_accuracy": 0.17104607522487641,
|
|
"num_tokens": 13236443.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.447632598876953,
|
|
"epoch": 0.5552353506243997,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000497618089174132,
|
|
"loss": 5.4225,
|
|
"mean_token_accuracy": 0.18674527406692504,
|
|
"num_tokens": 13248681.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.45471830368042,
|
|
"epoch": 0.5557156580211335,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004976131112826898,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.1897915154695511,
|
|
"num_tokens": 13258719.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.4247579097747805,
|
|
"epoch": 0.5561959654178674,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004976081282228323,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.18326718360185623,
|
|
"num_tokens": 13270544.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.5005025386810305,
|
|
"epoch": 0.5566762728146013,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000497603139994675,
|
|
"loss": 5.2919,
|
|
"mean_token_accuracy": 0.19663695842027665,
|
|
"num_tokens": 13280759.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.351595401763916,
|
|
"epoch": 0.5571565802113353,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004975981465983338,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.19050797075033188,
|
|
"num_tokens": 13292496.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.462756538391114,
|
|
"epoch": 0.5576368876080692,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004975931480339246,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.18254634588956833,
|
|
"num_tokens": 13303003.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.450956583023071,
|
|
"epoch": 0.5581171950048031,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004975881443015635,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.186819227039814,
|
|
"num_tokens": 13315036.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.450983762741089,
|
|
"epoch": 0.5585975024015369,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004975831354013667,
|
|
"loss": 5.3508,
|
|
"mean_token_accuracy": 0.18532153069972992,
|
|
"num_tokens": 13327529.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.454041481018066,
|
|
"epoch": 0.5590778097982709,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004975781213334503,
|
|
"loss": 5.3351,
|
|
"mean_token_accuracy": 0.18906956613063813,
|
|
"num_tokens": 13339494.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.430515480041504,
|
|
"epoch": 0.5595581171950048,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004975731020979309,
|
|
"loss": 5.3511,
|
|
"mean_token_accuracy": 0.18208261877298354,
|
|
"num_tokens": 13351184.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.407172727584839,
|
|
"epoch": 0.5600384245917387,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004975680776949249,
|
|
"loss": 5.2762,
|
|
"mean_token_accuracy": 0.19066329896450043,
|
|
"num_tokens": 13362402.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.398277616500854,
|
|
"epoch": 0.5605187319884726,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004975630481245492,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.18694706112146378,
|
|
"num_tokens": 13375257.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.475879573822022,
|
|
"epoch": 0.5609990393852066,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004975580133869202,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.18546998947858812,
|
|
"num_tokens": 13385917.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.519327878952026,
|
|
"epoch": 0.5614793467819404,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004975529734821552,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.18553060442209243,
|
|
"num_tokens": 13397962.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.369125461578369,
|
|
"epoch": 0.5619596541786743,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004975479284103708,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.1946108713746071,
|
|
"num_tokens": 13408654.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.441431856155395,
|
|
"epoch": 0.5624399615754082,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004975428781716845,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.1846861332654953,
|
|
"num_tokens": 13419790.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.440395641326904,
|
|
"epoch": 0.5629202689721422,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004975378227662134,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.19199451059103012,
|
|
"num_tokens": 13430305.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.40962929725647,
|
|
"epoch": 0.5634005763688761,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004975327621940746,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.1890603318810463,
|
|
"num_tokens": 13441730.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.505602598190308,
|
|
"epoch": 0.56388088376561,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004975276964553861,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.18663217574357988,
|
|
"num_tokens": 13452003.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.5089545249938965,
|
|
"epoch": 0.5643611911623438,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004975226255502651,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.1950973689556122,
|
|
"num_tokens": 13463953.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.448185634613037,
|
|
"epoch": 0.5648414985590778,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004975175494788297,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.18593832105398178,
|
|
"num_tokens": 13473820.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.460717630386353,
|
|
"epoch": 0.5653218059558117,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004975124682411974,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.1860885813832283,
|
|
"num_tokens": 13484181.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.511277198791504,
|
|
"epoch": 0.5658021133525456,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004975073818374863,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.1844969794154167,
|
|
"num_tokens": 13494480.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.416599559783935,
|
|
"epoch": 0.5662824207492796,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004975022902678145,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.19147448241710663,
|
|
"num_tokens": 13506026.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.520257091522216,
|
|
"epoch": 0.5667627281460135,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004974971935323003,
|
|
"loss": 5.4194,
|
|
"mean_token_accuracy": 0.182801653444767,
|
|
"num_tokens": 13516849.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.456636953353882,
|
|
"epoch": 0.5672430355427474,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004974920916310619,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.19325821250677108,
|
|
"num_tokens": 13527386.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.3854088306427,
|
|
"epoch": 0.5677233429394812,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004974869845642178,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.18449880331754684,
|
|
"num_tokens": 13540238.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.428995084762573,
|
|
"epoch": 0.5682036503362152,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004974818723318866,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.194813135266304,
|
|
"num_tokens": 13551808.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.3957782745361325,
|
|
"epoch": 0.5686839577329491,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004974767549341868,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.1883161708712578,
|
|
"num_tokens": 13563795.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.443729400634766,
|
|
"epoch": 0.569164265129683,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004974716323712376,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.1895475134253502,
|
|
"num_tokens": 13575168.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.507234525680542,
|
|
"epoch": 0.5696445725264169,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004974665046431576,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.18575030863285064,
|
|
"num_tokens": 13587013.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.396302652359009,
|
|
"epoch": 0.5701248799231509,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004974613717500659,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.18803299069404603,
|
|
"num_tokens": 13598138.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.4670515060424805,
|
|
"epoch": 0.5706051873198847,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004974562336920818,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.18367205709218978,
|
|
"num_tokens": 13609174.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.428857803344727,
|
|
"epoch": 0.5710854947166186,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004974510904693245,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.1903289094567299,
|
|
"num_tokens": 13619724.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.399194240570068,
|
|
"epoch": 0.5715658021133525,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004974459420819134,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.18765629678964615,
|
|
"num_tokens": 13631114.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.362923431396484,
|
|
"epoch": 0.5720461095100865,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000497440788529968,
|
|
"loss": 5.2797,
|
|
"mean_token_accuracy": 0.19567984342575073,
|
|
"num_tokens": 13643035.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.476286602020264,
|
|
"epoch": 0.5725264169068204,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004974356298136081,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.18529228121042252,
|
|
"num_tokens": 13656603.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.387987184524536,
|
|
"epoch": 0.5730067243035543,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004974304659329533,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.18811299204826354,
|
|
"num_tokens": 13668420.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.471386289596557,
|
|
"epoch": 0.5734870317002881,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004974252968881236,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.18334517478942872,
|
|
"num_tokens": 13680521.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.407588338851928,
|
|
"epoch": 0.5739673390970221,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000497420122679239,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.19422682821750642,
|
|
"num_tokens": 13692503.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.319512367248535,
|
|
"epoch": 0.574447646493756,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004974149433064196,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.2031061515212059,
|
|
"num_tokens": 13703318.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.403626155853272,
|
|
"epoch": 0.5749279538904899,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004974097587697856,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.18990399837493896,
|
|
"num_tokens": 13713957.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.453413772583008,
|
|
"epoch": 0.5754082612872238,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004974045690694575,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.18412325978279115,
|
|
"num_tokens": 13725300.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.494600439071656,
|
|
"epoch": 0.5758885686839578,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004973993742055557,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.18396205753087996,
|
|
"num_tokens": 13735463.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.513051128387451,
|
|
"epoch": 0.5763688760806917,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004973941741782007,
|
|
"loss": 5.4965,
|
|
"mean_token_accuracy": 0.1788262516260147,
|
|
"num_tokens": 13749062.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5763688760806917,
|
|
"eval_entropy": 5.391382442573871,
|
|
"eval_loss": 5.3939995765686035,
|
|
"eval_mean_token_accuracy": 0.1923779231173303,
|
|
"eval_num_tokens": 13749062.0,
|
|
"eval_runtime": 26.6581,
|
|
"eval_samples_per_second": 1230.958,
|
|
"eval_steps_per_second": 153.874,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.594244194030762,
|
|
"epoch": 0.5768491834774255,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004973889689875135,
|
|
"loss": 5.4567,
|
|
"mean_token_accuracy": 0.17287490218877793,
|
|
"num_tokens": 13761766.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.467732667922974,
|
|
"epoch": 0.5773294908741594,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004973837586336147,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.1873711794614792,
|
|
"num_tokens": 13774702.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.388287687301636,
|
|
"epoch": 0.5778097982708934,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004973785431166254,
|
|
"loss": 5.3238,
|
|
"mean_token_accuracy": 0.1841629922389984,
|
|
"num_tokens": 13786215.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.379306221008301,
|
|
"epoch": 0.5782901056676273,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004973733224366666,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.18715571910142897,
|
|
"num_tokens": 13797697.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.505963897705078,
|
|
"epoch": 0.5787704130643612,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004973680965938597,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.18360659927129747,
|
|
"num_tokens": 13810085.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.485981369018555,
|
|
"epoch": 0.579250720461095,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004973628655883258,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.1925201028585434,
|
|
"num_tokens": 13822054.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.295996761322021,
|
|
"epoch": 0.579731027857829,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004973576294201865,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.19221212714910507,
|
|
"num_tokens": 13834342.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.438166999816895,
|
|
"epoch": 0.5802113352545629,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004973523880895633,
|
|
"loss": 5.3843,
|
|
"mean_token_accuracy": 0.1854028046131134,
|
|
"num_tokens": 13846598.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.444848537445068,
|
|
"epoch": 0.5806916426512968,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004973471415965779,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.188867250084877,
|
|
"num_tokens": 13857515.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.325572919845581,
|
|
"epoch": 0.5811719500480308,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000497341889941352,
|
|
"loss": 5.2379,
|
|
"mean_token_accuracy": 0.1973300725221634,
|
|
"num_tokens": 13868333.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.4464198589324955,
|
|
"epoch": 0.5816522574447647,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004973366331240078,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.1817735403776169,
|
|
"num_tokens": 13879048.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.47771372795105,
|
|
"epoch": 0.5821325648414986,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000497331371144667,
|
|
"loss": 5.4594,
|
|
"mean_token_accuracy": 0.17890119254589082,
|
|
"num_tokens": 13891358.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.602402830123902,
|
|
"epoch": 0.5826128722382324,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004973261040034521,
|
|
"loss": 5.4929,
|
|
"mean_token_accuracy": 0.17942275404930114,
|
|
"num_tokens": 13902680.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.513533735275269,
|
|
"epoch": 0.5830931796349664,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004973208317004852,
|
|
"loss": 5.3803,
|
|
"mean_token_accuracy": 0.18414207845926284,
|
|
"num_tokens": 13913863.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.387319421768188,
|
|
"epoch": 0.5835734870317003,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004973155542358889,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.189805369079113,
|
|
"num_tokens": 13924917.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.282955503463745,
|
|
"epoch": 0.5840537944284342,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004973102716097853,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.19826523214578629,
|
|
"num_tokens": 13936022.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.456071472167968,
|
|
"epoch": 0.5845341018251681,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004973049838222973,
|
|
"loss": 5.3778,
|
|
"mean_token_accuracy": 0.18554320186376572,
|
|
"num_tokens": 13947594.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.481543970108032,
|
|
"epoch": 0.5850144092219021,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004972996908735479,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.18329488188028337,
|
|
"num_tokens": 13960698.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.424262666702271,
|
|
"epoch": 0.585494716618636,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004972943927636597,
|
|
"loss": 5.3493,
|
|
"mean_token_accuracy": 0.18691962212324142,
|
|
"num_tokens": 13971004.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.402873086929321,
|
|
"epoch": 0.5859750240153698,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972890894927558,
|
|
"loss": 5.36,
|
|
"mean_token_accuracy": 0.1917417049407959,
|
|
"num_tokens": 13982500.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.524716901779175,
|
|
"epoch": 0.5864553314121037,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004972837810609592,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.18116320669651031,
|
|
"num_tokens": 13994129.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.4113037109375,
|
|
"epoch": 0.5869356388088377,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004972784674683933,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.19135573953390123,
|
|
"num_tokens": 14005581.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.425225019454956,
|
|
"epoch": 0.5874159462055716,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004972731487151815,
|
|
"loss": 5.3684,
|
|
"mean_token_accuracy": 0.18579945117235183,
|
|
"num_tokens": 14015866.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.383860778808594,
|
|
"epoch": 0.5878962536023055,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004972678248014471,
|
|
"loss": 5.358,
|
|
"mean_token_accuracy": 0.1943156510591507,
|
|
"num_tokens": 14027002.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.3782281398773195,
|
|
"epoch": 0.5883765609990393,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004972624957273139,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.18841624408960342,
|
|
"num_tokens": 14038962.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.466955089569092,
|
|
"epoch": 0.5888568683957733,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004972571614929055,
|
|
"loss": 5.3941,
|
|
"mean_token_accuracy": 0.1893245682120323,
|
|
"num_tokens": 14049956.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.4190325260162355,
|
|
"epoch": 0.5893371757925072,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972518220983457,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.1856802999973297,
|
|
"num_tokens": 14062413.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.473791646957397,
|
|
"epoch": 0.5898174831892411,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004972464775437586,
|
|
"loss": 5.3723,
|
|
"mean_token_accuracy": 0.1883968785405159,
|
|
"num_tokens": 14075166.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.400057363510132,
|
|
"epoch": 0.590297790585975,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004972411278292683,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.19134089350700378,
|
|
"num_tokens": 14085208.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.528112077713013,
|
|
"epoch": 0.590778097982709,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004972357729549988,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.17733772099018097,
|
|
"num_tokens": 14096688.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.303466796875,
|
|
"epoch": 0.5912584053794429,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004972304129210746,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.1955884262919426,
|
|
"num_tokens": 14108737.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.388396978378296,
|
|
"epoch": 0.5917387127761767,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972250477276202,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.19089388847351074,
|
|
"num_tokens": 14120121.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.414858722686768,
|
|
"epoch": 0.5922190201729106,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004972196773747599,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.1914263740181923,
|
|
"num_tokens": 14132157.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.421557950973511,
|
|
"epoch": 0.5926993275696446,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004972143018626186,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.18856575340032578,
|
|
"num_tokens": 14143092.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.392038869857788,
|
|
"epoch": 0.5931796349663785,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004972089211913211,
|
|
"loss": 5.3087,
|
|
"mean_token_accuracy": 0.18959310948848723,
|
|
"num_tokens": 14153973.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.4936912059783936,
|
|
"epoch": 0.5936599423631124,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004972035353609923,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.17793257385492325,
|
|
"num_tokens": 14164919.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.423027610778808,
|
|
"epoch": 0.5941402497598463,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004971981443717572,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.19024920612573623,
|
|
"num_tokens": 14176803.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.44634518623352,
|
|
"epoch": 0.5946205571565802,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004971927482237409,
|
|
"loss": 5.2971,
|
|
"mean_token_accuracy": 0.18827152550220488,
|
|
"num_tokens": 14190087.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.450093936920166,
|
|
"epoch": 0.5951008645533141,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004971873469170689,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.17948530316352845,
|
|
"num_tokens": 14202242.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.474076890945435,
|
|
"epoch": 0.595581171950048,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004971819404518664,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.18267126381397247,
|
|
"num_tokens": 14214020.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.4121746063232425,
|
|
"epoch": 0.5960614793467819,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000497176528828259,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.19289236813783645,
|
|
"num_tokens": 14225455.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.338340520858765,
|
|
"epoch": 0.5965417867435159,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004971711120463722,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18932408541440965,
|
|
"num_tokens": 14235955.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.38538179397583,
|
|
"epoch": 0.5970220941402498,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000497165690106332,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.182011616230011,
|
|
"num_tokens": 14246107.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.437984466552734,
|
|
"epoch": 0.5975024015369836,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004971602630082642,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.18752168864011765,
|
|
"num_tokens": 14257042.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.5255238056182865,
|
|
"epoch": 0.5979827089337176,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004971548307522947,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.181718672811985,
|
|
"num_tokens": 14268670.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.423706769943237,
|
|
"epoch": 0.5984630163304515,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004971493933385498,
|
|
"loss": 5.2774,
|
|
"mean_token_accuracy": 0.19225098341703414,
|
|
"num_tokens": 14279538.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.444534683227539,
|
|
"epoch": 0.5989433237271854,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004971439507671556,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.18014575242996217,
|
|
"num_tokens": 14291928.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.425173711776734,
|
|
"epoch": 0.5994236311239193,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004971385030382384,
|
|
"loss": 5.3101,
|
|
"mean_token_accuracy": 0.19303133934736252,
|
|
"num_tokens": 14302958.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.406954002380371,
|
|
"epoch": 0.5999039385206533,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004971330501519248,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.18892101049423218,
|
|
"num_tokens": 14315585.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.401479005813599,
|
|
"epoch": 0.6003842459173871,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004971275921083414,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.18227880150079728,
|
|
"num_tokens": 14327228.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.523636722564698,
|
|
"epoch": 0.600864553314121,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000497122128907615,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.1836875319480896,
|
|
"num_tokens": 14338079.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.4651741027832035,
|
|
"epoch": 0.6013448607108549,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004971166605498722,
|
|
"loss": 5.3075,
|
|
"mean_token_accuracy": 0.19537494331598282,
|
|
"num_tokens": 14350220.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.468128061294555,
|
|
"epoch": 0.6018251681075889,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004971111870352401,
|
|
"loss": 5.3995,
|
|
"mean_token_accuracy": 0.1816209778189659,
|
|
"num_tokens": 14360761.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.448753786087036,
|
|
"epoch": 0.6023054755043228,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004971057083638458,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.1839236721396446,
|
|
"num_tokens": 14372056.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.515234518051147,
|
|
"epoch": 0.6027857829010567,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004971002245358166,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.18750105053186417,
|
|
"num_tokens": 14382601.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.590676403045654,
|
|
"epoch": 0.6032660902977905,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004970947355512795,
|
|
"loss": 5.4816,
|
|
"mean_token_accuracy": 0.17895192205905913,
|
|
"num_tokens": 14393749.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.477749538421631,
|
|
"epoch": 0.6037463976945245,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004970892414103622,
|
|
"loss": 5.3723,
|
|
"mean_token_accuracy": 0.18472715020179747,
|
|
"num_tokens": 14405001.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.281026363372803,
|
|
"epoch": 0.6042267050912584,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004970837421131921,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.1901577666401863,
|
|
"num_tokens": 14415875.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.327046680450439,
|
|
"epoch": 0.6047070124879923,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004970782376598972,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.18864146918058394,
|
|
"num_tokens": 14426896.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.454883766174317,
|
|
"epoch": 0.6051873198847262,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004970727280506048,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.1811344027519226,
|
|
"num_tokens": 14438712.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.4120667457580565,
|
|
"epoch": 0.6056676272814602,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004970672132854431,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.1871188297867775,
|
|
"num_tokens": 14450952.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.4106958389282225,
|
|
"epoch": 0.6061479346781941,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004970616933645403,
|
|
"loss": 5.3385,
|
|
"mean_token_accuracy": 0.19248796105384827,
|
|
"num_tokens": 14462139.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.395157098770142,
|
|
"epoch": 0.6066282420749279,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004970561682880242,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.18527979850769044,
|
|
"num_tokens": 14472817.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.464319038391113,
|
|
"epoch": 0.6071085494716618,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004970506380560233,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.17815070897340773,
|
|
"num_tokens": 14484241.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.376730060577392,
|
|
"epoch": 0.6075888568683958,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004970451026686659,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.18941431492567062,
|
|
"num_tokens": 14496327.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.460070943832397,
|
|
"epoch": 0.6080691642651297,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004970395621260806,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.18361499011516572,
|
|
"num_tokens": 14508041.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.431254482269287,
|
|
"epoch": 0.6085494716618636,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000497034016428396,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.1927487924695015,
|
|
"num_tokens": 14519023.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.3656209945678714,
|
|
"epoch": 0.6090297790585975,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004970284655757409,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.18459006696939467,
|
|
"num_tokens": 14530783.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.400503015518188,
|
|
"epoch": 0.6095100864553314,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004970229095682439,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.19315001517534255,
|
|
"num_tokens": 14541680.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.451666212081909,
|
|
"epoch": 0.6099903938520653,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004970173484060344,
|
|
"loss": 5.3521,
|
|
"mean_token_accuracy": 0.18292970210313797,
|
|
"num_tokens": 14553792.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.436286497116089,
|
|
"epoch": 0.6104707012487992,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004970117820892414,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.18426571935415267,
|
|
"num_tokens": 14565410.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.3938507556915285,
|
|
"epoch": 0.6109510086455331,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004970062106179939,
|
|
"loss": 5.2429,
|
|
"mean_token_accuracy": 0.1873038202524185,
|
|
"num_tokens": 14576722.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.364889001846313,
|
|
"epoch": 0.6114313160422671,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004970006339924214,
|
|
"loss": 5.2763,
|
|
"mean_token_accuracy": 0.19065423011779786,
|
|
"num_tokens": 14589443.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.4637962818145756,
|
|
"epoch": 0.611911623439001,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004969950522126534,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.1833744838833809,
|
|
"num_tokens": 14600731.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.415026617050171,
|
|
"epoch": 0.6123919308357348,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004969894652788196,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.1923918157815933,
|
|
"num_tokens": 14611152.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.44018177986145,
|
|
"epoch": 0.6128722382324687,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004969838731910494,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.17922666668891907,
|
|
"num_tokens": 14624526.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.415634250640869,
|
|
"epoch": 0.6133525456292027,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004969782759494729,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.19230301380157472,
|
|
"num_tokens": 14635527.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.461290121078491,
|
|
"epoch": 0.6138328530259366,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00049697267355422,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.18506784588098527,
|
|
"num_tokens": 14647372.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.5496093273162845,
|
|
"epoch": 0.6143131604226705,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004969670660054208,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.18408179730176927,
|
|
"num_tokens": 14659216.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.427420568466187,
|
|
"epoch": 0.6147934678194045,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004969614533032054,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.18339368849992752,
|
|
"num_tokens": 14670336.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.31213116645813,
|
|
"epoch": 0.6152737752161384,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004969558354477041,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.1918257251381874,
|
|
"num_tokens": 14680668.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.461543703079224,
|
|
"epoch": 0.6157540826128722,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004969502124390474,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.1822928488254547,
|
|
"num_tokens": 14691521.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.446273708343506,
|
|
"epoch": 0.6162343900096061,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004969445842773658,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.18367120921611785,
|
|
"num_tokens": 14702473.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.345534086227417,
|
|
"epoch": 0.6167146974063401,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00049693895096279,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.1895003318786621,
|
|
"num_tokens": 14713057.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.477782440185547,
|
|
"epoch": 0.617195004803074,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004969333124954508,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.18387351334095,
|
|
"num_tokens": 14725203.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.376272296905517,
|
|
"epoch": 0.6176753121998079,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004969276688754791,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.19398964643478395,
|
|
"num_tokens": 14735851.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.472036266326905,
|
|
"epoch": 0.6181556195965417,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004969220201030059,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.19013222604990004,
|
|
"num_tokens": 14747876.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.41585693359375,
|
|
"epoch": 0.6186359269932757,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004969163661781624,
|
|
"loss": 5.3456,
|
|
"mean_token_accuracy": 0.1899268090724945,
|
|
"num_tokens": 14758673.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.407340240478516,
|
|
"epoch": 0.6191162343900096,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004969107071010798,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.19403767287731172,
|
|
"num_tokens": 14770505.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.421085453033447,
|
|
"epoch": 0.6195965417867435,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004969050428718895,
|
|
"loss": 5.3537,
|
|
"mean_token_accuracy": 0.18687873035669328,
|
|
"num_tokens": 14782518.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.392564964294434,
|
|
"epoch": 0.6200768491834774,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000496899373490723,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.19183335602283477,
|
|
"num_tokens": 14794608.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.328503513336182,
|
|
"epoch": 0.6205571565802114,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000496893698957712,
|
|
"loss": 5.2157,
|
|
"mean_token_accuracy": 0.19725629240274428,
|
|
"num_tokens": 14804725.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.447431182861328,
|
|
"epoch": 0.6210374639769453,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004968880192729882,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.1898462802171707,
|
|
"num_tokens": 14816178.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.457472562789917,
|
|
"epoch": 0.6215177713736791,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004968823344366835,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.18324750810861587,
|
|
"num_tokens": 14827808.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.3914533138275145,
|
|
"epoch": 0.621998078770413,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004968766444489298,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.1886556029319763,
|
|
"num_tokens": 14839423.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.474667930603028,
|
|
"epoch": 0.622478386167147,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004968709493098593,
|
|
"loss": 5.4007,
|
|
"mean_token_accuracy": 0.18815280497074127,
|
|
"num_tokens": 14849678.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.340357923507691,
|
|
"epoch": 0.6229586935638809,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004968652490196041,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.1961539551615715,
|
|
"num_tokens": 14860912.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.359215307235718,
|
|
"epoch": 0.6234390009606148,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004968595435782967,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.18657833635807036,
|
|
"num_tokens": 14873028.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.49301381111145,
|
|
"epoch": 0.6239193083573487,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004968538329860695,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.18742749840021133,
|
|
"num_tokens": 14883985.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.461597871780396,
|
|
"epoch": 0.6243996157540826,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004968481172430549,
|
|
"loss": 5.368,
|
|
"mean_token_accuracy": 0.18283463567495345,
|
|
"num_tokens": 14896569.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.43288402557373,
|
|
"epoch": 0.6248799231508165,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000496842396349386,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.19527961015701295,
|
|
"num_tokens": 14907874.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.420658826828003,
|
|
"epoch": 0.6253602305475504,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004968366703051952,
|
|
"loss": 5.3322,
|
|
"mean_token_accuracy": 0.19150687158107757,
|
|
"num_tokens": 14919501.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.408752489089966,
|
|
"epoch": 0.6258405379442843,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004968309391106157,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.18907625526189803,
|
|
"num_tokens": 14929876.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.391577672958374,
|
|
"epoch": 0.6263208453410183,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004968252027657806,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.18368214070796968,
|
|
"num_tokens": 14941317.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.480224609375,
|
|
"epoch": 0.6268011527377522,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004968194612708229,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.18525346368551254,
|
|
"num_tokens": 14953038.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.379436111450195,
|
|
"epoch": 0.627281460134486,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004968137146258759,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.19222625941038132,
|
|
"num_tokens": 14964664.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.37131519317627,
|
|
"epoch": 0.6277617675312199,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004968079628310732,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.19383252710103988,
|
|
"num_tokens": 14975761.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.4234987735748295,
|
|
"epoch": 0.6282420749279539,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004968022058865482,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.1946899637579918,
|
|
"num_tokens": 14987670.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.346607255935669,
|
|
"epoch": 0.6287223823246878,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004967964437924346,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.1991036906838417,
|
|
"num_tokens": 14999390.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.344186592102051,
|
|
"epoch": 0.6292026897214217,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004967906765488662,
|
|
"loss": 5.3289,
|
|
"mean_token_accuracy": 0.18837945014238358,
|
|
"num_tokens": 15011691.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.536790609359741,
|
|
"epoch": 0.6296829971181557,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004967849041559769,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.18327112942934037,
|
|
"num_tokens": 15023539.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.4762969493865965,
|
|
"epoch": 0.6301633045148896,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004967791266139006,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.19257629811763763,
|
|
"num_tokens": 15035529.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.422998237609863,
|
|
"epoch": 0.6306436119116234,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004967733439227716,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.1900174215435982,
|
|
"num_tokens": 15047072.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.46677794456482,
|
|
"epoch": 0.6311239193083573,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000496767556082724,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.18688941448926927,
|
|
"num_tokens": 15058951.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.417145586013794,
|
|
"epoch": 0.6316042267050913,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004967617630938924,
|
|
"loss": 5.3879,
|
|
"mean_token_accuracy": 0.19218687117099761,
|
|
"num_tokens": 15070647.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.436992740631103,
|
|
"epoch": 0.6320845341018252,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000496755964956411,
|
|
"loss": 5.308,
|
|
"mean_token_accuracy": 0.19497922956943511,
|
|
"num_tokens": 15082324.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.488131141662597,
|
|
"epoch": 0.6325648414985591,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004967501616704147,
|
|
"loss": 5.4626,
|
|
"mean_token_accuracy": 0.17747684121131896,
|
|
"num_tokens": 15094641.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.557354927062988,
|
|
"epoch": 0.633045148895293,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000496744353236038,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.18662358373403548,
|
|
"num_tokens": 15106610.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.3808118343353275,
|
|
"epoch": 0.633525456292027,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000496738539653416,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.1909119114279747,
|
|
"num_tokens": 15118463.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.397026205062867,
|
|
"epoch": 0.6340057636887608,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004967327209226835,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.19154786914587021,
|
|
"num_tokens": 15130154.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.37779278755188,
|
|
"epoch": 0.6344860710854947,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004967268970439755,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.19595194458961487,
|
|
"num_tokens": 15140854.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.381403541564941,
|
|
"epoch": 0.6349663784822286,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004967210680174274,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.19121498614549637,
|
|
"num_tokens": 15151075.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.356026649475098,
|
|
"epoch": 0.6354466858789626,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004967152338431745,
|
|
"loss": 5.2727,
|
|
"mean_token_accuracy": 0.1972847431898117,
|
|
"num_tokens": 15162091.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.542326402664185,
|
|
"epoch": 0.6359269932756965,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004967093945213523,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.18341906666755675,
|
|
"num_tokens": 15175321.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.391190147399902,
|
|
"epoch": 0.6364073006724303,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004967035500520962,
|
|
"loss": 5.345,
|
|
"mean_token_accuracy": 0.19236933290958405,
|
|
"num_tokens": 15187058.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.4209099292755125,
|
|
"epoch": 0.6368876080691642,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004966977004355421,
|
|
"loss": 5.3279,
|
|
"mean_token_accuracy": 0.19033313244581224,
|
|
"num_tokens": 15198886.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.479446506500244,
|
|
"epoch": 0.6373679154658982,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004966918456718256,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.18606213927268983,
|
|
"num_tokens": 15211026.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.237106609344482,
|
|
"epoch": 0.6378482228626321,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004966859857610828,
|
|
"loss": 5.2724,
|
|
"mean_token_accuracy": 0.20162095427513121,
|
|
"num_tokens": 15222094.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.409952211380005,
|
|
"epoch": 0.638328530259366,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004966801207034497,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.1915718659758568,
|
|
"num_tokens": 15232464.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.457336807250977,
|
|
"epoch": 0.6388088376560999,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004966742504990624,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.19506607204675674,
|
|
"num_tokens": 15244564.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.454538059234619,
|
|
"epoch": 0.6392891450528339,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004966683751480572,
|
|
"loss": 5.43,
|
|
"mean_token_accuracy": 0.18866757303476334,
|
|
"num_tokens": 15255822.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.465950059890747,
|
|
"epoch": 0.6397694524495677,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004966624946505706,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.18331922441720963,
|
|
"num_tokens": 15267336.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.375289535522461,
|
|
"epoch": 0.6402497598463016,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004966566090067391,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.19735877364873886,
|
|
"num_tokens": 15278073.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.408173608779907,
|
|
"epoch": 0.6407300672430355,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004966507182166993,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.1848673477768898,
|
|
"num_tokens": 15290119.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.342706203460693,
|
|
"epoch": 0.6412103746397695,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000496644822280588,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.19946765452623366,
|
|
"num_tokens": 15302235.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.455457592010498,
|
|
"epoch": 0.6416906820365034,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000496638921198542,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.17861731052398683,
|
|
"num_tokens": 15312924.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.287777090072632,
|
|
"epoch": 0.6421709894332372,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004966330149706984,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.2019541308283806,
|
|
"num_tokens": 15323453.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.39892840385437,
|
|
"epoch": 0.6426512968299711,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004966271035971944,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.19235245883464813,
|
|
"num_tokens": 15334907.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.398792362213134,
|
|
"epoch": 0.6431316042267051,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004966211870781671,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.1934860497713089,
|
|
"num_tokens": 15347211.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.406028366088867,
|
|
"epoch": 0.643611911623439,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000496615265413754,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.18037029653787612,
|
|
"num_tokens": 15360171.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.566893434524536,
|
|
"epoch": 0.6440922190201729,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004966093386040923,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.18123398423194886,
|
|
"num_tokens": 15372209.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.519690656661988,
|
|
"epoch": 0.6445725264169068,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00049660340664932,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.18608277589082717,
|
|
"num_tokens": 15383753.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.458930158615113,
|
|
"epoch": 0.6450528338136408,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004965974695495746,
|
|
"loss": 5.3641,
|
|
"mean_token_accuracy": 0.18930920511484145,
|
|
"num_tokens": 15395202.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.4900514602661135,
|
|
"epoch": 0.6455331412103746,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004965915273049938,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.1904049649834633,
|
|
"num_tokens": 15407121.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.368436098098755,
|
|
"epoch": 0.6460134486071085,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004965855799157158,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.191600301861763,
|
|
"num_tokens": 15418063.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.434974575042725,
|
|
"epoch": 0.6464937560038425,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004965796273818787,
|
|
"loss": 5.3369,
|
|
"mean_token_accuracy": 0.18815235495567323,
|
|
"num_tokens": 15428830.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.413639879226684,
|
|
"epoch": 0.6469740634005764,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004965736697036206,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.18711058497428895,
|
|
"num_tokens": 15441009.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.401315784454345,
|
|
"epoch": 0.6474543707973103,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004965677068810798,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.1954300120472908,
|
|
"num_tokens": 15453008.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.469344186782837,
|
|
"epoch": 0.6479346781940442,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004965617389143947,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.1931136205792427,
|
|
"num_tokens": 15463907.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.430829906463623,
|
|
"epoch": 0.6484149855907781,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000496555765803704,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.19242316335439683,
|
|
"num_tokens": 15474706.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.408749389648437,
|
|
"epoch": 0.648895292987512,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004965497875491462,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.1895291328430176,
|
|
"num_tokens": 15486355.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.448469829559326,
|
|
"epoch": 0.6493756003842459,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004965438041508604,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.18742077946662902,
|
|
"num_tokens": 15498184.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.487996292114258,
|
|
"epoch": 0.6498559077809798,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004965378156089851,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.18962435573339462,
|
|
"num_tokens": 15509461.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.362503623962402,
|
|
"epoch": 0.6503362151777138,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004965318219236597,
|
|
"loss": 5.3264,
|
|
"mean_token_accuracy": 0.1874221906065941,
|
|
"num_tokens": 15520169.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.454718112945557,
|
|
"epoch": 0.6508165225744477,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004965258230950232,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.18056175708770753,
|
|
"num_tokens": 15532783.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.46618161201477,
|
|
"epoch": 0.6512968299711815,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004965198191232148,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.18317433297634125,
|
|
"num_tokens": 15543639.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.372718667984008,
|
|
"epoch": 0.6517771373679154,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000496513810008374,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.1894352987408638,
|
|
"num_tokens": 15555149.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.445323848724366,
|
|
"epoch": 0.6522574447646494,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004965077957506403,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.19207099080085754,
|
|
"num_tokens": 15566922.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.512098979949951,
|
|
"epoch": 0.6527377521613833,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004965017763501533,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.1858382925391197,
|
|
"num_tokens": 15578047.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.4678209781646725,
|
|
"epoch": 0.6532180595581172,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004964957518070529,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.1829053059220314,
|
|
"num_tokens": 15590378.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.465389442443848,
|
|
"epoch": 0.6536983669548511,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004964897221214788,
|
|
"loss": 5.3585,
|
|
"mean_token_accuracy": 0.1873955100774765,
|
|
"num_tokens": 15600866.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.442267370223999,
|
|
"epoch": 0.654178674351585,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000496483687293571,
|
|
"loss": 5.2324,
|
|
"mean_token_accuracy": 0.18718597888946534,
|
|
"num_tokens": 15612617.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.405890989303589,
|
|
"epoch": 0.6546589817483189,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004964776473234696,
|
|
"loss": 5.3329,
|
|
"mean_token_accuracy": 0.1965491771697998,
|
|
"num_tokens": 15624446.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.394840717315674,
|
|
"epoch": 0.6551392891450528,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000496471602211315,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.19656362235546113,
|
|
"num_tokens": 15635300.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.366667032241821,
|
|
"epoch": 0.6556195965417867,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004964655519572475,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.19457219541072845,
|
|
"num_tokens": 15646452.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.398584508895874,
|
|
"epoch": 0.6560999039385207,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004964594965614072,
|
|
"loss": 5.4091,
|
|
"mean_token_accuracy": 0.18492621332406997,
|
|
"num_tokens": 15658514.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.5249849319458,
|
|
"epoch": 0.6565802113352546,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004964534360239353,
|
|
"loss": 5.3289,
|
|
"mean_token_accuracy": 0.1848491057753563,
|
|
"num_tokens": 15670222.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.390076684951782,
|
|
"epoch": 0.6570605187319885,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000496447370344972,
|
|
"loss": 5.3375,
|
|
"mean_token_accuracy": 0.18988256454467772,
|
|
"num_tokens": 15681627.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.392456865310669,
|
|
"epoch": 0.6575408261287223,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004964412995246584,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.18991410583257676,
|
|
"num_tokens": 15692632.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.395306730270386,
|
|
"epoch": 0.6580211335254563,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004964352235631354,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.19022546857595443,
|
|
"num_tokens": 15704736.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.437859106063843,
|
|
"epoch": 0.6585014409221902,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000496429142460544,
|
|
"loss": 5.4344,
|
|
"mean_token_accuracy": 0.18680487126111983,
|
|
"num_tokens": 15717057.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.495915222167969,
|
|
"epoch": 0.6589817483189241,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004964230562170254,
|
|
"loss": 5.4921,
|
|
"mean_token_accuracy": 0.1785072550177574,
|
|
"num_tokens": 15728577.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.459878587722779,
|
|
"epoch": 0.659462055715658,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004964169648327209,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.1872129037976265,
|
|
"num_tokens": 15739714.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.437222337722778,
|
|
"epoch": 0.659942363112392,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000496410868307772,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.19761881232261658,
|
|
"num_tokens": 15751339.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.520535659790039,
|
|
"epoch": 0.6604226705091258,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004964047666423203,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.18299062699079513,
|
|
"num_tokens": 15763177.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.459117794036866,
|
|
"epoch": 0.6609029779058597,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004963986598365072,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.18871883153915406,
|
|
"num_tokens": 15774691.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.517058086395264,
|
|
"epoch": 0.6613832853025937,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004963925478904746,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.18887075483798982,
|
|
"num_tokens": 15785561.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.466109323501587,
|
|
"epoch": 0.6618635926993276,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004963864308043645,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.18537548631429673,
|
|
"num_tokens": 15795687.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.3591382026672365,
|
|
"epoch": 0.6623439000960615,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004963803085783189,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.1918278232216835,
|
|
"num_tokens": 15807191.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.452403974533081,
|
|
"epoch": 0.6628242074927954,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004963741812124799,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.18980597704648972,
|
|
"num_tokens": 15819585.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.505056524276734,
|
|
"epoch": 0.6633045148895294,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004963680487069898,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.188141630589962,
|
|
"num_tokens": 15831580.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.372838973999023,
|
|
"epoch": 0.6637848222862632,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004963619110619908,
|
|
"loss": 5.349,
|
|
"mean_token_accuracy": 0.18626470267772674,
|
|
"num_tokens": 15843848.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.509882307052612,
|
|
"epoch": 0.6642651296829971,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004963557682776256,
|
|
"loss": 5.4331,
|
|
"mean_token_accuracy": 0.1808481752872467,
|
|
"num_tokens": 15855091.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.444598722457886,
|
|
"epoch": 0.664745437079731,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004963496203540368,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.19024813771247864,
|
|
"num_tokens": 15866676.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.328142070770264,
|
|
"epoch": 0.665225744476465,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004963434672913671,
|
|
"loss": 5.2125,
|
|
"mean_token_accuracy": 0.1954273462295532,
|
|
"num_tokens": 15877901.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.398678112030029,
|
|
"epoch": 0.6657060518731989,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004963373090897592,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.18265456557273865,
|
|
"num_tokens": 15889284.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.373099327087402,
|
|
"epoch": 0.6661863592699327,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004963311457493563,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.1994304671883583,
|
|
"num_tokens": 15901218.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.30461483001709,
|
|
"epoch": 0.6666666666666666,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004963249772703015,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.19947979152202605,
|
|
"num_tokens": 15912452.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.380452871322632,
|
|
"epoch": 0.6671469740634006,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004963188036527378,
|
|
"loss": 5.3339,
|
|
"mean_token_accuracy": 0.1922300785779953,
|
|
"num_tokens": 15924353.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.5066570281982425,
|
|
"epoch": 0.6676272814601345,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004963126248968087,
|
|
"loss": 5.3545,
|
|
"mean_token_accuracy": 0.19190370440483093,
|
|
"num_tokens": 15936295.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.464797401428223,
|
|
"epoch": 0.6681075888568684,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004963064410026577,
|
|
"loss": 5.3367,
|
|
"mean_token_accuracy": 0.18397328108549119,
|
|
"num_tokens": 15948407.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.408189535140991,
|
|
"epoch": 0.6685878962536023,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004963002519704281,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.19000355303287506,
|
|
"num_tokens": 15959975.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.462561798095703,
|
|
"epoch": 0.6690682036503363,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000496294057800264,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.19165364801883697,
|
|
"num_tokens": 15973084.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.344120168685913,
|
|
"epoch": 0.6695485110470701,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004962878584923089,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.19582221955060958,
|
|
"num_tokens": 15984444.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.342095232009887,
|
|
"epoch": 0.670028818443804,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004962816540467068,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.1910207062959671,
|
|
"num_tokens": 15996611.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.418095445632934,
|
|
"epoch": 0.6705091258405379,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004962754444636017,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.1870596617460251,
|
|
"num_tokens": 16007144.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.389230728149414,
|
|
"epoch": 0.6709894332372719,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000496269229743138,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.19333738535642625,
|
|
"num_tokens": 16018878.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.478294420242309,
|
|
"epoch": 0.6714697406340058,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004962630098854597,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.18667296022176744,
|
|
"num_tokens": 16031273.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.479709196090698,
|
|
"epoch": 0.6719500480307397,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004962567848907113,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.18379569351673125,
|
|
"num_tokens": 16043101.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.352395915985108,
|
|
"epoch": 0.6724303554274735,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004962505547590374,
|
|
"loss": 5.2679,
|
|
"mean_token_accuracy": 0.18883143812417985,
|
|
"num_tokens": 16054922.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.490764188766479,
|
|
"epoch": 0.6729106628242075,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004962443194905826,
|
|
"loss": 5.3408,
|
|
"mean_token_accuracy": 0.1831253096461296,
|
|
"num_tokens": 16065461.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.434230852127075,
|
|
"epoch": 0.6733909702209414,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004962380790854916,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.1788187012076378,
|
|
"num_tokens": 16076715.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.397006845474243,
|
|
"epoch": 0.6738712776176753,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004962318335439094,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.19198958575725555,
|
|
"num_tokens": 16088937.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.384761619567871,
|
|
"epoch": 0.6743515850144092,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004962255828659809,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.19809892773628235,
|
|
"num_tokens": 16100004.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.4446470737457275,
|
|
"epoch": 0.6748318924111432,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004962193270518513,
|
|
"loss": 5.3497,
|
|
"mean_token_accuracy": 0.1927206665277481,
|
|
"num_tokens": 16112435.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.46750955581665,
|
|
"epoch": 0.675312199807877,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004962130661016659,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.18370037376880646,
|
|
"num_tokens": 16124246.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.542457580566406,
|
|
"epoch": 0.6757925072046109,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004962068000155699,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.18194731920957566,
|
|
"num_tokens": 16136291.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.392105674743652,
|
|
"epoch": 0.6762728146013448,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004962005287937088,
|
|
"loss": 5.2617,
|
|
"mean_token_accuracy": 0.19185828268527985,
|
|
"num_tokens": 16148641.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.339692640304565,
|
|
"epoch": 0.6767531219980788,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004961942524362283,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.20256917625665666,
|
|
"num_tokens": 16159152.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.4464000225067135,
|
|
"epoch": 0.6772334293948127,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004961879709432741,
|
|
"loss": 5.3635,
|
|
"mean_token_accuracy": 0.18551846593618393,
|
|
"num_tokens": 16170019.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.526552438735962,
|
|
"epoch": 0.6777137367915466,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000496181684314992,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.18400342911481857,
|
|
"num_tokens": 16181714.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.4214578628540036,
|
|
"epoch": 0.6781940441882806,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004961753925515279,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.18342450708150865,
|
|
"num_tokens": 16192822.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.3091799259185795,
|
|
"epoch": 0.6786743515850144,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000496169095653028,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.1941420316696167,
|
|
"num_tokens": 16203660.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.385712766647339,
|
|
"epoch": 0.6791546589817483,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004961627936196384,
|
|
"loss": 5.3231,
|
|
"mean_token_accuracy": 0.19611474722623826,
|
|
"num_tokens": 16215495.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.422764587402344,
|
|
"epoch": 0.6796349663784822,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004961564864515055,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.1954946756362915,
|
|
"num_tokens": 16227532.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.2686676502227785,
|
|
"epoch": 0.6801152737752162,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004961501741487757,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.2048894628882408,
|
|
"num_tokens": 16238979.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.274458646774292,
|
|
"epoch": 0.6805955811719501,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004961438567115955,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.19594721049070357,
|
|
"num_tokens": 16249146.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.386977481842041,
|
|
"epoch": 0.681075888568684,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004961375341401116,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.18883857429027556,
|
|
"num_tokens": 16262269.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.397275638580322,
|
|
"epoch": 0.6815561959654178,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004961312064344708,
|
|
"loss": 5.2629,
|
|
"mean_token_accuracy": 0.1970457300543785,
|
|
"num_tokens": 16273877.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.50013575553894,
|
|
"epoch": 0.6820365033621518,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00049612487359482,
|
|
"loss": 5.5355,
|
|
"mean_token_accuracy": 0.18614646792411804,
|
|
"num_tokens": 16285623.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.355951929092408,
|
|
"epoch": 0.6825168107588857,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004961185356213062,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.19960283786058425,
|
|
"num_tokens": 16296242.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.445132923126221,
|
|
"epoch": 0.6829971181556196,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004961121925140767,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.18793877810239792,
|
|
"num_tokens": 16308400.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.470288705825806,
|
|
"epoch": 0.6834774255523535,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004961058442732786,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.18972494900226594,
|
|
"num_tokens": 16319201.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.4567423343658445,
|
|
"epoch": 0.6839577329490875,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004960994908990594,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.18735696971416474,
|
|
"num_tokens": 16331462.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.435454034805298,
|
|
"epoch": 0.6844380403458213,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004960931323915665,
|
|
"loss": 5.3607,
|
|
"mean_token_accuracy": 0.18979617804288865,
|
|
"num_tokens": 16343428.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.474292659759522,
|
|
"epoch": 0.6849183477425552,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004960867687509475,
|
|
"loss": 5.2421,
|
|
"mean_token_accuracy": 0.19473725706338882,
|
|
"num_tokens": 16356270.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.35652437210083,
|
|
"epoch": 0.6853986551392891,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004960803999773504,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.19021278172731398,
|
|
"num_tokens": 16367039.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.306606674194336,
|
|
"epoch": 0.6858789625360231,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004960740260709228,
|
|
"loss": 5.3453,
|
|
"mean_token_accuracy": 0.19168916046619416,
|
|
"num_tokens": 16378601.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.479401254653931,
|
|
"epoch": 0.686359269932757,
|
|
"grad_norm": 6.59375,
|
|
"learning_rate": 0.0004960676470318128,
|
|
"loss": 5.3885,
|
|
"mean_token_accuracy": 0.1916048139333725,
|
|
"num_tokens": 16391096.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.389495229721069,
|
|
"epoch": 0.6868395773294909,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004960612628601683,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.1973610907793045,
|
|
"num_tokens": 16401527.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.425680160522461,
|
|
"epoch": 0.6873198847262247,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004960548735561379,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.17701541036367416,
|
|
"num_tokens": 16413948.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.4044373512268065,
|
|
"epoch": 0.6878001921229587,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004960484791198697,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.19330644607543945,
|
|
"num_tokens": 16425718.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.375082635879517,
|
|
"epoch": 0.6882804995196926,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004960420795515121,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.19107518941164017,
|
|
"num_tokens": 16437606.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.441378784179688,
|
|
"epoch": 0.6887608069164265,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004960356748512138,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.19059857875108718,
|
|
"num_tokens": 16448964.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.374948358535766,
|
|
"epoch": 0.6892411143131604,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004960292650191236,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.1918066069483757,
|
|
"num_tokens": 16459974.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.420234155654907,
|
|
"epoch": 0.6897214217098944,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004960228500553899,
|
|
"loss": 5.2751,
|
|
"mean_token_accuracy": 0.18620239049196244,
|
|
"num_tokens": 16471143.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.381014966964722,
|
|
"epoch": 0.6902017291066282,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004960164299601623,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.19609259814023972,
|
|
"num_tokens": 16482090.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.330925703048706,
|
|
"epoch": 0.6906820365033621,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004960100047335892,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.19356450587511062,
|
|
"num_tokens": 16493695.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.465975570678711,
|
|
"epoch": 0.691162343900096,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004960035743758202,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.189803908765316,
|
|
"num_tokens": 16505317.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.43049807548523,
|
|
"epoch": 0.69164265129683,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004959971388870044,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.1919502481818199,
|
|
"num_tokens": 16516719.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.382589673995971,
|
|
"epoch": 0.6921229586935639,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004959906982672912,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.19547758549451827,
|
|
"num_tokens": 16528302.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.351429414749146,
|
|
"epoch": 0.6926032660902978,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004959842525168302,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.18983298689126968,
|
|
"num_tokens": 16538471.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.440526485443115,
|
|
"epoch": 0.6930835734870316,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004959778016357712,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.1949208378791809,
|
|
"num_tokens": 16549283.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.3660050392150875,
|
|
"epoch": 0.6935638808837656,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004959713456242637,
|
|
"loss": 5.2603,
|
|
"mean_token_accuracy": 0.18636907190084456,
|
|
"num_tokens": 16560895.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.37461838722229,
|
|
"epoch": 0.6940441882804995,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004959648844824576,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.191277414560318,
|
|
"num_tokens": 16571306.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.417568969726562,
|
|
"epoch": 0.6945244956772334,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004959584182105032,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.19584214687347412,
|
|
"num_tokens": 16582399.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.346726608276367,
|
|
"epoch": 0.6950048030739674,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004959519468085504,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.19755541235208512,
|
|
"num_tokens": 16593617.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.332418775558471,
|
|
"epoch": 0.6954851104707013,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004959454702767494,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.19345726519823075,
|
|
"num_tokens": 16604109.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.483483839035034,
|
|
"epoch": 0.6959654178674352,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004959389886152507,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.18649379312992095,
|
|
"num_tokens": 16616007.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.439164161682129,
|
|
"epoch": 0.696445725264169,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004959325018242048,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.19164157062768936,
|
|
"num_tokens": 16627609.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.414792919158936,
|
|
"epoch": 0.696926032660903,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004959260099037622,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.18888843655586243,
|
|
"num_tokens": 16639842.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.451376724243164,
|
|
"epoch": 0.6974063400576369,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004959195128540737,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.17943353950977325,
|
|
"num_tokens": 16651620.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.394506216049194,
|
|
"epoch": 0.6978866474543708,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00049591301067529,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.1885972186923027,
|
|
"num_tokens": 16663637.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.396517658233643,
|
|
"epoch": 0.6983669548511047,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004959065033675623,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.18626101613044738,
|
|
"num_tokens": 16675685.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.468096828460693,
|
|
"epoch": 0.6988472622478387,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004958999909310414,
|
|
"loss": 5.2928,
|
|
"mean_token_accuracy": 0.18408166319131852,
|
|
"num_tokens": 16686268.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.377413988113403,
|
|
"epoch": 0.6993275696445725,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004958934733658788,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.1924181893467903,
|
|
"num_tokens": 16698382.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.456994152069091,
|
|
"epoch": 0.6998078770413064,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004958869506722256,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.18200154155492781,
|
|
"num_tokens": 16710421.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.4129057884216305,
|
|
"epoch": 0.7002881844380403,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004958804228502332,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.19510667622089387,
|
|
"num_tokens": 16721658.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.373976945877075,
|
|
"epoch": 0.7007684918347743,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004958738899000534,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.19303322732448577,
|
|
"num_tokens": 16734100.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.306042098999024,
|
|
"epoch": 0.7012487992315082,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004958673518218377,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.19008474051952362,
|
|
"num_tokens": 16746386.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.457220983505249,
|
|
"epoch": 0.7017291066282421,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004958608086157379,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.1953557088971138,
|
|
"num_tokens": 16756967.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.366976404190064,
|
|
"epoch": 0.7022094140249759,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000495854260281906,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.1987711861729622,
|
|
"num_tokens": 16767454.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.294095659255982,
|
|
"epoch": 0.7026897214217099,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004958477068204941,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.1918737694621086,
|
|
"num_tokens": 16779533.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.4249396324157715,
|
|
"epoch": 0.7031700288184438,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000495841148231654,
|
|
"loss": 5.3351,
|
|
"mean_token_accuracy": 0.18856797367334366,
|
|
"num_tokens": 16792019.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.36957893371582,
|
|
"epoch": 0.7036503362151777,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004958345845155383,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.193443001806736,
|
|
"num_tokens": 16803089.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.37037410736084,
|
|
"epoch": 0.7041306436119116,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004958280156722992,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.1954813063144684,
|
|
"num_tokens": 16813651.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.35937762260437,
|
|
"epoch": 0.7046109510086456,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004958214417020894,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.1992407187819481,
|
|
"num_tokens": 16825460.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.320385265350342,
|
|
"epoch": 0.7050912584053795,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004958148626050614,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.19488627314567566,
|
|
"num_tokens": 16836344.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.401589012145996,
|
|
"epoch": 0.7055715658021133,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000495808278381368,
|
|
"loss": 5.2885,
|
|
"mean_token_accuracy": 0.19181105196475984,
|
|
"num_tokens": 16848274.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.4050452709198,
|
|
"epoch": 0.7060518731988472,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000495801689031162,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.1882026121020317,
|
|
"num_tokens": 16860363.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.364719724655151,
|
|
"epoch": 0.7065321805955812,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004957950945545965,
|
|
"loss": 5.2793,
|
|
"mean_token_accuracy": 0.19339021742343904,
|
|
"num_tokens": 16872037.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.470697450637817,
|
|
"epoch": 0.7070124879923151,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004957884949518246,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.1876761481165886,
|
|
"num_tokens": 16883845.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.4732177734375,
|
|
"epoch": 0.707492795389049,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004957818902229992,
|
|
"loss": 5.3377,
|
|
"mean_token_accuracy": 0.18597989976406099,
|
|
"num_tokens": 16894965.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.3630016326904295,
|
|
"epoch": 0.7079731027857828,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004957752803682741,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.1854296952486038,
|
|
"num_tokens": 16907475.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.355823707580567,
|
|
"epoch": 0.7084534101825168,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004957686653878024,
|
|
"loss": 5.2242,
|
|
"mean_token_accuracy": 0.19145250618457793,
|
|
"num_tokens": 16918825.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.425852203369141,
|
|
"epoch": 0.7089337175792507,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000495762045281738,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.19509863257408142,
|
|
"num_tokens": 16930663.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.394859647750854,
|
|
"epoch": 0.7094140249759846,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004957554200502344,
|
|
"loss": 5.3009,
|
|
"mean_token_accuracy": 0.19530547708272933,
|
|
"num_tokens": 16942089.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.339275598526001,
|
|
"epoch": 0.7098943323727186,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004957487896934454,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.19127538353204726,
|
|
"num_tokens": 16954203.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.370598554611206,
|
|
"epoch": 0.7103746397694525,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000495742154211525,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.19286420345306396,
|
|
"num_tokens": 16966047.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.281306743621826,
|
|
"epoch": 0.7108549471661864,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004957355136046272,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.19679884910583495,
|
|
"num_tokens": 16977726.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.350837755203247,
|
|
"epoch": 0.7113352545629202,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004957288678729064,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.19669270366430283,
|
|
"num_tokens": 16990917.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.348010396957397,
|
|
"epoch": 0.7118155619596542,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004957222170165166,
|
|
"loss": 5.2776,
|
|
"mean_token_accuracy": 0.1934112176299095,
|
|
"num_tokens": 17001703.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.335374593734741,
|
|
"epoch": 0.7122958693563881,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004957155610356124,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.19498712420463563,
|
|
"num_tokens": 17011918.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.462284994125366,
|
|
"epoch": 0.712776176753122,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004957088999303481,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.19242413192987443,
|
|
"num_tokens": 17022653.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.329063081741333,
|
|
"epoch": 0.7132564841498559,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004957022337008787,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.19977978318929673,
|
|
"num_tokens": 17034775.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.319195938110352,
|
|
"epoch": 0.7137367915465899,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004956955623473587,
|
|
"loss": 5.2562,
|
|
"mean_token_accuracy": 0.18822196871042252,
|
|
"num_tokens": 17046835.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.493042373657227,
|
|
"epoch": 0.7142170989433237,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000495688885869943,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.190398208796978,
|
|
"num_tokens": 17059163.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.408080959320069,
|
|
"epoch": 0.7146974063400576,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004956822042687868,
|
|
"loss": 5.3508,
|
|
"mean_token_accuracy": 0.18790239095687866,
|
|
"num_tokens": 17070777.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.421570777893066,
|
|
"epoch": 0.7151777137367915,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004956755175440451,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.19134521931409837,
|
|
"num_tokens": 17083770.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.404145669937134,
|
|
"epoch": 0.7156580211335255,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004956688256958731,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.19096972942352294,
|
|
"num_tokens": 17096049.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.298589134216309,
|
|
"epoch": 0.7161383285302594,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004956621287244262,
|
|
"loss": 5.1809,
|
|
"mean_token_accuracy": 0.19574082046747207,
|
|
"num_tokens": 17107030.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.278734397888184,
|
|
"epoch": 0.7166186359269933,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004956554266298599,
|
|
"loss": 5.2637,
|
|
"mean_token_accuracy": 0.19119612127542496,
|
|
"num_tokens": 17118638.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.41753511428833,
|
|
"epoch": 0.7170989433237271,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004956487194123298,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.19086818844079972,
|
|
"num_tokens": 17129783.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.431677532196045,
|
|
"epoch": 0.7175792507204611,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004956420070719918,
|
|
"loss": 5.332,
|
|
"mean_token_accuracy": 0.18988775610923767,
|
|
"num_tokens": 17141939.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.384487867355347,
|
|
"epoch": 0.718059558117195,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004956352896090014,
|
|
"loss": 5.2859,
|
|
"mean_token_accuracy": 0.19325017035007477,
|
|
"num_tokens": 17153471.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.444349908828736,
|
|
"epoch": 0.7185398655139289,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004956285670235147,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.18837197571992875,
|
|
"num_tokens": 17164659.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.440321207046509,
|
|
"epoch": 0.7190201729106628,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004956218393156879,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.19292935729026794,
|
|
"num_tokens": 17175749.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.392650842666626,
|
|
"epoch": 0.7195004803073968,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004956151064856772,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.18586882054805756,
|
|
"num_tokens": 17187482.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.39450421333313,
|
|
"epoch": 0.7199807877041307,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004956083685336386,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.19471026808023453,
|
|
"num_tokens": 17199904.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.371392869949341,
|
|
"epoch": 0.7204610951008645,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004956016254597289,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.1884932443499565,
|
|
"num_tokens": 17210649.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.381744050979615,
|
|
"epoch": 0.7209414024975984,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004955948772641044,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.18555935770273208,
|
|
"num_tokens": 17223069.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.397015047073364,
|
|
"epoch": 0.7214217098943324,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000495588123946922,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.19745109379291534,
|
|
"num_tokens": 17235144.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.370836496353149,
|
|
"epoch": 0.7219020172910663,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004955813655083384,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.19031732231378556,
|
|
"num_tokens": 17246816.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.378262948989868,
|
|
"epoch": 0.7223823246878002,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004955746019485104,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.19473235309123993,
|
|
"num_tokens": 17259056.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.463152456283569,
|
|
"epoch": 0.722862632084534,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000495567833267595,
|
|
"loss": 5.3161,
|
|
"mean_token_accuracy": 0.1908079132437706,
|
|
"num_tokens": 17270391.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.449782848358154,
|
|
"epoch": 0.723342939481268,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004955610594657496,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.19024159759283066,
|
|
"num_tokens": 17281608.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.404439258575439,
|
|
"epoch": 0.7238232468780019,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004955542805431313,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.18304315954446793,
|
|
"num_tokens": 17293649.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.381678247451783,
|
|
"epoch": 0.7243035542747358,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004955474964998976,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.18936212956905366,
|
|
"num_tokens": 17305548.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.446031618118286,
|
|
"epoch": 0.7247838616714697,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004955407073362058,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.19551405757665635,
|
|
"num_tokens": 17317380.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.356749391555786,
|
|
"epoch": 0.7252641690682037,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004955339130522136,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.18997751474380492,
|
|
"num_tokens": 17329263.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.453513860702515,
|
|
"epoch": 0.7257444764649376,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000495527113648079,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.18590964376926422,
|
|
"num_tokens": 17343268.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.436152791976928,
|
|
"epoch": 0.7262247838616714,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004955203091239596,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.20218702405691147,
|
|
"num_tokens": 17353979.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.366891670227051,
|
|
"epoch": 0.7267050912584054,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004955134994800134,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.1873335897922516,
|
|
"num_tokens": 17367587.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.4155841827392575,
|
|
"epoch": 0.7271853986551393,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004955066847163984,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.18941086679697036,
|
|
"num_tokens": 17379093.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.461610507965088,
|
|
"epoch": 0.7276657060518732,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004954998648332731,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.19426215440034866,
|
|
"num_tokens": 17391254.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.329599523544312,
|
|
"epoch": 0.7281460134486071,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004954930398307956,
|
|
"loss": 5.2857,
|
|
"mean_token_accuracy": 0.1910361185669899,
|
|
"num_tokens": 17402532.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.429715776443482,
|
|
"epoch": 0.7286263208453411,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004954862097091245,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.19515106827020645,
|
|
"num_tokens": 17413849.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.343151712417603,
|
|
"epoch": 0.729106628242075,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004954793744684184,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.20000943094491958,
|
|
"num_tokens": 17424982.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.460010099411011,
|
|
"epoch": 0.7295869356388088,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004954725341088358,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.179095321893692,
|
|
"num_tokens": 17437774.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.454359292984009,
|
|
"epoch": 0.7300672430355427,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004954656886305356,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.19837107956409455,
|
|
"num_tokens": 17448676.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.436759281158447,
|
|
"epoch": 0.7305475504322767,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004954588380336768,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.194442480802536,
|
|
"num_tokens": 17459576.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.30203104019165,
|
|
"epoch": 0.7310278578290106,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004954519823184184,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.2036220461130142,
|
|
"num_tokens": 17471220.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.369773244857788,
|
|
"epoch": 0.7315081652257445,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004954451214849196,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.18353285491466523,
|
|
"num_tokens": 17483939.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.437369537353516,
|
|
"epoch": 0.7319884726224783,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004954382555333397,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.196310655772686,
|
|
"num_tokens": 17496058.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.3552384853363035,
|
|
"epoch": 0.7324687800192123,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000495431384463838,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.1946453332901001,
|
|
"num_tokens": 17507750.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.347149848937988,
|
|
"epoch": 0.7329490874159462,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004954245082765741,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.2009843945503235,
|
|
"num_tokens": 17520208.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.397583436965943,
|
|
"epoch": 0.7334293948126801,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004954176269717077,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.1947871431708336,
|
|
"num_tokens": 17531655.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.329985284805298,
|
|
"epoch": 0.733909702209414,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004954107405493984,
|
|
"loss": 5.2555,
|
|
"mean_token_accuracy": 0.19235846996307374,
|
|
"num_tokens": 17543766.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.432396936416626,
|
|
"epoch": 0.734390009606148,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004954038490098064,
|
|
"loss": 5.3427,
|
|
"mean_token_accuracy": 0.18324017971754075,
|
|
"num_tokens": 17555710.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.334878444671631,
|
|
"epoch": 0.7348703170028819,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004953969523530914,
|
|
"loss": 5.2101,
|
|
"mean_token_accuracy": 0.19792094230651855,
|
|
"num_tokens": 17566674.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.4214776992797855,
|
|
"epoch": 0.7353506243996157,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004953900505794136,
|
|
"loss": 5.3163,
|
|
"mean_token_accuracy": 0.19025304466485976,
|
|
"num_tokens": 17579320.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.4200674533844,
|
|
"epoch": 0.7358309317963496,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004953831436889332,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.1850394368171692,
|
|
"num_tokens": 17590679.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.367720127105713,
|
|
"epoch": 0.7363112391930836,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004953762316818106,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.20518195927143096,
|
|
"num_tokens": 17600928.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.2725715160369875,
|
|
"epoch": 0.7367915465898175,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004953693145582064,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.20383870005607604,
|
|
"num_tokens": 17611906.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.323664426803589,
|
|
"epoch": 0.7372718539865514,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000495362392318281,
|
|
"loss": 5.3641,
|
|
"mean_token_accuracy": 0.19108777940273286,
|
|
"num_tokens": 17623165.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.452879619598389,
|
|
"epoch": 0.7377521613832853,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004953554649621951,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.19726396799087526,
|
|
"num_tokens": 17633632.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.3472850799560545,
|
|
"epoch": 0.7382324687800192,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004953485324901098,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.19999130070209503,
|
|
"num_tokens": 17644801.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.3102232933044435,
|
|
"epoch": 0.7387127761767531,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004953415949021857,
|
|
"loss": 5.2822,
|
|
"mean_token_accuracy": 0.18756644278764725,
|
|
"num_tokens": 17656852.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.41955976486206,
|
|
"epoch": 0.739193083573487,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004953346521985843,
|
|
"loss": 5.2921,
|
|
"mean_token_accuracy": 0.1916919767856598,
|
|
"num_tokens": 17667538.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.335768604278565,
|
|
"epoch": 0.7396733909702209,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004953277043794663,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.19577167481184005,
|
|
"num_tokens": 17680049.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.317630386352539,
|
|
"epoch": 0.7401536983669549,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004953207514449933,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.1916391983628273,
|
|
"num_tokens": 17692611.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.385031509399414,
|
|
"epoch": 0.7406340057636888,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004953137933953267,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.1983467757701874,
|
|
"num_tokens": 17704145.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.448598766326905,
|
|
"epoch": 0.7411143131604226,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000495306830230628,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.18565167784690856,
|
|
"num_tokens": 17715467.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.377538251876831,
|
|
"epoch": 0.7415946205571565,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004952998619510589,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.19642675668001175,
|
|
"num_tokens": 17726709.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.3718647956848145,
|
|
"epoch": 0.7420749279538905,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004952928885567811,
|
|
"loss": 5.2173,
|
|
"mean_token_accuracy": 0.20163513571023942,
|
|
"num_tokens": 17736896.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.421212959289551,
|
|
"epoch": 0.7425552353506244,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004952859100479566,
|
|
"loss": 5.2949,
|
|
"mean_token_accuracy": 0.18503678739070892,
|
|
"num_tokens": 17747658.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.380327463150024,
|
|
"epoch": 0.7430355427473583,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004952789264247474,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.1982392832636833,
|
|
"num_tokens": 17757833.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.331891298294067,
|
|
"epoch": 0.7435158501440923,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004952719376873156,
|
|
"loss": 5.2377,
|
|
"mean_token_accuracy": 0.1930388405919075,
|
|
"num_tokens": 17769144.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.41746940612793,
|
|
"epoch": 0.7439961575408262,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004952649438358234,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.18804989010095596,
|
|
"num_tokens": 17781357.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.495258522033692,
|
|
"epoch": 0.74447646493756,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004952579448704334,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.1938771441578865,
|
|
"num_tokens": 17793640.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.374048852920533,
|
|
"epoch": 0.7449567723342939,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000495250940791308,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.18867946565151214,
|
|
"num_tokens": 17804228.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.355391120910644,
|
|
"epoch": 0.7454370797310279,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004952439315986096,
|
|
"loss": 5.2884,
|
|
"mean_token_accuracy": 0.19074462354183197,
|
|
"num_tokens": 17816153.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.3792389869689945,
|
|
"epoch": 0.7459173871277618,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004952369172925012,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.1932196393609047,
|
|
"num_tokens": 17828464.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.308259391784668,
|
|
"epoch": 0.7463976945244957,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004952298978731454,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.19391650408506395,
|
|
"num_tokens": 17840126.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.339615297317505,
|
|
"epoch": 0.7468780019212296,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004952228733407055,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.19899795949459076,
|
|
"num_tokens": 17851735.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.43651967048645,
|
|
"epoch": 0.7473583093179635,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004952158436953444,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.1948774352669716,
|
|
"num_tokens": 17862897.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.3573570728302,
|
|
"epoch": 0.7478386167146974,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004952088089372252,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.19403435289859772,
|
|
"num_tokens": 17874235.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.35567569732666,
|
|
"epoch": 0.7483189241114313,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004952017690665114,
|
|
"loss": 5.302,
|
|
"mean_token_accuracy": 0.19129539281129837,
|
|
"num_tokens": 17885677.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.369703149795532,
|
|
"epoch": 0.7487992315081652,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004951947240833664,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.19623667746782303,
|
|
"num_tokens": 17896204.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.466663122177124,
|
|
"epoch": 0.7492795389048992,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004951876739879537,
|
|
"loss": 5.3103,
|
|
"mean_token_accuracy": 0.19217686206102372,
|
|
"num_tokens": 17908514.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.406633090972901,
|
|
"epoch": 0.7497598463016331,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004951806187804371,
|
|
"loss": 5.1962,
|
|
"mean_token_accuracy": 0.20257627815008164,
|
|
"num_tokens": 17918493.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.3837216854095455,
|
|
"epoch": 0.7502401536983669,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004951735584609804,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.20404653251171112,
|
|
"num_tokens": 17929016.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.27390456199646,
|
|
"epoch": 0.7507204610951008,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004951664930297474,
|
|
"loss": 5.266,
|
|
"mean_token_accuracy": 0.1927507683634758,
|
|
"num_tokens": 17940674.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.417548131942749,
|
|
"epoch": 0.7512007684918348,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000495159422486902,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.19038532227277755,
|
|
"num_tokens": 17951431.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.526469707489014,
|
|
"epoch": 0.7516810758885687,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004951523468326088,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.18628415912389756,
|
|
"num_tokens": 17961434.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.267174339294433,
|
|
"epoch": 0.7521613832853026,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004951452660670317,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.20382616072893142,
|
|
"num_tokens": 17971917.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.352742862701416,
|
|
"epoch": 0.7526416906820365,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004951381801903352,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.1986750155687332,
|
|
"num_tokens": 17983754.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.343587589263916,
|
|
"epoch": 0.7531219980787704,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004951310892026839,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.19234987646341323,
|
|
"num_tokens": 17994088.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.373450660705567,
|
|
"epoch": 0.7536023054755043,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004951239931042424,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.19949763566255568,
|
|
"num_tokens": 18004847.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.313560152053833,
|
|
"epoch": 0.7540826128722382,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004951168918951753,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.20220328867435455,
|
|
"num_tokens": 18015756.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.335494136810302,
|
|
"epoch": 0.7545629202689721,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004951097855756476,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.18886298090219497,
|
|
"num_tokens": 18026417.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.381666135787964,
|
|
"epoch": 0.7550432276657061,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004951026741458243,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.19316712468862535,
|
|
"num_tokens": 18038205.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.433653688430786,
|
|
"epoch": 0.75552353506244,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004950955576058705,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.1950031191110611,
|
|
"num_tokens": 18049223.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.418736457824707,
|
|
"epoch": 0.7560038424591738,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004950884359559513,
|
|
"loss": 5.2724,
|
|
"mean_token_accuracy": 0.19370467960834503,
|
|
"num_tokens": 18061855.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.3388352394104,
|
|
"epoch": 0.7564841498559077,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004950813091962324,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.19691956490278245,
|
|
"num_tokens": 18073969.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.368044805526734,
|
|
"epoch": 0.7569644572526417,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004950741773268788,
|
|
"loss": 5.2018,
|
|
"mean_token_accuracy": 0.19612170457839967,
|
|
"num_tokens": 18085786.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.408827543258667,
|
|
"epoch": 0.7574447646493756,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004950670403480562,
|
|
"loss": 5.2151,
|
|
"mean_token_accuracy": 0.1967058449983597,
|
|
"num_tokens": 18096263.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.3796820640563965,
|
|
"epoch": 0.7579250720461095,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004950598982599306,
|
|
"loss": 5.3299,
|
|
"mean_token_accuracy": 0.18323681950569154,
|
|
"num_tokens": 18108769.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.384113502502442,
|
|
"epoch": 0.7584053794428435,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004950527510626675,
|
|
"loss": 5.3382,
|
|
"mean_token_accuracy": 0.19338110387325286,
|
|
"num_tokens": 18120255.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.396039915084839,
|
|
"epoch": 0.7588856868395774,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004950455987564329,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.1955770120024681,
|
|
"num_tokens": 18132016.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.34745602607727,
|
|
"epoch": 0.7593659942363112,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004950384413413931,
|
|
"loss": 5.2139,
|
|
"mean_token_accuracy": 0.19548893719911575,
|
|
"num_tokens": 18144101.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.4066825866699215,
|
|
"epoch": 0.7598463016330451,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004950312788177139,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.19860927909612655,
|
|
"num_tokens": 18155086.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.38053789138794,
|
|
"epoch": 0.7603266090297791,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004950241111855618,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.19188836514949797,
|
|
"num_tokens": 18166902.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.398432874679566,
|
|
"epoch": 0.760806916426513,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004950169384451031,
|
|
"loss": 5.2484,
|
|
"mean_token_accuracy": 0.19742103517055512,
|
|
"num_tokens": 18178258.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.36683759689331,
|
|
"epoch": 0.7612872238232469,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004950097605965045,
|
|
"loss": 5.2931,
|
|
"mean_token_accuracy": 0.19071005284786224,
|
|
"num_tokens": 18190580.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.421039676666259,
|
|
"epoch": 0.7617675312199808,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004950025776399326,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.18787630051374435,
|
|
"num_tokens": 18204912.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.378742361068726,
|
|
"epoch": 0.7622478386167147,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000494995389575554,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.19148027151823044,
|
|
"num_tokens": 18215129.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.417219114303589,
|
|
"epoch": 0.7627281460134486,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004949881964035357,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.1875670626759529,
|
|
"num_tokens": 18225640.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.377304887771606,
|
|
"epoch": 0.7632084534101825,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004949809981240448,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.19860284626483918,
|
|
"num_tokens": 18236641.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.315788221359253,
|
|
"epoch": 0.7636887608069164,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004949737947372483,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.1945876345038414,
|
|
"num_tokens": 18249244.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.4028219223022464,
|
|
"epoch": 0.7641690682036504,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004949665862433134,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.1907445564866066,
|
|
"num_tokens": 18261595.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.424557638168335,
|
|
"epoch": 0.7646493756003843,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004949593726424077,
|
|
"loss": 5.2758,
|
|
"mean_token_accuracy": 0.19563941806554794,
|
|
"num_tokens": 18272609.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.44644021987915,
|
|
"epoch": 0.7651296829971181,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004949521539346985,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.19190972447395324,
|
|
"num_tokens": 18283886.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.404463243484497,
|
|
"epoch": 0.765609990393852,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004949449301203533,
|
|
"loss": 5.3161,
|
|
"mean_token_accuracy": 0.19465096443891525,
|
|
"num_tokens": 18294794.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.495356655120849,
|
|
"epoch": 0.766090297790586,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004949377011995399,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.19217901527881623,
|
|
"num_tokens": 18306250.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.421238994598388,
|
|
"epoch": 0.7665706051873199,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004949304671724263,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.19345854967832565,
|
|
"num_tokens": 18317743.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.295167398452759,
|
|
"epoch": 0.7670509125840538,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004949232280391802,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.19705990701913834,
|
|
"num_tokens": 18328287.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.365210819244385,
|
|
"epoch": 0.7675312199807877,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004949159837999698,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.18874591141939162,
|
|
"num_tokens": 18341354.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.432317066192627,
|
|
"epoch": 0.7680115273775217,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004949087344549633,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.1904577851295471,
|
|
"num_tokens": 18353822.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.516468906402588,
|
|
"epoch": 0.7684918347742555,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000494901480004329,
|
|
"loss": 5.2823,
|
|
"mean_token_accuracy": 0.1891055792570114,
|
|
"num_tokens": 18365491.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.250404500961304,
|
|
"epoch": 0.7689721421709894,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004948942204482351,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.19362736195325853,
|
|
"num_tokens": 18376329.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.385899353027344,
|
|
"epoch": 0.7694524495677233,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004948869557868506,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.18819482922554015,
|
|
"num_tokens": 18387105.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.412772226333618,
|
|
"epoch": 0.7699327569644573,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004948796860203439,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.19209769666194915,
|
|
"num_tokens": 18398113.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.367074108123779,
|
|
"epoch": 0.7704130643611912,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004948724111488838,
|
|
"loss": 5.251,
|
|
"mean_token_accuracy": 0.19539596289396285,
|
|
"num_tokens": 18409315.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.292338895797729,
|
|
"epoch": 0.770893371757925,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004948651311726391,
|
|
"loss": 5.281,
|
|
"mean_token_accuracy": 0.1888511836528778,
|
|
"num_tokens": 18421110.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.429877138137817,
|
|
"epoch": 0.7713736791546589,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004948578460917789,
|
|
"loss": 5.3334,
|
|
"mean_token_accuracy": 0.19012463837862015,
|
|
"num_tokens": 18433145.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.47140908241272,
|
|
"epoch": 0.7718539865513929,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004948505559064725,
|
|
"loss": 5.2776,
|
|
"mean_token_accuracy": 0.18811897039413453,
|
|
"num_tokens": 18444689.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.337078332901001,
|
|
"epoch": 0.7723342939481268,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004948432606168889,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.19592492282390594,
|
|
"num_tokens": 18455943.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.2788911819458,
|
|
"epoch": 0.7728146013448607,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004948359602231976,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.2019103229045868,
|
|
"num_tokens": 18466763.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.392308759689331,
|
|
"epoch": 0.7732949087415946,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004948286547255681,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.18780143260955812,
|
|
"num_tokens": 18477647.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.381778860092163,
|
|
"epoch": 0.7737752161383286,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00049482134412417,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.2007139027118683,
|
|
"num_tokens": 18488465.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.4515125274658205,
|
|
"epoch": 0.7742555235350624,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000494814028419173,
|
|
"loss": 5.3597,
|
|
"mean_token_accuracy": 0.19449682384729386,
|
|
"num_tokens": 18500705.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.380729055404663,
|
|
"epoch": 0.7747358309317963,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000494806707610747,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.19191479235887526,
|
|
"num_tokens": 18512253.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.349826765060425,
|
|
"epoch": 0.7752161383285303,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000494799381699062,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.19469085335731506,
|
|
"num_tokens": 18524231.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.452904129028321,
|
|
"epoch": 0.7756964457252642,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004947920506842879,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.19417499154806137,
|
|
"num_tokens": 18535824.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.4485352516174315,
|
|
"epoch": 0.7761767531219981,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004947847145665951,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.19426287114620208,
|
|
"num_tokens": 18547957.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.360448169708252,
|
|
"epoch": 0.776657060518732,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004947773733461539,
|
|
"loss": 5.2797,
|
|
"mean_token_accuracy": 0.19322233349084855,
|
|
"num_tokens": 18559297.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.406730127334595,
|
|
"epoch": 0.777137367915466,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004947700270231347,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.19115198105573655,
|
|
"num_tokens": 18570264.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.387463092803955,
|
|
"epoch": 0.7776176753121998,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004947626755977079,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.19484462589025497,
|
|
"num_tokens": 18582417.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.390276765823364,
|
|
"epoch": 0.7780979827089337,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004947553190700444,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.1876293435692787,
|
|
"num_tokens": 18593703.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.36275954246521,
|
|
"epoch": 0.7785782901056676,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000494747957440315,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.19769291430711747,
|
|
"num_tokens": 18605050.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.386284637451172,
|
|
"epoch": 0.7790585975024016,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004947405907086905,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.18341726958751678,
|
|
"num_tokens": 18616962.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.396425199508667,
|
|
"epoch": 0.7795389048991355,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004947332188753419,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.19090291112661362,
|
|
"num_tokens": 18628640.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.400382232666016,
|
|
"epoch": 0.7800192122958693,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004947258419404405,
|
|
"loss": 5.2946,
|
|
"mean_token_accuracy": 0.19053932577371596,
|
|
"num_tokens": 18640488.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.335408306121826,
|
|
"epoch": 0.7804995196926032,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004947184599041576,
|
|
"loss": 5.2627,
|
|
"mean_token_accuracy": 0.19515257328748703,
|
|
"num_tokens": 18652095.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.381952476501465,
|
|
"epoch": 0.7809798270893372,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004947110727666644,
|
|
"loss": 5.2348,
|
|
"mean_token_accuracy": 0.19744855910539627,
|
|
"num_tokens": 18662767.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.389344978332519,
|
|
"epoch": 0.7814601344860711,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004947036805281325,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.19188299775123596,
|
|
"num_tokens": 18673568.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.387752056121826,
|
|
"epoch": 0.781940441882805,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004946962831887336,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.20563167780637742,
|
|
"num_tokens": 18684456.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.382151746749878,
|
|
"epoch": 0.7824207492795389,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004946888807486393,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.18668509572744368,
|
|
"num_tokens": 18695942.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.488183069229126,
|
|
"epoch": 0.7829010566762729,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004946814732080214,
|
|
"loss": 5.3408,
|
|
"mean_token_accuracy": 0.19334076195955277,
|
|
"num_tokens": 18708110.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.477972316741943,
|
|
"epoch": 0.7833813640730067,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004946740605670523,
|
|
"loss": 5.3308,
|
|
"mean_token_accuracy": 0.19009837210178376,
|
|
"num_tokens": 18718864.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.338687753677368,
|
|
"epoch": 0.7838616714697406,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004946666428259037,
|
|
"loss": 5.2142,
|
|
"mean_token_accuracy": 0.19310434758663178,
|
|
"num_tokens": 18730338.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.368350887298584,
|
|
"epoch": 0.7843419788664745,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004946592199847478,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.18230630159378053,
|
|
"num_tokens": 18743433.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.415580177307129,
|
|
"epoch": 0.7848222862632085,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004946517920437571,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.19327433109283448,
|
|
"num_tokens": 18754631.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.390597867965698,
|
|
"epoch": 0.7853025936599424,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004946443590031041,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.19704635739326476,
|
|
"num_tokens": 18766118.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.418410730361939,
|
|
"epoch": 0.7857829010566763,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004946369208629613,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.1961783766746521,
|
|
"num_tokens": 18777743.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.338965368270874,
|
|
"epoch": 0.7862632084534101,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004946294776235013,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.19982785433530809,
|
|
"num_tokens": 18789684.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.253990411758423,
|
|
"epoch": 0.7867435158501441,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004946220292848971,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.19799993932247162,
|
|
"num_tokens": 18801088.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.375244569778443,
|
|
"epoch": 0.787223823246878,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004946145758473214,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.1825365826487541,
|
|
"num_tokens": 18812478.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.544604301452637,
|
|
"epoch": 0.7877041306436119,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004946071173109475,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.1940308019518852,
|
|
"num_tokens": 18823573.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.3184661865234375,
|
|
"epoch": 0.7881844380403458,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004945996536759484,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.19500154703855516,
|
|
"num_tokens": 18833880.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.326853466033936,
|
|
"epoch": 0.7886647454370798,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004945921849424974,
|
|
"loss": 5.1911,
|
|
"mean_token_accuracy": 0.19733449518680574,
|
|
"num_tokens": 18844367.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.410817670822143,
|
|
"epoch": 0.7891450528338136,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004945847111107679,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.18654292076826096,
|
|
"num_tokens": 18856309.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.408186960220337,
|
|
"epoch": 0.7896253602305475,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004945772321809334,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.19013492614030839,
|
|
"num_tokens": 18868873.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.32963228225708,
|
|
"epoch": 0.7901056676272814,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004945697481531677,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.19453502595424652,
|
|
"num_tokens": 18879953.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.444918251037597,
|
|
"epoch": 0.7905859750240154,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004945622590276443,
|
|
"loss": 5.3386,
|
|
"mean_token_accuracy": 0.18775013834238052,
|
|
"num_tokens": 18892220.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.422673940658569,
|
|
"epoch": 0.7910662824207493,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004945547648045373,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.19337849467992782,
|
|
"num_tokens": 18903261.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.369199991226196,
|
|
"epoch": 0.7915465898174832,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004945472654840206,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.19510689675807952,
|
|
"num_tokens": 18913702.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.452567434310913,
|
|
"epoch": 0.7920268972142172,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004945397610662683,
|
|
"loss": 5.3378,
|
|
"mean_token_accuracy": 0.18533655554056166,
|
|
"num_tokens": 18925024.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.383784341812134,
|
|
"epoch": 0.792507204610951,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004945322515514547,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.2047622248530388,
|
|
"num_tokens": 18935939.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.400283718109131,
|
|
"epoch": 0.7929875120076849,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000494524736939754,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.19320725947618483,
|
|
"num_tokens": 18946091.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.474302816390991,
|
|
"epoch": 0.7934678194044188,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004945172172313408,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.18396852761507035,
|
|
"num_tokens": 18957471.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.493697547912598,
|
|
"epoch": 0.7939481268011528,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004945096924263896,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.1846723437309265,
|
|
"num_tokens": 18969462.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.42394528388977,
|
|
"epoch": 0.7944284341978867,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004945021625250753,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.18909084796905518,
|
|
"num_tokens": 18980228.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.46893630027771,
|
|
"epoch": 0.7949087415946205,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004944946275275724,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.18460303097963332,
|
|
"num_tokens": 18991661.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.4125611782073975,
|
|
"epoch": 0.7953890489913544,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004944870874340561,
|
|
"loss": 5.2921,
|
|
"mean_token_accuracy": 0.19383617490530014,
|
|
"num_tokens": 19003082.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.408040761947632,
|
|
"epoch": 0.7958693563880884,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004944795422447013,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.19174865037202835,
|
|
"num_tokens": 19015408.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.444769048690796,
|
|
"epoch": 0.7963496637848223,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004944719919596835,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.19427991807460784,
|
|
"num_tokens": 19027246.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.418350124359131,
|
|
"epoch": 0.7968299711815562,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004944644365791776,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.20031838566064836,
|
|
"num_tokens": 19038126.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.32525634765625,
|
|
"epoch": 0.7973102785782901,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000494456876103359,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.20074736177921296,
|
|
"num_tokens": 19047998.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.313124275207519,
|
|
"epoch": 0.7977905859750241,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004944493105324035,
|
|
"loss": 5.2991,
|
|
"mean_token_accuracy": 0.18852553218603135,
|
|
"num_tokens": 19058969.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.351770830154419,
|
|
"epoch": 0.7982708933717579,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004944417398664866,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.19643116593360901,
|
|
"num_tokens": 19070314.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.420844650268554,
|
|
"epoch": 0.7987512007684918,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004944341641057843,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.19828618466854095,
|
|
"num_tokens": 19082575.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.296345329284668,
|
|
"epoch": 0.7992315081652257,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004944265832504721,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.19786602556705474,
|
|
"num_tokens": 19095719.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.383054637908936,
|
|
"epoch": 0.7997118155619597,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004944189973007262,
|
|
"loss": 5.2203,
|
|
"mean_token_accuracy": 0.19829194098711014,
|
|
"num_tokens": 19106894.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.3365484237670895,
|
|
"epoch": 0.8001921229586936,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004944114062567229,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.19062076658010482,
|
|
"num_tokens": 19118206.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.404685306549072,
|
|
"epoch": 0.8006724303554275,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004944038101186381,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.18689830750226974,
|
|
"num_tokens": 19129613.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.385619306564331,
|
|
"epoch": 0.8011527377521613,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004943962088866483,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.19819785803556442,
|
|
"num_tokens": 19142214.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.403306579589843,
|
|
"epoch": 0.8016330451488953,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004943886025609301,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.1897999107837677,
|
|
"num_tokens": 19153906.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.396410608291626,
|
|
"epoch": 0.8021133525456292,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00049438099114166,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.18854821920394899,
|
|
"num_tokens": 19163677.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.400742244720459,
|
|
"epoch": 0.8025936599423631,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004943733746290147,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.1931081086397171,
|
|
"num_tokens": 19175240.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.3174515724182125,
|
|
"epoch": 0.803073967339097,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000494365753023171,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.20141686052083968,
|
|
"num_tokens": 19185529.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.325999212265015,
|
|
"epoch": 0.803554274735831,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004943581263243059,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.19571770280599593,
|
|
"num_tokens": 19197153.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.396734189987183,
|
|
"epoch": 0.8040345821325648,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004943504945325965,
|
|
"loss": 5.3914,
|
|
"mean_token_accuracy": 0.18932325541973113,
|
|
"num_tokens": 19208439.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.351518821716309,
|
|
"epoch": 0.8045148895292987,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004943428576482198,
|
|
"loss": 5.2015,
|
|
"mean_token_accuracy": 0.20140155106782914,
|
|
"num_tokens": 19218570.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.352016496658325,
|
|
"epoch": 0.8049951969260326,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004943352156713535,
|
|
"loss": 5.2293,
|
|
"mean_token_accuracy": 0.19814103543758393,
|
|
"num_tokens": 19229080.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.401249790191651,
|
|
"epoch": 0.8054755043227666,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004943275686021747,
|
|
"loss": 5.3164,
|
|
"mean_token_accuracy": 0.1952598959207535,
|
|
"num_tokens": 19239299.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.423311853408814,
|
|
"epoch": 0.8059558117195005,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000494319916440861,
|
|
"loss": 5.2486,
|
|
"mean_token_accuracy": 0.19928672462701796,
|
|
"num_tokens": 19250691.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.361232423782349,
|
|
"epoch": 0.8064361191162344,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004943122591875901,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.20244060605764388,
|
|
"num_tokens": 19260868.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.436623811721802,
|
|
"epoch": 0.8069164265129684,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004943045968425398,
|
|
"loss": 5.3237,
|
|
"mean_token_accuracy": 0.19038853496313096,
|
|
"num_tokens": 19271924.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.3783989429473875,
|
|
"epoch": 0.8073967339097022,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004942969294058878,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.1993526339530945,
|
|
"num_tokens": 19283340.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.4472033977508545,
|
|
"epoch": 0.8078770413064361,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004942892568778125,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.18856506198644638,
|
|
"num_tokens": 19294903.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.428958940505981,
|
|
"epoch": 0.80835734870317,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004942815792584917,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.1962373971939087,
|
|
"num_tokens": 19305670.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.376930856704712,
|
|
"epoch": 0.808837656099904,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004942738965481038,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.19721640646457672,
|
|
"num_tokens": 19317043.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.397046899795532,
|
|
"epoch": 0.8093179634966379,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004942662087468272,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.19107830971479417,
|
|
"num_tokens": 19329161.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.389262008666992,
|
|
"epoch": 0.8097982708933718,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004942585158548402,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.19399819672107696,
|
|
"num_tokens": 19340706.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.439792919158935,
|
|
"epoch": 0.8102785782901056,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004942508178723214,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.1924287885427475,
|
|
"num_tokens": 19352422.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.402951288223266,
|
|
"epoch": 0.8107588856868396,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004942431147994499,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.1888471707701683,
|
|
"num_tokens": 19364109.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.383220434188843,
|
|
"epoch": 0.8112391930835735,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004942354066364042,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.18616687655448913,
|
|
"num_tokens": 19377386.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.379947185516357,
|
|
"epoch": 0.8117195004803074,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004942276933833634,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.20263410955667496,
|
|
"num_tokens": 19388453.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.366377592086792,
|
|
"epoch": 0.8121998078770413,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004942199750405064,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.18946326971054078,
|
|
"num_tokens": 19402240.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.389968967437744,
|
|
"epoch": 0.8126801152737753,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004942122516080127,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.19347688406705857,
|
|
"num_tokens": 19414260.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.3555137634277346,
|
|
"epoch": 0.8131604226705091,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004942045230860614,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.1945435658097267,
|
|
"num_tokens": 19426356.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.363530683517456,
|
|
"epoch": 0.813640730067243,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004941967894748319,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.19305806905031203,
|
|
"num_tokens": 19438881.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.392398405075073,
|
|
"epoch": 0.8141210374639769,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004941890507745039,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.19344445765018464,
|
|
"num_tokens": 19450109.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.39263424873352,
|
|
"epoch": 0.8146013448607109,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004941813069852569,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.19751955568790436,
|
|
"num_tokens": 19461155.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.456835508346558,
|
|
"epoch": 0.8150816522574448,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004941735581072708,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.1894826352596283,
|
|
"num_tokens": 19474364.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.3985669136047365,
|
|
"epoch": 0.8155619596541787,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004941658041407255,
|
|
"loss": 5.2159,
|
|
"mean_token_accuracy": 0.20274985879659652,
|
|
"num_tokens": 19485271.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.444395685195923,
|
|
"epoch": 0.8160422670509125,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000494158045085801,
|
|
"loss": 5.4036,
|
|
"mean_token_accuracy": 0.18302276730537415,
|
|
"num_tokens": 19497117.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.389369535446167,
|
|
"epoch": 0.8165225744476465,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004941502809426776,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.20128502696752548,
|
|
"num_tokens": 19507035.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.2925615310668945,
|
|
"epoch": 0.8170028818443804,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004941425117115354,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.19550191462039948,
|
|
"num_tokens": 19517791.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.3593018531799315,
|
|
"epoch": 0.8174831892411143,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004941347373925547,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.19915928542613984,
|
|
"num_tokens": 19529577.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.476502704620361,
|
|
"epoch": 0.8179634966378482,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004941269579859161,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.1887993961572647,
|
|
"num_tokens": 19542355.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.419625377655029,
|
|
"epoch": 0.8184438040345822,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004941191734918002,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.18974844515323638,
|
|
"num_tokens": 19553819.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.424053096771241,
|
|
"epoch": 0.818924111431316,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000494111383910388,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.18588172793388366,
|
|
"num_tokens": 19565816.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.4313558578491214,
|
|
"epoch": 0.8194044188280499,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004941035892418597,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.19463450312614441,
|
|
"num_tokens": 19577991.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.353194999694824,
|
|
"epoch": 0.8198847262247838,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004940957894863968,
|
|
"loss": 5.2415,
|
|
"mean_token_accuracy": 0.1920216679573059,
|
|
"num_tokens": 19590225.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.378624725341797,
|
|
"epoch": 0.8203650336215178,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004940879846441804,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.19345015585422515,
|
|
"num_tokens": 19602966.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.468559217453003,
|
|
"epoch": 0.8208453410182517,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004940801747153914,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.1942879244685173,
|
|
"num_tokens": 19613148.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.267355346679688,
|
|
"epoch": 0.8213256484149856,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004940723597002113,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.20505749732255935,
|
|
"num_tokens": 19624361.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.304432725906372,
|
|
"epoch": 0.8218059558117194,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004940645395988216,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.19914115071296692,
|
|
"num_tokens": 19635915.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.390110921859741,
|
|
"epoch": 0.8222862632084534,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004940567144114036,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.18822350800037385,
|
|
"num_tokens": 19646701.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.456581497192383,
|
|
"epoch": 0.8227665706051873,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004940488841381393,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.18938471674919127,
|
|
"num_tokens": 19657804.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.45032377243042,
|
|
"epoch": 0.8232468780019212,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004940410487792103,
|
|
"loss": 5.3673,
|
|
"mean_token_accuracy": 0.1936648204922676,
|
|
"num_tokens": 19670202.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.258342742919922,
|
|
"epoch": 0.8237271853986552,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004940332083347986,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.20448355078697206,
|
|
"num_tokens": 19681362.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.31924614906311,
|
|
"epoch": 0.8242074927953891,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004940253628050861,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.19031556695699692,
|
|
"num_tokens": 19693429.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.453513336181641,
|
|
"epoch": 0.824687800192123,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004940175121902552,
|
|
"loss": 5.3218,
|
|
"mean_token_accuracy": 0.1932925894856453,
|
|
"num_tokens": 19704667.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.419979238510132,
|
|
"epoch": 0.8251681075888568,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000494009656490488,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.19172892719507217,
|
|
"num_tokens": 19716002.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.370490264892578,
|
|
"epoch": 0.8256484149855908,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004940017957059668,
|
|
"loss": 5.2847,
|
|
"mean_token_accuracy": 0.1934389740228653,
|
|
"num_tokens": 19726626.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.364405536651612,
|
|
"epoch": 0.8261287223823247,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004939939298368742,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.19498982280492783,
|
|
"num_tokens": 19738250.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.427344703674317,
|
|
"epoch": 0.8266090297790586,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004939860588833929,
|
|
"loss": 5.3453,
|
|
"mean_token_accuracy": 0.19303781539201736,
|
|
"num_tokens": 19750119.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.425992107391357,
|
|
"epoch": 0.8270893371757925,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004939781828457055,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.1902000978589058,
|
|
"num_tokens": 19761709.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.406402587890625,
|
|
"epoch": 0.8275696445725265,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000493970301723995,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.1903778627514839,
|
|
"num_tokens": 19773562.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.515379476547241,
|
|
"epoch": 0.8280499519692603,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004939624155184443,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.187325219810009,
|
|
"num_tokens": 19785327.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.4205245018005375,
|
|
"epoch": 0.8285302593659942,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004939545242292365,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.1893976628780365,
|
|
"num_tokens": 19796760.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.360515213012695,
|
|
"epoch": 0.8290105667627281,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004939466278565547,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.19780270755290985,
|
|
"num_tokens": 19807271.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.357036304473877,
|
|
"epoch": 0.8294908741594621,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004939387264005825,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.1989939898252487,
|
|
"num_tokens": 19818098.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.3540637493133545,
|
|
"epoch": 0.829971181556196,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004939308198615031,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.19724859446287155,
|
|
"num_tokens": 19829482.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.438948297500611,
|
|
"epoch": 0.8304514889529299,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004939229082395001,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.19536018073558808,
|
|
"num_tokens": 19840883.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.320067071914673,
|
|
"epoch": 0.8309317963496637,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004939149915347573,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.19495573341846467,
|
|
"num_tokens": 19852619.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.270103025436401,
|
|
"epoch": 0.8314121037463977,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004939070697474585,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.199944931268692,
|
|
"num_tokens": 19863316.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.403096675872803,
|
|
"epoch": 0.8318924111431316,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004938991428777875,
|
|
"loss": 5.3361,
|
|
"mean_token_accuracy": 0.19362263530492782,
|
|
"num_tokens": 19873965.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.395878410339355,
|
|
"epoch": 0.8323727185398655,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004938912109259284,
|
|
"loss": 5.2606,
|
|
"mean_token_accuracy": 0.194809927046299,
|
|
"num_tokens": 19884685.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.356817007064819,
|
|
"epoch": 0.8328530259365994,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004938832738920654,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.1967201828956604,
|
|
"num_tokens": 19897594.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.388972520828247,
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004938753317763826,
|
|
"loss": 5.312,
|
|
"mean_token_accuracy": 0.19195151031017305,
|
|
"num_tokens": 19908093.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.451654005050659,
|
|
"epoch": 0.8338136407300673,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004938673845790646,
|
|
"loss": 5.3454,
|
|
"mean_token_accuracy": 0.18652617633342744,
|
|
"num_tokens": 19920502.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.36719446182251,
|
|
"epoch": 0.8342939481268011,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004938594323002957,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.20161306709051133,
|
|
"num_tokens": 19931437.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.3172218799591064,
|
|
"epoch": 0.834774255523535,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004938514749402609,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.19911665171384813,
|
|
"num_tokens": 19942592.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.421259260177612,
|
|
"epoch": 0.835254562920269,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004938435124991447,
|
|
"loss": 5.4225,
|
|
"mean_token_accuracy": 0.1849104180932045,
|
|
"num_tokens": 19953802.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.400475645065308,
|
|
"epoch": 0.8357348703170029,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004938355449771318,
|
|
"loss": 5.2509,
|
|
"mean_token_accuracy": 0.19384113550186158,
|
|
"num_tokens": 19964686.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.373258304595947,
|
|
"epoch": 0.8362151777137368,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004938275723744075,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.19449401795864105,
|
|
"num_tokens": 19975603.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.442459774017334,
|
|
"epoch": 0.8366954851104706,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004938195946911567,
|
|
"loss": 5.3493,
|
|
"mean_token_accuracy": 0.18805384486913682,
|
|
"num_tokens": 19986205.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.398763799667359,
|
|
"epoch": 0.8371757925072046,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004938116119275645,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.20078344643115997,
|
|
"num_tokens": 19997323.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.3614967346191404,
|
|
"epoch": 0.8376560999039385,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004938036240838166,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.2019427612423897,
|
|
"num_tokens": 20007334.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.4310449123382565,
|
|
"epoch": 0.8381364073006724,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004937956311600983,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.1901556819677353,
|
|
"num_tokens": 20017476.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.285951900482178,
|
|
"epoch": 0.8386167146974063,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004937876331565951,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.19222691059112548,
|
|
"num_tokens": 20029323.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.318617486953736,
|
|
"epoch": 0.8390970220941403,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004937796300734926,
|
|
"loss": 5.2203,
|
|
"mean_token_accuracy": 0.18935052901506425,
|
|
"num_tokens": 20040317.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.3973370552062985,
|
|
"epoch": 0.8395773294908742,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004937716219109769,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.19618357717990875,
|
|
"num_tokens": 20050495.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.461271047592163,
|
|
"epoch": 0.840057636887608,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004937636086692336,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.18598054796457292,
|
|
"num_tokens": 20061185.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.414768648147583,
|
|
"epoch": 0.840537944284342,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000493755590348449,
|
|
"loss": 5.2867,
|
|
"mean_token_accuracy": 0.19658587425947188,
|
|
"num_tokens": 20073746.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.4302146434783936,
|
|
"epoch": 0.8410182516810759,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004937475669488091,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.19282436221837998,
|
|
"num_tokens": 20085667.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.411467552185059,
|
|
"epoch": 0.8414985590778098,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004937395384705004,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.204672409594059,
|
|
"num_tokens": 20096017.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.334100961685181,
|
|
"epoch": 0.8419788664745437,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004937315049137089,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.19416530877351762,
|
|
"num_tokens": 20106928.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.328470897674561,
|
|
"epoch": 0.8424591738712777,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004937234662786216,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.19781202226877212,
|
|
"num_tokens": 20118768.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.493528699874878,
|
|
"epoch": 0.8429394812680115,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004937154225654246,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.18760730177164078,
|
|
"num_tokens": 20129009.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.406347799301147,
|
|
"epoch": 0.8434197886647454,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004937073737743051,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.19011209011077881,
|
|
"num_tokens": 20141577.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.4522148132324215,
|
|
"epoch": 0.8439000960614793,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004936993199054499,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.1947518765926361,
|
|
"num_tokens": 20153636.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.335200929641724,
|
|
"epoch": 0.8443804034582133,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004936912609590458,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.19758563488721848,
|
|
"num_tokens": 20165719.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.370564079284668,
|
|
"epoch": 0.8448607108549472,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00049368319693528,
|
|
"loss": 5.302,
|
|
"mean_token_accuracy": 0.18864322751760482,
|
|
"num_tokens": 20178260.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.4461256980896,
|
|
"epoch": 0.8453410182516811,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004936751278343397,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.1917430117726326,
|
|
"num_tokens": 20189667.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.4010473728179935,
|
|
"epoch": 0.845821325648415,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004936670536564123,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.18697932064533235,
|
|
"num_tokens": 20201451.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.4120279312133786,
|
|
"epoch": 0.8463016330451489,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004936589744016853,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.19138943105936052,
|
|
"num_tokens": 20213257.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.443713808059693,
|
|
"epoch": 0.8467819404418828,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000493650890070346,
|
|
"loss": 5.2953,
|
|
"mean_token_accuracy": 0.19443745017051697,
|
|
"num_tokens": 20225301.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.3895618438720705,
|
|
"epoch": 0.8472622478386167,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004936428006625824,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.19551685601472854,
|
|
"num_tokens": 20236183.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.483028268814087,
|
|
"epoch": 0.8477425552353506,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004936347061785823,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.18863052874803543,
|
|
"num_tokens": 20248663.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.377487087249756,
|
|
"epoch": 0.8482228626320846,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004936266066185334,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.20531052798032762,
|
|
"num_tokens": 20259293.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.399657535552978,
|
|
"epoch": 0.8487031700288185,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004936185019826239,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.18434687703847885,
|
|
"num_tokens": 20270601.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.428639936447143,
|
|
"epoch": 0.8491834774255523,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004936103922710419,
|
|
"loss": 5.3339,
|
|
"mean_token_accuracy": 0.19664848148822783,
|
|
"num_tokens": 20281471.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.384542798995971,
|
|
"epoch": 0.8496637848222862,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004936022774839759,
|
|
"loss": 5.1855,
|
|
"mean_token_accuracy": 0.195806385576725,
|
|
"num_tokens": 20291941.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.388844013214111,
|
|
"epoch": 0.8501440922190202,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004935941576216141,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.18780387938022614,
|
|
"num_tokens": 20302631.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.502013397216797,
|
|
"epoch": 0.8506243996157541,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000493586032684145,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.1927383527159691,
|
|
"num_tokens": 20314955.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.446310901641846,
|
|
"epoch": 0.851104707012488,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004935779026717573,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.1961928054690361,
|
|
"num_tokens": 20326791.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.365289545059204,
|
|
"epoch": 0.8515850144092219,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004935697675846396,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.1964481234550476,
|
|
"num_tokens": 20338912.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.361674976348877,
|
|
"epoch": 0.8520653218059558,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004935616274229811,
|
|
"loss": 5.2511,
|
|
"mean_token_accuracy": 0.19960997402668,
|
|
"num_tokens": 20349414.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.440748023986816,
|
|
"epoch": 0.8525456292026897,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004935534821869705,
|
|
"loss": 5.2693,
|
|
"mean_token_accuracy": 0.19753523170948029,
|
|
"num_tokens": 20360346.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.38953971862793,
|
|
"epoch": 0.8530259365994236,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004935453318767971,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.19536848813295365,
|
|
"num_tokens": 20371965.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.348725652694702,
|
|
"epoch": 0.8535062439961575,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00049353717649265,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.19363913387060167,
|
|
"num_tokens": 20382632.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.390606117248535,
|
|
"epoch": 0.8539865513928915,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004935290160347185,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.19887724071741103,
|
|
"num_tokens": 20395796.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.440628290176392,
|
|
"epoch": 0.8544668587896254,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004935208505031922,
|
|
"loss": 5.3186,
|
|
"mean_token_accuracy": 0.19276156425476074,
|
|
"num_tokens": 20407113.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.422786712646484,
|
|
"epoch": 0.8549471661863592,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004935126798982606,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.19261221587657928,
|
|
"num_tokens": 20419012.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.43376522064209,
|
|
"epoch": 0.8554274735830932,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004935045042201135,
|
|
"loss": 5.2628,
|
|
"mean_token_accuracy": 0.19217123985290527,
|
|
"num_tokens": 20430337.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.341459608078003,
|
|
"epoch": 0.8559077809798271,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004934963234689407,
|
|
"loss": 5.2884,
|
|
"mean_token_accuracy": 0.1902077838778496,
|
|
"num_tokens": 20441614.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.3434123516082765,
|
|
"epoch": 0.856388088376561,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000493488137644932,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.20667791813611985,
|
|
"num_tokens": 20453170.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.338638210296631,
|
|
"epoch": 0.8568683957732949,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004934799467482774,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.1991856336593628,
|
|
"num_tokens": 20464585.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.350225353240967,
|
|
"epoch": 0.8573487031700289,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004934717507791673,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.2073020800948143,
|
|
"num_tokens": 20473903.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.344707345962524,
|
|
"epoch": 0.8578290105667628,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004934635497377919,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.196464966237545,
|
|
"num_tokens": 20484778.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.346668672561646,
|
|
"epoch": 0.8583093179634966,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004934553436243415,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.18907110542058944,
|
|
"num_tokens": 20495534.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.51176905632019,
|
|
"epoch": 0.8587896253602305,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004934471324390067,
|
|
"loss": 5.37,
|
|
"mean_token_accuracy": 0.18888648599386215,
|
|
"num_tokens": 20506853.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.410428667068482,
|
|
"epoch": 0.8592699327569645,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004934389161819783,
|
|
"loss": 5.3015,
|
|
"mean_token_accuracy": 0.19316813498735427,
|
|
"num_tokens": 20519112.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.406508255004883,
|
|
"epoch": 0.8597502401536984,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004934306948534467,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.1921637773513794,
|
|
"num_tokens": 20530060.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.41430082321167,
|
|
"epoch": 0.8602305475504323,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004934224684536031,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.19633077830076218,
|
|
"num_tokens": 20541802.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.293176507949829,
|
|
"epoch": 0.8607108549471661,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004934142369826382,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.19946417659521104,
|
|
"num_tokens": 20552494.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.329283618927002,
|
|
"epoch": 0.8611911623439001,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004934060004407434,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.19979164153337478,
|
|
"num_tokens": 20564467.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.43250150680542,
|
|
"epoch": 0.861671469740634,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004933977588281099,
|
|
"loss": 5.3315,
|
|
"mean_token_accuracy": 0.19024426192045213,
|
|
"num_tokens": 20575399.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.4357610702514645,
|
|
"epoch": 0.8621517771373679,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004933895121449288,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.19513940215110778,
|
|
"num_tokens": 20586212.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.4440700054168705,
|
|
"epoch": 0.8626320845341018,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004933812603913917,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.19323743581771852,
|
|
"num_tokens": 20597020.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.403150367736816,
|
|
"epoch": 0.8631123919308358,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004933730035676903,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.1938205450773239,
|
|
"num_tokens": 20609447.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.3863848686218265,
|
|
"epoch": 0.8635926993275697,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004933647416740161,
|
|
"loss": 5.2318,
|
|
"mean_token_accuracy": 0.19161730855703354,
|
|
"num_tokens": 20621780.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.301457357406616,
|
|
"epoch": 0.8640730067243035,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000493356474710561,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.2016572281718254,
|
|
"num_tokens": 20632331.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.3469079494476315,
|
|
"epoch": 0.8645533141210374,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000493348202677517,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.19837099313735962,
|
|
"num_tokens": 20643357.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.8645533141210374,
|
|
"eval_entropy": 5.214188244562507,
|
|
"eval_loss": 5.295583248138428,
|
|
"eval_mean_token_accuracy": 0.19974388994062198,
|
|
"eval_num_tokens": 20643357.0,
|
|
"eval_runtime": 26.6752,
|
|
"eval_samples_per_second": 1230.171,
|
|
"eval_steps_per_second": 153.776,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.319790649414062,
|
|
"epoch": 0.8650336215177714,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004933399255750761,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.20552109479904174,
|
|
"num_tokens": 20655212.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.292992973327637,
|
|
"epoch": 0.8655139289145053,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004933316434034304,
|
|
"loss": 5.0855,
|
|
"mean_token_accuracy": 0.2076722964644432,
|
|
"num_tokens": 20666467.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.324105739593506,
|
|
"epoch": 0.8659942363112392,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004933233561627723,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.1977165386080742,
|
|
"num_tokens": 20677709.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.374633121490478,
|
|
"epoch": 0.866474543707973,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004933150638532942,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.1895079419016838,
|
|
"num_tokens": 20688880.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.435467195510864,
|
|
"epoch": 0.866954851104707,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004933067664751885,
|
|
"loss": 5.399,
|
|
"mean_token_accuracy": 0.18083080649375916,
|
|
"num_tokens": 20701384.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.4591577529907225,
|
|
"epoch": 0.8674351585014409,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000493298464028648,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.18601617515087127,
|
|
"num_tokens": 20713736.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.299443674087525,
|
|
"epoch": 0.8679154658981748,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004932901565138653,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.19958783090114593,
|
|
"num_tokens": 20725424.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.35780816078186,
|
|
"epoch": 0.8683957732949087,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004932818439310334,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.19774211347103118,
|
|
"num_tokens": 20737454.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.452247571945191,
|
|
"epoch": 0.8688760806916427,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004932735262803452,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.19008514881134034,
|
|
"num_tokens": 20748882.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.372403478622436,
|
|
"epoch": 0.8693563880883766,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004932652035619939,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.20026716589927673,
|
|
"num_tokens": 20759622.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.307312536239624,
|
|
"epoch": 0.8698366954851104,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004932568757761727,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.19591446667909623,
|
|
"num_tokens": 20770658.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.435375928878784,
|
|
"epoch": 0.8703170028818443,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004932485429230748,
|
|
"loss": 5.2762,
|
|
"mean_token_accuracy": 0.19558858573436738,
|
|
"num_tokens": 20782176.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.467179918289185,
|
|
"epoch": 0.8707973102785783,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000493240205002894,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.18266102522611619,
|
|
"num_tokens": 20793592.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.402525949478149,
|
|
"epoch": 0.8712776176753122,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004932318620158235,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.1949774757027626,
|
|
"num_tokens": 20804226.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.361907863616944,
|
|
"epoch": 0.8717579250720461,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004932235139620574,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.18637584000825883,
|
|
"num_tokens": 20815336.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.397728490829468,
|
|
"epoch": 0.8722382324687801,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004932151608417892,
|
|
"loss": 5.2562,
|
|
"mean_token_accuracy": 0.20355497896671296,
|
|
"num_tokens": 20826936.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.411286020278931,
|
|
"epoch": 0.872718539865514,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004932068026552127,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.19251975566148757,
|
|
"num_tokens": 20838159.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.403781127929688,
|
|
"epoch": 0.8731988472622478,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004931984394025224,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.1905702084302902,
|
|
"num_tokens": 20848605.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.384661340713501,
|
|
"epoch": 0.8736791546589817,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004931900710839123,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.18770140856504441,
|
|
"num_tokens": 20860494.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.419786643981934,
|
|
"epoch": 0.8741594620557157,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004931816976995766,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.19947386980056764,
|
|
"num_tokens": 20871327.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.361711931228638,
|
|
"epoch": 0.8746397694524496,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004931733192497097,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.1988350734114647,
|
|
"num_tokens": 20883032.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.391395950317383,
|
|
"epoch": 0.8751200768491835,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004931649357345062,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.1914994791150093,
|
|
"num_tokens": 20894327.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.352286529541016,
|
|
"epoch": 0.8756003842459174,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004931565471541606,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.20428362339735032,
|
|
"num_tokens": 20905489.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.357045125961304,
|
|
"epoch": 0.8760806916426513,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004931481535088679,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.1897742196917534,
|
|
"num_tokens": 20917044.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.380188369750977,
|
|
"epoch": 0.8765609990393852,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004931397547988229,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.19599434435367585,
|
|
"num_tokens": 20928065.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.405956602096557,
|
|
"epoch": 0.8770413064361191,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004931313510242204,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.201428684592247,
|
|
"num_tokens": 20939396.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.446123790740967,
|
|
"epoch": 0.877521613832853,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004931229421852557,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.191171233355999,
|
|
"num_tokens": 20950844.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.366133832931519,
|
|
"epoch": 0.878001921229587,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000493114528282124,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.19597537517547609,
|
|
"num_tokens": 20961567.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.541252994537354,
|
|
"epoch": 0.8784822286263209,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004931061093150206,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.19285230934619904,
|
|
"num_tokens": 20972762.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.329995584487915,
|
|
"epoch": 0.8789625360230547,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004930976852841409,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.19554354697465898,
|
|
"num_tokens": 20983848.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.383824348449707,
|
|
"epoch": 0.8794428434197886,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004930892561896806,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.19015206396579742,
|
|
"num_tokens": 20996418.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.404303693771363,
|
|
"epoch": 0.8799231508165226,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004930808220318354,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.19629869908094405,
|
|
"num_tokens": 21008714.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.420473670959472,
|
|
"epoch": 0.8804034582132565,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004930723828108012,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.1992582142353058,
|
|
"num_tokens": 21020453.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.280115604400635,
|
|
"epoch": 0.8808837656099904,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004930639385267736,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.19808709174394606,
|
|
"num_tokens": 21032211.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.382225084304809,
|
|
"epoch": 0.8813640730067243,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000493055489179949,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.1933873787522316,
|
|
"num_tokens": 21042995.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.341494941711426,
|
|
"epoch": 0.8818443804034583,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004930470347705234,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.2004062846302986,
|
|
"num_tokens": 21054306.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.37236065864563,
|
|
"epoch": 0.8823246878001921,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000493038575298693,
|
|
"loss": 5.3271,
|
|
"mean_token_accuracy": 0.1897224262356758,
|
|
"num_tokens": 21067144.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.531492280960083,
|
|
"epoch": 0.882804995196926,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004930301107646545,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.18749115318059922,
|
|
"num_tokens": 21078885.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.5086592674255375,
|
|
"epoch": 0.8832853025936599,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004930216411686042,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.18278430551290512,
|
|
"num_tokens": 21089482.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.44271330833435,
|
|
"epoch": 0.8837656099903939,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004930131665107387,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.18601189106702803,
|
|
"num_tokens": 21102046.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.362988042831421,
|
|
"epoch": 0.8842459173871278,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000493004686791255,
|
|
"loss": 5.1942,
|
|
"mean_token_accuracy": 0.19421408623456954,
|
|
"num_tokens": 21112827.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.400761413574219,
|
|
"epoch": 0.8847262247838616,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004929962020103496,
|
|
"loss": 5.297,
|
|
"mean_token_accuracy": 0.19207022935152054,
|
|
"num_tokens": 21123108.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.409162759780884,
|
|
"epoch": 0.8852065321805955,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004929877121682198,
|
|
"loss": 5.3154,
|
|
"mean_token_accuracy": 0.19236302077770234,
|
|
"num_tokens": 21134955.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.387013673782349,
|
|
"epoch": 0.8856868395773295,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004929792172650627,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.20066718459129335,
|
|
"num_tokens": 21146415.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.33963303565979,
|
|
"epoch": 0.8861671469740634,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004929707173010753,
|
|
"loss": 5.2323,
|
|
"mean_token_accuracy": 0.20095980763435364,
|
|
"num_tokens": 21158691.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.355684757232666,
|
|
"epoch": 0.8866474543707973,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004929622122764552,
|
|
"loss": 5.2572,
|
|
"mean_token_accuracy": 0.19015011489391326,
|
|
"num_tokens": 21170063.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.431982803344726,
|
|
"epoch": 0.8871277617675313,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004929537021913997,
|
|
"loss": 5.3289,
|
|
"mean_token_accuracy": 0.19112800806760788,
|
|
"num_tokens": 21182427.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.394394874572754,
|
|
"epoch": 0.8876080691642652,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004929451870461064,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.19691623598337174,
|
|
"num_tokens": 21195011.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.375449895858765,
|
|
"epoch": 0.888088376560999,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004929366668407731,
|
|
"loss": 5.2389,
|
|
"mean_token_accuracy": 0.1980753645300865,
|
|
"num_tokens": 21207886.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.3231419086456295,
|
|
"epoch": 0.8885686839577329,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004929281415755974,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.20334324836730958,
|
|
"num_tokens": 21219285.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.421673107147217,
|
|
"epoch": 0.8890489913544669,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004929196112507775,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.19196344614028932,
|
|
"num_tokens": 21231208.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.350038051605225,
|
|
"epoch": 0.8895292987512008,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004929110758665112,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.19924798756837844,
|
|
"num_tokens": 21242573.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.237231779098511,
|
|
"epoch": 0.8900096061479347,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004929025354229969,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.20820244401693344,
|
|
"num_tokens": 21254966.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.3665369033813475,
|
|
"epoch": 0.8904899135446686,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004928939899204326,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.18944831490516661,
|
|
"num_tokens": 21266167.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.415092134475708,
|
|
"epoch": 0.8909702209414025,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000492885439359017,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.19464683830738067,
|
|
"num_tokens": 21277036.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.3250429153442385,
|
|
"epoch": 0.8914505283381364,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004928768837389485,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.1972446471452713,
|
|
"num_tokens": 21288887.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.3988782405853275,
|
|
"epoch": 0.8919308357348703,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004928683230604257,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.1861489549279213,
|
|
"num_tokens": 21300664.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.475399017333984,
|
|
"epoch": 0.8924111431316042,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004928597573236474,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.19874988943338395,
|
|
"num_tokens": 21311535.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.2980047225952145,
|
|
"epoch": 0.8928914505283382,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004928511865288123,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.1983889237046242,
|
|
"num_tokens": 21323248.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.315932846069336,
|
|
"epoch": 0.8933717579250721,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004928426106761197,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.19994667172431946,
|
|
"num_tokens": 21334901.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.490907478332519,
|
|
"epoch": 0.8938520653218059,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004928340297657685,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.19272645860910415,
|
|
"num_tokens": 21345902.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.45790958404541,
|
|
"epoch": 0.8943323727185398,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004928254437979578,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.18789408057928086,
|
|
"num_tokens": 21358240.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.252040672302246,
|
|
"epoch": 0.8948126801152738,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004928168527728873,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.20298046618700027,
|
|
"num_tokens": 21368209.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.282319402694702,
|
|
"epoch": 0.8952929875120077,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004928082566907562,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.1902171015739441,
|
|
"num_tokens": 21379484.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.376897668838501,
|
|
"epoch": 0.8957732949087416,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004927996555517642,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.19863976538181305,
|
|
"num_tokens": 21391750.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.434967279434204,
|
|
"epoch": 0.8962536023054755,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004927910493561109,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.19308367669582366,
|
|
"num_tokens": 21402583.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.3867422580719,
|
|
"epoch": 0.8967339097022095,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000492782438103996,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.18686265200376512,
|
|
"num_tokens": 21412892.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.356006622314453,
|
|
"epoch": 0.8972142170989433,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004927738217956197,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.19290295392274856,
|
|
"num_tokens": 21422828.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.293871212005615,
|
|
"epoch": 0.8976945244956772,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004927652004311819,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.19278172105550767,
|
|
"num_tokens": 21434441.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.424458646774292,
|
|
"epoch": 0.8981748318924111,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004927565740108828,
|
|
"loss": 5.3934,
|
|
"mean_token_accuracy": 0.1887845903635025,
|
|
"num_tokens": 21445945.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.456415605545044,
|
|
"epoch": 0.8986551392891451,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004927479425349226,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.19610380828380586,
|
|
"num_tokens": 21457265.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.3642435550689695,
|
|
"epoch": 0.899135446685879,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004927393060035018,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.19245890378952027,
|
|
"num_tokens": 21469090.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.368222188949585,
|
|
"epoch": 0.8996157540826129,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004927306644168207,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.18543377965688707,
|
|
"num_tokens": 21480280.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.34284782409668,
|
|
"epoch": 0.9000960614793467,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004927220177750803,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.20020502656698227,
|
|
"num_tokens": 21491856.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.388748836517334,
|
|
"epoch": 0.9005763688760807,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004927133660784811,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.19540146142244338,
|
|
"num_tokens": 21501814.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.383769416809082,
|
|
"epoch": 0.9010566762728146,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004927047093272241,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.19255306273698808,
|
|
"num_tokens": 21514725.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.320773458480835,
|
|
"epoch": 0.9015369836695485,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00049269604752151,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.1984529584646225,
|
|
"num_tokens": 21526523.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.336462211608887,
|
|
"epoch": 0.9020172910662824,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004926873806615403,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.19943687021732331,
|
|
"num_tokens": 21537947.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.446700811386108,
|
|
"epoch": 0.9024975984630164,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004926787087475158,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.18979995995759963,
|
|
"num_tokens": 21550238.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.364442968368531,
|
|
"epoch": 0.9029779058597502,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004926700317796382,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.1879432648420334,
|
|
"num_tokens": 21561546.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.408336925506592,
|
|
"epoch": 0.9034582132564841,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004926613497581088,
|
|
"loss": 5.287,
|
|
"mean_token_accuracy": 0.19076864719390868,
|
|
"num_tokens": 21572034.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.350472354888916,
|
|
"epoch": 0.9039385206532181,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004926526626831292,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.18989201933145522,
|
|
"num_tokens": 21583427.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.372383165359497,
|
|
"epoch": 0.904418828049952,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004926439705549011,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.19854346364736558,
|
|
"num_tokens": 21595071.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.46326642036438,
|
|
"epoch": 0.9048991354466859,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004926352733736262,
|
|
"loss": 5.2816,
|
|
"mean_token_accuracy": 0.1946068823337555,
|
|
"num_tokens": 21606007.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.383008003234863,
|
|
"epoch": 0.9053794428434198,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004926265711395065,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.1993948295712471,
|
|
"num_tokens": 21617988.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.362982988357544,
|
|
"epoch": 0.9058597502401537,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000492617863852744,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.1956845372915268,
|
|
"num_tokens": 21629832.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.386901140213013,
|
|
"epoch": 0.9063400576368876,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004926091515135409,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.19297112822532653,
|
|
"num_tokens": 21641295.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.300440263748169,
|
|
"epoch": 0.9068203650336215,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004926004341220995,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.20337535440921783,
|
|
"num_tokens": 21652829.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.463212776184082,
|
|
"epoch": 0.9073006724303554,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004925917116786222,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.1866364523768425,
|
|
"num_tokens": 21665032.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.269292116165161,
|
|
"epoch": 0.9077809798270894,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004925829841833114,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.20581218153238295,
|
|
"num_tokens": 21675814.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.336495971679687,
|
|
"epoch": 0.9082612872238233,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004925742516363699,
|
|
"loss": 5.2619,
|
|
"mean_token_accuracy": 0.19505233317613602,
|
|
"num_tokens": 21687581.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.445864200592041,
|
|
"epoch": 0.9087415946205571,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004925655140380002,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.18777590095996857,
|
|
"num_tokens": 21700167.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.414084529876709,
|
|
"epoch": 0.909221902017291,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004925567713884054,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.19373577386140822,
|
|
"num_tokens": 21712309.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.35190258026123,
|
|
"epoch": 0.909702209414025,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004925480236877884,
|
|
"loss": 5.2154,
|
|
"mean_token_accuracy": 0.2007080465555191,
|
|
"num_tokens": 21723391.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.35431981086731,
|
|
"epoch": 0.9101825168107589,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004925392709363522,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.1985024854540825,
|
|
"num_tokens": 21735052.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.437685775756836,
|
|
"epoch": 0.9106628242074928,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004925305131343001,
|
|
"loss": 5.2971,
|
|
"mean_token_accuracy": 0.18960195481777192,
|
|
"num_tokens": 21746424.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.382255172729492,
|
|
"epoch": 0.9111431316042267,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004925217502818355,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.19176243096590043,
|
|
"num_tokens": 21756960.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.4193182468414305,
|
|
"epoch": 0.9116234390009607,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004925129823791616,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.1988448679447174,
|
|
"num_tokens": 21767621.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.4150067329406735,
|
|
"epoch": 0.9121037463976945,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004925042094264822,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.1916612908244133,
|
|
"num_tokens": 21779403.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.487259197235107,
|
|
"epoch": 0.9125840537944284,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000492495431424001,
|
|
"loss": 5.3745,
|
|
"mean_token_accuracy": 0.18581128120422363,
|
|
"num_tokens": 21791039.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.520426940917969,
|
|
"epoch": 0.9130643611911623,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004924866483719216,
|
|
"loss": 5.3491,
|
|
"mean_token_accuracy": 0.1887574389576912,
|
|
"num_tokens": 21803731.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.437395095825195,
|
|
"epoch": 0.9135446685878963,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004924778602704481,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.19384080022573472,
|
|
"num_tokens": 21816139.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.256186199188233,
|
|
"epoch": 0.9140249759846302,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004924690671197845,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.2019031748175621,
|
|
"num_tokens": 21826861.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.321603488922119,
|
|
"epoch": 0.914505283381364,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004924602689201348,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.19992187917232512,
|
|
"num_tokens": 21838083.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.396101331710815,
|
|
"epoch": 0.9149855907780979,
|
|
"grad_norm": 5.53125,
|
|
"learning_rate": 0.0004924514656717034,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.19334015399217605,
|
|
"num_tokens": 21849232.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.442108631134033,
|
|
"epoch": 0.9154658981748319,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004924426573746948,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.18857376277446747,
|
|
"num_tokens": 21861650.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.535091924667358,
|
|
"epoch": 0.9159462055715658,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004924338440293131,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.18689346462488174,
|
|
"num_tokens": 21873369.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.426569032669067,
|
|
"epoch": 0.9164265129682997,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004924250256357635,
|
|
"loss": 5.2561,
|
|
"mean_token_accuracy": 0.19275580942630768,
|
|
"num_tokens": 21884563.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.407162189483643,
|
|
"epoch": 0.9169068203650336,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004924162021942502,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.18890339136123657,
|
|
"num_tokens": 21896114.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.407561922073365,
|
|
"epoch": 0.9173871277617676,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004924073737049784,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.19579027444124222,
|
|
"num_tokens": 21907386.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.447867918014526,
|
|
"epoch": 0.9178674351585014,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004923985401681528,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.1974613383412361,
|
|
"num_tokens": 21918312.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.352988958358765,
|
|
"epoch": 0.9183477425552353,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004923897015839788,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.2020619332790375,
|
|
"num_tokens": 21930101.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.369843196868897,
|
|
"epoch": 0.9188280499519692,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004923808579526613,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.19904195368289948,
|
|
"num_tokens": 21941739.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.400526666641236,
|
|
"epoch": 0.9193083573487032,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004923720092744059,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.1840466007590294,
|
|
"num_tokens": 21953342.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.472770500183105,
|
|
"epoch": 0.9197886647454371,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004923631555494179,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.19470929652452468,
|
|
"num_tokens": 21963506.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.472641944885254,
|
|
"epoch": 0.920268972142171,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004923542967779028,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.187233130633831,
|
|
"num_tokens": 21975078.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.388547897338867,
|
|
"epoch": 0.920749279538905,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004923454329600664,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.1975598618388176,
|
|
"num_tokens": 21987128.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.387301588058472,
|
|
"epoch": 0.9212295869356388,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004923365640961143,
|
|
"loss": 5.317,
|
|
"mean_token_accuracy": 0.19394897818565368,
|
|
"num_tokens": 22000106.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.363097286224365,
|
|
"epoch": 0.9217098943323727,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004923276901862526,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.19964518398046494,
|
|
"num_tokens": 22010571.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.349168586730957,
|
|
"epoch": 0.9221902017291066,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004923188112306874,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.20611703097820283,
|
|
"num_tokens": 22021399.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.340490484237671,
|
|
"epoch": 0.9226705091258406,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004923099272296246,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.20286252796649934,
|
|
"num_tokens": 22032302.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.359250450134278,
|
|
"epoch": 0.9231508165225745,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004923010381832706,
|
|
"loss": 5.2064,
|
|
"mean_token_accuracy": 0.20294761061668395,
|
|
"num_tokens": 22043762.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.421875,
|
|
"epoch": 0.9236311239193083,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004922921440918318,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.20064163953065872,
|
|
"num_tokens": 22054885.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.486204767227173,
|
|
"epoch": 0.9241114313160422,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004922832449555144,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.1889108180999756,
|
|
"num_tokens": 22066627.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.318388605117798,
|
|
"epoch": 0.9245917387127762,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004922743407745255,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.19961403012275697,
|
|
"num_tokens": 22078062.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.325558471679687,
|
|
"epoch": 0.9250720461095101,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004922654315490714,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.19793693721294403,
|
|
"num_tokens": 22089465.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.3975550651550295,
|
|
"epoch": 0.925552353506244,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004922565172793593,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.19478186666965486,
|
|
"num_tokens": 22101688.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.38715124130249,
|
|
"epoch": 0.9260326609029779,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004922475979655958,
|
|
"loss": 5.2866,
|
|
"mean_token_accuracy": 0.1929781600832939,
|
|
"num_tokens": 22112912.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.426280546188354,
|
|
"epoch": 0.9265129682997119,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004922386736079883,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.1836224839091301,
|
|
"num_tokens": 22125079.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.476082515716553,
|
|
"epoch": 0.9269932756964457,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004922297442067438,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.19882182478904725,
|
|
"num_tokens": 22137146.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.335666751861572,
|
|
"epoch": 0.9274735830931796,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004922208097620697,
|
|
"loss": 5.229,
|
|
"mean_token_accuracy": 0.19252820312976837,
|
|
"num_tokens": 22148330.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.309677457809448,
|
|
"epoch": 0.9279538904899135,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004922118702741735,
|
|
"loss": 5.218,
|
|
"mean_token_accuracy": 0.19758376479148865,
|
|
"num_tokens": 22160511.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.3699281215667725,
|
|
"epoch": 0.9284341978866475,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004922029257432625,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.19192028641700745,
|
|
"num_tokens": 22171298.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.334575033187866,
|
|
"epoch": 0.9289145052833814,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004921939761695446,
|
|
"loss": 5.2676,
|
|
"mean_token_accuracy": 0.19729354977607727,
|
|
"num_tokens": 22181897.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.4648600101470945,
|
|
"epoch": 0.9293948126801153,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004921850215532275,
|
|
"loss": 5.3663,
|
|
"mean_token_accuracy": 0.195632903277874,
|
|
"num_tokens": 22194630.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.424686479568481,
|
|
"epoch": 0.9298751200768491,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004921760618945192,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.19682292640209198,
|
|
"num_tokens": 22206041.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.34432544708252,
|
|
"epoch": 0.9303554274735831,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004921670971936276,
|
|
"loss": 5.2767,
|
|
"mean_token_accuracy": 0.1924143522977829,
|
|
"num_tokens": 22218434.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.42786340713501,
|
|
"epoch": 0.930835734870317,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004921581274507607,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.18786528408527375,
|
|
"num_tokens": 22229182.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.445178556442261,
|
|
"epoch": 0.9313160422670509,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000492149152666127,
|
|
"loss": 5.3685,
|
|
"mean_token_accuracy": 0.18807477951049806,
|
|
"num_tokens": 22241142.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.437403202056885,
|
|
"epoch": 0.9317963496637848,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004921401728399348,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.19175815135240554,
|
|
"num_tokens": 22252695.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.310226726531982,
|
|
"epoch": 0.9322766570605188,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004921311879723926,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.2067328378558159,
|
|
"num_tokens": 22264159.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.405073881149292,
|
|
"epoch": 0.9327569644572526,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004921221980637088,
|
|
"loss": 5.2651,
|
|
"mean_token_accuracy": 0.1962537631392479,
|
|
"num_tokens": 22276154.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.328506326675415,
|
|
"epoch": 0.9332372718539865,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004921132031140925,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.19734954386949538,
|
|
"num_tokens": 22288328.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.392610168457031,
|
|
"epoch": 0.9337175792507204,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004921042031237521,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.19224864095449448,
|
|
"num_tokens": 22300154.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.2410666942596436,
|
|
"epoch": 0.9341978866474544,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004920951980928969,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.21091974675655364,
|
|
"num_tokens": 22311176.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.370237970352173,
|
|
"epoch": 0.9346781940441883,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004920861880217359,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.19298372715711593,
|
|
"num_tokens": 22321953.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.403165578842163,
|
|
"epoch": 0.9351585014409222,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004920771729104781,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.19578431993722917,
|
|
"num_tokens": 22333152.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.381178903579712,
|
|
"epoch": 0.9356388088376562,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004920681527593329,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.19532056599855424,
|
|
"num_tokens": 22344848.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.36601710319519,
|
|
"epoch": 0.93611911623439,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004920591275685098,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.19312046319246293,
|
|
"num_tokens": 22355100.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.386777877807617,
|
|
"epoch": 0.9365994236311239,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004920500973382184,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.20108671486377716,
|
|
"num_tokens": 22366045.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.344554233551025,
|
|
"epoch": 0.9370797310278578,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004920410620686682,
|
|
"loss": 5.2223,
|
|
"mean_token_accuracy": 0.19255712777376174,
|
|
"num_tokens": 22378781.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.460892105102539,
|
|
"epoch": 0.9375600384245918,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004920320217600689,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.19091278463602065,
|
|
"num_tokens": 22390121.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.340709495544433,
|
|
"epoch": 0.9380403458213257,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004920229764126306,
|
|
"loss": 5.2055,
|
|
"mean_token_accuracy": 0.20116310864686965,
|
|
"num_tokens": 22402261.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.385502433776855,
|
|
"epoch": 0.9385206532180596,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004920139260265632,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.19694014340639115,
|
|
"num_tokens": 22413939.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.395786762237549,
|
|
"epoch": 0.9390009606147934,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004920048706020769,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.19680802375078202,
|
|
"num_tokens": 22425439.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.419207143783569,
|
|
"epoch": 0.9394812680115274,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004919958101393817,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.1908087447285652,
|
|
"num_tokens": 22436989.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.366714382171631,
|
|
"epoch": 0.9399615754082613,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004919867446386883,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.19211360365152358,
|
|
"num_tokens": 22449181.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.289137697219848,
|
|
"epoch": 0.9404418828049952,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000491977674100207,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.19916170090436935,
|
|
"num_tokens": 22460592.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.2588519096374515,
|
|
"epoch": 0.9409221902017291,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004919685985241483,
|
|
"loss": 5.1848,
|
|
"mean_token_accuracy": 0.20611105859279633,
|
|
"num_tokens": 22471718.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.424605131149292,
|
|
"epoch": 0.9414024975984631,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000491959517910723,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.20368617475032808,
|
|
"num_tokens": 22482413.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.346623706817627,
|
|
"epoch": 0.9418828049951969,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004919504322601421,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.20130807608366014,
|
|
"num_tokens": 22494016.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.361317920684814,
|
|
"epoch": 0.9423631123919308,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004919413415726162,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.1888505131006241,
|
|
"num_tokens": 22505015.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.337130784988403,
|
|
"epoch": 0.9428434197886647,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004919322458483566,
|
|
"loss": 5.2996,
|
|
"mean_token_accuracy": 0.20140142887830734,
|
|
"num_tokens": 22516691.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.384731149673462,
|
|
"epoch": 0.9433237271853987,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004919231450875745,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.19500363767147064,
|
|
"num_tokens": 22527740.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.368558311462403,
|
|
"epoch": 0.9438040345821326,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004919140392904809,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.20168010741472245,
|
|
"num_tokens": 22537685.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.386229372024536,
|
|
"epoch": 0.9442843419788665,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004919049284572875,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.20708050578832626,
|
|
"num_tokens": 22548282.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.261020803451538,
|
|
"epoch": 0.9447646493756003,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004918958125882058,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.20510132908821105,
|
|
"num_tokens": 22559277.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.369067430496216,
|
|
"epoch": 0.9452449567723343,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004918866916834474,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.19554455280303956,
|
|
"num_tokens": 22570664.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.348180294036865,
|
|
"epoch": 0.9457252641690682,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004918775657432239,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.20561182349920273,
|
|
"num_tokens": 22580410.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.273010206222534,
|
|
"epoch": 0.9462055715658021,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004918684347677474,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.2004478693008423,
|
|
"num_tokens": 22591630.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.381022787094116,
|
|
"epoch": 0.946685878962536,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004918592987572298,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.19584041833877563,
|
|
"num_tokens": 22603658.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.375761318206787,
|
|
"epoch": 0.94716618635927,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004918501577118832,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.18672425597906112,
|
|
"num_tokens": 22614812.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.396744203567505,
|
|
"epoch": 0.9476464937560038,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00049184101163192,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.19715383946895598,
|
|
"num_tokens": 22626924.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.398779392242432,
|
|
"epoch": 0.9481268011527377,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004918318605175522,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.1908237174153328,
|
|
"num_tokens": 22638715.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.488548278808594,
|
|
"epoch": 0.9486071085494716,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004918227043689924,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.18225012123584747,
|
|
"num_tokens": 22650257.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.359689664840698,
|
|
"epoch": 0.9490874159462056,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004918135431864534,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.19737939685583114,
|
|
"num_tokens": 22662480.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.343315935134887,
|
|
"epoch": 0.9495677233429395,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004918043769701478,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.19172091782093048,
|
|
"num_tokens": 22673927.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.501454019546509,
|
|
"epoch": 0.9500480307396734,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004917952057202882,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.19981193840503692,
|
|
"num_tokens": 22684670.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.411140727996826,
|
|
"epoch": 0.9505283381364072,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004917860294370877,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.1897347390651703,
|
|
"num_tokens": 22696571.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.279243087768554,
|
|
"epoch": 0.9510086455331412,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004917768481207593,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.20495676696300508,
|
|
"num_tokens": 22708987.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.379358243942261,
|
|
"epoch": 0.9514889529298751,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004917676617715162,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.2038042888045311,
|
|
"num_tokens": 22720769.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.376408338546753,
|
|
"epoch": 0.951969260326609,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004917584703895717,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.19668340682983398,
|
|
"num_tokens": 22732592.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.390679979324341,
|
|
"epoch": 0.952449567723343,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004917492739751391,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.18807051479816436,
|
|
"num_tokens": 22744440.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.369322061538696,
|
|
"epoch": 0.9529298751200769,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000491740072528432,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.197923880815506,
|
|
"num_tokens": 22756336.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.345338249206543,
|
|
"epoch": 0.9534101825168108,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000491730866049664,
|
|
"loss": 5.2356,
|
|
"mean_token_accuracy": 0.19126826375722886,
|
|
"num_tokens": 22768256.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.47787389755249,
|
|
"epoch": 0.9538904899135446,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004917216545390489,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.19381358623504638,
|
|
"num_tokens": 22779693.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.253392314910888,
|
|
"epoch": 0.9543707973102786,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004917124379968004,
|
|
"loss": 5.1369,
|
|
"mean_token_accuracy": 0.1992025136947632,
|
|
"num_tokens": 22791417.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.3891936302185055,
|
|
"epoch": 0.9548511047070125,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004917032164231327,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.19839159101247789,
|
|
"num_tokens": 22803541.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.402176570892334,
|
|
"epoch": 0.9553314121037464,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004916939898182598,
|
|
"loss": 5.254,
|
|
"mean_token_accuracy": 0.19071769267320632,
|
|
"num_tokens": 22814648.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.364959383010865,
|
|
"epoch": 0.9558117195004803,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004916847581823958,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.19924654811620712,
|
|
"num_tokens": 22825672.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.4027454376220705,
|
|
"epoch": 0.9562920268972143,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004916755215157552,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.19255754649639129,
|
|
"num_tokens": 22837663.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.255894899368286,
|
|
"epoch": 0.9567723342939481,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004916662798185524,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.2012002944946289,
|
|
"num_tokens": 22849531.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.368396997451782,
|
|
"epoch": 0.957252641690682,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004916570330910019,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.1924448788166046,
|
|
"num_tokens": 22861784.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.451567268371582,
|
|
"epoch": 0.9577329490874159,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004916477813333185,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.1922279790043831,
|
|
"num_tokens": 22873482.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.371184873580932,
|
|
"epoch": 0.9582132564841499,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004916385245457168,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.20192530155181884,
|
|
"num_tokens": 22883917.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.35193247795105,
|
|
"epoch": 0.9586935638808838,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000491629262728412,
|
|
"loss": 5.2348,
|
|
"mean_token_accuracy": 0.19415521621704102,
|
|
"num_tokens": 22896167.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.357525730133057,
|
|
"epoch": 0.9591738712776177,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004916199958816188,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.19849079400300979,
|
|
"num_tokens": 22908350.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.488919401168824,
|
|
"epoch": 0.9596541786743515,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004916107240055527,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.19449115991592408,
|
|
"num_tokens": 22918913.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.292144727706909,
|
|
"epoch": 0.9601344860710855,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004916014471004287,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.20597919970750808,
|
|
"num_tokens": 22929336.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.307368993759155,
|
|
"epoch": 0.9606147934678194,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004915921651664622,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.19407544881105424,
|
|
"num_tokens": 22940406.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.348668622970581,
|
|
"epoch": 0.9610951008645533,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000491582878203869,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.19643348902463914,
|
|
"num_tokens": 22951518.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.2929301261901855,
|
|
"epoch": 0.9615754082612872,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004915735862128643,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.20273940414190292,
|
|
"num_tokens": 22962309.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.376764822006225,
|
|
"epoch": 0.9620557156580212,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004915642891936641,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.2020348146557808,
|
|
"num_tokens": 22973996.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.398353338241577,
|
|
"epoch": 0.962536023054755,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004915549871464841,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.19329437911510466,
|
|
"num_tokens": 22984964.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.399173831939697,
|
|
"epoch": 0.9630163304514889,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004915456800715403,
|
|
"loss": 5.2797,
|
|
"mean_token_accuracy": 0.18719930648803712,
|
|
"num_tokens": 22996058.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.333802080154419,
|
|
"epoch": 0.9634966378482228,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000491536367969049,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.20807814449071885,
|
|
"num_tokens": 23006140.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.364311218261719,
|
|
"epoch": 0.9639769452449568,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004915270508392261,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.18995533883571625,
|
|
"num_tokens": 23018129.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.436270141601563,
|
|
"epoch": 0.9644572526416907,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000491517728682288,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.20244865864515305,
|
|
"num_tokens": 23028673.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.351939487457275,
|
|
"epoch": 0.9649375600384246,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004915084014984512,
|
|
"loss": 5.2029,
|
|
"mean_token_accuracy": 0.1979590028524399,
|
|
"num_tokens": 23040778.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.296909141540527,
|
|
"epoch": 0.9654178674351584,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004914990692879322,
|
|
"loss": 5.2278,
|
|
"mean_token_accuracy": 0.2034088686108589,
|
|
"num_tokens": 23052170.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.358656215667724,
|
|
"epoch": 0.9658981748318924,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004914897320509478,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.1957473948597908,
|
|
"num_tokens": 23063455.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.30962061882019,
|
|
"epoch": 0.9663784822286263,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004914803897877146,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.20433489382266998,
|
|
"num_tokens": 23075009.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.370506811141968,
|
|
"epoch": 0.9668587896253602,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004914710424984495,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.19421422183513642,
|
|
"num_tokens": 23085921.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.466443157196045,
|
|
"epoch": 0.9673390970220941,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004914616901833696,
|
|
"loss": 5.368,
|
|
"mean_token_accuracy": 0.18565791994333267,
|
|
"num_tokens": 23098181.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.338989639282227,
|
|
"epoch": 0.9678194044188281,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000491452332842692,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.1956307664513588,
|
|
"num_tokens": 23109904.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.347525930404663,
|
|
"epoch": 0.968299711815562,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000491442970476634,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.19307613521814346,
|
|
"num_tokens": 23122356.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.367475271224976,
|
|
"epoch": 0.9687800192122958,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004914336030854129,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.20187202841043472,
|
|
"num_tokens": 23134055.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.310868787765503,
|
|
"epoch": 0.9692603266090298,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004914242306692461,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.20374749451875687,
|
|
"num_tokens": 23145388.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.36150484085083,
|
|
"epoch": 0.9697406340057637,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004914148532283516,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.1874200463294983,
|
|
"num_tokens": 23157083.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.380633878707886,
|
|
"epoch": 0.9702209414024976,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004914054707629466,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.19765482544898988,
|
|
"num_tokens": 23169154.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.318311738967895,
|
|
"epoch": 0.9707012487992315,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004913960832732493,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.20090494006872178,
|
|
"num_tokens": 23179879.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.316896104812622,
|
|
"epoch": 0.9711815561959655,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004913866907594774,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.19927761256694793,
|
|
"num_tokens": 23190632.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.441259956359863,
|
|
"epoch": 0.9716618635926993,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004913772932218491,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.1860272616147995,
|
|
"num_tokens": 23202060.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.429521894454956,
|
|
"epoch": 0.9721421709894332,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004913678906605825,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.1872340440750122,
|
|
"num_tokens": 23214103.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.358136367797852,
|
|
"epoch": 0.9726224783861671,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004913584830758961,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.20135337710380555,
|
|
"num_tokens": 23224676.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.388266372680664,
|
|
"epoch": 0.9731027857829011,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004913490704680081,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.20236930549144744,
|
|
"num_tokens": 23235478.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.410058832168579,
|
|
"epoch": 0.973583093179635,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004913396528371371,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.19678158015012742,
|
|
"num_tokens": 23246913.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.343859481811523,
|
|
"epoch": 0.9740634005763689,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004913302301835018,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.1970997631549835,
|
|
"num_tokens": 23258472.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.438864469528198,
|
|
"epoch": 0.9745437079731027,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.000491320802507321,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.18568275570869447,
|
|
"num_tokens": 23270443.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.4093412399292,
|
|
"epoch": 0.9750240153698367,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004913113698088133,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.20590991377830506,
|
|
"num_tokens": 23281199.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.296328687667847,
|
|
"epoch": 0.9755043227665706,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000491301932088198,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.19928632229566573,
|
|
"num_tokens": 23291980.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.439354133605957,
|
|
"epoch": 0.9759846301633045,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004912924893456942,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.1918912336230278,
|
|
"num_tokens": 23303673.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.50971531867981,
|
|
"epoch": 0.9764649375600384,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000491283041581521,
|
|
"loss": 5.2719,
|
|
"mean_token_accuracy": 0.1940137818455696,
|
|
"num_tokens": 23315830.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.426065301895141,
|
|
"epoch": 0.9769452449567724,
|
|
"grad_norm": 13.4375,
|
|
"learning_rate": 0.0004912735887958978,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.18928514122962953,
|
|
"num_tokens": 23329860.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.334433317184448,
|
|
"epoch": 0.9774255523535063,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004912641309890441,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.20020253956317902,
|
|
"num_tokens": 23340610.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.337919902801514,
|
|
"epoch": 0.9779058597502401,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004912546681611794,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.19779051393270491,
|
|
"num_tokens": 23352153.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.288594341278076,
|
|
"epoch": 0.978386167146974,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004912452003125234,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.20293716341257095,
|
|
"num_tokens": 23363630.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.359788608551026,
|
|
"epoch": 0.978866474543708,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000491235727443296,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.19922154992818833,
|
|
"num_tokens": 23375922.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.327295780181885,
|
|
"epoch": 0.9793467819404419,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004912262495537171,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.20141881704330444,
|
|
"num_tokens": 23386446.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.300418710708618,
|
|
"epoch": 0.9798270893371758,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004912167666440068,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.20769673734903335,
|
|
"num_tokens": 23398458.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.324464321136475,
|
|
"epoch": 0.9803073967339097,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004912072787143852,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.19903348833322526,
|
|
"num_tokens": 23409725.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.3119487285614015,
|
|
"epoch": 0.9807877041306436,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004911977857650725,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.20016496926546096,
|
|
"num_tokens": 23420468.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.387360954284668,
|
|
"epoch": 0.9812680115273775,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004911882877962893,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.19513286501169205,
|
|
"num_tokens": 23431386.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.440367603302002,
|
|
"epoch": 0.9817483189241114,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004911787848082559,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.19321776330471038,
|
|
"num_tokens": 23442759.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.381049060821534,
|
|
"epoch": 0.9822286263208453,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004911692768011931,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.2051030680537224,
|
|
"num_tokens": 23454372.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.42848687171936,
|
|
"epoch": 0.9827089337175793,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004911597637753217,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.19997452348470687,
|
|
"num_tokens": 23465557.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.286953687667847,
|
|
"epoch": 0.9831892411143132,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004911502457308623,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.20363888442516326,
|
|
"num_tokens": 23475850.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.30987434387207,
|
|
"epoch": 0.983669548511047,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000491140722668036,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.2009579584002495,
|
|
"num_tokens": 23487145.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.346234607696533,
|
|
"epoch": 0.984149855907781,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000491131194587064,
|
|
"loss": 5.2324,
|
|
"mean_token_accuracy": 0.19113098382949828,
|
|
"num_tokens": 23498112.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.351706504821777,
|
|
"epoch": 0.9846301633045149,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004911216614881675,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.20384518206119537,
|
|
"num_tokens": 23509865.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.413609361648559,
|
|
"epoch": 0.9851104707012488,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004911121233715677,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.18676220774650573,
|
|
"num_tokens": 23521153.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.362878274917603,
|
|
"epoch": 0.9855907780979827,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004911025802374861,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.19076319932937622,
|
|
"num_tokens": 23532372.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.381707096099854,
|
|
"epoch": 0.9860710854947167,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004910930320861442,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.19311443865299224,
|
|
"num_tokens": 23543494.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.4404397964477536,
|
|
"epoch": 0.9865513928914506,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004910834789177639,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.1928661823272705,
|
|
"num_tokens": 23554020.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.481026268005371,
|
|
"epoch": 0.9870317002881844,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004910739207325668,
|
|
"loss": 5.3725,
|
|
"mean_token_accuracy": 0.1903602033853531,
|
|
"num_tokens": 23565032.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.308665561676025,
|
|
"epoch": 0.9875120076849183,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004910643575307749,
|
|
"loss": 5.2366,
|
|
"mean_token_accuracy": 0.19494978934526444,
|
|
"num_tokens": 23576243.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.369306802749634,
|
|
"epoch": 0.9879923150816523,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004910547893126102,
|
|
"loss": 5.281,
|
|
"mean_token_accuracy": 0.19268425107002257,
|
|
"num_tokens": 23586111.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.457032108306885,
|
|
"epoch": 0.9884726224783862,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004910452160782948,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.19325252920389174,
|
|
"num_tokens": 23597718.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.493101644515991,
|
|
"epoch": 0.9889529298751201,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000491035637828051,
|
|
"loss": 5.2978,
|
|
"mean_token_accuracy": 0.18808236122131347,
|
|
"num_tokens": 23608241.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.420267486572266,
|
|
"epoch": 0.989433237271854,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004910260545621012,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.19275065660476684,
|
|
"num_tokens": 23619120.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.32737455368042,
|
|
"epoch": 0.9899135446685879,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004910164662806679,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.20073831379413604,
|
|
"num_tokens": 23630642.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.328326606750489,
|
|
"epoch": 0.9903938520653218,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004910068729839736,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.20349667221307755,
|
|
"num_tokens": 23641987.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.42763614654541,
|
|
"epoch": 0.9908741594620557,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004909972746722413,
|
|
"loss": 5.339,
|
|
"mean_token_accuracy": 0.19256781339645385,
|
|
"num_tokens": 23653144.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.386298656463623,
|
|
"epoch": 0.9913544668587896,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004909876713456935,
|
|
"loss": 5.2544,
|
|
"mean_token_accuracy": 0.19387101531028747,
|
|
"num_tokens": 23663807.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.3090744972229,
|
|
"epoch": 0.9918347742555236,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004909780630045534,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.1971955418586731,
|
|
"num_tokens": 23674341.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.359406900405884,
|
|
"epoch": 0.9923150816522575,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000490968449649044,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.19592582285404206,
|
|
"num_tokens": 23685415.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.4454261302948,
|
|
"epoch": 0.9927953890489913,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004909588312793884,
|
|
"loss": 5.2819,
|
|
"mean_token_accuracy": 0.19722168296575546,
|
|
"num_tokens": 23696652.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.3882434368133545,
|
|
"epoch": 0.9932756964457252,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004909492078958101,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.19429783523082733,
|
|
"num_tokens": 23708939.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.369251489639282,
|
|
"epoch": 0.9937560038424592,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004909395794985324,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.1963334009051323,
|
|
"num_tokens": 23720587.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.279649543762207,
|
|
"epoch": 0.9942363112391931,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004909299460877788,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.19969542175531388,
|
|
"num_tokens": 23732345.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.382672357559204,
|
|
"epoch": 0.994716618635927,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004909203076637732,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.19261985272169113,
|
|
"num_tokens": 23743149.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.4967328071594235,
|
|
"epoch": 0.9951969260326609,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004909106642267392,
|
|
"loss": 5.2627,
|
|
"mean_token_accuracy": 0.198738257586956,
|
|
"num_tokens": 23755508.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.356519365310669,
|
|
"epoch": 0.9956772334293948,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004909010157769006,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.1936712607741356,
|
|
"num_tokens": 23766313.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.263210487365723,
|
|
"epoch": 0.9961575408261287,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004908913623144814,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.2092423692345619,
|
|
"num_tokens": 23777776.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.378554487228394,
|
|
"epoch": 0.9966378482228626,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000490881703839706,
|
|
"loss": 5.3086,
|
|
"mean_token_accuracy": 0.19899863004684448,
|
|
"num_tokens": 23791143.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.503311586380005,
|
|
"epoch": 0.9971181556195965,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004908720403527984,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.1919129014015198,
|
|
"num_tokens": 23802446.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.299834775924682,
|
|
"epoch": 0.9975984630163305,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000490862371853983,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.20518070012331008,
|
|
"num_tokens": 23813757.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.311198663711548,
|
|
"epoch": 0.9980787704130644,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004908526983434844,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.1979399248957634,
|
|
"num_tokens": 23824934.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.440586757659912,
|
|
"epoch": 0.9985590778097982,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.000490843019821527,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.1918754205107689,
|
|
"num_tokens": 23836872.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.490906286239624,
|
|
"epoch": 0.9990393852065321,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004908333362883358,
|
|
"loss": 5.2426,
|
|
"mean_token_accuracy": 0.19100466817617417,
|
|
"num_tokens": 23847853.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.298523759841919,
|
|
"epoch": 0.9995196926032661,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004908236477441353,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.2047051355242729,
|
|
"num_tokens": 23859208.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.25507493019104,
|
|
"epoch": 1.0,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004908139541891505,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.1997172936797142,
|
|
"num_tokens": 23868536.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.35916576385498,
|
|
"epoch": 1.0004803073967339,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004908042556236066,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.1983928233385086,
|
|
"num_tokens": 23881335.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.30327844619751,
|
|
"epoch": 1.0009606147934678,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004907945520477286,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.20289318710565568,
|
|
"num_tokens": 23891694.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.288583993911743,
|
|
"epoch": 1.0014409221902016,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004907848434617419,
|
|
"loss": 5.1372,
|
|
"mean_token_accuracy": 0.19711353480815888,
|
|
"num_tokens": 23903560.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.47208800315857,
|
|
"epoch": 1.0019212295869357,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000490775129865872,
|
|
"loss": 5.3221,
|
|
"mean_token_accuracy": 0.18646362125873567,
|
|
"num_tokens": 23914525.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.452016878128052,
|
|
"epoch": 1.0024015369836696,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004907654112603442,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.20110237300395967,
|
|
"num_tokens": 23926492.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.402464389801025,
|
|
"epoch": 1.0028818443804035,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004907556876453843,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.19879360347986222,
|
|
"num_tokens": 23936326.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.201600027084351,
|
|
"epoch": 1.0033621517771374,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000490745959021218,
|
|
"loss": 4.9686,
|
|
"mean_token_accuracy": 0.21124709844589235,
|
|
"num_tokens": 23947173.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.371070861816406,
|
|
"epoch": 1.0038424591738713,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004907362253880711,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.2001799076795578,
|
|
"num_tokens": 23959771.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.351351308822632,
|
|
"epoch": 1.0043227665706052,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004907264867461697,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.19711594581604003,
|
|
"num_tokens": 23970908.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.33805136680603,
|
|
"epoch": 1.004803073967339,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 0.0004907167430957399,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.19941968470811844,
|
|
"num_tokens": 23981640.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.437816190719604,
|
|
"epoch": 1.005283381364073,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004907069944370077,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.19937537610530853,
|
|
"num_tokens": 23992913.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.343357515335083,
|
|
"epoch": 1.005763688760807,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004906972407701998,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.19388407915830613,
|
|
"num_tokens": 24003819.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.362512111663818,
|
|
"epoch": 1.006243996157541,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004906874820955423,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.19612828493118287,
|
|
"num_tokens": 24013997.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.324533557891845,
|
|
"epoch": 1.0067243035542748,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004906777184132621,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.19982564747333526,
|
|
"num_tokens": 24025244.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.258550691604614,
|
|
"epoch": 1.0072046109510087,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004906679497235856,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.19847694635391236,
|
|
"num_tokens": 24037701.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.407458353042602,
|
|
"epoch": 1.0076849183477425,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004906581760267397,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.19189472645521163,
|
|
"num_tokens": 24049369.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.356171464920044,
|
|
"epoch": 1.0081652257444764,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004906483973229513,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.19589548408985138,
|
|
"num_tokens": 24060625.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.423621988296508,
|
|
"epoch": 1.0086455331412103,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004906386136124476,
|
|
"loss": 5.1949,
|
|
"mean_token_accuracy": 0.19404211193323134,
|
|
"num_tokens": 24072527.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.402671384811401,
|
|
"epoch": 1.0091258405379442,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004906288248954554,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.19060073643922806,
|
|
"num_tokens": 24083979.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.330675411224365,
|
|
"epoch": 1.0096061479346783,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004906190311722023,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.20352004915475846,
|
|
"num_tokens": 24095926.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.304249668121338,
|
|
"epoch": 1.0100864553314122,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004906092324429155,
|
|
"loss": 5.0919,
|
|
"mean_token_accuracy": 0.205551378428936,
|
|
"num_tokens": 24107898.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.318305540084839,
|
|
"epoch": 1.010566762728146,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004905994287078227,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.20388976484537125,
|
|
"num_tokens": 24118713.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.376314926147461,
|
|
"epoch": 1.01104707012488,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004905896199671512,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.20016107857227325,
|
|
"num_tokens": 24130410.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.379752540588379,
|
|
"epoch": 1.0115273775216138,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000490579806221129,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.19758369624614716,
|
|
"num_tokens": 24140961.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.407641839981079,
|
|
"epoch": 1.0120076849183477,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004905699874699838,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.19086066782474517,
|
|
"num_tokens": 24153467.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.302155494689941,
|
|
"epoch": 1.0124879923150816,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004905601637139436,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.20565125942230225,
|
|
"num_tokens": 24163873.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.225621843338013,
|
|
"epoch": 1.0129682997118155,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004905503349532365,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.20568412989377977,
|
|
"num_tokens": 24175852.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.357414054870605,
|
|
"epoch": 1.0134486071085496,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004905405011880906,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.19606508165597916,
|
|
"num_tokens": 24187759.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.385495281219482,
|
|
"epoch": 1.0139289145052834,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004905306624187343,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.20722429007291793,
|
|
"num_tokens": 24199725.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.41778073310852,
|
|
"epoch": 1.0144092219020173,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004905208186453961,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.1956380143761635,
|
|
"num_tokens": 24210739.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.416292524337768,
|
|
"epoch": 1.0148895292987512,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004905109698683044,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.18740409463644028,
|
|
"num_tokens": 24221873.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.332883071899414,
|
|
"epoch": 1.015369836695485,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004905011160876878,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.19635324627161027,
|
|
"num_tokens": 24233503.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.334778261184693,
|
|
"epoch": 1.015850144092219,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004904912573037753,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.19603917598724366,
|
|
"num_tokens": 24244465.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.276717329025269,
|
|
"epoch": 1.0163304514889528,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004904813935167957,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.20925995111465454,
|
|
"num_tokens": 24255807.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.411048841476441,
|
|
"epoch": 1.0168107588856867,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004904715247269779,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.18983708173036576,
|
|
"num_tokens": 24268195.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.2618835926055905,
|
|
"epoch": 1.0172910662824208,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004904616509345514,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.20803383737802505,
|
|
"num_tokens": 24278915.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.349010944366455,
|
|
"epoch": 1.0177713736791547,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004904517721397449,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.20545896142721176,
|
|
"num_tokens": 24289115.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.3358502864837645,
|
|
"epoch": 1.0182516810758886,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004904418883427881,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.19754030108451842,
|
|
"num_tokens": 24300646.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.518046188354492,
|
|
"epoch": 1.0187319884726225,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004904319995439104,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.1906458780169487,
|
|
"num_tokens": 24312344.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.3027870655059814,
|
|
"epoch": 1.0192122958693564,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004904221057433412,
|
|
"loss": 5.0919,
|
|
"mean_token_accuracy": 0.20173458606004716,
|
|
"num_tokens": 24323382.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.296759748458863,
|
|
"epoch": 1.0196926032660902,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004904122069413105,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.19988326281309127,
|
|
"num_tokens": 24336820.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.396545362472534,
|
|
"epoch": 1.0201729106628241,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000490402303138048,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.20109147131443023,
|
|
"num_tokens": 24348547.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.443462705612182,
|
|
"epoch": 1.0206532180595582,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004903923943337836,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.19088246300816536,
|
|
"num_tokens": 24359586.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.390566301345825,
|
|
"epoch": 1.021133525456292,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004903824805287475,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.1936145007610321,
|
|
"num_tokens": 24371647.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.3553379535675045,
|
|
"epoch": 1.021613832853026,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004903725617231696,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.19957351982593535,
|
|
"num_tokens": 24382308.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.319635534286499,
|
|
"epoch": 1.0220941402497599,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004903626379172805,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.19824805557727815,
|
|
"num_tokens": 24393224.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.294248247146607,
|
|
"epoch": 1.0225744476464937,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004903527091113102,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.19135986715555192,
|
|
"num_tokens": 24405220.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.418373441696167,
|
|
"epoch": 1.0230547550432276,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004903427753054897,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.19548535495996475,
|
|
"num_tokens": 24416406.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.381947326660156,
|
|
"epoch": 1.0235350624399615,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004903328365000492,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.19457056373357773,
|
|
"num_tokens": 24428595.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.353590583801269,
|
|
"epoch": 1.0240153698366954,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004903228926952199,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.20169458091259002,
|
|
"num_tokens": 24439568.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.366839456558227,
|
|
"epoch": 1.0244956772334295,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004903129438912322,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.20210112780332565,
|
|
"num_tokens": 24451736.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.327310609817505,
|
|
"epoch": 1.0249759846301634,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004903029900883174,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.20306526720523835,
|
|
"num_tokens": 24463463.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.331499528884888,
|
|
"epoch": 1.0254562920268973,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004902930312867063,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.19781286865472794,
|
|
"num_tokens": 24474425.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.383645009994507,
|
|
"epoch": 1.0259365994236311,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004902830674866306,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.20142365843057633,
|
|
"num_tokens": 24486482.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.339239406585693,
|
|
"epoch": 1.026416906820365,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004902730986883211,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.19678469002246857,
|
|
"num_tokens": 24497709.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.309704351425171,
|
|
"epoch": 1.026897214217099,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004902631248920096,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.20305254310369492,
|
|
"num_tokens": 24508406.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.271453809738159,
|
|
"epoch": 1.0273775216138328,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004902531460979274,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.19548801630735396,
|
|
"num_tokens": 24520688.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.267741632461548,
|
|
"epoch": 1.0278578290105667,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004902431623063065,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.20485226362943648,
|
|
"num_tokens": 24531473.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.3205039501190186,
|
|
"epoch": 1.0283381364073008,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004902331735173785,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.19298290014266967,
|
|
"num_tokens": 24543263.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.366945123672485,
|
|
"epoch": 1.0288184438040346,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004902231797313752,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.20559680014848708,
|
|
"num_tokens": 24554067.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.235648059844971,
|
|
"epoch": 1.0292987512007685,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004902131809485288,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.2079134076833725,
|
|
"num_tokens": 24566291.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.348055839538574,
|
|
"epoch": 1.0297790585975024,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004902031771690713,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.19839471727609634,
|
|
"num_tokens": 24579248.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.304089164733886,
|
|
"epoch": 1.0302593659942363,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004901931683932352,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.2068445473909378,
|
|
"num_tokens": 24591047.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.428918838500977,
|
|
"epoch": 1.0307396733909702,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004901831546212526,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.19905165433883668,
|
|
"num_tokens": 24602454.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.348472166061401,
|
|
"epoch": 1.031219980787704,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004901731358533562,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.20431284755468368,
|
|
"num_tokens": 24614168.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.320114803314209,
|
|
"epoch": 1.031700288184438,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004901631120897785,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.2016324982047081,
|
|
"num_tokens": 24625588.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.336018323898315,
|
|
"epoch": 1.032180595581172,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004901530833307522,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.19757412523031234,
|
|
"num_tokens": 24637744.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.2790380954742435,
|
|
"epoch": 1.032660902977906,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004901430495765103,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.20606896728277208,
|
|
"num_tokens": 24649631.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.284367513656616,
|
|
"epoch": 1.0331412103746398,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004901330108272855,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.20179992616176606,
|
|
"num_tokens": 24660622.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.371030998229981,
|
|
"epoch": 1.0336215177713737,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004901229670833111,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.20080428719520568,
|
|
"num_tokens": 24671072.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.308475732803345,
|
|
"epoch": 1.0341018251681076,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004901129183448201,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.19608522802591324,
|
|
"num_tokens": 24683160.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.3464209079742435,
|
|
"epoch": 1.0345821325648414,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004901028646120459,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.19651904553174973,
|
|
"num_tokens": 24694703.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.299839019775391,
|
|
"epoch": 1.0350624399615753,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000490092805885222,
|
|
"loss": 5.1222,
|
|
"mean_token_accuracy": 0.20476236790418625,
|
|
"num_tokens": 24706429.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.331740140914917,
|
|
"epoch": 1.0355427473583094,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004900827421645816,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.20401365756988527,
|
|
"num_tokens": 24717682.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.410942125320434,
|
|
"epoch": 1.0360230547550433,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004900726734503589,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.19769208431243895,
|
|
"num_tokens": 24728789.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.268787050247193,
|
|
"epoch": 1.0365033621517772,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004900625997427872,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.20358683466911315,
|
|
"num_tokens": 24739788.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.314316129684448,
|
|
"epoch": 1.036983669548511,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004900525210421006,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.19738685786724092,
|
|
"num_tokens": 24751828.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.359867000579834,
|
|
"epoch": 1.037463976945245,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004900424373485329,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.2034547060728073,
|
|
"num_tokens": 24762061.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.286533308029175,
|
|
"epoch": 1.0379442843419788,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004900323486623185,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.20575871765613557,
|
|
"num_tokens": 24774018.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.303113317489624,
|
|
"epoch": 1.0384245917387127,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004900222549836914,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.20768230706453322,
|
|
"num_tokens": 24785206.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.325172042846679,
|
|
"epoch": 1.0389048991354466,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000490012156312886,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.20208380371332169,
|
|
"num_tokens": 24797730.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.336231279373169,
|
|
"epoch": 1.0393852065321807,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004900020526501369,
|
|
"loss": 5.2617,
|
|
"mean_token_accuracy": 0.19558039605617522,
|
|
"num_tokens": 24809267.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.36703405380249,
|
|
"epoch": 1.0398655139289146,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004899919439956785,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.19523145854473115,
|
|
"num_tokens": 24820461.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.258511400222778,
|
|
"epoch": 1.0403458213256485,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004899818303497455,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.1982979491353035,
|
|
"num_tokens": 24831959.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.291241455078125,
|
|
"epoch": 1.0408261287223823,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004899717117125728,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.20087361037731172,
|
|
"num_tokens": 24843655.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.3269788265228275,
|
|
"epoch": 1.0413064361191162,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004899615880843953,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.19905167818069458,
|
|
"num_tokens": 24855643.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.326853799819946,
|
|
"epoch": 1.04178674351585,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004899514594654481,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.20727464109659194,
|
|
"num_tokens": 24865745.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.258389139175415,
|
|
"epoch": 1.042267050912584,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004899413258559662,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.20829951465129853,
|
|
"num_tokens": 24876567.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.25359320640564,
|
|
"epoch": 1.0427473583093179,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004899311872561849,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.20130243450403212,
|
|
"num_tokens": 24888294.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.358793592453003,
|
|
"epoch": 1.043227665706052,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004899210436663398,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.19389114379882813,
|
|
"num_tokens": 24899559.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.33980541229248,
|
|
"epoch": 1.0437079731027858,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004899108950866661,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.2026054412126541,
|
|
"num_tokens": 24911205.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.3029063701629635,
|
|
"epoch": 1.0441882804995197,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004899007415173997,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.20214444547891616,
|
|
"num_tokens": 24922635.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.262282419204712,
|
|
"epoch": 1.0446685878962536,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004898905829587762,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.2085036426782608,
|
|
"num_tokens": 24932941.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.378588724136352,
|
|
"epoch": 1.0451488952929875,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004898804194110313,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.20182866007089614,
|
|
"num_tokens": 24943980.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.380227136611938,
|
|
"epoch": 1.0456292026897214,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 0.0004898702508744012,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.19424990564584732,
|
|
"num_tokens": 24955233.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.32433066368103,
|
|
"epoch": 1.0461095100864553,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004898600773491221,
|
|
"loss": 5.202,
|
|
"mean_token_accuracy": 0.19754131138324738,
|
|
"num_tokens": 24966971.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.388955116271973,
|
|
"epoch": 1.0465898174831891,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004898498988354297,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.19758228659629823,
|
|
"num_tokens": 24977515.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.365273952484131,
|
|
"epoch": 1.0470701248799232,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004898397153335608,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.20484659522771836,
|
|
"num_tokens": 24988131.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.382366371154785,
|
|
"epoch": 1.0475504322766571,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004898295268437517,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.19517035633325577,
|
|
"num_tokens": 24999238.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.3594996452331545,
|
|
"epoch": 1.048030739673391,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004898193333662388,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.19282138347625732,
|
|
"num_tokens": 25011443.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.324726533889771,
|
|
"epoch": 1.0485110470701249,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004898091349012588,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.2023757666349411,
|
|
"num_tokens": 25022151.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.3478271484375,
|
|
"epoch": 1.0489913544668588,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004897989314490486,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.20534102469682694,
|
|
"num_tokens": 25032730.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.261315107345581,
|
|
"epoch": 1.0494716618635926,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004897887230098451,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.20467284321784973,
|
|
"num_tokens": 25044455.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.2687413692474365,
|
|
"epoch": 1.0499519692603265,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004897785095838852,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.21040538251399993,
|
|
"num_tokens": 25056647.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.285398197174072,
|
|
"epoch": 1.0504322766570606,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004897682911714061,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.2036648541688919,
|
|
"num_tokens": 25067618.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.316044807434082,
|
|
"epoch": 1.0509125840537945,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000489758067772645,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.2035629704594612,
|
|
"num_tokens": 25079753.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.283793640136719,
|
|
"epoch": 1.0513928914505284,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004897478393878392,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.19937746673822404,
|
|
"num_tokens": 25091023.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.331173467636108,
|
|
"epoch": 1.0518731988472623,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004897376060172264,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.19686004221439363,
|
|
"num_tokens": 25101396.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.344325304031372,
|
|
"epoch": 1.0523535062439962,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004897273676610438,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.1974998876452446,
|
|
"num_tokens": 25112562.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.333099269866944,
|
|
"epoch": 1.05283381364073,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004897171243195295,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.20290710031986237,
|
|
"num_tokens": 25124401.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.302322673797607,
|
|
"epoch": 1.053314121037464,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000489706875992921,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.19728537499904633,
|
|
"num_tokens": 25137345.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.349043846130371,
|
|
"epoch": 1.0537944284341978,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004896966226814565,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.19820962399244307,
|
|
"num_tokens": 25149300.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.3485993385314945,
|
|
"epoch": 1.054274735830932,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004896863643853739,
|
|
"loss": 5.0985,
|
|
"mean_token_accuracy": 0.20550342947244643,
|
|
"num_tokens": 25159510.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.36569390296936,
|
|
"epoch": 1.0547550432276658,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004896761011049114,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.19641568064689635,
|
|
"num_tokens": 25172346.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.395049571990967,
|
|
"epoch": 1.0552353506243997,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004896658328403074,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.2000742509961128,
|
|
"num_tokens": 25183471.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.3808046817779545,
|
|
"epoch": 1.0557156580211335,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004896555595918001,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.20059962719678878,
|
|
"num_tokens": 25195067.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.3311121463775635,
|
|
"epoch": 1.0561959654178674,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004896452813596281,
|
|
"loss": 5.1882,
|
|
"mean_token_accuracy": 0.19561705291271209,
|
|
"num_tokens": 25206165.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.315497589111328,
|
|
"epoch": 1.0566762728146013,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004896349981440301,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.20908810794353486,
|
|
"num_tokens": 25217229.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.408291530609131,
|
|
"epoch": 1.0571565802113352,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004896247099452447,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.19362145364284516,
|
|
"num_tokens": 25229349.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.351105976104736,
|
|
"epoch": 1.057636887608069,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004896144167635108,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.20179051756858826,
|
|
"num_tokens": 25240367.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.346260929107666,
|
|
"epoch": 1.0581171950048032,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004896041185990675,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.1944615662097931,
|
|
"num_tokens": 25252025.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.35924391746521,
|
|
"epoch": 1.058597502401537,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004895938154521538,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.20582169741392137,
|
|
"num_tokens": 25264846.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.307664060592652,
|
|
"epoch": 1.059077809798271,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004895835073230089,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.20170839875936508,
|
|
"num_tokens": 25276150.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.334551429748535,
|
|
"epoch": 1.0595581171950048,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004895731942118722,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.20394746214151382,
|
|
"num_tokens": 25287819.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.361875438690186,
|
|
"epoch": 1.0600384245917387,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004895628761189829,
|
|
"loss": 5.1969,
|
|
"mean_token_accuracy": 0.1970707193017006,
|
|
"num_tokens": 25300467.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.241466903686524,
|
|
"epoch": 1.0605187319884726,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004895525530445809,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.20045005530118942,
|
|
"num_tokens": 25312447.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.337131118774414,
|
|
"epoch": 1.0609990393852065,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004895422249889057,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.19588236808776854,
|
|
"num_tokens": 25324160.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.342945718765259,
|
|
"epoch": 1.0614793467819403,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004895318919521971,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.21145522445440293,
|
|
"num_tokens": 25335106.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.2834875106811525,
|
|
"epoch": 1.0619596541786744,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004895215539346949,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.20613888949155806,
|
|
"num_tokens": 25345246.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.288952732086182,
|
|
"epoch": 1.0624399615754083,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004895112109366393,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.20038184523582458,
|
|
"num_tokens": 25356665.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.320684862136841,
|
|
"epoch": 1.0629202689721422,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004895008629582703,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.20399431735277176,
|
|
"num_tokens": 25368128.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.256019353866577,
|
|
"epoch": 1.063400576368876,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004894905099998283,
|
|
"loss": 5.0985,
|
|
"mean_token_accuracy": 0.20649359077215196,
|
|
"num_tokens": 25379061.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.323419713973999,
|
|
"epoch": 1.06388088376561,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004894801520615535,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.20609591603279115,
|
|
"num_tokens": 25390157.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.295299339294433,
|
|
"epoch": 1.0643611911623438,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004894697891436863,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.2000119388103485,
|
|
"num_tokens": 25400446.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.354647254943847,
|
|
"epoch": 1.0648414985590777,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004894594212464676,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.19363622069358827,
|
|
"num_tokens": 25412064.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.314082050323487,
|
|
"epoch": 1.0653218059558118,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004894490483701381,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.20125600844621658,
|
|
"num_tokens": 25422898.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.329068040847778,
|
|
"epoch": 1.0658021133525457,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004894386705149382,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.19680934250354767,
|
|
"num_tokens": 25434318.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.27101616859436,
|
|
"epoch": 1.0662824207492796,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004894282876811093,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.2062190964818001,
|
|
"num_tokens": 25444941.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.35099687576294,
|
|
"epoch": 1.0667627281460135,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004894178998688921,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.2039244294166565,
|
|
"num_tokens": 25455971.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.288018321990966,
|
|
"epoch": 1.0672430355427474,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004894075070785281,
|
|
"loss": 5.0985,
|
|
"mean_token_accuracy": 0.19993453323841096,
|
|
"num_tokens": 25467587.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.234090805053711,
|
|
"epoch": 1.0677233429394812,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004893971093102585,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.20735440403223038,
|
|
"num_tokens": 25479137.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.4302772045135494,
|
|
"epoch": 1.0682036503362151,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004893867065643245,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.19399198442697524,
|
|
"num_tokens": 25491755.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.269463062286377,
|
|
"epoch": 1.068683957732949,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004893762988409678,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.20891222655773162,
|
|
"num_tokens": 25503581.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.301801300048828,
|
|
"epoch": 1.069164265129683,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004893658861404301,
|
|
"loss": 5.1632,
|
|
"mean_token_accuracy": 0.2034335657954216,
|
|
"num_tokens": 25515032.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.270562839508057,
|
|
"epoch": 1.069644572526417,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004893554684629529,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.20247771888971328,
|
|
"num_tokens": 25526347.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.378921699523926,
|
|
"epoch": 1.0701248799231509,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004893450458087784,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.2016587108373642,
|
|
"num_tokens": 25538287.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.190388250350952,
|
|
"epoch": 1.0706051873198847,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004893346181781483,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.21713515669107436,
|
|
"num_tokens": 25548431.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.284275913238526,
|
|
"epoch": 1.0710854947166186,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004893241855713048,
|
|
"loss": 5.2511,
|
|
"mean_token_accuracy": 0.19596656560897827,
|
|
"num_tokens": 25558706.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.369014835357666,
|
|
"epoch": 1.0715658021133525,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004893137479884903,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.19954039752483368,
|
|
"num_tokens": 25569920.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.312915992736817,
|
|
"epoch": 1.0720461095100864,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004893033054299468,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.21186500042676926,
|
|
"num_tokens": 25581340.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.303180742263794,
|
|
"epoch": 1.0725264169068203,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000489292857895917,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.19763920754194259,
|
|
"num_tokens": 25592477.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.361607789993286,
|
|
"epoch": 1.0730067243035544,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004892824053866432,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.20616717934608458,
|
|
"num_tokens": 25604583.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.438195610046387,
|
|
"epoch": 1.0734870317002883,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004892719479023683,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.19459341019392012,
|
|
"num_tokens": 25614743.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.242146968841553,
|
|
"epoch": 1.0739673390970221,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000489261485443335,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.21015122681856155,
|
|
"num_tokens": 25626796.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.30523681640625,
|
|
"epoch": 1.074447646493756,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004892510180097863,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.20219666808843612,
|
|
"num_tokens": 25638014.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.284056901931763,
|
|
"epoch": 1.07492795389049,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004892405456019651,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.20499511957168579,
|
|
"num_tokens": 25649555.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.376839256286621,
|
|
"epoch": 1.0754082612872238,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004892300682201147,
|
|
"loss": 5.2426,
|
|
"mean_token_accuracy": 0.19616783708333968,
|
|
"num_tokens": 25662886.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.367648506164551,
|
|
"epoch": 1.0758885686839577,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004892195858644782,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.20881618708372116,
|
|
"num_tokens": 25673802.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.28165488243103,
|
|
"epoch": 1.0763688760806915,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000489209098535299,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.20603721886873244,
|
|
"num_tokens": 25685545.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.269009351730347,
|
|
"epoch": 1.0768491834774256,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004891986062328205,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.2044074445962906,
|
|
"num_tokens": 25697955.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.363277864456177,
|
|
"epoch": 1.0773294908741595,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004891881089572865,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.19669867306947708,
|
|
"num_tokens": 25709707.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.349743318557739,
|
|
"epoch": 1.0778097982708934,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004891776067089406,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.19733243435621262,
|
|
"num_tokens": 25720576.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.282660341262817,
|
|
"epoch": 1.0782901056676273,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004891670994880266,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.20656931549310684,
|
|
"num_tokens": 25731387.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.293915271759033,
|
|
"epoch": 1.0787704130643612,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004891565872947888,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.2143150970339775,
|
|
"num_tokens": 25741813.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.3240571975708,
|
|
"epoch": 1.079250720461095,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004891460701294706,
|
|
"loss": 5.1486,
|
|
"mean_token_accuracy": 0.1984674945473671,
|
|
"num_tokens": 25753763.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.302602529525757,
|
|
"epoch": 1.079731027857829,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004891355479923167,
|
|
"loss": 5.0815,
|
|
"mean_token_accuracy": 0.20513346344232558,
|
|
"num_tokens": 25765269.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.304611253738403,
|
|
"epoch": 1.080211335254563,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004891250208835712,
|
|
"loss": 5.1672,
|
|
"mean_token_accuracy": 0.2030718818306923,
|
|
"num_tokens": 25776841.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.368564414978027,
|
|
"epoch": 1.080691642651297,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004891144888034784,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.18602197021245956,
|
|
"num_tokens": 25788151.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.337092876434326,
|
|
"epoch": 1.0811719500480308,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004891039517522832,
|
|
"loss": 5.0752,
|
|
"mean_token_accuracy": 0.2106889858841896,
|
|
"num_tokens": 25799194.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.287901401519775,
|
|
"epoch": 1.0816522574447647,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004890934097302299,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.19977914839982985,
|
|
"num_tokens": 25809483.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.252952909469604,
|
|
"epoch": 1.0821325648414986,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004890828627375632,
|
|
"loss": 5.0917,
|
|
"mean_token_accuracy": 0.19584571123123168,
|
|
"num_tokens": 25820781.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.362701177597046,
|
|
"epoch": 1.0826128722382324,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004890723107745283,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.1962701588869095,
|
|
"num_tokens": 25832111.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.428535985946655,
|
|
"epoch": 1.0830931796349663,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004890617538413699,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.20441062301397322,
|
|
"num_tokens": 25843300.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.380526542663574,
|
|
"epoch": 1.0835734870317002,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004890511919383333,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.19422634094953536,
|
|
"num_tokens": 25855337.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.4125570297241214,
|
|
"epoch": 1.084053794428434,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004890406250656636,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.19568423926830292,
|
|
"num_tokens": 25866683.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.261790180206299,
|
|
"epoch": 1.0845341018251682,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004890300532236062,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.20246828198432923,
|
|
"num_tokens": 25878041.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.398085498809815,
|
|
"epoch": 1.085014409221902,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004890194764124064,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.19958120584487915,
|
|
"num_tokens": 25889059.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.281335115432739,
|
|
"epoch": 1.085494716618636,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004890088946323099,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.21608632951974868,
|
|
"num_tokens": 25900062.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.316459131240845,
|
|
"epoch": 1.0859750240153698,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004889983078835623,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.19546637386083604,
|
|
"num_tokens": 25911813.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.36879415512085,
|
|
"epoch": 1.0864553314121037,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004889877161664096,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.20611478239297867,
|
|
"num_tokens": 25922321.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.315264940261841,
|
|
"epoch": 1.0869356388088376,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004889771194810974,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.20887239575386046,
|
|
"num_tokens": 25933631.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.375712156295776,
|
|
"epoch": 1.0874159462055715,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004889665178278719,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.20074028968811036,
|
|
"num_tokens": 25945190.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.365614700317383,
|
|
"epoch": 1.0878962536023056,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004889559112069792,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.20831136107444764,
|
|
"num_tokens": 25956817.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.401874113082886,
|
|
"epoch": 1.0883765609990395,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004889452996186657,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.2048810377717018,
|
|
"num_tokens": 25968134.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.25398621559143,
|
|
"epoch": 1.0888568683957733,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004889346830631774,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.20354647785425187,
|
|
"num_tokens": 25981825.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.364640998840332,
|
|
"epoch": 1.0893371757925072,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000488924061540761,
|
|
"loss": 5.2423,
|
|
"mean_token_accuracy": 0.18749297857284547,
|
|
"num_tokens": 25993962.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.307242155075073,
|
|
"epoch": 1.089817483189241,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004889134350516633,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.20552517622709274,
|
|
"num_tokens": 26005705.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.316702270507813,
|
|
"epoch": 1.090297790585975,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004889028035961308,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.20994055718183519,
|
|
"num_tokens": 26017111.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.319946193695069,
|
|
"epoch": 1.0907780979827089,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004888921671744103,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.19824621826410294,
|
|
"num_tokens": 26028097.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.317778205871582,
|
|
"epoch": 1.0912584053794427,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004888815257867488,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.2026633307337761,
|
|
"num_tokens": 26039281.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.342022180557251,
|
|
"epoch": 1.0917387127761768,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004888708794333934,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.19024603068828583,
|
|
"num_tokens": 26051133.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.314816284179687,
|
|
"epoch": 1.0922190201729107,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004888602281145913,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.1988406077027321,
|
|
"num_tokens": 26062220.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.314972734451294,
|
|
"epoch": 1.0926993275696446,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004888495718305897,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.21319786161184312,
|
|
"num_tokens": 26072556.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.380842208862305,
|
|
"epoch": 1.0931796349663785,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000488838910581636,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.19425466656684875,
|
|
"num_tokens": 26084218.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.4592187881469725,
|
|
"epoch": 1.0936599423631124,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004888282443679777,
|
|
"loss": 5.3343,
|
|
"mean_token_accuracy": 0.19081743508577348,
|
|
"num_tokens": 26096272.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.376057863235474,
|
|
"epoch": 1.0941402497598463,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004888175731898627,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.1963579311966896,
|
|
"num_tokens": 26109247.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.3417774677276615,
|
|
"epoch": 1.0946205571565801,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004888068970475384,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.20040577352046968,
|
|
"num_tokens": 26121340.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.357487201690674,
|
|
"epoch": 1.0951008645533142,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004887962159412529,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.19647157937288284,
|
|
"num_tokens": 26133135.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.256601476669312,
|
|
"epoch": 1.0955811719500481,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004887855298712541,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.20414958596229554,
|
|
"num_tokens": 26145324.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.238174772262573,
|
|
"epoch": 1.096061479346782,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048877483883779,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.20625945925712585,
|
|
"num_tokens": 26156739.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.3349381446838375,
|
|
"epoch": 1.0965417867435159,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004887641428411091,
|
|
"loss": 5.1561,
|
|
"mean_token_accuracy": 0.1959335044026375,
|
|
"num_tokens": 26169543.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.362424612045288,
|
|
"epoch": 1.0970220941402498,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004887534418814595,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.20367608070373536,
|
|
"num_tokens": 26181317.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.394422101974487,
|
|
"epoch": 1.0975024015369836,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004887427359590897,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.19395215213298797,
|
|
"num_tokens": 26193402.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.307780361175537,
|
|
"epoch": 1.0979827089337175,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004887320250742482,
|
|
"loss": 5.0916,
|
|
"mean_token_accuracy": 0.20511206686496736,
|
|
"num_tokens": 26204660.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.383396196365356,
|
|
"epoch": 1.0984630163304514,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004887213092271838,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.1984705463051796,
|
|
"num_tokens": 26215593.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.260968637466431,
|
|
"epoch": 1.0989433237271853,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004887105884181451,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.21085789948701858,
|
|
"num_tokens": 26227481.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.341152286529541,
|
|
"epoch": 1.0994236311239194,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004886998626473813,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.19789917320013045,
|
|
"num_tokens": 26238260.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.365911197662354,
|
|
"epoch": 1.0999039385206533,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004886891319151411,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.2019819512963295,
|
|
"num_tokens": 26249749.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.36580228805542,
|
|
"epoch": 1.1003842459173871,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004886783962216738,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.2028710126876831,
|
|
"num_tokens": 26260639.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.286028146743774,
|
|
"epoch": 1.100864553314121,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004886676555672287,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.1980138450860977,
|
|
"num_tokens": 26271797.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.326308965682983,
|
|
"epoch": 1.101344860710855,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004886569099520551,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.19022870510816575,
|
|
"num_tokens": 26283298.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.240048599243164,
|
|
"epoch": 1.1018251681075888,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004886461593764024,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.20655218809843062,
|
|
"num_tokens": 26293632.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.30937933921814,
|
|
"epoch": 1.1023054755043227,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004886354038405204,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.1942225769162178,
|
|
"num_tokens": 26307053.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.308082342147827,
|
|
"epoch": 1.1027857829010568,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004886246433446586,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.21324211806058885,
|
|
"num_tokens": 26317136.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.310516214370727,
|
|
"epoch": 1.1032660902977907,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004886138778890669,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.20462871193885804,
|
|
"num_tokens": 26328865.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.286093759536743,
|
|
"epoch": 1.1037463976945245,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004886031074739953,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.20698221772909164,
|
|
"num_tokens": 26341010.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.3811126232147215,
|
|
"epoch": 1.1042267050912584,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004885923320996938,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.1976682350039482,
|
|
"num_tokens": 26352203.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.369465780258179,
|
|
"epoch": 1.1047070124879923,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004885815517664127,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.1991453006863594,
|
|
"num_tokens": 26363096.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.235171985626221,
|
|
"epoch": 1.1051873198847262,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.000488570766474402,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.20452217906713485,
|
|
"num_tokens": 26374776.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.288644599914551,
|
|
"epoch": 1.10566762728146,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004885599762239124,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.2004079893231392,
|
|
"num_tokens": 26386654.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.281540012359619,
|
|
"epoch": 1.106147934678194,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004885491810151943,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.20224497318267823,
|
|
"num_tokens": 26400022.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.292015504837036,
|
|
"epoch": 1.106628242074928,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004885383808484982,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.20151816606521605,
|
|
"num_tokens": 26412308.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.387752437591553,
|
|
"epoch": 1.107108549471662,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004885275757240751,
|
|
"loss": 5.2164,
|
|
"mean_token_accuracy": 0.1877727374434471,
|
|
"num_tokens": 26424506.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.326724243164063,
|
|
"epoch": 1.1075888568683958,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004885167656421757,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.20713104903697968,
|
|
"num_tokens": 26435020.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.194391345977783,
|
|
"epoch": 1.1080691642651297,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000488505950603051,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.20736747235059738,
|
|
"num_tokens": 26447952.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.345295095443726,
|
|
"epoch": 1.1085494716618636,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000488495130606952,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.20188061892986298,
|
|
"num_tokens": 26460001.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.325395345687866,
|
|
"epoch": 1.1090297790585975,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004884843056541302,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.2056600719690323,
|
|
"num_tokens": 26472139.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.324504566192627,
|
|
"epoch": 1.1095100864553313,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004884734757448367,
|
|
"loss": 5.1583,
|
|
"mean_token_accuracy": 0.20389454215765,
|
|
"num_tokens": 26483855.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.380694341659546,
|
|
"epoch": 1.1099903938520654,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000488462640879323,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.1924385756254196,
|
|
"num_tokens": 26496529.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.328584671020508,
|
|
"epoch": 1.1104707012487993,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004884518010578405,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.21022463589906693,
|
|
"num_tokens": 26506663.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.344662618637085,
|
|
"epoch": 1.1109510086455332,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004884409562806411,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.19380222856998444,
|
|
"num_tokens": 26519091.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.3521080493927,
|
|
"epoch": 1.111431316042267,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004884301065479765,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.19393169283866882,
|
|
"num_tokens": 26530145.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.370323705673218,
|
|
"epoch": 1.111911623439001,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004884192518600986,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.19910329729318618,
|
|
"num_tokens": 26541228.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.36710524559021,
|
|
"epoch": 1.1123919308357348,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004884083922172593,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.19784497767686843,
|
|
"num_tokens": 26551359.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.198082780838012,
|
|
"epoch": 1.1128722382324687,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004883975276197108,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.2030889168381691,
|
|
"num_tokens": 26562911.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.3775718212127686,
|
|
"epoch": 1.1133525456292026,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004883866580677055,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.20831287354230882,
|
|
"num_tokens": 26573198.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.297350549697876,
|
|
"epoch": 1.1138328530259365,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004883757835614956,
|
|
"loss": 5.1507,
|
|
"mean_token_accuracy": 0.1993216633796692,
|
|
"num_tokens": 26584932.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.391242742538452,
|
|
"epoch": 1.1143131604226706,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004883649041013335,
|
|
"loss": 5.2766,
|
|
"mean_token_accuracy": 0.19492211639881135,
|
|
"num_tokens": 26596042.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.391051769256592,
|
|
"epoch": 1.1147934678194045,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000488354019687472,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.1957885205745697,
|
|
"num_tokens": 26607359.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.418501377105713,
|
|
"epoch": 1.1152737752161384,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004883431303201636,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.20717217326164244,
|
|
"num_tokens": 26617095.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.34371018409729,
|
|
"epoch": 1.1157540826128722,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004883322359996613,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.20002456605434418,
|
|
"num_tokens": 26628450.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.275143957138061,
|
|
"epoch": 1.1162343900096061,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004883213367262179,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.20413772612810135,
|
|
"num_tokens": 26639428.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.212841367721557,
|
|
"epoch": 1.11671469740634,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004883104325000866,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.20164805948734282,
|
|
"num_tokens": 26650730.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.359587049484253,
|
|
"epoch": 1.1171950048030739,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004882995233215203,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.19986220002174376,
|
|
"num_tokens": 26661745.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.304432821273804,
|
|
"epoch": 1.117675312199808,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004882886091907726,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.21270100474357606,
|
|
"num_tokens": 26672976.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.3710681915283205,
|
|
"epoch": 1.1181556195965419,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048827769010809666,
|
|
"loss": 5.1715,
|
|
"mean_token_accuracy": 0.20010971128940583,
|
|
"num_tokens": 26683503.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.333467483520508,
|
|
"epoch": 1.1186359269932757,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048826676607374606,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.19441845864057541,
|
|
"num_tokens": 26695160.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.298226356506348,
|
|
"epoch": 1.1191162343900096,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048825583708797434,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.2089619129896164,
|
|
"num_tokens": 26706514.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.269511890411377,
|
|
"epoch": 1.1195965417867435,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004882449031510354,
|
|
"loss": 5.0291,
|
|
"mean_token_accuracy": 0.21192042529582977,
|
|
"num_tokens": 26717268.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.412432432174683,
|
|
"epoch": 1.1200768491834774,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000488233964263183,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.1944217398762703,
|
|
"num_tokens": 26728821.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.372755098342895,
|
|
"epoch": 1.1205571565802113,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048822302042467115,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.1952611729502678,
|
|
"num_tokens": 26740476.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.358553028106689,
|
|
"epoch": 1.1210374639769451,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004882120716357539,
|
|
"loss": 5.2108,
|
|
"mean_token_accuracy": 0.2008669763803482,
|
|
"num_tokens": 26751289.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.260187387466431,
|
|
"epoch": 1.1215177713736793,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004882011178966854,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.20536865890026093,
|
|
"num_tokens": 26762115.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.263187265396118,
|
|
"epoch": 1.1219980787704131,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004881901592077201,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.2028586134314537,
|
|
"num_tokens": 26772837.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.413993549346924,
|
|
"epoch": 1.122478386167147,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004881791955691123,
|
|
"loss": 5.1597,
|
|
"mean_token_accuracy": 0.20203806608915328,
|
|
"num_tokens": 26783721.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.288437223434448,
|
|
"epoch": 1.122958693563881,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048816822698111655,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.20836410373449327,
|
|
"num_tokens": 26794320.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.328686952590942,
|
|
"epoch": 1.1234390009606148,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048815725344398766,
|
|
"loss": 5.2619,
|
|
"mean_token_accuracy": 0.18543754518032074,
|
|
"num_tokens": 26807053.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.432075452804566,
|
|
"epoch": 1.1239193083573487,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048814627495798017,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.19605380892753602,
|
|
"num_tokens": 26817245.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.318490743637085,
|
|
"epoch": 1.1243996157540825,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004881352915233492,
|
|
"loss": 5.2033,
|
|
"mean_token_accuracy": 0.19369176179170608,
|
|
"num_tokens": 26829498.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.269003677368164,
|
|
"epoch": 1.1248799231508164,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048812430314034956,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.20862208157777787,
|
|
"num_tokens": 26840534.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.345874357223511,
|
|
"epoch": 1.1253602305475505,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004881133098092365,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.19713760316371917,
|
|
"num_tokens": 26851305.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.286346864700318,
|
|
"epoch": 1.1258405379442844,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004881023115302652,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.19811634868383407,
|
|
"num_tokens": 26862620.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.341561412811279,
|
|
"epoch": 1.1263208453410183,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000488091308303691,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.19700847566127777,
|
|
"num_tokens": 26874108.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.379293823242188,
|
|
"epoch": 1.1268011527377522,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004880803001297694,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.19801948666572572,
|
|
"num_tokens": 26886523.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.268254137039184,
|
|
"epoch": 1.127281460134486,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004880692870087559,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.20859607309103012,
|
|
"num_tokens": 26897316.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.292900800704956,
|
|
"epoch": 1.12776176753122,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048805826894090626,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.1993417963385582,
|
|
"num_tokens": 26909807.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.404553413391113,
|
|
"epoch": 1.1282420749279538,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048804724592647626,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.1930053010582924,
|
|
"num_tokens": 26922054.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.2868565082550045,
|
|
"epoch": 1.1287223823246877,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004880362179657218,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.19807282090187073,
|
|
"num_tokens": 26933838.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.286669588088989,
|
|
"epoch": 1.1292026897214218,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048802518505889904,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.19519306868314742,
|
|
"num_tokens": 26945396.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.4107646465301515,
|
|
"epoch": 1.1296829971181557,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048801414720626404,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.19581684917211534,
|
|
"num_tokens": 26957809.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.381056547164917,
|
|
"epoch": 1.1301633045148896,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048800310440807294,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.213106144964695,
|
|
"num_tokens": 26969024.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.2403723239898685,
|
|
"epoch": 1.1306436119116234,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004879920566645823,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.20311659723520278,
|
|
"num_tokens": 26980689.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.381258153915406,
|
|
"epoch": 1.1311239193083573,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004879810039760486,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.19316246062517167,
|
|
"num_tokens": 26992115.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.416398000717163,
|
|
"epoch": 1.1316042267050912,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004879699463427284,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.2001924678683281,
|
|
"num_tokens": 27003042.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.269796848297119,
|
|
"epoch": 1.132084534101825,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004879588837648785,
|
|
"loss": 5.0768,
|
|
"mean_token_accuracy": 0.20741364657878875,
|
|
"num_tokens": 27013863.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.209153270721435,
|
|
"epoch": 1.1325648414985592,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048794781624275554,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.20994998663663864,
|
|
"num_tokens": 27024423.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.273507118225098,
|
|
"epoch": 1.133045148895293,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048793674377661664,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.19897654950618743,
|
|
"num_tokens": 27035460.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.308765459060669,
|
|
"epoch": 1.133525456292027,
|
|
"grad_norm": 4.9375,
|
|
"learning_rate": 0.00048792566636671886,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.2021664023399353,
|
|
"num_tokens": 27046731.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.317369031906128,
|
|
"epoch": 1.1340057636887608,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004879145840133194,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.20544746965169908,
|
|
"num_tokens": 27057758.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.419113540649414,
|
|
"epoch": 1.1344860710854947,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004879034967166755,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.19622780233621598,
|
|
"num_tokens": 27068055.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.274322271347046,
|
|
"epoch": 1.1349663784822286,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004878924044770446,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.20086952447891235,
|
|
"num_tokens": 27078602.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.241742944717407,
|
|
"epoch": 1.1354466858789625,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004878813072946843,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.2024749681353569,
|
|
"num_tokens": 27089944.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.316387081146241,
|
|
"epoch": 1.1359269932756964,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048787020516985203,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.21009573638439177,
|
|
"num_tokens": 27100486.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.327194261550903,
|
|
"epoch": 1.1364073006724302,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048785909810280576,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.2001217260956764,
|
|
"num_tokens": 27111435.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.339106178283691,
|
|
"epoch": 1.1368876080691643,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004878479860938033,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.2010580375790596,
|
|
"num_tokens": 27123482.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.316496467590332,
|
|
"epoch": 1.1373679154658982,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048783686914310266,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.20054138600826263,
|
|
"num_tokens": 27135009.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.292483854293823,
|
|
"epoch": 1.137848222862632,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004878257472509619,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.2079618513584137,
|
|
"num_tokens": 27145230.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.257307815551758,
|
|
"epoch": 1.138328530259366,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004878146204176392,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.20189673453569412,
|
|
"num_tokens": 27156490.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.317572021484375,
|
|
"epoch": 1.1388088376560999,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000487803488643393,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.20475540459156036,
|
|
"num_tokens": 27166727.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.336464738845825,
|
|
"epoch": 1.1392891450528337,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048779235192848166,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.20334441661834718,
|
|
"num_tokens": 27177969.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.328475856781006,
|
|
"epoch": 1.1397694524495678,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004877812102731638,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.2028002917766571,
|
|
"num_tokens": 27189637.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.419164037704467,
|
|
"epoch": 1.1402497598463017,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048777006367769804,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.19987482130527495,
|
|
"num_tokens": 27201124.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.4266434669494625,
|
|
"epoch": 1.1407300672430356,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004877589121423432,
|
|
"loss": 5.1971,
|
|
"mean_token_accuracy": 0.1969528913497925,
|
|
"num_tokens": 27212399.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.347195625305176,
|
|
"epoch": 1.1412103746397695,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004877477556673582,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.20323327630758287,
|
|
"num_tokens": 27224469.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.340413570404053,
|
|
"epoch": 1.1416906820365034,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000487736594253002,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.2063771441578865,
|
|
"num_tokens": 27236026.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.325238943099976,
|
|
"epoch": 1.1421709894332372,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00048772542789953384,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.19896686524152757,
|
|
"num_tokens": 27248332.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.320242500305175,
|
|
"epoch": 1.1426512968299711,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048771425660721284,
|
|
"loss": 5.0651,
|
|
"mean_token_accuracy": 0.20700283348560333,
|
|
"num_tokens": 27258701.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.341927719116211,
|
|
"epoch": 1.143131604226705,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048770308037629853,
|
|
"loss": 5.1962,
|
|
"mean_token_accuracy": 0.1995152086019516,
|
|
"num_tokens": 27269808.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.358848667144775,
|
|
"epoch": 1.143611911623439,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004876918992070502,
|
|
"loss": 5.2243,
|
|
"mean_token_accuracy": 0.19571249932050705,
|
|
"num_tokens": 27282440.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.430353212356567,
|
|
"epoch": 1.144092219020173,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004876807130997276,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.20419214218854903,
|
|
"num_tokens": 27294430.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.386064529418945,
|
|
"epoch": 1.1445725264169069,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004876695220545903,
|
|
"loss": 5.2157,
|
|
"mean_token_accuracy": 0.20013083666563034,
|
|
"num_tokens": 27305896.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.426707410812378,
|
|
"epoch": 1.1450528338136408,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048765832607189824,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.19146447330713273,
|
|
"num_tokens": 27318195.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.2909684658050535,
|
|
"epoch": 1.1455331412103746,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048764712515191136,
|
|
"loss": 5.1082,
|
|
"mean_token_accuracy": 0.19882248640060424,
|
|
"num_tokens": 27329055.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.309229183197021,
|
|
"epoch": 1.1460134486071085,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048763591929488966,
|
|
"loss": 5.0994,
|
|
"mean_token_accuracy": 0.2096550866961479,
|
|
"num_tokens": 27340296.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.35607123374939,
|
|
"epoch": 1.1464937560038424,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004876247085010933,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.19835602343082429,
|
|
"num_tokens": 27350995.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.312476348876953,
|
|
"epoch": 1.1469740634005763,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048761349277078253,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.19872767776250838,
|
|
"num_tokens": 27362463.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.3264600276947025,
|
|
"epoch": 1.1474543707973104,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048760227210421775,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.2142341449856758,
|
|
"num_tokens": 27373579.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.311580657958984,
|
|
"epoch": 1.1479346781940443,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004875910465016596,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.20801135301589965,
|
|
"num_tokens": 27383813.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.319390487670899,
|
|
"epoch": 1.1484149855907781,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004875798159633686,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.19501575827598572,
|
|
"num_tokens": 27395651.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.360228490829468,
|
|
"epoch": 1.148895292987512,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004875685804896055,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.19930996000766754,
|
|
"num_tokens": 27407827.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.359977388381958,
|
|
"epoch": 1.149375600384246,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004875573400806312,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.19832769632339478,
|
|
"num_tokens": 27418777.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.3723530769348145,
|
|
"epoch": 1.1498559077809798,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048754609473670654,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.19500161111354827,
|
|
"num_tokens": 27429626.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.429681301116943,
|
|
"epoch": 1.1503362151777137,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004875348444580927,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.19333478510379792,
|
|
"num_tokens": 27442304.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.349698638916015,
|
|
"epoch": 1.1508165225744476,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000487523589245051,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.2069244235754013,
|
|
"num_tokens": 27454421.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.262469625473022,
|
|
"epoch": 1.1512968299711814,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004875123290978425,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.20779014974832535,
|
|
"num_tokens": 27465220.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.276208305358887,
|
|
"epoch": 1.1517771373679155,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048750106401672876,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.1957992672920227,
|
|
"num_tokens": 27476542.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.275929069519043,
|
|
"epoch": 1.1522574447646494,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048748979400197134,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.20864951312541963,
|
|
"num_tokens": 27487721.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.3089026927948,
|
|
"epoch": 1.1527377521613833,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048747851905383183,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.20202126801013948,
|
|
"num_tokens": 27498982.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.1527377521613833,
|
|
"eval_entropy": 5.155717872282983,
|
|
"eval_loss": 5.226895809173584,
|
|
"eval_mean_token_accuracy": 0.2056008455589203,
|
|
"eval_num_tokens": 27498982.0,
|
|
"eval_runtime": 26.5965,
|
|
"eval_samples_per_second": 1233.81,
|
|
"eval_steps_per_second": 154.231,
|
|
"step": 12000
|
|
}
|
|
],
|
|
"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": 4.2059085251328e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|