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": 4.905435800552368,
|
||
|
|
"epoch": 0.0004803073967339097,
|
||
|
|
"grad_norm": 15.375,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 14.4544,
|
||
|
|
"mean_token_accuracy": 6.385695887729525e-05,
|
||
|
|
"num_tokens": 10855.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.913383293151855,
|
||
|
|
"epoch": 0.0009606147934678194,
|
||
|
|
"grad_norm": 16.625,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 14.5216,
|
||
|
|
"mean_token_accuracy": 0.00014638935390394182,
|
||
|
|
"num_tokens": 24110.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.925370550155639,
|
||
|
|
"epoch": 0.001440922190201729,
|
||
|
|
"grad_norm": 18.125,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 14.412,
|
||
|
|
"mean_token_accuracy": 6.793478387407958e-05,
|
||
|
|
"num_tokens": 35984.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.947782182693482,
|
||
|
|
"epoch": 0.0019212295869356388,
|
||
|
|
"grad_norm": 19.5,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 14.2345,
|
||
|
|
"mean_token_accuracy": 9.48766595683992e-05,
|
||
|
|
"num_tokens": 48152.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.064438819885254,
|
||
|
|
"epoch": 0.0024015369836695487,
|
||
|
|
"grad_norm": 23.75,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 13.7842,
|
||
|
|
"mean_token_accuracy": 0.00013405063073150812,
|
||
|
|
"num_tokens": 59810.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.404191589355468,
|
||
|
|
"epoch": 0.002881844380403458,
|
||
|
|
"grad_norm": 31.125,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 13.1568,
|
||
|
|
"mean_token_accuracy": 8.628127980045975e-05,
|
||
|
|
"num_tokens": 70852.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.142218971252442,
|
||
|
|
"epoch": 0.0033621517771373678,
|
||
|
|
"grad_norm": 21.0,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 11.9814,
|
||
|
|
"mean_token_accuracy": 5.5741361575201156e-05,
|
||
|
|
"num_tokens": 83378.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.262308692932129,
|
||
|
|
"epoch": 0.0038424591738712775,
|
||
|
|
"grad_norm": 3.5625,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.9117,
|
||
|
|
"mean_token_accuracy": 9.433962404727935e-05,
|
||
|
|
"num_tokens": 95505.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.698264122009277,
|
||
|
|
"epoch": 0.004322766570605188,
|
||
|
|
"grad_norm": 3.203125,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 10.7241,
|
||
|
|
"mean_token_accuracy": 0.0005975825013592839,
|
||
|
|
"num_tokens": 106812.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.737651824951172,
|
||
|
|
"epoch": 0.004803073967339097,
|
||
|
|
"grad_norm": 2.78125,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 10.5853,
|
||
|
|
"mean_token_accuracy": 0.009875867154914886,
|
||
|
|
"num_tokens": 118572.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.73659906387329,
|
||
|
|
"epoch": 0.005283381364073006,
|
||
|
|
"grad_norm": 2.109375,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 10.3833,
|
||
|
|
"mean_token_accuracy": 0.014529264252632856,
|
||
|
|
"num_tokens": 130051.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.701386642456054,
|
||
|
|
"epoch": 0.005763688760806916,
|
||
|
|
"grad_norm": 2.046875,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 10.2322,
|
||
|
|
"mean_token_accuracy": 0.014093486312776803,
|
||
|
|
"num_tokens": 141920.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.711284351348876,
|
||
|
|
"epoch": 0.006243996157540826,
|
||
|
|
"grad_norm": 1.796875,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 10.045,
|
||
|
|
"mean_token_accuracy": 0.015402647480368615,
|
||
|
|
"num_tokens": 152706.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.732075595855713,
|
||
|
|
"epoch": 0.0067243035542747355,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.9817,
|
||
|
|
"mean_token_accuracy": 0.013764715194702149,
|
||
|
|
"num_tokens": 165253.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.734086227416991,
|
||
|
|
"epoch": 0.007204610951008645,
|
||
|
|
"grad_norm": 1.8046875,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.8756,
|
||
|
|
"mean_token_accuracy": 0.02153849443420768,
|
||
|
|
"num_tokens": 176708.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.729099750518799,
|
||
|
|
"epoch": 0.007684918347742555,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.8268,
|
||
|
|
"mean_token_accuracy": 0.020801819767802952,
|
||
|
|
"num_tokens": 188240.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.723050022125244,
|
||
|
|
"epoch": 0.008165225744476465,
|
||
|
|
"grad_norm": 1.796875,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.6525,
|
||
|
|
"mean_token_accuracy": 0.01858828719705343,
|
||
|
|
"num_tokens": 198355.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.719482040405273,
|
||
|
|
"epoch": 0.008645533141210375,
|
||
|
|
"grad_norm": 1.71875,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.5811,
|
||
|
|
"mean_token_accuracy": 0.01679358258843422,
|
||
|
|
"num_tokens": 209497.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.711874198913574,
|
||
|
|
"epoch": 0.009125840537944284,
|
||
|
|
"grad_norm": 1.828125,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.5018,
|
||
|
|
"mean_token_accuracy": 0.016100958082824947,
|
||
|
|
"num_tokens": 220859.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.695251655578613,
|
||
|
|
"epoch": 0.009606147934678195,
|
||
|
|
"grad_norm": 1.703125,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.4214,
|
||
|
|
"mean_token_accuracy": 0.017460816819220782,
|
||
|
|
"num_tokens": 231550.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.673291873931884,
|
||
|
|
"epoch": 0.010086455331412104,
|
||
|
|
"grad_norm": 1.671875,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 9.2854,
|
||
|
|
"mean_token_accuracy": 0.016554870828986167,
|
||
|
|
"num_tokens": 244210.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.652278709411622,
|
||
|
|
"epoch": 0.010566762728146013,
|
||
|
|
"grad_norm": 1.7578125,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 9.1581,
|
||
|
|
"mean_token_accuracy": 0.024293087422847748,
|
||
|
|
"num_tokens": 255745.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.617483043670655,
|
||
|
|
"epoch": 0.011047070124879923,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 9.055,
|
||
|
|
"mean_token_accuracy": 0.03160325270146132,
|
||
|
|
"num_tokens": 266180.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.569834327697754,
|
||
|
|
"epoch": 0.011527377521613832,
|
||
|
|
"grad_norm": 1.65625,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.939,
|
||
|
|
"mean_token_accuracy": 0.025451960042119026,
|
||
|
|
"num_tokens": 277736.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.52544527053833,
|
||
|
|
"epoch": 0.012007684918347743,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.8203,
|
||
|
|
"mean_token_accuracy": 0.034478765353560446,
|
||
|
|
"num_tokens": 289069.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.468996620178222,
|
||
|
|
"epoch": 0.012487992315081652,
|
||
|
|
"grad_norm": 1.5546875,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.6972,
|
||
|
|
"mean_token_accuracy": 0.03924299031496048,
|
||
|
|
"num_tokens": 300240.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.390470600128173,
|
||
|
|
"epoch": 0.012968299711815562,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.622,
|
||
|
|
"mean_token_accuracy": 0.033455712348222734,
|
||
|
|
"num_tokens": 311698.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.308708190917969,
|
||
|
|
"epoch": 0.013448607108549471,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.4986,
|
||
|
|
"mean_token_accuracy": 0.036465326137840745,
|
||
|
|
"num_tokens": 322844.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.209622859954834,
|
||
|
|
"epoch": 0.013928914505283382,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.3864,
|
||
|
|
"mean_token_accuracy": 0.04093883950263262,
|
||
|
|
"num_tokens": 335092.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.091598796844483,
|
||
|
|
"epoch": 0.01440922190201729,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.2513,
|
||
|
|
"mean_token_accuracy": 0.041372421011328694,
|
||
|
|
"num_tokens": 347033.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.934578609466552,
|
||
|
|
"epoch": 0.014889529298751201,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.133,
|
||
|
|
"mean_token_accuracy": 0.04138694703578949,
|
||
|
|
"num_tokens": 358696.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.762340259552001,
|
||
|
|
"epoch": 0.01536983669548511,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 8.0344,
|
||
|
|
"mean_token_accuracy": 0.04901535548269749,
|
||
|
|
"num_tokens": 369390.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.557822990417481,
|
||
|
|
"epoch": 0.01585014409221902,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.9344,
|
||
|
|
"mean_token_accuracy": 0.04700087420642376,
|
||
|
|
"num_tokens": 380540.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.355019855499268,
|
||
|
|
"epoch": 0.01633045148895293,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.8587,
|
||
|
|
"mean_token_accuracy": 0.04431998413056135,
|
||
|
|
"num_tokens": 391243.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.114866542816163,
|
||
|
|
"epoch": 0.01681075888568684,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.7947,
|
||
|
|
"mean_token_accuracy": 0.05138894282281399,
|
||
|
|
"num_tokens": 403336.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.863803100585937,
|
||
|
|
"epoch": 0.01729106628242075,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.693,
|
||
|
|
"mean_token_accuracy": 0.054227447509765624,
|
||
|
|
"num_tokens": 413886.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.668179988861084,
|
||
|
|
"epoch": 0.01777137367915466,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.7008,
|
||
|
|
"mean_token_accuracy": 0.05373974815011025,
|
||
|
|
"num_tokens": 425277.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.488366603851318,
|
||
|
|
"epoch": 0.01825168107588857,
|
||
|
|
"grad_norm": 0.72265625,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.7708,
|
||
|
|
"mean_token_accuracy": 0.05546994470059872,
|
||
|
|
"num_tokens": 436868.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.390744590759278,
|
||
|
|
"epoch": 0.018731988472622477,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.5877,
|
||
|
|
"mean_token_accuracy": 0.052850323542952535,
|
||
|
|
"num_tokens": 448349.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.283522891998292,
|
||
|
|
"epoch": 0.01921229586935639,
|
||
|
|
"grad_norm": 0.77734375,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.5809,
|
||
|
|
"mean_token_accuracy": 0.05953923240303993,
|
||
|
|
"num_tokens": 459447.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.150887298583985,
|
||
|
|
"epoch": 0.0196926032660903,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.5463,
|
||
|
|
"mean_token_accuracy": 0.05646048374474048,
|
||
|
|
"num_tokens": 470734.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.137212657928467,
|
||
|
|
"epoch": 0.020172910662824207,
|
||
|
|
"grad_norm": 0.7578125,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.5847,
|
||
|
|
"mean_token_accuracy": 0.06030619703233242,
|
||
|
|
"num_tokens": 482015.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.123589897155762,
|
||
|
|
"epoch": 0.020653218059558116,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.5311,
|
||
|
|
"mean_token_accuracy": 0.06505471915006637,
|
||
|
|
"num_tokens": 493339.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.091688442230225,
|
||
|
|
"epoch": 0.021133525456292025,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.4806,
|
||
|
|
"mean_token_accuracy": 0.06740148589015008,
|
||
|
|
"num_tokens": 504924.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.105245876312257,
|
||
|
|
"epoch": 0.021613832853025938,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.4493,
|
||
|
|
"mean_token_accuracy": 0.06430868282914162,
|
||
|
|
"num_tokens": 516603.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.071302318572998,
|
||
|
|
"epoch": 0.022094140249759846,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.3628,
|
||
|
|
"mean_token_accuracy": 0.07100334689021111,
|
||
|
|
"num_tokens": 528347.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.018728876113892,
|
||
|
|
"epoch": 0.022574447646493755,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.4365,
|
||
|
|
"mean_token_accuracy": 0.07649173960089684,
|
||
|
|
"num_tokens": 539328.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.024458360671996,
|
||
|
|
"epoch": 0.023054755043227664,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.4121,
|
||
|
|
"mean_token_accuracy": 0.07992132529616355,
|
||
|
|
"num_tokens": 549297.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.979285478591919,
|
||
|
|
"epoch": 0.023535062439961577,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.373,
|
||
|
|
"mean_token_accuracy": 0.07391561307013035,
|
||
|
|
"num_tokens": 560306.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.05026822090149,
|
||
|
|
"epoch": 0.024015369836695485,
|
||
|
|
"grad_norm": 2.078125,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.4298,
|
||
|
|
"mean_token_accuracy": 0.07491427883505822,
|
||
|
|
"num_tokens": 571972.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.011105632781982,
|
||
|
|
"epoch": 0.024495677233429394,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.3324,
|
||
|
|
"mean_token_accuracy": 0.07995120882987976,
|
||
|
|
"num_tokens": 582962.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.978642559051513,
|
||
|
|
"epoch": 0.024975984630163303,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.29,
|
||
|
|
"mean_token_accuracy": 0.07967569157481194,
|
||
|
|
"num_tokens": 597193.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.959802865982056,
|
||
|
|
"epoch": 0.025456292026897216,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.3629,
|
||
|
|
"mean_token_accuracy": 0.08052113763988018,
|
||
|
|
"num_tokens": 608982.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.93332347869873,
|
||
|
|
"epoch": 0.025936599423631124,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.3853,
|
||
|
|
"mean_token_accuracy": 0.07839832231402397,
|
||
|
|
"num_tokens": 619953.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.012384223937989,
|
||
|
|
"epoch": 0.026416906820365033,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.3273,
|
||
|
|
"mean_token_accuracy": 0.08211004585027695,
|
||
|
|
"num_tokens": 631039.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.914879417419433,
|
||
|
|
"epoch": 0.026897214217098942,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.3281,
|
||
|
|
"mean_token_accuracy": 0.0799741841852665,
|
||
|
|
"num_tokens": 642656.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.884822368621826,
|
||
|
|
"epoch": 0.027377521613832854,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.1901,
|
||
|
|
"mean_token_accuracy": 0.09594471827149391,
|
||
|
|
"num_tokens": 653748.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.860710859298706,
|
||
|
|
"epoch": 0.027857829010566763,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.1763,
|
||
|
|
"mean_token_accuracy": 0.08746851906180382,
|
||
|
|
"num_tokens": 665618.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.799470329284668,
|
||
|
|
"epoch": 0.028338136407300672,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.1972,
|
||
|
|
"mean_token_accuracy": 0.08807335570454597,
|
||
|
|
"num_tokens": 677329.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.814197397232055,
|
||
|
|
"epoch": 0.02881844380403458,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.1466,
|
||
|
|
"mean_token_accuracy": 0.09343294948339462,
|
||
|
|
"num_tokens": 688278.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.766972303390503,
|
||
|
|
"epoch": 0.029298751200768493,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.2009,
|
||
|
|
"mean_token_accuracy": 0.09057235419750213,
|
||
|
|
"num_tokens": 700739.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.782851505279541,
|
||
|
|
"epoch": 0.029779058597502402,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.1242,
|
||
|
|
"mean_token_accuracy": 0.09343240261077881,
|
||
|
|
"num_tokens": 712527.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.725392866134643,
|
||
|
|
"epoch": 0.03025936599423631,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.1564,
|
||
|
|
"mean_token_accuracy": 0.09019288495182991,
|
||
|
|
"num_tokens": 724514.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.741910028457641,
|
||
|
|
"epoch": 0.03073967339097022,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.1047,
|
||
|
|
"mean_token_accuracy": 0.09378963932394982,
|
||
|
|
"num_tokens": 735679.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.70381178855896,
|
||
|
|
"epoch": 0.03121998078770413,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.0993,
|
||
|
|
"mean_token_accuracy": 0.0981727458536625,
|
||
|
|
"num_tokens": 747896.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6704418659210205,
|
||
|
|
"epoch": 0.03170028818443804,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 7.1443,
|
||
|
|
"mean_token_accuracy": 0.09557413160800934,
|
||
|
|
"num_tokens": 759081.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.715982484817505,
|
||
|
|
"epoch": 0.03218059558117195,
|
||
|
|
"grad_norm": 1.546875,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.0815,
|
||
|
|
"mean_token_accuracy": 0.09094736129045486,
|
||
|
|
"num_tokens": 770459.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.668689107894897,
|
||
|
|
"epoch": 0.03266090297790586,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 7.0395,
|
||
|
|
"mean_token_accuracy": 0.09340968057513237,
|
||
|
|
"num_tokens": 783960.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.586823654174805,
|
||
|
|
"epoch": 0.03314121037463977,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 7.118,
|
||
|
|
"mean_token_accuracy": 0.10006800666451454,
|
||
|
|
"num_tokens": 795425.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6425714015960695,
|
||
|
|
"epoch": 0.03362151777137368,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 7.0715,
|
||
|
|
"mean_token_accuracy": 0.09306764900684357,
|
||
|
|
"num_tokens": 807536.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6408501148223875,
|
||
|
|
"epoch": 0.034101825168107586,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.1133,
|
||
|
|
"mean_token_accuracy": 0.09133664220571518,
|
||
|
|
"num_tokens": 818801.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.592654371261597,
|
||
|
|
"epoch": 0.0345821325648415,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 6.997,
|
||
|
|
"mean_token_accuracy": 0.09742675051093101,
|
||
|
|
"num_tokens": 831497.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.561050844192505,
|
||
|
|
"epoch": 0.03506243996157541,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 6.9518,
|
||
|
|
"mean_token_accuracy": 0.10334301143884658,
|
||
|
|
"num_tokens": 842491.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5975159168243405,
|
||
|
|
"epoch": 0.03554274735830932,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 7.038,
|
||
|
|
"mean_token_accuracy": 0.09360877349972725,
|
||
|
|
"num_tokens": 854560.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.535368490219116,
|
||
|
|
"epoch": 0.03602305475504323,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 6.9465,
|
||
|
|
"mean_token_accuracy": 0.1063318483531475,
|
||
|
|
"num_tokens": 866688.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5550884246826175,
|
||
|
|
"epoch": 0.03650336215177714,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.0347,
|
||
|
|
"mean_token_accuracy": 0.09658555164933205,
|
||
|
|
"num_tokens": 879484.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.572937870025635,
|
||
|
|
"epoch": 0.036983669548511046,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 7.0152,
|
||
|
|
"mean_token_accuracy": 0.10198549181222916,
|
||
|
|
"num_tokens": 890807.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.576615810394287,
|
||
|
|
"epoch": 0.037463976945244955,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 6.9605,
|
||
|
|
"mean_token_accuracy": 0.10429177060723305,
|
||
|
|
"num_tokens": 901759.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.430867433547974,
|
||
|
|
"epoch": 0.037944284341978864,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 6.89,
|
||
|
|
"mean_token_accuracy": 0.10844507589936256,
|
||
|
|
"num_tokens": 912212.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.53248782157898,
|
||
|
|
"epoch": 0.03842459173871278,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 6.9851,
|
||
|
|
"mean_token_accuracy": 0.10315561667084694,
|
||
|
|
"num_tokens": 923947.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.401272916793824,
|
||
|
|
"epoch": 0.03890489913544669,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 6.9312,
|
||
|
|
"mean_token_accuracy": 0.10761535987257957,
|
||
|
|
"num_tokens": 935732.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.374160099029541,
|
||
|
|
"epoch": 0.0393852065321806,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 6.8693,
|
||
|
|
"mean_token_accuracy": 0.10408192500472069,
|
||
|
|
"num_tokens": 948261.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.473669195175171,
|
||
|
|
"epoch": 0.039865513928914506,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 6.9775,
|
||
|
|
"mean_token_accuracy": 0.10531274750828742,
|
||
|
|
"num_tokens": 959574.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.502210903167724,
|
||
|
|
"epoch": 0.040345821325648415,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 7.0212,
|
||
|
|
"mean_token_accuracy": 0.10413776263594628,
|
||
|
|
"num_tokens": 970329.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.457794141769409,
|
||
|
|
"epoch": 0.040826128722382324,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 6.897,
|
||
|
|
"mean_token_accuracy": 0.11288983076810837,
|
||
|
|
"num_tokens": 982037.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.320314025878906,
|
||
|
|
"epoch": 0.04130643611911623,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 6.8488,
|
||
|
|
"mean_token_accuracy": 0.10890574008226395,
|
||
|
|
"num_tokens": 994612.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.436053037643433,
|
||
|
|
"epoch": 0.04178674351585014,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 6.9562,
|
||
|
|
"mean_token_accuracy": 0.11320589855313301,
|
||
|
|
"num_tokens": 1005960.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.342877960205078,
|
||
|
|
"epoch": 0.04226705091258405,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 6.8312,
|
||
|
|
"mean_token_accuracy": 0.10930031016469002,
|
||
|
|
"num_tokens": 1017618.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3924178123474125,
|
||
|
|
"epoch": 0.042747358309317966,
|
||
|
|
"grad_norm": 1.78125,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 6.8722,
|
||
|
|
"mean_token_accuracy": 0.10684446468949318,
|
||
|
|
"num_tokens": 1029307.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.34854736328125,
|
||
|
|
"epoch": 0.043227665706051875,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 6.8798,
|
||
|
|
"mean_token_accuracy": 0.10711006596684455,
|
||
|
|
"num_tokens": 1042027.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3988017559051515,
|
||
|
|
"epoch": 0.043707973102785784,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 6.8815,
|
||
|
|
"mean_token_accuracy": 0.10970013663172722,
|
||
|
|
"num_tokens": 1053125.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.270225954055786,
|
||
|
|
"epoch": 0.04418828049951969,
|
||
|
|
"grad_norm": 1.6328125,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 6.8643,
|
||
|
|
"mean_token_accuracy": 0.11234270855784416,
|
||
|
|
"num_tokens": 1064908.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.329568862915039,
|
||
|
|
"epoch": 0.0446685878962536,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 6.7486,
|
||
|
|
"mean_token_accuracy": 0.11601889058947563,
|
||
|
|
"num_tokens": 1076328.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.339612579345703,
|
||
|
|
"epoch": 0.04514889529298751,
|
||
|
|
"grad_norm": 1.546875,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 6.9582,
|
||
|
|
"mean_token_accuracy": 0.10401691868901253,
|
||
|
|
"num_tokens": 1088469.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.294072389602661,
|
||
|
|
"epoch": 0.04562920268972142,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 6.764,
|
||
|
|
"mean_token_accuracy": 0.11554281786084175,
|
||
|
|
"num_tokens": 1099408.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.170223951339722,
|
||
|
|
"epoch": 0.04610951008645533,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 6.6937,
|
||
|
|
"mean_token_accuracy": 0.11718685477972031,
|
||
|
|
"num_tokens": 1111101.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.192569828033447,
|
||
|
|
"epoch": 0.046589817483189244,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 6.6999,
|
||
|
|
"mean_token_accuracy": 0.11837229505181313,
|
||
|
|
"num_tokens": 1122877.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.259336137771607,
|
||
|
|
"epoch": 0.04707012487992315,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 6.811,
|
||
|
|
"mean_token_accuracy": 0.10224953144788743,
|
||
|
|
"num_tokens": 1133956.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.205342721939087,
|
||
|
|
"epoch": 0.04755043227665706,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.7171,
|
||
|
|
"mean_token_accuracy": 0.11888269484043121,
|
||
|
|
"num_tokens": 1146101.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.218681526184082,
|
||
|
|
"epoch": 0.04803073967339097,
|
||
|
|
"grad_norm": 1.6015625,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.8062,
|
||
|
|
"mean_token_accuracy": 0.12109306752681732,
|
||
|
|
"num_tokens": 1157432.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.241644239425659,
|
||
|
|
"epoch": 0.04851104707012488,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 6.7906,
|
||
|
|
"mean_token_accuracy": 0.11429283022880554,
|
||
|
|
"num_tokens": 1167601.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.20673680305481,
|
||
|
|
"epoch": 0.04899135446685879,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.6849,
|
||
|
|
"mean_token_accuracy": 0.11796795651316642,
|
||
|
|
"num_tokens": 1178818.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.338191556930542,
|
||
|
|
"epoch": 0.0494716618635927,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 6.9209,
|
||
|
|
"mean_token_accuracy": 0.11272176653146744,
|
||
|
|
"num_tokens": 1189977.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.15383129119873,
|
||
|
|
"epoch": 0.049951969260326606,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.7585,
|
||
|
|
"mean_token_accuracy": 0.11906541213393211,
|
||
|
|
"num_tokens": 1201039.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.194189023971558,
|
||
|
|
"epoch": 0.05043227665706052,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.7788,
|
||
|
|
"mean_token_accuracy": 0.11931035146117211,
|
||
|
|
"num_tokens": 1212573.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.264106559753418,
|
||
|
|
"epoch": 0.05091258405379443,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.7181,
|
||
|
|
"mean_token_accuracy": 0.12056513205170631,
|
||
|
|
"num_tokens": 1223382.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.170845222473145,
|
||
|
|
"epoch": 0.05139289145052834,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.7927,
|
||
|
|
"mean_token_accuracy": 0.1244619682431221,
|
||
|
|
"num_tokens": 1236501.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.22953052520752,
|
||
|
|
"epoch": 0.05187319884726225,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 6.7818,
|
||
|
|
"mean_token_accuracy": 0.11887621656060218,
|
||
|
|
"num_tokens": 1246798.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1261049747467045,
|
||
|
|
"epoch": 0.05235350624399616,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.7113,
|
||
|
|
"mean_token_accuracy": 0.12007794082164765,
|
||
|
|
"num_tokens": 1258182.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.136359167098999,
|
||
|
|
"epoch": 0.052833813640730067,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.6647,
|
||
|
|
"mean_token_accuracy": 0.11331228986382484,
|
||
|
|
"num_tokens": 1270273.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1538010597229,
|
||
|
|
"epoch": 0.053314121037463975,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.7157,
|
||
|
|
"mean_token_accuracy": 0.1148271806538105,
|
||
|
|
"num_tokens": 1281136.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.182579135894775,
|
||
|
|
"epoch": 0.053794428434197884,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.6991,
|
||
|
|
"mean_token_accuracy": 0.11754038706421852,
|
||
|
|
"num_tokens": 1294488.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.084699916839599,
|
||
|
|
"epoch": 0.05427473583093179,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.6054,
|
||
|
|
"mean_token_accuracy": 0.12230072245001793,
|
||
|
|
"num_tokens": 1304113.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.104630041122436,
|
||
|
|
"epoch": 0.05475504322766571,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.6713,
|
||
|
|
"mean_token_accuracy": 0.12584275975823403,
|
||
|
|
"num_tokens": 1315417.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.049445104598999,
|
||
|
|
"epoch": 0.05523535062439962,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.6306,
|
||
|
|
"mean_token_accuracy": 0.12282092794775963,
|
||
|
|
"num_tokens": 1328084.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.128454923629761,
|
||
|
|
"epoch": 0.05571565802113353,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.7747,
|
||
|
|
"mean_token_accuracy": 0.12278011664748192,
|
||
|
|
"num_tokens": 1338696.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.090286588668823,
|
||
|
|
"epoch": 0.056195965417867436,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.7179,
|
||
|
|
"mean_token_accuracy": 0.11662147119641304,
|
||
|
|
"num_tokens": 1350240.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.117737483978272,
|
||
|
|
"epoch": 0.056676272814601344,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.6639,
|
||
|
|
"mean_token_accuracy": 0.11824186667799949,
|
||
|
|
"num_tokens": 1361720.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.979755496978759,
|
||
|
|
"epoch": 0.05715658021133525,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.6611,
|
||
|
|
"mean_token_accuracy": 0.12714812606573106,
|
||
|
|
"num_tokens": 1373286.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1012420654296875,
|
||
|
|
"epoch": 0.05763688760806916,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.6116,
|
||
|
|
"mean_token_accuracy": 0.12019829899072647,
|
||
|
|
"num_tokens": 1384274.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.009186458587647,
|
||
|
|
"epoch": 0.05811719500480307,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.6625,
|
||
|
|
"mean_token_accuracy": 0.12345866709947587,
|
||
|
|
"num_tokens": 1395355.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.984350728988647,
|
||
|
|
"epoch": 0.05859750240153699,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.5861,
|
||
|
|
"mean_token_accuracy": 0.1286102719604969,
|
||
|
|
"num_tokens": 1406664.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.138849353790283,
|
||
|
|
"epoch": 0.059077809798270896,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.7404,
|
||
|
|
"mean_token_accuracy": 0.11916537806391717,
|
||
|
|
"num_tokens": 1418450.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0278784275054935,
|
||
|
|
"epoch": 0.059558117195004805,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.6374,
|
||
|
|
"mean_token_accuracy": 0.1211201086640358,
|
||
|
|
"num_tokens": 1430048.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.098714780807495,
|
||
|
|
"epoch": 0.060038424591738714,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.6739,
|
||
|
|
"mean_token_accuracy": 0.12407828345894814,
|
||
|
|
"num_tokens": 1441820.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.935336065292359,
|
||
|
|
"epoch": 0.06051873198847262,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.5317,
|
||
|
|
"mean_token_accuracy": 0.12386323809623719,
|
||
|
|
"num_tokens": 1453209.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9461079120635985,
|
||
|
|
"epoch": 0.06099903938520653,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.546,
|
||
|
|
"mean_token_accuracy": 0.122261643409729,
|
||
|
|
"num_tokens": 1465423.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.992834091186523,
|
||
|
|
"epoch": 0.06147934678194044,
|
||
|
|
"grad_norm": 1.609375,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.5324,
|
||
|
|
"mean_token_accuracy": 0.12468917295336723,
|
||
|
|
"num_tokens": 1476575.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9027880191802975,
|
||
|
|
"epoch": 0.06195965417867435,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.495,
|
||
|
|
"mean_token_accuracy": 0.12275839298963546,
|
||
|
|
"num_tokens": 1486932.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.965601539611816,
|
||
|
|
"epoch": 0.06243996157540826,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.532,
|
||
|
|
"mean_token_accuracy": 0.12491905614733696,
|
||
|
|
"num_tokens": 1498494.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.929765415191651,
|
||
|
|
"epoch": 0.06292026897214217,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.5786,
|
||
|
|
"mean_token_accuracy": 0.1209442898631096,
|
||
|
|
"num_tokens": 1509937.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.01481876373291,
|
||
|
|
"epoch": 0.06340057636887608,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.6063,
|
||
|
|
"mean_token_accuracy": 0.1320799134671688,
|
||
|
|
"num_tokens": 1519823.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.075559997558594,
|
||
|
|
"epoch": 0.06388088376560999,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.6301,
|
||
|
|
"mean_token_accuracy": 0.12214003503322601,
|
||
|
|
"num_tokens": 1529943.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.827705144882202,
|
||
|
|
"epoch": 0.0643611911623439,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.4589,
|
||
|
|
"mean_token_accuracy": 0.12923690006136895,
|
||
|
|
"num_tokens": 1540618.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.919480466842652,
|
||
|
|
"epoch": 0.06484149855907781,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.5779,
|
||
|
|
"mean_token_accuracy": 0.12186570391058922,
|
||
|
|
"num_tokens": 1553208.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.962458515167237,
|
||
|
|
"epoch": 0.06532180595581172,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.5472,
|
||
|
|
"mean_token_accuracy": 0.13120265454053878,
|
||
|
|
"num_tokens": 1563975.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.013445615768433,
|
||
|
|
"epoch": 0.06580211335254563,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.5969,
|
||
|
|
"mean_token_accuracy": 0.12027480229735374,
|
||
|
|
"num_tokens": 1575998.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.872586297988891,
|
||
|
|
"epoch": 0.06628242074927954,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.4957,
|
||
|
|
"mean_token_accuracy": 0.12978472113609313,
|
||
|
|
"num_tokens": 1586041.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.915009069442749,
|
||
|
|
"epoch": 0.06676272814601344,
|
||
|
|
"grad_norm": 1.546875,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.5464,
|
||
|
|
"mean_token_accuracy": 0.12723507061600686,
|
||
|
|
"num_tokens": 1597531.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.859202480316162,
|
||
|
|
"epoch": 0.06724303554274735,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.5324,
|
||
|
|
"mean_token_accuracy": 0.1253533720970154,
|
||
|
|
"num_tokens": 1609255.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.813373184204101,
|
||
|
|
"epoch": 0.06772334293948126,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.5279,
|
||
|
|
"mean_token_accuracy": 0.1321180894970894,
|
||
|
|
"num_tokens": 1621098.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.89396710395813,
|
||
|
|
"epoch": 0.06820365033621517,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.4187,
|
||
|
|
"mean_token_accuracy": 0.14093777388334275,
|
||
|
|
"num_tokens": 1631941.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.811427450180053,
|
||
|
|
"epoch": 0.0686839577329491,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.4234,
|
||
|
|
"mean_token_accuracy": 0.13498233929276465,
|
||
|
|
"num_tokens": 1643117.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.800242614746094,
|
||
|
|
"epoch": 0.069164265129683,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.4627,
|
||
|
|
"mean_token_accuracy": 0.13018925338983536,
|
||
|
|
"num_tokens": 1653595.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.83650918006897,
|
||
|
|
"epoch": 0.06964457252641691,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.5025,
|
||
|
|
"mean_token_accuracy": 0.13135557770729064,
|
||
|
|
"num_tokens": 1664495.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.802758979797363,
|
||
|
|
"epoch": 0.07012487992315082,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.4803,
|
||
|
|
"mean_token_accuracy": 0.1322146400809288,
|
||
|
|
"num_tokens": 1674923.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.83389892578125,
|
||
|
|
"epoch": 0.07060518731988473,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.3745,
|
||
|
|
"mean_token_accuracy": 0.1347797356545925,
|
||
|
|
"num_tokens": 1685904.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.834182548522949,
|
||
|
|
"epoch": 0.07108549471661864,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.5992,
|
||
|
|
"mean_token_accuracy": 0.12240826413035392,
|
||
|
|
"num_tokens": 1699133.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7865643978118895,
|
||
|
|
"epoch": 0.07156580211335255,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.408,
|
||
|
|
"mean_token_accuracy": 0.13333356380462646,
|
||
|
|
"num_tokens": 1711559.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8253981590271,
|
||
|
|
"epoch": 0.07204610951008646,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.3276,
|
||
|
|
"mean_token_accuracy": 0.1389731504023075,
|
||
|
|
"num_tokens": 1722526.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7026113986969,
|
||
|
|
"epoch": 0.07252641690682037,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.3874,
|
||
|
|
"mean_token_accuracy": 0.13594599291682244,
|
||
|
|
"num_tokens": 1734261.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.764468193054199,
|
||
|
|
"epoch": 0.07300672430355427,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.3728,
|
||
|
|
"mean_token_accuracy": 0.14337323382496833,
|
||
|
|
"num_tokens": 1745151.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.874772214889527,
|
||
|
|
"epoch": 0.07348703170028818,
|
||
|
|
"grad_norm": 1.6328125,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.5351,
|
||
|
|
"mean_token_accuracy": 0.132026257365942,
|
||
|
|
"num_tokens": 1755463.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.830476856231689,
|
||
|
|
"epoch": 0.07396733909702209,
|
||
|
|
"grad_norm": 1.5546875,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.4887,
|
||
|
|
"mean_token_accuracy": 0.13159892857074737,
|
||
|
|
"num_tokens": 1767717.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.660166883468628,
|
||
|
|
"epoch": 0.074447646493756,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.321,
|
||
|
|
"mean_token_accuracy": 0.1407831773161888,
|
||
|
|
"num_tokens": 1779115.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.616621780395508,
|
||
|
|
"epoch": 0.07492795389048991,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.2814,
|
||
|
|
"mean_token_accuracy": 0.13830310627818107,
|
||
|
|
"num_tokens": 1789644.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.793073272705078,
|
||
|
|
"epoch": 0.07540826128722382,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.4934,
|
||
|
|
"mean_token_accuracy": 0.13178734481334686,
|
||
|
|
"num_tokens": 1800606.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.812487077713013,
|
||
|
|
"epoch": 0.07588856868395773,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.4962,
|
||
|
|
"mean_token_accuracy": 0.130271115899086,
|
||
|
|
"num_tokens": 1812168.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.774988603591919,
|
||
|
|
"epoch": 0.07636887608069164,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.4425,
|
||
|
|
"mean_token_accuracy": 0.12558576837182045,
|
||
|
|
"num_tokens": 1823830.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7873927593231205,
|
||
|
|
"epoch": 0.07684918347742556,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.4269,
|
||
|
|
"mean_token_accuracy": 0.13118278980255127,
|
||
|
|
"num_tokens": 1835611.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.705799150466919,
|
||
|
|
"epoch": 0.07732949087415947,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.4715,
|
||
|
|
"mean_token_accuracy": 0.12893390357494355,
|
||
|
|
"num_tokens": 1847036.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.743785047531128,
|
||
|
|
"epoch": 0.07780979827089338,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.416,
|
||
|
|
"mean_token_accuracy": 0.1317111983895302,
|
||
|
|
"num_tokens": 1857476.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.710385322570801,
|
||
|
|
"epoch": 0.07829010566762729,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.4346,
|
||
|
|
"mean_token_accuracy": 0.13412694856524468,
|
||
|
|
"num_tokens": 1869073.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6248006343841555,
|
||
|
|
"epoch": 0.0787704130643612,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.3166,
|
||
|
|
"mean_token_accuracy": 0.1385165847837925,
|
||
|
|
"num_tokens": 1880439.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.801689147949219,
|
||
|
|
"epoch": 0.0792507204610951,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.499,
|
||
|
|
"mean_token_accuracy": 0.128297408670187,
|
||
|
|
"num_tokens": 1891600.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.755054044723511,
|
||
|
|
"epoch": 0.07973102785782901,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.4488,
|
||
|
|
"mean_token_accuracy": 0.1346999153494835,
|
||
|
|
"num_tokens": 1903126.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.787124109268189,
|
||
|
|
"epoch": 0.08021133525456292,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.417,
|
||
|
|
"mean_token_accuracy": 0.1378346562385559,
|
||
|
|
"num_tokens": 1913913.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.613849306106568,
|
||
|
|
"epoch": 0.08069164265129683,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.3337,
|
||
|
|
"mean_token_accuracy": 0.14059634506702423,
|
||
|
|
"num_tokens": 1924961.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.824811744689941,
|
||
|
|
"epoch": 0.08117195004803074,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.4201,
|
||
|
|
"mean_token_accuracy": 0.12982920035719872,
|
||
|
|
"num_tokens": 1936773.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.610549211502075,
|
||
|
|
"epoch": 0.08165225744476465,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.3343,
|
||
|
|
"mean_token_accuracy": 0.13738347217440605,
|
||
|
|
"num_tokens": 1948190.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6286153316497805,
|
||
|
|
"epoch": 0.08213256484149856,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.3262,
|
||
|
|
"mean_token_accuracy": 0.138392174243927,
|
||
|
|
"num_tokens": 1960038.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.762907218933106,
|
||
|
|
"epoch": 0.08261287223823247,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.4021,
|
||
|
|
"mean_token_accuracy": 0.13606049939990045,
|
||
|
|
"num_tokens": 1970535.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.655164575576782,
|
||
|
|
"epoch": 0.08309317963496637,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.3764,
|
||
|
|
"mean_token_accuracy": 0.13180122673511505,
|
||
|
|
"num_tokens": 1981386.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.615013980865479,
|
||
|
|
"epoch": 0.08357348703170028,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.2949,
|
||
|
|
"mean_token_accuracy": 0.1441991925239563,
|
||
|
|
"num_tokens": 1993196.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.65190896987915,
|
||
|
|
"epoch": 0.08405379442843419,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.3309,
|
||
|
|
"mean_token_accuracy": 0.14546860083937646,
|
||
|
|
"num_tokens": 2004756.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.595526599884034,
|
||
|
|
"epoch": 0.0845341018251681,
|
||
|
|
"grad_norm": 1.6484375,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.2971,
|
||
|
|
"mean_token_accuracy": 0.1399446427822113,
|
||
|
|
"num_tokens": 2016020.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.638343858718872,
|
||
|
|
"epoch": 0.08501440922190202,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.3364,
|
||
|
|
"mean_token_accuracy": 0.14163062497973442,
|
||
|
|
"num_tokens": 2027747.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.649935054779053,
|
||
|
|
"epoch": 0.08549471661863593,
|
||
|
|
"grad_norm": 1.7265625,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.3262,
|
||
|
|
"mean_token_accuracy": 0.13975787982344628,
|
||
|
|
"num_tokens": 2038841.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.640672445297241,
|
||
|
|
"epoch": 0.08597502401536984,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.3547,
|
||
|
|
"mean_token_accuracy": 0.13744548857212066,
|
||
|
|
"num_tokens": 2049905.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.644440841674805,
|
||
|
|
"epoch": 0.08645533141210375,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.4266,
|
||
|
|
"mean_token_accuracy": 0.13376614451408386,
|
||
|
|
"num_tokens": 2062492.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.674169445037842,
|
||
|
|
"epoch": 0.08693563880883766,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.3634,
|
||
|
|
"mean_token_accuracy": 0.13451617136597632,
|
||
|
|
"num_tokens": 2073840.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.615630722045898,
|
||
|
|
"epoch": 0.08741594620557157,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.2784,
|
||
|
|
"mean_token_accuracy": 0.13790287226438522,
|
||
|
|
"num_tokens": 2085720.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.676623725891114,
|
||
|
|
"epoch": 0.08789625360230548,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.3559,
|
||
|
|
"mean_token_accuracy": 0.14061954542994498,
|
||
|
|
"num_tokens": 2096649.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.63926134109497,
|
||
|
|
"epoch": 0.08837656099903939,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.3586,
|
||
|
|
"mean_token_accuracy": 0.1393554113805294,
|
||
|
|
"num_tokens": 2109030.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6048328399658205,
|
||
|
|
"epoch": 0.0888568683957733,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.2757,
|
||
|
|
"mean_token_accuracy": 0.142194165289402,
|
||
|
|
"num_tokens": 2121384.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563203191757202,
|
||
|
|
"epoch": 0.0893371757925072,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.2225,
|
||
|
|
"mean_token_accuracy": 0.14719335213303567,
|
||
|
|
"num_tokens": 2131377.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.577233839035034,
|
||
|
|
"epoch": 0.08981748318924111,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.4123,
|
||
|
|
"mean_token_accuracy": 0.13454320505261422,
|
||
|
|
"num_tokens": 2142364.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.619031524658203,
|
||
|
|
"epoch": 0.09029779058597502,
|
||
|
|
"grad_norm": 1.6875,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.2849,
|
||
|
|
"mean_token_accuracy": 0.13945741057395936,
|
||
|
|
"num_tokens": 2153040.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.542799091339111,
|
||
|
|
"epoch": 0.09077809798270893,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.3295,
|
||
|
|
"mean_token_accuracy": 0.14165178686380386,
|
||
|
|
"num_tokens": 2165571.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.620811080932617,
|
||
|
|
"epoch": 0.09125840537944284,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.3003,
|
||
|
|
"mean_token_accuracy": 0.13918614387512207,
|
||
|
|
"num_tokens": 2177241.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.539478206634522,
|
||
|
|
"epoch": 0.09173871277617675,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.3211,
|
||
|
|
"mean_token_accuracy": 0.135619805008173,
|
||
|
|
"num_tokens": 2187475.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6213781356811525,
|
||
|
|
"epoch": 0.09221902017291066,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.3492,
|
||
|
|
"mean_token_accuracy": 0.1400366671383381,
|
||
|
|
"num_tokens": 2198185.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5712048530578615,
|
||
|
|
"epoch": 0.09269932756964457,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.3041,
|
||
|
|
"mean_token_accuracy": 0.1407790169119835,
|
||
|
|
"num_tokens": 2210404.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.612986421585083,
|
||
|
|
"epoch": 0.09317963496637849,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.2737,
|
||
|
|
"mean_token_accuracy": 0.13978574126958848,
|
||
|
|
"num_tokens": 2222188.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.56772894859314,
|
||
|
|
"epoch": 0.0936599423631124,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.333,
|
||
|
|
"mean_token_accuracy": 0.13907585740089418,
|
||
|
|
"num_tokens": 2233418.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.512521982192993,
|
||
|
|
"epoch": 0.0941402497598463,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.2849,
|
||
|
|
"mean_token_accuracy": 0.1478159360587597,
|
||
|
|
"num_tokens": 2245053.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.605170869827271,
|
||
|
|
"epoch": 0.09462055715658022,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.3158,
|
||
|
|
"mean_token_accuracy": 0.14485108256340026,
|
||
|
|
"num_tokens": 2256375.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.405674791336059,
|
||
|
|
"epoch": 0.09510086455331412,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.1641,
|
||
|
|
"mean_token_accuracy": 0.1475372150540352,
|
||
|
|
"num_tokens": 2267074.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.520063352584839,
|
||
|
|
"epoch": 0.09558117195004803,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.1987,
|
||
|
|
"mean_token_accuracy": 0.1514969453215599,
|
||
|
|
"num_tokens": 2277168.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.435000085830689,
|
||
|
|
"epoch": 0.09606147934678194,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.1878,
|
||
|
|
"mean_token_accuracy": 0.15069199353456497,
|
||
|
|
"num_tokens": 2288178.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.503354835510254,
|
||
|
|
"epoch": 0.09654178674351585,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999999983283737,
|
||
|
|
"loss": 6.1929,
|
||
|
|
"mean_token_accuracy": 0.14548032358288765,
|
||
|
|
"num_tokens": 2299765.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.603171157836914,
|
||
|
|
"epoch": 0.09702209414024976,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004999999915373924,
|
||
|
|
"loss": 6.3207,
|
||
|
|
"mean_token_accuracy": 0.1360747143626213,
|
||
|
|
"num_tokens": 2312047.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.503301382064819,
|
||
|
|
"epoch": 0.09750240153698367,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.0004999999795225793,
|
||
|
|
"loss": 6.2995,
|
||
|
|
"mean_token_accuracy": 0.1352042004466057,
|
||
|
|
"num_tokens": 2324118.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.585948276519775,
|
||
|
|
"epoch": 0.09798270893371758,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004999999622839347,
|
||
|
|
"loss": 6.2985,
|
||
|
|
"mean_token_accuracy": 0.14105767011642456,
|
||
|
|
"num_tokens": 2335171.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.513099575042725,
|
||
|
|
"epoch": 0.09846301633045149,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004999999398214593,
|
||
|
|
"loss": 6.1997,
|
||
|
|
"mean_token_accuracy": 0.14366835802793504,
|
||
|
|
"num_tokens": 2346338.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.442260217666626,
|
||
|
|
"epoch": 0.0989433237271854,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004999999121351532,
|
||
|
|
"loss": 6.2248,
|
||
|
|
"mean_token_accuracy": 0.15347937047481536,
|
||
|
|
"num_tokens": 2357185.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.52047381401062,
|
||
|
|
"epoch": 0.0994236311239193,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999998792250173,
|
||
|
|
"loss": 6.1793,
|
||
|
|
"mean_token_accuracy": 0.15213955715298652,
|
||
|
|
"num_tokens": 2368494.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.535188245773315,
|
||
|
|
"epoch": 0.09990393852065321,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004999998410910524,
|
||
|
|
"loss": 6.3719,
|
||
|
|
"mean_token_accuracy": 0.13562044501304626,
|
||
|
|
"num_tokens": 2380800.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.575578689575195,
|
||
|
|
"epoch": 0.10038424591738712,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004999997977332592,
|
||
|
|
"loss": 6.3159,
|
||
|
|
"mean_token_accuracy": 0.14009395092725754,
|
||
|
|
"num_tokens": 2391753.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.376717662811279,
|
||
|
|
"epoch": 0.10086455331412104,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004999997491516389,
|
||
|
|
"loss": 6.1859,
|
||
|
|
"mean_token_accuracy": 0.14269104301929475,
|
||
|
|
"num_tokens": 2403324.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.512421941757202,
|
||
|
|
"epoch": 0.10134486071085495,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004999996953461925,
|
||
|
|
"loss": 6.2805,
|
||
|
|
"mean_token_accuracy": 0.1382668823003769,
|
||
|
|
"num_tokens": 2414873.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.387165594100952,
|
||
|
|
"epoch": 0.10182516810758886,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999996363169212,
|
||
|
|
"loss": 6.0851,
|
||
|
|
"mean_token_accuracy": 0.15157609730958937,
|
||
|
|
"num_tokens": 2425308.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.382681798934937,
|
||
|
|
"epoch": 0.10230547550432277,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999995720638266,
|
||
|
|
"loss": 6.1202,
|
||
|
|
"mean_token_accuracy": 0.15165834426879882,
|
||
|
|
"num_tokens": 2436835.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.456397867202758,
|
||
|
|
"epoch": 0.10278578290105668,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00049999950258691,
|
||
|
|
"loss": 6.2256,
|
||
|
|
"mean_token_accuracy": 0.14640265703201294,
|
||
|
|
"num_tokens": 2446798.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.332650756835937,
|
||
|
|
"epoch": 0.10326609029779059,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999994278861731,
|
||
|
|
"loss": 6.1221,
|
||
|
|
"mean_token_accuracy": 0.14805126786231995,
|
||
|
|
"num_tokens": 2457308.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4620646953582765,
|
||
|
|
"epoch": 0.1037463976945245,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999993479616175,
|
||
|
|
"loss": 6.1985,
|
||
|
|
"mean_token_accuracy": 0.13535723462700844,
|
||
|
|
"num_tokens": 2468917.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.465546655654907,
|
||
|
|
"epoch": 0.1042267050912584,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0004999992628132451,
|
||
|
|
"loss": 6.2148,
|
||
|
|
"mean_token_accuracy": 0.1429847039282322,
|
||
|
|
"num_tokens": 2481363.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.456140518188477,
|
||
|
|
"epoch": 0.10470701248799232,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999991724410582,
|
||
|
|
"loss": 6.2043,
|
||
|
|
"mean_token_accuracy": 0.14445993900299073,
|
||
|
|
"num_tokens": 2493082.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3651855945587155,
|
||
|
|
"epoch": 0.10518731988472622,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999990768450583,
|
||
|
|
"loss": 6.1666,
|
||
|
|
"mean_token_accuracy": 0.14558956474065782,
|
||
|
|
"num_tokens": 2503849.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.470709943771363,
|
||
|
|
"epoch": 0.10566762728146013,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004999989760252482,
|
||
|
|
"loss": 6.2132,
|
||
|
|
"mean_token_accuracy": 0.1486193262040615,
|
||
|
|
"num_tokens": 2514528.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.319680213928223,
|
||
|
|
"epoch": 0.10614793467819404,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0004999988699816299,
|
||
|
|
"loss": 6.1932,
|
||
|
|
"mean_token_accuracy": 0.1492076650261879,
|
||
|
|
"num_tokens": 2524971.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.440478706359864,
|
||
|
|
"epoch": 0.10662824207492795,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999987587142058,
|
||
|
|
"loss": 6.0986,
|
||
|
|
"mean_token_accuracy": 0.14526561200618743,
|
||
|
|
"num_tokens": 2535674.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.500247812271118,
|
||
|
|
"epoch": 0.10710854947166186,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004999986422229789,
|
||
|
|
"loss": 6.3347,
|
||
|
|
"mean_token_accuracy": 0.13726388663053513,
|
||
|
|
"num_tokens": 2547108.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.384337902069092,
|
||
|
|
"epoch": 0.10758885686839577,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999985205079514,
|
||
|
|
"loss": 6.1486,
|
||
|
|
"mean_token_accuracy": 0.14365847408771515,
|
||
|
|
"num_tokens": 2559474.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2849139213562015,
|
||
|
|
"epoch": 0.10806916426512968,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999983935691265,
|
||
|
|
"loss": 5.9875,
|
||
|
|
"mean_token_accuracy": 0.16158309876918792,
|
||
|
|
"num_tokens": 2571264.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.373571968078613,
|
||
|
|
"epoch": 0.10854947166186359,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000499998261406507,
|
||
|
|
"loss": 6.1607,
|
||
|
|
"mean_token_accuracy": 0.14907533824443817,
|
||
|
|
"num_tokens": 2583731.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.570598459243774,
|
||
|
|
"epoch": 0.10902977905859751,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999981240200958,
|
||
|
|
"loss": 6.209,
|
||
|
|
"mean_token_accuracy": 0.14517664313316345,
|
||
|
|
"num_tokens": 2595497.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.279880571365356,
|
||
|
|
"epoch": 0.10951008645533142,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999979814098966,
|
||
|
|
"loss": 6.1441,
|
||
|
|
"mean_token_accuracy": 0.14655442014336587,
|
||
|
|
"num_tokens": 2607358.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.362181329727173,
|
||
|
|
"epoch": 0.10999039385206533,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999978335759121,
|
||
|
|
"loss": 6.087,
|
||
|
|
"mean_token_accuracy": 0.15378076806664467,
|
||
|
|
"num_tokens": 2618936.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.368446207046508,
|
||
|
|
"epoch": 0.11047070124879924,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999976805181461,
|
||
|
|
"loss": 6.2243,
|
||
|
|
"mean_token_accuracy": 0.14323752224445344,
|
||
|
|
"num_tokens": 2631840.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.41338152885437,
|
||
|
|
"epoch": 0.11095100864553314,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.000499997522236602,
|
||
|
|
"loss": 6.1738,
|
||
|
|
"mean_token_accuracy": 0.1520377591252327,
|
||
|
|
"num_tokens": 2642412.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.376598930358886,
|
||
|
|
"epoch": 0.11143131604226705,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999973587312837,
|
||
|
|
"loss": 6.1544,
|
||
|
|
"mean_token_accuracy": 0.14735933318734168,
|
||
|
|
"num_tokens": 2653890.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446410703659057,
|
||
|
|
"epoch": 0.11191162343900096,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999971900021947,
|
||
|
|
"loss": 6.2058,
|
||
|
|
"mean_token_accuracy": 0.15076753124594688,
|
||
|
|
"num_tokens": 2664888.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.336441469192505,
|
||
|
|
"epoch": 0.11239193083573487,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999970160493391,
|
||
|
|
"loss": 6.1032,
|
||
|
|
"mean_token_accuracy": 0.14862595051527022,
|
||
|
|
"num_tokens": 2675550.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2902812480926515,
|
||
|
|
"epoch": 0.11287223823246878,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999968368727209,
|
||
|
|
"loss": 6.1139,
|
||
|
|
"mean_token_accuracy": 0.15255775302648544,
|
||
|
|
"num_tokens": 2688022.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3844489574432375,
|
||
|
|
"epoch": 0.11335254562920269,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004999966524723442,
|
||
|
|
"loss": 6.116,
|
||
|
|
"mean_token_accuracy": 0.1474123939871788,
|
||
|
|
"num_tokens": 2698737.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.314852046966553,
|
||
|
|
"epoch": 0.1138328530259366,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999964628482135,
|
||
|
|
"loss": 6.0924,
|
||
|
|
"mean_token_accuracy": 0.15541501641273497,
|
||
|
|
"num_tokens": 2709844.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.342870473861694,
|
||
|
|
"epoch": 0.1143131604226705,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999962680003328,
|
||
|
|
"loss": 6.1408,
|
||
|
|
"mean_token_accuracy": 0.1548864386975765,
|
||
|
|
"num_tokens": 2720273.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.401251649856567,
|
||
|
|
"epoch": 0.11479346781940442,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000499996067928707,
|
||
|
|
"loss": 6.1552,
|
||
|
|
"mean_token_accuracy": 0.15096053779125213,
|
||
|
|
"num_tokens": 2731354.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.333895015716553,
|
||
|
|
"epoch": 0.11527377521613832,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999958626333406,
|
||
|
|
"loss": 6.1386,
|
||
|
|
"mean_token_accuracy": 0.15193476974964143,
|
||
|
|
"num_tokens": 2742966.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.265989780426025,
|
||
|
|
"epoch": 0.11575408261287223,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999956521142383,
|
||
|
|
"loss": 6.0592,
|
||
|
|
"mean_token_accuracy": 0.15965109765529634,
|
||
|
|
"num_tokens": 2755010.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.39248833656311,
|
||
|
|
"epoch": 0.11623439000960614,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004999954363714051,
|
||
|
|
"loss": 6.0964,
|
||
|
|
"mean_token_accuracy": 0.14827171862125396,
|
||
|
|
"num_tokens": 2766176.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.379584693908692,
|
||
|
|
"epoch": 0.11671469740634005,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999952154048459,
|
||
|
|
"loss": 6.2296,
|
||
|
|
"mean_token_accuracy": 0.14675042033195496,
|
||
|
|
"num_tokens": 2777861.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.266990661621094,
|
||
|
|
"epoch": 0.11719500480307397,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000499994989214566,
|
||
|
|
"loss": 6.0566,
|
||
|
|
"mean_token_accuracy": 0.14940764307975768,
|
||
|
|
"num_tokens": 2788725.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2430566310882565,
|
||
|
|
"epoch": 0.11767531219980788,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999947578005705,
|
||
|
|
"loss": 6.0743,
|
||
|
|
"mean_token_accuracy": 0.15087774246931077,
|
||
|
|
"num_tokens": 2801613.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.386273336410523,
|
||
|
|
"epoch": 0.11815561959654179,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999945211628648,
|
||
|
|
"loss": 6.1488,
|
||
|
|
"mean_token_accuracy": 0.15173738598823547,
|
||
|
|
"num_tokens": 2812474.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.247502326965332,
|
||
|
|
"epoch": 0.1186359269932757,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004999942793014544,
|
||
|
|
"loss": 6.0647,
|
||
|
|
"mean_token_accuracy": 0.15294726118445395,
|
||
|
|
"num_tokens": 2823178.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.219358348846436,
|
||
|
|
"epoch": 0.11911623439000961,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000499994032216345,
|
||
|
|
"loss": 6.0531,
|
||
|
|
"mean_token_accuracy": 0.1527070477604866,
|
||
|
|
"num_tokens": 2836486.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.325845193862915,
|
||
|
|
"epoch": 0.11959654178674352,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999937799075422,
|
||
|
|
"loss": 6.1189,
|
||
|
|
"mean_token_accuracy": 0.15587549209594725,
|
||
|
|
"num_tokens": 2847902.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.120101833343506,
|
||
|
|
"epoch": 0.12007684918347743,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000499993522375052,
|
||
|
|
"loss": 5.9993,
|
||
|
|
"mean_token_accuracy": 0.15293321758508682,
|
||
|
|
"num_tokens": 2859991.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.44623122215271,
|
||
|
|
"epoch": 0.12055715658021134,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999932596188802,
|
||
|
|
"loss": 6.1907,
|
||
|
|
"mean_token_accuracy": 0.1484307639300823,
|
||
|
|
"num_tokens": 2870269.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.26564474105835,
|
||
|
|
"epoch": 0.12103746397694524,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999929916390331,
|
||
|
|
"loss": 6.0708,
|
||
|
|
"mean_token_accuracy": 0.1487228438258171,
|
||
|
|
"num_tokens": 2882191.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.222062683105468,
|
||
|
|
"epoch": 0.12151777137367915,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999927184355169,
|
||
|
|
"loss": 6.0777,
|
||
|
|
"mean_token_accuracy": 0.14720139130949975,
|
||
|
|
"num_tokens": 2892775.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.304709196090698,
|
||
|
|
"epoch": 0.12199807877041306,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999924400083377,
|
||
|
|
"loss": 6.0619,
|
||
|
|
"mean_token_accuracy": 0.15707618668675422,
|
||
|
|
"num_tokens": 2904750.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.313355350494385,
|
||
|
|
"epoch": 0.12247838616714697,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999921563575022,
|
||
|
|
"loss": 6.119,
|
||
|
|
"mean_token_accuracy": 0.14971737340092658,
|
||
|
|
"num_tokens": 2916150.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3394777297973635,
|
||
|
|
"epoch": 0.12295869356388088,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999918674830169,
|
||
|
|
"loss": 6.1047,
|
||
|
|
"mean_token_accuracy": 0.14871277660131454,
|
||
|
|
"num_tokens": 2928452.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.252659940719605,
|
||
|
|
"epoch": 0.12343900096061479,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999915733848886,
|
||
|
|
"loss": 6.0908,
|
||
|
|
"mean_token_accuracy": 0.14653694331645967,
|
||
|
|
"num_tokens": 2940577.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2738316535949705,
|
||
|
|
"epoch": 0.1239193083573487,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000499991274063124,
|
||
|
|
"loss": 6.0563,
|
||
|
|
"mean_token_accuracy": 0.15000832378864287,
|
||
|
|
"num_tokens": 2952302.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.277376508712768,
|
||
|
|
"epoch": 0.12439961575408261,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004999909695177301,
|
||
|
|
"loss": 6.1199,
|
||
|
|
"mean_token_accuracy": 0.1537736400961876,
|
||
|
|
"num_tokens": 2964611.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.316516351699829,
|
||
|
|
"epoch": 0.12487992315081652,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499990659748714,
|
||
|
|
"loss": 6.1008,
|
||
|
|
"mean_token_accuracy": 0.14772574454545975,
|
||
|
|
"num_tokens": 2975668.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.379649114608765,
|
||
|
|
"epoch": 0.12536023054755044,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999903447560828,
|
||
|
|
"loss": 6.163,
|
||
|
|
"mean_token_accuracy": 0.15174921303987504,
|
||
|
|
"num_tokens": 2987303.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3311192989349365,
|
||
|
|
"epoch": 0.12584053794428435,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999900245398439,
|
||
|
|
"loss": 6.06,
|
||
|
|
"mean_token_accuracy": 0.155066779255867,
|
||
|
|
"num_tokens": 3000400.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.25769944190979,
|
||
|
|
"epoch": 0.12632084534101826,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999896991000047,
|
||
|
|
"loss": 5.9963,
|
||
|
|
"mean_token_accuracy": 0.15082165524363517,
|
||
|
|
"num_tokens": 3012336.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3025330066680905,
|
||
|
|
"epoch": 0.12680115273775217,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004999893684365729,
|
||
|
|
"loss": 6.0618,
|
||
|
|
"mean_token_accuracy": 0.1516493648290634,
|
||
|
|
"num_tokens": 3023004.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.239853048324585,
|
||
|
|
"epoch": 0.12728146013448607,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999890325495559,
|
||
|
|
"loss": 6.1332,
|
||
|
|
"mean_token_accuracy": 0.1481592871248722,
|
||
|
|
"num_tokens": 3035147.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.269144773483276,
|
||
|
|
"epoch": 0.12776176753121998,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999886914389617,
|
||
|
|
"loss": 5.964,
|
||
|
|
"mean_token_accuracy": 0.15615130662918092,
|
||
|
|
"num_tokens": 3045611.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211176919937134,
|
||
|
|
"epoch": 0.1282420749279539,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999883451047981,
|
||
|
|
"loss": 5.9794,
|
||
|
|
"mean_token_accuracy": 0.15196620672941208,
|
||
|
|
"num_tokens": 3056420.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.195685625076294,
|
||
|
|
"epoch": 0.1287223823246878,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999879935470733,
|
||
|
|
"loss": 5.963,
|
||
|
|
"mean_token_accuracy": 0.15559092015028,
|
||
|
|
"num_tokens": 3068770.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.254584407806396,
|
||
|
|
"epoch": 0.1292026897214217,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999876367657954,
|
||
|
|
"loss": 6.0985,
|
||
|
|
"mean_token_accuracy": 0.1450921505689621,
|
||
|
|
"num_tokens": 3080806.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.348188734054565,
|
||
|
|
"epoch": 0.12968299711815562,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999872747609725,
|
||
|
|
"loss": 6.1052,
|
||
|
|
"mean_token_accuracy": 0.14815450757741927,
|
||
|
|
"num_tokens": 3091769.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.241403007507325,
|
||
|
|
"epoch": 0.13016330451488953,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004999869075326132,
|
||
|
|
"loss": 6.0277,
|
||
|
|
"mean_token_accuracy": 0.15045573711395263,
|
||
|
|
"num_tokens": 3103121.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2066021919250485,
|
||
|
|
"epoch": 0.13064361191162344,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.000499986535080726,
|
||
|
|
"loss": 6.0157,
|
||
|
|
"mean_token_accuracy": 0.15554290562868117,
|
||
|
|
"num_tokens": 3115606.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.200456380844116,
|
||
|
|
"epoch": 0.13112391930835735,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999861574053196,
|
||
|
|
"loss": 5.9027,
|
||
|
|
"mean_token_accuracy": 0.16081953197717666,
|
||
|
|
"num_tokens": 3127961.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141843366622925,
|
||
|
|
"epoch": 0.13160422670509125,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999857745064027,
|
||
|
|
"loss": 5.9219,
|
||
|
|
"mean_token_accuracy": 0.16132236272096634,
|
||
|
|
"num_tokens": 3138316.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1357402324676515,
|
||
|
|
"epoch": 0.13208453410182516,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000499985386383984,
|
||
|
|
"loss": 5.9155,
|
||
|
|
"mean_token_accuracy": 0.15786689072847365,
|
||
|
|
"num_tokens": 3150818.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.233044052124024,
|
||
|
|
"epoch": 0.13256484149855907,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999849930380729,
|
||
|
|
"loss": 6.0552,
|
||
|
|
"mean_token_accuracy": 0.1527769923210144,
|
||
|
|
"num_tokens": 3162066.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.123853874206543,
|
||
|
|
"epoch": 0.13304514889529298,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999845944686781,
|
||
|
|
"loss": 6.0345,
|
||
|
|
"mean_token_accuracy": 0.1494033455848694,
|
||
|
|
"num_tokens": 3172209.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.176547431945801,
|
||
|
|
"epoch": 0.1335254562920269,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999841906758093,
|
||
|
|
"loss": 5.8576,
|
||
|
|
"mean_token_accuracy": 0.16600174009799956,
|
||
|
|
"num_tokens": 3183248.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.142237281799316,
|
||
|
|
"epoch": 0.1340057636887608,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999837816594757,
|
||
|
|
"loss": 5.9616,
|
||
|
|
"mean_token_accuracy": 0.15896387100219728,
|
||
|
|
"num_tokens": 3194748.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1211505889892575,
|
||
|
|
"epoch": 0.1344860710854947,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999833674196865,
|
||
|
|
"loss": 5.9232,
|
||
|
|
"mean_token_accuracy": 0.16622720211744307,
|
||
|
|
"num_tokens": 3205669.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.197529077529907,
|
||
|
|
"epoch": 0.13496637848222862,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999829479564518,
|
||
|
|
"loss": 6.0093,
|
||
|
|
"mean_token_accuracy": 0.15054902583360671,
|
||
|
|
"num_tokens": 3216035.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.228098821640015,
|
||
|
|
"epoch": 0.13544668587896252,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000499982523269781,
|
||
|
|
"loss": 6.0043,
|
||
|
|
"mean_token_accuracy": 0.15448517501354217,
|
||
|
|
"num_tokens": 3227192.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.172352313995361,
|
||
|
|
"epoch": 0.13592699327569643,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999820933596842,
|
||
|
|
"loss": 6.0283,
|
||
|
|
"mean_token_accuracy": 0.1561071217060089,
|
||
|
|
"num_tokens": 3240237.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.193251514434815,
|
||
|
|
"epoch": 0.13640730067243034,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000499981658226171,
|
||
|
|
"loss": 5.9033,
|
||
|
|
"mean_token_accuracy": 0.16419047713279725,
|
||
|
|
"num_tokens": 3251963.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.135825729370117,
|
||
|
|
"epoch": 0.13688760806916425,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000499981217869252,
|
||
|
|
"loss": 6.0291,
|
||
|
|
"mean_token_accuracy": 0.16153036952018737,
|
||
|
|
"num_tokens": 3263101.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.17513861656189,
|
||
|
|
"epoch": 0.1373679154658982,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000499980772288937,
|
||
|
|
"loss": 5.9057,
|
||
|
|
"mean_token_accuracy": 0.16388555020093917,
|
||
|
|
"num_tokens": 3275100.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.167034149169922,
|
||
|
|
"epoch": 0.1378482228626321,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999803214852367,
|
||
|
|
"loss": 6.0065,
|
||
|
|
"mean_token_accuracy": 0.1535780042409897,
|
||
|
|
"num_tokens": 3287025.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.230725336074829,
|
||
|
|
"epoch": 0.138328530259366,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999798654581613,
|
||
|
|
"loss": 6.0077,
|
||
|
|
"mean_token_accuracy": 0.15366143360733986,
|
||
|
|
"num_tokens": 3299867.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1359796047210695,
|
||
|
|
"epoch": 0.13880883765609991,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999794042077214,
|
||
|
|
"loss": 5.9324,
|
||
|
|
"mean_token_accuracy": 0.15622105449438095,
|
||
|
|
"num_tokens": 3311183.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.170093536376953,
|
||
|
|
"epoch": 0.13928914505283382,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004999789377339279,
|
||
|
|
"loss": 6.0028,
|
||
|
|
"mean_token_accuracy": 0.15496657863259317,
|
||
|
|
"num_tokens": 3322247.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.195834493637085,
|
||
|
|
"epoch": 0.13976945244956773,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999784660367915,
|
||
|
|
"loss": 5.9332,
|
||
|
|
"mean_token_accuracy": 0.1554928407073021,
|
||
|
|
"num_tokens": 3333369.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.079760551452637,
|
||
|
|
"epoch": 0.14024975984630164,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999779891163231,
|
||
|
|
"loss": 5.9575,
|
||
|
|
"mean_token_accuracy": 0.15849529206752777,
|
||
|
|
"num_tokens": 3345876.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.154807806015015,
|
||
|
|
"epoch": 0.14073006724303555,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999775069725339,
|
||
|
|
"loss": 5.8498,
|
||
|
|
"mean_token_accuracy": 0.1605023294687271,
|
||
|
|
"num_tokens": 3357323.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.096273374557495,
|
||
|
|
"epoch": 0.14121037463976946,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000499977019605435,
|
||
|
|
"loss": 5.9311,
|
||
|
|
"mean_token_accuracy": 0.15962084680795668,
|
||
|
|
"num_tokens": 3367689.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006128931045533,
|
||
|
|
"epoch": 0.14169068203650337,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999765270150378,
|
||
|
|
"loss": 5.8952,
|
||
|
|
"mean_token_accuracy": 0.16288901418447493,
|
||
|
|
"num_tokens": 3379472.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.239159154891968,
|
||
|
|
"epoch": 0.14217098943323728,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999760292013536,
|
||
|
|
"loss": 5.9533,
|
||
|
|
"mean_token_accuracy": 0.15554243996739386,
|
||
|
|
"num_tokens": 3390929.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.209478282928467,
|
||
|
|
"epoch": 0.14265129682997119,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999755261643941,
|
||
|
|
"loss": 5.9401,
|
||
|
|
"mean_token_accuracy": 0.16148580312728883,
|
||
|
|
"num_tokens": 3401242.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.060628652572632,
|
||
|
|
"epoch": 0.1431316042267051,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999750179041709,
|
||
|
|
"loss": 5.9322,
|
||
|
|
"mean_token_accuracy": 0.1567712590098381,
|
||
|
|
"num_tokens": 3411169.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.067643499374389,
|
||
|
|
"epoch": 0.143611911623439,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999745044206959,
|
||
|
|
"loss": 5.7653,
|
||
|
|
"mean_token_accuracy": 0.1653980001807213,
|
||
|
|
"num_tokens": 3423265.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061836051940918,
|
||
|
|
"epoch": 0.1440922190201729,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999739857139809,
|
||
|
|
"loss": 5.8723,
|
||
|
|
"mean_token_accuracy": 0.1658122293651104,
|
||
|
|
"num_tokens": 3434793.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.013027095794678,
|
||
|
|
"epoch": 0.14457252641690682,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000499973461784038,
|
||
|
|
"loss": 5.8078,
|
||
|
|
"mean_token_accuracy": 0.17317451983690263,
|
||
|
|
"num_tokens": 3445732.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.127257823944092,
|
||
|
|
"epoch": 0.14505283381364073,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999729326308792,
|
||
|
|
"loss": 5.9813,
|
||
|
|
"mean_token_accuracy": 0.15522808730602264,
|
||
|
|
"num_tokens": 3457090.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.194346618652344,
|
||
|
|
"epoch": 0.14553314121037464,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000499972398254517,
|
||
|
|
"loss": 5.9726,
|
||
|
|
"mean_token_accuracy": 0.15402631014585494,
|
||
|
|
"num_tokens": 3468087.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.157139253616333,
|
||
|
|
"epoch": 0.14601344860710855,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000499971858654964,
|
||
|
|
"loss": 5.9108,
|
||
|
|
"mean_token_accuracy": 0.15916238874197006,
|
||
|
|
"num_tokens": 3478820.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0432126998901365,
|
||
|
|
"epoch": 0.14649375600384246,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999713138322321,
|
||
|
|
"loss": 5.9387,
|
||
|
|
"mean_token_accuracy": 0.15639192685484887,
|
||
|
|
"num_tokens": 3489878.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.179038763046265,
|
||
|
|
"epoch": 0.14697406340057637,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999707637863346,
|
||
|
|
"loss": 5.9227,
|
||
|
|
"mean_token_accuracy": 0.15898001939058304,
|
||
|
|
"num_tokens": 3500944.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006661891937256,
|
||
|
|
"epoch": 0.14745437079731027,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999702085172838,
|
||
|
|
"loss": 5.8949,
|
||
|
|
"mean_token_accuracy": 0.166755573451519,
|
||
|
|
"num_tokens": 3511383.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.193773031234741,
|
||
|
|
"epoch": 0.14793467819404418,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999696480250929,
|
||
|
|
"loss": 6.0009,
|
||
|
|
"mean_token_accuracy": 0.1563890740275383,
|
||
|
|
"num_tokens": 3523300.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.137639045715332,
|
||
|
|
"epoch": 0.1484149855907781,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004999690823097747,
|
||
|
|
"loss": 5.904,
|
||
|
|
"mean_token_accuracy": 0.15553956106305122,
|
||
|
|
"num_tokens": 3534371.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.11188440322876,
|
||
|
|
"epoch": 0.148895292987512,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999685113713426,
|
||
|
|
"loss": 5.8848,
|
||
|
|
"mean_token_accuracy": 0.1581243097782135,
|
||
|
|
"num_tokens": 3544847.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.084521484375,
|
||
|
|
"epoch": 0.1493756003842459,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999679352098096,
|
||
|
|
"loss": 5.8683,
|
||
|
|
"mean_token_accuracy": 0.1633513331413269,
|
||
|
|
"num_tokens": 3555859.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.081562280654907,
|
||
|
|
"epoch": 0.14985590778097982,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999673538251891,
|
||
|
|
"loss": 5.8724,
|
||
|
|
"mean_token_accuracy": 0.16277971267700195,
|
||
|
|
"num_tokens": 3568283.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.040332508087158,
|
||
|
|
"epoch": 0.15033621517771373,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999667672174947,
|
||
|
|
"loss": 5.9535,
|
||
|
|
"mean_token_accuracy": 0.15841858685016633,
|
||
|
|
"num_tokens": 3581442.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.214689922332764,
|
||
|
|
"epoch": 0.15081652257444764,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00049996617538674,
|
||
|
|
"loss": 5.999,
|
||
|
|
"mean_token_accuracy": 0.15400405079126359,
|
||
|
|
"num_tokens": 3594055.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.139510774612427,
|
||
|
|
"epoch": 0.15129682997118155,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999655783329386,
|
||
|
|
"loss": 5.9564,
|
||
|
|
"mean_token_accuracy": 0.1526302471756935,
|
||
|
|
"num_tokens": 3605952.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.104340982437134,
|
||
|
|
"epoch": 0.15177713736791545,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999649760561046,
|
||
|
|
"loss": 5.9762,
|
||
|
|
"mean_token_accuracy": 0.15697605460882186,
|
||
|
|
"num_tokens": 3618544.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.139195299148559,
|
||
|
|
"epoch": 0.15225744476464936,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999643685562519,
|
||
|
|
"loss": 5.928,
|
||
|
|
"mean_token_accuracy": 0.16384828090667725,
|
||
|
|
"num_tokens": 3630445.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.140196180343628,
|
||
|
|
"epoch": 0.15273775216138327,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999637558333945,
|
||
|
|
"loss": 5.9277,
|
||
|
|
"mean_token_accuracy": 0.162806536257267,
|
||
|
|
"num_tokens": 3642516.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.032298421859741,
|
||
|
|
"epoch": 0.15321805955811718,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999631378875467,
|
||
|
|
"loss": 5.8473,
|
||
|
|
"mean_token_accuracy": 0.1700352057814598,
|
||
|
|
"num_tokens": 3654425.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.052908039093017,
|
||
|
|
"epoch": 0.15369836695485112,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999625147187228,
|
||
|
|
"loss": 5.8659,
|
||
|
|
"mean_token_accuracy": 0.1607646018266678,
|
||
|
|
"num_tokens": 3666521.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.144074392318726,
|
||
|
|
"epoch": 0.15417867435158503,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999618863269373,
|
||
|
|
"loss": 5.9113,
|
||
|
|
"mean_token_accuracy": 0.15713147521018983,
|
||
|
|
"num_tokens": 3679121.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.08037257194519,
|
||
|
|
"epoch": 0.15465898174831894,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999612527122049,
|
||
|
|
"loss": 5.9215,
|
||
|
|
"mean_token_accuracy": 0.15551023483276366,
|
||
|
|
"num_tokens": 3691095.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048700380325317,
|
||
|
|
"epoch": 0.15513928914505284,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004999606138745402,
|
||
|
|
"loss": 5.8863,
|
||
|
|
"mean_token_accuracy": 0.16148294806480407,
|
||
|
|
"num_tokens": 3703426.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.160890388488769,
|
||
|
|
"epoch": 0.15561959654178675,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999599698139581,
|
||
|
|
"loss": 5.9506,
|
||
|
|
"mean_token_accuracy": 0.16333511769771575,
|
||
|
|
"num_tokens": 3715429.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.134197616577149,
|
||
|
|
"epoch": 0.15609990393852066,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999593205304734,
|
||
|
|
"loss": 5.9302,
|
||
|
|
"mean_token_accuracy": 0.1580351047217846,
|
||
|
|
"num_tokens": 3726327.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.134684467315674,
|
||
|
|
"epoch": 0.15658021133525457,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999586660241012,
|
||
|
|
"loss": 5.9004,
|
||
|
|
"mean_token_accuracy": 0.15458485931158067,
|
||
|
|
"num_tokens": 3736818.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.102252435684204,
|
||
|
|
"epoch": 0.15706051873198848,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999580062948569,
|
||
|
|
"loss": 5.9023,
|
||
|
|
"mean_token_accuracy": 0.16163242906332015,
|
||
|
|
"num_tokens": 3747776.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.938621568679809,
|
||
|
|
"epoch": 0.1575408261287224,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999573413427556,
|
||
|
|
"loss": 5.7522,
|
||
|
|
"mean_token_accuracy": 0.16386649161577224,
|
||
|
|
"num_tokens": 3758990.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073081064224243,
|
||
|
|
"epoch": 0.1580211335254563,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999566711678128,
|
||
|
|
"loss": 5.8335,
|
||
|
|
"mean_token_accuracy": 0.1618332728743553,
|
||
|
|
"num_tokens": 3769686.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.034470748901367,
|
||
|
|
"epoch": 0.1585014409221902,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999559957700442,
|
||
|
|
"loss": 5.8842,
|
||
|
|
"mean_token_accuracy": 0.16474503725767137,
|
||
|
|
"num_tokens": 3781815.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.107155132293701,
|
||
|
|
"epoch": 0.15898174831892412,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999553151494653,
|
||
|
|
"loss": 5.9224,
|
||
|
|
"mean_token_accuracy": 0.16111959964036943,
|
||
|
|
"num_tokens": 3793392.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.020937395095825,
|
||
|
|
"epoch": 0.15946205571565802,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999546293060919,
|
||
|
|
"loss": 5.8622,
|
||
|
|
"mean_token_accuracy": 0.15857846289873123,
|
||
|
|
"num_tokens": 3804974.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.980496025085449,
|
||
|
|
"epoch": 0.15994236311239193,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00049995393823994,
|
||
|
|
"loss": 5.7399,
|
||
|
|
"mean_token_accuracy": 0.1712213933467865,
|
||
|
|
"num_tokens": 3817166.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985702800750732,
|
||
|
|
"epoch": 0.16042267050912584,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999532419510255,
|
||
|
|
"loss": 5.8584,
|
||
|
|
"mean_token_accuracy": 0.16114549189805985,
|
||
|
|
"num_tokens": 3828151.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.079834032058716,
|
||
|
|
"epoch": 0.16090297790585975,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499952540439365,
|
||
|
|
"loss": 5.8566,
|
||
|
|
"mean_token_accuracy": 0.16157617270946503,
|
||
|
|
"num_tokens": 3839439.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.109479236602783,
|
||
|
|
"epoch": 0.16138328530259366,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999518337049743,
|
||
|
|
"loss": 5.9183,
|
||
|
|
"mean_token_accuracy": 0.15559976994991304,
|
||
|
|
"num_tokens": 3851694.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.999596118927002,
|
||
|
|
"epoch": 0.16186359269932757,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00049995112174787,
|
||
|
|
"loss": 5.8943,
|
||
|
|
"mean_token_accuracy": 0.15952107906341553,
|
||
|
|
"num_tokens": 3863593.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.972264003753662,
|
||
|
|
"epoch": 0.16234390009606148,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999504045680687,
|
||
|
|
"loss": 5.8039,
|
||
|
|
"mean_token_accuracy": 0.16952102333307267,
|
||
|
|
"num_tokens": 3874588.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094362878799439,
|
||
|
|
"epoch": 0.1628242074927954,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999496821655869,
|
||
|
|
"loss": 5.8981,
|
||
|
|
"mean_token_accuracy": 0.15856973826885223,
|
||
|
|
"num_tokens": 3884662.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.140773725509644,
|
||
|
|
"epoch": 0.1633045148895293,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999489545404414,
|
||
|
|
"loss": 5.9891,
|
||
|
|
"mean_token_accuracy": 0.15623455494642258,
|
||
|
|
"num_tokens": 3896569.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.140805101394653,
|
||
|
|
"epoch": 0.1637848222862632,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999482216926493,
|
||
|
|
"loss": 5.8462,
|
||
|
|
"mean_token_accuracy": 0.16176871806383133,
|
||
|
|
"num_tokens": 3907691.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.034537076950073,
|
||
|
|
"epoch": 0.1642651296829971,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999474836222273,
|
||
|
|
"loss": 5.8498,
|
||
|
|
"mean_token_accuracy": 0.16770250350236893,
|
||
|
|
"num_tokens": 3918794.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.016002893447876,
|
||
|
|
"epoch": 0.16474543707973102,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999467403291928,
|
||
|
|
"loss": 5.8424,
|
||
|
|
"mean_token_accuracy": 0.17401330322027206,
|
||
|
|
"num_tokens": 3929773.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039723968505859,
|
||
|
|
"epoch": 0.16522574447646493,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999459918135628,
|
||
|
|
"loss": 5.8626,
|
||
|
|
"mean_token_accuracy": 0.16028911992907524,
|
||
|
|
"num_tokens": 3940264.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.988501930236817,
|
||
|
|
"epoch": 0.16570605187319884,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000499945238075355,
|
||
|
|
"loss": 5.7585,
|
||
|
|
"mean_token_accuracy": 0.16902887523174287,
|
||
|
|
"num_tokens": 3951500.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.034324693679809,
|
||
|
|
"epoch": 0.16618635926993275,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999444791145865,
|
||
|
|
"loss": 5.8427,
|
||
|
|
"mean_token_accuracy": 0.16535028964281082,
|
||
|
|
"num_tokens": 3963580.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986796712875366,
|
||
|
|
"epoch": 0.16666666666666666,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999437149312754,
|
||
|
|
"loss": 5.7757,
|
||
|
|
"mean_token_accuracy": 0.17422386556863784,
|
||
|
|
"num_tokens": 3975994.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9908356189727785,
|
||
|
|
"epoch": 0.16714697406340057,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000499942945525439,
|
||
|
|
"loss": 5.7922,
|
||
|
|
"mean_token_accuracy": 0.1610643297433853,
|
||
|
|
"num_tokens": 3987897.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048891305923462,
|
||
|
|
"epoch": 0.16762728146013448,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999421708970954,
|
||
|
|
"loss": 5.9403,
|
||
|
|
"mean_token_accuracy": 0.1578907661139965,
|
||
|
|
"num_tokens": 3999829.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001609849929809,
|
||
|
|
"epoch": 0.16810758885686838,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999413910462625,
|
||
|
|
"loss": 5.7895,
|
||
|
|
"mean_token_accuracy": 0.16723742038011552,
|
||
|
|
"num_tokens": 4010882.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978082466125488,
|
||
|
|
"epoch": 0.1685878962536023,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999406059729586,
|
||
|
|
"loss": 5.7717,
|
||
|
|
"mean_token_accuracy": 0.16948328018188477,
|
||
|
|
"num_tokens": 4021423.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093415307998657,
|
||
|
|
"epoch": 0.1690682036503362,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999398156772016,
|
||
|
|
"loss": 5.9183,
|
||
|
|
"mean_token_accuracy": 0.15228435546159744,
|
||
|
|
"num_tokens": 4033590.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.927422332763672,
|
||
|
|
"epoch": 0.16954851104707014,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00049993902015901,
|
||
|
|
"loss": 5.7775,
|
||
|
|
"mean_token_accuracy": 0.16497890055179595,
|
||
|
|
"num_tokens": 4043978.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.080128145217896,
|
||
|
|
"epoch": 0.17002881844380405,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999382194184023,
|
||
|
|
"loss": 5.9011,
|
||
|
|
"mean_token_accuracy": 0.16162478625774385,
|
||
|
|
"num_tokens": 4054513.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0692665576934814,
|
||
|
|
"epoch": 0.17050912584053796,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999374134553972,
|
||
|
|
"loss": 5.8467,
|
||
|
|
"mean_token_accuracy": 0.16818321645259857,
|
||
|
|
"num_tokens": 4066019.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.963143253326416,
|
||
|
|
"epoch": 0.17098943323727187,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999366022700131,
|
||
|
|
"loss": 5.8214,
|
||
|
|
"mean_token_accuracy": 0.16922373026609422,
|
||
|
|
"num_tokens": 4077688.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.082214260101319,
|
||
|
|
"epoch": 0.17146974063400577,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999357858622691,
|
||
|
|
"loss": 5.8939,
|
||
|
|
"mean_token_accuracy": 0.1704793967306614,
|
||
|
|
"num_tokens": 4089803.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019527435302734,
|
||
|
|
"epoch": 0.17195004803073968,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999349642321842,
|
||
|
|
"loss": 5.8323,
|
||
|
|
"mean_token_accuracy": 0.16811123341321946,
|
||
|
|
"num_tokens": 4101969.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995560216903686,
|
||
|
|
"epoch": 0.1724303554274736,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999341373797772,
|
||
|
|
"loss": 5.8181,
|
||
|
|
"mean_token_accuracy": 0.16215983778238297,
|
||
|
|
"num_tokens": 4113567.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.987828254699707,
|
||
|
|
"epoch": 0.1729106628242075,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999333053050675,
|
||
|
|
"loss": 5.7861,
|
||
|
|
"mean_token_accuracy": 0.1671761840581894,
|
||
|
|
"num_tokens": 4125191.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.054584407806397,
|
||
|
|
"epoch": 0.1733909702209414,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004999324680080744,
|
||
|
|
"loss": 5.8297,
|
||
|
|
"mean_token_accuracy": 0.167048180103302,
|
||
|
|
"num_tokens": 4135050.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.962006425857544,
|
||
|
|
"epoch": 0.17387127761767532,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999316254888172,
|
||
|
|
"loss": 5.8864,
|
||
|
|
"mean_token_accuracy": 0.16525756269693376,
|
||
|
|
"num_tokens": 4146874.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.027948713302612,
|
||
|
|
"epoch": 0.17435158501440923,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999307777473157,
|
||
|
|
"loss": 5.8119,
|
||
|
|
"mean_token_accuracy": 0.16480804234743118,
|
||
|
|
"num_tokens": 4158118.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.980266284942627,
|
||
|
|
"epoch": 0.17483189241114314,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004999299247835893,
|
||
|
|
"loss": 5.7898,
|
||
|
|
"mean_token_accuracy": 0.17785038501024247,
|
||
|
|
"num_tokens": 4169035.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911714839935303,
|
||
|
|
"epoch": 0.17531219980787704,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499929066597658,
|
||
|
|
"loss": 5.767,
|
||
|
|
"mean_token_accuracy": 0.17150768488645554,
|
||
|
|
"num_tokens": 4180314.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.06360354423523,
|
||
|
|
"epoch": 0.17579250720461095,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999282031895418,
|
||
|
|
"loss": 5.8574,
|
||
|
|
"mean_token_accuracy": 0.1665028989315033,
|
||
|
|
"num_tokens": 4192238.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.918634033203125,
|
||
|
|
"epoch": 0.17627281460134486,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999273345592604,
|
||
|
|
"loss": 5.7864,
|
||
|
|
"mean_token_accuracy": 0.16353099048137665,
|
||
|
|
"num_tokens": 4203346.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.99358344078064,
|
||
|
|
"epoch": 0.17675312199807877,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999264607068343,
|
||
|
|
"loss": 5.8248,
|
||
|
|
"mean_token_accuracy": 0.16922380030155182,
|
||
|
|
"num_tokens": 4213763.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.949887943267822,
|
||
|
|
"epoch": 0.17723342939481268,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999255816322837,
|
||
|
|
"loss": 5.7987,
|
||
|
|
"mean_token_accuracy": 0.1714692607522011,
|
||
|
|
"num_tokens": 4225553.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.06374306678772,
|
||
|
|
"epoch": 0.1777137367915466,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499924697335629,
|
||
|
|
"loss": 5.7171,
|
||
|
|
"mean_token_accuracy": 0.17483123242855073,
|
||
|
|
"num_tokens": 4236058.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.883856916427613,
|
||
|
|
"epoch": 0.1781940441882805,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999238078168906,
|
||
|
|
"loss": 5.7983,
|
||
|
|
"mean_token_accuracy": 0.17132625132799148,
|
||
|
|
"num_tokens": 4248299.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.987727499008178,
|
||
|
|
"epoch": 0.1786743515850144,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004999229130760894,
|
||
|
|
"loss": 5.7295,
|
||
|
|
"mean_token_accuracy": 0.16837194561958313,
|
||
|
|
"num_tokens": 4259704.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.883204078674316,
|
||
|
|
"epoch": 0.17915465898174832,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000499922013113246,
|
||
|
|
"loss": 5.6159,
|
||
|
|
"mean_token_accuracy": 0.183360692858696,
|
||
|
|
"num_tokens": 4270480.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.932878494262695,
|
||
|
|
"epoch": 0.17963496637848222,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999211079283814,
|
||
|
|
"loss": 5.8661,
|
||
|
|
"mean_token_accuracy": 0.16950789242982864,
|
||
|
|
"num_tokens": 4282104.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039040184020996,
|
||
|
|
"epoch": 0.18011527377521613,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999201975215164,
|
||
|
|
"loss": 5.8454,
|
||
|
|
"mean_token_accuracy": 0.16162874400615693,
|
||
|
|
"num_tokens": 4294251.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.932565784454345,
|
||
|
|
"epoch": 0.18059558117195004,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999192818926725,
|
||
|
|
"loss": 5.7256,
|
||
|
|
"mean_token_accuracy": 0.16642534136772155,
|
||
|
|
"num_tokens": 4305569.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.010633945465088,
|
||
|
|
"epoch": 0.18107588856868395,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999183610418706,
|
||
|
|
"loss": 5.856,
|
||
|
|
"mean_token_accuracy": 0.16204970329999924,
|
||
|
|
"num_tokens": 4317845.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.937364482879639,
|
||
|
|
"epoch": 0.18155619596541786,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004999174349691322,
|
||
|
|
"loss": 5.7241,
|
||
|
|
"mean_token_accuracy": 0.16895480155944825,
|
||
|
|
"num_tokens": 4329987.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916909265518188,
|
||
|
|
"epoch": 0.18203650336215177,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004999165036744788,
|
||
|
|
"loss": 5.7336,
|
||
|
|
"mean_token_accuracy": 0.16701279431581498,
|
||
|
|
"num_tokens": 4341628.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.97577314376831,
|
||
|
|
"epoch": 0.18251681075888568,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999155671579322,
|
||
|
|
"loss": 5.8141,
|
||
|
|
"mean_token_accuracy": 0.16247764229774475,
|
||
|
|
"num_tokens": 4352379.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.888210439682007,
|
||
|
|
"epoch": 0.1829971181556196,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499914625419514,
|
||
|
|
"loss": 5.7384,
|
||
|
|
"mean_token_accuracy": 0.17271625846624375,
|
||
|
|
"num_tokens": 4364800.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.934367513656616,
|
||
|
|
"epoch": 0.1834774255523535,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999136784592459,
|
||
|
|
"loss": 5.7544,
|
||
|
|
"mean_token_accuracy": 0.16907702684402465,
|
||
|
|
"num_tokens": 4376048.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916653251647949,
|
||
|
|
"epoch": 0.1839577329490874,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999127262771502,
|
||
|
|
"loss": 5.7474,
|
||
|
|
"mean_token_accuracy": 0.16713621020317077,
|
||
|
|
"num_tokens": 4388072.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049605655670166,
|
||
|
|
"epoch": 0.1844380403458213,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999117688732487,
|
||
|
|
"loss": 5.8408,
|
||
|
|
"mean_token_accuracy": 0.16282255798578263,
|
||
|
|
"num_tokens": 4399843.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.854936361312866,
|
||
|
|
"epoch": 0.18491834774255522,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999108062475638,
|
||
|
|
"loss": 5.692,
|
||
|
|
"mean_token_accuracy": 0.17128440588712693,
|
||
|
|
"num_tokens": 4411373.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.888366031646728,
|
||
|
|
"epoch": 0.18539865513928913,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000499909838400118,
|
||
|
|
"loss": 5.6829,
|
||
|
|
"mean_token_accuracy": 0.1735598623752594,
|
||
|
|
"num_tokens": 4421857.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947378730773925,
|
||
|
|
"epoch": 0.18587896253602307,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999088653309334,
|
||
|
|
"loss": 5.7819,
|
||
|
|
"mean_token_accuracy": 0.1680931806564331,
|
||
|
|
"num_tokens": 4432728.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.886118745803833,
|
||
|
|
"epoch": 0.18635926993275698,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999078870400329,
|
||
|
|
"loss": 5.714,
|
||
|
|
"mean_token_accuracy": 0.1756661355495453,
|
||
|
|
"num_tokens": 4444683.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994152688980103,
|
||
|
|
"epoch": 0.18683957732949089,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999069035274391,
|
||
|
|
"loss": 5.8381,
|
||
|
|
"mean_token_accuracy": 0.16196750849485397,
|
||
|
|
"num_tokens": 4456961.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.912719821929931,
|
||
|
|
"epoch": 0.1873198847262248,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004999059147931747,
|
||
|
|
"loss": 5.6738,
|
||
|
|
"mean_token_accuracy": 0.17798083573579787,
|
||
|
|
"num_tokens": 4468424.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.929690361022949,
|
||
|
|
"epoch": 0.1878001921229587,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999049208372629,
|
||
|
|
"loss": 5.8701,
|
||
|
|
"mean_token_accuracy": 0.15679999366402625,
|
||
|
|
"num_tokens": 4479813.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.098432826995849,
|
||
|
|
"epoch": 0.1882804995196926,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999039216597267,
|
||
|
|
"loss": 5.8826,
|
||
|
|
"mean_token_accuracy": 0.16513065099716187,
|
||
|
|
"num_tokens": 4491172.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.891456174850464,
|
||
|
|
"epoch": 0.18876080691642652,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999029172605892,
|
||
|
|
"loss": 5.7655,
|
||
|
|
"mean_token_accuracy": 0.17174434214830397,
|
||
|
|
"num_tokens": 4503063.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019789409637451,
|
||
|
|
"epoch": 0.18924111431316043,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004999019076398738,
|
||
|
|
"loss": 5.8443,
|
||
|
|
"mean_token_accuracy": 0.15457844734191895,
|
||
|
|
"num_tokens": 4514188.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.98090615272522,
|
||
|
|
"epoch": 0.18972142170989434,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000499900892797604,
|
||
|
|
"loss": 5.7495,
|
||
|
|
"mean_token_accuracy": 0.17291804850101472,
|
||
|
|
"num_tokens": 4525293.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9353631973266605,
|
||
|
|
"epoch": 0.19020172910662825,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998998727338031,
|
||
|
|
"loss": 5.8315,
|
||
|
|
"mean_token_accuracy": 0.16792338639497756,
|
||
|
|
"num_tokens": 4536589.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.87034125328064,
|
||
|
|
"epoch": 0.19068203650336216,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004998988474484952,
|
||
|
|
"loss": 5.5689,
|
||
|
|
"mean_token_accuracy": 0.19097184985876084,
|
||
|
|
"num_tokens": 4547594.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.888665723800659,
|
||
|
|
"epoch": 0.19116234390009607,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004998978169417038,
|
||
|
|
"loss": 5.7814,
|
||
|
|
"mean_token_accuracy": 0.173173625767231,
|
||
|
|
"num_tokens": 4559850.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.935269927978515,
|
||
|
|
"epoch": 0.19164265129682997,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998967812134529,
|
||
|
|
"loss": 5.7343,
|
||
|
|
"mean_token_accuracy": 0.16940659731626512,
|
||
|
|
"num_tokens": 4570727.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.766289901733399,
|
||
|
|
"epoch": 0.19212295869356388,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998957402637664,
|
||
|
|
"loss": 5.6639,
|
||
|
|
"mean_token_accuracy": 0.17158041000366211,
|
||
|
|
"num_tokens": 4582248.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.963186931610108,
|
||
|
|
"epoch": 0.1926032660902978,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998946940926687,
|
||
|
|
"loss": 5.7005,
|
||
|
|
"mean_token_accuracy": 0.16607439517974854,
|
||
|
|
"num_tokens": 4592604.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.888526773452758,
|
||
|
|
"epoch": 0.1930835734870317,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000499893642700184,
|
||
|
|
"loss": 5.7435,
|
||
|
|
"mean_token_accuracy": 0.1702524498105049,
|
||
|
|
"num_tokens": 4604398.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.91964282989502,
|
||
|
|
"epoch": 0.1935638808837656,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004998925860863368,
|
||
|
|
"loss": 5.8039,
|
||
|
|
"mean_token_accuracy": 0.16930960565805436,
|
||
|
|
"num_tokens": 4616434.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.981127023696899,
|
||
|
|
"epoch": 0.19404418828049952,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004998915242511516,
|
||
|
|
"loss": 5.7597,
|
||
|
|
"mean_token_accuracy": 0.17877342998981477,
|
||
|
|
"num_tokens": 4627577.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.960260248184204,
|
||
|
|
"epoch": 0.19452449567723343,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998904571946528,
|
||
|
|
"loss": 5.8227,
|
||
|
|
"mean_token_accuracy": 0.16877581179141998,
|
||
|
|
"num_tokens": 4639698.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.018915462493896,
|
||
|
|
"epoch": 0.19500480307396734,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004998893849168655,
|
||
|
|
"loss": 5.8322,
|
||
|
|
"mean_token_accuracy": 0.16535419821739197,
|
||
|
|
"num_tokens": 4650643.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.94498839378357,
|
||
|
|
"epoch": 0.19548511047070125,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004998883074178144,
|
||
|
|
"loss": 5.7511,
|
||
|
|
"mean_token_accuracy": 0.17331523150205613,
|
||
|
|
"num_tokens": 4662897.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.939677953720093,
|
||
|
|
"epoch": 0.19596541786743515,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998872246975247,
|
||
|
|
"loss": 5.8446,
|
||
|
|
"mean_token_accuracy": 0.1710888773202896,
|
||
|
|
"num_tokens": 4673701.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.051514387130737,
|
||
|
|
"epoch": 0.19644572526416906,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998861367560213,
|
||
|
|
"loss": 5.7976,
|
||
|
|
"mean_token_accuracy": 0.17028483599424363,
|
||
|
|
"num_tokens": 4685873.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.855360126495361,
|
||
|
|
"epoch": 0.19692603266090297,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004998850435933296,
|
||
|
|
"loss": 5.6799,
|
||
|
|
"mean_token_accuracy": 0.171894171833992,
|
||
|
|
"num_tokens": 4697179.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.93500165939331,
|
||
|
|
"epoch": 0.19740634005763688,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998839452094749,
|
||
|
|
"loss": 5.7239,
|
||
|
|
"mean_token_accuracy": 0.17378782033920287,
|
||
|
|
"num_tokens": 4707752.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.785550880432129,
|
||
|
|
"epoch": 0.1978866474543708,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998828416044829,
|
||
|
|
"loss": 5.5828,
|
||
|
|
"mean_token_accuracy": 0.17932410091161727,
|
||
|
|
"num_tokens": 4718413.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.901092576980591,
|
||
|
|
"epoch": 0.1983669548511047,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000499881732778379,
|
||
|
|
"loss": 5.7755,
|
||
|
|
"mean_token_accuracy": 0.167689011991024,
|
||
|
|
"num_tokens": 4730033.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.849337959289551,
|
||
|
|
"epoch": 0.1988472622478386,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.000499880618731189,
|
||
|
|
"loss": 5.632,
|
||
|
|
"mean_token_accuracy": 0.17377811521291733,
|
||
|
|
"num_tokens": 4742084.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.942147588729858,
|
||
|
|
"epoch": 0.19932756964457252,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004998794994629388,
|
||
|
|
"loss": 5.8568,
|
||
|
|
"mean_token_accuracy": 0.16341482400894164,
|
||
|
|
"num_tokens": 4753885.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.894834518432617,
|
||
|
|
"epoch": 0.19980787704130643,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998783749736545,
|
||
|
|
"loss": 5.7098,
|
||
|
|
"mean_token_accuracy": 0.1734362706542015,
|
||
|
|
"num_tokens": 4765686.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.933993625640869,
|
||
|
|
"epoch": 0.20028818443804033,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004998772452633619,
|
||
|
|
"loss": 5.7384,
|
||
|
|
"mean_token_accuracy": 0.16806679219007492,
|
||
|
|
"num_tokens": 4777157.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.881355714797974,
|
||
|
|
"epoch": 0.20076849183477424,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998761103320876,
|
||
|
|
"loss": 5.6823,
|
||
|
|
"mean_token_accuracy": 0.1787089616060257,
|
||
|
|
"num_tokens": 4788583.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965854835510254,
|
||
|
|
"epoch": 0.20124879923150815,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004998749701798577,
|
||
|
|
"loss": 5.7908,
|
||
|
|
"mean_token_accuracy": 0.1650993473827839,
|
||
|
|
"num_tokens": 4800749.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.834138011932373,
|
||
|
|
"epoch": 0.2017291066282421,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004998738248066986,
|
||
|
|
"loss": 5.7169,
|
||
|
|
"mean_token_accuracy": 0.17363064736127853,
|
||
|
|
"num_tokens": 4812488.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952000665664673,
|
||
|
|
"epoch": 0.202209414024976,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998726742126372,
|
||
|
|
"loss": 5.6942,
|
||
|
|
"mean_token_accuracy": 0.16981008946895598,
|
||
|
|
"num_tokens": 4823495.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.821967363357544,
|
||
|
|
"epoch": 0.2026897214217099,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004998715183976999,
|
||
|
|
"loss": 5.7474,
|
||
|
|
"mean_token_accuracy": 0.17119863927364348,
|
||
|
|
"num_tokens": 4834450.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.896064186096192,
|
||
|
|
"epoch": 0.20317002881844382,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004998703573619137,
|
||
|
|
"loss": 5.653,
|
||
|
|
"mean_token_accuracy": 0.18205936402082443,
|
||
|
|
"num_tokens": 4846826.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.961601400375367,
|
||
|
|
"epoch": 0.20365033621517772,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004998691911053056,
|
||
|
|
"loss": 5.8431,
|
||
|
|
"mean_token_accuracy": 0.16039666682481765,
|
||
|
|
"num_tokens": 4859668.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8840587615966795,
|
||
|
|
"epoch": 0.20413064361191163,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998680196279026,
|
||
|
|
"loss": 5.7134,
|
||
|
|
"mean_token_accuracy": 0.17416077703237534,
|
||
|
|
"num_tokens": 4871727.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.968330240249633,
|
||
|
|
"epoch": 0.20461095100864554,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004998668429297319,
|
||
|
|
"loss": 5.78,
|
||
|
|
"mean_token_accuracy": 0.1742082878947258,
|
||
|
|
"num_tokens": 4882191.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897537279129028,
|
||
|
|
"epoch": 0.20509125840537945,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998656610108208,
|
||
|
|
"loss": 5.7018,
|
||
|
|
"mean_token_accuracy": 0.1743673115968704,
|
||
|
|
"num_tokens": 4892416.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.846418809890747,
|
||
|
|
"epoch": 0.20557156580211336,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998644738711969,
|
||
|
|
"loss": 5.6797,
|
||
|
|
"mean_token_accuracy": 0.1706405311822891,
|
||
|
|
"num_tokens": 4903572.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.968627214431763,
|
||
|
|
"epoch": 0.20605187319884727,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004998632815108874,
|
||
|
|
"loss": 5.7787,
|
||
|
|
"mean_token_accuracy": 0.16432214826345443,
|
||
|
|
"num_tokens": 4915417.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.875264406204224,
|
||
|
|
"epoch": 0.20653218059558118,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004998620839299203,
|
||
|
|
"loss": 5.6596,
|
||
|
|
"mean_token_accuracy": 0.17557333707809447,
|
||
|
|
"num_tokens": 4926943.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.82595853805542,
|
||
|
|
"epoch": 0.2070124879923151,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004998608811283233,
|
||
|
|
"loss": 5.6216,
|
||
|
|
"mean_token_accuracy": 0.1786582961678505,
|
||
|
|
"num_tokens": 4937724.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967111301422119,
|
||
|
|
"epoch": 0.207492795389049,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004998596731061244,
|
||
|
|
"loss": 5.7773,
|
||
|
|
"mean_token_accuracy": 0.16382010281085968,
|
||
|
|
"num_tokens": 4949970.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.899398708343506,
|
||
|
|
"epoch": 0.2079731027857829,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998584598633516,
|
||
|
|
"loss": 5.7756,
|
||
|
|
"mean_token_accuracy": 0.1687404468655586,
|
||
|
|
"num_tokens": 4961389.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956924343109131,
|
||
|
|
"epoch": 0.2084534101825168,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998572414000329,
|
||
|
|
"loss": 5.8212,
|
||
|
|
"mean_token_accuracy": 0.16519832164049147,
|
||
|
|
"num_tokens": 4973888.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.873337078094482,
|
||
|
|
"epoch": 0.20893371757925072,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998560177161969,
|
||
|
|
"loss": 5.7713,
|
||
|
|
"mean_token_accuracy": 0.1622347429394722,
|
||
|
|
"num_tokens": 4985423.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.875820159912109,
|
||
|
|
"epoch": 0.20941402497598463,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004998547888118718,
|
||
|
|
"loss": 5.7277,
|
||
|
|
"mean_token_accuracy": 0.16388818621635437,
|
||
|
|
"num_tokens": 4997711.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944964838027954,
|
||
|
|
"epoch": 0.20989433237271854,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004998535546870862,
|
||
|
|
"loss": 5.7587,
|
||
|
|
"mean_token_accuracy": 0.17094310671091079,
|
||
|
|
"num_tokens": 5009633.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.89435224533081,
|
||
|
|
"epoch": 0.21037463976945245,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004998523153418687,
|
||
|
|
"loss": 5.6898,
|
||
|
|
"mean_token_accuracy": 0.17721298336982727,
|
||
|
|
"num_tokens": 5021523.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.954970121383667,
|
||
|
|
"epoch": 0.21085494716618636,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004998510707762481,
|
||
|
|
"loss": 5.7963,
|
||
|
|
"mean_token_accuracy": 0.1734875962138176,
|
||
|
|
"num_tokens": 5033513.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01756477355957,
|
||
|
|
"epoch": 0.21133525456292027,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004998498209902533,
|
||
|
|
"loss": 5.7897,
|
||
|
|
"mean_token_accuracy": 0.16785951554775239,
|
||
|
|
"num_tokens": 5047055.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.842679691314697,
|
||
|
|
"epoch": 0.21181556195965417,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998485659839134,
|
||
|
|
"loss": 5.6612,
|
||
|
|
"mean_token_accuracy": 0.17763629406690598,
|
||
|
|
"num_tokens": 5057613.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.941239261627198,
|
||
|
|
"epoch": 0.21229586935638808,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004998473057572575,
|
||
|
|
"loss": 5.7791,
|
||
|
|
"mean_token_accuracy": 0.170269151031971,
|
||
|
|
"num_tokens": 5068886.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8616218090057375,
|
||
|
|
"epoch": 0.212776176753122,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998460403103146,
|
||
|
|
"loss": 5.7561,
|
||
|
|
"mean_token_accuracy": 0.16782673597335815,
|
||
|
|
"num_tokens": 5079978.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.881478404998779,
|
||
|
|
"epoch": 0.2132564841498559,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998447696431146,
|
||
|
|
"loss": 5.7203,
|
||
|
|
"mean_token_accuracy": 0.1720557138323784,
|
||
|
|
"num_tokens": 5091021.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.84704737663269,
|
||
|
|
"epoch": 0.2137367915465898,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998434937556865,
|
||
|
|
"loss": 5.6118,
|
||
|
|
"mean_token_accuracy": 0.18117671012878417,
|
||
|
|
"num_tokens": 5101483.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8953385829925535,
|
||
|
|
"epoch": 0.21421709894332372,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004998422126480602,
|
||
|
|
"loss": 5.7518,
|
||
|
|
"mean_token_accuracy": 0.16402507573366165,
|
||
|
|
"num_tokens": 5113116.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.954845809936524,
|
||
|
|
"epoch": 0.21469740634005763,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998409263202653,
|
||
|
|
"loss": 5.6943,
|
||
|
|
"mean_token_accuracy": 0.17064779102802277,
|
||
|
|
"num_tokens": 5124824.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.77202959060669,
|
||
|
|
"epoch": 0.21517771373679154,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998396347723318,
|
||
|
|
"loss": 5.6247,
|
||
|
|
"mean_token_accuracy": 0.1712438568472862,
|
||
|
|
"num_tokens": 5137567.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.833844184875488,
|
||
|
|
"epoch": 0.21565802113352545,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004998383380042895,
|
||
|
|
"loss": 5.6923,
|
||
|
|
"mean_token_accuracy": 0.17277579456567765,
|
||
|
|
"num_tokens": 5149016.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.808039903640747,
|
||
|
|
"epoch": 0.21613832853025935,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998370360161688,
|
||
|
|
"loss": 5.5749,
|
||
|
|
"mean_token_accuracy": 0.1784022033214569,
|
||
|
|
"num_tokens": 5160356.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.881575202941894,
|
||
|
|
"epoch": 0.21661863592699326,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004998357288079996,
|
||
|
|
"loss": 5.7716,
|
||
|
|
"mean_token_accuracy": 0.16418982148170472,
|
||
|
|
"num_tokens": 5172100.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9312032699584964,
|
||
|
|
"epoch": 0.21709894332372717,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004998344163798125,
|
||
|
|
"loss": 5.7397,
|
||
|
|
"mean_token_accuracy": 0.16633592247962953,
|
||
|
|
"num_tokens": 5183984.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.862771272659302,
|
||
|
|
"epoch": 0.21757925072046108,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004998330987316379,
|
||
|
|
"loss": 5.7188,
|
||
|
|
"mean_token_accuracy": 0.1685562714934349,
|
||
|
|
"num_tokens": 5195853.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7872209548950195,
|
||
|
|
"epoch": 0.21805955811719502,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004998317758635062,
|
||
|
|
"loss": 5.564,
|
||
|
|
"mean_token_accuracy": 0.17655707597732545,
|
||
|
|
"num_tokens": 5206995.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.662486600875854,
|
||
|
|
"epoch": 0.21853986551392893,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004998304477754484,
|
||
|
|
"loss": 5.601,
|
||
|
|
"mean_token_accuracy": 0.17818109691143036,
|
||
|
|
"num_tokens": 5219291.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.872530078887939,
|
||
|
|
"epoch": 0.21902017291066284,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998291144674952,
|
||
|
|
"loss": 5.6762,
|
||
|
|
"mean_token_accuracy": 0.17558231055736542,
|
||
|
|
"num_tokens": 5230856.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.743492794036865,
|
||
|
|
"epoch": 0.21950048030739674,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998277759396776,
|
||
|
|
"loss": 5.5404,
|
||
|
|
"mean_token_accuracy": 0.18575960099697114,
|
||
|
|
"num_tokens": 5242871.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.753171300888061,
|
||
|
|
"epoch": 0.21998078770413065,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998264321920265,
|
||
|
|
"loss": 5.645,
|
||
|
|
"mean_token_accuracy": 0.17795871943235397,
|
||
|
|
"num_tokens": 5253835.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.834173107147217,
|
||
|
|
"epoch": 0.22046109510086456,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004998250832245734,
|
||
|
|
"loss": 5.6285,
|
||
|
|
"mean_token_accuracy": 0.17905001789331437,
|
||
|
|
"num_tokens": 5266195.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.795336961746216,
|
||
|
|
"epoch": 0.22094140249759847,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998237290373494,
|
||
|
|
"loss": 5.6088,
|
||
|
|
"mean_token_accuracy": 0.18106043636798858,
|
||
|
|
"num_tokens": 5277499.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.926272821426392,
|
||
|
|
"epoch": 0.22142170989433238,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000499822369630386,
|
||
|
|
"loss": 5.7316,
|
||
|
|
"mean_token_accuracy": 0.16407669484615325,
|
||
|
|
"num_tokens": 5288622.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.853435325622558,
|
||
|
|
"epoch": 0.2219020172910663,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004998210050037148,
|
||
|
|
"loss": 5.7626,
|
||
|
|
"mean_token_accuracy": 0.1640668675303459,
|
||
|
|
"num_tokens": 5299664.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.848914766311646,
|
||
|
|
"epoch": 0.2223823246878002,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998196351573674,
|
||
|
|
"loss": 5.6597,
|
||
|
|
"mean_token_accuracy": 0.17648861855268477,
|
||
|
|
"num_tokens": 5311627.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.746734476089477,
|
||
|
|
"epoch": 0.2228626320845341,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998182600913757,
|
||
|
|
"loss": 5.5634,
|
||
|
|
"mean_token_accuracy": 0.18326989710330963,
|
||
|
|
"num_tokens": 5323000.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.806483554840088,
|
||
|
|
"epoch": 0.22334293948126802,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004998168798057715,
|
||
|
|
"loss": 5.601,
|
||
|
|
"mean_token_accuracy": 0.17859914302825927,
|
||
|
|
"num_tokens": 5333811.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.761362361907959,
|
||
|
|
"epoch": 0.22382324687800192,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000499815494300587,
|
||
|
|
"loss": 5.6037,
|
||
|
|
"mean_token_accuracy": 0.17953155487775802,
|
||
|
|
"num_tokens": 5344762.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.87151312828064,
|
||
|
|
"epoch": 0.22430355427473583,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998141035758542,
|
||
|
|
"loss": 5.6178,
|
||
|
|
"mean_token_accuracy": 0.17849526405334473,
|
||
|
|
"num_tokens": 5356112.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.816241693496704,
|
||
|
|
"epoch": 0.22478386167146974,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998127076316054,
|
||
|
|
"loss": 5.7338,
|
||
|
|
"mean_token_accuracy": 0.17089829891920089,
|
||
|
|
"num_tokens": 5367339.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.803972244262695,
|
||
|
|
"epoch": 0.22526416906820365,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004998113064678734,
|
||
|
|
"loss": 5.6492,
|
||
|
|
"mean_token_accuracy": 0.1800484448671341,
|
||
|
|
"num_tokens": 5378627.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.852473402023316,
|
||
|
|
"epoch": 0.22574447646493756,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998099000846901,
|
||
|
|
"loss": 5.6988,
|
||
|
|
"mean_token_accuracy": 0.170039651542902,
|
||
|
|
"num_tokens": 5390209.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897865295410156,
|
||
|
|
"epoch": 0.22622478386167147,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998084884820887,
|
||
|
|
"loss": 5.6853,
|
||
|
|
"mean_token_accuracy": 0.17408402562141417,
|
||
|
|
"num_tokens": 5401578.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.756231594085693,
|
||
|
|
"epoch": 0.22670509125840538,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004998070716601016,
|
||
|
|
"loss": 5.604,
|
||
|
|
"mean_token_accuracy": 0.17672595530748367,
|
||
|
|
"num_tokens": 5413831.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.865112972259522,
|
||
|
|
"epoch": 0.2271853986551393,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004998056496187618,
|
||
|
|
"loss": 5.6552,
|
||
|
|
"mean_token_accuracy": 0.17331201881170272,
|
||
|
|
"num_tokens": 5425430.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.671746349334716,
|
||
|
|
"epoch": 0.2276657060518732,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998042223581025,
|
||
|
|
"loss": 5.5077,
|
||
|
|
"mean_token_accuracy": 0.18612135499715804,
|
||
|
|
"num_tokens": 5435353.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.847486209869385,
|
||
|
|
"epoch": 0.2281460134486071,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004998027898781565,
|
||
|
|
"loss": 5.7082,
|
||
|
|
"mean_token_accuracy": 0.17188700735569,
|
||
|
|
"num_tokens": 5446925.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.763326358795166,
|
||
|
|
"epoch": 0.228626320845341,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004998013521789574,
|
||
|
|
"loss": 5.5835,
|
||
|
|
"mean_token_accuracy": 0.18231132328510286,
|
||
|
|
"num_tokens": 5456613.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.823438310623169,
|
||
|
|
"epoch": 0.22910662824207492,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004997999092605384,
|
||
|
|
"loss": 5.6236,
|
||
|
|
"mean_token_accuracy": 0.17775536924600602,
|
||
|
|
"num_tokens": 5467790.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.813823795318603,
|
||
|
|
"epoch": 0.22958693563880883,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000499798461122933,
|
||
|
|
"loss": 5.6084,
|
||
|
|
"mean_token_accuracy": 0.17633272111415862,
|
||
|
|
"num_tokens": 5479166.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.752776956558227,
|
||
|
|
"epoch": 0.23006724303554274,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004997970077661748,
|
||
|
|
"loss": 5.592,
|
||
|
|
"mean_token_accuracy": 0.18635759204626084,
|
||
|
|
"num_tokens": 5490186.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.799315357208252,
|
||
|
|
"epoch": 0.23054755043227665,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004997955491902977,
|
||
|
|
"loss": 5.581,
|
||
|
|
"mean_token_accuracy": 0.173208612203598,
|
||
|
|
"num_tokens": 5500416.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.78081750869751,
|
||
|
|
"epoch": 0.23102785782901056,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997940853953354,
|
||
|
|
"loss": 5.6455,
|
||
|
|
"mean_token_accuracy": 0.17610323131084443,
|
||
|
|
"num_tokens": 5512189.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.750943851470947,
|
||
|
|
"epoch": 0.23150816522574447,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000499792616381322,
|
||
|
|
"loss": 5.5152,
|
||
|
|
"mean_token_accuracy": 0.18103354275226594,
|
||
|
|
"num_tokens": 5523631.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.769753503799438,
|
||
|
|
"epoch": 0.23198847262247838,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004997911421482914,
|
||
|
|
"loss": 5.5793,
|
||
|
|
"mean_token_accuracy": 0.18183256834745407,
|
||
|
|
"num_tokens": 5535637.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7926108837127686,
|
||
|
|
"epoch": 0.23246878001921228,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499789662696278,
|
||
|
|
"loss": 5.5809,
|
||
|
|
"mean_token_accuracy": 0.18048014342784882,
|
||
|
|
"num_tokens": 5546470.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.866393899917602,
|
||
|
|
"epoch": 0.2329490874159462,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004997881780253162,
|
||
|
|
"loss": 5.7472,
|
||
|
|
"mean_token_accuracy": 0.1731916069984436,
|
||
|
|
"num_tokens": 5558633.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.785652208328247,
|
||
|
|
"epoch": 0.2334293948126801,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004997866881354403,
|
||
|
|
"loss": 5.6529,
|
||
|
|
"mean_token_accuracy": 0.1741258069872856,
|
||
|
|
"num_tokens": 5570427.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.814468336105347,
|
||
|
|
"epoch": 0.23390970220941404,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000499785193026685,
|
||
|
|
"loss": 5.6383,
|
||
|
|
"mean_token_accuracy": 0.17221823185682297,
|
||
|
|
"num_tokens": 5580991.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.831542491912842,
|
||
|
|
"epoch": 0.23439000960614795,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004997836926990851,
|
||
|
|
"loss": 5.688,
|
||
|
|
"mean_token_accuracy": 0.1702160969376564,
|
||
|
|
"num_tokens": 5592777.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.743597841262817,
|
||
|
|
"epoch": 0.23487031700288186,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997821871526752,
|
||
|
|
"loss": 5.5844,
|
||
|
|
"mean_token_accuracy": 0.18186513036489488,
|
||
|
|
"num_tokens": 5603326.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7442912578582765,
|
||
|
|
"epoch": 0.23535062439961577,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997806763874905,
|
||
|
|
"loss": 5.5642,
|
||
|
|
"mean_token_accuracy": 0.17944303005933762,
|
||
|
|
"num_tokens": 5614504.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.771292018890381,
|
||
|
|
"epoch": 0.23583093179634967,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004997791604035659,
|
||
|
|
"loss": 5.6286,
|
||
|
|
"mean_token_accuracy": 0.18041289001703262,
|
||
|
|
"num_tokens": 5625150.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.772236967086792,
|
||
|
|
"epoch": 0.23631123919308358,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004997776392009366,
|
||
|
|
"loss": 5.6376,
|
||
|
|
"mean_token_accuracy": 0.17271037846803666,
|
||
|
|
"num_tokens": 5636815.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.824061107635498,
|
||
|
|
"epoch": 0.2367915465898175,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004997761127796381,
|
||
|
|
"loss": 5.6228,
|
||
|
|
"mean_token_accuracy": 0.17515492290258408,
|
||
|
|
"num_tokens": 5648272.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.761957883834839,
|
||
|
|
"epoch": 0.2372718539865514,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997745811397056,
|
||
|
|
"loss": 5.5481,
|
||
|
|
"mean_token_accuracy": 0.17955229729413985,
|
||
|
|
"num_tokens": 5659227.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7706011772155765,
|
||
|
|
"epoch": 0.2377521613832853,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004997730442811748,
|
||
|
|
"loss": 5.668,
|
||
|
|
"mean_token_accuracy": 0.1772313669323921,
|
||
|
|
"num_tokens": 5670411.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.764390659332276,
|
||
|
|
"epoch": 0.23823246878001922,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997715022040814,
|
||
|
|
"loss": 5.5125,
|
||
|
|
"mean_token_accuracy": 0.1818181738257408,
|
||
|
|
"num_tokens": 5681570.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.693533134460449,
|
||
|
|
"epoch": 0.23871277617675313,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000499769954908461,
|
||
|
|
"loss": 5.5075,
|
||
|
|
"mean_token_accuracy": 0.18814098387956618,
|
||
|
|
"num_tokens": 5693021.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.732751131057739,
|
||
|
|
"epoch": 0.23919308357348704,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004997684023943498,
|
||
|
|
"loss": 5.5841,
|
||
|
|
"mean_token_accuracy": 0.17531975656747817,
|
||
|
|
"num_tokens": 5704043.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.747956085205078,
|
||
|
|
"epoch": 0.23967339097022095,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997668446617837,
|
||
|
|
"loss": 5.6703,
|
||
|
|
"mean_token_accuracy": 0.17353179901838303,
|
||
|
|
"num_tokens": 5715735.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.906291723251343,
|
||
|
|
"epoch": 0.24015369836695485,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997652817107989,
|
||
|
|
"loss": 5.6301,
|
||
|
|
"mean_token_accuracy": 0.1773464038968086,
|
||
|
|
"num_tokens": 5725778.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7474383354187015,
|
||
|
|
"epoch": 0.24063400576368876,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004997637135414315,
|
||
|
|
"loss": 5.6558,
|
||
|
|
"mean_token_accuracy": 0.17596883922815323,
|
||
|
|
"num_tokens": 5737224.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.883420705795288,
|
||
|
|
"epoch": 0.24111431316042267,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004997621401537183,
|
||
|
|
"loss": 5.6777,
|
||
|
|
"mean_token_accuracy": 0.17386398762464522,
|
||
|
|
"num_tokens": 5749226.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.84810619354248,
|
||
|
|
"epoch": 0.24159462055715658,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997605615476955,
|
||
|
|
"loss": 5.6523,
|
||
|
|
"mean_token_accuracy": 0.17698420137166976,
|
||
|
|
"num_tokens": 5760282.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.712239980697632,
|
||
|
|
"epoch": 0.2420749279538905,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004997589777234,
|
||
|
|
"loss": 5.5534,
|
||
|
|
"mean_token_accuracy": 0.18517332524061203,
|
||
|
|
"num_tokens": 5771756.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.766052198410034,
|
||
|
|
"epoch": 0.2425552353506244,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997573886808684,
|
||
|
|
"loss": 5.5824,
|
||
|
|
"mean_token_accuracy": 0.1730706885457039,
|
||
|
|
"num_tokens": 5783237.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8274911403656,
|
||
|
|
"epoch": 0.2430355427473583,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004997557944201375,
|
||
|
|
"loss": 5.6739,
|
||
|
|
"mean_token_accuracy": 0.17468079626560212,
|
||
|
|
"num_tokens": 5794825.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.793378686904907,
|
||
|
|
"epoch": 0.24351585014409222,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004997541949412445,
|
||
|
|
"loss": 5.5834,
|
||
|
|
"mean_token_accuracy": 0.18117998987436296,
|
||
|
|
"num_tokens": 5805578.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.833753156661987,
|
||
|
|
"epoch": 0.24399615754082613,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004997525902442266,
|
||
|
|
"loss": 5.6623,
|
||
|
|
"mean_token_accuracy": 0.16987032443284988,
|
||
|
|
"num_tokens": 5818201.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.754938840866089,
|
||
|
|
"epoch": 0.24447646493756003,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004997509803291207,
|
||
|
|
"loss": 5.5809,
|
||
|
|
"mean_token_accuracy": 0.17766104489564896,
|
||
|
|
"num_tokens": 5830319.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7188770294189455,
|
||
|
|
"epoch": 0.24495677233429394,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997493651959647,
|
||
|
|
"loss": 5.5319,
|
||
|
|
"mean_token_accuracy": 0.18243667036294936,
|
||
|
|
"num_tokens": 5840638.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.779051208496094,
|
||
|
|
"epoch": 0.24543707973102785,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004997477448447955,
|
||
|
|
"loss": 5.5674,
|
||
|
|
"mean_token_accuracy": 0.17579597234725952,
|
||
|
|
"num_tokens": 5852472.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.779905652999878,
|
||
|
|
"epoch": 0.24591738712776176,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997461192756512,
|
||
|
|
"loss": 5.6071,
|
||
|
|
"mean_token_accuracy": 0.17549769282341005,
|
||
|
|
"num_tokens": 5863455.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7139819145202635,
|
||
|
|
"epoch": 0.24639769452449567,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997444884885694,
|
||
|
|
"loss": 5.5082,
|
||
|
|
"mean_token_accuracy": 0.1821136549115181,
|
||
|
|
"num_tokens": 5873141.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.714353847503662,
|
||
|
|
"epoch": 0.24687800192122958,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997428524835879,
|
||
|
|
"loss": 5.6137,
|
||
|
|
"mean_token_accuracy": 0.177882120013237,
|
||
|
|
"num_tokens": 5884363.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8017199516296385,
|
||
|
|
"epoch": 0.2473583093179635,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004997412112607446,
|
||
|
|
"loss": 5.6563,
|
||
|
|
"mean_token_accuracy": 0.17355215102434157,
|
||
|
|
"num_tokens": 5895856.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7232537269592285,
|
||
|
|
"epoch": 0.2478386167146974,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004997395648200778,
|
||
|
|
"loss": 5.4999,
|
||
|
|
"mean_token_accuracy": 0.18378839939832686,
|
||
|
|
"num_tokens": 5906657.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.733435249328613,
|
||
|
|
"epoch": 0.2483189241114313,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004997379131616257,
|
||
|
|
"loss": 5.6144,
|
||
|
|
"mean_token_accuracy": 0.17644155025482178,
|
||
|
|
"num_tokens": 5919496.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.843182802200317,
|
||
|
|
"epoch": 0.24879923150816521,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004997362562854266,
|
||
|
|
"loss": 5.6782,
|
||
|
|
"mean_token_accuracy": 0.16554286181926728,
|
||
|
|
"num_tokens": 5932593.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.776597499847412,
|
||
|
|
"epoch": 0.24927953890489912,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997345941915187,
|
||
|
|
"loss": 5.5987,
|
||
|
|
"mean_token_accuracy": 0.1750054731965065,
|
||
|
|
"num_tokens": 5944080.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.734813213348389,
|
||
|
|
"epoch": 0.24975984630163303,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997329268799412,
|
||
|
|
"loss": 5.5622,
|
||
|
|
"mean_token_accuracy": 0.18719092905521392,
|
||
|
|
"num_tokens": 5955703.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.736793804168701,
|
||
|
|
"epoch": 0.25024015369836694,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004997312543507322,
|
||
|
|
"loss": 5.6578,
|
||
|
|
"mean_token_accuracy": 0.1708198830485344,
|
||
|
|
"num_tokens": 5966979.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.811160707473755,
|
||
|
|
"epoch": 0.2507204610951009,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997295766039309,
|
||
|
|
"loss": 5.5433,
|
||
|
|
"mean_token_accuracy": 0.17897313684225083,
|
||
|
|
"num_tokens": 5978808.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.785584354400635,
|
||
|
|
"epoch": 0.25120076849183476,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004997278936395761,
|
||
|
|
"loss": 5.7051,
|
||
|
|
"mean_token_accuracy": 0.16843380331993102,
|
||
|
|
"num_tokens": 5992145.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7584997653961185,
|
||
|
|
"epoch": 0.2516810758885687,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997262054577071,
|
||
|
|
"loss": 5.5743,
|
||
|
|
"mean_token_accuracy": 0.17471926659345627,
|
||
|
|
"num_tokens": 6003723.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.771317625045777,
|
||
|
|
"epoch": 0.2521613832853026,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997245120583627,
|
||
|
|
"loss": 5.6058,
|
||
|
|
"mean_token_accuracy": 0.18242801427841188,
|
||
|
|
"num_tokens": 6014064.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.698479509353637,
|
||
|
|
"epoch": 0.2526416906820365,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004997228134415825,
|
||
|
|
"loss": 5.5187,
|
||
|
|
"mean_token_accuracy": 0.18279289156198503,
|
||
|
|
"num_tokens": 6025455.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.782511425018311,
|
||
|
|
"epoch": 0.2531219980787704,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997211096074059,
|
||
|
|
"loss": 5.6313,
|
||
|
|
"mean_token_accuracy": 0.1700494483113289,
|
||
|
|
"num_tokens": 6037347.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6879799365997314,
|
||
|
|
"epoch": 0.25360230547550433,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997194005558722,
|
||
|
|
"loss": 5.5155,
|
||
|
|
"mean_token_accuracy": 0.18077107816934584,
|
||
|
|
"num_tokens": 6049236.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.664460229873657,
|
||
|
|
"epoch": 0.2540826128722382,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004997176862870216,
|
||
|
|
"loss": 5.5396,
|
||
|
|
"mean_token_accuracy": 0.1818702682852745,
|
||
|
|
"num_tokens": 6060982.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.795065593719483,
|
||
|
|
"epoch": 0.25456292026897215,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997159668008933,
|
||
|
|
"loss": 5.5409,
|
||
|
|
"mean_token_accuracy": 0.18014705032110215,
|
||
|
|
"num_tokens": 6070925.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.672208833694458,
|
||
|
|
"epoch": 0.25504322766570603,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997142420975277,
|
||
|
|
"loss": 5.505,
|
||
|
|
"mean_token_accuracy": 0.18191429376602172,
|
||
|
|
"num_tokens": 6081279.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.707340812683105,
|
||
|
|
"epoch": 0.25552353506243997,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004997125121769647,
|
||
|
|
"loss": 5.5966,
|
||
|
|
"mean_token_accuracy": 0.17941437065601348,
|
||
|
|
"num_tokens": 6091797.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.816579580307007,
|
||
|
|
"epoch": 0.25600384245917385,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004997107770392444,
|
||
|
|
"loss": 5.6217,
|
||
|
|
"mean_token_accuracy": 0.18266446739435196,
|
||
|
|
"num_tokens": 6103435.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8208917617797855,
|
||
|
|
"epoch": 0.2564841498559078,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000499709036684407,
|
||
|
|
"loss": 5.6735,
|
||
|
|
"mean_token_accuracy": 0.1784491568803787,
|
||
|
|
"num_tokens": 6114531.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.659421300888061,
|
||
|
|
"epoch": 0.25696445725264166,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004997072911124932,
|
||
|
|
"loss": 5.5132,
|
||
|
|
"mean_token_accuracy": 0.1838804692029953,
|
||
|
|
"num_tokens": 6126110.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.79349536895752,
|
||
|
|
"epoch": 0.2574447646493756,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004997055403235432,
|
||
|
|
"loss": 5.6132,
|
||
|
|
"mean_token_accuracy": 0.17701641321182252,
|
||
|
|
"num_tokens": 6137114.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.69478325843811,
|
||
|
|
"epoch": 0.2579250720461095,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004997037843175978,
|
||
|
|
"loss": 5.5683,
|
||
|
|
"mean_token_accuracy": 0.17944201529026033,
|
||
|
|
"num_tokens": 6148696.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.735519981384277,
|
||
|
|
"epoch": 0.2584053794428434,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004997020230946978,
|
||
|
|
"loss": 5.5677,
|
||
|
|
"mean_token_accuracy": 0.18062195777893067,
|
||
|
|
"num_tokens": 6160235.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.747908687591552,
|
||
|
|
"epoch": 0.25888568683957736,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004997002566548841,
|
||
|
|
"loss": 5.5407,
|
||
|
|
"mean_token_accuracy": 0.17935636788606643,
|
||
|
|
"num_tokens": 6172031.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.596827173233033,
|
||
|
|
"epoch": 0.25936599423631124,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004996984849981976,
|
||
|
|
"loss": 5.4283,
|
||
|
|
"mean_token_accuracy": 0.18828413337469102,
|
||
|
|
"num_tokens": 6183547.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.798890924453735,
|
||
|
|
"epoch": 0.2598463016330452,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004996967081246794,
|
||
|
|
"loss": 5.6161,
|
||
|
|
"mean_token_accuracy": 0.17421343475580214,
|
||
|
|
"num_tokens": 6194768.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.752058315277099,
|
||
|
|
"epoch": 0.26032660902977905,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004996949260343711,
|
||
|
|
"loss": 5.6108,
|
||
|
|
"mean_token_accuracy": 0.17473251819610597,
|
||
|
|
"num_tokens": 6206099.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.768714952468872,
|
||
|
|
"epoch": 0.260806916426513,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004996931387273137,
|
||
|
|
"loss": 5.6049,
|
||
|
|
"mean_token_accuracy": 0.18249890506267546,
|
||
|
|
"num_tokens": 6217530.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.824987697601318,
|
||
|
|
"epoch": 0.2612872238232469,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004996913462035487,
|
||
|
|
"loss": 5.6404,
|
||
|
|
"mean_token_accuracy": 0.1773010641336441,
|
||
|
|
"num_tokens": 6228564.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.682008457183838,
|
||
|
|
"epoch": 0.2617675312199808,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000499689548463118,
|
||
|
|
"loss": 5.5072,
|
||
|
|
"mean_token_accuracy": 0.18143168538808824,
|
||
|
|
"num_tokens": 6239945.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.719662475585937,
|
||
|
|
"epoch": 0.2622478386167147,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004996877455060631,
|
||
|
|
"loss": 5.6148,
|
||
|
|
"mean_token_accuracy": 0.17328692674636842,
|
||
|
|
"num_tokens": 6251829.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.861980676651001,
|
||
|
|
"epoch": 0.2627281460134486,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004996859373324259,
|
||
|
|
"loss": 5.7102,
|
||
|
|
"mean_token_accuracy": 0.1663394570350647,
|
||
|
|
"num_tokens": 6264823.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.684702014923095,
|
||
|
|
"epoch": 0.2632084534101825,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004996841239422485,
|
||
|
|
"loss": 5.4084,
|
||
|
|
"mean_token_accuracy": 0.18651311248540878,
|
||
|
|
"num_tokens": 6276247.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.626027154922485,
|
||
|
|
"epoch": 0.26368876080691644,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004996823053355729,
|
||
|
|
"loss": 5.5308,
|
||
|
|
"mean_token_accuracy": 0.18354606330394746,
|
||
|
|
"num_tokens": 6287593.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.799522447586059,
|
||
|
|
"epoch": 0.2641690682036503,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004996804815124413,
|
||
|
|
"loss": 5.676,
|
||
|
|
"mean_token_accuracy": 0.17569343596696854,
|
||
|
|
"num_tokens": 6299918.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.681373929977417,
|
||
|
|
"epoch": 0.26464937560038426,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004996786524728962,
|
||
|
|
"loss": 5.5314,
|
||
|
|
"mean_token_accuracy": 0.18340865522623062,
|
||
|
|
"num_tokens": 6311147.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.615675544738769,
|
||
|
|
"epoch": 0.26512968299711814,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004996768182169797,
|
||
|
|
"loss": 5.4432,
|
||
|
|
"mean_token_accuracy": 0.18849314153194427,
|
||
|
|
"num_tokens": 6323239.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.773361492156982,
|
||
|
|
"epoch": 0.2656099903938521,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004996749787447349,
|
||
|
|
"loss": 5.5348,
|
||
|
|
"mean_token_accuracy": 0.1791366621851921,
|
||
|
|
"num_tokens": 6334625.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.70220251083374,
|
||
|
|
"epoch": 0.26609029779058596,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000499673134056204,
|
||
|
|
"loss": 5.5651,
|
||
|
|
"mean_token_accuracy": 0.17963075488805771,
|
||
|
|
"num_tokens": 6346068.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.713240051269532,
|
||
|
|
"epoch": 0.2665706051873199,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004996712841514303,
|
||
|
|
"loss": 5.5531,
|
||
|
|
"mean_token_accuracy": 0.18010566383600235,
|
||
|
|
"num_tokens": 6357097.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7573648452758786,
|
||
|
|
"epoch": 0.2670509125840538,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004996694290304563,
|
||
|
|
"loss": 5.6084,
|
||
|
|
"mean_token_accuracy": 0.17204165309667588,
|
||
|
|
"num_tokens": 6367481.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.685487174987793,
|
||
|
|
"epoch": 0.2675312199807877,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004996675686933255,
|
||
|
|
"loss": 5.5207,
|
||
|
|
"mean_token_accuracy": 0.18194421827793122,
|
||
|
|
"num_tokens": 6378873.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.747344875335694,
|
||
|
|
"epoch": 0.2680115273775216,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004996657031400807,
|
||
|
|
"loss": 5.5625,
|
||
|
|
"mean_token_accuracy": 0.1808866173028946,
|
||
|
|
"num_tokens": 6390651.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.640884160995483,
|
||
|
|
"epoch": 0.26849183477425553,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004996638323707655,
|
||
|
|
"loss": 5.4351,
|
||
|
|
"mean_token_accuracy": 0.18793859630823134,
|
||
|
|
"num_tokens": 6401631.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6249631404876705,
|
||
|
|
"epoch": 0.2689721421709894,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004996619563854232,
|
||
|
|
"loss": 5.5219,
|
||
|
|
"mean_token_accuracy": 0.186911478638649,
|
||
|
|
"num_tokens": 6413875.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.782164573669434,
|
||
|
|
"epoch": 0.26945244956772335,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004996600751840974,
|
||
|
|
"loss": 5.5488,
|
||
|
|
"mean_token_accuracy": 0.17567767947912216,
|
||
|
|
"num_tokens": 6425764.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.648550701141358,
|
||
|
|
"epoch": 0.26993275696445723,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004996581887668317,
|
||
|
|
"loss": 5.4617,
|
||
|
|
"mean_token_accuracy": 0.1833810329437256,
|
||
|
|
"num_tokens": 6437911.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6579090595245365,
|
||
|
|
"epoch": 0.27041306436119117,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00049965629713367,
|
||
|
|
"loss": 5.4874,
|
||
|
|
"mean_token_accuracy": 0.1852079749107361,
|
||
|
|
"num_tokens": 6449942.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.709984302520752,
|
||
|
|
"epoch": 0.27089337175792505,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004996544002846561,
|
||
|
|
"loss": 5.6016,
|
||
|
|
"mean_token_accuracy": 0.18187092244625092,
|
||
|
|
"num_tokens": 6461729.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.747480726242065,
|
||
|
|
"epoch": 0.271373679154659,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004996524982198343,
|
||
|
|
"loss": 5.5839,
|
||
|
|
"mean_token_accuracy": 0.18295794278383254,
|
||
|
|
"num_tokens": 6472046.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.714561557769775,
|
||
|
|
"epoch": 0.27185398655139287,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004996505909392485,
|
||
|
|
"loss": 5.5436,
|
||
|
|
"mean_token_accuracy": 0.1794055625796318,
|
||
|
|
"num_tokens": 6483308.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5759443759918215,
|
||
|
|
"epoch": 0.2723342939481268,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004996486784429429,
|
||
|
|
"loss": 5.4213,
|
||
|
|
"mean_token_accuracy": 0.18884292393922805,
|
||
|
|
"num_tokens": 6495093.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.70222053527832,
|
||
|
|
"epoch": 0.2728146013448607,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004996467607309622,
|
||
|
|
"loss": 5.5213,
|
||
|
|
"mean_token_accuracy": 0.18563241511583328,
|
||
|
|
"num_tokens": 6505933.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.663483715057373,
|
||
|
|
"epoch": 0.2732949087415946,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004996448378033507,
|
||
|
|
"loss": 5.56,
|
||
|
|
"mean_token_accuracy": 0.17418374568223954,
|
||
|
|
"num_tokens": 6517280.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.739472961425781,
|
||
|
|
"epoch": 0.2737752161383285,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004996429096601532,
|
||
|
|
"loss": 5.62,
|
||
|
|
"mean_token_accuracy": 0.1724501520395279,
|
||
|
|
"num_tokens": 6528980.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.694519329071045,
|
||
|
|
"epoch": 0.27425552353506244,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004996409763014144,
|
||
|
|
"loss": 5.6063,
|
||
|
|
"mean_token_accuracy": 0.18012285381555557,
|
||
|
|
"num_tokens": 6540670.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6691272258758545,
|
||
|
|
"epoch": 0.2747358309317964,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004996390377271791,
|
||
|
|
"loss": 5.5641,
|
||
|
|
"mean_token_accuracy": 0.18185704350471496,
|
||
|
|
"num_tokens": 6551302.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.717091369628906,
|
||
|
|
"epoch": 0.27521613832853026,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004996370939374924,
|
||
|
|
"loss": 5.5206,
|
||
|
|
"mean_token_accuracy": 0.17356996536254882,
|
||
|
|
"num_tokens": 6563177.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.848795604705811,
|
||
|
|
"epoch": 0.2756964457252642,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004996351449323994,
|
||
|
|
"loss": 5.6331,
|
||
|
|
"mean_token_accuracy": 0.18121621906757354,
|
||
|
|
"num_tokens": 6573323.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6664739608764645,
|
||
|
|
"epoch": 0.2761767531219981,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004996331907119455,
|
||
|
|
"loss": 5.5584,
|
||
|
|
"mean_token_accuracy": 0.17100237160921097,
|
||
|
|
"num_tokens": 6585382.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.612715768814087,
|
||
|
|
"epoch": 0.276657060518732,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004996312312761758,
|
||
|
|
"loss": 5.4473,
|
||
|
|
"mean_token_accuracy": 0.18974230736494063,
|
||
|
|
"num_tokens": 6596629.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.721270322799683,
|
||
|
|
"epoch": 0.2771373679154659,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000499629266625136,
|
||
|
|
"loss": 5.5591,
|
||
|
|
"mean_token_accuracy": 0.17991002202033995,
|
||
|
|
"num_tokens": 6608408.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.779607629776001,
|
||
|
|
"epoch": 0.27761767531219983,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004996272967588715,
|
||
|
|
"loss": 5.5857,
|
||
|
|
"mean_token_accuracy": 0.17561327517032624,
|
||
|
|
"num_tokens": 6619375.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.758464813232422,
|
||
|
|
"epoch": 0.2780979827089337,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004996253216774283,
|
||
|
|
"loss": 5.6217,
|
||
|
|
"mean_token_accuracy": 0.17862538397312164,
|
||
|
|
"num_tokens": 6631317.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.706511449813843,
|
||
|
|
"epoch": 0.27857829010566765,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004996233413808521,
|
||
|
|
"loss": 5.4881,
|
||
|
|
"mean_token_accuracy": 0.18149750381708146,
|
||
|
|
"num_tokens": 6642009.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.686898136138916,
|
||
|
|
"epoch": 0.27905859750240153,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004996213558691889,
|
||
|
|
"loss": 5.6358,
|
||
|
|
"mean_token_accuracy": 0.17196063697338104,
|
||
|
|
"num_tokens": 6654713.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.74081768989563,
|
||
|
|
"epoch": 0.27953890489913547,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004996193651424848,
|
||
|
|
"loss": 5.5878,
|
||
|
|
"mean_token_accuracy": 0.1804736316204071,
|
||
|
|
"num_tokens": 6667157.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.703048181533814,
|
||
|
|
"epoch": 0.28001921229586935,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000499617369200786,
|
||
|
|
"loss": 5.5329,
|
||
|
|
"mean_token_accuracy": 0.1874094307422638,
|
||
|
|
"num_tokens": 6679573.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.73606538772583,
|
||
|
|
"epoch": 0.2804995196926033,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0004996153680441389,
|
||
|
|
"loss": 5.6154,
|
||
|
|
"mean_token_accuracy": 0.1785501942038536,
|
||
|
|
"num_tokens": 6691768.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.75312385559082,
|
||
|
|
"epoch": 0.28097982708933716,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00049961336167259,
|
||
|
|
"loss": 5.5727,
|
||
|
|
"mean_token_accuracy": 0.1757212147116661,
|
||
|
|
"num_tokens": 6701964.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.748111152648926,
|
||
|
|
"epoch": 0.2814601344860711,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004996113500861857,
|
||
|
|
"loss": 5.5561,
|
||
|
|
"mean_token_accuracy": 0.18022931665182113,
|
||
|
|
"num_tokens": 6713506.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.749008369445801,
|
||
|
|
"epoch": 0.281940441882805,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004996093332849729,
|
||
|
|
"loss": 5.5821,
|
||
|
|
"mean_token_accuracy": 0.17544898986816407,
|
||
|
|
"num_tokens": 6724616.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6963791847229,
|
||
|
|
"epoch": 0.2824207492795389,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004996073112689983,
|
||
|
|
"loss": 5.5629,
|
||
|
|
"mean_token_accuracy": 0.18043071925640106,
|
||
|
|
"num_tokens": 6735054.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.741255426406861,
|
||
|
|
"epoch": 0.2829010566762728,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004996052840383088,
|
||
|
|
"loss": 5.6018,
|
||
|
|
"mean_token_accuracy": 0.1793173149228096,
|
||
|
|
"num_tokens": 6746756.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.704806613922119,
|
||
|
|
"epoch": 0.28338136407300674,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004996032515929516,
|
||
|
|
"loss": 5.4832,
|
||
|
|
"mean_token_accuracy": 0.1823109433054924,
|
||
|
|
"num_tokens": 6759566.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.69014163017273,
|
||
|
|
"epoch": 0.2838616714697406,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004996012139329738,
|
||
|
|
"loss": 5.5125,
|
||
|
|
"mean_token_accuracy": 0.18087273538112641,
|
||
|
|
"num_tokens": 6771375.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.748940420150757,
|
||
|
|
"epoch": 0.28434197886647455,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004995991710584228,
|
||
|
|
"loss": 5.6176,
|
||
|
|
"mean_token_accuracy": 0.1698983356356621,
|
||
|
|
"num_tokens": 6783252.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6928369998931885,
|
||
|
|
"epoch": 0.28482228626320844,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004995971229693459,
|
||
|
|
"loss": 5.5816,
|
||
|
|
"mean_token_accuracy": 0.1742567628622055,
|
||
|
|
"num_tokens": 6795525.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.742653036117554,
|
||
|
|
"epoch": 0.28530259365994237,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004995950696657909,
|
||
|
|
"loss": 5.5129,
|
||
|
|
"mean_token_accuracy": 0.18347676545381547,
|
||
|
|
"num_tokens": 6807212.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.64953875541687,
|
||
|
|
"epoch": 0.28578290105667625,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004995930111478051,
|
||
|
|
"loss": 5.458,
|
||
|
|
"mean_token_accuracy": 0.18245918452739715,
|
||
|
|
"num_tokens": 6819367.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.665671300888062,
|
||
|
|
"epoch": 0.2862632084534102,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004995909474154365,
|
||
|
|
"loss": 5.5454,
|
||
|
|
"mean_token_accuracy": 0.18168749809265136,
|
||
|
|
"num_tokens": 6830405.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6374242305755615,
|
||
|
|
"epoch": 0.28674351585014407,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004995888784687331,
|
||
|
|
"loss": 5.513,
|
||
|
|
"mean_token_accuracy": 0.1782350167632103,
|
||
|
|
"num_tokens": 6841479.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.671642160415649,
|
||
|
|
"epoch": 0.287223823246878,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004995868043077428,
|
||
|
|
"loss": 5.5612,
|
||
|
|
"mean_token_accuracy": 0.17904469966888428,
|
||
|
|
"num_tokens": 6851585.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.694643163681031,
|
||
|
|
"epoch": 0.2877041306436119,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004995847249325137,
|
||
|
|
"loss": 5.521,
|
||
|
|
"mean_token_accuracy": 0.18657984137535094,
|
||
|
|
"num_tokens": 6863176.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.726582813262939,
|
||
|
|
"epoch": 0.2881844380403458,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004995826403430942,
|
||
|
|
"loss": 5.5769,
|
||
|
|
"mean_token_accuracy": 0.1821230873465538,
|
||
|
|
"num_tokens": 6874021.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2881844380403458,
|
||
|
|
"eval_entropy": 5.499006296238743,
|
||
|
|
"eval_loss": 5.545695781707764,
|
||
|
|
"eval_mean_token_accuracy": 0.1887321266854706,
|
||
|
|
"eval_num_tokens": 6874021.0,
|
||
|
|
"eval_runtime": 20.7487,
|
||
|
|
"eval_samples_per_second": 1581.543,
|
||
|
|
"eval_steps_per_second": 197.699,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 104090,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 10,
|
||
|
|
"save_steps": 3000,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1562945946255360.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|