0c7ef51387
Model: fpadovani/hin-deva-100mb-after-ppt-Dp-100mb-ckpt500_seed455 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2881844380403458,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 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
|
|
}
|
|
],
|
|
"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": 1.0587455152128e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|