374d25c765
Model: fpadovani/hin-deva-10mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
24079 lines
661 KiB
JSON
24079 lines
661 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.1527377521613833,
|
|
"eval_steps": 3000,
|
|
"global_step": 12000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.307085371017456,
|
|
"epoch": 0.0004803073967339097,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.6711,
|
|
"mean_token_accuracy": 0.11963684856891632,
|
|
"num_tokens": 10855.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.261483955383301,
|
|
"epoch": 0.0009606147934678194,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.611,
|
|
"mean_token_accuracy": 0.12699446231126785,
|
|
"num_tokens": 24110.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.322568655014038,
|
|
"epoch": 0.001440922190201729,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.712,
|
|
"mean_token_accuracy": 0.11978077217936516,
|
|
"num_tokens": 35984.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.314567613601684,
|
|
"epoch": 0.0019212295869356388,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.8292,
|
|
"mean_token_accuracy": 0.11400551423430443,
|
|
"num_tokens": 48152.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.27342529296875,
|
|
"epoch": 0.0024015369836695487,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.7211,
|
|
"mean_token_accuracy": 0.12296620458364486,
|
|
"num_tokens": 59810.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.184682607650757,
|
|
"epoch": 0.002881844380403458,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.5527,
|
|
"mean_token_accuracy": 0.12848290130496026,
|
|
"num_tokens": 70852.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.165819931030273,
|
|
"epoch": 0.0033621517771373678,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.6676,
|
|
"mean_token_accuracy": 0.12854331284761428,
|
|
"num_tokens": 83378.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.211078310012818,
|
|
"epoch": 0.0038424591738712775,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.7318,
|
|
"mean_token_accuracy": 0.12352305576205254,
|
|
"num_tokens": 95505.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.143542957305908,
|
|
"epoch": 0.004322766570605188,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.6624,
|
|
"mean_token_accuracy": 0.13083189800381662,
|
|
"num_tokens": 106812.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.1696985244750975,
|
|
"epoch": 0.004803073967339097,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.6905,
|
|
"mean_token_accuracy": 0.12702840194106102,
|
|
"num_tokens": 118572.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.134132242202758,
|
|
"epoch": 0.005283381364073006,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.6333,
|
|
"mean_token_accuracy": 0.13059643805027008,
|
|
"num_tokens": 130051.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.118882560729981,
|
|
"epoch": 0.005763688760806916,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.7479,
|
|
"mean_token_accuracy": 0.12762305215001107,
|
|
"num_tokens": 141920.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.106608819961548,
|
|
"epoch": 0.006243996157540826,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.6002,
|
|
"mean_token_accuracy": 0.13259410262107849,
|
|
"num_tokens": 152706.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.095578145980835,
|
|
"epoch": 0.0067243035542747355,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.6396,
|
|
"mean_token_accuracy": 0.1325068600475788,
|
|
"num_tokens": 165253.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.086773347854614,
|
|
"epoch": 0.007204610951008645,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.5959,
|
|
"mean_token_accuracy": 0.13050568848848343,
|
|
"num_tokens": 176708.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.126611709594727,
|
|
"epoch": 0.007684918347742555,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.69,
|
|
"mean_token_accuracy": 0.1262853056192398,
|
|
"num_tokens": 188240.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.042779111862183,
|
|
"epoch": 0.008165225744476465,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.496,
|
|
"mean_token_accuracy": 0.14095853343605996,
|
|
"num_tokens": 198355.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.078471279144287,
|
|
"epoch": 0.008645533141210375,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.586,
|
|
"mean_token_accuracy": 0.12663363963365554,
|
|
"num_tokens": 209497.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.093791770935058,
|
|
"epoch": 0.009125840537944284,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.6097,
|
|
"mean_token_accuracy": 0.1298912487924099,
|
|
"num_tokens": 220859.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.139126348495483,
|
|
"epoch": 0.009606147934678195,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.7121,
|
|
"mean_token_accuracy": 0.12592171207070352,
|
|
"num_tokens": 231550.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.0799497127532955,
|
|
"epoch": 0.010086455331412104,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.6082,
|
|
"mean_token_accuracy": 0.12669628784060477,
|
|
"num_tokens": 244210.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.108440780639649,
|
|
"epoch": 0.010566762728146013,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.5846,
|
|
"mean_token_accuracy": 0.13026389181613923,
|
|
"num_tokens": 255745.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.094820356369018,
|
|
"epoch": 0.011047070124879923,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.581,
|
|
"mean_token_accuracy": 0.1345028355717659,
|
|
"num_tokens": 266180.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.168249034881592,
|
|
"epoch": 0.011527377521613832,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.6584,
|
|
"mean_token_accuracy": 0.13001366779208184,
|
|
"num_tokens": 277736.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.125609493255615,
|
|
"epoch": 0.012007684918347743,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.6671,
|
|
"mean_token_accuracy": 0.1278264619410038,
|
|
"num_tokens": 289069.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.0424315452575685,
|
|
"epoch": 0.012487992315081652,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.6483,
|
|
"mean_token_accuracy": 0.1312246046960354,
|
|
"num_tokens": 300240.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.105067348480224,
|
|
"epoch": 0.012968299711815562,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.6951,
|
|
"mean_token_accuracy": 0.13201999366283418,
|
|
"num_tokens": 311698.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.135102462768555,
|
|
"epoch": 0.013448607108549471,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.652,
|
|
"mean_token_accuracy": 0.129649805277586,
|
|
"num_tokens": 322844.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.104988622665405,
|
|
"epoch": 0.013928914505283382,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.6544,
|
|
"mean_token_accuracy": 0.13054293021559715,
|
|
"num_tokens": 335092.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.036244344711304,
|
|
"epoch": 0.01440922190201729,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.6388,
|
|
"mean_token_accuracy": 0.13229672610759735,
|
|
"num_tokens": 347033.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.0629229068756105,
|
|
"epoch": 0.014889529298751201,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.6368,
|
|
"mean_token_accuracy": 0.12350815683603286,
|
|
"num_tokens": 358696.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.103863048553467,
|
|
"epoch": 0.01536983669548511,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.6527,
|
|
"mean_token_accuracy": 0.12880626693367958,
|
|
"num_tokens": 369390.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.0600316524505615,
|
|
"epoch": 0.01585014409221902,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.5942,
|
|
"mean_token_accuracy": 0.12720233500003814,
|
|
"num_tokens": 380540.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.0939164638519285,
|
|
"epoch": 0.01633045148895293,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.5928,
|
|
"mean_token_accuracy": 0.1307683579623699,
|
|
"num_tokens": 391243.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.08874363899231,
|
|
"epoch": 0.01681075888568684,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.5721,
|
|
"mean_token_accuracy": 0.1347414717078209,
|
|
"num_tokens": 403336.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.054573011398316,
|
|
"epoch": 0.01729106628242075,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.5372,
|
|
"mean_token_accuracy": 0.1348336383700371,
|
|
"num_tokens": 413886.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.076615619659424,
|
|
"epoch": 0.01777137367915466,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.6369,
|
|
"mean_token_accuracy": 0.12773096263408662,
|
|
"num_tokens": 425277.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.169283103942871,
|
|
"epoch": 0.01825168107588857,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.6817,
|
|
"mean_token_accuracy": 0.13388459086418153,
|
|
"num_tokens": 436868.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.070893096923828,
|
|
"epoch": 0.018731988472622477,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.5585,
|
|
"mean_token_accuracy": 0.13712915256619454,
|
|
"num_tokens": 448349.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.00331335067749,
|
|
"epoch": 0.01921229586935639,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.5787,
|
|
"mean_token_accuracy": 0.13295828625559808,
|
|
"num_tokens": 459447.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.017018413543701,
|
|
"epoch": 0.0196926032660903,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.5664,
|
|
"mean_token_accuracy": 0.13398413211107255,
|
|
"num_tokens": 470734.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.074815893173218,
|
|
"epoch": 0.020172910662824207,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.6675,
|
|
"mean_token_accuracy": 0.1243060939013958,
|
|
"num_tokens": 482015.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.051287984848022,
|
|
"epoch": 0.020653218059558116,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.5853,
|
|
"mean_token_accuracy": 0.12988396733999252,
|
|
"num_tokens": 493339.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.021688842773438,
|
|
"epoch": 0.021133525456292025,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.5124,
|
|
"mean_token_accuracy": 0.13405952081084252,
|
|
"num_tokens": 504924.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.087656021118164,
|
|
"epoch": 0.021613832853025938,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.5272,
|
|
"mean_token_accuracy": 0.12774203419685365,
|
|
"num_tokens": 516603.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 6.912145376205444,
|
|
"epoch": 0.022094140249759846,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.4572,
|
|
"mean_token_accuracy": 0.13284713625907899,
|
|
"num_tokens": 528347.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.009493589401245,
|
|
"epoch": 0.022574447646493755,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.5941,
|
|
"mean_token_accuracy": 0.13424275815486908,
|
|
"num_tokens": 539328.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.143858766555786,
|
|
"epoch": 0.023054755043227664,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.5522,
|
|
"mean_token_accuracy": 0.1398538187146187,
|
|
"num_tokens": 549297.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 6.905237674713135,
|
|
"epoch": 0.023535062439961577,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.545,
|
|
"mean_token_accuracy": 0.13216322883963585,
|
|
"num_tokens": 560306.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.09604697227478,
|
|
"epoch": 0.024015369836695485,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.6323,
|
|
"mean_token_accuracy": 0.1321306437253952,
|
|
"num_tokens": 571972.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.053035020828247,
|
|
"epoch": 0.024495677233429394,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.5172,
|
|
"mean_token_accuracy": 0.13756523206830024,
|
|
"num_tokens": 582962.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 6.858367395401001,
|
|
"epoch": 0.024975984630163303,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.5103,
|
|
"mean_token_accuracy": 0.13402715027332307,
|
|
"num_tokens": 597193.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.156196880340576,
|
|
"epoch": 0.025456292026897216,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.5892,
|
|
"mean_token_accuracy": 0.12901883125305175,
|
|
"num_tokens": 608982.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.014424085617065,
|
|
"epoch": 0.025936599423631124,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.6212,
|
|
"mean_token_accuracy": 0.12978230491280557,
|
|
"num_tokens": 619953.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.096269750595093,
|
|
"epoch": 0.026416906820365033,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.6321,
|
|
"mean_token_accuracy": 0.12898936718702317,
|
|
"num_tokens": 631039.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.03494119644165,
|
|
"epoch": 0.026897214217098942,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.6062,
|
|
"mean_token_accuracy": 0.13531998470425605,
|
|
"num_tokens": 642656.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 6.969197034835815,
|
|
"epoch": 0.027377521613832854,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.4944,
|
|
"mean_token_accuracy": 0.1461842603981495,
|
|
"num_tokens": 653748.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 6.980546951293945,
|
|
"epoch": 0.027857829010566763,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.4709,
|
|
"mean_token_accuracy": 0.1350526325404644,
|
|
"num_tokens": 665618.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 6.976346349716186,
|
|
"epoch": 0.028338136407300672,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.5103,
|
|
"mean_token_accuracy": 0.13303453028202056,
|
|
"num_tokens": 677329.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.96361517906189,
|
|
"epoch": 0.02881844380403458,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.5113,
|
|
"mean_token_accuracy": 0.1333675727248192,
|
|
"num_tokens": 688278.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.986789083480835,
|
|
"epoch": 0.029298751200768493,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.5677,
|
|
"mean_token_accuracy": 0.13771163299679756,
|
|
"num_tokens": 700739.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 6.966262865066528,
|
|
"epoch": 0.029779058597502402,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.5046,
|
|
"mean_token_accuracy": 0.13294478878378868,
|
|
"num_tokens": 712527.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.959698724746704,
|
|
"epoch": 0.03025936599423631,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.5456,
|
|
"mean_token_accuracy": 0.13097512274980544,
|
|
"num_tokens": 724514.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.038305854797363,
|
|
"epoch": 0.03073967339097022,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.5092,
|
|
"mean_token_accuracy": 0.13729717060923577,
|
|
"num_tokens": 735679.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 6.877438640594482,
|
|
"epoch": 0.03121998078770413,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.4986,
|
|
"mean_token_accuracy": 0.13833012878894807,
|
|
"num_tokens": 747896.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.030805873870849,
|
|
"epoch": 0.03170028818443804,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.5506,
|
|
"mean_token_accuracy": 0.13383892253041269,
|
|
"num_tokens": 759081.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 6.936169385910034,
|
|
"epoch": 0.03218059558117195,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.502,
|
|
"mean_token_accuracy": 0.1336835578083992,
|
|
"num_tokens": 770459.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.922156190872192,
|
|
"epoch": 0.03266090297790586,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.4557,
|
|
"mean_token_accuracy": 0.13467910513281822,
|
|
"num_tokens": 783960.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.945554304122925,
|
|
"epoch": 0.03314121037463977,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.5724,
|
|
"mean_token_accuracy": 0.13674034401774407,
|
|
"num_tokens": 795425.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 6.9888596534729,
|
|
"epoch": 0.03362151777137368,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.5241,
|
|
"mean_token_accuracy": 0.13427431806921958,
|
|
"num_tokens": 807536.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.014977931976318,
|
|
"epoch": 0.034101825168107586,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.5882,
|
|
"mean_token_accuracy": 0.13020211309194565,
|
|
"num_tokens": 818801.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 6.9366690158844,
|
|
"epoch": 0.0345821325648415,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.4507,
|
|
"mean_token_accuracy": 0.13554891422390938,
|
|
"num_tokens": 831497.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 6.8712386131286625,
|
|
"epoch": 0.03506243996157541,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.4424,
|
|
"mean_token_accuracy": 0.13640913739800453,
|
|
"num_tokens": 842491.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.009519624710083,
|
|
"epoch": 0.03554274735830932,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.523,
|
|
"mean_token_accuracy": 0.12829140126705169,
|
|
"num_tokens": 854560.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.867582225799561,
|
|
"epoch": 0.03602305475504323,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.4306,
|
|
"mean_token_accuracy": 0.14245563745498657,
|
|
"num_tokens": 866688.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.9899519920349125,
|
|
"epoch": 0.03650336215177714,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.5572,
|
|
"mean_token_accuracy": 0.12518782839179038,
|
|
"num_tokens": 879484.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.972244501113892,
|
|
"epoch": 0.036983669548511046,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.5485,
|
|
"mean_token_accuracy": 0.12844221517443657,
|
|
"num_tokens": 890807.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 6.982624101638794,
|
|
"epoch": 0.037463976945244955,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.4655,
|
|
"mean_token_accuracy": 0.1351318120956421,
|
|
"num_tokens": 901759.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.820593404769897,
|
|
"epoch": 0.037944284341978864,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.4239,
|
|
"mean_token_accuracy": 0.13946242481470109,
|
|
"num_tokens": 912212.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.997915410995484,
|
|
"epoch": 0.03842459173871278,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.5082,
|
|
"mean_token_accuracy": 0.1373220317065716,
|
|
"num_tokens": 923947.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.887757110595703,
|
|
"epoch": 0.03890489913544669,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.4624,
|
|
"mean_token_accuracy": 0.13495285138487817,
|
|
"num_tokens": 935732.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.860993576049805,
|
|
"epoch": 0.0393852065321806,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.4234,
|
|
"mean_token_accuracy": 0.13301072269678116,
|
|
"num_tokens": 948261.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.998539113998413,
|
|
"epoch": 0.039865513928914506,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.5408,
|
|
"mean_token_accuracy": 0.13510932326316832,
|
|
"num_tokens": 959574.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.97111144065857,
|
|
"epoch": 0.040345821325648415,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.6136,
|
|
"mean_token_accuracy": 0.12621866688132286,
|
|
"num_tokens": 970329.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.985296583175659,
|
|
"epoch": 0.040826128722382324,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.4701,
|
|
"mean_token_accuracy": 0.14006434381008148,
|
|
"num_tokens": 982037.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.804930353164673,
|
|
"epoch": 0.04130643611911623,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.4271,
|
|
"mean_token_accuracy": 0.13567045107483863,
|
|
"num_tokens": 994612.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.955875444412231,
|
|
"epoch": 0.04178674351585014,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.5617,
|
|
"mean_token_accuracy": 0.13497636914253236,
|
|
"num_tokens": 1005960.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.869253540039063,
|
|
"epoch": 0.04226705091258405,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.4174,
|
|
"mean_token_accuracy": 0.13668350800871848,
|
|
"num_tokens": 1017618.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.8875102519989015,
|
|
"epoch": 0.042747358309317966,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.48,
|
|
"mean_token_accuracy": 0.13301057890057563,
|
|
"num_tokens": 1029307.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.912690162658691,
|
|
"epoch": 0.043227665706051875,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.4972,
|
|
"mean_token_accuracy": 0.13038710951805116,
|
|
"num_tokens": 1042027.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.889484977722168,
|
|
"epoch": 0.043707973102785784,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.4819,
|
|
"mean_token_accuracy": 0.13361246138811111,
|
|
"num_tokens": 1053125.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.828107833862305,
|
|
"epoch": 0.04418828049951969,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.4905,
|
|
"mean_token_accuracy": 0.13674674183130264,
|
|
"num_tokens": 1064908.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.9115313529968265,
|
|
"epoch": 0.0446685878962536,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.3581,
|
|
"mean_token_accuracy": 0.14502883404493333,
|
|
"num_tokens": 1076328.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.896181726455689,
|
|
"epoch": 0.04514889529298751,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.5895,
|
|
"mean_token_accuracy": 0.1260202206671238,
|
|
"num_tokens": 1088469.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.823418760299683,
|
|
"epoch": 0.04562920268972142,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.391,
|
|
"mean_token_accuracy": 0.1406915917992592,
|
|
"num_tokens": 1099408.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.765524959564209,
|
|
"epoch": 0.04610951008645533,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.3342,
|
|
"mean_token_accuracy": 0.14521979689598083,
|
|
"num_tokens": 1111101.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.744671630859375,
|
|
"epoch": 0.046589817483189244,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.3479,
|
|
"mean_token_accuracy": 0.14791416078805925,
|
|
"num_tokens": 1122877.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.7991739273071286,
|
|
"epoch": 0.04707012487992315,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.454,
|
|
"mean_token_accuracy": 0.1279207557439804,
|
|
"num_tokens": 1133956.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.823109483718872,
|
|
"epoch": 0.04755043227665706,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.3641,
|
|
"mean_token_accuracy": 0.13983470499515532,
|
|
"num_tokens": 1146101.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.855337381362915,
|
|
"epoch": 0.04803073967339097,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.4502,
|
|
"mean_token_accuracy": 0.14883086159825326,
|
|
"num_tokens": 1157432.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.822028875350952,
|
|
"epoch": 0.04851104707012488,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.4439,
|
|
"mean_token_accuracy": 0.14014339298009873,
|
|
"num_tokens": 1167601.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.793749713897705,
|
|
"epoch": 0.04899135446685879,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.3433,
|
|
"mean_token_accuracy": 0.14071932584047317,
|
|
"num_tokens": 1178818.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.961408185958862,
|
|
"epoch": 0.0494716618635927,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.5897,
|
|
"mean_token_accuracy": 0.13712238147854805,
|
|
"num_tokens": 1189977.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.825463342666626,
|
|
"epoch": 0.049951969260326606,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.4273,
|
|
"mean_token_accuracy": 0.13879103511571883,
|
|
"num_tokens": 1201039.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.885947799682617,
|
|
"epoch": 0.05043227665706052,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.4418,
|
|
"mean_token_accuracy": 0.13869711384177208,
|
|
"num_tokens": 1212573.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.831294298171997,
|
|
"epoch": 0.05091258405379443,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.3877,
|
|
"mean_token_accuracy": 0.14377668723464013,
|
|
"num_tokens": 1223382.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.8336584091186525,
|
|
"epoch": 0.05139289145052834,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.4756,
|
|
"mean_token_accuracy": 0.1397824764251709,
|
|
"num_tokens": 1236501.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.854681539535522,
|
|
"epoch": 0.05187319884726225,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.4854,
|
|
"mean_token_accuracy": 0.1359047219157219,
|
|
"num_tokens": 1246798.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.818022680282593,
|
|
"epoch": 0.05235350624399616,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.3993,
|
|
"mean_token_accuracy": 0.1383517175912857,
|
|
"num_tokens": 1258182.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.725576877593994,
|
|
"epoch": 0.052833813640730067,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.3529,
|
|
"mean_token_accuracy": 0.13154633566737176,
|
|
"num_tokens": 1270273.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.824942541122437,
|
|
"epoch": 0.053314121037463975,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.4187,
|
|
"mean_token_accuracy": 0.13395696729421616,
|
|
"num_tokens": 1281136.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.798213529586792,
|
|
"epoch": 0.053794428434197884,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.388,
|
|
"mean_token_accuracy": 0.13719379529356956,
|
|
"num_tokens": 1294488.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.690643072128296,
|
|
"epoch": 0.05427473583093179,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.342,
|
|
"mean_token_accuracy": 0.13738902136683465,
|
|
"num_tokens": 1304113.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.811877346038818,
|
|
"epoch": 0.05475504322766571,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.1435349702835083,
|
|
"num_tokens": 1315417.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.705857038497925,
|
|
"epoch": 0.05523535062439962,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.3487,
|
|
"mean_token_accuracy": 0.13941997289657593,
|
|
"num_tokens": 1328084.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.830380821228028,
|
|
"epoch": 0.05571565802113353,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.4948,
|
|
"mean_token_accuracy": 0.13673060759902,
|
|
"num_tokens": 1338696.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.816842555999756,
|
|
"epoch": 0.056195965417867436,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.4362,
|
|
"mean_token_accuracy": 0.13864873573184014,
|
|
"num_tokens": 1350240.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.8044596195220945,
|
|
"epoch": 0.056676272814601344,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.3876,
|
|
"mean_token_accuracy": 0.13224058821797371,
|
|
"num_tokens": 1361720.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.702146100997925,
|
|
"epoch": 0.05715658021133525,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.388,
|
|
"mean_token_accuracy": 0.14646777287125587,
|
|
"num_tokens": 1373286.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.792327165603638,
|
|
"epoch": 0.05763688760806916,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.3357,
|
|
"mean_token_accuracy": 0.14013056233525276,
|
|
"num_tokens": 1384274.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.695337629318237,
|
|
"epoch": 0.05811719500480307,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.3866,
|
|
"mean_token_accuracy": 0.13806435391306876,
|
|
"num_tokens": 1395355.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.67833251953125,
|
|
"epoch": 0.05859750240153699,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.3185,
|
|
"mean_token_accuracy": 0.14838905334472657,
|
|
"num_tokens": 1406664.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.84452452659607,
|
|
"epoch": 0.059077809798270896,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.4734,
|
|
"mean_token_accuracy": 0.1365173079073429,
|
|
"num_tokens": 1418450.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.745831251144409,
|
|
"epoch": 0.059558117195004805,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.365,
|
|
"mean_token_accuracy": 0.1397569701075554,
|
|
"num_tokens": 1430048.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.811714601516724,
|
|
"epoch": 0.060038424591738714,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.4099,
|
|
"mean_token_accuracy": 0.13645492121577263,
|
|
"num_tokens": 1441820.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.656697416305542,
|
|
"epoch": 0.06051873198847262,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.2619,
|
|
"mean_token_accuracy": 0.14607831984758377,
|
|
"num_tokens": 1453209.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.677804946899414,
|
|
"epoch": 0.06099903938520653,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.2859,
|
|
"mean_token_accuracy": 0.139230377972126,
|
|
"num_tokens": 1465423.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.6918044090271,
|
|
"epoch": 0.06147934678194044,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.14577876925468444,
|
|
"num_tokens": 1476575.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.6395305633544925,
|
|
"epoch": 0.06195965417867435,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.2269,
|
|
"mean_token_accuracy": 0.14229501113295556,
|
|
"num_tokens": 1486932.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.6645488262176515,
|
|
"epoch": 0.06243996157540826,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.2634,
|
|
"mean_token_accuracy": 0.1412537418305874,
|
|
"num_tokens": 1498494.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.728798723220825,
|
|
"epoch": 0.06292026897214217,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.3314,
|
|
"mean_token_accuracy": 0.1367237947881222,
|
|
"num_tokens": 1509937.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.730763149261475,
|
|
"epoch": 0.06340057636887608,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.3493,
|
|
"mean_token_accuracy": 0.14772669598460197,
|
|
"num_tokens": 1519823.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.728877162933349,
|
|
"epoch": 0.06388088376560999,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.377,
|
|
"mean_token_accuracy": 0.1385086067020893,
|
|
"num_tokens": 1529943.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.646539354324341,
|
|
"epoch": 0.0643611911623439,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.218,
|
|
"mean_token_accuracy": 0.1462228536605835,
|
|
"num_tokens": 1540618.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.621165466308594,
|
|
"epoch": 0.06484149855907781,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.3349,
|
|
"mean_token_accuracy": 0.13347838148474694,
|
|
"num_tokens": 1553208.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.75033278465271,
|
|
"epoch": 0.06532180595581172,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.3079,
|
|
"mean_token_accuracy": 0.14778160005807878,
|
|
"num_tokens": 1563975.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.730441284179688,
|
|
"epoch": 0.06580211335254563,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.3601,
|
|
"mean_token_accuracy": 0.13537456542253495,
|
|
"num_tokens": 1575998.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.659586429595947,
|
|
"epoch": 0.06628242074927954,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.263,
|
|
"mean_token_accuracy": 0.14849890321493148,
|
|
"num_tokens": 1586041.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.605801343917847,
|
|
"epoch": 0.06676272814601344,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.324,
|
|
"mean_token_accuracy": 0.14218652099370957,
|
|
"num_tokens": 1597531.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.669734811782837,
|
|
"epoch": 0.06724303554274735,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.3116,
|
|
"mean_token_accuracy": 0.13976099193096161,
|
|
"num_tokens": 1609255.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.609857988357544,
|
|
"epoch": 0.06772334293948126,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.14360181987285614,
|
|
"num_tokens": 1621098.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.6083897113800045,
|
|
"epoch": 0.06820365033621517,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.189,
|
|
"mean_token_accuracy": 0.15515244603157044,
|
|
"num_tokens": 1631941.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.57919979095459,
|
|
"epoch": 0.0686839577329491,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.2074,
|
|
"mean_token_accuracy": 0.14852219969034194,
|
|
"num_tokens": 1643117.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.576744127273559,
|
|
"epoch": 0.069164265129683,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.1395713485777378,
|
|
"num_tokens": 1653595.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.663236331939697,
|
|
"epoch": 0.06964457252641691,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.2792,
|
|
"mean_token_accuracy": 0.14607299417257308,
|
|
"num_tokens": 1664495.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.556261014938355,
|
|
"epoch": 0.07012487992315082,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.2639,
|
|
"mean_token_accuracy": 0.1435217887163162,
|
|
"num_tokens": 1674923.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.618684720993042,
|
|
"epoch": 0.07060518731988473,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.1667,
|
|
"mean_token_accuracy": 0.1526644468307495,
|
|
"num_tokens": 1685904.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.627186965942383,
|
|
"epoch": 0.07108549471661864,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.3877,
|
|
"mean_token_accuracy": 0.13355778381228448,
|
|
"num_tokens": 1699133.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.548422527313233,
|
|
"epoch": 0.07156580211335255,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.2018,
|
|
"mean_token_accuracy": 0.14151064530014992,
|
|
"num_tokens": 1711559.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.550561428070068,
|
|
"epoch": 0.07204610951008646,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.1509994685649872,
|
|
"num_tokens": 1722526.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.532330465316773,
|
|
"epoch": 0.07252641690682037,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.1889,
|
|
"mean_token_accuracy": 0.14655965566635132,
|
|
"num_tokens": 1734261.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.53015832901001,
|
|
"epoch": 0.07300672430355427,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.1803,
|
|
"mean_token_accuracy": 0.15340202897787095,
|
|
"num_tokens": 1745151.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.69319715499878,
|
|
"epoch": 0.07348703170028818,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3355,
|
|
"mean_token_accuracy": 0.1429338976740837,
|
|
"num_tokens": 1755463.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.623394536972046,
|
|
"epoch": 0.07396733909702209,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.13968928754329682,
|
|
"num_tokens": 1767717.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.437202119827271,
|
|
"epoch": 0.074447646493756,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.1355,
|
|
"mean_token_accuracy": 0.15134122371673583,
|
|
"num_tokens": 1779115.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.419523668289185,
|
|
"epoch": 0.07492795389048991,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.087,
|
|
"mean_token_accuracy": 0.15281283408403395,
|
|
"num_tokens": 1789644.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.6132158756256105,
|
|
"epoch": 0.07540826128722382,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.14345607832074164,
|
|
"num_tokens": 1800606.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.524192380905151,
|
|
"epoch": 0.07588856868395773,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.301,
|
|
"mean_token_accuracy": 0.13897362276911734,
|
|
"num_tokens": 1812168.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.73820424079895,
|
|
"epoch": 0.07636887608069164,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.2386,
|
|
"mean_token_accuracy": 0.14347319155931473,
|
|
"num_tokens": 1823830.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.445359086990356,
|
|
"epoch": 0.07684918347742556,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.2403,
|
|
"mean_token_accuracy": 0.1467433527112007,
|
|
"num_tokens": 1835611.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.597848510742187,
|
|
"epoch": 0.07732949087415947,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.13762886747717856,
|
|
"num_tokens": 1847036.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.562679290771484,
|
|
"epoch": 0.07780979827089338,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.2378,
|
|
"mean_token_accuracy": 0.14037195593118668,
|
|
"num_tokens": 1857476.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.5669573783874515,
|
|
"epoch": 0.07829010566762729,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2621,
|
|
"mean_token_accuracy": 0.14760917276144028,
|
|
"num_tokens": 1869073.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.387801313400269,
|
|
"epoch": 0.0787704130643612,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.1509813189506531,
|
|
"num_tokens": 1880439.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.699515724182129,
|
|
"epoch": 0.0792507204610951,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.2976,
|
|
"mean_token_accuracy": 0.14118361324071885,
|
|
"num_tokens": 1891600.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.5128673076629635,
|
|
"epoch": 0.07973102785782901,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2569,
|
|
"mean_token_accuracy": 0.14543531611561775,
|
|
"num_tokens": 1903126.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.672891998291016,
|
|
"epoch": 0.08021133525456292,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.226,
|
|
"mean_token_accuracy": 0.14782591313123702,
|
|
"num_tokens": 1913913.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.366758394241333,
|
|
"epoch": 0.08069164265129683,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.1501,
|
|
"mean_token_accuracy": 0.1501932203769684,
|
|
"num_tokens": 1924961.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.692445278167725,
|
|
"epoch": 0.08117195004803074,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.2407,
|
|
"mean_token_accuracy": 0.1381278119981289,
|
|
"num_tokens": 1936773.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.406199932098389,
|
|
"epoch": 0.08165225744476465,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.1643,
|
|
"mean_token_accuracy": 0.1459251821041107,
|
|
"num_tokens": 1948190.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.452398300170898,
|
|
"epoch": 0.08213256484149856,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.1575,
|
|
"mean_token_accuracy": 0.14858585894107817,
|
|
"num_tokens": 1960038.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.57236967086792,
|
|
"epoch": 0.08261287223823247,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.2384,
|
|
"mean_token_accuracy": 0.14626160115003586,
|
|
"num_tokens": 1970535.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.537123394012451,
|
|
"epoch": 0.08309317963496637,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.142296252399683,
|
|
"num_tokens": 1981386.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.4313184261322025,
|
|
"epoch": 0.08357348703170028,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.1375,
|
|
"mean_token_accuracy": 0.14900052845478057,
|
|
"num_tokens": 1993196.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.4812110424041744,
|
|
"epoch": 0.08405379442843419,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.1562,
|
|
"mean_token_accuracy": 0.15512351393699647,
|
|
"num_tokens": 2004756.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.437265253067016,
|
|
"epoch": 0.0845341018251681,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.1392,
|
|
"mean_token_accuracy": 0.14693072885274888,
|
|
"num_tokens": 2016020.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.458638095855713,
|
|
"epoch": 0.08501440922190202,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.1858,
|
|
"mean_token_accuracy": 0.14666839689016342,
|
|
"num_tokens": 2027747.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.551916837692261,
|
|
"epoch": 0.08549471661863593,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.1604,
|
|
"mean_token_accuracy": 0.14383722916245462,
|
|
"num_tokens": 2038841.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.44727840423584,
|
|
"epoch": 0.08597502401536984,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.14256930723786354,
|
|
"num_tokens": 2049905.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.512820863723755,
|
|
"epoch": 0.08645533141210375,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2817,
|
|
"mean_token_accuracy": 0.14085745438933372,
|
|
"num_tokens": 2062492.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.474342775344849,
|
|
"epoch": 0.08693563880883766,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.216,
|
|
"mean_token_accuracy": 0.14198037534952163,
|
|
"num_tokens": 2073840.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.469565916061401,
|
|
"epoch": 0.08741594620557157,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.14328503012657165,
|
|
"num_tokens": 2085720.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.508474731445313,
|
|
"epoch": 0.08789625360230548,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2079,
|
|
"mean_token_accuracy": 0.14646697416901588,
|
|
"num_tokens": 2096649.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.526723051071167,
|
|
"epoch": 0.08837656099903939,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.2087,
|
|
"mean_token_accuracy": 0.14670456051826478,
|
|
"num_tokens": 2109030.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.422917222976684,
|
|
"epoch": 0.0888568683957733,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.1155,
|
|
"mean_token_accuracy": 0.15043116360902786,
|
|
"num_tokens": 2121384.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.429614877700805,
|
|
"epoch": 0.0893371757925072,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.0734,
|
|
"mean_token_accuracy": 0.15336936861276626,
|
|
"num_tokens": 2131377.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.468717241287232,
|
|
"epoch": 0.08981748318924111,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2611,
|
|
"mean_token_accuracy": 0.14346477389335632,
|
|
"num_tokens": 2142364.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.449568080902099,
|
|
"epoch": 0.09029779058597502,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.14927371144294738,
|
|
"num_tokens": 2153040.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.434846210479736,
|
|
"epoch": 0.09077809798270893,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.1895,
|
|
"mean_token_accuracy": 0.15058233961462975,
|
|
"num_tokens": 2165571.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.456413507461548,
|
|
"epoch": 0.09125840537944284,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.1612,
|
|
"mean_token_accuracy": 0.14620548188686372,
|
|
"num_tokens": 2177241.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.455846166610717,
|
|
"epoch": 0.09173871277617675,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.1925,
|
|
"mean_token_accuracy": 0.13922726288437842,
|
|
"num_tokens": 2187475.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.435314750671386,
|
|
"epoch": 0.09221902017291066,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2183,
|
|
"mean_token_accuracy": 0.1472764365375042,
|
|
"num_tokens": 2198185.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.411659860610962,
|
|
"epoch": 0.09269932756964457,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.1554,
|
|
"mean_token_accuracy": 0.14865822941064835,
|
|
"num_tokens": 2210404.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.521021556854248,
|
|
"epoch": 0.09317963496637849,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.1382,
|
|
"mean_token_accuracy": 0.14820332527160646,
|
|
"num_tokens": 2222188.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.401497077941895,
|
|
"epoch": 0.0936599423631124,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.1825,
|
|
"mean_token_accuracy": 0.1503289483487606,
|
|
"num_tokens": 2233418.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.386258792877197,
|
|
"epoch": 0.0941402497598463,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.1549,
|
|
"mean_token_accuracy": 0.15336488783359528,
|
|
"num_tokens": 2245053.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.497596883773804,
|
|
"epoch": 0.09462055715658022,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.1799,
|
|
"mean_token_accuracy": 0.1518462046980858,
|
|
"num_tokens": 2256375.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.297069692611695,
|
|
"epoch": 0.09510086455331412,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.0222,
|
|
"mean_token_accuracy": 0.1536286234855652,
|
|
"num_tokens": 2267074.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.3477600574493405,
|
|
"epoch": 0.09558117195004803,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.15113484859466553,
|
|
"num_tokens": 2277168.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.337840461730957,
|
|
"epoch": 0.09606147934678194,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.0562,
|
|
"mean_token_accuracy": 0.15290841460227966,
|
|
"num_tokens": 2288178.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.316500282287597,
|
|
"epoch": 0.09654178674351585,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999983283737,
|
|
"loss": 6.0619,
|
|
"mean_token_accuracy": 0.1515717551112175,
|
|
"num_tokens": 2299765.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.519514703750611,
|
|
"epoch": 0.09702209414024976,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999999915373924,
|
|
"loss": 6.1835,
|
|
"mean_token_accuracy": 0.13907498270273208,
|
|
"num_tokens": 2312047.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.364095211029053,
|
|
"epoch": 0.09750240153698367,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999999795225793,
|
|
"loss": 6.1611,
|
|
"mean_token_accuracy": 0.14061366766691208,
|
|
"num_tokens": 2324118.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.4445971012115475,
|
|
"epoch": 0.09798270893371758,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999999622839347,
|
|
"loss": 6.1611,
|
|
"mean_token_accuracy": 0.14967067837715148,
|
|
"num_tokens": 2335171.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.398542642593384,
|
|
"epoch": 0.09846301633045149,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999398214593,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.1492784783244133,
|
|
"num_tokens": 2346338.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.369733762741089,
|
|
"epoch": 0.0989433237271854,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999121351532,
|
|
"loss": 6.1011,
|
|
"mean_token_accuracy": 0.15191911309957504,
|
|
"num_tokens": 2357185.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.378099775314331,
|
|
"epoch": 0.0994236311239193,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999998792250173,
|
|
"loss": 6.0369,
|
|
"mean_token_accuracy": 0.15464141294360162,
|
|
"num_tokens": 2368494.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.379990863800049,
|
|
"epoch": 0.09990393852065321,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999998410910524,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.14129094332456588,
|
|
"num_tokens": 2380800.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.467003870010376,
|
|
"epoch": 0.10038424591738712,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999997977332592,
|
|
"loss": 6.1819,
|
|
"mean_token_accuracy": 0.1439610406756401,
|
|
"num_tokens": 2391753.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.27177791595459,
|
|
"epoch": 0.10086455331412104,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999997491516389,
|
|
"loss": 6.0646,
|
|
"mean_token_accuracy": 0.14684219062328338,
|
|
"num_tokens": 2403324.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.4170433521270756,
|
|
"epoch": 0.10134486071085495,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999996953461925,
|
|
"loss": 6.1568,
|
|
"mean_token_accuracy": 0.1471158519387245,
|
|
"num_tokens": 2414873.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.226349878311157,
|
|
"epoch": 0.10182516810758886,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999996363169212,
|
|
"loss": 5.9522,
|
|
"mean_token_accuracy": 0.15969930738210678,
|
|
"num_tokens": 2425308.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.280011129379273,
|
|
"epoch": 0.10230547550432277,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999995720638266,
|
|
"loss": 5.9956,
|
|
"mean_token_accuracy": 0.15745754390954972,
|
|
"num_tokens": 2436835.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.318831586837769,
|
|
"epoch": 0.10278578290105668,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00049999950258691,
|
|
"loss": 6.1016,
|
|
"mean_token_accuracy": 0.15324254631996154,
|
|
"num_tokens": 2446798.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.259381628036499,
|
|
"epoch": 0.10326609029779059,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999994278861731,
|
|
"loss": 6.0097,
|
|
"mean_token_accuracy": 0.15251461267471314,
|
|
"num_tokens": 2457308.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.345122861862182,
|
|
"epoch": 0.1037463976945245,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999993479616175,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.14187726974487305,
|
|
"num_tokens": 2468917.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.341993236541748,
|
|
"epoch": 0.1042267050912584,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999992628132451,
|
|
"loss": 6.0947,
|
|
"mean_token_accuracy": 0.145965027064085,
|
|
"num_tokens": 2481363.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.322693538665772,
|
|
"epoch": 0.10470701248799232,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999991724410582,
|
|
"loss": 6.0875,
|
|
"mean_token_accuracy": 0.15120186507701874,
|
|
"num_tokens": 2493082.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.3057647228240965,
|
|
"epoch": 0.10518731988472622,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999990768450583,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.15195624977350236,
|
|
"num_tokens": 2503849.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.302676057815551,
|
|
"epoch": 0.10566762728146013,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999989760252482,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.15190254151821136,
|
|
"num_tokens": 2514528.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.300235176086426,
|
|
"epoch": 0.10614793467819404,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004999988699816299,
|
|
"loss": 6.0734,
|
|
"mean_token_accuracy": 0.15657310485839843,
|
|
"num_tokens": 2524971.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.231389999389648,
|
|
"epoch": 0.10662824207492795,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999987587142058,
|
|
"loss": 5.9787,
|
|
"mean_token_accuracy": 0.1494237408041954,
|
|
"num_tokens": 2535674.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.4110383033752445,
|
|
"epoch": 0.10710854947166186,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999986422229789,
|
|
"loss": 6.2173,
|
|
"mean_token_accuracy": 0.14188248962163924,
|
|
"num_tokens": 2547108.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.270652484893799,
|
|
"epoch": 0.10758885686839577,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999985205079514,
|
|
"loss": 6.0312,
|
|
"mean_token_accuracy": 0.14654332846403123,
|
|
"num_tokens": 2559474.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.178351354598999,
|
|
"epoch": 0.10806916426512968,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999983935691265,
|
|
"loss": 5.877,
|
|
"mean_token_accuracy": 0.16631512492895126,
|
|
"num_tokens": 2571264.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.240466594696045,
|
|
"epoch": 0.10854947166186359,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499998261406507,
|
|
"loss": 6.0402,
|
|
"mean_token_accuracy": 0.1550907276570797,
|
|
"num_tokens": 2583731.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.455864334106446,
|
|
"epoch": 0.10902977905859751,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999981240200958,
|
|
"loss": 6.0865,
|
|
"mean_token_accuracy": 0.15334258675575257,
|
|
"num_tokens": 2595497.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.156699085235596,
|
|
"epoch": 0.10951008645533142,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999979814098966,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.1544922299683094,
|
|
"num_tokens": 2607358.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.313141107559204,
|
|
"epoch": 0.10999039385206533,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999978335759121,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.16003676876425743,
|
|
"num_tokens": 2618936.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.253233003616333,
|
|
"epoch": 0.11047070124879924,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999976805181461,
|
|
"loss": 6.1273,
|
|
"mean_token_accuracy": 0.1448728360235691,
|
|
"num_tokens": 2631840.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.283588409423828,
|
|
"epoch": 0.11095100864553314,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499997522236602,
|
|
"loss": 6.0696,
|
|
"mean_token_accuracy": 0.15917213410139083,
|
|
"num_tokens": 2642412.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.2728049755096436,
|
|
"epoch": 0.11143131604226705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999973587312837,
|
|
"loss": 6.0413,
|
|
"mean_token_accuracy": 0.15381678342819213,
|
|
"num_tokens": 2653890.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.398951053619385,
|
|
"epoch": 0.11191162343900096,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999971900021947,
|
|
"loss": 6.0976,
|
|
"mean_token_accuracy": 0.1579543687403202,
|
|
"num_tokens": 2664888.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.157506227493286,
|
|
"epoch": 0.11239193083573487,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999970160493391,
|
|
"loss": 6.0067,
|
|
"mean_token_accuracy": 0.1552426412701607,
|
|
"num_tokens": 2675550.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.209622144699097,
|
|
"epoch": 0.11287223823246878,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999968368727209,
|
|
"loss": 6.01,
|
|
"mean_token_accuracy": 0.15791884660720826,
|
|
"num_tokens": 2688022.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.314128446578979,
|
|
"epoch": 0.11335254562920269,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999966524723442,
|
|
"loss": 6.0035,
|
|
"mean_token_accuracy": 0.15661349296569824,
|
|
"num_tokens": 2698737.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.17528281211853,
|
|
"epoch": 0.1138328530259366,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999964628482135,
|
|
"loss": 5.9803,
|
|
"mean_token_accuracy": 0.1625732421875,
|
|
"num_tokens": 2709844.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.311813545227051,
|
|
"epoch": 0.1143131604226705,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999962680003328,
|
|
"loss": 6.0243,
|
|
"mean_token_accuracy": 0.15992799401283264,
|
|
"num_tokens": 2720273.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.231012916564941,
|
|
"epoch": 0.11479346781940442,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499996067928707,
|
|
"loss": 6.0555,
|
|
"mean_token_accuracy": 0.1537340298295021,
|
|
"num_tokens": 2731354.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.250294923782349,
|
|
"epoch": 0.11527377521613832,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999958626333406,
|
|
"loss": 6.0383,
|
|
"mean_token_accuracy": 0.15496493577957154,
|
|
"num_tokens": 2742966.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.222562694549561,
|
|
"epoch": 0.11575408261287223,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999956521142383,
|
|
"loss": 5.9677,
|
|
"mean_token_accuracy": 0.1614091530442238,
|
|
"num_tokens": 2755010.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.238761901855469,
|
|
"epoch": 0.11623439000960614,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999954363714051,
|
|
"loss": 5.9963,
|
|
"mean_token_accuracy": 0.1529179558157921,
|
|
"num_tokens": 2766176.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.375168800354004,
|
|
"epoch": 0.11671469740634005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999952154048459,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.1510852135717869,
|
|
"num_tokens": 2777861.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.179434299468994,
|
|
"epoch": 0.11719500480307397,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499994989214566,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.15724676698446274,
|
|
"num_tokens": 2788725.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.156388998031616,
|
|
"epoch": 0.11767531219980788,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999947578005705,
|
|
"loss": 5.9829,
|
|
"mean_token_accuracy": 0.1558725953102112,
|
|
"num_tokens": 2801613.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.306823587417602,
|
|
"epoch": 0.11815561959654179,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999945211628648,
|
|
"loss": 6.0591,
|
|
"mean_token_accuracy": 0.15092146396636963,
|
|
"num_tokens": 2812474.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.149747133255005,
|
|
"epoch": 0.1186359269932757,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999942793014544,
|
|
"loss": 5.9613,
|
|
"mean_token_accuracy": 0.15863570123910903,
|
|
"num_tokens": 2823178.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.148617744445801,
|
|
"epoch": 0.11911623439000961,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499994032216345,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.15689361244440078,
|
|
"num_tokens": 2836486.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.2577982425689695,
|
|
"epoch": 0.11959654178674352,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999937799075422,
|
|
"loss": 6.0325,
|
|
"mean_token_accuracy": 0.1582626670598984,
|
|
"num_tokens": 2847902.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.061917066574097,
|
|
"epoch": 0.12007684918347743,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499993522375052,
|
|
"loss": 5.9155,
|
|
"mean_token_accuracy": 0.15855048298835756,
|
|
"num_tokens": 2859991.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.334481048583984,
|
|
"epoch": 0.12055715658021134,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999932596188802,
|
|
"loss": 6.103,
|
|
"mean_token_accuracy": 0.14992666617035866,
|
|
"num_tokens": 2870269.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.16114387512207,
|
|
"epoch": 0.12103746397694524,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999929916390331,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.15265119820833206,
|
|
"num_tokens": 2882191.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.185744333267212,
|
|
"epoch": 0.12151777137367915,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999927184355169,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.15251912623643876,
|
|
"num_tokens": 2892775.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.141828775405884,
|
|
"epoch": 0.12199807877041306,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999924400083377,
|
|
"loss": 5.9617,
|
|
"mean_token_accuracy": 0.15787012949585916,
|
|
"num_tokens": 2904750.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.286509704589844,
|
|
"epoch": 0.12247838616714697,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999921563575022,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.1519160158932209,
|
|
"num_tokens": 2916150.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.238752746582032,
|
|
"epoch": 0.12295869356388088,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999918674830169,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.15371812880039215,
|
|
"num_tokens": 2928452.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.158025789260864,
|
|
"epoch": 0.12343900096061479,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999915733848886,
|
|
"loss": 5.999,
|
|
"mean_token_accuracy": 0.15188550055027009,
|
|
"num_tokens": 2940577.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.150114059448242,
|
|
"epoch": 0.1239193083573487,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499991274063124,
|
|
"loss": 5.9678,
|
|
"mean_token_accuracy": 0.1559542365372181,
|
|
"num_tokens": 2952302.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.235889863967896,
|
|
"epoch": 0.12439961575408261,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999909695177301,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.15738558918237686,
|
|
"num_tokens": 2964611.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.222271394729614,
|
|
"epoch": 0.12487992315081652,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499990659748714,
|
|
"loss": 6.0135,
|
|
"mean_token_accuracy": 0.1533857174217701,
|
|
"num_tokens": 2975668.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.2896746635437015,
|
|
"epoch": 0.12536023054755044,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999903447560828,
|
|
"loss": 6.0706,
|
|
"mean_token_accuracy": 0.15294826924800872,
|
|
"num_tokens": 2987303.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.250040912628174,
|
|
"epoch": 0.12584053794428435,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999900245398439,
|
|
"loss": 5.9698,
|
|
"mean_token_accuracy": 0.15828934013843537,
|
|
"num_tokens": 3000400.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.187452220916748,
|
|
"epoch": 0.12632084534101826,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999896991000047,
|
|
"loss": 5.9104,
|
|
"mean_token_accuracy": 0.1555943712592125,
|
|
"num_tokens": 3012336.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.189295625686645,
|
|
"epoch": 0.12680115273775217,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999893684365729,
|
|
"loss": 5.9769,
|
|
"mean_token_accuracy": 0.15539684668183326,
|
|
"num_tokens": 3023004.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.154639005661011,
|
|
"epoch": 0.12728146013448607,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999890325495559,
|
|
"loss": 6.0444,
|
|
"mean_token_accuracy": 0.15357957929372787,
|
|
"num_tokens": 3035147.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.1711499214172365,
|
|
"epoch": 0.12776176753121998,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999886914389617,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.15838308334350587,
|
|
"num_tokens": 3045611.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.135772943496704,
|
|
"epoch": 0.1282420749279539,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999883451047981,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.1591949164867401,
|
|
"num_tokens": 3056420.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.1266110897064205,
|
|
"epoch": 0.1287223823246878,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999879935470733,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.16175246238708496,
|
|
"num_tokens": 3068770.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.193431091308594,
|
|
"epoch": 0.1292026897214217,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999876367657954,
|
|
"loss": 6.0132,
|
|
"mean_token_accuracy": 0.14821962267160416,
|
|
"num_tokens": 3080806.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.241663312911987,
|
|
"epoch": 0.12968299711815562,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999872747609725,
|
|
"loss": 6.0259,
|
|
"mean_token_accuracy": 0.15041830465197564,
|
|
"num_tokens": 3091769.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.161892700195312,
|
|
"epoch": 0.13016330451488953,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999869075326132,
|
|
"loss": 5.9515,
|
|
"mean_token_accuracy": 0.15427336543798448,
|
|
"num_tokens": 3103121.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.167838478088379,
|
|
"epoch": 0.13064361191162344,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499986535080726,
|
|
"loss": 5.9257,
|
|
"mean_token_accuracy": 0.1637582778930664,
|
|
"num_tokens": 3115606.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.070174360275269,
|
|
"epoch": 0.13112391930835735,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999861574053196,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.15959180593490602,
|
|
"num_tokens": 3127961.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.0476092338562015,
|
|
"epoch": 0.13160422670509125,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999857745064027,
|
|
"loss": 5.8378,
|
|
"mean_token_accuracy": 0.16003572195768356,
|
|
"num_tokens": 3138316.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.09722580909729,
|
|
"epoch": 0.13208453410182516,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499985386383984,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.16383897215127946,
|
|
"num_tokens": 3150818.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.173034286499023,
|
|
"epoch": 0.13256484149855907,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999849930380729,
|
|
"loss": 5.9896,
|
|
"mean_token_accuracy": 0.15335828065872192,
|
|
"num_tokens": 3162066.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.091350126266479,
|
|
"epoch": 0.13304514889529298,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999845944686781,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.15436633825302123,
|
|
"num_tokens": 3172209.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.033679103851318,
|
|
"epoch": 0.1335254562920269,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999841906758093,
|
|
"loss": 5.7728,
|
|
"mean_token_accuracy": 0.17072101235389708,
|
|
"num_tokens": 3183248.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.115644407272339,
|
|
"epoch": 0.1340057636887608,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999837816594757,
|
|
"loss": 5.8801,
|
|
"mean_token_accuracy": 0.1629835158586502,
|
|
"num_tokens": 3194748.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.074833250045776,
|
|
"epoch": 0.1344860710854947,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999833674196865,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.16948780417442322,
|
|
"num_tokens": 3205669.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.105074739456176,
|
|
"epoch": 0.13496637848222862,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999829479564518,
|
|
"loss": 5.9361,
|
|
"mean_token_accuracy": 0.1520385757088661,
|
|
"num_tokens": 3216035.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.140946578979492,
|
|
"epoch": 0.13544668587896252,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499982523269781,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.15891541689634323,
|
|
"num_tokens": 3227192.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.1240339279174805,
|
|
"epoch": 0.13592699327569643,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999820933596842,
|
|
"loss": 5.9534,
|
|
"mean_token_accuracy": 0.1581968516111374,
|
|
"num_tokens": 3240237.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.090185928344726,
|
|
"epoch": 0.13640730067243034,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499981658226171,
|
|
"loss": 5.8259,
|
|
"mean_token_accuracy": 0.16865789741277695,
|
|
"num_tokens": 3251963.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.063898086547852,
|
|
"epoch": 0.13688760806916425,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499981217869252,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.1649617299437523,
|
|
"num_tokens": 3263101.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.1431561470031735,
|
|
"epoch": 0.1373679154658982,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499980772288937,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.16629794836044312,
|
|
"num_tokens": 3275100.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.106657552719116,
|
|
"epoch": 0.1378482228626321,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999803214852367,
|
|
"loss": 5.9272,
|
|
"mean_token_accuracy": 0.15512363463640214,
|
|
"num_tokens": 3287025.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.167088365554809,
|
|
"epoch": 0.138328530259366,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999798654581613,
|
|
"loss": 5.9322,
|
|
"mean_token_accuracy": 0.15951334238052367,
|
|
"num_tokens": 3299867.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.086508417129517,
|
|
"epoch": 0.13880883765609991,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999794042077214,
|
|
"loss": 5.8733,
|
|
"mean_token_accuracy": 0.15924615412950516,
|
|
"num_tokens": 3311183.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.092142724990845,
|
|
"epoch": 0.13928914505283382,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999789377339279,
|
|
"loss": 5.9375,
|
|
"mean_token_accuracy": 0.1590658202767372,
|
|
"num_tokens": 3322247.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.110898780822754,
|
|
"epoch": 0.13976945244956773,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999784660367915,
|
|
"loss": 5.8514,
|
|
"mean_token_accuracy": 0.16008831560611725,
|
|
"num_tokens": 3333369.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.026701641082764,
|
|
"epoch": 0.14024975984630164,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999779891163231,
|
|
"loss": 5.8907,
|
|
"mean_token_accuracy": 0.1609531357884407,
|
|
"num_tokens": 3345876.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.066957569122314,
|
|
"epoch": 0.14073006724303555,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999775069725339,
|
|
"loss": 5.778,
|
|
"mean_token_accuracy": 0.16528390794992448,
|
|
"num_tokens": 3357323.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.024584341049194,
|
|
"epoch": 0.14121037463976946,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499977019605435,
|
|
"loss": 5.8666,
|
|
"mean_token_accuracy": 0.1610391244292259,
|
|
"num_tokens": 3367689.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.971542263031006,
|
|
"epoch": 0.14169068203650337,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999765270150378,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.16424132734537125,
|
|
"num_tokens": 3379472.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.139827394485474,
|
|
"epoch": 0.14217098943323728,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999760292013536,
|
|
"loss": 5.8726,
|
|
"mean_token_accuracy": 0.15778491795063018,
|
|
"num_tokens": 3390929.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.217739486694336,
|
|
"epoch": 0.14265129682997119,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999755261643941,
|
|
"loss": 5.8688,
|
|
"mean_token_accuracy": 0.16537885516881942,
|
|
"num_tokens": 3401242.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.921372890472412,
|
|
"epoch": 0.1431316042267051,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999750179041709,
|
|
"loss": 5.8606,
|
|
"mean_token_accuracy": 0.16257801353931428,
|
|
"num_tokens": 3411169.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.042217111587524,
|
|
"epoch": 0.143611911623439,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999745044206959,
|
|
"loss": 5.6965,
|
|
"mean_token_accuracy": 0.16992068588733672,
|
|
"num_tokens": 3423265.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.984377431869507,
|
|
"epoch": 0.1440922190201729,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999739857139809,
|
|
"loss": 5.8066,
|
|
"mean_token_accuracy": 0.1671621523797512,
|
|
"num_tokens": 3434793.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 5.961929225921631,
|
|
"epoch": 0.14457252641690682,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499973461784038,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.17664009779691697,
|
|
"num_tokens": 3445732.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.045278692245484,
|
|
"epoch": 0.14505283381364073,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999729326308792,
|
|
"loss": 5.9086,
|
|
"mean_token_accuracy": 0.16037625521421434,
|
|
"num_tokens": 3457090.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.174110746383667,
|
|
"epoch": 0.14553314121037464,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499972398254517,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.15567544400691985,
|
|
"num_tokens": 3468087.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.075960445404053,
|
|
"epoch": 0.14601344860710855,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499971858654964,
|
|
"loss": 5.8393,
|
|
"mean_token_accuracy": 0.16277710646390914,
|
|
"num_tokens": 3478820.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.011015510559082,
|
|
"epoch": 0.14649375600384246,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999713138322321,
|
|
"loss": 5.864,
|
|
"mean_token_accuracy": 0.15902443826198578,
|
|
"num_tokens": 3489878.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.096222686767578,
|
|
"epoch": 0.14697406340057637,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999707637863346,
|
|
"loss": 5.849,
|
|
"mean_token_accuracy": 0.16232544481754302,
|
|
"num_tokens": 3500944.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.966727018356323,
|
|
"epoch": 0.14745437079731027,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999702085172838,
|
|
"loss": 5.8314,
|
|
"mean_token_accuracy": 0.16640263050794601,
|
|
"num_tokens": 3511383.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.095454359054566,
|
|
"epoch": 0.14793467819404418,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999696480250929,
|
|
"loss": 5.921,
|
|
"mean_token_accuracy": 0.1610638305544853,
|
|
"num_tokens": 3523300.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.080443000793457,
|
|
"epoch": 0.1484149855907781,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999690823097747,
|
|
"loss": 5.8507,
|
|
"mean_token_accuracy": 0.15561971068382263,
|
|
"num_tokens": 3534371.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.039649724960327,
|
|
"epoch": 0.148895292987512,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999685113713426,
|
|
"loss": 5.8226,
|
|
"mean_token_accuracy": 0.16583748608827592,
|
|
"num_tokens": 3544847.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.0535636901855465,
|
|
"epoch": 0.1493756003842459,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999679352098096,
|
|
"loss": 5.7929,
|
|
"mean_token_accuracy": 0.16670662462711333,
|
|
"num_tokens": 3555859.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.992221164703369,
|
|
"epoch": 0.14985590778097982,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999673538251891,
|
|
"loss": 5.8236,
|
|
"mean_token_accuracy": 0.166217839717865,
|
|
"num_tokens": 3568283.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.987648916244507,
|
|
"epoch": 0.15033621517771373,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999667672174947,
|
|
"loss": 5.8857,
|
|
"mean_token_accuracy": 0.15877313315868377,
|
|
"num_tokens": 3581442.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.158979511260986,
|
|
"epoch": 0.15081652257444764,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00049996617538674,
|
|
"loss": 5.9279,
|
|
"mean_token_accuracy": 0.15592343956232071,
|
|
"num_tokens": 3594055.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.06167197227478,
|
|
"epoch": 0.15129682997118155,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999655783329386,
|
|
"loss": 5.8897,
|
|
"mean_token_accuracy": 0.15909540206193923,
|
|
"num_tokens": 3605952.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.10714282989502,
|
|
"epoch": 0.15177713736791545,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999649760561046,
|
|
"loss": 5.9099,
|
|
"mean_token_accuracy": 0.1594424292445183,
|
|
"num_tokens": 3618544.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.059627628326416,
|
|
"epoch": 0.15225744476464936,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999643685562519,
|
|
"loss": 5.8529,
|
|
"mean_token_accuracy": 0.164482718706131,
|
|
"num_tokens": 3630445.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.061960506439209,
|
|
"epoch": 0.15273775216138327,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999637558333945,
|
|
"loss": 5.8683,
|
|
"mean_token_accuracy": 0.16716394126415252,
|
|
"num_tokens": 3642516.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.999404573440552,
|
|
"epoch": 0.15321805955811718,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999631378875467,
|
|
"loss": 5.7843,
|
|
"mean_token_accuracy": 0.1711465001106262,
|
|
"num_tokens": 3654425.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.989068651199341,
|
|
"epoch": 0.15369836695485112,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999625147187228,
|
|
"loss": 5.8055,
|
|
"mean_token_accuracy": 0.1635123535990715,
|
|
"num_tokens": 3666521.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.065861177444458,
|
|
"epoch": 0.15417867435158503,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999618863269373,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.15598922967910767,
|
|
"num_tokens": 3679121.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.048035669326782,
|
|
"epoch": 0.15465898174831894,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999612527122049,
|
|
"loss": 5.8645,
|
|
"mean_token_accuracy": 0.15967089980840682,
|
|
"num_tokens": 3691095.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.985746097564697,
|
|
"epoch": 0.15513928914505284,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999606138745402,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.16446878761053085,
|
|
"num_tokens": 3703426.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.084816551208496,
|
|
"epoch": 0.15561959654178675,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999599698139581,
|
|
"loss": 5.8925,
|
|
"mean_token_accuracy": 0.16607261896133424,
|
|
"num_tokens": 3715429.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.091441202163696,
|
|
"epoch": 0.15609990393852066,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999593205304734,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.16095825433731079,
|
|
"num_tokens": 3726327.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.048316621780396,
|
|
"epoch": 0.15658021133525457,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999586660241012,
|
|
"loss": 5.8316,
|
|
"mean_token_accuracy": 0.15777417570352553,
|
|
"num_tokens": 3736818.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.080630207061768,
|
|
"epoch": 0.15706051873198848,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999580062948569,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.16248745918273927,
|
|
"num_tokens": 3747776.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.891999816894531,
|
|
"epoch": 0.1575408261287224,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999573413427556,
|
|
"loss": 5.6917,
|
|
"mean_token_accuracy": 0.1702808439731598,
|
|
"num_tokens": 3758990.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.972564077377319,
|
|
"epoch": 0.1580211335254563,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999566711678128,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.165286822617054,
|
|
"num_tokens": 3769686.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.024297380447388,
|
|
"epoch": 0.1585014409221902,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999559957700442,
|
|
"loss": 5.8409,
|
|
"mean_token_accuracy": 0.16243061274290085,
|
|
"num_tokens": 3781815.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.015322732925415,
|
|
"epoch": 0.15898174831892412,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999553151494653,
|
|
"loss": 5.8773,
|
|
"mean_token_accuracy": 0.1623807817697525,
|
|
"num_tokens": 3793392.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.032832622528076,
|
|
"epoch": 0.15946205571565802,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999546293060919,
|
|
"loss": 5.826,
|
|
"mean_token_accuracy": 0.16092282980680467,
|
|
"num_tokens": 3804974.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.871552133560181,
|
|
"epoch": 0.15994236311239193,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049995393823994,
|
|
"loss": 5.6694,
|
|
"mean_token_accuracy": 0.1742493450641632,
|
|
"num_tokens": 3817166.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.0467840194702145,
|
|
"epoch": 0.16042267050912584,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999532419510255,
|
|
"loss": 5.798,
|
|
"mean_token_accuracy": 0.16097687929868698,
|
|
"num_tokens": 3828151.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.955699825286866,
|
|
"epoch": 0.16090297790585975,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499952540439365,
|
|
"loss": 5.81,
|
|
"mean_token_accuracy": 0.164180888235569,
|
|
"num_tokens": 3839439.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.0351283073425295,
|
|
"epoch": 0.16138328530259366,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999518337049743,
|
|
"loss": 5.8468,
|
|
"mean_token_accuracy": 0.16053693741559982,
|
|
"num_tokens": 3851694.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.977187013626098,
|
|
"epoch": 0.16186359269932757,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049995112174787,
|
|
"loss": 5.8331,
|
|
"mean_token_accuracy": 0.1628563791513443,
|
|
"num_tokens": 3863593.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.929252243041992,
|
|
"epoch": 0.16234390009606148,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999504045680687,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.17348818629980087,
|
|
"num_tokens": 3874588.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.014736175537109,
|
|
"epoch": 0.1628242074927954,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999496821655869,
|
|
"loss": 5.8407,
|
|
"mean_token_accuracy": 0.163246688246727,
|
|
"num_tokens": 3884662.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.109212112426758,
|
|
"epoch": 0.1633045148895293,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999489545404414,
|
|
"loss": 5.9364,
|
|
"mean_token_accuracy": 0.1559630572795868,
|
|
"num_tokens": 3896569.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.078909492492675,
|
|
"epoch": 0.1637848222862632,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999482216926493,
|
|
"loss": 5.7962,
|
|
"mean_token_accuracy": 0.16575282365083693,
|
|
"num_tokens": 3907691.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.001922178268432,
|
|
"epoch": 0.1642651296829971,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999474836222273,
|
|
"loss": 5.8099,
|
|
"mean_token_accuracy": 0.16902267709374427,
|
|
"num_tokens": 3918794.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.976260614395142,
|
|
"epoch": 0.16474543707973102,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999467403291928,
|
|
"loss": 5.7941,
|
|
"mean_token_accuracy": 0.17384963780641555,
|
|
"num_tokens": 3929773.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.973721170425415,
|
|
"epoch": 0.16522574447646493,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999459918135628,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.16380798667669297,
|
|
"num_tokens": 3940264.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.907494354248047,
|
|
"epoch": 0.16570605187319884,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499945238075355,
|
|
"loss": 5.7114,
|
|
"mean_token_accuracy": 0.1722415491938591,
|
|
"num_tokens": 3951500.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.023552942276001,
|
|
"epoch": 0.16618635926993275,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999444791145865,
|
|
"loss": 5.7824,
|
|
"mean_token_accuracy": 0.1692255288362503,
|
|
"num_tokens": 3963580.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.8660492420196535,
|
|
"epoch": 0.16666666666666666,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999437149312754,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.17743493169546126,
|
|
"num_tokens": 3975994.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.00585618019104,
|
|
"epoch": 0.16714697406340057,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499942945525439,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.16235984563827516,
|
|
"num_tokens": 3987897.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.995152854919434,
|
|
"epoch": 0.16762728146013448,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999421708970954,
|
|
"loss": 5.8941,
|
|
"mean_token_accuracy": 0.15724924057722092,
|
|
"num_tokens": 3999829.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.933386898040771,
|
|
"epoch": 0.16810758885686838,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999413910462625,
|
|
"loss": 5.7299,
|
|
"mean_token_accuracy": 0.17098538130521773,
|
|
"num_tokens": 4010882.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.917968273162842,
|
|
"epoch": 0.1685878962536023,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999406059729586,
|
|
"loss": 5.7206,
|
|
"mean_token_accuracy": 0.16878145337104797,
|
|
"num_tokens": 4021423.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.074040222167969,
|
|
"epoch": 0.1690682036503362,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999398156772016,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.1553002655506134,
|
|
"num_tokens": 4033590.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.8794393062591555,
|
|
"epoch": 0.16954851104707014,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049993902015901,
|
|
"loss": 5.7225,
|
|
"mean_token_accuracy": 0.17117420434951783,
|
|
"num_tokens": 4043978.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.0071815013885494,
|
|
"epoch": 0.17002881844380405,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999382194184023,
|
|
"loss": 5.8558,
|
|
"mean_token_accuracy": 0.16220006048679353,
|
|
"num_tokens": 4054513.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.068150615692138,
|
|
"epoch": 0.17050912584053796,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999374134553972,
|
|
"loss": 5.7949,
|
|
"mean_token_accuracy": 0.16809019297361374,
|
|
"num_tokens": 4066019.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.9036009311676025,
|
|
"epoch": 0.17098943323727187,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999366022700131,
|
|
"loss": 5.7542,
|
|
"mean_token_accuracy": 0.17212767601013185,
|
|
"num_tokens": 4077688.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.022014522552491,
|
|
"epoch": 0.17146974063400577,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999357858622691,
|
|
"loss": 5.8467,
|
|
"mean_token_accuracy": 0.16922961324453353,
|
|
"num_tokens": 4089803.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.994244956970215,
|
|
"epoch": 0.17195004803073968,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999349642321842,
|
|
"loss": 5.7916,
|
|
"mean_token_accuracy": 0.1677403450012207,
|
|
"num_tokens": 4101969.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.974350070953369,
|
|
"epoch": 0.1724303554274736,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999341373797772,
|
|
"loss": 5.7811,
|
|
"mean_token_accuracy": 0.16280766427516938,
|
|
"num_tokens": 4113567.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.9534135341644285,
|
|
"epoch": 0.1729106628242075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999333053050675,
|
|
"loss": 5.7357,
|
|
"mean_token_accuracy": 0.1677995041012764,
|
|
"num_tokens": 4125191.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.986348867416382,
|
|
"epoch": 0.1733909702209414,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999324680080744,
|
|
"loss": 5.7731,
|
|
"mean_token_accuracy": 0.16389087438583375,
|
|
"num_tokens": 4135050.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.944538688659668,
|
|
"epoch": 0.17387127761767532,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999316254888172,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.1667800709605217,
|
|
"num_tokens": 4146874.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.925647783279419,
|
|
"epoch": 0.17435158501440923,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999307777473157,
|
|
"loss": 5.7567,
|
|
"mean_token_accuracy": 0.16681902706623078,
|
|
"num_tokens": 4158118.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.988029193878174,
|
|
"epoch": 0.17483189241114314,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999299247835893,
|
|
"loss": 5.7486,
|
|
"mean_token_accuracy": 0.17824842482805253,
|
|
"num_tokens": 4169035.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.898885297775268,
|
|
"epoch": 0.17531219980787704,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499929066597658,
|
|
"loss": 5.7262,
|
|
"mean_token_accuracy": 0.17178142070770264,
|
|
"num_tokens": 4180314.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.002191352844238,
|
|
"epoch": 0.17579250720461095,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999282031895418,
|
|
"loss": 5.8002,
|
|
"mean_token_accuracy": 0.1674297496676445,
|
|
"num_tokens": 4192238.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.8907599449157715,
|
|
"epoch": 0.17627281460134486,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999273345592604,
|
|
"loss": 5.7252,
|
|
"mean_token_accuracy": 0.16727315485477448,
|
|
"num_tokens": 4203346.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.895097637176514,
|
|
"epoch": 0.17675312199807877,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999264607068343,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.1713564246892929,
|
|
"num_tokens": 4213763.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.920028400421143,
|
|
"epoch": 0.17723342939481268,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999255816322837,
|
|
"loss": 5.754,
|
|
"mean_token_accuracy": 0.16816631257534026,
|
|
"num_tokens": 4225553.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.013068199157715,
|
|
"epoch": 0.1777137367915466,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499924697335629,
|
|
"loss": 5.6628,
|
|
"mean_token_accuracy": 0.17668255865573884,
|
|
"num_tokens": 4236058.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.8163008213043215,
|
|
"epoch": 0.1781940441882805,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999238078168906,
|
|
"loss": 5.7584,
|
|
"mean_token_accuracy": 0.17156918495893478,
|
|
"num_tokens": 4248299.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.956279039382935,
|
|
"epoch": 0.1786743515850144,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999229130760894,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.17354945242404937,
|
|
"num_tokens": 4259704.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.824860429763794,
|
|
"epoch": 0.17915465898174832,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499922013113246,
|
|
"loss": 5.5708,
|
|
"mean_token_accuracy": 0.1824245736002922,
|
|
"num_tokens": 4270480.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.922730875015259,
|
|
"epoch": 0.17963496637848222,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999211079283814,
|
|
"loss": 5.8211,
|
|
"mean_token_accuracy": 0.16856807470321655,
|
|
"num_tokens": 4282104.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.019510555267334,
|
|
"epoch": 0.18011527377521613,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999201975215164,
|
|
"loss": 5.7974,
|
|
"mean_token_accuracy": 0.16135748475790024,
|
|
"num_tokens": 4294251.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.900371026992798,
|
|
"epoch": 0.18059558117195004,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999192818926725,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.1701715335249901,
|
|
"num_tokens": 4305569.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.941131639480591,
|
|
"epoch": 0.18107588856868395,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999183610418706,
|
|
"loss": 5.8057,
|
|
"mean_token_accuracy": 0.1641265444457531,
|
|
"num_tokens": 4317845.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.888107252120972,
|
|
"epoch": 0.18155619596541786,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999174349691322,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.17280717492103576,
|
|
"num_tokens": 4329987.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.836309289932251,
|
|
"epoch": 0.18203650336215177,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999165036744788,
|
|
"loss": 5.6926,
|
|
"mean_token_accuracy": 0.17172161340713502,
|
|
"num_tokens": 4341628.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.965258646011352,
|
|
"epoch": 0.18251681075888568,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999155671579322,
|
|
"loss": 5.7545,
|
|
"mean_token_accuracy": 0.16519593745470046,
|
|
"num_tokens": 4352379.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.800844955444336,
|
|
"epoch": 0.1829971181556196,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499914625419514,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.17391971200704576,
|
|
"num_tokens": 4364800.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.960105085372925,
|
|
"epoch": 0.1834774255523535,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999136784592459,
|
|
"loss": 5.7164,
|
|
"mean_token_accuracy": 0.1672212541103363,
|
|
"num_tokens": 4376048.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.888760232925415,
|
|
"epoch": 0.1839577329490874,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999127262771502,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.17140705287456512,
|
|
"num_tokens": 4388072.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.9937965869903564,
|
|
"epoch": 0.1844380403458213,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999117688732487,
|
|
"loss": 5.8004,
|
|
"mean_token_accuracy": 0.1623227506875992,
|
|
"num_tokens": 4399843.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.803120040893555,
|
|
"epoch": 0.18491834774255522,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999108062475638,
|
|
"loss": 5.6574,
|
|
"mean_token_accuracy": 0.17487162053585054,
|
|
"num_tokens": 4411373.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.846405506134033,
|
|
"epoch": 0.18539865513928913,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499909838400118,
|
|
"loss": 5.6564,
|
|
"mean_token_accuracy": 0.17340814918279648,
|
|
"num_tokens": 4421857.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.95341854095459,
|
|
"epoch": 0.18587896253602307,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999088653309334,
|
|
"loss": 5.7408,
|
|
"mean_token_accuracy": 0.16888684779405594,
|
|
"num_tokens": 4432728.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.844529104232788,
|
|
"epoch": 0.18635926993275698,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999078870400329,
|
|
"loss": 5.6742,
|
|
"mean_token_accuracy": 0.1769302397966385,
|
|
"num_tokens": 4444683.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.96117753982544,
|
|
"epoch": 0.18683957732949089,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999069035274391,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.16333086788654327,
|
|
"num_tokens": 4456961.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.875500202178955,
|
|
"epoch": 0.1873198847262248,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999059147931747,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.17937855124473573,
|
|
"num_tokens": 4468424.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.871504831314087,
|
|
"epoch": 0.1878001921229587,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999049208372629,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.15889065861701965,
|
|
"num_tokens": 4479813.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.061702728271484,
|
|
"epoch": 0.1882804995196926,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999039216597267,
|
|
"loss": 5.8364,
|
|
"mean_token_accuracy": 0.16994454562664033,
|
|
"num_tokens": 4491172.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.844229984283447,
|
|
"epoch": 0.18876080691642652,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999029172605892,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.17361883521080018,
|
|
"num_tokens": 4503063.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.998745012283325,
|
|
"epoch": 0.18924111431316043,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999019076398738,
|
|
"loss": 5.8005,
|
|
"mean_token_accuracy": 0.1544879749417305,
|
|
"num_tokens": 4514188.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.911010074615478,
|
|
"epoch": 0.18972142170989434,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499900892797604,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.17505204379558564,
|
|
"num_tokens": 4525293.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.906450510025024,
|
|
"epoch": 0.19020172910662825,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998998727338031,
|
|
"loss": 5.785,
|
|
"mean_token_accuracy": 0.16963134258985518,
|
|
"num_tokens": 4536589.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.855934715270996,
|
|
"epoch": 0.19068203650336216,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998988474484952,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.1919272780418396,
|
|
"num_tokens": 4547594.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.856652116775512,
|
|
"epoch": 0.19116234390009607,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998978169417038,
|
|
"loss": 5.7494,
|
|
"mean_token_accuracy": 0.17164870202541352,
|
|
"num_tokens": 4559850.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.886022758483887,
|
|
"epoch": 0.19164265129682997,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998967812134529,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.1702727809548378,
|
|
"num_tokens": 4570727.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.75973162651062,
|
|
"epoch": 0.19212295869356388,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998957402637664,
|
|
"loss": 5.6355,
|
|
"mean_token_accuracy": 0.174292254447937,
|
|
"num_tokens": 4582248.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.904182481765747,
|
|
"epoch": 0.1926032660902978,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998946940926687,
|
|
"loss": 5.6548,
|
|
"mean_token_accuracy": 0.17286083698272706,
|
|
"num_tokens": 4592604.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.794434881210327,
|
|
"epoch": 0.1930835734870317,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499893642700184,
|
|
"loss": 5.6982,
|
|
"mean_token_accuracy": 0.17326663583517074,
|
|
"num_tokens": 4604398.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.889737224578857,
|
|
"epoch": 0.1935638808837656,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998925860863368,
|
|
"loss": 5.7798,
|
|
"mean_token_accuracy": 0.16947566717863083,
|
|
"num_tokens": 4616434.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.953923463821411,
|
|
"epoch": 0.19404418828049952,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998915242511516,
|
|
"loss": 5.7198,
|
|
"mean_token_accuracy": 0.17970746457576753,
|
|
"num_tokens": 4627577.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.960914373397827,
|
|
"epoch": 0.19452449567723343,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998904571946528,
|
|
"loss": 5.7831,
|
|
"mean_token_accuracy": 0.1678330808877945,
|
|
"num_tokens": 4639698.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.958297538757324,
|
|
"epoch": 0.19500480307396734,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998893849168655,
|
|
"loss": 5.7914,
|
|
"mean_token_accuracy": 0.16515226066112518,
|
|
"num_tokens": 4650643.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.87400336265564,
|
|
"epoch": 0.19548511047070125,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998883074178144,
|
|
"loss": 5.7203,
|
|
"mean_token_accuracy": 0.1693568304181099,
|
|
"num_tokens": 4662897.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.9375998973846436,
|
|
"epoch": 0.19596541786743515,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998872246975247,
|
|
"loss": 5.7942,
|
|
"mean_token_accuracy": 0.17414003014564514,
|
|
"num_tokens": 4673701.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.967000341415405,
|
|
"epoch": 0.19644572526416906,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998861367560213,
|
|
"loss": 5.7591,
|
|
"mean_token_accuracy": 0.16811660975217818,
|
|
"num_tokens": 4685873.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.925240468978882,
|
|
"epoch": 0.19692603266090297,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998850435933296,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.17622891664505005,
|
|
"num_tokens": 4697179.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.831101989746093,
|
|
"epoch": 0.19740634005763688,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998839452094749,
|
|
"loss": 5.6862,
|
|
"mean_token_accuracy": 0.1738536462187767,
|
|
"num_tokens": 4707752.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.746025085449219,
|
|
"epoch": 0.1978866474543708,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998828416044829,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.18245317041873932,
|
|
"num_tokens": 4718413.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.855678606033325,
|
|
"epoch": 0.1983669548511047,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499881732778379,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.16523946076631546,
|
|
"num_tokens": 4730033.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.843948650360107,
|
|
"epoch": 0.1988472622478386,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499880618731189,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.17743310034275056,
|
|
"num_tokens": 4742084.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.899618673324585,
|
|
"epoch": 0.19932756964457252,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998794994629388,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.16559504121541976,
|
|
"num_tokens": 4753885.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.831307220458984,
|
|
"epoch": 0.19980787704130643,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998783749736545,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.17495889812707902,
|
|
"num_tokens": 4765686.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.899104452133178,
|
|
"epoch": 0.20028818443804033,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998772452633619,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.16899442821741104,
|
|
"num_tokens": 4777157.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.828914642333984,
|
|
"epoch": 0.20076849183477424,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998761103320876,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.17771946042776107,
|
|
"num_tokens": 4788583.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.88235239982605,
|
|
"epoch": 0.20124879923150815,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998749701798577,
|
|
"loss": 5.755,
|
|
"mean_token_accuracy": 0.16652097702026367,
|
|
"num_tokens": 4800749.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.819902420043945,
|
|
"epoch": 0.2017291066282421,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998738248066986,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.17305531948804856,
|
|
"num_tokens": 4812488.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.922385215759277,
|
|
"epoch": 0.202209414024976,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998726742126372,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.17342206686735154,
|
|
"num_tokens": 4823495.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.770005416870117,
|
|
"epoch": 0.2026897214217099,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998715183976999,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.16901031583547593,
|
|
"num_tokens": 4834450.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.839266920089722,
|
|
"epoch": 0.20317002881844382,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998703573619137,
|
|
"loss": 5.6129,
|
|
"mean_token_accuracy": 0.18550968468189238,
|
|
"num_tokens": 4846826.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.970982599258423,
|
|
"epoch": 0.20365033621517772,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998691911053056,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.16186073422431946,
|
|
"num_tokens": 4859668.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.834139776229859,
|
|
"epoch": 0.20413064361191163,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998680196279026,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.17062558084726334,
|
|
"num_tokens": 4871727.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.955994033813477,
|
|
"epoch": 0.20461095100864554,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998668429297319,
|
|
"loss": 5.7366,
|
|
"mean_token_accuracy": 0.1794666439294815,
|
|
"num_tokens": 4882191.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.847929811477661,
|
|
"epoch": 0.20509125840537945,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998656610108208,
|
|
"loss": 5.6706,
|
|
"mean_token_accuracy": 0.17324328422546387,
|
|
"num_tokens": 4892416.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.728474712371826,
|
|
"epoch": 0.20557156580211336,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998644738711969,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.16920143961906434,
|
|
"num_tokens": 4903572.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.977149581909179,
|
|
"epoch": 0.20605187319884727,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998632815108874,
|
|
"loss": 5.7446,
|
|
"mean_token_accuracy": 0.17007820159196854,
|
|
"num_tokens": 4915417.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.810878467559815,
|
|
"epoch": 0.20653218059558118,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998620839299203,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.17479929476976394,
|
|
"num_tokens": 4926943.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.80943193435669,
|
|
"epoch": 0.2070124879923151,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998608811283233,
|
|
"loss": 5.5847,
|
|
"mean_token_accuracy": 0.17787374258041383,
|
|
"num_tokens": 4937724.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.957506895065308,
|
|
"epoch": 0.207492795389049,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998596731061244,
|
|
"loss": 5.7368,
|
|
"mean_token_accuracy": 0.1671774461865425,
|
|
"num_tokens": 4949970.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.856918811798096,
|
|
"epoch": 0.2079731027857829,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998584598633516,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.16863747537136078,
|
|
"num_tokens": 4961389.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.930571174621582,
|
|
"epoch": 0.2084534101825168,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998572414000329,
|
|
"loss": 5.787,
|
|
"mean_token_accuracy": 0.16769310384988784,
|
|
"num_tokens": 4973888.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.846202564239502,
|
|
"epoch": 0.20893371757925072,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998560177161969,
|
|
"loss": 5.7358,
|
|
"mean_token_accuracy": 0.16144881695508956,
|
|
"num_tokens": 4985423.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.814085817337036,
|
|
"epoch": 0.20941402497598463,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998547888118718,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.16614219099283217,
|
|
"num_tokens": 4997711.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.891442108154297,
|
|
"epoch": 0.20989433237271854,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998535546870862,
|
|
"loss": 5.7239,
|
|
"mean_token_accuracy": 0.17229223549365996,
|
|
"num_tokens": 5009633.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.876784420013427,
|
|
"epoch": 0.21037463976945245,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998523153418687,
|
|
"loss": 5.6628,
|
|
"mean_token_accuracy": 0.17913604974746705,
|
|
"num_tokens": 5021523.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.9075572967529295,
|
|
"epoch": 0.21085494716618636,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998510707762481,
|
|
"loss": 5.7561,
|
|
"mean_token_accuracy": 0.1698111966252327,
|
|
"num_tokens": 5033513.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.961580562591553,
|
|
"epoch": 0.21133525456292027,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998498209902533,
|
|
"loss": 5.7608,
|
|
"mean_token_accuracy": 0.16819328367710112,
|
|
"num_tokens": 5047055.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.845474815368652,
|
|
"epoch": 0.21181556195965417,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998485659839134,
|
|
"loss": 5.6379,
|
|
"mean_token_accuracy": 0.17564828246831893,
|
|
"num_tokens": 5057613.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.840123701095581,
|
|
"epoch": 0.21229586935638808,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998473057572575,
|
|
"loss": 5.7558,
|
|
"mean_token_accuracy": 0.16806377619504928,
|
|
"num_tokens": 5068886.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.85970664024353,
|
|
"epoch": 0.212776176753122,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998460403103146,
|
|
"loss": 5.7283,
|
|
"mean_token_accuracy": 0.167040803283453,
|
|
"num_tokens": 5079978.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.902343082427978,
|
|
"epoch": 0.2132564841498559,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998447696431146,
|
|
"loss": 5.6819,
|
|
"mean_token_accuracy": 0.1737098440527916,
|
|
"num_tokens": 5091021.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.76426329612732,
|
|
"epoch": 0.2137367915465898,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998434937556865,
|
|
"loss": 5.5926,
|
|
"mean_token_accuracy": 0.1794767439365387,
|
|
"num_tokens": 5101483.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.874709224700927,
|
|
"epoch": 0.21421709894332372,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998422126480602,
|
|
"loss": 5.712,
|
|
"mean_token_accuracy": 0.16954506933689117,
|
|
"num_tokens": 5113116.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.8735052108764645,
|
|
"epoch": 0.21469740634005763,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998409263202653,
|
|
"loss": 5.6648,
|
|
"mean_token_accuracy": 0.16956303715705873,
|
|
"num_tokens": 5124824.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.7920280456542965,
|
|
"epoch": 0.21517771373679154,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998396347723318,
|
|
"loss": 5.5907,
|
|
"mean_token_accuracy": 0.1711305171251297,
|
|
"num_tokens": 5137567.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.7892828464508055,
|
|
"epoch": 0.21565802113352545,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998383380042895,
|
|
"loss": 5.6577,
|
|
"mean_token_accuracy": 0.17161570936441423,
|
|
"num_tokens": 5149016.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.763986873626709,
|
|
"epoch": 0.21613832853025935,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998370360161688,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.17783051282167434,
|
|
"num_tokens": 5160356.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.848583841323853,
|
|
"epoch": 0.21661863592699326,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998357288079996,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.16622594892978668,
|
|
"num_tokens": 5172100.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.9171970844268795,
|
|
"epoch": 0.21709894332372717,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998344163798125,
|
|
"loss": 5.7146,
|
|
"mean_token_accuracy": 0.16663871705532074,
|
|
"num_tokens": 5183984.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.842860412597656,
|
|
"epoch": 0.21757925072046108,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998330987316379,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.16949303299188614,
|
|
"num_tokens": 5195853.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.7196276664733885,
|
|
"epoch": 0.21805955811719502,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998317758635062,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.17934199124574662,
|
|
"num_tokens": 5206995.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.686021423339843,
|
|
"epoch": 0.21853986551392893,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998304477754484,
|
|
"loss": 5.5664,
|
|
"mean_token_accuracy": 0.17936804592609407,
|
|
"num_tokens": 5219291.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.80483112335205,
|
|
"epoch": 0.21902017291066284,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998291144674952,
|
|
"loss": 5.6432,
|
|
"mean_token_accuracy": 0.17933146953582763,
|
|
"num_tokens": 5230856.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.694868040084839,
|
|
"epoch": 0.21950048030739674,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998277759396776,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.1853230893611908,
|
|
"num_tokens": 5242871.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.757525062561035,
|
|
"epoch": 0.21998078770413065,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998264321920265,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.17693334370851516,
|
|
"num_tokens": 5253835.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.757721900939941,
|
|
"epoch": 0.22046109510086456,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998250832245734,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.1778374120593071,
|
|
"num_tokens": 5266195.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.770969820022583,
|
|
"epoch": 0.22094140249759847,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998237290373494,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.17990957647562028,
|
|
"num_tokens": 5277499.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.856108522415161,
|
|
"epoch": 0.22142170989433238,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499822369630386,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.1632763683795929,
|
|
"num_tokens": 5288622.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.837642621994019,
|
|
"epoch": 0.2219020172910663,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004998210050037148,
|
|
"loss": 5.7363,
|
|
"mean_token_accuracy": 0.1674153745174408,
|
|
"num_tokens": 5299664.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.8238342761993405,
|
|
"epoch": 0.2223823246878002,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998196351573674,
|
|
"loss": 5.6326,
|
|
"mean_token_accuracy": 0.1764681726694107,
|
|
"num_tokens": 5311627.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.69834566116333,
|
|
"epoch": 0.2228626320845341,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998182600913757,
|
|
"loss": 5.5328,
|
|
"mean_token_accuracy": 0.1816352590918541,
|
|
"num_tokens": 5323000.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.7694638729095455,
|
|
"epoch": 0.22334293948126802,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998168798057715,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.18260359317064284,
|
|
"num_tokens": 5333811.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.779385423660278,
|
|
"epoch": 0.22382324687800192,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499815494300587,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.17485559582710267,
|
|
"num_tokens": 5344762.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.806505537033081,
|
|
"epoch": 0.22430355427473583,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998141035758542,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.18179302662611008,
|
|
"num_tokens": 5356112.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.832508087158203,
|
|
"epoch": 0.22478386167146974,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998127076316054,
|
|
"loss": 5.6984,
|
|
"mean_token_accuracy": 0.1719257727265358,
|
|
"num_tokens": 5367339.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.7249836921691895,
|
|
"epoch": 0.22526416906820365,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998113064678734,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.18138026893138887,
|
|
"num_tokens": 5378627.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.868769311904908,
|
|
"epoch": 0.22574447646493756,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998099000846901,
|
|
"loss": 5.6632,
|
|
"mean_token_accuracy": 0.17547774761915208,
|
|
"num_tokens": 5390209.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.81194429397583,
|
|
"epoch": 0.22622478386167147,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998084884820887,
|
|
"loss": 5.6538,
|
|
"mean_token_accuracy": 0.1727759525179863,
|
|
"num_tokens": 5401578.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.7616051197052,
|
|
"epoch": 0.22670509125840538,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998070716601016,
|
|
"loss": 5.575,
|
|
"mean_token_accuracy": 0.17865398079156875,
|
|
"num_tokens": 5413831.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.82645959854126,
|
|
"epoch": 0.2271853986551393,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998056496187618,
|
|
"loss": 5.6293,
|
|
"mean_token_accuracy": 0.17196177393198014,
|
|
"num_tokens": 5425430.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.588806056976319,
|
|
"epoch": 0.2276657060518732,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998042223581025,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.18928515762090684,
|
|
"num_tokens": 5435353.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.8202369689941404,
|
|
"epoch": 0.2281460134486071,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998027898781565,
|
|
"loss": 5.6808,
|
|
"mean_token_accuracy": 0.1762748748064041,
|
|
"num_tokens": 5446925.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.709089374542236,
|
|
"epoch": 0.228626320845341,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998013521789574,
|
|
"loss": 5.5578,
|
|
"mean_token_accuracy": 0.18197699040174484,
|
|
"num_tokens": 5456613.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.799993944168091,
|
|
"epoch": 0.22910662824207492,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997999092605384,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.17672255784273147,
|
|
"num_tokens": 5467790.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.814759111404419,
|
|
"epoch": 0.22958693563880883,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499798461122933,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.1812552884221077,
|
|
"num_tokens": 5479166.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.6896861553192135,
|
|
"epoch": 0.23006724303554274,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997970077661748,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.18635332137346267,
|
|
"num_tokens": 5490186.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.738391304016114,
|
|
"epoch": 0.23054755043227665,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997955491902977,
|
|
"loss": 5.5424,
|
|
"mean_token_accuracy": 0.17801296710968018,
|
|
"num_tokens": 5500416.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.766972875595092,
|
|
"epoch": 0.23102785782901056,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997940853953354,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.1773225635290146,
|
|
"num_tokens": 5512189.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.711191701889038,
|
|
"epoch": 0.23150816522574447,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499792616381322,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.18552721440792083,
|
|
"num_tokens": 5523631.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.715830135345459,
|
|
"epoch": 0.23198847262247838,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997911421482914,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.1831541910767555,
|
|
"num_tokens": 5535637.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.736978912353516,
|
|
"epoch": 0.23246878001921228,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499789662696278,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.1847958281636238,
|
|
"num_tokens": 5546470.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.8512872695922855,
|
|
"epoch": 0.2329490874159462,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997881780253162,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.1715322643518448,
|
|
"num_tokens": 5558633.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.771648311614991,
|
|
"epoch": 0.2334293948126801,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997866881354403,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.17206788063049316,
|
|
"num_tokens": 5570427.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.735009336471558,
|
|
"epoch": 0.23390970220941404,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499785193026685,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.17571118026971816,
|
|
"num_tokens": 5580991.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.840723323822021,
|
|
"epoch": 0.23439000960614795,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997836926990851,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.17219943851232528,
|
|
"num_tokens": 5592777.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.714860486984253,
|
|
"epoch": 0.23487031700288186,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997821871526752,
|
|
"loss": 5.5575,
|
|
"mean_token_accuracy": 0.1838330253958702,
|
|
"num_tokens": 5603326.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.682803630828857,
|
|
"epoch": 0.23535062439961577,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997806763874905,
|
|
"loss": 5.542,
|
|
"mean_token_accuracy": 0.18075062334537506,
|
|
"num_tokens": 5614504.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.7689934253692625,
|
|
"epoch": 0.23583093179634967,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997791604035659,
|
|
"loss": 5.6115,
|
|
"mean_token_accuracy": 0.18290183395147325,
|
|
"num_tokens": 5625150.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.732327699661255,
|
|
"epoch": 0.23631123919308358,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997776392009366,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.17373958230018616,
|
|
"num_tokens": 5636815.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.774140119552612,
|
|
"epoch": 0.2367915465898175,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997761127796381,
|
|
"loss": 5.6077,
|
|
"mean_token_accuracy": 0.17858083546161652,
|
|
"num_tokens": 5648272.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.742091226577759,
|
|
"epoch": 0.2372718539865514,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997745811397056,
|
|
"loss": 5.5252,
|
|
"mean_token_accuracy": 0.18127477020025254,
|
|
"num_tokens": 5659227.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.748807668685913,
|
|
"epoch": 0.2377521613832853,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997730442811748,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.17652334049344062,
|
|
"num_tokens": 5670411.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.703849220275879,
|
|
"epoch": 0.23823246878001922,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997715022040814,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.18095139116048814,
|
|
"num_tokens": 5681570.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.688530683517456,
|
|
"epoch": 0.23871277617675313,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499769954908461,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.18896123319864272,
|
|
"num_tokens": 5693021.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.6701000213623045,
|
|
"epoch": 0.23919308357348704,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997684023943498,
|
|
"loss": 5.565,
|
|
"mean_token_accuracy": 0.1783182293176651,
|
|
"num_tokens": 5704043.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.731194639205933,
|
|
"epoch": 0.23967339097022095,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997668446617837,
|
|
"loss": 5.6502,
|
|
"mean_token_accuracy": 0.17267276644706725,
|
|
"num_tokens": 5715735.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.862462711334229,
|
|
"epoch": 0.24015369836695485,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997652817107989,
|
|
"loss": 5.6205,
|
|
"mean_token_accuracy": 0.1759555384516716,
|
|
"num_tokens": 5725778.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.732063245773316,
|
|
"epoch": 0.24063400576368876,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997637135414315,
|
|
"loss": 5.6296,
|
|
"mean_token_accuracy": 0.17513870894908906,
|
|
"num_tokens": 5737224.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.8137345790863035,
|
|
"epoch": 0.24111431316042267,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997621401537183,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.17411693036556244,
|
|
"num_tokens": 5749226.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.8183518409729,
|
|
"epoch": 0.24159462055715658,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997605615476955,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.17504109144210817,
|
|
"num_tokens": 5760282.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.663213491439819,
|
|
"epoch": 0.2420749279538905,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997589777234,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.1830235943198204,
|
|
"num_tokens": 5771756.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.753743457794189,
|
|
"epoch": 0.2425552353506244,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997573886808684,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.1693316325545311,
|
|
"num_tokens": 5783237.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.788538599014283,
|
|
"epoch": 0.2430355427473583,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997557944201375,
|
|
"loss": 5.6374,
|
|
"mean_token_accuracy": 0.17653653472661973,
|
|
"num_tokens": 5794825.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.7611926078796385,
|
|
"epoch": 0.24351585014409222,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997541949412445,
|
|
"loss": 5.5517,
|
|
"mean_token_accuracy": 0.1838692843914032,
|
|
"num_tokens": 5805578.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.798102807998657,
|
|
"epoch": 0.24399615754082613,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997525902442266,
|
|
"loss": 5.6398,
|
|
"mean_token_accuracy": 0.17110283374786378,
|
|
"num_tokens": 5818201.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.721447992324829,
|
|
"epoch": 0.24447646493756003,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997509803291207,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.1799464926123619,
|
|
"num_tokens": 5830319.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.658524894714356,
|
|
"epoch": 0.24495677233429394,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997493651959647,
|
|
"loss": 5.5081,
|
|
"mean_token_accuracy": 0.18168970346450805,
|
|
"num_tokens": 5840638.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.725489377975464,
|
|
"epoch": 0.24543707973102785,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997477448447955,
|
|
"loss": 5.5401,
|
|
"mean_token_accuracy": 0.17641098499298097,
|
|
"num_tokens": 5852472.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.8019109725952145,
|
|
"epoch": 0.24591738712776176,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997461192756512,
|
|
"loss": 5.5784,
|
|
"mean_token_accuracy": 0.17450501769781113,
|
|
"num_tokens": 5863455.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.637508058547974,
|
|
"epoch": 0.24639769452449567,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997444884885694,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.18074321746826172,
|
|
"num_tokens": 5873141.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.688677740097046,
|
|
"epoch": 0.24687800192122958,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997428524835879,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.1751626744866371,
|
|
"num_tokens": 5884363.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.763658571243286,
|
|
"epoch": 0.2473583093179635,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997412112607446,
|
|
"loss": 5.6443,
|
|
"mean_token_accuracy": 0.1757771074771881,
|
|
"num_tokens": 5895856.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.676737451553345,
|
|
"epoch": 0.2478386167146974,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997395648200778,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.1850918784737587,
|
|
"num_tokens": 5906657.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.710775470733642,
|
|
"epoch": 0.2483189241114313,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997379131616257,
|
|
"loss": 5.5895,
|
|
"mean_token_accuracy": 0.17889538109302522,
|
|
"num_tokens": 5919496.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.750392150878906,
|
|
"epoch": 0.24879923150816521,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997362562854266,
|
|
"loss": 5.6576,
|
|
"mean_token_accuracy": 0.16503879725933074,
|
|
"num_tokens": 5932593.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.737170696258545,
|
|
"epoch": 0.24927953890489912,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997345941915187,
|
|
"loss": 5.5772,
|
|
"mean_token_accuracy": 0.17579198330640794,
|
|
"num_tokens": 5944080.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.748187398910522,
|
|
"epoch": 0.24975984630163303,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997329268799412,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.18597260415554046,
|
|
"num_tokens": 5955703.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.728941822052002,
|
|
"epoch": 0.25024015369836694,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997312543507322,
|
|
"loss": 5.6317,
|
|
"mean_token_accuracy": 0.17275256365537645,
|
|
"num_tokens": 5966979.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.767943668365478,
|
|
"epoch": 0.2507204610951009,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997295766039309,
|
|
"loss": 5.5183,
|
|
"mean_token_accuracy": 0.1809815689921379,
|
|
"num_tokens": 5978808.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.720742416381836,
|
|
"epoch": 0.25120076849183476,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997278936395761,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.1722423776984215,
|
|
"num_tokens": 5992145.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.732787466049194,
|
|
"epoch": 0.2516810758885687,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997262054577071,
|
|
"loss": 5.5557,
|
|
"mean_token_accuracy": 0.17480167895555496,
|
|
"num_tokens": 6003723.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.763635778427124,
|
|
"epoch": 0.2521613832853026,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997245120583627,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.18482747673988342,
|
|
"num_tokens": 6014064.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.620661401748658,
|
|
"epoch": 0.2526416906820365,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997228134415825,
|
|
"loss": 5.4966,
|
|
"mean_token_accuracy": 0.18726035058498383,
|
|
"num_tokens": 6025455.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.755416059494019,
|
|
"epoch": 0.2531219980787704,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997211096074059,
|
|
"loss": 5.6073,
|
|
"mean_token_accuracy": 0.16819422841072082,
|
|
"num_tokens": 6037347.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.697003602981567,
|
|
"epoch": 0.25360230547550433,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997194005558722,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.18332696408033372,
|
|
"num_tokens": 6049236.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.591462659835815,
|
|
"epoch": 0.2540826128722382,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997176862870216,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.1839895710349083,
|
|
"num_tokens": 6060982.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.785092067718506,
|
|
"epoch": 0.25456292026897215,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997159668008933,
|
|
"loss": 5.5093,
|
|
"mean_token_accuracy": 0.183223856985569,
|
|
"num_tokens": 6070925.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.637601613998413,
|
|
"epoch": 0.25504322766570603,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997142420975277,
|
|
"loss": 5.4662,
|
|
"mean_token_accuracy": 0.18813761025667192,
|
|
"num_tokens": 6081279.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.6759350299835205,
|
|
"epoch": 0.25552353506243997,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997125121769647,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.18180250078439714,
|
|
"num_tokens": 6091797.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.803980493545533,
|
|
"epoch": 0.25600384245917385,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997107770392444,
|
|
"loss": 5.5878,
|
|
"mean_token_accuracy": 0.18288871198892592,
|
|
"num_tokens": 6103435.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.7139026641845705,
|
|
"epoch": 0.2564841498559078,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499709036684407,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.1780319407582283,
|
|
"num_tokens": 6114531.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.635207653045654,
|
|
"epoch": 0.25696445725264166,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997072911124932,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.1845824345946312,
|
|
"num_tokens": 6126110.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.746867656707764,
|
|
"epoch": 0.2574447646493756,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997055403235432,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.17680004984140396,
|
|
"num_tokens": 6137114.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.682720375061035,
|
|
"epoch": 0.2579250720461095,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997037843175978,
|
|
"loss": 5.5435,
|
|
"mean_token_accuracy": 0.1826479434967041,
|
|
"num_tokens": 6148696.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.668850469589233,
|
|
"epoch": 0.2584053794428434,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997020230946978,
|
|
"loss": 5.5377,
|
|
"mean_token_accuracy": 0.18099813014268876,
|
|
"num_tokens": 6160235.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.727720451354981,
|
|
"epoch": 0.25888568683957736,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997002566548841,
|
|
"loss": 5.5204,
|
|
"mean_token_accuracy": 0.18033260554075242,
|
|
"num_tokens": 6172031.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.558167171478272,
|
|
"epoch": 0.25936599423631124,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996984849981976,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.19067923128604888,
|
|
"num_tokens": 6183547.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.730989408493042,
|
|
"epoch": 0.2598463016330452,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996967081246794,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.17200068533420562,
|
|
"num_tokens": 6194768.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.720772361755371,
|
|
"epoch": 0.26032660902977905,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996949260343711,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.17187345325946807,
|
|
"num_tokens": 6206099.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.782607173919677,
|
|
"epoch": 0.260806916426513,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996931387273137,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.18310263007879257,
|
|
"num_tokens": 6217530.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.787333059310913,
|
|
"epoch": 0.2612872238232469,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996913462035487,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.1762217938899994,
|
|
"num_tokens": 6228564.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.637451457977295,
|
|
"epoch": 0.2617675312199808,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499689548463118,
|
|
"loss": 5.4915,
|
|
"mean_token_accuracy": 0.17907891869544984,
|
|
"num_tokens": 6239945.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.713913059234619,
|
|
"epoch": 0.2622478386167147,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996877455060631,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.17165847718715668,
|
|
"num_tokens": 6251829.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.83690390586853,
|
|
"epoch": 0.2627281460134486,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996859373324259,
|
|
"loss": 5.6997,
|
|
"mean_token_accuracy": 0.16278707683086396,
|
|
"num_tokens": 6264823.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.652474355697632,
|
|
"epoch": 0.2632084534101825,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996841239422485,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.18814935386180878,
|
|
"num_tokens": 6276247.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.562798309326172,
|
|
"epoch": 0.26368876080691644,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996823053355729,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.18557627648115158,
|
|
"num_tokens": 6287593.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.779765367507935,
|
|
"epoch": 0.2641690682036503,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996804815124413,
|
|
"loss": 5.6677,
|
|
"mean_token_accuracy": 0.17469124346971512,
|
|
"num_tokens": 6299918.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.652080011367798,
|
|
"epoch": 0.26464937560038426,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996786524728962,
|
|
"loss": 5.5093,
|
|
"mean_token_accuracy": 0.18570335656404496,
|
|
"num_tokens": 6311147.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.57460036277771,
|
|
"epoch": 0.26512968299711814,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996768182169797,
|
|
"loss": 5.4136,
|
|
"mean_token_accuracy": 0.1906318724155426,
|
|
"num_tokens": 6323239.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.755684471130371,
|
|
"epoch": 0.2656099903938521,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996749787447349,
|
|
"loss": 5.5058,
|
|
"mean_token_accuracy": 0.1824209213256836,
|
|
"num_tokens": 6334625.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.676227712631226,
|
|
"epoch": 0.26609029779058596,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499673134056204,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.17851219475269317,
|
|
"num_tokens": 6346068.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.677485752105713,
|
|
"epoch": 0.2665706051873199,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996712841514303,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.17988724559545516,
|
|
"num_tokens": 6357097.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.752181959152222,
|
|
"epoch": 0.2670509125840538,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996694290304563,
|
|
"loss": 5.5887,
|
|
"mean_token_accuracy": 0.16941747516393663,
|
|
"num_tokens": 6367481.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.618309497833252,
|
|
"epoch": 0.2675312199807877,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996675686933255,
|
|
"loss": 5.4942,
|
|
"mean_token_accuracy": 0.18622181862592696,
|
|
"num_tokens": 6378873.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.736754608154297,
|
|
"epoch": 0.2680115273775216,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996657031400807,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.17920784205198287,
|
|
"num_tokens": 6390651.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.613878059387207,
|
|
"epoch": 0.26849183477425553,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996638323707655,
|
|
"loss": 5.4195,
|
|
"mean_token_accuracy": 0.19438366293907167,
|
|
"num_tokens": 6401631.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.575555801391602,
|
|
"epoch": 0.2689721421709894,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996619563854232,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.18674360662698747,
|
|
"num_tokens": 6413875.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.771028232574463,
|
|
"epoch": 0.26945244956772335,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996600751840974,
|
|
"loss": 5.541,
|
|
"mean_token_accuracy": 0.17710736989974976,
|
|
"num_tokens": 6425764.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.621025276184082,
|
|
"epoch": 0.26993275696445723,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996581887668317,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.18712297081947327,
|
|
"num_tokens": 6437911.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.597506284713745,
|
|
"epoch": 0.27041306436119117,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049965629713367,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.18105038553476333,
|
|
"num_tokens": 6449942.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.707987642288208,
|
|
"epoch": 0.27089337175792505,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996544002846561,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.18570097982883454,
|
|
"num_tokens": 6461729.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.729322052001953,
|
|
"epoch": 0.271373679154659,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996524982198343,
|
|
"loss": 5.553,
|
|
"mean_token_accuracy": 0.18336791172623634,
|
|
"num_tokens": 6472046.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.643385314941407,
|
|
"epoch": 0.27185398655139287,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996505909392485,
|
|
"loss": 5.5346,
|
|
"mean_token_accuracy": 0.17891884595155716,
|
|
"num_tokens": 6483308.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.559644651412964,
|
|
"epoch": 0.2723342939481268,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996486784429429,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.18978026360273362,
|
|
"num_tokens": 6495093.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.695954370498657,
|
|
"epoch": 0.2728146013448607,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996467607309622,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.18494741916656493,
|
|
"num_tokens": 6505933.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.6591239929199215,
|
|
"epoch": 0.2732949087415946,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996448378033507,
|
|
"loss": 5.5485,
|
|
"mean_token_accuracy": 0.17702232003211976,
|
|
"num_tokens": 6517280.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.6757430076599125,
|
|
"epoch": 0.2737752161383285,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996429096601532,
|
|
"loss": 5.5964,
|
|
"mean_token_accuracy": 0.17370087206363677,
|
|
"num_tokens": 6528980.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.688251590728759,
|
|
"epoch": 0.27425552353506244,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996409763014144,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.18222061842679976,
|
|
"num_tokens": 6540670.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.640368938446045,
|
|
"epoch": 0.2747358309317964,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996390377271791,
|
|
"loss": 5.545,
|
|
"mean_token_accuracy": 0.1811893939971924,
|
|
"num_tokens": 6551302.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.676407194137573,
|
|
"epoch": 0.27521613832853026,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996370939374924,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.17508159577846527,
|
|
"num_tokens": 6563177.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.826377010345459,
|
|
"epoch": 0.2756964457252642,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996351449323994,
|
|
"loss": 5.6048,
|
|
"mean_token_accuracy": 0.17976640462875365,
|
|
"num_tokens": 6573323.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.664675855636597,
|
|
"epoch": 0.2761767531219981,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996331907119455,
|
|
"loss": 5.5386,
|
|
"mean_token_accuracy": 0.17416994124650956,
|
|
"num_tokens": 6585382.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.553443956375122,
|
|
"epoch": 0.276657060518732,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996312312761758,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.1913624182343483,
|
|
"num_tokens": 6596629.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.703445148468018,
|
|
"epoch": 0.2771373679154659,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499629266625136,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.1806390777230263,
|
|
"num_tokens": 6608408.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.732683229446411,
|
|
"epoch": 0.27761767531219983,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996272967588715,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.1764448568224907,
|
|
"num_tokens": 6619375.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.728315591812134,
|
|
"epoch": 0.2780979827089337,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996253216774283,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.17850979417562485,
|
|
"num_tokens": 6631317.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.662656164169311,
|
|
"epoch": 0.27857829010566765,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996233413808521,
|
|
"loss": 5.4637,
|
|
"mean_token_accuracy": 0.18195123523473739,
|
|
"num_tokens": 6642009.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.683246278762818,
|
|
"epoch": 0.27905859750240153,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996213558691889,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.172495736181736,
|
|
"num_tokens": 6654713.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.6839197158813475,
|
|
"epoch": 0.27953890489913547,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996193651424848,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.1797851651906967,
|
|
"num_tokens": 6667157.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.665137672424317,
|
|
"epoch": 0.28001921229586935,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499617369200786,
|
|
"loss": 5.5158,
|
|
"mean_token_accuracy": 0.1891197681427002,
|
|
"num_tokens": 6679573.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.741504096984864,
|
|
"epoch": 0.2804995196926033,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996153680441389,
|
|
"loss": 5.5958,
|
|
"mean_token_accuracy": 0.17464567720890045,
|
|
"num_tokens": 6691768.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.721974849700928,
|
|
"epoch": 0.28097982708933716,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049961336167259,
|
|
"loss": 5.556,
|
|
"mean_token_accuracy": 0.17392836958169938,
|
|
"num_tokens": 6701964.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.678666019439698,
|
|
"epoch": 0.2814601344860711,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996113500861857,
|
|
"loss": 5.5394,
|
|
"mean_token_accuracy": 0.1783669501543045,
|
|
"num_tokens": 6713506.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.680933046340942,
|
|
"epoch": 0.281940441882805,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996093332849729,
|
|
"loss": 5.5647,
|
|
"mean_token_accuracy": 0.1761838361620903,
|
|
"num_tokens": 6724616.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.70354528427124,
|
|
"epoch": 0.2824207492795389,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996073112689983,
|
|
"loss": 5.5319,
|
|
"mean_token_accuracy": 0.18018208295106888,
|
|
"num_tokens": 6735054.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.704903030395508,
|
|
"epoch": 0.2829010566762728,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996052840383088,
|
|
"loss": 5.589,
|
|
"mean_token_accuracy": 0.18162762224674225,
|
|
"num_tokens": 6746756.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.67103385925293,
|
|
"epoch": 0.28338136407300674,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996032515929516,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.18400953710079193,
|
|
"num_tokens": 6759566.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.649921560287476,
|
|
"epoch": 0.2838616714697406,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996012139329738,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.18114203959703445,
|
|
"num_tokens": 6771375.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.739535665512085,
|
|
"epoch": 0.28434197886647455,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995991710584228,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.1726598024368286,
|
|
"num_tokens": 6783252.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.614906644821167,
|
|
"epoch": 0.28482228626320844,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995971229693459,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.17417452335357667,
|
|
"num_tokens": 6795525.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.7367006778717045,
|
|
"epoch": 0.28530259365994237,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995950696657909,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.18741291463375093,
|
|
"num_tokens": 6807212.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.595437860488891,
|
|
"epoch": 0.28578290105667625,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995930111478051,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.1817941963672638,
|
|
"num_tokens": 6819367.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.637096786499024,
|
|
"epoch": 0.2862632084534102,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995909474154365,
|
|
"loss": 5.5174,
|
|
"mean_token_accuracy": 0.18265894204378127,
|
|
"num_tokens": 6830405.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.62329068183899,
|
|
"epoch": 0.28674351585014407,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995888784687331,
|
|
"loss": 5.4952,
|
|
"mean_token_accuracy": 0.1821579173207283,
|
|
"num_tokens": 6841479.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.622311162948608,
|
|
"epoch": 0.287223823246878,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995868043077428,
|
|
"loss": 5.5304,
|
|
"mean_token_accuracy": 0.1803388327360153,
|
|
"num_tokens": 6851585.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.658223676681518,
|
|
"epoch": 0.2877041306436119,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995847249325137,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.1853910952806473,
|
|
"num_tokens": 6863176.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.698240089416504,
|
|
"epoch": 0.2881844380403458,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995826403430942,
|
|
"loss": 5.5613,
|
|
"mean_token_accuracy": 0.18125778138637544,
|
|
"num_tokens": 6874021.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2881844380403458,
|
|
"eval_entropy": 5.4392175834856635,
|
|
"eval_loss": 5.524839878082275,
|
|
"eval_mean_token_accuracy": 0.1890813923326899,
|
|
"eval_num_tokens": 6874021.0,
|
|
"eval_runtime": 20.7338,
|
|
"eval_samples_per_second": 1582.678,
|
|
"eval_steps_per_second": 197.841,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.700993347167969,
|
|
"epoch": 0.2886647454370797,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995805505395328,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.17984089851379395,
|
|
"num_tokens": 6884999.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.678546047210693,
|
|
"epoch": 0.28914505283381364,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995784555218778,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.18251369148492813,
|
|
"num_tokens": 6897021.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.577228927612305,
|
|
"epoch": 0.2896253602305475,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995763552901779,
|
|
"loss": 5.5079,
|
|
"mean_token_accuracy": 0.1816476598381996,
|
|
"num_tokens": 6908320.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.693873882293701,
|
|
"epoch": 0.29010566762728146,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995742498444818,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.18809738755226135,
|
|
"num_tokens": 6919957.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.694812393188476,
|
|
"epoch": 0.2905859750240154,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995721391848387,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.1813945174217224,
|
|
"num_tokens": 6930531.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.677816247940063,
|
|
"epoch": 0.2910662824207493,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995700233112972,
|
|
"loss": 5.5802,
|
|
"mean_token_accuracy": 0.17819592505693435,
|
|
"num_tokens": 6942556.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.662592124938965,
|
|
"epoch": 0.2915465898174832,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995679022239066,
|
|
"loss": 5.5308,
|
|
"mean_token_accuracy": 0.18774571269750595,
|
|
"num_tokens": 6954410.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.652567958831787,
|
|
"epoch": 0.2920268972142171,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995657759227162,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.17681581825017928,
|
|
"num_tokens": 6964970.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.637769889831543,
|
|
"epoch": 0.29250720461095103,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995636444077751,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.1918710544705391,
|
|
"num_tokens": 6976016.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.602601861953735,
|
|
"epoch": 0.2929875120076849,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995615076791333,
|
|
"loss": 5.4599,
|
|
"mean_token_accuracy": 0.1865808606147766,
|
|
"num_tokens": 6987199.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.6089927673339846,
|
|
"epoch": 0.29346781940441885,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995593657368399,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.19195563346147537,
|
|
"num_tokens": 6999174.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.653221988677979,
|
|
"epoch": 0.29394812680115273,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499557218580945,
|
|
"loss": 5.5526,
|
|
"mean_token_accuracy": 0.1775237575173378,
|
|
"num_tokens": 7012148.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.551672124862671,
|
|
"epoch": 0.29442843419788667,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995550662114981,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.1860169753432274,
|
|
"num_tokens": 7023238.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.6040300846099855,
|
|
"epoch": 0.29490874159462055,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995529086285495,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.18213031440973282,
|
|
"num_tokens": 7034944.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.660197782516479,
|
|
"epoch": 0.2953890489913545,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499550745832149,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.1897702306509018,
|
|
"num_tokens": 7046880.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.606032466888427,
|
|
"epoch": 0.29586935638808837,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995485778223471,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.18246425986289977,
|
|
"num_tokens": 7057678.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.530951976776123,
|
|
"epoch": 0.2963496637848223,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995464045991939,
|
|
"loss": 5.4289,
|
|
"mean_token_accuracy": 0.18984924107789994,
|
|
"num_tokens": 7068336.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.612528896331787,
|
|
"epoch": 0.2968299711815562,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049954422616274,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.1788366675376892,
|
|
"num_tokens": 7080341.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.7698705196380615,
|
|
"epoch": 0.2973102785782901,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995420425130359,
|
|
"loss": 5.6488,
|
|
"mean_token_accuracy": 0.17575520128011704,
|
|
"num_tokens": 7090618.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.592949104309082,
|
|
"epoch": 0.297790585975024,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995398536501324,
|
|
"loss": 5.3945,
|
|
"mean_token_accuracy": 0.19016729593276976,
|
|
"num_tokens": 7101843.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.547535753250122,
|
|
"epoch": 0.29827089337175794,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995376595740801,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.18589547425508499,
|
|
"num_tokens": 7112014.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.645080947875977,
|
|
"epoch": 0.2987512007684918,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995354602849302,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.17661455273628235,
|
|
"num_tokens": 7123860.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.68672022819519,
|
|
"epoch": 0.29923150816522576,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995332557827337,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.1843189463019371,
|
|
"num_tokens": 7135901.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.60950345993042,
|
|
"epoch": 0.29971181556195964,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995310460675416,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.19353332966566086,
|
|
"num_tokens": 7148743.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.700359869003296,
|
|
"epoch": 0.3001921229586936,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995288311394053,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.1854911118745804,
|
|
"num_tokens": 7160731.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.662644529342652,
|
|
"epoch": 0.30067243035542746,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995266109983764,
|
|
"loss": 5.5154,
|
|
"mean_token_accuracy": 0.18299192190170288,
|
|
"num_tokens": 7172861.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.613388013839722,
|
|
"epoch": 0.3011527377521614,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995243856445062,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.180388443171978,
|
|
"num_tokens": 7183954.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.5486509799957275,
|
|
"epoch": 0.3016330451488953,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995221550778466,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.18174690902233123,
|
|
"num_tokens": 7195466.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.612729692459107,
|
|
"epoch": 0.3021133525456292,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995199192984491,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.19040560573339463,
|
|
"num_tokens": 7207173.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.657872819900513,
|
|
"epoch": 0.3025936599423631,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995176783063657,
|
|
"loss": 5.5693,
|
|
"mean_token_accuracy": 0.18644312173128127,
|
|
"num_tokens": 7220095.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.569757556915283,
|
|
"epoch": 0.30307396733909703,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995154321016487,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.1882634222507477,
|
|
"num_tokens": 7230664.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.642200469970703,
|
|
"epoch": 0.3035542747358309,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995131806843499,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.18630266934633255,
|
|
"num_tokens": 7241278.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.545270013809204,
|
|
"epoch": 0.30403458213256485,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995109240545218,
|
|
"loss": 5.5928,
|
|
"mean_token_accuracy": 0.1777158111333847,
|
|
"num_tokens": 7252999.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.653474807739258,
|
|
"epoch": 0.3045148895292987,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995086622122167,
|
|
"loss": 5.4169,
|
|
"mean_token_accuracy": 0.1864437311887741,
|
|
"num_tokens": 7263949.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.639758348464966,
|
|
"epoch": 0.30499519692603266,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995063951574871,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.18542171269655228,
|
|
"num_tokens": 7275467.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.585669755935669,
|
|
"epoch": 0.30547550432276654,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995041228903856,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.19193329364061357,
|
|
"num_tokens": 7285534.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.6947675228118895,
|
|
"epoch": 0.3059558117195005,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499501845410965,
|
|
"loss": 5.5569,
|
|
"mean_token_accuracy": 0.1815490484237671,
|
|
"num_tokens": 7297252.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.607858324050904,
|
|
"epoch": 0.30643611911623436,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004994995627192781,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.19153623431921005,
|
|
"num_tokens": 7308492.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.569702529907227,
|
|
"epoch": 0.3069164265129683,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994972748153781,
|
|
"loss": 5.4581,
|
|
"mean_token_accuracy": 0.18491947501897812,
|
|
"num_tokens": 7319703.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.674600601196289,
|
|
"epoch": 0.30739673390970224,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499494981699318,
|
|
"loss": 5.4274,
|
|
"mean_token_accuracy": 0.1937693625688553,
|
|
"num_tokens": 7331022.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.56959900856018,
|
|
"epoch": 0.3078770413064361,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499492683371151,
|
|
"loss": 5.4772,
|
|
"mean_token_accuracy": 0.18553764522075653,
|
|
"num_tokens": 7342977.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.66892671585083,
|
|
"epoch": 0.30835734870317005,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994903798309306,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.18036793321371078,
|
|
"num_tokens": 7353227.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.670237398147583,
|
|
"epoch": 0.30883765609990393,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994880710787102,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.1748569056391716,
|
|
"num_tokens": 7364165.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.555734395980835,
|
|
"epoch": 0.30931796349663787,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994857571145432,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.18816640377044677,
|
|
"num_tokens": 7374800.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.496872520446777,
|
|
"epoch": 0.30979827089337175,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994834379384837,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.1932916134595871,
|
|
"num_tokens": 7386360.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.606559085845947,
|
|
"epoch": 0.3102785782901057,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994811135505851,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.18842349499464034,
|
|
"num_tokens": 7397066.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.683773517608643,
|
|
"epoch": 0.31075888568683957,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994787839509018,
|
|
"loss": 5.5188,
|
|
"mean_token_accuracy": 0.1811457246541977,
|
|
"num_tokens": 7408349.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.629186201095581,
|
|
"epoch": 0.3112391930835735,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994764491394876,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.17683551460504532,
|
|
"num_tokens": 7420343.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.65942530632019,
|
|
"epoch": 0.3117195004803074,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994741091163969,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.18691066205501555,
|
|
"num_tokens": 7431683.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.466778755187988,
|
|
"epoch": 0.3121998078770413,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499471763881684,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.1865973576903343,
|
|
"num_tokens": 7443327.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.634066247940064,
|
|
"epoch": 0.3126801152737752,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994694134354031,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.18632208704948425,
|
|
"num_tokens": 7454002.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.543521547317505,
|
|
"epoch": 0.31316042267050914,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499467057777609,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.18688408136367798,
|
|
"num_tokens": 7464074.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.55138783454895,
|
|
"epoch": 0.313640730067243,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994646969083565,
|
|
"loss": 5.3983,
|
|
"mean_token_accuracy": 0.19326114803552627,
|
|
"num_tokens": 7475543.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.635407209396362,
|
|
"epoch": 0.31412103746397696,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994623308277002,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.18384750932455063,
|
|
"num_tokens": 7486818.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.62159948348999,
|
|
"epoch": 0.31460134486071084,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499459959535695,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.18008041083812715,
|
|
"num_tokens": 7499046.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.600229930877686,
|
|
"epoch": 0.3150816522574448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994575830323962,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.18267867863178253,
|
|
"num_tokens": 7509853.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.477385759353638,
|
|
"epoch": 0.31556195965417866,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994552013178586,
|
|
"loss": 5.2819,
|
|
"mean_token_accuracy": 0.1905076265335083,
|
|
"num_tokens": 7521091.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.560299873352051,
|
|
"epoch": 0.3160422670509126,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499452814392138,
|
|
"loss": 5.4164,
|
|
"mean_token_accuracy": 0.1956005111336708,
|
|
"num_tokens": 7531317.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.59887285232544,
|
|
"epoch": 0.3165225744476465,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994504222552894,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.18225086703896523,
|
|
"num_tokens": 7542822.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.675664710998535,
|
|
"epoch": 0.3170028818443804,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994480249073684,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.17975055873394014,
|
|
"num_tokens": 7552434.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.594845724105835,
|
|
"epoch": 0.3174831892411143,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994456223484308,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.19091499149799346,
|
|
"num_tokens": 7563895.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.409893989562988,
|
|
"epoch": 0.31796349663784823,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994432145785323,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.19512586593627929,
|
|
"num_tokens": 7575391.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.639042043685913,
|
|
"epoch": 0.3184438040345821,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994408015977288,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.19067961126565933,
|
|
"num_tokens": 7587119.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.650514125823975,
|
|
"epoch": 0.31892411143131605,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994383834060764,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.18139485269784927,
|
|
"num_tokens": 7598615.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.662230205535889,
|
|
"epoch": 0.31940441882804993,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994359600036311,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.19163189232349395,
|
|
"num_tokens": 7610159.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.627119827270508,
|
|
"epoch": 0.31988472622478387,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994335313904493,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.1873135432600975,
|
|
"num_tokens": 7620922.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.546042776107788,
|
|
"epoch": 0.32036503362151775,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994310975665873,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.19363973736763002,
|
|
"num_tokens": 7632343.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.685207319259644,
|
|
"epoch": 0.3208453410182517,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994286585321017,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.17316349148750304,
|
|
"num_tokens": 7644748.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.689049005508423,
|
|
"epoch": 0.32132564841498557,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499426214287049,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.19029539227485656,
|
|
"num_tokens": 7655449.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.639818286895752,
|
|
"epoch": 0.3218059558117195,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994237648314862,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.18956416994333267,
|
|
"num_tokens": 7665623.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.548650217056275,
|
|
"epoch": 0.3222862632084534,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994213101654697,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.19147212505340577,
|
|
"num_tokens": 7676860.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.647919225692749,
|
|
"epoch": 0.3227665706051873,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499418850289057,
|
|
"loss": 5.5559,
|
|
"mean_token_accuracy": 0.18325860053300858,
|
|
"num_tokens": 7687778.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.633452653884888,
|
|
"epoch": 0.32324687800192126,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994163852023048,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.18514435291290282,
|
|
"num_tokens": 7699154.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.59450101852417,
|
|
"epoch": 0.32372718539865514,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994139149052706,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.18767904341220856,
|
|
"num_tokens": 7711010.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.627596235275268,
|
|
"epoch": 0.3242074927953891,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994114393980117,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.18083676546812058,
|
|
"num_tokens": 7721969.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.615005588531494,
|
|
"epoch": 0.32468780019212296,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.18771904110908508,
|
|
"num_tokens": 7733762.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.603797101974488,
|
|
"epoch": 0.3251681075888569,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994064727530496,
|
|
"loss": 5.4356,
|
|
"mean_token_accuracy": 0.1839058965444565,
|
|
"num_tokens": 7744614.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.560338926315308,
|
|
"epoch": 0.3256484149855908,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994039816154618,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.1955147460103035,
|
|
"num_tokens": 7755799.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.513249158859253,
|
|
"epoch": 0.3261287223823247,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049940148526788,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.1901847615838051,
|
|
"num_tokens": 7768140.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.557335901260376,
|
|
"epoch": 0.3266090297790586,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993989837103618,
|
|
"loss": 5.4366,
|
|
"mean_token_accuracy": 0.19033351689577102,
|
|
"num_tokens": 7778494.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.683393812179565,
|
|
"epoch": 0.3270893371757925,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993964769429657,
|
|
"loss": 5.5064,
|
|
"mean_token_accuracy": 0.1925898015499115,
|
|
"num_tokens": 7789234.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.557097578048706,
|
|
"epoch": 0.3275696445725264,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993939649657498,
|
|
"loss": 5.4937,
|
|
"mean_token_accuracy": 0.18996243476867675,
|
|
"num_tokens": 7800602.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.510222053527832,
|
|
"epoch": 0.32804995196926034,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004993914477787721,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.19364566057920457,
|
|
"num_tokens": 7812803.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.749662780761719,
|
|
"epoch": 0.3285302593659942,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993889253820915,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.17690031826496125,
|
|
"num_tokens": 7825432.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.600550270080566,
|
|
"epoch": 0.32901056676272816,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993863977757663,
|
|
"loss": 5.4376,
|
|
"mean_token_accuracy": 0.18812805712223052,
|
|
"num_tokens": 7837258.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.522640132904053,
|
|
"epoch": 0.32949087415946204,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993838649598552,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.1966621220111847,
|
|
"num_tokens": 7847573.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.63411316871643,
|
|
"epoch": 0.329971181556196,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993813269344171,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.18168777078390122,
|
|
"num_tokens": 7857957.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.580896186828613,
|
|
"epoch": 0.33045148895292986,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993787836995108,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.1964847505092621,
|
|
"num_tokens": 7867996.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.501073503494263,
|
|
"epoch": 0.3309317963496638,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993762352551954,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.1835190922021866,
|
|
"num_tokens": 7879245.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.646635055541992,
|
|
"epoch": 0.3314121037463977,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993736816015301,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.17995858192443848,
|
|
"num_tokens": 7891186.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.6572953224182125,
|
|
"epoch": 0.3318924111431316,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993711227385742,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.19139863401651383,
|
|
"num_tokens": 7902231.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.600442361831665,
|
|
"epoch": 0.3323727185398655,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993685586663871,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.18677273094654084,
|
|
"num_tokens": 7913364.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.820091962814331,
|
|
"epoch": 0.33285302593659943,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993659893850281,
|
|
"loss": 5.6781,
|
|
"mean_token_accuracy": 0.1703316792845726,
|
|
"num_tokens": 7925217.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.581819820404053,
|
|
"epoch": 0.3333333333333333,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993634148945573,
|
|
"loss": 5.4198,
|
|
"mean_token_accuracy": 0.1796149030327797,
|
|
"num_tokens": 7937636.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.565121173858643,
|
|
"epoch": 0.33381364073006725,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993608351950341,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.18050845563411713,
|
|
"num_tokens": 7948958.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.6448219299316404,
|
|
"epoch": 0.33429394812680113,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993582502865185,
|
|
"loss": 5.4741,
|
|
"mean_token_accuracy": 0.1872809574007988,
|
|
"num_tokens": 7960013.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.595401859283447,
|
|
"epoch": 0.33477425552353507,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993556601690706,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.18324995785951614,
|
|
"num_tokens": 7971041.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.632128286361694,
|
|
"epoch": 0.33525456292026895,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993530648427505,
|
|
"loss": 5.5098,
|
|
"mean_token_accuracy": 0.17839510440826417,
|
|
"num_tokens": 7982752.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.637563943862915,
|
|
"epoch": 0.3357348703170029,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993504643076184,
|
|
"loss": 5.3971,
|
|
"mean_token_accuracy": 0.18504412919282914,
|
|
"num_tokens": 7993681.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.538132953643799,
|
|
"epoch": 0.33621517771373677,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993478585637347,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.18824413269758225,
|
|
"num_tokens": 8004727.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.585167694091797,
|
|
"epoch": 0.3366954851104707,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993452476111599,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.1928482621908188,
|
|
"num_tokens": 8015423.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.588391065597534,
|
|
"epoch": 0.3371757925072046,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004993426314499546,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.19309359788894653,
|
|
"num_tokens": 8027911.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.594974565505981,
|
|
"epoch": 0.3376560999039385,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993400100801796,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.18888370990753173,
|
|
"num_tokens": 8038831.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.477750301361084,
|
|
"epoch": 0.3381364073006724,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993373835018956,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.19790522754192352,
|
|
"num_tokens": 8049906.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.484724855422973,
|
|
"epoch": 0.33861671469740634,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993347517151638,
|
|
"loss": 5.4212,
|
|
"mean_token_accuracy": 0.18728912770748138,
|
|
"num_tokens": 8061158.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.6147716522216795,
|
|
"epoch": 0.3390970220941403,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993321147200452,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.18561409711837767,
|
|
"num_tokens": 8071958.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.567511987686157,
|
|
"epoch": 0.33957732949087416,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499329472516601,
|
|
"loss": 5.38,
|
|
"mean_token_accuracy": 0.18467946201562882,
|
|
"num_tokens": 8084068.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.463061094284058,
|
|
"epoch": 0.3400576368876081,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993268251048925,
|
|
"loss": 5.2918,
|
|
"mean_token_accuracy": 0.20272473245859146,
|
|
"num_tokens": 8096132.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.551108026504517,
|
|
"epoch": 0.340537944284342,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993241724849814,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.1927696093916893,
|
|
"num_tokens": 8107327.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.619629001617431,
|
|
"epoch": 0.3410182516810759,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499321514656929,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.18920674920082092,
|
|
"num_tokens": 8118584.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.625332069396973,
|
|
"epoch": 0.3414985590778098,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993188516207972,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.1815608412027359,
|
|
"num_tokens": 8130081.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.557459163665771,
|
|
"epoch": 0.34197886647454373,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993161833766478,
|
|
"loss": 5.441,
|
|
"mean_token_accuracy": 0.18856000006198884,
|
|
"num_tokens": 8141463.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.623035001754761,
|
|
"epoch": 0.3424591738712776,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993135099245426,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.18447892665863036,
|
|
"num_tokens": 8153863.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.488258695602417,
|
|
"epoch": 0.34293948126801155,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993108312645438,
|
|
"loss": 5.3974,
|
|
"mean_token_accuracy": 0.18443325012922288,
|
|
"num_tokens": 8165695.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.602726173400879,
|
|
"epoch": 0.34341978866474543,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993081473967135,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.1891469821333885,
|
|
"num_tokens": 8176456.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.6182811737060545,
|
|
"epoch": 0.34390009606147937,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993054583211143,
|
|
"loss": 5.4567,
|
|
"mean_token_accuracy": 0.1888190761208534,
|
|
"num_tokens": 8189050.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.482992887496948,
|
|
"epoch": 0.34438040345821325,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004993027640378081,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.19064465761184693,
|
|
"num_tokens": 8200011.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.55635633468628,
|
|
"epoch": 0.3448607108549472,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499300064546858,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.19231539517641066,
|
|
"num_tokens": 8211770.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.568660497665405,
|
|
"epoch": 0.34534101825168106,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992973598483264,
|
|
"loss": 5.408,
|
|
"mean_token_accuracy": 0.19162147790193557,
|
|
"num_tokens": 8223582.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.642741394042969,
|
|
"epoch": 0.345821325648415,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499294649942276,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.18496304154396057,
|
|
"num_tokens": 8234336.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.624276733398437,
|
|
"epoch": 0.3463016330451489,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992919348287699,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.18882226347923278,
|
|
"num_tokens": 8244605.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.608572101593017,
|
|
"epoch": 0.3467819404418828,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992892145078711,
|
|
"loss": 5.4808,
|
|
"mean_token_accuracy": 0.18347105085849763,
|
|
"num_tokens": 8255876.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.549061632156372,
|
|
"epoch": 0.3472622478386167,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992864889796427,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.19023108333349228,
|
|
"num_tokens": 8266602.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.546348810195923,
|
|
"epoch": 0.34774255523535064,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004992837582441481,
|
|
"loss": 5.3625,
|
|
"mean_token_accuracy": 0.19489242136478424,
|
|
"num_tokens": 8279804.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.629941320419311,
|
|
"epoch": 0.3482228626320845,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992810223014506,
|
|
"loss": 5.4606,
|
|
"mean_token_accuracy": 0.1908916175365448,
|
|
"num_tokens": 8291020.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.618665075302124,
|
|
"epoch": 0.34870317002881845,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992782811516137,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.19629807025194168,
|
|
"num_tokens": 8302192.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.548134994506836,
|
|
"epoch": 0.34918347742555234,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004992755347947011,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.1896643429994583,
|
|
"num_tokens": 8313649.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.500442028045654,
|
|
"epoch": 0.34966378482228627,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992727832307766,
|
|
"loss": 5.385,
|
|
"mean_token_accuracy": 0.1900986060500145,
|
|
"num_tokens": 8324694.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.660983419418335,
|
|
"epoch": 0.35014409221902015,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992700264599039,
|
|
"loss": 5.5324,
|
|
"mean_token_accuracy": 0.18272839337587357,
|
|
"num_tokens": 8336517.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.593430089950561,
|
|
"epoch": 0.3506243996157541,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992672644821473,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.1796460419893265,
|
|
"num_tokens": 8349001.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.585159015655518,
|
|
"epoch": 0.35110470701248797,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992644972975707,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.1927414983510971,
|
|
"num_tokens": 8361230.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.5338012218475345,
|
|
"epoch": 0.3515850144092219,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992617249062383,
|
|
"loss": 5.3264,
|
|
"mean_token_accuracy": 0.19598029255867006,
|
|
"num_tokens": 8372159.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.557580852508545,
|
|
"epoch": 0.3520653218059558,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992589473082147,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.19024865478277206,
|
|
"num_tokens": 8383228.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.60696702003479,
|
|
"epoch": 0.3525456292026897,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992561645035641,
|
|
"loss": 5.3997,
|
|
"mean_token_accuracy": 0.18926765471696855,
|
|
"num_tokens": 8394582.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.584086465835571,
|
|
"epoch": 0.3530259365994236,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992533764923515,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.18775029927492143,
|
|
"num_tokens": 8406784.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.534383869171142,
|
|
"epoch": 0.35350624399615754,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992505832746412,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.194275338947773,
|
|
"num_tokens": 8418405.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.582950401306152,
|
|
"epoch": 0.3539865513928914,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992477848504983,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.19232997596263884,
|
|
"num_tokens": 8430432.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.566782712936401,
|
|
"epoch": 0.35446685878962536,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004992449812199877,
|
|
"loss": 5.4912,
|
|
"mean_token_accuracy": 0.18145429342985153,
|
|
"num_tokens": 8442423.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.585980749130249,
|
|
"epoch": 0.3549471661863593,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004992421723831745,
|
|
"loss": 5.4931,
|
|
"mean_token_accuracy": 0.18717589229345322,
|
|
"num_tokens": 8454951.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.527453804016114,
|
|
"epoch": 0.3554274735830932,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992393583401239,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.1946762263774872,
|
|
"num_tokens": 8467758.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.585886812210083,
|
|
"epoch": 0.3559077809798271,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992365390909014,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.18967984169721602,
|
|
"num_tokens": 8479728.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.6186473846435545,
|
|
"epoch": 0.356388088376561,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992337146355721,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.18735775500535964,
|
|
"num_tokens": 8492099.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.608113765716553,
|
|
"epoch": 0.35686839577329493,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992308849742019,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.1802011474967003,
|
|
"num_tokens": 8504657.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.57549901008606,
|
|
"epoch": 0.3573487031700288,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992280501068563,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.19084483236074448,
|
|
"num_tokens": 8514728.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.635108757019043,
|
|
"epoch": 0.35782901056676275,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992252100336012,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.18584865778684617,
|
|
"num_tokens": 8525588.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.581790542602539,
|
|
"epoch": 0.35830931796349663,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992223647545027,
|
|
"loss": 5.4877,
|
|
"mean_token_accuracy": 0.18325926661491393,
|
|
"num_tokens": 8537468.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.597702932357788,
|
|
"epoch": 0.35878962536023057,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992195142696266,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.19316060990095138,
|
|
"num_tokens": 8548598.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.409280014038086,
|
|
"epoch": 0.35926993275696445,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992166585790391,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.20413144379854203,
|
|
"num_tokens": 8560301.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.53164644241333,
|
|
"epoch": 0.3597502401536984,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992137976828067,
|
|
"loss": 5.368,
|
|
"mean_token_accuracy": 0.1967419356107712,
|
|
"num_tokens": 8571186.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.545560312271118,
|
|
"epoch": 0.36023054755043227,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992109315809955,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.19761675149202346,
|
|
"num_tokens": 8580725.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.526527690887451,
|
|
"epoch": 0.3607108549471662,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992080602736725,
|
|
"loss": 5.5078,
|
|
"mean_token_accuracy": 0.1807180315256119,
|
|
"num_tokens": 8594598.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.6951195240020756,
|
|
"epoch": 0.3611911623439001,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992051837609039,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.18285927772521973,
|
|
"num_tokens": 8606733.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.609960460662842,
|
|
"epoch": 0.361671469740634,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992023020427568,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.1881916657090187,
|
|
"num_tokens": 8618863.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.424804210662842,
|
|
"epoch": 0.3621517771373679,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991994151192979,
|
|
"loss": 5.2702,
|
|
"mean_token_accuracy": 0.1962995320558548,
|
|
"num_tokens": 8629270.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.53543701171875,
|
|
"epoch": 0.36263208453410184,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991965229905943,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.19050425440073013,
|
|
"num_tokens": 8641363.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.642627811431884,
|
|
"epoch": 0.3631123919308357,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991936256567133,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.1923316612839699,
|
|
"num_tokens": 8653233.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.533376264572143,
|
|
"epoch": 0.36359269932756966,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499190723117722,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.18614102751016617,
|
|
"num_tokens": 8665192.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.642783832550049,
|
|
"epoch": 0.36407300672430354,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991878153736877,
|
|
"loss": 5.5196,
|
|
"mean_token_accuracy": 0.18100242018699647,
|
|
"num_tokens": 8677669.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.474308347702026,
|
|
"epoch": 0.3645533141210375,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991849024246781,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.19570468962192536,
|
|
"num_tokens": 8688002.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.516477632522583,
|
|
"epoch": 0.36503362151777136,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991819842707608,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.18995878249406814,
|
|
"num_tokens": 8698396.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.623310947418213,
|
|
"epoch": 0.3655139289145053,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991790609120035,
|
|
"loss": 5.3885,
|
|
"mean_token_accuracy": 0.19130971878767014,
|
|
"num_tokens": 8711135.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.50729808807373,
|
|
"epoch": 0.3659942363112392,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499176132348474,
|
|
"loss": 5.4236,
|
|
"mean_token_accuracy": 0.19352682530879975,
|
|
"num_tokens": 8723707.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.572604703903198,
|
|
"epoch": 0.3664745437079731,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991731985802405,
|
|
"loss": 5.3627,
|
|
"mean_token_accuracy": 0.1964678570628166,
|
|
"num_tokens": 8734193.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.517657279968262,
|
|
"epoch": 0.366954851104707,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991702596073708,
|
|
"loss": 5.4572,
|
|
"mean_token_accuracy": 0.18392777889966966,
|
|
"num_tokens": 8745619.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.462949419021607,
|
|
"epoch": 0.36743515850144093,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991673154299335,
|
|
"loss": 5.3582,
|
|
"mean_token_accuracy": 0.19223012924194335,
|
|
"num_tokens": 8757331.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.527809762954712,
|
|
"epoch": 0.3679154658981748,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991643660479967,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.19106081277132034,
|
|
"num_tokens": 8768840.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.562812089920044,
|
|
"epoch": 0.36839577329490875,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991614114616289,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.19561284482479097,
|
|
"num_tokens": 8781214.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.584686708450318,
|
|
"epoch": 0.3688760806916426,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991584516708988,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.1916833609342575,
|
|
"num_tokens": 8791645.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.599692010879517,
|
|
"epoch": 0.36935638808837656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991554866758751,
|
|
"loss": 5.5787,
|
|
"mean_token_accuracy": 0.17887818589806556,
|
|
"num_tokens": 8803286.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.589219093322754,
|
|
"epoch": 0.36983669548511044,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991525164766265,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.18918564915657043,
|
|
"num_tokens": 8814207.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.53467755317688,
|
|
"epoch": 0.3703170028818444,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991495410732222,
|
|
"loss": 5.417,
|
|
"mean_token_accuracy": 0.18368727713823318,
|
|
"num_tokens": 8825540.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.591689157485962,
|
|
"epoch": 0.37079731027857826,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991465604657311,
|
|
"loss": 5.547,
|
|
"mean_token_accuracy": 0.17688291668891906,
|
|
"num_tokens": 8838182.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.570683383941651,
|
|
"epoch": 0.3712776176753122,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991435746542224,
|
|
"loss": 5.4198,
|
|
"mean_token_accuracy": 0.19610581248998643,
|
|
"num_tokens": 8850211.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.517876291275025,
|
|
"epoch": 0.37175792507204614,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991405836387655,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.182083423435688,
|
|
"num_tokens": 8862804.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.559181594848633,
|
|
"epoch": 0.37223823246878,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991375874194298,
|
|
"loss": 5.405,
|
|
"mean_token_accuracy": 0.18535222709178925,
|
|
"num_tokens": 8874112.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.540090560913086,
|
|
"epoch": 0.37271853986551395,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499134585996285,
|
|
"loss": 5.4274,
|
|
"mean_token_accuracy": 0.18555488735437392,
|
|
"num_tokens": 8885114.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.529178762435913,
|
|
"epoch": 0.37319884726224783,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991315793694004,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.19386369735002518,
|
|
"num_tokens": 8895555.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.464783573150635,
|
|
"epoch": 0.37367915465898177,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991285675388463,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.20528001785278321,
|
|
"num_tokens": 8906073.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.548325109481811,
|
|
"epoch": 0.37415946205571565,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991255505046922,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.18886378407478333,
|
|
"num_tokens": 8916587.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.586668920516968,
|
|
"epoch": 0.3746397694524496,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991225282670083,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.1910933658480644,
|
|
"num_tokens": 8927923.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.475469779968262,
|
|
"epoch": 0.37512007684918347,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499119500825865,
|
|
"loss": 5.405,
|
|
"mean_token_accuracy": 0.1913732722401619,
|
|
"num_tokens": 8939939.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.515975379943848,
|
|
"epoch": 0.3756003842459174,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991164681813323,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.19644259959459304,
|
|
"num_tokens": 8951748.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.5175879955291744,
|
|
"epoch": 0.3760806916426513,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991134303334807,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.201249860227108,
|
|
"num_tokens": 8962922.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.4236226081848145,
|
|
"epoch": 0.3765609990393852,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991103872823807,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.1982575923204422,
|
|
"num_tokens": 8974013.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.478136730194092,
|
|
"epoch": 0.3770413064361191,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499107339028103,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.19188770800828933,
|
|
"num_tokens": 8986032.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.5743492603302,
|
|
"epoch": 0.37752161383285304,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991042855707184,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.19044692516326905,
|
|
"num_tokens": 8996889.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.498291397094727,
|
|
"epoch": 0.3780019212295869,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991012269102977,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.19032660573720933,
|
|
"num_tokens": 9007594.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.414751243591309,
|
|
"epoch": 0.37848222862632086,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990981630469119,
|
|
"loss": 5.33,
|
|
"mean_token_accuracy": 0.19158338755369186,
|
|
"num_tokens": 9018097.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.559832191467285,
|
|
"epoch": 0.37896253602305474,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990950939806323,
|
|
"loss": 5.4603,
|
|
"mean_token_accuracy": 0.1812780097126961,
|
|
"num_tokens": 9029554.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.55887622833252,
|
|
"epoch": 0.3794428434197887,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00049909201971153,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.19056572914123535,
|
|
"num_tokens": 9042518.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.506370973587036,
|
|
"epoch": 0.37992315081652256,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990889402396763,
|
|
"loss": 5.3644,
|
|
"mean_token_accuracy": 0.19444247484207153,
|
|
"num_tokens": 9054524.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.506084156036377,
|
|
"epoch": 0.3804034582132565,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990858555651431,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.18973129987716675,
|
|
"num_tokens": 9065375.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.506417083740234,
|
|
"epoch": 0.3808837656099904,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990827656880015,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.19565317034721375,
|
|
"num_tokens": 9076338.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.502223873138428,
|
|
"epoch": 0.3813640730067243,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990796706083235,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.19122555553913118,
|
|
"num_tokens": 9088407.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.494334125518799,
|
|
"epoch": 0.3818443804034582,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990765703261809,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.19051105678081512,
|
|
"num_tokens": 9099833.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.3872777938842775,
|
|
"epoch": 0.38232468780019213,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990734648416458,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.19974401593208313,
|
|
"num_tokens": 9111126.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.513306760787964,
|
|
"epoch": 0.382804995196926,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990703541547901,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.1958555817604065,
|
|
"num_tokens": 9121979.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.5826314926147464,
|
|
"epoch": 0.38328530259365995,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990672382656863,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.1911478102207184,
|
|
"num_tokens": 9132929.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.551815366744995,
|
|
"epoch": 0.38376560999039383,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990641171744064,
|
|
"loss": 5.3495,
|
|
"mean_token_accuracy": 0.19590957462787628,
|
|
"num_tokens": 9143903.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.567360591888428,
|
|
"epoch": 0.38424591738712777,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990609908810231,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.19291835129261017,
|
|
"num_tokens": 9154416.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.54535870552063,
|
|
"epoch": 0.38472622478386165,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990578593856089,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.19129804521799088,
|
|
"num_tokens": 9165613.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.470605134963989,
|
|
"epoch": 0.3852065321805956,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990547226882366,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.1947087824344635,
|
|
"num_tokens": 9177884.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.600809383392334,
|
|
"epoch": 0.38568683957732947,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990515807889788,
|
|
"loss": 5.4902,
|
|
"mean_token_accuracy": 0.1800956666469574,
|
|
"num_tokens": 9190041.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.623603248596192,
|
|
"epoch": 0.3861671469740634,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990484336879087,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.19113666117191314,
|
|
"num_tokens": 9202390.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.474275207519531,
|
|
"epoch": 0.3866474543707973,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990452813850992,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.19006328135728837,
|
|
"num_tokens": 9213437.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.555831718444824,
|
|
"epoch": 0.3871277617675312,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990421238806236,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.1827810600399971,
|
|
"num_tokens": 9226310.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.534276008605957,
|
|
"epoch": 0.38760806916426516,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990389611745551,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.1896564930677414,
|
|
"num_tokens": 9236271.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.5598194122314455,
|
|
"epoch": 0.38808837656099904,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990357932669672,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.1913477137684822,
|
|
"num_tokens": 9247755.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.499641227722168,
|
|
"epoch": 0.388568683957733,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990326201579335,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.20061542093753815,
|
|
"num_tokens": 9259821.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.5496776580810545,
|
|
"epoch": 0.38904899135446686,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990294418475274,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.18962285965681075,
|
|
"num_tokens": 9270663.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.5318115234375,
|
|
"epoch": 0.3895292987512008,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990262583358231,
|
|
"loss": 5.4028,
|
|
"mean_token_accuracy": 0.1873584508895874,
|
|
"num_tokens": 9282588.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.505263233184815,
|
|
"epoch": 0.3900096061479347,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990230696228943,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.18254790604114532,
|
|
"num_tokens": 9293368.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.559754848480225,
|
|
"epoch": 0.3904899135446686,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990198757088149,
|
|
"loss": 5.4642,
|
|
"mean_token_accuracy": 0.18748684972524643,
|
|
"num_tokens": 9305962.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.516952753067017,
|
|
"epoch": 0.3909702209414025,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990166765936593,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.19609273076057435,
|
|
"num_tokens": 9317955.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.497630071640015,
|
|
"epoch": 0.3914505283381364,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990134722775016,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.19048384428024293,
|
|
"num_tokens": 9329491.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.501287317276001,
|
|
"epoch": 0.3919308357348703,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990102627604162,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.19690733551979064,
|
|
"num_tokens": 9341612.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.572618722915649,
|
|
"epoch": 0.39241114313160425,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990070480424778,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.18688351958990096,
|
|
"num_tokens": 9352302.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.529020738601685,
|
|
"epoch": 0.3928914505283381,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990038281237608,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.19336572736501695,
|
|
"num_tokens": 9363303.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.446750688552856,
|
|
"epoch": 0.39337175792507206,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990006030043401,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.1869595780968666,
|
|
"num_tokens": 9375878.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.538749361038208,
|
|
"epoch": 0.39385206532180594,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989973726842906,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.1941888928413391,
|
|
"num_tokens": 9388342.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.456574630737305,
|
|
"epoch": 0.3943323727185399,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989941371636872,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.19488134682178498,
|
|
"num_tokens": 9399047.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.524734115600586,
|
|
"epoch": 0.39481268011527376,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989908964426051,
|
|
"loss": 5.3773,
|
|
"mean_token_accuracy": 0.1977031409740448,
|
|
"num_tokens": 9410172.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.5667112350463865,
|
|
"epoch": 0.3952929875120077,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989876505211194,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.18664929568767546,
|
|
"num_tokens": 9422287.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.591302490234375,
|
|
"epoch": 0.3957732949087416,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989843993993056,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.19570473879575728,
|
|
"num_tokens": 9433709.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.40889949798584,
|
|
"epoch": 0.3962536023054755,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989811430772392,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.19686949849128724,
|
|
"num_tokens": 9445138.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.490507650375366,
|
|
"epoch": 0.3967339097022094,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989778815549957,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.18909133076667786,
|
|
"num_tokens": 9455263.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.5528974533081055,
|
|
"epoch": 0.39721421709894333,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989746148326508,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.19381564110517502,
|
|
"num_tokens": 9465491.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.424878263473511,
|
|
"epoch": 0.3976945244956772,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989713429102805,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.1861468955874443,
|
|
"num_tokens": 9477601.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.505374145507813,
|
|
"epoch": 0.39817483189241115,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004989680657879607,
|
|
"loss": 5.3778,
|
|
"mean_token_accuracy": 0.1953922465443611,
|
|
"num_tokens": 9489385.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.459268808364868,
|
|
"epoch": 0.39865513928914503,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989647834657675,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.2002091407775879,
|
|
"num_tokens": 9501131.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.464940404891967,
|
|
"epoch": 0.39913544668587897,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498961495943777,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.19082237184047698,
|
|
"num_tokens": 9513094.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.63197512626648,
|
|
"epoch": 0.39961575408261285,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989582032220656,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.18408708721399308,
|
|
"num_tokens": 9524538.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.56934609413147,
|
|
"epoch": 0.4000960614793468,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989549053007096,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.20425097048282623,
|
|
"num_tokens": 9535284.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.497316694259643,
|
|
"epoch": 0.40057636887608067,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989516021797858,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.1898416116833687,
|
|
"num_tokens": 9546472.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.518751907348633,
|
|
"epoch": 0.4010566762728146,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498948293859371,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.18592777997255325,
|
|
"num_tokens": 9558358.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.598344326019287,
|
|
"epoch": 0.4015369836695485,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004989449803395415,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.19122905135154725,
|
|
"num_tokens": 9570653.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.527167081832886,
|
|
"epoch": 0.4020172910662824,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989416616203747,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.19405449777841569,
|
|
"num_tokens": 9582150.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.54949803352356,
|
|
"epoch": 0.4024975984630163,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989383377019476,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.1968682125210762,
|
|
"num_tokens": 9592462.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.459809732437134,
|
|
"epoch": 0.40297790585975024,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989350085843371,
|
|
"loss": 5.3186,
|
|
"mean_token_accuracy": 0.19509333968162537,
|
|
"num_tokens": 9604027.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.4236900329589846,
|
|
"epoch": 0.4034582132564842,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004989316742676207,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.19438586235046387,
|
|
"num_tokens": 9616325.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.422830820083618,
|
|
"epoch": 0.40393852065321806,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989283347518757,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.1953098714351654,
|
|
"num_tokens": 9628133.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.626201915740967,
|
|
"epoch": 0.404418828049952,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989249900371797,
|
|
"loss": 5.4747,
|
|
"mean_token_accuracy": 0.18496284484863282,
|
|
"num_tokens": 9639686.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.500379610061645,
|
|
"epoch": 0.4048991354466859,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989216401236103,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.1925930693745613,
|
|
"num_tokens": 9650222.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.430653524398804,
|
|
"epoch": 0.4053794428434198,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989182850112455,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.20574321448802949,
|
|
"num_tokens": 9661792.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.5395571231842045,
|
|
"epoch": 0.4058597502401537,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989149247001629,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.18767669349908828,
|
|
"num_tokens": 9673000.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.5615856647491455,
|
|
"epoch": 0.40634005763688763,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989115591904407,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.19707095324993135,
|
|
"num_tokens": 9685253.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.451553249359131,
|
|
"epoch": 0.4068203650336215,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989081884821569,
|
|
"loss": 5.3231,
|
|
"mean_token_accuracy": 0.19093127846717833,
|
|
"num_tokens": 9697245.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.4586076736450195,
|
|
"epoch": 0.40730067243035545,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004989048125753899,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.19377574026584626,
|
|
"num_tokens": 9710095.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.475905895233154,
|
|
"epoch": 0.40778097982708933,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498901431470218,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.20166248977184295,
|
|
"num_tokens": 9721488.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.341732978820801,
|
|
"epoch": 0.40826128722382327,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988980451667198,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.20070856511592866,
|
|
"num_tokens": 9733280.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.480173921585083,
|
|
"epoch": 0.40874159462055715,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988946536649737,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.18952195197343827,
|
|
"num_tokens": 9744514.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.479455947875977,
|
|
"epoch": 0.4092219020172911,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988912569650585,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.19506131410598754,
|
|
"num_tokens": 9754931.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.408810377120972,
|
|
"epoch": 0.40970220941402496,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004988878550670533,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.19845788776874543,
|
|
"num_tokens": 9765635.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.524256181716919,
|
|
"epoch": 0.4101825168107589,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988844479710369,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.1866440549492836,
|
|
"num_tokens": 9777512.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.5750714302062985,
|
|
"epoch": 0.4106628242074928,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988810356770884,
|
|
"loss": 5.4248,
|
|
"mean_token_accuracy": 0.1778908535838127,
|
|
"num_tokens": 9790128.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.4882549285888675,
|
|
"epoch": 0.4111431316042267,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000498877618185287,
|
|
"loss": 5.3427,
|
|
"mean_token_accuracy": 0.19739877730607985,
|
|
"num_tokens": 9802549.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.437657594680786,
|
|
"epoch": 0.4116234390009606,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988741954957121,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.19505833089351654,
|
|
"num_tokens": 9813736.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.389750909805298,
|
|
"epoch": 0.41210374639769454,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988707676084432,
|
|
"loss": 5.286,
|
|
"mean_token_accuracy": 0.20560728162527084,
|
|
"num_tokens": 9823785.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.458524465560913,
|
|
"epoch": 0.4125840537944284,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988673345235597,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.1967891976237297,
|
|
"num_tokens": 9834910.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.488246631622315,
|
|
"epoch": 0.41306436119116235,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004988638962411416,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.19697232395410538,
|
|
"num_tokens": 9845593.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.402709579467773,
|
|
"epoch": 0.41354466858789624,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004988604527612685,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.21107767671346664,
|
|
"num_tokens": 9856763.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.507501029968262,
|
|
"epoch": 0.4140249759846302,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988570040840205,
|
|
"loss": 5.4395,
|
|
"mean_token_accuracy": 0.18462781310081483,
|
|
"num_tokens": 9869528.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.452263307571411,
|
|
"epoch": 0.41450528338136405,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988535502094774,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.19700846821069717,
|
|
"num_tokens": 9881170.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.508918333053589,
|
|
"epoch": 0.414985590778098,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988500911377198,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.18960152417421341,
|
|
"num_tokens": 9893119.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.370126962661743,
|
|
"epoch": 0.41546589817483187,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988466268688276,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.20651557743549348,
|
|
"num_tokens": 9905339.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.523185920715332,
|
|
"epoch": 0.4159462055715658,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988431574028814,
|
|
"loss": 5.353,
|
|
"mean_token_accuracy": 0.19940332025289537,
|
|
"num_tokens": 9917500.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.49964451789856,
|
|
"epoch": 0.4164265129682997,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988396827399618,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.1904998764395714,
|
|
"num_tokens": 9929667.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.51170916557312,
|
|
"epoch": 0.4169068203650336,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988362028801495,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.19802108108997346,
|
|
"num_tokens": 9941102.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.4384832859039305,
|
|
"epoch": 0.4173871277617675,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988327178235253,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.20404383093118666,
|
|
"num_tokens": 9951986.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.39904203414917,
|
|
"epoch": 0.41786743515850144,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004988292275701699,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.1993297517299652,
|
|
"num_tokens": 9964486.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.455586671829224,
|
|
"epoch": 0.4183477425552353,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988257321201646,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.19409458339214325,
|
|
"num_tokens": 9975909.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.496417570114136,
|
|
"epoch": 0.41882804995196926,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988222314735902,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.19777753502130507,
|
|
"num_tokens": 9986951.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.5789155006408695,
|
|
"epoch": 0.41930835734870314,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988187256305284,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.1878629818558693,
|
|
"num_tokens": 9999234.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.499477052688599,
|
|
"epoch": 0.4197886647454371,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988152145910603,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.20171295255422592,
|
|
"num_tokens": 10010178.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.425793218612671,
|
|
"epoch": 0.420268972142171,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988116983552675,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.19647194296121598,
|
|
"num_tokens": 10021183.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.567107248306274,
|
|
"epoch": 0.4207492795389049,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988081769232317,
|
|
"loss": 5.5645,
|
|
"mean_token_accuracy": 0.18234878778457642,
|
|
"num_tokens": 10033686.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.449434423446656,
|
|
"epoch": 0.42122958693563883,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988046502950346,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.1972568526864052,
|
|
"num_tokens": 10045923.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.306301689147949,
|
|
"epoch": 0.4217098943323727,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498801118470758,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.19959155470132828,
|
|
"num_tokens": 10057196.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.449332141876221,
|
|
"epoch": 0.42219020172910665,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498797581450484,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.19375586211681367,
|
|
"num_tokens": 10069655.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.511579084396362,
|
|
"epoch": 0.42267050912584053,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004987940392342948,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.19924264699220656,
|
|
"num_tokens": 10080876.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.482829475402832,
|
|
"epoch": 0.42315081652257447,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004987904918222726,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.18975469768047332,
|
|
"num_tokens": 10091986.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.5305768013000485,
|
|
"epoch": 0.42363112391930835,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987869392144996,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.19329569041728972,
|
|
"num_tokens": 10104027.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.5070350646972654,
|
|
"epoch": 0.4241114313160423,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987833814110584,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.19417518377304077,
|
|
"num_tokens": 10114665.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.434443378448487,
|
|
"epoch": 0.42459173871277617,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004987798184120316,
|
|
"loss": 5.312,
|
|
"mean_token_accuracy": 0.19974145740270616,
|
|
"num_tokens": 10126032.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.545246362686157,
|
|
"epoch": 0.4250720461095101,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987762502175018,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.19160096794366838,
|
|
"num_tokens": 10137256.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.383159017562866,
|
|
"epoch": 0.425552353506244,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000498772676827552,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.1996947318315506,
|
|
"num_tokens": 10149445.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.5012122631073,
|
|
"epoch": 0.4260326609029779,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987690982422652,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.19004785567522048,
|
|
"num_tokens": 10161607.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.553760147094726,
|
|
"epoch": 0.4265129682997118,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987655144617243,
|
|
"loss": 5.3855,
|
|
"mean_token_accuracy": 0.1945369154214859,
|
|
"num_tokens": 10173184.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.452174377441406,
|
|
"epoch": 0.42699327569644574,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987619254860126,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.2024209216237068,
|
|
"num_tokens": 10184617.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.451268672943115,
|
|
"epoch": 0.4274735830931796,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987583313152134,
|
|
"loss": 5.2866,
|
|
"mean_token_accuracy": 0.1954964816570282,
|
|
"num_tokens": 10195608.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.481286334991455,
|
|
"epoch": 0.42795389048991356,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004987547319494104,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.19195548743009566,
|
|
"num_tokens": 10206763.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.507647132873535,
|
|
"epoch": 0.42843419788664744,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987511273886867,
|
|
"loss": 5.3352,
|
|
"mean_token_accuracy": 0.19549722224473953,
|
|
"num_tokens": 10218714.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.460297584533691,
|
|
"epoch": 0.4289145052833814,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987475176331263,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.19259987473487855,
|
|
"num_tokens": 10229902.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.434809589385987,
|
|
"epoch": 0.42939481268011526,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004987439026828129,
|
|
"loss": 5.2242,
|
|
"mean_token_accuracy": 0.19963788241147995,
|
|
"num_tokens": 10241578.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.37636399269104,
|
|
"epoch": 0.4298751200768492,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987402825378305,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.20253763049840928,
|
|
"num_tokens": 10252109.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.490766906738282,
|
|
"epoch": 0.4303554274735831,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987366571982631,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.19313031136989595,
|
|
"num_tokens": 10263357.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.491276741027832,
|
|
"epoch": 0.430835734870317,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004987330266641948,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.1924482449889183,
|
|
"num_tokens": 10275536.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.56570987701416,
|
|
"epoch": 0.4313160422670509,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987293909357101,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.19930241852998734,
|
|
"num_tokens": 10286901.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.362359619140625,
|
|
"epoch": 0.43179634966378483,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987257500128933,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.19796304106712342,
|
|
"num_tokens": 10298961.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.4794525623321535,
|
|
"epoch": 0.4322766570605187,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004987221038958288,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.19520987272262574,
|
|
"num_tokens": 10310911.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.569372749328613,
|
|
"epoch": 0.43275696445725265,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987184525846015,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.19102310240268708,
|
|
"num_tokens": 10322267.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.460135221481323,
|
|
"epoch": 0.4332372718539865,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987147960792958,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.19574257284402846,
|
|
"num_tokens": 10335111.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.537425756454468,
|
|
"epoch": 0.43371757925072046,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004987111343799971,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.19893868863582612,
|
|
"num_tokens": 10345672.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.535245752334594,
|
|
"epoch": 0.43419788664745435,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049870746748679,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.19822679609060287,
|
|
"num_tokens": 10357369.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.475355434417724,
|
|
"epoch": 0.4346781940441883,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987037953997598,
|
|
"loss": 5.3352,
|
|
"mean_token_accuracy": 0.19392889589071274,
|
|
"num_tokens": 10368842.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.417094087600708,
|
|
"epoch": 0.43515850144092216,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987001181189918,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.19415317475795746,
|
|
"num_tokens": 10380096.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.3792015552520756,
|
|
"epoch": 0.4356388088376561,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004986964356445713,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.19834728091955184,
|
|
"num_tokens": 10391996.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.506541299819946,
|
|
"epoch": 0.43611911623439004,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986927479765837,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.1930739849805832,
|
|
"num_tokens": 10403607.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.444096088409424,
|
|
"epoch": 0.4365994236311239,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986890551151148,
|
|
"loss": 5.2746,
|
|
"mean_token_accuracy": 0.1976367026567459,
|
|
"num_tokens": 10413580.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.40678129196167,
|
|
"epoch": 0.43707973102785785,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986853570602503,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.1981777012348175,
|
|
"num_tokens": 10426456.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.5582586288452145,
|
|
"epoch": 0.43756003842459174,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986816538120758,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.18815538436174392,
|
|
"num_tokens": 10438869.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.448095989227295,
|
|
"epoch": 0.43804034582132567,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986779453706778,
|
|
"loss": 5.3537,
|
|
"mean_token_accuracy": 0.18729300647974015,
|
|
"num_tokens": 10450672.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.459218215942383,
|
|
"epoch": 0.43852065321805955,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986742317361419,
|
|
"loss": 5.261,
|
|
"mean_token_accuracy": 0.20304668992757796,
|
|
"num_tokens": 10461890.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.565139579772949,
|
|
"epoch": 0.4390009606147935,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986705129085546,
|
|
"loss": 5.3919,
|
|
"mean_token_accuracy": 0.18603334277868272,
|
|
"num_tokens": 10473866.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.509669589996338,
|
|
"epoch": 0.43948126801152737,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986667888880021,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.1933439001441002,
|
|
"num_tokens": 10484889.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.42793641090393,
|
|
"epoch": 0.4399615754082613,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986630596745709,
|
|
"loss": 5.3419,
|
|
"mean_token_accuracy": 0.19692840725183486,
|
|
"num_tokens": 10496108.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.463746356964111,
|
|
"epoch": 0.4404418828049952,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986593252683477,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.19601958990097046,
|
|
"num_tokens": 10505472.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.345721244812012,
|
|
"epoch": 0.4409221902017291,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986555856694191,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.20081722289323806,
|
|
"num_tokens": 10516954.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.5342426776885985,
|
|
"epoch": 0.441402497598463,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004986518408778718,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.1927899092435837,
|
|
"num_tokens": 10528166.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.422142553329468,
|
|
"epoch": 0.44188280499519694,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004986480908937929,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.19853255301713943,
|
|
"num_tokens": 10538112.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.489729166030884,
|
|
"epoch": 0.4423631123919308,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986443357172695,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.19151799231767655,
|
|
"num_tokens": 10549888.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.626604223251343,
|
|
"epoch": 0.44284341978866476,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004986405753483887,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.1831491395831108,
|
|
"num_tokens": 10561710.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.424169254302979,
|
|
"epoch": 0.44332372718539864,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004986368097872377,
|
|
"loss": 5.3121,
|
|
"mean_token_accuracy": 0.1889724239706993,
|
|
"num_tokens": 10574564.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.4898937225341795,
|
|
"epoch": 0.4438040345821326,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986330390339042,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.1978645905852318,
|
|
"num_tokens": 10586639.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.4653246879577635,
|
|
"epoch": 0.44428434197886646,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004986292630884755,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.19615231901407243,
|
|
"num_tokens": 10598730.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.420555067062378,
|
|
"epoch": 0.4447646493756004,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004986254819510393,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.21116500198841096,
|
|
"num_tokens": 10610352.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.394788074493408,
|
|
"epoch": 0.4452449567723343,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004986216956216835,
|
|
"loss": 5.3007,
|
|
"mean_token_accuracy": 0.19723331481218337,
|
|
"num_tokens": 10621951.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.444929742813111,
|
|
"epoch": 0.4457252641690682,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000498617904100496,
|
|
"loss": 5.2438,
|
|
"mean_token_accuracy": 0.20000688582658768,
|
|
"num_tokens": 10633207.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.516901731491089,
|
|
"epoch": 0.4462055715658021,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986141073875646,
|
|
"loss": 5.3495,
|
|
"mean_token_accuracy": 0.18970742523670198,
|
|
"num_tokens": 10645853.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.386112785339355,
|
|
"epoch": 0.44668587896253603,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986103054829779,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.20123800486326218,
|
|
"num_tokens": 10656892.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.392650985717774,
|
|
"epoch": 0.4471661863592699,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004986064983868237,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.19400574266910553,
|
|
"num_tokens": 10670110.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.4809633731842045,
|
|
"epoch": 0.44764649375600385,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986026860991906,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.196006740629673,
|
|
"num_tokens": 10681255.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.473309946060181,
|
|
"epoch": 0.44812680115273773,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004985988686201672,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.19332450479269028,
|
|
"num_tokens": 10692631.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.477552318572998,
|
|
"epoch": 0.44860710854947167,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004985950459498419,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.20014705508947372,
|
|
"num_tokens": 10704880.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.45638484954834,
|
|
"epoch": 0.44908741594620555,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985912180883037,
|
|
"loss": 5.2484,
|
|
"mean_token_accuracy": 0.20326420962810515,
|
|
"num_tokens": 10715561.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.385212564468384,
|
|
"epoch": 0.4495677233429395,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985873850356411,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.19535834789276124,
|
|
"num_tokens": 10727232.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.416689777374268,
|
|
"epoch": 0.45004803073967337,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985835467919436,
|
|
"loss": 5.2857,
|
|
"mean_token_accuracy": 0.2015791967511177,
|
|
"num_tokens": 10739404.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.449459791183472,
|
|
"epoch": 0.4505283381364073,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985797033572999,
|
|
"loss": 5.3113,
|
|
"mean_token_accuracy": 0.19386572688817977,
|
|
"num_tokens": 10751948.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.434033584594727,
|
|
"epoch": 0.4510086455331412,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004985758547317994,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.19730297327041627,
|
|
"num_tokens": 10764611.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.465791463851929,
|
|
"epoch": 0.4514889529298751,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004985720009155315,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.19460007399320603,
|
|
"num_tokens": 10775954.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.45864953994751,
|
|
"epoch": 0.45196926032660906,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004985681419085856,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.18940264582633973,
|
|
"num_tokens": 10788723.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.474675464630127,
|
|
"epoch": 0.45244956772334294,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004985642777110513,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.19875997453927993,
|
|
"num_tokens": 10799879.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.400967597961426,
|
|
"epoch": 0.4529298751200769,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985604083230183,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.1981558918952942,
|
|
"num_tokens": 10811838.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.49187388420105,
|
|
"epoch": 0.45341018251681076,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985565337445765,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.1971256822347641,
|
|
"num_tokens": 10822910.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.49492335319519,
|
|
"epoch": 0.4538904899135447,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004985526539758158,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.19619156718254088,
|
|
"num_tokens": 10835344.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.4535280704498295,
|
|
"epoch": 0.4543707973102786,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004985487690168263,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.19785993695259094,
|
|
"num_tokens": 10846043.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.456455278396606,
|
|
"epoch": 0.4548511047070125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498544878867698,
|
|
"loss": 5.2462,
|
|
"mean_token_accuracy": 0.20247492641210557,
|
|
"num_tokens": 10857783.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.465985870361328,
|
|
"epoch": 0.4553314121037464,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004985409835285215,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.1979512870311737,
|
|
"num_tokens": 10870527.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.441158056259155,
|
|
"epoch": 0.45581171950048033,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985370829993873,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.2029913693666458,
|
|
"num_tokens": 10882285.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.489823675155639,
|
|
"epoch": 0.4562920268972142,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004985331772803857,
|
|
"loss": 5.3154,
|
|
"mean_token_accuracy": 0.19783458560705186,
|
|
"num_tokens": 10895319.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.472352361679077,
|
|
"epoch": 0.45677233429394815,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985292663716074,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.19923655539751053,
|
|
"num_tokens": 10906253.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.335994291305542,
|
|
"epoch": 0.457252641690682,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004985253502731435,
|
|
"loss": 5.1855,
|
|
"mean_token_accuracy": 0.2086847722530365,
|
|
"num_tokens": 10918197.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.443401622772217,
|
|
"epoch": 0.45773294908741596,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004985214289850845,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.18888968527317046,
|
|
"num_tokens": 10930771.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.4748773097991945,
|
|
"epoch": 0.45821325648414984,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004985175025075217,
|
|
"loss": 5.2834,
|
|
"mean_token_accuracy": 0.1973588064312935,
|
|
"num_tokens": 10942759.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.6522383213043215,
|
|
"epoch": 0.4586935638808838,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985135708405462,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.18645619004964828,
|
|
"num_tokens": 10953557.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.401769304275513,
|
|
"epoch": 0.45917387127761766,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985096339842493,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.20662152916193008,
|
|
"num_tokens": 10963142.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.379817962646484,
|
|
"epoch": 0.4596541786743516,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985056919387224,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.20357681661844254,
|
|
"num_tokens": 10974321.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.509200239181519,
|
|
"epoch": 0.4601344860710855,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985017447040569,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.19487691521644593,
|
|
"num_tokens": 10985524.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.494694328308105,
|
|
"epoch": 0.4606147934678194,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004984977922803447,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.19958257526159287,
|
|
"num_tokens": 10997606.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.412304258346557,
|
|
"epoch": 0.4610951008645533,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004984938346676772,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.1943564847111702,
|
|
"num_tokens": 11010692.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.417695474624634,
|
|
"epoch": 0.46157540826128723,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004984898718661468,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.20364998728036882,
|
|
"num_tokens": 11022517.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.4359543800354,
|
|
"epoch": 0.4620557156580211,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004984859038758451,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.1995931401848793,
|
|
"num_tokens": 11033141.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.396144914627075,
|
|
"epoch": 0.46253602305475505,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004984819306968642,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.19817344099283218,
|
|
"num_tokens": 11044619.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.519974994659424,
|
|
"epoch": 0.46301633045148893,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004984779523292966,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.20086241513490677,
|
|
"num_tokens": 11055934.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.440757846832275,
|
|
"epoch": 0.46349663784822287,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984739687732345,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.20307007431983948,
|
|
"num_tokens": 11066203.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.272681379318238,
|
|
"epoch": 0.46397694524495675,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984699800287705,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.2047649070620537,
|
|
"num_tokens": 11079664.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.312569189071655,
|
|
"epoch": 0.4644572526416907,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498465986095997,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.20340044498443605,
|
|
"num_tokens": 11091186.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.447326278686523,
|
|
"epoch": 0.46493756003842457,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004984619869750069,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.19724527150392532,
|
|
"num_tokens": 11102710.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.387120294570923,
|
|
"epoch": 0.4654178674351585,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498457982665893,
|
|
"loss": 5.2046,
|
|
"mean_token_accuracy": 0.2028914585709572,
|
|
"num_tokens": 11114746.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.423678159713745,
|
|
"epoch": 0.4658981748318924,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984539731687483,
|
|
"loss": 5.2561,
|
|
"mean_token_accuracy": 0.19754694998264313,
|
|
"num_tokens": 11126572.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.399871730804444,
|
|
"epoch": 0.4663784822286263,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984499584836659,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.20589766055345535,
|
|
"num_tokens": 11137830.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.381054067611695,
|
|
"epoch": 0.4668587896253602,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498445938610739,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.2022456184029579,
|
|
"num_tokens": 11148860.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.438592147827149,
|
|
"epoch": 0.46733909702209414,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984419135500608,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.19238598942756652,
|
|
"num_tokens": 11161311.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.425858068466186,
|
|
"epoch": 0.4678194044188281,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004984378833017249,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.19774759262800218,
|
|
"num_tokens": 11173124.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.395693683624268,
|
|
"epoch": 0.46829971181556196,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004984338478658248,
|
|
"loss": 5.3059,
|
|
"mean_token_accuracy": 0.1966658964753151,
|
|
"num_tokens": 11184879.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.4837006568908695,
|
|
"epoch": 0.4687800192122959,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004984298072424542,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.1932589590549469,
|
|
"num_tokens": 11196243.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.432374286651611,
|
|
"epoch": 0.4692603266090298,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498425761431707,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.20986756533384324,
|
|
"num_tokens": 11207485.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.388256454467774,
|
|
"epoch": 0.4697406340057637,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498421710433677,
|
|
"loss": 5.2099,
|
|
"mean_token_accuracy": 0.19842060953378676,
|
|
"num_tokens": 11219891.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.479468727111817,
|
|
"epoch": 0.4702209414024976,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004984176542484584,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.19674236327409744,
|
|
"num_tokens": 11231329.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.403811025619507,
|
|
"epoch": 0.47070124879923153,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984135928761452,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.20610021948814392,
|
|
"num_tokens": 11241367.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.443480825424194,
|
|
"epoch": 0.4711815561959654,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004984095263168317,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.19220978170633315,
|
|
"num_tokens": 11254532.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.511846876144409,
|
|
"epoch": 0.47166186359269935,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004984054545706124,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.18875951766967775,
|
|
"num_tokens": 11265223.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.373107099533081,
|
|
"epoch": 0.47214217098943323,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000498401377637582,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.19637542366981506,
|
|
"num_tokens": 11278228.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.564932346343994,
|
|
"epoch": 0.47262247838616717,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000498397295517835,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.1917308121919632,
|
|
"num_tokens": 11289654.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.421516752243042,
|
|
"epoch": 0.47310278578290105,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983932082114659,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.2053057834506035,
|
|
"num_tokens": 11301911.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.5105547428131105,
|
|
"epoch": 0.473583093179635,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004983891157185699,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.191430202126503,
|
|
"num_tokens": 11312945.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.598050594329834,
|
|
"epoch": 0.47406340057636887,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004983850180392421,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.18814169615507126,
|
|
"num_tokens": 11324126.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.4626157760620115,
|
|
"epoch": 0.4745437079731028,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983809151735775,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.1932709753513336,
|
|
"num_tokens": 11336395.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.45054349899292,
|
|
"epoch": 0.4750240153698367,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983768071216713,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.2002416417002678,
|
|
"num_tokens": 11347387.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.3878782272338865,
|
|
"epoch": 0.4755043227665706,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983726938836189,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.20208385437726975,
|
|
"num_tokens": 11358467.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.491963720321655,
|
|
"epoch": 0.4759846301633045,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004983685754595159,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.1896727964282036,
|
|
"num_tokens": 11370322.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.352085447311401,
|
|
"epoch": 0.47646493756003844,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983644518494578,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.20571735352277756,
|
|
"num_tokens": 11381719.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.39383020401001,
|
|
"epoch": 0.4769452449567723,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983603230535403,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.19686990678310395,
|
|
"num_tokens": 11393561.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.495372152328491,
|
|
"epoch": 0.47742555235350626,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004983561890718594,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.19655826836824417,
|
|
"num_tokens": 11405411.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.526172113418579,
|
|
"epoch": 0.47790585975024014,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498352049904511,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.18656282126903534,
|
|
"num_tokens": 11417419.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.416673946380615,
|
|
"epoch": 0.4783861671469741,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983479055515914,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.19893506020307541,
|
|
"num_tokens": 11428145.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.351204967498779,
|
|
"epoch": 0.47886647454370795,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004983437560131964,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.20236289799213408,
|
|
"num_tokens": 11439224.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.425208616256714,
|
|
"epoch": 0.4793467819404419,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983396012894228,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.19770564287900924,
|
|
"num_tokens": 11451731.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.458701133728027,
|
|
"epoch": 0.47982708933717577,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983354413803666,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.20528912395238877,
|
|
"num_tokens": 11463058.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.543280839920044,
|
|
"epoch": 0.4803073967339097,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004983312762861248,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.19466368705034257,
|
|
"num_tokens": 11472618.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.399996662139893,
|
|
"epoch": 0.4807877041306436,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004983271060067939,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.1996273174881935,
|
|
"num_tokens": 11483114.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.363938045501709,
|
|
"epoch": 0.4812680115273775,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983229305424707,
|
|
"loss": 5.1987,
|
|
"mean_token_accuracy": 0.20535318106412886,
|
|
"num_tokens": 11494281.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.440830373764038,
|
|
"epoch": 0.4817483189241114,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983187498932522,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.19693202525377274,
|
|
"num_tokens": 11505962.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.44342532157898,
|
|
"epoch": 0.48222862632084534,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004983145640592354,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.18968168497085572,
|
|
"num_tokens": 11517558.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.45598030090332,
|
|
"epoch": 0.4827089337175792,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983103730405176,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.19084265679121018,
|
|
"num_tokens": 11529184.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.452455759048462,
|
|
"epoch": 0.48318924111431316,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498306176837196,
|
|
"loss": 5.257,
|
|
"mean_token_accuracy": 0.1939294755458832,
|
|
"num_tokens": 11540727.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.3856573581695555,
|
|
"epoch": 0.48366954851104704,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004983019754493681,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.20147235542535782,
|
|
"num_tokens": 11551510.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.441668701171875,
|
|
"epoch": 0.484149855907781,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982977688771314,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.20095289647579193,
|
|
"num_tokens": 11563203.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.4081573486328125,
|
|
"epoch": 0.4846301633045149,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004982935571205835,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.20497542768716812,
|
|
"num_tokens": 11576013.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.323009014129639,
|
|
"epoch": 0.4851104707012488,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004982893401798223,
|
|
"loss": 5.1553,
|
|
"mean_token_accuracy": 0.21624571532011033,
|
|
"num_tokens": 11587535.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.364218139648438,
|
|
"epoch": 0.48559077809798273,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004982851180549456,
|
|
"loss": 5.2053,
|
|
"mean_token_accuracy": 0.20111326426267623,
|
|
"num_tokens": 11598487.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.324197387695312,
|
|
"epoch": 0.4860710854947166,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982808907460515,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.22296716421842575,
|
|
"num_tokens": 11609457.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.3482780933380125,
|
|
"epoch": 0.48655139289145055,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982766582532382,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.2081102043390274,
|
|
"num_tokens": 11620251.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.358762311935425,
|
|
"epoch": 0.48703170028818443,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982724205766038,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.20766099393367768,
|
|
"num_tokens": 11630956.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.420529079437256,
|
|
"epoch": 0.48751200768491837,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004982681777162468,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.20143322944641112,
|
|
"num_tokens": 11642560.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.312218856811524,
|
|
"epoch": 0.48799231508165225,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982639296722657,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.20298496782779693,
|
|
"num_tokens": 11654050.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.3660177230834964,
|
|
"epoch": 0.4884726224783862,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982596764447591,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.19897778779268266,
|
|
"num_tokens": 11664947.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.4209997177124025,
|
|
"epoch": 0.48895292987512007,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982554180338258,
|
|
"loss": 5.2324,
|
|
"mean_token_accuracy": 0.20139615535736083,
|
|
"num_tokens": 11676927.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.530186462402344,
|
|
"epoch": 0.489433237271854,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004982511544395646,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.19309221357107162,
|
|
"num_tokens": 11688573.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.338684368133545,
|
|
"epoch": 0.4899135446685879,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004982468856620745,
|
|
"loss": 5.2421,
|
|
"mean_token_accuracy": 0.1984547719359398,
|
|
"num_tokens": 11698704.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.307417392730713,
|
|
"epoch": 0.4903938520653218,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004982426117014545,
|
|
"loss": 5.1715,
|
|
"mean_token_accuracy": 0.20310387909412383,
|
|
"num_tokens": 11709466.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.384412813186645,
|
|
"epoch": 0.4908741594620557,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982383325578041,
|
|
"loss": 5.2733,
|
|
"mean_token_accuracy": 0.19685922116041182,
|
|
"num_tokens": 11721120.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.509656810760498,
|
|
"epoch": 0.49135446685878964,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004982340482312226,
|
|
"loss": 5.2637,
|
|
"mean_token_accuracy": 0.1910458594560623,
|
|
"num_tokens": 11732120.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.373399448394776,
|
|
"epoch": 0.4918347742555235,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004982297587218092,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.20690827518701554,
|
|
"num_tokens": 11743501.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.366362190246582,
|
|
"epoch": 0.49231508165225746,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982254640296637,
|
|
"loss": 5.2242,
|
|
"mean_token_accuracy": 0.20181894153356553,
|
|
"num_tokens": 11755051.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.41463942527771,
|
|
"epoch": 0.49279538904899134,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004982211641548857,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.1938163235783577,
|
|
"num_tokens": 11767663.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.473185110092163,
|
|
"epoch": 0.4932756964457253,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004982168590975752,
|
|
"loss": 5.2429,
|
|
"mean_token_accuracy": 0.20339857041835785,
|
|
"num_tokens": 11778828.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.507049894332885,
|
|
"epoch": 0.49375600384245916,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982125488578321,
|
|
"loss": 5.4109,
|
|
"mean_token_accuracy": 0.19114813357591628,
|
|
"num_tokens": 11790654.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.4209589004516605,
|
|
"epoch": 0.4942363112391931,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982082334357563,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.19969180077314377,
|
|
"num_tokens": 11801489.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.366079807281494,
|
|
"epoch": 0.494716618635927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982039128314481,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.20027052909135817,
|
|
"num_tokens": 11813818.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.347721862792969,
|
|
"epoch": 0.4951969260326609,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981995870450079,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.20178951025009156,
|
|
"num_tokens": 11824814.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.463880491256714,
|
|
"epoch": 0.4956772334293948,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004981952560765361,
|
|
"loss": 5.2617,
|
|
"mean_token_accuracy": 0.19569255411624908,
|
|
"num_tokens": 11836252.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.381760025024414,
|
|
"epoch": 0.49615754082612873,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981909199261331,
|
|
"loss": 5.1709,
|
|
"mean_token_accuracy": 0.20152270197868347,
|
|
"num_tokens": 11847715.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.327801704406738,
|
|
"epoch": 0.4966378482228626,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004981865785938998,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.20665301084518434,
|
|
"num_tokens": 11860309.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.362015056610107,
|
|
"epoch": 0.49711815561959655,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004981822320799367,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.20086576491594316,
|
|
"num_tokens": 11872569.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.359728670120239,
|
|
"epoch": 0.49759846301633043,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981778803843449,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.20249261260032653,
|
|
"num_tokens": 11884778.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.437938070297241,
|
|
"epoch": 0.49807877041306436,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981735235072256,
|
|
"loss": 5.2555,
|
|
"mean_token_accuracy": 0.20191961973905564,
|
|
"num_tokens": 11897324.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.447718381881714,
|
|
"epoch": 0.49855907780979825,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004981691614486796,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.19850171953439713,
|
|
"num_tokens": 11909145.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.35249171257019,
|
|
"epoch": 0.4990393852065322,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981647942088084,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.20171126276254653,
|
|
"num_tokens": 11921021.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.519689655303955,
|
|
"epoch": 0.49951969260326606,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981604217877135,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.1942518636584282,
|
|
"num_tokens": 11932565.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.374987077713013,
|
|
"epoch": 0.5,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498156044185496,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.19995938688516618,
|
|
"num_tokens": 11943225.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.364169502258301,
|
|
"epoch": 0.5004803073967339,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981516614022579,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.2035745918750763,
|
|
"num_tokens": 11954821.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.43224196434021,
|
|
"epoch": 0.5009606147934679,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981472734381008,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.20336654484272004,
|
|
"num_tokens": 11966090.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.41751708984375,
|
|
"epoch": 0.5014409221902018,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981428802931267,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.19972468316555023,
|
|
"num_tokens": 11977410.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.4079958438873295,
|
|
"epoch": 0.5019212295869356,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981384819674375,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.19654285460710524,
|
|
"num_tokens": 11989119.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.499818134307861,
|
|
"epoch": 0.5024015369836695,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004981340784611354,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.19646679908037185,
|
|
"num_tokens": 12000165.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.40293173789978,
|
|
"epoch": 0.5028818443804035,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004981296697743224,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.1927013948559761,
|
|
"num_tokens": 12012118.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.442527198791504,
|
|
"epoch": 0.5033621517771374,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004981252559071012,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.19446006715297698,
|
|
"num_tokens": 12023432.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.4181389808654785,
|
|
"epoch": 0.5038424591738713,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981208368595739,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.20718919187784196,
|
|
"num_tokens": 12034323.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.35970139503479,
|
|
"epoch": 0.5043227665706052,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981164126318435,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.19909979403018951,
|
|
"num_tokens": 12045532.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.451566362380982,
|
|
"epoch": 0.5048030739673391,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004981119832240124,
|
|
"loss": 5.2431,
|
|
"mean_token_accuracy": 0.19895632565021515,
|
|
"num_tokens": 12057346.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.349082517623901,
|
|
"epoch": 0.505283381364073,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004981075486361837,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.20472613275051116,
|
|
"num_tokens": 12068670.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.4529791355133055,
|
|
"epoch": 0.5057636887608069,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981031088684601,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.19437083154916762,
|
|
"num_tokens": 12079664.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.469378185272217,
|
|
"epoch": 0.5062439961575408,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004980986639209448,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.2042248487472534,
|
|
"num_tokens": 12089984.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.319522666931152,
|
|
"epoch": 0.5067243035542748,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498094213793741,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.20940718650817872,
|
|
"num_tokens": 12101182.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.4405517578125,
|
|
"epoch": 0.5072046109510087,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498089758486952,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.19249950349330902,
|
|
"num_tokens": 12112002.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.489940357208252,
|
|
"epoch": 0.5076849183477425,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004980852980006812,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.1845449000597,
|
|
"num_tokens": 12124194.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.358373641967773,
|
|
"epoch": 0.5081652257444764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004980808323350323,
|
|
"loss": 5.2607,
|
|
"mean_token_accuracy": 0.20721071660518647,
|
|
"num_tokens": 12133966.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.400069761276245,
|
|
"epoch": 0.5086455331412104,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980763614901089,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.2029334396123886,
|
|
"num_tokens": 12145643.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.388980054855347,
|
|
"epoch": 0.5091258405379443,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004980718854660146,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.19128015339374543,
|
|
"num_tokens": 12156804.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.410366010665894,
|
|
"epoch": 0.5096061479346782,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004980674042628537,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.19946327358484267,
|
|
"num_tokens": 12168700.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.441403770446778,
|
|
"epoch": 0.5100864553314121,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00049806291788073,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.19958012998104097,
|
|
"num_tokens": 12181050.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.441706371307373,
|
|
"epoch": 0.510566762728146,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004980584263197477,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.1931978940963745,
|
|
"num_tokens": 12192001.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.559450435638428,
|
|
"epoch": 0.5110470701248799,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980539295800111,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.19310695230960845,
|
|
"num_tokens": 12202436.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.374323940277099,
|
|
"epoch": 0.5115273775216138,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004980494276616246,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.20342611223459245,
|
|
"num_tokens": 12214454.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.385732889175415,
|
|
"epoch": 0.5120076849183477,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980449205646926,
|
|
"loss": 5.2272,
|
|
"mean_token_accuracy": 0.20538058280944824,
|
|
"num_tokens": 12225924.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.471169757843017,
|
|
"epoch": 0.5124879923150817,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049804040828932,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.20452706813812255,
|
|
"num_tokens": 12236456.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.417616176605224,
|
|
"epoch": 0.5129682997118156,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004980358908356113,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.20173069089651108,
|
|
"num_tokens": 12247719.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.375013160705566,
|
|
"epoch": 0.5134486071085494,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004980313682036717,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.1980268254876137,
|
|
"num_tokens": 12259141.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.52657642364502,
|
|
"epoch": 0.5139289145052833,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004980268403936058,
|
|
"loss": 5.342,
|
|
"mean_token_accuracy": 0.19116934835910798,
|
|
"num_tokens": 12269748.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.426257944107055,
|
|
"epoch": 0.5144092219020173,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004980223074055189,
|
|
"loss": 5.297,
|
|
"mean_token_accuracy": 0.2044803574681282,
|
|
"num_tokens": 12281456.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.440986442565918,
|
|
"epoch": 0.5148895292987512,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004980177692395164,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.1947730675339699,
|
|
"num_tokens": 12293763.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.409850406646728,
|
|
"epoch": 0.5153698366954851,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004980132258957035,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.20839707404375077,
|
|
"num_tokens": 12305398.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.35020489692688,
|
|
"epoch": 0.515850144092219,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004980086773741856,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.199608738720417,
|
|
"num_tokens": 12316582.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.461497783660889,
|
|
"epoch": 0.516330451488953,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980041236750685,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.1998691514134407,
|
|
"num_tokens": 12328463.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.471179628372193,
|
|
"epoch": 0.5168107588856868,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004979995647984577,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.2032223239541054,
|
|
"num_tokens": 12341040.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.324481773376465,
|
|
"epoch": 0.5172910662824207,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004979950007444593,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.2048783466219902,
|
|
"num_tokens": 12353024.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.357087421417236,
|
|
"epoch": 0.5177713736791547,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004979904315131792,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.20590624809265137,
|
|
"num_tokens": 12366100.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.353571033477783,
|
|
"epoch": 0.5182516810758886,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979858571047233,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.20849017649888993,
|
|
"num_tokens": 12377829.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.511527395248413,
|
|
"epoch": 0.5187319884726225,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979812775191979,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.19967973232269287,
|
|
"num_tokens": 12390830.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.343885278701782,
|
|
"epoch": 0.5192122958693564,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004979766927567094,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.20680712759494782,
|
|
"num_tokens": 12401642.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.35053563117981,
|
|
"epoch": 0.5196926032660903,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004979721028173643,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.20148641914129256,
|
|
"num_tokens": 12411653.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.414511108398438,
|
|
"epoch": 0.5201729106628242,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497967507701269,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.2088325709104538,
|
|
"num_tokens": 12422891.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.461643075942993,
|
|
"epoch": 0.5206532180595581,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979629074085303,
|
|
"loss": 5.2585,
|
|
"mean_token_accuracy": 0.20017822086811066,
|
|
"num_tokens": 12434190.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.425161838531494,
|
|
"epoch": 0.521133525456292,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004979583019392548,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.19771393835544587,
|
|
"num_tokens": 12445796.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.515705680847168,
|
|
"epoch": 0.521613832853026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979536912935497,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.19371298253536223,
|
|
"num_tokens": 12456212.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.369207715988159,
|
|
"epoch": 0.5220941402497599,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000497949075471522,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.20107672214508057,
|
|
"num_tokens": 12467871.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.394469690322876,
|
|
"epoch": 0.5225744476464937,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004979444544732786,
|
|
"loss": 5.2053,
|
|
"mean_token_accuracy": 0.1949324682354927,
|
|
"num_tokens": 12478626.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.365805816650391,
|
|
"epoch": 0.5230547550432276,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000497939828298927,
|
|
"loss": 5.2886,
|
|
"mean_token_accuracy": 0.19763265550136566,
|
|
"num_tokens": 12491487.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.461965608596802,
|
|
"epoch": 0.5235350624399616,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979351969485747,
|
|
"loss": 5.2327,
|
|
"mean_token_accuracy": 0.19547561854124068,
|
|
"num_tokens": 12503240.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.455387878417969,
|
|
"epoch": 0.5240153698366955,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979305604223291,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.20037689208984374,
|
|
"num_tokens": 12513860.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.3650209426879885,
|
|
"epoch": 0.5244956772334294,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979259187202978,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.20282870829105376,
|
|
"num_tokens": 12525884.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.4195245742797855,
|
|
"epoch": 0.5249759846301633,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979212718425887,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.20026529282331468,
|
|
"num_tokens": 12536709.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.410429239273071,
|
|
"epoch": 0.5254562920268973,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004979166197893096,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.20506655275821686,
|
|
"num_tokens": 12549727.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.3270786762237545,
|
|
"epoch": 0.5259365994236311,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004979119625605683,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.19516700655221939,
|
|
"num_tokens": 12562053.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.345616006851197,
|
|
"epoch": 0.526416906820365,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004979073001564734,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.20667382925748826,
|
|
"num_tokens": 12574096.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.460164356231689,
|
|
"epoch": 0.5268972142170989,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004979026325771328,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.20060795843601226,
|
|
"num_tokens": 12585416.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.413971662521362,
|
|
"epoch": 0.5273775216138329,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004978979598226549,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.20576133579015732,
|
|
"num_tokens": 12596861.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.333009815216064,
|
|
"epoch": 0.5278578290105668,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004978932818931483,
|
|
"loss": 5.1927,
|
|
"mean_token_accuracy": 0.20716883689165116,
|
|
"num_tokens": 12607761.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.443383312225341,
|
|
"epoch": 0.5283381364073007,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978885987887216,
|
|
"loss": 5.3051,
|
|
"mean_token_accuracy": 0.20227987468242645,
|
|
"num_tokens": 12619889.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.509159994125366,
|
|
"epoch": 0.5288184438040345,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004978839105094833,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.19618211537599564,
|
|
"num_tokens": 12630604.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.314917039871216,
|
|
"epoch": 0.5292987512007685,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978792170555426,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.20746731758117676,
|
|
"num_tokens": 12641172.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.312827301025391,
|
|
"epoch": 0.5297790585975024,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978745184270083,
|
|
"loss": 5.0923,
|
|
"mean_token_accuracy": 0.21527302861213685,
|
|
"num_tokens": 12651731.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.386341571807861,
|
|
"epoch": 0.5302593659942363,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004978698146239893,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.20662128329277038,
|
|
"num_tokens": 12663050.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.479044103622437,
|
|
"epoch": 0.5307396733909702,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004978651056465952,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.19395910054445267,
|
|
"num_tokens": 12674732.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.313097810745239,
|
|
"epoch": 0.5312199807877042,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000497860391494935,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.2039245158433914,
|
|
"num_tokens": 12685981.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.447102403640747,
|
|
"epoch": 0.531700288184438,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978556721691183,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.19787385314702988,
|
|
"num_tokens": 12697139.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.3786839008331295,
|
|
"epoch": 0.5321805955811719,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004978509476692547,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.19959738850593567,
|
|
"num_tokens": 12708268.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.375888729095459,
|
|
"epoch": 0.5326609029779059,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004978462179954538,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.20851173847913743,
|
|
"num_tokens": 12720715.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.367966890335083,
|
|
"epoch": 0.5331412103746398,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978414831478253,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.20525323897600173,
|
|
"num_tokens": 12732409.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.346772003173828,
|
|
"epoch": 0.5336215177713737,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004978367431264794,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.1936624139547348,
|
|
"num_tokens": 12745174.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.437586259841919,
|
|
"epoch": 0.5341018251681076,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004978319979315261,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.20328891277313232,
|
|
"num_tokens": 12756116.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.431155967712402,
|
|
"epoch": 0.5345821325648416,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004978272475630752,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.20230283141136168,
|
|
"num_tokens": 12768183.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.306485891342163,
|
|
"epoch": 0.5350624399615754,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004978224920212374,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.19942874312400818,
|
|
"num_tokens": 12778537.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.288288307189942,
|
|
"epoch": 0.5355427473583093,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004978177313061232,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.2020668715238571,
|
|
"num_tokens": 12789691.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.450948762893677,
|
|
"epoch": 0.5360230547550432,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978129654178426,
|
|
"loss": 5.2781,
|
|
"mean_token_accuracy": 0.19842252731323243,
|
|
"num_tokens": 12801438.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.403745031356811,
|
|
"epoch": 0.5365033621517772,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004978081943565067,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.19873054474592208,
|
|
"num_tokens": 12812425.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.376599311828613,
|
|
"epoch": 0.5369836695485111,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004978034181222261,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.19666872173547745,
|
|
"num_tokens": 12824735.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.448877477645874,
|
|
"epoch": 0.537463976945245,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004977986367151119,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.2031214103102684,
|
|
"num_tokens": 12835454.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.4336474418640135,
|
|
"epoch": 0.5379442843419788,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977938501352747,
|
|
"loss": 5.3367,
|
|
"mean_token_accuracy": 0.1929567873477936,
|
|
"num_tokens": 12847086.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.420505571365356,
|
|
"epoch": 0.5384245917387128,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004977890583828259,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.19988568872213364,
|
|
"num_tokens": 12857713.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.375241994857788,
|
|
"epoch": 0.5389048991354467,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004977842614578768,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.1993047297000885,
|
|
"num_tokens": 12869967.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.490482473373413,
|
|
"epoch": 0.5393852065321806,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004977794593605386,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.19814034998416902,
|
|
"num_tokens": 12881230.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.39257779121399,
|
|
"epoch": 0.5398655139289145,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000497774652090923,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.19702692776918412,
|
|
"num_tokens": 12892376.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.413067626953125,
|
|
"epoch": 0.5403458213256485,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977698396491414,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.20418344736099242,
|
|
"num_tokens": 12903709.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.319581651687622,
|
|
"epoch": 0.5408261287223823,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004977650220353055,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.20584484487771987,
|
|
"num_tokens": 12914958.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.376936054229736,
|
|
"epoch": 0.5413064361191162,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004977601992495274,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.20099034607410432,
|
|
"num_tokens": 12927418.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.412064933776856,
|
|
"epoch": 0.5417867435158501,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004977553712919189,
|
|
"loss": 5.2503,
|
|
"mean_token_accuracy": 0.20160660594701768,
|
|
"num_tokens": 12939874.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.416967535018921,
|
|
"epoch": 0.5422670509125841,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004977505381625921,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.19486918598413466,
|
|
"num_tokens": 12951113.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.315142440795898,
|
|
"epoch": 0.542747358309318,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004977456998616593,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.2023612678050995,
|
|
"num_tokens": 12961940.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.284940385818482,
|
|
"epoch": 0.5432276657060519,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004977408563892327,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.19892300814390182,
|
|
"num_tokens": 12973938.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.412263488769531,
|
|
"epoch": 0.5437079731027857,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977360077454249,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.20297273993492126,
|
|
"num_tokens": 12985400.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.385592126846314,
|
|
"epoch": 0.5441882804995197,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004977311539303483,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.20850644558668135,
|
|
"num_tokens": 12996402.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.293762063980102,
|
|
"epoch": 0.5446685878962536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004977262949441158,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.21470348685979843,
|
|
"num_tokens": 13006991.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.397123908996582,
|
|
"epoch": 0.5451488952929875,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977214307868399,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.20438773483037947,
|
|
"num_tokens": 13016969.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.392855453491211,
|
|
"epoch": 0.5456292026897214,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000497716561458634,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.20777873545885087,
|
|
"num_tokens": 13027759.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.486040258407593,
|
|
"epoch": 0.5461095100864554,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004977116869596107,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.1973151370882988,
|
|
"num_tokens": 13039881.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.378542852401734,
|
|
"epoch": 0.5465898174831892,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004977068072898834,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.20589208602905273,
|
|
"num_tokens": 13051443.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.4433074474334715,
|
|
"epoch": 0.5470701248799231,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977019224495652,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.1966116562485695,
|
|
"num_tokens": 13063474.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.370102453231811,
|
|
"epoch": 0.547550432276657,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004976970324387698,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.2106616035103798,
|
|
"num_tokens": 13074365.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.358544445037841,
|
|
"epoch": 0.548030739673391,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004976921372576104,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.20368915945291519,
|
|
"num_tokens": 13087354.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.370021200180053,
|
|
"epoch": 0.5485110470701249,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004976872369062011,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.19930920600891114,
|
|
"num_tokens": 13099306.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.408384513854981,
|
|
"epoch": 0.5489913544668588,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004976823313846552,
|
|
"loss": 5.3329,
|
|
"mean_token_accuracy": 0.19190380424261094,
|
|
"num_tokens": 13111259.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.45887770652771,
|
|
"epoch": 0.5494716618635928,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004976774206930869,
|
|
"loss": 5.2471,
|
|
"mean_token_accuracy": 0.19341034889221193,
|
|
"num_tokens": 13123589.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.377495574951172,
|
|
"epoch": 0.5499519692603266,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004976725048316101,
|
|
"loss": 5.2444,
|
|
"mean_token_accuracy": 0.19959345310926438,
|
|
"num_tokens": 13136485.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.409855890274048,
|
|
"epoch": 0.5504322766570605,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004976675838003388,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.19824812114238738,
|
|
"num_tokens": 13148067.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.3532360076904295,
|
|
"epoch": 0.5509125840537944,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004976626575993877,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.19984031617641448,
|
|
"num_tokens": 13159813.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.414771270751953,
|
|
"epoch": 0.5513928914505284,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004976577262288705,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.19723765850067138,
|
|
"num_tokens": 13170828.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.348534822463989,
|
|
"epoch": 0.5518731988472623,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004976527896889023,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.21700155436992646,
|
|
"num_tokens": 13181883.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.332348966598511,
|
|
"epoch": 0.5523535062439962,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976478479795974,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.20436936616897583,
|
|
"num_tokens": 13193530.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.461158657073975,
|
|
"epoch": 0.55283381364073,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004976429011010706,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.1911667287349701,
|
|
"num_tokens": 13205822.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.377006673812867,
|
|
"epoch": 0.553314121037464,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976379490534366,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.210676147043705,
|
|
"num_tokens": 13216698.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.346554327011108,
|
|
"epoch": 0.5537944284341979,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004976329918368107,
|
|
"loss": 5.2225,
|
|
"mean_token_accuracy": 0.2032114490866661,
|
|
"num_tokens": 13228389.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.437006664276123,
|
|
"epoch": 0.5542747358309318,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976280294513079,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.19674807637929917,
|
|
"num_tokens": 13239628.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.438928031921387,
|
|
"epoch": 0.5547550432276657,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004976230618970431,
|
|
"loss": 5.2726,
|
|
"mean_token_accuracy": 0.20090280920267106,
|
|
"num_tokens": 13251149.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.4733867168426515,
|
|
"epoch": 0.5552353506243997,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000497618089174132,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.19709511697292328,
|
|
"num_tokens": 13264846.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.324634456634522,
|
|
"epoch": 0.5557156580211335,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004976131112826898,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.2113727256655693,
|
|
"num_tokens": 13275409.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.231151103973389,
|
|
"epoch": 0.5561959654178674,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976081282228323,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.20907817929983138,
|
|
"num_tokens": 13287173.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.402900981903076,
|
|
"epoch": 0.5566762728146013,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000497603139994675,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.2003258064389229,
|
|
"num_tokens": 13298225.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.381881332397461,
|
|
"epoch": 0.5571565802113353,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004975981465983338,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.20382763296365738,
|
|
"num_tokens": 13309685.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.313303709030151,
|
|
"epoch": 0.5576368876080692,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004975931480339246,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.20920694172382354,
|
|
"num_tokens": 13320837.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.373168277740478,
|
|
"epoch": 0.5581171950048031,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004975881443015635,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.20333101153373717,
|
|
"num_tokens": 13333512.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.478464984893799,
|
|
"epoch": 0.5585975024015369,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004975831354013667,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.19963099658489228,
|
|
"num_tokens": 13345189.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.362034654617309,
|
|
"epoch": 0.5590778097982709,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004975781213334503,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.2086104243993759,
|
|
"num_tokens": 13356123.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.3880220413208,
|
|
"epoch": 0.5595581171950048,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004975731020979309,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.20239470899105072,
|
|
"num_tokens": 13366902.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.459943771362305,
|
|
"epoch": 0.5600384245917387,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004975680776949249,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.200407475233078,
|
|
"num_tokens": 13377567.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.400122451782226,
|
|
"epoch": 0.5605187319884726,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004975630481245492,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.2129899948835373,
|
|
"num_tokens": 13387297.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.408231210708618,
|
|
"epoch": 0.5609990393852066,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004975580133869202,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.20631884038448334,
|
|
"num_tokens": 13397723.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.416802930831909,
|
|
"epoch": 0.5614793467819404,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004975529734821552,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.20144724398851394,
|
|
"num_tokens": 13409875.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.36104941368103,
|
|
"epoch": 0.5619596541786743,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004975479284103708,
|
|
"loss": 5.1902,
|
|
"mean_token_accuracy": 0.20576498061418533,
|
|
"num_tokens": 13421338.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.426533842086792,
|
|
"epoch": 0.5624399615754082,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975428781716845,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.20507221519947053,
|
|
"num_tokens": 13431373.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.410734415054321,
|
|
"epoch": 0.5629202689721422,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004975378227662134,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.20476576089859008,
|
|
"num_tokens": 13443158.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.4595184326171875,
|
|
"epoch": 0.5634005763688761,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004975327621940746,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.1933220088481903,
|
|
"num_tokens": 13454559.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.514381456375122,
|
|
"epoch": 0.56388088376561,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004975276964553861,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.19711938351392747,
|
|
"num_tokens": 13466934.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.40661940574646,
|
|
"epoch": 0.5643611911623438,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004975226255502651,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.21357636600732804,
|
|
"num_tokens": 13477770.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.451413154602051,
|
|
"epoch": 0.5648414985590778,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004975175494788297,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.1998008131980896,
|
|
"num_tokens": 13490093.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.453090238571167,
|
|
"epoch": 0.5653218059558117,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004975124682411974,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.20121294111013413,
|
|
"num_tokens": 13500663.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.405351638793945,
|
|
"epoch": 0.5658021133525456,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004975073818374863,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.2002902314066887,
|
|
"num_tokens": 13512369.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.3891054630279545,
|
|
"epoch": 0.5662824207492796,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004975022902678145,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.20277402997016908,
|
|
"num_tokens": 13523181.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.361138439178466,
|
|
"epoch": 0.5667627281460135,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004974971935323003,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.20029759407043457,
|
|
"num_tokens": 13534113.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.327734184265137,
|
|
"epoch": 0.5672430355427474,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004974920916310619,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.20367970913648606,
|
|
"num_tokens": 13545037.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.405796194076538,
|
|
"epoch": 0.5677233429394812,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974869845642178,
|
|
"loss": 5.2249,
|
|
"mean_token_accuracy": 0.20131197422742844,
|
|
"num_tokens": 13555541.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.352486181259155,
|
|
"epoch": 0.5682036503362152,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004974818723318866,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.20470297634601592,
|
|
"num_tokens": 13566951.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.4211790561676025,
|
|
"epoch": 0.5686839577329491,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004974767549341868,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.2000730812549591,
|
|
"num_tokens": 13578492.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.4369526386260985,
|
|
"epoch": 0.569164265129683,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974716323712376,
|
|
"loss": 5.1561,
|
|
"mean_token_accuracy": 0.21389784663915634,
|
|
"num_tokens": 13589183.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.404523801803589,
|
|
"epoch": 0.5696445725264169,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004974665046431576,
|
|
"loss": 5.2862,
|
|
"mean_token_accuracy": 0.202628256380558,
|
|
"num_tokens": 13600588.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.343457460403442,
|
|
"epoch": 0.5701248799231509,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004974613717500659,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.20688795298337936,
|
|
"num_tokens": 13612107.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.510196113586426,
|
|
"epoch": 0.5706051873198847,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004974562336920818,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.1963939294219017,
|
|
"num_tokens": 13623973.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.374628925323487,
|
|
"epoch": 0.5710854947166186,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004974510904693245,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.20711901485919954,
|
|
"num_tokens": 13634994.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.426691341400146,
|
|
"epoch": 0.5715658021133525,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004974459420819134,
|
|
"loss": 5.3057,
|
|
"mean_token_accuracy": 0.20290742069482803,
|
|
"num_tokens": 13646361.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.406249523162842,
|
|
"epoch": 0.5720461095100865,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000497440788529968,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.20263564288616182,
|
|
"num_tokens": 13656975.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.3955769538879395,
|
|
"epoch": 0.5725264169068204,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004974356298136081,
|
|
"loss": 5.2381,
|
|
"mean_token_accuracy": 0.19841890335083007,
|
|
"num_tokens": 13668434.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.416602754592896,
|
|
"epoch": 0.5730067243035543,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004974304659329533,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.19981901794672013,
|
|
"num_tokens": 13679266.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.355310297012329,
|
|
"epoch": 0.5734870317002881,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004974252968881236,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.1961240813136101,
|
|
"num_tokens": 13690921.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.414062929153443,
|
|
"epoch": 0.5739673390970221,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497420122679239,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.20539622157812118,
|
|
"num_tokens": 13702329.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.3050618171691895,
|
|
"epoch": 0.574447646493756,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004974149433064196,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.2154633417725563,
|
|
"num_tokens": 13713356.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.2760419845581055,
|
|
"epoch": 0.5749279538904899,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004974097587697856,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.20253586918115615,
|
|
"num_tokens": 13724718.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.281339883804321,
|
|
"epoch": 0.5754082612872238,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004974045690694575,
|
|
"loss": 5.1596,
|
|
"mean_token_accuracy": 0.2093519538640976,
|
|
"num_tokens": 13736113.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.454013776779175,
|
|
"epoch": 0.5758885686839578,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004973993742055557,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.2056156277656555,
|
|
"num_tokens": 13748322.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.352500104904175,
|
|
"epoch": 0.5763688760806917,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973941741782007,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.19695847779512404,
|
|
"num_tokens": 13759433.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5763688760806917,
|
|
"eval_entropy": 5.17189993351509,
|
|
"eval_loss": 5.2146196365356445,
|
|
"eval_mean_token_accuracy": 0.2106242566784959,
|
|
"eval_num_tokens": 13759433.0,
|
|
"eval_runtime": 20.5416,
|
|
"eval_samples_per_second": 1597.487,
|
|
"eval_steps_per_second": 199.692,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.306978511810303,
|
|
"epoch": 0.5768491834774255,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973889689875135,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.2072141870856285,
|
|
"num_tokens": 13770181.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.3306817531585695,
|
|
"epoch": 0.5773294908741594,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004973837586336147,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.2056859627366066,
|
|
"num_tokens": 13781792.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.371387672424317,
|
|
"epoch": 0.5778097982708934,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004973785431166254,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.1999555066227913,
|
|
"num_tokens": 13792101.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.355870532989502,
|
|
"epoch": 0.5782901056676273,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004973733224366666,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.2045416697859764,
|
|
"num_tokens": 13803640.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.396602439880371,
|
|
"epoch": 0.5787704130643612,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004973680965938597,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.20828541219234467,
|
|
"num_tokens": 13815017.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.471268939971924,
|
|
"epoch": 0.579250720461095,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004973628655883258,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.1929504841566086,
|
|
"num_tokens": 13826119.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.325129604339599,
|
|
"epoch": 0.579731027857829,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004973576294201865,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.20424154549837112,
|
|
"num_tokens": 13837869.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.520558834075928,
|
|
"epoch": 0.5802113352545629,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973523880895633,
|
|
"loss": 5.3258,
|
|
"mean_token_accuracy": 0.189467091858387,
|
|
"num_tokens": 13849333.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.431898689270019,
|
|
"epoch": 0.5806916426512968,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004973471415965779,
|
|
"loss": 5.1768,
|
|
"mean_token_accuracy": 0.20163828879594803,
|
|
"num_tokens": 13860648.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.487684631347657,
|
|
"epoch": 0.5811719500480308,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000497341889941352,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.19369055032730104,
|
|
"num_tokens": 13872979.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.381687974929809,
|
|
"epoch": 0.5816522574447647,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973366331240078,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.19978900402784347,
|
|
"num_tokens": 13884363.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.368413972854614,
|
|
"epoch": 0.5821325648414986,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497331371144667,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.19701047241687775,
|
|
"num_tokens": 13895424.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.420424938201904,
|
|
"epoch": 0.5826128722382324,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004973261040034521,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.1924986258149147,
|
|
"num_tokens": 13907319.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.286451292037964,
|
|
"epoch": 0.5830931796349664,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004973208317004852,
|
|
"loss": 5.1442,
|
|
"mean_token_accuracy": 0.20716721713542938,
|
|
"num_tokens": 13920013.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.358293342590332,
|
|
"epoch": 0.5835734870317003,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004973155542358889,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.20192718803882598,
|
|
"num_tokens": 13932033.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.3162446975708,
|
|
"epoch": 0.5840537944284342,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004973102716097853,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.21228280961513518,
|
|
"num_tokens": 13943324.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.365341424942017,
|
|
"epoch": 0.5845341018251681,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004973049838222973,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.21387782841920852,
|
|
"num_tokens": 13954291.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.43151888847351,
|
|
"epoch": 0.5850144092219021,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004972996908735479,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.19576199650764464,
|
|
"num_tokens": 13966264.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.4537965774536135,
|
|
"epoch": 0.585494716618636,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004972943927636597,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.19616830497980117,
|
|
"num_tokens": 13977785.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.328124332427978,
|
|
"epoch": 0.5859750240153698,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004972890894927558,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.2037198066711426,
|
|
"num_tokens": 13989704.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.399294757843018,
|
|
"epoch": 0.5864553314121037,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004972837810609592,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.20562218874692917,
|
|
"num_tokens": 14000565.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.290426778793335,
|
|
"epoch": 0.5869356388088377,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004972784674683933,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.21431584507226945,
|
|
"num_tokens": 14011521.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.309748888015747,
|
|
"epoch": 0.5874159462055716,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004972731487151815,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.21178604513406754,
|
|
"num_tokens": 14022966.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.457789134979248,
|
|
"epoch": 0.5878962536023055,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004972678248014471,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.20152803361415864,
|
|
"num_tokens": 14034905.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.296006965637207,
|
|
"epoch": 0.5883765609990393,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004972624957273139,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.20513343960046768,
|
|
"num_tokens": 14045816.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.307597351074219,
|
|
"epoch": 0.5888568683957733,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004972571614929055,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.204602187871933,
|
|
"num_tokens": 14057316.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.402098369598389,
|
|
"epoch": 0.5893371757925072,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004972518220983457,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.19972933381795882,
|
|
"num_tokens": 14067542.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.303103017807007,
|
|
"epoch": 0.5898174831892411,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004972464775437586,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.20539776235818863,
|
|
"num_tokens": 14079467.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.288284063339233,
|
|
"epoch": 0.590297790585975,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004972411278292683,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.214233922958374,
|
|
"num_tokens": 14090695.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.334277677536011,
|
|
"epoch": 0.590778097982709,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004972357729549988,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.21341056525707244,
|
|
"num_tokens": 14101380.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.30261263847351,
|
|
"epoch": 0.5912584053794429,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004972304129210746,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.20822506695985793,
|
|
"num_tokens": 14112265.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.358154821395874,
|
|
"epoch": 0.5917387127761767,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004972250477276202,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.20382460057735444,
|
|
"num_tokens": 14124294.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.372543287277222,
|
|
"epoch": 0.5922190201729106,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004972196773747599,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.20522281378507615,
|
|
"num_tokens": 14135230.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.3968939781188965,
|
|
"epoch": 0.5926993275696446,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004972143018626186,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.19905537217855454,
|
|
"num_tokens": 14147576.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.329421806335449,
|
|
"epoch": 0.5931796349663785,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004972089211913211,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.2102440357208252,
|
|
"num_tokens": 14158834.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.39668607711792,
|
|
"epoch": 0.5936599423631124,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004972035353609923,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.19556810408830644,
|
|
"num_tokens": 14170694.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.349567079544068,
|
|
"epoch": 0.5941402497598463,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004971981443717572,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.2067970633506775,
|
|
"num_tokens": 14183184.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.46701717376709,
|
|
"epoch": 0.5946205571565802,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004971927482237409,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.20054755210876465,
|
|
"num_tokens": 14194761.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.333970355987549,
|
|
"epoch": 0.5951008645533141,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004971873469170689,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.20996096581220627,
|
|
"num_tokens": 14205820.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.245835304260254,
|
|
"epoch": 0.595581171950048,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004971819404518664,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.20841328501701356,
|
|
"num_tokens": 14217826.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.3001384258270265,
|
|
"epoch": 0.5960614793467819,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497176528828259,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.21605950444936753,
|
|
"num_tokens": 14228632.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.387531566619873,
|
|
"epoch": 0.5965417867435159,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004971711120463722,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.1957363396883011,
|
|
"num_tokens": 14240231.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.439971780776977,
|
|
"epoch": 0.5970220941402498,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000497165690106332,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.20782527029514314,
|
|
"num_tokens": 14251718.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.36957859992981,
|
|
"epoch": 0.5975024015369836,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004971602630082642,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.2077389195561409,
|
|
"num_tokens": 14263129.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.275402593612671,
|
|
"epoch": 0.5979827089337176,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971548307522947,
|
|
"loss": 5.0912,
|
|
"mean_token_accuracy": 0.20676200836896896,
|
|
"num_tokens": 14274465.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.432278680801391,
|
|
"epoch": 0.5984630163304515,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004971493933385498,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.2048093259334564,
|
|
"num_tokens": 14286190.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.438970947265625,
|
|
"epoch": 0.5989433237271854,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004971439507671556,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.20013955533504485,
|
|
"num_tokens": 14297638.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.327042865753174,
|
|
"epoch": 0.5994236311239193,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004971385030382384,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.2074238583445549,
|
|
"num_tokens": 14309773.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.352311897277832,
|
|
"epoch": 0.5999039385206533,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004971330501519248,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.20862484276294707,
|
|
"num_tokens": 14320543.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.395197534561158,
|
|
"epoch": 0.6003842459173871,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004971275921083414,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.20144042670726775,
|
|
"num_tokens": 14332076.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.317584037780762,
|
|
"epoch": 0.600864553314121,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000497122128907615,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.20920995026826858,
|
|
"num_tokens": 14343768.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.310052871704102,
|
|
"epoch": 0.6013448607108549,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004971166605498722,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.2052968069911003,
|
|
"num_tokens": 14357051.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.353819084167481,
|
|
"epoch": 0.6018251681075889,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004971111870352401,
|
|
"loss": 5.1891,
|
|
"mean_token_accuracy": 0.20196061283349992,
|
|
"num_tokens": 14368800.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.3648130893707275,
|
|
"epoch": 0.6023054755043228,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004971057083638458,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.20868575274944307,
|
|
"num_tokens": 14379617.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.339131259918213,
|
|
"epoch": 0.6027857829010567,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004971002245358166,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.213275907933712,
|
|
"num_tokens": 14391454.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.36895980834961,
|
|
"epoch": 0.6032660902977905,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004970947355512795,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.2128308355808258,
|
|
"num_tokens": 14402379.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.328395509719849,
|
|
"epoch": 0.6037463976945245,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004970892414103622,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.20732113867998123,
|
|
"num_tokens": 14415040.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.362541007995605,
|
|
"epoch": 0.6042267050912584,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004970837421131921,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.19479774683713913,
|
|
"num_tokens": 14426677.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.357956600189209,
|
|
"epoch": 0.6047070124879923,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004970782376598972,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.206345434486866,
|
|
"num_tokens": 14436676.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.376431560516357,
|
|
"epoch": 0.6051873198847262,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004970727280506048,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.2027482271194458,
|
|
"num_tokens": 14448294.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.328565835952759,
|
|
"epoch": 0.6056676272814602,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004970672132854431,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.20563995242118835,
|
|
"num_tokens": 14460642.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.29191780090332,
|
|
"epoch": 0.6061479346781941,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004970616933645403,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.21846782863140107,
|
|
"num_tokens": 14471370.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.412834596633911,
|
|
"epoch": 0.6066282420749279,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004970561682880242,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.20499045699834822,
|
|
"num_tokens": 14482358.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.385143852233886,
|
|
"epoch": 0.6071085494716618,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004970506380560233,
|
|
"loss": 5.2463,
|
|
"mean_token_accuracy": 0.20311239063739778,
|
|
"num_tokens": 14494413.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.395890903472901,
|
|
"epoch": 0.6075888568683958,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004970451026686659,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.21031228005886077,
|
|
"num_tokens": 14506370.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.366713953018189,
|
|
"epoch": 0.6080691642651297,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004970395621260806,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.21305836588144303,
|
|
"num_tokens": 14517198.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.424633312225342,
|
|
"epoch": 0.6085494716618636,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000497034016428396,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.1964514061808586,
|
|
"num_tokens": 14529434.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.307683801651001,
|
|
"epoch": 0.6090297790585975,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004970284655757409,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.2103516861796379,
|
|
"num_tokens": 14540857.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.319919157028198,
|
|
"epoch": 0.6095100864553314,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004970229095682439,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.20560289323329925,
|
|
"num_tokens": 14552594.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.375809860229492,
|
|
"epoch": 0.6099903938520653,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004970173484060344,
|
|
"loss": 5.2158,
|
|
"mean_token_accuracy": 0.2014269471168518,
|
|
"num_tokens": 14563599.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.400948429107666,
|
|
"epoch": 0.6104707012487992,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004970117820892414,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.20366021990776062,
|
|
"num_tokens": 14575905.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.380741024017334,
|
|
"epoch": 0.6109510086455331,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004970062106179939,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.21184269338846207,
|
|
"num_tokens": 14587800.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.326152706146241,
|
|
"epoch": 0.6114313160422671,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004970006339924214,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.21315738260746003,
|
|
"num_tokens": 14600654.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.393792629241943,
|
|
"epoch": 0.611911623439001,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004969950522126534,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.20788408666849137,
|
|
"num_tokens": 14611985.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.295234346389771,
|
|
"epoch": 0.6123919308357348,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004969894652788196,
|
|
"loss": 5.1226,
|
|
"mean_token_accuracy": 0.21155203580856324,
|
|
"num_tokens": 14625004.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.367025756835938,
|
|
"epoch": 0.6128722382324687,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969838731910494,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.20544978678226472,
|
|
"num_tokens": 14635381.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.317724943161011,
|
|
"epoch": 0.6133525456292027,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969782759494729,
|
|
"loss": 5.1284,
|
|
"mean_token_accuracy": 0.21093843430280684,
|
|
"num_tokens": 14646582.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.312413883209229,
|
|
"epoch": 0.6138328530259366,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049697267355422,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.21181879341602325,
|
|
"num_tokens": 14658024.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.485131025314331,
|
|
"epoch": 0.6143131604226705,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004969670660054208,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.19830967038869857,
|
|
"num_tokens": 14669933.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.379800939559937,
|
|
"epoch": 0.6147934678194045,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004969614533032054,
|
|
"loss": 5.1814,
|
|
"mean_token_accuracy": 0.20320038497447968,
|
|
"num_tokens": 14681331.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.237337875366211,
|
|
"epoch": 0.6152737752161384,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004969558354477041,
|
|
"loss": 5.0217,
|
|
"mean_token_accuracy": 0.21839836984872818,
|
|
"num_tokens": 14691361.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.315851306915283,
|
|
"epoch": 0.6157540826128722,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969502124390474,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.20834049731492996,
|
|
"num_tokens": 14701791.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.390240621566773,
|
|
"epoch": 0.6162343900096061,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004969445842773658,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.19944172948598862,
|
|
"num_tokens": 14713672.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.303598499298095,
|
|
"epoch": 0.6167146974063401,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049693895096279,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.2155421108007431,
|
|
"num_tokens": 14724789.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.286634874343872,
|
|
"epoch": 0.617195004803074,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004969333124954508,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.20550125539302827,
|
|
"num_tokens": 14737212.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.292817258834839,
|
|
"epoch": 0.6176753121998079,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004969276688754791,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.20599037855863572,
|
|
"num_tokens": 14748387.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.363704776763916,
|
|
"epoch": 0.6181556195965417,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004969220201030059,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.20211084485054015,
|
|
"num_tokens": 14758477.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.370852279663086,
|
|
"epoch": 0.6186359269932757,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969163661781624,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.20346666276454925,
|
|
"num_tokens": 14769650.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.252781963348388,
|
|
"epoch": 0.6191162343900096,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969107071010798,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.21276762336492538,
|
|
"num_tokens": 14780988.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.361257648468017,
|
|
"epoch": 0.6195965417867435,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004969050428718895,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.20762884467840195,
|
|
"num_tokens": 14792458.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.369265222549439,
|
|
"epoch": 0.6200768491834774,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000496899373490723,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.20686816722154616,
|
|
"num_tokens": 14804772.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.3651207447052,
|
|
"epoch": 0.6205571565802114,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496893698957712,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.20470530688762664,
|
|
"num_tokens": 14816126.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.397782659530639,
|
|
"epoch": 0.6210374639769453,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004968880192729882,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.20079650729894638,
|
|
"num_tokens": 14829376.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.312540054321289,
|
|
"epoch": 0.6215177713736791,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004968823344366835,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.2153061196208,
|
|
"num_tokens": 14841098.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.303245687484742,
|
|
"epoch": 0.621998078770413,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004968766444489298,
|
|
"loss": 5.1098,
|
|
"mean_token_accuracy": 0.20885020941495896,
|
|
"num_tokens": 14852690.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.3362432479858395,
|
|
"epoch": 0.622478386167147,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004968709493098593,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.20867665559053422,
|
|
"num_tokens": 14863327.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.387118530273438,
|
|
"epoch": 0.6229586935638809,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004968652490196041,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.20046956092119217,
|
|
"num_tokens": 14875213.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.348819875717163,
|
|
"epoch": 0.6234390009606148,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004968595435782967,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.22016421258449553,
|
|
"num_tokens": 14886129.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.426475858688354,
|
|
"epoch": 0.6239193083573487,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004968538329860695,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.19709108769893646,
|
|
"num_tokens": 14897217.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.355967044830322,
|
|
"epoch": 0.6243996157540826,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004968481172430549,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.20492311269044877,
|
|
"num_tokens": 14908438.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.276374959945679,
|
|
"epoch": 0.6248799231508165,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000496842396349386,
|
|
"loss": 5.0919,
|
|
"mean_token_accuracy": 0.2137288123369217,
|
|
"num_tokens": 14920472.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.299534654617309,
|
|
"epoch": 0.6253602305475504,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004968366703051952,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.209611739218235,
|
|
"num_tokens": 14932075.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.330506467819214,
|
|
"epoch": 0.6258405379442843,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004968309391106157,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.21013996005058289,
|
|
"num_tokens": 14942971.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.315490245819092,
|
|
"epoch": 0.6263208453410183,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004968252027657806,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.2154913440346718,
|
|
"num_tokens": 14954288.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.256664657592774,
|
|
"epoch": 0.6268011527377522,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004968194612708229,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.20832486301660538,
|
|
"num_tokens": 14966017.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.360432958602905,
|
|
"epoch": 0.627281460134486,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004968137146258759,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.20783136337995528,
|
|
"num_tokens": 14978022.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.269650602340699,
|
|
"epoch": 0.6277617675312199,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004968079628310732,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.21249632388353348,
|
|
"num_tokens": 14990370.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.248974943161011,
|
|
"epoch": 0.6282420749279539,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004968022058865482,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.21422789245843887,
|
|
"num_tokens": 15001535.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.416878795623779,
|
|
"epoch": 0.6287223823246878,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004967964437924346,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.21044517308473587,
|
|
"num_tokens": 15012560.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.257675266265869,
|
|
"epoch": 0.6292026897214217,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004967906765488662,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.21322489976882936,
|
|
"num_tokens": 15024594.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.326331043243409,
|
|
"epoch": 0.6296829971181557,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004967849041559769,
|
|
"loss": 5.1057,
|
|
"mean_token_accuracy": 0.21285986304283142,
|
|
"num_tokens": 15034735.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.396697187423706,
|
|
"epoch": 0.6301633045148896,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004967791266139006,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.20284678786993027,
|
|
"num_tokens": 15046955.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.3369475364685055,
|
|
"epoch": 0.6306436119116234,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004967733439227716,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.20890088230371476,
|
|
"num_tokens": 15058250.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.359533166885376,
|
|
"epoch": 0.6311239193083573,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496767556082724,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.20450974106788636,
|
|
"num_tokens": 15069451.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.3008757591247555,
|
|
"epoch": 0.6316042267050913,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004967617630938924,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.21107075065374375,
|
|
"num_tokens": 15080920.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.284978914260864,
|
|
"epoch": 0.6320845341018252,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000496755964956411,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.20591130405664443,
|
|
"num_tokens": 15091579.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.308378839492798,
|
|
"epoch": 0.6325648414985591,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967501616704147,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.20694429576396942,
|
|
"num_tokens": 15103097.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.305421543121338,
|
|
"epoch": 0.633045148895293,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496744353236038,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.21201552748680114,
|
|
"num_tokens": 15114646.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.406478595733643,
|
|
"epoch": 0.633525456292027,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000496738539653416,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.2054781585931778,
|
|
"num_tokens": 15126019.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.364590787887574,
|
|
"epoch": 0.6340057636887608,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004967327209226835,
|
|
"loss": 5.1486,
|
|
"mean_token_accuracy": 0.21009373515844346,
|
|
"num_tokens": 15136132.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.3448058605194095,
|
|
"epoch": 0.6344860710854947,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004967268970439755,
|
|
"loss": 5.2203,
|
|
"mean_token_accuracy": 0.20390277355909348,
|
|
"num_tokens": 15149016.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.399990177154541,
|
|
"epoch": 0.6349663784822286,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004967210680174274,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.2116396740078926,
|
|
"num_tokens": 15160302.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.350642824172974,
|
|
"epoch": 0.6354466858789626,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004967152338431745,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.20768017321825027,
|
|
"num_tokens": 15171770.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.319510459899902,
|
|
"epoch": 0.6359269932756965,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004967093945213523,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.21049544364213943,
|
|
"num_tokens": 15182283.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.277123641967774,
|
|
"epoch": 0.6364073006724303,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004967035500520962,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.20742365568876267,
|
|
"num_tokens": 15193917.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.453793668746949,
|
|
"epoch": 0.6368876080691642,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004966977004355421,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.20050635039806367,
|
|
"num_tokens": 15205854.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.287836170196533,
|
|
"epoch": 0.6373679154658982,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004966918456718256,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.21320753097534179,
|
|
"num_tokens": 15217884.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.347429323196411,
|
|
"epoch": 0.6378482228626321,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004966859857610828,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.20406776517629624,
|
|
"num_tokens": 15229493.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.344024515151977,
|
|
"epoch": 0.638328530259366,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004966801207034497,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.20313767045736314,
|
|
"num_tokens": 15241402.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.389021968841552,
|
|
"epoch": 0.6388088376560999,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004966742504990624,
|
|
"loss": 5.1781,
|
|
"mean_token_accuracy": 0.20621784329414367,
|
|
"num_tokens": 15252981.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.3174539566040036,
|
|
"epoch": 0.6392891450528339,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004966683751480572,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.21280963718891144,
|
|
"num_tokens": 15264171.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.3186562061309814,
|
|
"epoch": 0.6397694524495677,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004966624946505706,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.20979261100292207,
|
|
"num_tokens": 15275595.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.387149906158447,
|
|
"epoch": 0.6402497598463016,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004966566090067391,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.20688546895980836,
|
|
"num_tokens": 15286074.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.379571866989136,
|
|
"epoch": 0.6407300672430355,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004966507182166993,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.2026302382349968,
|
|
"num_tokens": 15296230.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.316071510314941,
|
|
"epoch": 0.6412103746397695,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000496644822280588,
|
|
"loss": 5.1324,
|
|
"mean_token_accuracy": 0.20843050479888917,
|
|
"num_tokens": 15307428.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.408726644515991,
|
|
"epoch": 0.6416906820365034,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000496638921198542,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.19868980199098588,
|
|
"num_tokens": 15318796.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.310985040664673,
|
|
"epoch": 0.6421709894332372,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004966330149706984,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.2115129992365837,
|
|
"num_tokens": 15330914.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.282835483551025,
|
|
"epoch": 0.6426512968299711,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004966271035971944,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.20557762086391448,
|
|
"num_tokens": 15341756.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.40358681678772,
|
|
"epoch": 0.6431316042267051,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004966211870781671,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.20149461328983306,
|
|
"num_tokens": 15353217.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.3673028469085695,
|
|
"epoch": 0.643611911623439,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000496615265413754,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.2055822029709816,
|
|
"num_tokens": 15363813.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.288237810134888,
|
|
"epoch": 0.6440922190201729,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966093386040923,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.2095430463552475,
|
|
"num_tokens": 15375223.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.326645851135254,
|
|
"epoch": 0.6445725264169068,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049660340664932,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.21088357269763947,
|
|
"num_tokens": 15385523.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.3942523956298825,
|
|
"epoch": 0.6450528338136408,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004965974695495746,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.20370138734579085,
|
|
"num_tokens": 15397262.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.243142366409302,
|
|
"epoch": 0.6455331412103746,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004965915273049938,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.21149415522813797,
|
|
"num_tokens": 15409043.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.320618915557861,
|
|
"epoch": 0.6460134486071085,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004965855799157158,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.20918045789003373,
|
|
"num_tokens": 15420859.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.36569995880127,
|
|
"epoch": 0.6464937560038425,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004965796273818787,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.20250088423490525,
|
|
"num_tokens": 15433650.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.275715637207031,
|
|
"epoch": 0.6469740634005764,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004965736697036206,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.21408701539039612,
|
|
"num_tokens": 15445158.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.418146705627441,
|
|
"epoch": 0.6474543707973103,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004965677068810798,
|
|
"loss": 5.3321,
|
|
"mean_token_accuracy": 0.19387490600347518,
|
|
"num_tokens": 15456974.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.41830039024353,
|
|
"epoch": 0.6479346781940442,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004965617389143947,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.20549649000167847,
|
|
"num_tokens": 15467395.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.293714284896851,
|
|
"epoch": 0.6484149855907781,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000496555765803704,
|
|
"loss": 5.193,
|
|
"mean_token_accuracy": 0.2080518677830696,
|
|
"num_tokens": 15479396.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.310993337631226,
|
|
"epoch": 0.648895292987512,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004965497875491462,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.21137345135211943,
|
|
"num_tokens": 15490992.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.4591199398040775,
|
|
"epoch": 0.6493756003842459,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004965438041508604,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.19662567228078842,
|
|
"num_tokens": 15502413.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.374146842956543,
|
|
"epoch": 0.6498559077809798,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004965378156089851,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.20146453827619554,
|
|
"num_tokens": 15512588.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.319894742965698,
|
|
"epoch": 0.6503362151777138,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004965318219236597,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.2045357957482338,
|
|
"num_tokens": 15523252.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.309787845611572,
|
|
"epoch": 0.6508165225744477,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004965258230950232,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.2023079663515091,
|
|
"num_tokens": 15534975.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.322136354446411,
|
|
"epoch": 0.6512968299711815,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965198191232148,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.2112494647502899,
|
|
"num_tokens": 15545709.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.382352638244629,
|
|
"epoch": 0.6517771373679154,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000496513810008374,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.21332192420959473,
|
|
"num_tokens": 15557270.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.391598176956177,
|
|
"epoch": 0.6522574447646494,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004965077957506403,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.20827943235635757,
|
|
"num_tokens": 15569156.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.294995450973511,
|
|
"epoch": 0.6527377521613833,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004965017763501533,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.20894810557365417,
|
|
"num_tokens": 15579270.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.2520428657531735,
|
|
"epoch": 0.6532180595581172,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004964957518070529,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.21518850773572923,
|
|
"num_tokens": 15589912.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.378147077560425,
|
|
"epoch": 0.6536983669548511,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004964897221214788,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.20349239856004714,
|
|
"num_tokens": 15601088.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.376770877838135,
|
|
"epoch": 0.654178674351585,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496483687293571,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.20756430178880692,
|
|
"num_tokens": 15612520.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.302024173736572,
|
|
"epoch": 0.6546589817483189,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004964776473234696,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.21862724870443345,
|
|
"num_tokens": 15623991.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.218190479278564,
|
|
"epoch": 0.6551392891450528,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000496471602211315,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.21332069784402846,
|
|
"num_tokens": 15635389.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.326016759872436,
|
|
"epoch": 0.6556195965417867,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004964655519572475,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.2181401401758194,
|
|
"num_tokens": 15646427.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.2474266529083256,
|
|
"epoch": 0.6560999039385207,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004964594965614072,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.2103773534297943,
|
|
"num_tokens": 15657518.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.351989126205444,
|
|
"epoch": 0.6565802113352546,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004964534360239353,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.20573293566703796,
|
|
"num_tokens": 15669775.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.312732362747193,
|
|
"epoch": 0.6570605187319885,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000496447370344972,
|
|
"loss": 5.1466,
|
|
"mean_token_accuracy": 0.20142304003238679,
|
|
"num_tokens": 15682566.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.272958993911743,
|
|
"epoch": 0.6575408261287223,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004964412995246584,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.2153865084052086,
|
|
"num_tokens": 15693168.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.333586740493774,
|
|
"epoch": 0.6580211335254563,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004964352235631354,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.2094581201672554,
|
|
"num_tokens": 15703879.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.400853109359741,
|
|
"epoch": 0.6585014409221902,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000496429142460544,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.20100296437740325,
|
|
"num_tokens": 15716015.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.411762380599976,
|
|
"epoch": 0.6589817483189241,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004964230562170254,
|
|
"loss": 5.1781,
|
|
"mean_token_accuracy": 0.2079763263463974,
|
|
"num_tokens": 15728254.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.31914324760437,
|
|
"epoch": 0.659462055715658,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004964169648327209,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.20646823644638063,
|
|
"num_tokens": 15738778.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.350067758560181,
|
|
"epoch": 0.659942363112392,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496410868307772,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.2045704886317253,
|
|
"num_tokens": 15750305.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.372748517990113,
|
|
"epoch": 0.6604226705091258,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004964047666423203,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.20822612941265106,
|
|
"num_tokens": 15761303.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.299829530715942,
|
|
"epoch": 0.6609029779058597,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004963986598365072,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.21532647013664247,
|
|
"num_tokens": 15773095.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.351714468002319,
|
|
"epoch": 0.6613832853025937,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004963925478904746,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.21195616871118544,
|
|
"num_tokens": 15784405.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.235157918930054,
|
|
"epoch": 0.6618635926993276,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004963864308043645,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.20711841732263564,
|
|
"num_tokens": 15795178.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.290901565551758,
|
|
"epoch": 0.6623439000960615,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004963803085783189,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.2067147433757782,
|
|
"num_tokens": 15806205.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.313950729370117,
|
|
"epoch": 0.6628242074927954,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004963741812124799,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.21753399223089218,
|
|
"num_tokens": 15817474.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.268809366226196,
|
|
"epoch": 0.6633045148895294,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004963680487069898,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.2037314921617508,
|
|
"num_tokens": 15829728.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.385620164871216,
|
|
"epoch": 0.6637848222862632,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004963619110619908,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.20655222982168198,
|
|
"num_tokens": 15840082.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.380099678039551,
|
|
"epoch": 0.6642651296829971,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004963557682776256,
|
|
"loss": 5.115,
|
|
"mean_token_accuracy": 0.20173939764499665,
|
|
"num_tokens": 15851450.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.400586414337158,
|
|
"epoch": 0.664745437079731,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004963496203540368,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.20122259259223937,
|
|
"num_tokens": 15864168.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.3505774974823,
|
|
"epoch": 0.665225744476465,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004963434672913671,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.2109785258769989,
|
|
"num_tokens": 15875634.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.464935636520385,
|
|
"epoch": 0.6657060518731989,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004963373090897592,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.20236394703388214,
|
|
"num_tokens": 15888411.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.358474016189575,
|
|
"epoch": 0.6661863592699327,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004963311457493563,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.20183018147945403,
|
|
"num_tokens": 15901084.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.398572540283203,
|
|
"epoch": 0.6666666666666666,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004963249772703015,
|
|
"loss": 5.2033,
|
|
"mean_token_accuracy": 0.20429981648921966,
|
|
"num_tokens": 15912061.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.398046255111694,
|
|
"epoch": 0.6671469740634006,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004963188036527378,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.20116444826126098,
|
|
"num_tokens": 15925439.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.292640972137451,
|
|
"epoch": 0.6676272814601345,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004963126248968087,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.22056220322847367,
|
|
"num_tokens": 15937762.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.226414442062378,
|
|
"epoch": 0.6681075888568684,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004963064410026577,
|
|
"loss": 5.036,
|
|
"mean_token_accuracy": 0.21784193813800812,
|
|
"num_tokens": 15948656.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.370252323150635,
|
|
"epoch": 0.6685878962536023,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004963002519704281,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.20235869139432908,
|
|
"num_tokens": 15960376.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.392440366744995,
|
|
"epoch": 0.6690682036503363,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496294057800264,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.20715708136558533,
|
|
"num_tokens": 15971913.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.336017179489136,
|
|
"epoch": 0.6695485110470701,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004962878584923089,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.20061488151550294,
|
|
"num_tokens": 15984775.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.324187469482422,
|
|
"epoch": 0.670028818443804,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004962816540467068,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.20296642184257507,
|
|
"num_tokens": 15996717.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.31804633140564,
|
|
"epoch": 0.6705091258405379,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004962754444636017,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.21299038529396058,
|
|
"num_tokens": 16007964.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.302518272399903,
|
|
"epoch": 0.6709894332372719,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000496269229743138,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.2090325817465782,
|
|
"num_tokens": 16019185.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.34990234375,
|
|
"epoch": 0.6714697406340058,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004962630098854597,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.21032043546438217,
|
|
"num_tokens": 16029983.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.316616630554199,
|
|
"epoch": 0.6719500480307397,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004962567848907113,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.20968452394008635,
|
|
"num_tokens": 16040574.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.368011045455932,
|
|
"epoch": 0.6724303554274735,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004962505547590374,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.20728860199451446,
|
|
"num_tokens": 16052037.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.393733358383178,
|
|
"epoch": 0.6729106628242075,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004962443194905826,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.2026839643716812,
|
|
"num_tokens": 16063413.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.387011575698852,
|
|
"epoch": 0.6733909702209414,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004962380790854916,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.20336944609880447,
|
|
"num_tokens": 16074373.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.370492839813233,
|
|
"epoch": 0.6738712776176753,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004962318335439094,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.19826406985521317,
|
|
"num_tokens": 16086575.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.306420516967774,
|
|
"epoch": 0.6743515850144092,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004962255828659809,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.21166469156742096,
|
|
"num_tokens": 16098529.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.295602798461914,
|
|
"epoch": 0.6748318924111432,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004962193270518513,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.21224457025527954,
|
|
"num_tokens": 16110085.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.29178900718689,
|
|
"epoch": 0.675312199807877,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004962130661016659,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.21021574437618257,
|
|
"num_tokens": 16120249.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.408480501174926,
|
|
"epoch": 0.6757925072046109,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004962068000155699,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.19446971565485,
|
|
"num_tokens": 16132645.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.334974527359009,
|
|
"epoch": 0.6762728146013448,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004962005287937088,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.21253057569265366,
|
|
"num_tokens": 16143808.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.309336805343628,
|
|
"epoch": 0.6767531219980788,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961942524362283,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.21257366091012955,
|
|
"num_tokens": 16154309.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.348855829238891,
|
|
"epoch": 0.6772334293948127,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004961879709432741,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.20713894218206405,
|
|
"num_tokens": 16164654.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.409746599197388,
|
|
"epoch": 0.6777137367915466,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496181684314992,
|
|
"loss": 5.1632,
|
|
"mean_token_accuracy": 0.20302171260118484,
|
|
"num_tokens": 16177837.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.29151873588562,
|
|
"epoch": 0.6781940441882806,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004961753925515279,
|
|
"loss": 5.0592,
|
|
"mean_token_accuracy": 0.21328389942646026,
|
|
"num_tokens": 16189073.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.369131755828858,
|
|
"epoch": 0.6786743515850144,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000496169095653028,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.2068806990981102,
|
|
"num_tokens": 16200371.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.326678657531739,
|
|
"epoch": 0.6791546589817483,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004961627936196384,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.21685010492801665,
|
|
"num_tokens": 16210526.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.347667503356933,
|
|
"epoch": 0.6796349663784822,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004961564864515055,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.21133444607257842,
|
|
"num_tokens": 16221687.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.2318473815917965,
|
|
"epoch": 0.6801152737752162,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004961501741487757,
|
|
"loss": 5.0217,
|
|
"mean_token_accuracy": 0.22075052410364152,
|
|
"num_tokens": 16233828.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.2553661346435545,
|
|
"epoch": 0.6805955811719501,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004961438567115955,
|
|
"loss": 5.0146,
|
|
"mean_token_accuracy": 0.22390031367540358,
|
|
"num_tokens": 16243900.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.280510330200196,
|
|
"epoch": 0.681075888568684,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004961375341401116,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.2133181780576706,
|
|
"num_tokens": 16256347.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.319049263000489,
|
|
"epoch": 0.6815561959654178,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004961312064344708,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.21245002895593643,
|
|
"num_tokens": 16267743.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.236669540405273,
|
|
"epoch": 0.6820365033621518,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049612487359482,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.21554897278547286,
|
|
"num_tokens": 16278280.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.234877729415894,
|
|
"epoch": 0.6825168107588857,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961185356213062,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.21809980124235154,
|
|
"num_tokens": 16288568.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.294752979278565,
|
|
"epoch": 0.6829971181556196,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004961121925140767,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.21069593280553817,
|
|
"num_tokens": 16300730.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.304313468933105,
|
|
"epoch": 0.6834774255523535,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961058442732786,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.20534905791282654,
|
|
"num_tokens": 16311789.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.305329036712647,
|
|
"epoch": 0.6839577329490875,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004960994908990594,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.20463583320379258,
|
|
"num_tokens": 16324439.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.416294384002685,
|
|
"epoch": 0.6844380403458213,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004960931323915665,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.21601954698562623,
|
|
"num_tokens": 16335344.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.329084968566894,
|
|
"epoch": 0.6849183477425552,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004960867687509475,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.21148615926504136,
|
|
"num_tokens": 16349018.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.325907421112061,
|
|
"epoch": 0.6853986551392891,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960803999773504,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.20542858988046647,
|
|
"num_tokens": 16360137.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.354696941375733,
|
|
"epoch": 0.6858789625360231,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004960740260709228,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.21040215939283372,
|
|
"num_tokens": 16372277.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.36764178276062,
|
|
"epoch": 0.686359269932757,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004960676470318128,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.20619126707315444,
|
|
"num_tokens": 16383440.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.336434745788575,
|
|
"epoch": 0.6868395773294909,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004960612628601683,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.20799643397331238,
|
|
"num_tokens": 16394330.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.259572553634643,
|
|
"epoch": 0.6873198847262247,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004960548735561379,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.21908190548419954,
|
|
"num_tokens": 16405734.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.3112781047821045,
|
|
"epoch": 0.6878001921229587,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960484791198697,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.20679262578487395,
|
|
"num_tokens": 16416025.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.296441125869751,
|
|
"epoch": 0.6882804995196926,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004960420795515121,
|
|
"loss": 5.0933,
|
|
"mean_token_accuracy": 0.21095090508460998,
|
|
"num_tokens": 16427416.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.288483285903931,
|
|
"epoch": 0.6887608069164265,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004960356748512138,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.213330939412117,
|
|
"num_tokens": 16438073.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.276486349105835,
|
|
"epoch": 0.6892411143131604,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004960292650191236,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.2134612113237381,
|
|
"num_tokens": 16449994.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.2832695007324215,
|
|
"epoch": 0.6897214217098944,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004960228500553899,
|
|
"loss": 5.0432,
|
|
"mean_token_accuracy": 0.22136877477169037,
|
|
"num_tokens": 16460355.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.358346033096313,
|
|
"epoch": 0.6902017291066282,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004960164299601623,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.20528924614191055,
|
|
"num_tokens": 16472274.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.3691483497619625,
|
|
"epoch": 0.6906820365033621,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004960100047335892,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.21010650247335433,
|
|
"num_tokens": 16482959.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.345746898651123,
|
|
"epoch": 0.691162343900096,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004960035743758202,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.2034367188811302,
|
|
"num_tokens": 16494533.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.212039041519165,
|
|
"epoch": 0.69164265129683,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004959971388870044,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.21525924652814865,
|
|
"num_tokens": 16506124.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.305228567123413,
|
|
"epoch": 0.6921229586935639,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004959906982672912,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.2091907739639282,
|
|
"num_tokens": 16517867.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.256267166137695,
|
|
"epoch": 0.6926032660902978,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004959842525168302,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.21432278901338578,
|
|
"num_tokens": 16529075.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.317261743545532,
|
|
"epoch": 0.6930835734870316,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004959778016357712,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.2152673825621605,
|
|
"num_tokens": 16540326.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.318550968170166,
|
|
"epoch": 0.6935638808837656,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004959713456242637,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.21104695349931718,
|
|
"num_tokens": 16551570.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.385565185546875,
|
|
"epoch": 0.6940441882804995,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004959648844824576,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.21007074266672135,
|
|
"num_tokens": 16562636.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.319220018386841,
|
|
"epoch": 0.6945244956772334,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004959584182105032,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.21816612184047698,
|
|
"num_tokens": 16573867.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.206090497970581,
|
|
"epoch": 0.6950048030739674,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004959519468085504,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.2207987681031227,
|
|
"num_tokens": 16584533.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.289491128921509,
|
|
"epoch": 0.6954851104707013,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004959454702767494,
|
|
"loss": 5.2381,
|
|
"mean_token_accuracy": 0.2078647419810295,
|
|
"num_tokens": 16596562.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.348395824432373,
|
|
"epoch": 0.6959654178674352,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004959389886152507,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.2130254775285721,
|
|
"num_tokens": 16607508.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.350907850265503,
|
|
"epoch": 0.696445725264169,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004959325018242048,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.20744186639785767,
|
|
"num_tokens": 16617737.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.369990825653076,
|
|
"epoch": 0.696926032660903,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004959260099037622,
|
|
"loss": 5.1509,
|
|
"mean_token_accuracy": 0.20871317833662034,
|
|
"num_tokens": 16628518.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.323066663742066,
|
|
"epoch": 0.6974063400576369,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004959195128540737,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.20603234469890594,
|
|
"num_tokens": 16639644.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.429886150360107,
|
|
"epoch": 0.6978866474543708,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00049591301067529,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.19961978644132614,
|
|
"num_tokens": 16650882.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.371072101593017,
|
|
"epoch": 0.6983669548511047,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004959065033675623,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.20525182038545609,
|
|
"num_tokens": 16662464.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.361147451400757,
|
|
"epoch": 0.6988472622478387,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004958999909310414,
|
|
"loss": 5.1558,
|
|
"mean_token_accuracy": 0.20310764908790588,
|
|
"num_tokens": 16673718.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.267883825302124,
|
|
"epoch": 0.6993275696445725,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004958934733658788,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.20379672348499298,
|
|
"num_tokens": 16684957.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.354166889190674,
|
|
"epoch": 0.6998078770413064,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004958869506722256,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.20695476233959198,
|
|
"num_tokens": 16695782.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.318038415908814,
|
|
"epoch": 0.7002881844380403,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004958804228502332,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.21745894253253936,
|
|
"num_tokens": 16707448.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.206328392028809,
|
|
"epoch": 0.7007684918347743,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004958738899000534,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.20685766786336898,
|
|
"num_tokens": 16718074.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.296359872817993,
|
|
"epoch": 0.7012487992315082,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004958673518218377,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.2153885081410408,
|
|
"num_tokens": 16728656.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.316540145874024,
|
|
"epoch": 0.7017291066282421,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004958608086157379,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.2120751053094864,
|
|
"num_tokens": 16740703.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.307763719558716,
|
|
"epoch": 0.7022094140249759,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495854260281906,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.22452596575021744,
|
|
"num_tokens": 16753320.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.209990787506103,
|
|
"epoch": 0.7026897214217099,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004958477068204941,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.2123555824160576,
|
|
"num_tokens": 16764889.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.362256240844727,
|
|
"epoch": 0.7031700288184438,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000495841148231654,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.21161444634199142,
|
|
"num_tokens": 16776301.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.346973085403443,
|
|
"epoch": 0.7036503362151777,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004958345845155383,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.2196694180369377,
|
|
"num_tokens": 16786935.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.265995645523072,
|
|
"epoch": 0.7041306436119116,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004958280156722992,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.20905097723007202,
|
|
"num_tokens": 16799335.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.230437231063843,
|
|
"epoch": 0.7046109510086456,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004958214417020894,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.20976387858390808,
|
|
"num_tokens": 16811376.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.359433364868164,
|
|
"epoch": 0.7050912584053795,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004958148626050614,
|
|
"loss": 5.1172,
|
|
"mean_token_accuracy": 0.2076278418302536,
|
|
"num_tokens": 16822859.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.313623666763306,
|
|
"epoch": 0.7055715658021133,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000495808278381368,
|
|
"loss": 5.0985,
|
|
"mean_token_accuracy": 0.21256341636180878,
|
|
"num_tokens": 16833831.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.299200201034546,
|
|
"epoch": 0.7060518731988472,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000495801689031162,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.21099364310503005,
|
|
"num_tokens": 16846827.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.329308938980103,
|
|
"epoch": 0.7065321805955812,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004957950945545965,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.2063808485865593,
|
|
"num_tokens": 16858166.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.376455068588257,
|
|
"epoch": 0.7070124879923151,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004957884949518246,
|
|
"loss": 5.234,
|
|
"mean_token_accuracy": 0.19484158605337143,
|
|
"num_tokens": 16870201.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.372378778457642,
|
|
"epoch": 0.707492795389049,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004957818902229992,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.21045285314321518,
|
|
"num_tokens": 16880891.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.342394495010376,
|
|
"epoch": 0.7079731027857828,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004957752803682741,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.20331737101078035,
|
|
"num_tokens": 16893498.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.355802011489868,
|
|
"epoch": 0.7084534101825168,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004957686653878024,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.2090783879160881,
|
|
"num_tokens": 16904959.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.3680956840515135,
|
|
"epoch": 0.7089337175792507,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000495762045281738,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.20913613587617874,
|
|
"num_tokens": 16916547.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.297506475448609,
|
|
"epoch": 0.7094140249759846,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004957554200502344,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.21234960705041886,
|
|
"num_tokens": 16928580.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.319205904006958,
|
|
"epoch": 0.7098943323727186,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004957487896934454,
|
|
"loss": 5.1372,
|
|
"mean_token_accuracy": 0.20790536105632781,
|
|
"num_tokens": 16941247.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.383007049560547,
|
|
"epoch": 0.7103746397694525,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000495742154211525,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.2079955071210861,
|
|
"num_tokens": 16951119.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.295486354827881,
|
|
"epoch": 0.7108549471661864,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004957355136046272,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.21048038601875305,
|
|
"num_tokens": 16962608.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.264986562728882,
|
|
"epoch": 0.7113352545629202,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004957288678729064,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.21038804352283477,
|
|
"num_tokens": 16973291.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.36090874671936,
|
|
"epoch": 0.7118155619596542,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004957222170165166,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.20317897647619249,
|
|
"num_tokens": 16984895.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.349123573303222,
|
|
"epoch": 0.7122958693563881,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004957155610356124,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.20322143286466599,
|
|
"num_tokens": 16997109.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.303277158737183,
|
|
"epoch": 0.712776176753122,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004957088999303481,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.2074026107788086,
|
|
"num_tokens": 17008640.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.281453371047974,
|
|
"epoch": 0.7132564841498559,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004957022337008787,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.21270692795515062,
|
|
"num_tokens": 17018924.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.27117953300476,
|
|
"epoch": 0.7137367915465899,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004956955623473587,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.2093396544456482,
|
|
"num_tokens": 17029932.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.348640775680542,
|
|
"epoch": 0.7142170989433237,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000495688885869943,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.20419342815876007,
|
|
"num_tokens": 17042164.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.344086837768555,
|
|
"epoch": 0.7146974063400576,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004956822042687868,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.19928455352783203,
|
|
"num_tokens": 17054729.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.251951551437378,
|
|
"epoch": 0.7151777137367915,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956755175440451,
|
|
"loss": 5.0243,
|
|
"mean_token_accuracy": 0.2236065834760666,
|
|
"num_tokens": 17066537.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.29123477935791,
|
|
"epoch": 0.7156580211335255,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004956688256958731,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.21617083251476288,
|
|
"num_tokens": 17077787.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.267868709564209,
|
|
"epoch": 0.7161383285302594,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956621287244262,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.20687348544597625,
|
|
"num_tokens": 17089555.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.373935079574585,
|
|
"epoch": 0.7166186359269933,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004956554266298599,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.21658468544483184,
|
|
"num_tokens": 17099911.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.261654949188232,
|
|
"epoch": 0.7170989433237271,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004956487194123298,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.21106222569942473,
|
|
"num_tokens": 17110880.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.261746025085449,
|
|
"epoch": 0.7175792507204611,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004956420070719918,
|
|
"loss": 5.0196,
|
|
"mean_token_accuracy": 0.21547937095165254,
|
|
"num_tokens": 17122272.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.31106014251709,
|
|
"epoch": 0.718059558117195,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004956352896090014,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.20728080123662948,
|
|
"num_tokens": 17133995.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.331283950805664,
|
|
"epoch": 0.7185398655139289,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004956285670235147,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.21416814774274825,
|
|
"num_tokens": 17145970.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.3921637535095215,
|
|
"epoch": 0.7190201729106628,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004956218393156879,
|
|
"loss": 5.2366,
|
|
"mean_token_accuracy": 0.19899100363254546,
|
|
"num_tokens": 17157747.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.292384815216065,
|
|
"epoch": 0.7195004803073968,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004956151064856772,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.21398458033800125,
|
|
"num_tokens": 17168357.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.332787752151489,
|
|
"epoch": 0.7199807877041307,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004956083685336386,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.2166551887989044,
|
|
"num_tokens": 17179871.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.333356714248657,
|
|
"epoch": 0.7204610951008645,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004956016254597289,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.21713766753673552,
|
|
"num_tokens": 17190456.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.292677927017212,
|
|
"epoch": 0.7209414024975984,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004955948772641044,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.20351035445928572,
|
|
"num_tokens": 17201623.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.273524570465088,
|
|
"epoch": 0.7214217098943324,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000495588123946922,
|
|
"loss": 5.0593,
|
|
"mean_token_accuracy": 0.21409086734056473,
|
|
"num_tokens": 17212891.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.306383371353149,
|
|
"epoch": 0.7219020172910663,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004955813655083384,
|
|
"loss": 5.1116,
|
|
"mean_token_accuracy": 0.21043863296508789,
|
|
"num_tokens": 17223983.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.348400354385376,
|
|
"epoch": 0.7223823246878002,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004955746019485104,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.21320433765649796,
|
|
"num_tokens": 17233701.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.291280460357666,
|
|
"epoch": 0.722862632084534,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000495567833267595,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.2105158671736717,
|
|
"num_tokens": 17245958.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.397392225265503,
|
|
"epoch": 0.723342939481268,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004955610594657496,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.1996593102812767,
|
|
"num_tokens": 17257687.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.378547048568725,
|
|
"epoch": 0.7238232468780019,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004955542805431313,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.20859490633010863,
|
|
"num_tokens": 17270247.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.287229585647583,
|
|
"epoch": 0.7243035542747358,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004955474964998976,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.21423844248056412,
|
|
"num_tokens": 17281920.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.405027866363525,
|
|
"epoch": 0.7247838616714697,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004955407073362058,
|
|
"loss": 5.2695,
|
|
"mean_token_accuracy": 0.19586165845394135,
|
|
"num_tokens": 17293602.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.391187238693237,
|
|
"epoch": 0.7252641690682037,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004955339130522136,
|
|
"loss": 5.056,
|
|
"mean_token_accuracy": 0.2137158066034317,
|
|
"num_tokens": 17304484.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.19770622253418,
|
|
"epoch": 0.7257444764649376,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000495527113648079,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.21465377360582352,
|
|
"num_tokens": 17314953.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.306738376617432,
|
|
"epoch": 0.7262247838616714,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004955203091239596,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.2061687335371971,
|
|
"num_tokens": 17326813.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.413270282745361,
|
|
"epoch": 0.7267050912584054,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004955134994800134,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.2014137849211693,
|
|
"num_tokens": 17337968.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.325583982467651,
|
|
"epoch": 0.7271853986551393,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004955066847163984,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.21064977049827577,
|
|
"num_tokens": 17350406.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.234203243255616,
|
|
"epoch": 0.7276657060518732,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004954998648332731,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.21830987334251403,
|
|
"num_tokens": 17361888.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.269831943511963,
|
|
"epoch": 0.7281460134486071,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004954930398307956,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.2094791740179062,
|
|
"num_tokens": 17374047.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.331007862091065,
|
|
"epoch": 0.7286263208453411,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004954862097091245,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.20073632299900054,
|
|
"num_tokens": 17386175.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.310300588607788,
|
|
"epoch": 0.729106628242075,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004954793744684184,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.22059799134731292,
|
|
"num_tokens": 17398168.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.2579484462738035,
|
|
"epoch": 0.7295869356388088,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004954725341088358,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.21232549101114273,
|
|
"num_tokens": 17408825.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.305180788040161,
|
|
"epoch": 0.7300672430355427,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004954656886305356,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.2107972264289856,
|
|
"num_tokens": 17419813.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.37008376121521,
|
|
"epoch": 0.7305475504322767,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004954588380336768,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.20207465142011644,
|
|
"num_tokens": 17431134.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.261743974685669,
|
|
"epoch": 0.7310278578290106,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004954519823184184,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.21424833685159683,
|
|
"num_tokens": 17442614.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.327200174331665,
|
|
"epoch": 0.7315081652257445,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004954451214849196,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.21629141122102738,
|
|
"num_tokens": 17454615.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.336834573745728,
|
|
"epoch": 0.7319884726224783,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004954382555333397,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.20628802478313446,
|
|
"num_tokens": 17467025.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.264048147201538,
|
|
"epoch": 0.7324687800192123,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000495431384463838,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.21480168998241425,
|
|
"num_tokens": 17477681.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.285310077667236,
|
|
"epoch": 0.7329490874159462,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004954245082765741,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.21148568838834764,
|
|
"num_tokens": 17489814.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.346252346038819,
|
|
"epoch": 0.7334293948126801,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004954176269717077,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.2132637083530426,
|
|
"num_tokens": 17501701.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.3037293434143065,
|
|
"epoch": 0.733909702209414,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004954107405493984,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.214559967815876,
|
|
"num_tokens": 17513585.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.3021446704864506,
|
|
"epoch": 0.734390009606148,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004954038490098064,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.2128313183784485,
|
|
"num_tokens": 17525557.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.2387083053588865,
|
|
"epoch": 0.7348703170028819,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004953969523530914,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.20948038697242738,
|
|
"num_tokens": 17538312.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.418973731994629,
|
|
"epoch": 0.7353506243996157,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004953900505794136,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.20908292829990388,
|
|
"num_tokens": 17550248.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.292871332168579,
|
|
"epoch": 0.7358309317963496,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004953831436889332,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.20809418261051177,
|
|
"num_tokens": 17560624.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.309444332122803,
|
|
"epoch": 0.7363112391930836,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004953762316818106,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.20811459124088288,
|
|
"num_tokens": 17572439.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.343560075759887,
|
|
"epoch": 0.7367915465898175,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004953693145582064,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.20418035835027695,
|
|
"num_tokens": 17583120.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.212920808792115,
|
|
"epoch": 0.7372718539865514,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000495362392318281,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.2187417581677437,
|
|
"num_tokens": 17593677.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.2843059539794925,
|
|
"epoch": 0.7377521613832853,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004953554649621951,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.20589945167303086,
|
|
"num_tokens": 17605180.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.331402111053467,
|
|
"epoch": 0.7382324687800192,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004953485324901098,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.21452029049396515,
|
|
"num_tokens": 17617459.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.290313196182251,
|
|
"epoch": 0.7387127761767531,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004953415949021857,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.2178971976041794,
|
|
"num_tokens": 17628024.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.239890813827515,
|
|
"epoch": 0.739193083573487,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004953346521985843,
|
|
"loss": 5.088,
|
|
"mean_token_accuracy": 0.20925626009702683,
|
|
"num_tokens": 17639833.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.369693613052368,
|
|
"epoch": 0.7396733909702209,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004953277043794663,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.1988198459148407,
|
|
"num_tokens": 17651057.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.329780864715576,
|
|
"epoch": 0.7401536983669549,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953207514449933,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.21758732348680496,
|
|
"num_tokens": 17662288.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.29347710609436,
|
|
"epoch": 0.7406340057636888,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004953137933953267,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.21002478748559952,
|
|
"num_tokens": 17673885.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.31736159324646,
|
|
"epoch": 0.7411143131604226,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495306830230628,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.21368523836135864,
|
|
"num_tokens": 17685030.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.289226102828979,
|
|
"epoch": 0.7415946205571565,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004952998619510589,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.2157010018825531,
|
|
"num_tokens": 17696624.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.273167467117309,
|
|
"epoch": 0.7420749279538905,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004952928885567811,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.21482881605625154,
|
|
"num_tokens": 17707386.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.425893783569336,
|
|
"epoch": 0.7425552353506244,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004952859100479566,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.20461898297071457,
|
|
"num_tokens": 17718605.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.3197441577911375,
|
|
"epoch": 0.7430355427473583,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004952789264247474,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.2129740059375763,
|
|
"num_tokens": 17730275.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.359417963027954,
|
|
"epoch": 0.7435158501440923,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004952719376873156,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.20866380780935287,
|
|
"num_tokens": 17741390.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.301401042938233,
|
|
"epoch": 0.7439961575408262,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004952649438358234,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.21666279733181,
|
|
"num_tokens": 17752354.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.350618362426758,
|
|
"epoch": 0.74447646493756,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952579448704334,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.21065741777420044,
|
|
"num_tokens": 17762839.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.312939834594727,
|
|
"epoch": 0.7449567723342939,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000495250940791308,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.20553001314401625,
|
|
"num_tokens": 17775800.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.317015075683594,
|
|
"epoch": 0.7454370797310279,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004952439315986096,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.21331654787063598,
|
|
"num_tokens": 17787804.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.355747652053833,
|
|
"epoch": 0.7459173871277618,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004952369172925012,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.21383114010095597,
|
|
"num_tokens": 17800291.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.299292850494385,
|
|
"epoch": 0.7463976945244957,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004952298978731454,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.2166093558073044,
|
|
"num_tokens": 17811548.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.3169831275939945,
|
|
"epoch": 0.7468780019212296,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004952228733407055,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.22119933664798735,
|
|
"num_tokens": 17822589.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.22701244354248,
|
|
"epoch": 0.7473583093179635,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004952158436953444,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.21899669468402863,
|
|
"num_tokens": 17834203.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.295480871200562,
|
|
"epoch": 0.7478386167146974,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004952088089372252,
|
|
"loss": 5.1013,
|
|
"mean_token_accuracy": 0.20918091088533403,
|
|
"num_tokens": 17846238.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.289197826385498,
|
|
"epoch": 0.7483189241114313,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004952017690665114,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.21453914940357208,
|
|
"num_tokens": 17857640.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.2739338874816895,
|
|
"epoch": 0.7487992315081652,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004951947240833664,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.21228243559598922,
|
|
"num_tokens": 17868755.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.256406688690186,
|
|
"epoch": 0.7492795389048992,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004951876739879537,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.20885979682207106,
|
|
"num_tokens": 17881078.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.248721313476563,
|
|
"epoch": 0.7497598463016331,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004951806187804371,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.2142539069056511,
|
|
"num_tokens": 17893888.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.3160608291625975,
|
|
"epoch": 0.7502401536983669,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004951735584609804,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.20865219682455063,
|
|
"num_tokens": 17904443.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.25682487487793,
|
|
"epoch": 0.7507204610951008,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004951664930297474,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.21454736590385437,
|
|
"num_tokens": 17918090.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.233595657348633,
|
|
"epoch": 0.7512007684918348,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495159422486902,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.2176428869366646,
|
|
"num_tokens": 17929233.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.296094274520874,
|
|
"epoch": 0.7516810758885687,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004951523468326088,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.209262515604496,
|
|
"num_tokens": 17940580.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.33233232498169,
|
|
"epoch": 0.7521613832853026,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004951452660670317,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.20420581698417664,
|
|
"num_tokens": 17953993.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.270310974121093,
|
|
"epoch": 0.7526416906820365,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004951381801903352,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.21062700897455217,
|
|
"num_tokens": 17966033.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.194505786895752,
|
|
"epoch": 0.7531219980787704,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004951310892026839,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.222573122382164,
|
|
"num_tokens": 17977943.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.292294883728028,
|
|
"epoch": 0.7536023054755043,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004951239931042424,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.2184312343597412,
|
|
"num_tokens": 17990135.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.232913684844971,
|
|
"epoch": 0.7540826128722382,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004951168918951753,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.21639539897441865,
|
|
"num_tokens": 18002126.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.200091791152954,
|
|
"epoch": 0.7545629202689721,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004951097855756476,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.22055791765451432,
|
|
"num_tokens": 18013147.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.337146377563476,
|
|
"epoch": 0.7550432276657061,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004951026741458243,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.215498249232769,
|
|
"num_tokens": 18025146.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.257822465896607,
|
|
"epoch": 0.75552353506244,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004950955576058705,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.21024022549390792,
|
|
"num_tokens": 18036412.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.274294996261597,
|
|
"epoch": 0.7560038424591738,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004950884359559513,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.21416025012731552,
|
|
"num_tokens": 18048041.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.3436744689941404,
|
|
"epoch": 0.7564841498559077,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004950813091962324,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.2061038300395012,
|
|
"num_tokens": 18060163.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.331613254547119,
|
|
"epoch": 0.7569644572526417,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004950741773268788,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.20520974397659303,
|
|
"num_tokens": 18071628.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.216393280029297,
|
|
"epoch": 0.7574447646493756,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004950670403480562,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.21191180646419525,
|
|
"num_tokens": 18082979.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.271268558502197,
|
|
"epoch": 0.7579250720461095,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004950598982599306,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.21403386443853378,
|
|
"num_tokens": 18093889.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.256098937988281,
|
|
"epoch": 0.7584053794428435,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004950527510626675,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.2129449024796486,
|
|
"num_tokens": 18105559.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.318772459030152,
|
|
"epoch": 0.7588856868395774,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004950455987564329,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.20708672255277633,
|
|
"num_tokens": 18116316.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.3347306728363035,
|
|
"epoch": 0.7593659942363112,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004950384413413931,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.21373462826013565,
|
|
"num_tokens": 18126851.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.3427056789398195,
|
|
"epoch": 0.7598463016330451,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004950312788177139,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.20313034504652022,
|
|
"num_tokens": 18139571.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.376320457458496,
|
|
"epoch": 0.7603266090297791,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004950241111855618,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.20792322903871535,
|
|
"num_tokens": 18150680.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.326610422134399,
|
|
"epoch": 0.760806916426513,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004950169384451031,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.21604117900133132,
|
|
"num_tokens": 18161911.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.296671390533447,
|
|
"epoch": 0.7612872238232469,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004950097605965045,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.2198405459523201,
|
|
"num_tokens": 18172714.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.313606548309326,
|
|
"epoch": 0.7617675312199808,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004950025776399326,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.21653930395841597,
|
|
"num_tokens": 18184250.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.385619831085205,
|
|
"epoch": 0.7622478386167147,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000494995389575554,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.2073808193206787,
|
|
"num_tokens": 18195299.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.40221004486084,
|
|
"epoch": 0.7627281460134486,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004949881964035357,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.20646310448646546,
|
|
"num_tokens": 18206863.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.363748502731323,
|
|
"epoch": 0.7632084534101825,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004949809981240448,
|
|
"loss": 5.1684,
|
|
"mean_token_accuracy": 0.20585118383169174,
|
|
"num_tokens": 18219643.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.275132751464843,
|
|
"epoch": 0.7636887608069164,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004949737947372483,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.21818018108606338,
|
|
"num_tokens": 18230461.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.316145420074463,
|
|
"epoch": 0.7641690682036504,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004949665862433134,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.20263040512800218,
|
|
"num_tokens": 18243768.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.322182703018188,
|
|
"epoch": 0.7646493756003843,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004949593726424077,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.2150597706437111,
|
|
"num_tokens": 18255322.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.315861701965332,
|
|
"epoch": 0.7651296829971181,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004949521539346985,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.21947134137153626,
|
|
"num_tokens": 18267262.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.276798105239868,
|
|
"epoch": 0.765609990393852,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004949449301203533,
|
|
"loss": 5.0097,
|
|
"mean_token_accuracy": 0.21508977562189102,
|
|
"num_tokens": 18277332.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.286798334121704,
|
|
"epoch": 0.766090297790586,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004949377011995399,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.2131699487566948,
|
|
"num_tokens": 18289547.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.307200813293457,
|
|
"epoch": 0.7665706051873199,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004949304671724263,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.21467551290988923,
|
|
"num_tokens": 18302097.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.323423957824707,
|
|
"epoch": 0.7670509125840538,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004949232280391802,
|
|
"loss": 5.1158,
|
|
"mean_token_accuracy": 0.21219189018011092,
|
|
"num_tokens": 18314151.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.2811822414398195,
|
|
"epoch": 0.7675312199807877,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004949159837999698,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.20877229869365693,
|
|
"num_tokens": 18326085.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.306690454483032,
|
|
"epoch": 0.7680115273775217,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004949087344549633,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.2084398701786995,
|
|
"num_tokens": 18338158.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.289818334579468,
|
|
"epoch": 0.7684918347742555,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000494901480004329,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.21258990615606307,
|
|
"num_tokens": 18349418.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.309824275970459,
|
|
"epoch": 0.7689721421709894,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004948942204482351,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.21151256561279297,
|
|
"num_tokens": 18361964.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.252948999404907,
|
|
"epoch": 0.7694524495677233,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004948869557868506,
|
|
"loss": 4.9762,
|
|
"mean_token_accuracy": 0.22491969764232636,
|
|
"num_tokens": 18373108.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.176406383514404,
|
|
"epoch": 0.7699327569644573,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004948796860203439,
|
|
"loss": 4.9821,
|
|
"mean_token_accuracy": 0.21920865774154663,
|
|
"num_tokens": 18385310.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.328154754638672,
|
|
"epoch": 0.7704130643611912,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004948724111488838,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.20643505156040193,
|
|
"num_tokens": 18396132.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.468338966369629,
|
|
"epoch": 0.770893371757925,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004948651311726391,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.20121830999851226,
|
|
"num_tokens": 18409930.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.381359672546386,
|
|
"epoch": 0.7713736791546589,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004948578460917789,
|
|
"loss": 5.158,
|
|
"mean_token_accuracy": 0.20594588071107864,
|
|
"num_tokens": 18421204.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.324843168258667,
|
|
"epoch": 0.7718539865513929,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004948505559064725,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.21968425065279007,
|
|
"num_tokens": 18433194.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.23973913192749,
|
|
"epoch": 0.7723342939481268,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004948432606168889,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.21483880132436753,
|
|
"num_tokens": 18445282.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.287118530273437,
|
|
"epoch": 0.7728146013448607,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004948359602231976,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.2178490787744522,
|
|
"num_tokens": 18456264.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.248097944259643,
|
|
"epoch": 0.7732949087415946,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004948286547255681,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.21612643152475358,
|
|
"num_tokens": 18467573.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.284157228469849,
|
|
"epoch": 0.7737752161383286,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049482134412417,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.22036667317152023,
|
|
"num_tokens": 18478333.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.258845043182373,
|
|
"epoch": 0.7742555235350624,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000494814028419173,
|
|
"loss": 4.9873,
|
|
"mean_token_accuracy": 0.2183872029185295,
|
|
"num_tokens": 18489106.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.31499285697937,
|
|
"epoch": 0.7747358309317963,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000494806707610747,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.21177464425563813,
|
|
"num_tokens": 18500090.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.348161792755127,
|
|
"epoch": 0.7752161383285303,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000494799381699062,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.21690022945404053,
|
|
"num_tokens": 18510305.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.342441606521606,
|
|
"epoch": 0.7756964457252642,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004947920506842879,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.2126712679862976,
|
|
"num_tokens": 18523048.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.220316600799561,
|
|
"epoch": 0.7761767531219981,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004947847145665951,
|
|
"loss": 5.0074,
|
|
"mean_token_accuracy": 0.22062323242425919,
|
|
"num_tokens": 18534145.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.297750473022461,
|
|
"epoch": 0.776657060518732,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004947773733461539,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.21516508013010024,
|
|
"num_tokens": 18545045.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.289766788482666,
|
|
"epoch": 0.777137367915466,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004947700270231347,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.21543944478034974,
|
|
"num_tokens": 18557531.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.29792013168335,
|
|
"epoch": 0.7776176753121998,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004947626755977079,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.211107274889946,
|
|
"num_tokens": 18569127.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.334991550445556,
|
|
"epoch": 0.7780979827089337,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004947553190700444,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.2164621651172638,
|
|
"num_tokens": 18580606.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.38695068359375,
|
|
"epoch": 0.7785782901056676,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000494747957440315,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.20214432328939438,
|
|
"num_tokens": 18592330.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.366260242462158,
|
|
"epoch": 0.7790585975024016,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004947405907086905,
|
|
"loss": 5.1969,
|
|
"mean_token_accuracy": 0.21018484532833098,
|
|
"num_tokens": 18604721.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.311359643936157,
|
|
"epoch": 0.7795389048991355,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004947332188753419,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.21536423712968827,
|
|
"num_tokens": 18616814.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.3130049228668215,
|
|
"epoch": 0.7800192122958693,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004947258419404405,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.21512551456689835,
|
|
"num_tokens": 18628224.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.322597169876099,
|
|
"epoch": 0.7804995196926032,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004947184599041576,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.2130896508693695,
|
|
"num_tokens": 18639777.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.247894668579102,
|
|
"epoch": 0.7809798270893372,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004947110727666644,
|
|
"loss": 5.0393,
|
|
"mean_token_accuracy": 0.21201369166374207,
|
|
"num_tokens": 18651044.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.340291166305542,
|
|
"epoch": 0.7814601344860711,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004947036805281325,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.21264140903949738,
|
|
"num_tokens": 18663142.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.407776498794556,
|
|
"epoch": 0.781940441882805,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004946962831887336,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.21024056524038315,
|
|
"num_tokens": 18674079.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.303403282165528,
|
|
"epoch": 0.7824207492795389,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004946888807486393,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.205235031247139,
|
|
"num_tokens": 18685744.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.248520612716675,
|
|
"epoch": 0.7829010566762729,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946814732080214,
|
|
"loss": 5.0343,
|
|
"mean_token_accuracy": 0.21602775305509567,
|
|
"num_tokens": 18697049.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.258074617385864,
|
|
"epoch": 0.7833813640730067,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004946740605670523,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.2155240595340729,
|
|
"num_tokens": 18708765.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.2804708003997805,
|
|
"epoch": 0.7838616714697406,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004946666428259037,
|
|
"loss": 5.0309,
|
|
"mean_token_accuracy": 0.2173507660627365,
|
|
"num_tokens": 18719819.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.360841226577759,
|
|
"epoch": 0.7843419788664745,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004946592199847478,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.20799025595188142,
|
|
"num_tokens": 18730668.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.232181358337402,
|
|
"epoch": 0.7848222862632085,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004946517920437571,
|
|
"loss": 4.9112,
|
|
"mean_token_accuracy": 0.21585632264614105,
|
|
"num_tokens": 18741991.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.265512418746948,
|
|
"epoch": 0.7853025936599424,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004946443590031041,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.21428398042917252,
|
|
"num_tokens": 18753919.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.343008947372437,
|
|
"epoch": 0.7857829010566763,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004946369208629613,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.21879064440727233,
|
|
"num_tokens": 18764342.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.224815607070923,
|
|
"epoch": 0.7862632084534101,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004946294776235013,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.21366302222013472,
|
|
"num_tokens": 18776044.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.361653757095337,
|
|
"epoch": 0.7867435158501441,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004946220292848971,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.21397276669740678,
|
|
"num_tokens": 18787354.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.29656491279602,
|
|
"epoch": 0.787223823246878,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004946145758473214,
|
|
"loss": 5.021,
|
|
"mean_token_accuracy": 0.2148450046777725,
|
|
"num_tokens": 18797845.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.332850360870362,
|
|
"epoch": 0.7877041306436119,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004946071173109475,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.21267470121383666,
|
|
"num_tokens": 18809253.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.281962251663208,
|
|
"epoch": 0.7881844380403458,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945996536759484,
|
|
"loss": 4.9557,
|
|
"mean_token_accuracy": 0.2228683426976204,
|
|
"num_tokens": 18819768.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.376068496704102,
|
|
"epoch": 0.7886647454370798,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004945921849424974,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.20812487453222275,
|
|
"num_tokens": 18831151.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.298772668838501,
|
|
"epoch": 0.7891450528338136,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004945847111107679,
|
|
"loss": 4.9938,
|
|
"mean_token_accuracy": 0.2198323428630829,
|
|
"num_tokens": 18842133.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.333953189849853,
|
|
"epoch": 0.7896253602305475,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945772321809334,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.20703756660223008,
|
|
"num_tokens": 18853295.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.309771633148193,
|
|
"epoch": 0.7901056676272814,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004945697481531677,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.21196287423372268,
|
|
"num_tokens": 18865802.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.278874111175537,
|
|
"epoch": 0.7905859750240154,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004945622590276443,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.2236466497182846,
|
|
"num_tokens": 18877693.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.312116718292236,
|
|
"epoch": 0.7910662824207493,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004945547648045373,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.2173798993229866,
|
|
"num_tokens": 18888549.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.265875720977784,
|
|
"epoch": 0.7915465898174832,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004945472654840206,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.2210939735174179,
|
|
"num_tokens": 18899132.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.192903280258179,
|
|
"epoch": 0.7920268972142172,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004945397610662683,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.20927611887454986,
|
|
"num_tokens": 18911774.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.341684484481812,
|
|
"epoch": 0.792507204610951,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004945322515514547,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.21303036212921142,
|
|
"num_tokens": 18922806.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.304209280014038,
|
|
"epoch": 0.7929875120076849,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000494524736939754,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.2213797003030777,
|
|
"num_tokens": 18934861.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.3362915992736815,
|
|
"epoch": 0.7934678194044188,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004945172172313408,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.21906474530696868,
|
|
"num_tokens": 18944269.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.304548740386963,
|
|
"epoch": 0.7939481268011528,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004945096924263896,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.2116611495614052,
|
|
"num_tokens": 18957197.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.318814945220947,
|
|
"epoch": 0.7944284341978867,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004945021625250753,
|
|
"loss": 5.0964,
|
|
"mean_token_accuracy": 0.20900236517190934,
|
|
"num_tokens": 18968254.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.243633127212524,
|
|
"epoch": 0.7949087415946205,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004944946275275724,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.22381478399038315,
|
|
"num_tokens": 18979372.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.267259693145752,
|
|
"epoch": 0.7953890489913544,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004944870874340561,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.21762784272432328,
|
|
"num_tokens": 18991075.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.216023206710815,
|
|
"epoch": 0.7958693563880884,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004944795422447013,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.21929397135972978,
|
|
"num_tokens": 19002324.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.336474275588989,
|
|
"epoch": 0.7963496637848223,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004944719919596835,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.21083132326602935,
|
|
"num_tokens": 19014406.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.261001443862915,
|
|
"epoch": 0.7968299711815562,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004944644365791776,
|
|
"loss": 4.9947,
|
|
"mean_token_accuracy": 0.22041784971952438,
|
|
"num_tokens": 19025984.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.304883861541748,
|
|
"epoch": 0.7973102785782901,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000494456876103359,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.2139579251408577,
|
|
"num_tokens": 19036189.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.298628091812134,
|
|
"epoch": 0.7977905859750241,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004944493105324035,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.21011899709701537,
|
|
"num_tokens": 19047587.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.321364879608154,
|
|
"epoch": 0.7982708933717579,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004944417398664866,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.21218617111444474,
|
|
"num_tokens": 19058467.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.311764240264893,
|
|
"epoch": 0.7987512007684918,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004944341641057843,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.21255367547273635,
|
|
"num_tokens": 19070235.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.350745058059692,
|
|
"epoch": 0.7992315081652257,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004944265832504721,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.2127568766474724,
|
|
"num_tokens": 19082005.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.33294358253479,
|
|
"epoch": 0.7997118155619597,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004944189973007262,
|
|
"loss": 5.1159,
|
|
"mean_token_accuracy": 0.21368397921323776,
|
|
"num_tokens": 19092922.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.3136883735656735,
|
|
"epoch": 0.8001921229586936,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004944114062567229,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.20616220384836198,
|
|
"num_tokens": 19104832.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.316489171981812,
|
|
"epoch": 0.8006724303554275,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004944038101186381,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.21133978068828582,
|
|
"num_tokens": 19116261.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.345134830474853,
|
|
"epoch": 0.8011527377521613,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004943962088866483,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.2103720039129257,
|
|
"num_tokens": 19127195.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.354102516174317,
|
|
"epoch": 0.8016330451488953,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004943886025609301,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.20509569197893143,
|
|
"num_tokens": 19138164.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.332017135620117,
|
|
"epoch": 0.8021133525456292,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049438099114166,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.20557694584131242,
|
|
"num_tokens": 19149153.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.336039447784424,
|
|
"epoch": 0.8025936599423631,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004943733746290147,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.20478908866643905,
|
|
"num_tokens": 19161023.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.268671226501465,
|
|
"epoch": 0.803073967339097,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000494365753023171,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.22398886680603028,
|
|
"num_tokens": 19172466.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.311010837554932,
|
|
"epoch": 0.803554274735831,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004943581263243059,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.21735257506370545,
|
|
"num_tokens": 19183684.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.220240926742553,
|
|
"epoch": 0.8040345821325648,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004943504945325965,
|
|
"loss": 4.9761,
|
|
"mean_token_accuracy": 0.22056413292884827,
|
|
"num_tokens": 19194479.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.32010817527771,
|
|
"epoch": 0.8045148895292987,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004943428576482198,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.20862782299518584,
|
|
"num_tokens": 19206323.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.388244867324829,
|
|
"epoch": 0.8049951969260326,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004943352156713535,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.20637688040733337,
|
|
"num_tokens": 19218849.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.249980735778808,
|
|
"epoch": 0.8054755043227666,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004943275686021747,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.21490692347288132,
|
|
"num_tokens": 19229603.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.330032634735107,
|
|
"epoch": 0.8059558117195005,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000494319916440861,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.2045476630330086,
|
|
"num_tokens": 19241318.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.319420433044433,
|
|
"epoch": 0.8064361191162344,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004943122591875901,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.2140294134616852,
|
|
"num_tokens": 19252640.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.231271123886108,
|
|
"epoch": 0.8069164265129684,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004943045968425398,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.21692116260528566,
|
|
"num_tokens": 19262971.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.307226085662842,
|
|
"epoch": 0.8073967339097022,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004942969294058878,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.21388705521821977,
|
|
"num_tokens": 19274426.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.297821855545044,
|
|
"epoch": 0.8078770413064361,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004942892568778125,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.216566564142704,
|
|
"num_tokens": 19286806.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.2695924758911135,
|
|
"epoch": 0.80835734870317,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004942815792584917,
|
|
"loss": 5.052,
|
|
"mean_token_accuracy": 0.21475101560354232,
|
|
"num_tokens": 19297997.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.280530595779419,
|
|
"epoch": 0.808837656099904,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004942738965481038,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.21553569585084914,
|
|
"num_tokens": 19309789.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.273676586151123,
|
|
"epoch": 0.8093179634966379,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004942662087468272,
|
|
"loss": 5.0488,
|
|
"mean_token_accuracy": 0.21843004673719407,
|
|
"num_tokens": 19320688.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.272088527679443,
|
|
"epoch": 0.8097982708933718,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004942585158548402,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.21727826297283173,
|
|
"num_tokens": 19331670.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.3112115383148195,
|
|
"epoch": 0.8102785782901056,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004942508178723214,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.21233619451522828,
|
|
"num_tokens": 19343578.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.327071809768677,
|
|
"epoch": 0.8107588856868396,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942431147994499,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.20958428382873534,
|
|
"num_tokens": 19354875.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.278344964981079,
|
|
"epoch": 0.8112391930835735,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004942354066364042,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.21839356869459153,
|
|
"num_tokens": 19366353.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.199359893798828,
|
|
"epoch": 0.8117195004803074,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004942276933833634,
|
|
"loss": 4.9548,
|
|
"mean_token_accuracy": 0.22472579181194305,
|
|
"num_tokens": 19377534.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.278019905090332,
|
|
"epoch": 0.8121998078770413,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004942199750405064,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.20319292545318604,
|
|
"num_tokens": 19388188.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.194910717010498,
|
|
"epoch": 0.8126801152737753,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004942122516080127,
|
|
"loss": 4.9371,
|
|
"mean_token_accuracy": 0.22797464877367019,
|
|
"num_tokens": 19399910.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.314953899383545,
|
|
"epoch": 0.8131604226705091,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004942045230860614,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.2186409667134285,
|
|
"num_tokens": 19411715.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.35609073638916,
|
|
"epoch": 0.813640730067243,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004941967894748319,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.20044416934251785,
|
|
"num_tokens": 19423275.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.326424169540405,
|
|
"epoch": 0.8141210374639769,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004941890507745039,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.21137083023786546,
|
|
"num_tokens": 19436035.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.260590887069702,
|
|
"epoch": 0.8146013448607109,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004941813069852569,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.20944691002368926,
|
|
"num_tokens": 19447755.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.320154428482056,
|
|
"epoch": 0.8150816522574448,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004941735581072708,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.21846593767404557,
|
|
"num_tokens": 19459044.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.282533979415893,
|
|
"epoch": 0.8155619596541787,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004941658041407255,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.21304513663053512,
|
|
"num_tokens": 19471486.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.1884088039398195,
|
|
"epoch": 0.8160422670509125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000494158045085801,
|
|
"loss": 4.9506,
|
|
"mean_token_accuracy": 0.22496270686388015,
|
|
"num_tokens": 19482428.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.263566970825195,
|
|
"epoch": 0.8165225744476465,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004941502809426776,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.21201093643903732,
|
|
"num_tokens": 19494616.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.311705684661865,
|
|
"epoch": 0.8170028818443804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004941425117115354,
|
|
"loss": 5.0121,
|
|
"mean_token_accuracy": 0.2129536598920822,
|
|
"num_tokens": 19504953.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.31019082069397,
|
|
"epoch": 0.8174831892411143,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004941347373925547,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.21713680177927017,
|
|
"num_tokens": 19517408.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.219766092300415,
|
|
"epoch": 0.8179634966378482,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004941269579859161,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.22046579122543336,
|
|
"num_tokens": 19529190.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.269935750961304,
|
|
"epoch": 0.8184438040345822,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004941191734918002,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.20842382907867432,
|
|
"num_tokens": 19540278.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.2772321701049805,
|
|
"epoch": 0.818924111431316,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000494111383910388,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.21376252621412278,
|
|
"num_tokens": 19551224.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.384726285934448,
|
|
"epoch": 0.8194044188280499,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004941035892418597,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.2107518121600151,
|
|
"num_tokens": 19564386.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.337044095993042,
|
|
"epoch": 0.8198847262247838,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004940957894863968,
|
|
"loss": 5.0488,
|
|
"mean_token_accuracy": 0.21811206936836242,
|
|
"num_tokens": 19576170.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.269604015350342,
|
|
"epoch": 0.8203650336215178,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004940879846441804,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.2122248664498329,
|
|
"num_tokens": 19587220.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.269298839569092,
|
|
"epoch": 0.8208453410182517,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004940801747153914,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.2137961208820343,
|
|
"num_tokens": 19598649.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.3189338684082035,
|
|
"epoch": 0.8213256484149856,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004940723597002113,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.21246107369661332,
|
|
"num_tokens": 19610243.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.2762247085571286,
|
|
"epoch": 0.8218059558117194,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004940645395988216,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.20773303806781768,
|
|
"num_tokens": 19621467.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.373956537246704,
|
|
"epoch": 0.8222862632084534,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004940567144114036,
|
|
"loss": 5.1736,
|
|
"mean_token_accuracy": 0.20707048177719117,
|
|
"num_tokens": 19633367.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.264904308319092,
|
|
"epoch": 0.8227665706051873,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004940488841381393,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.21329474300146103,
|
|
"num_tokens": 19643144.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.2883038997650145,
|
|
"epoch": 0.8232468780019212,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004940410487792103,
|
|
"loss": 5.1158,
|
|
"mean_token_accuracy": 0.21210776567459105,
|
|
"num_tokens": 19654501.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.3344793796539305,
|
|
"epoch": 0.8237271853986552,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004940332083347986,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.21060514599084854,
|
|
"num_tokens": 19665382.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.28497314453125,
|
|
"epoch": 0.8242074927953891,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004940253628050861,
|
|
"loss": 4.9169,
|
|
"mean_token_accuracy": 0.2215944454073906,
|
|
"num_tokens": 19677222.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.228455591201782,
|
|
"epoch": 0.824687800192123,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004940175121902552,
|
|
"loss": 5.0155,
|
|
"mean_token_accuracy": 0.2186749666929245,
|
|
"num_tokens": 19688550.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.3542252540588375,
|
|
"epoch": 0.8251681075888568,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000494009656490488,
|
|
"loss": 5.1282,
|
|
"mean_token_accuracy": 0.20551174283027648,
|
|
"num_tokens": 19700125.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.346072673797607,
|
|
"epoch": 0.8256484149855908,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004940017957059668,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.21430510133504868,
|
|
"num_tokens": 19711969.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.289309549331665,
|
|
"epoch": 0.8261287223823247,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004939939298368742,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.21634469777345658,
|
|
"num_tokens": 19723813.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.3289323329925535,
|
|
"epoch": 0.8266090297790586,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004939860588833929,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.20782829970121383,
|
|
"num_tokens": 19735539.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.4116464138031,
|
|
"epoch": 0.8270893371757925,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004939781828457055,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.20933855473995208,
|
|
"num_tokens": 19747106.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.297164821624756,
|
|
"epoch": 0.8275696445725265,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000493970301723995,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.22183773517608643,
|
|
"num_tokens": 19760156.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.2421060562133786,
|
|
"epoch": 0.8280499519692603,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004939624155184443,
|
|
"loss": 4.9628,
|
|
"mean_token_accuracy": 0.21803604662418366,
|
|
"num_tokens": 19771256.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.2874242782592775,
|
|
"epoch": 0.8285302593659942,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004939545242292365,
|
|
"loss": 4.9806,
|
|
"mean_token_accuracy": 0.2207653284072876,
|
|
"num_tokens": 19781332.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.342556381225586,
|
|
"epoch": 0.8290105667627281,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004939466278565547,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.20954972207546235,
|
|
"num_tokens": 19793573.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.270900583267212,
|
|
"epoch": 0.8294908741594621,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004939387264005825,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.21954465955495833,
|
|
"num_tokens": 19803421.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.230138206481934,
|
|
"epoch": 0.829971181556196,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004939308198615031,
|
|
"loss": 4.9319,
|
|
"mean_token_accuracy": 0.22324181348085403,
|
|
"num_tokens": 19814440.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.267609262466431,
|
|
"epoch": 0.8304514889529299,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004939229082395001,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.212125663459301,
|
|
"num_tokens": 19825721.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.2827794551849365,
|
|
"epoch": 0.8309317963496637,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004939149915347573,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.22333361208438873,
|
|
"num_tokens": 19837273.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.296159315109253,
|
|
"epoch": 0.8314121037463977,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004939070697474585,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.21818834990262986,
|
|
"num_tokens": 19849436.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.228702163696289,
|
|
"epoch": 0.8318924111431316,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004938991428777875,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.22886181771755218,
|
|
"num_tokens": 19860222.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.275073003768921,
|
|
"epoch": 0.8323727185398655,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004938912109259284,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.22205011248588563,
|
|
"num_tokens": 19870934.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.318188142776489,
|
|
"epoch": 0.8328530259365994,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004938832738920654,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.2088473320007324,
|
|
"num_tokens": 19882149.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.3246297359466555,
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004938753317763826,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.21744603663682938,
|
|
"num_tokens": 19893276.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.317847013473511,
|
|
"epoch": 0.8338136407300673,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004938673845790646,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.20508771240711213,
|
|
"num_tokens": 19904723.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.305253314971924,
|
|
"epoch": 0.8342939481268011,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004938594323002957,
|
|
"loss": 5.0738,
|
|
"mean_token_accuracy": 0.21140864938497544,
|
|
"num_tokens": 19915226.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.2678173065185545,
|
|
"epoch": 0.834774255523535,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004938514749402609,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.21481076925992965,
|
|
"num_tokens": 19927911.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.294334888458252,
|
|
"epoch": 0.835254562920269,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004938435124991447,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.21382291465997696,
|
|
"num_tokens": 19940356.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.338834476470947,
|
|
"epoch": 0.8357348703170029,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004938355449771318,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.209849514067173,
|
|
"num_tokens": 19951108.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.2430558681488035,
|
|
"epoch": 0.8362151777137368,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004938275723744075,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.22043029069900513,
|
|
"num_tokens": 19962427.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.359533452987671,
|
|
"epoch": 0.8366954851104706,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004938195946911567,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.20995877534151078,
|
|
"num_tokens": 19973476.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.330000019073486,
|
|
"epoch": 0.8371757925072046,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004938116119275645,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.21438438147306443,
|
|
"num_tokens": 19984034.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.327744674682617,
|
|
"epoch": 0.8376560999039385,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004938036240838166,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.21417146921157837,
|
|
"num_tokens": 19996035.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.346033334732056,
|
|
"epoch": 0.8381364073006724,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004937956311600983,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.2186152383685112,
|
|
"num_tokens": 20007259.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.299717998504638,
|
|
"epoch": 0.8386167146974063,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004937876331565951,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.21087097525596618,
|
|
"num_tokens": 20018673.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.246153783798218,
|
|
"epoch": 0.8390970220941403,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004937796300734926,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.21319071799516678,
|
|
"num_tokens": 20030767.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.349096250534058,
|
|
"epoch": 0.8395773294908742,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004937716219109769,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.2091129019856453,
|
|
"num_tokens": 20041268.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.251312494277954,
|
|
"epoch": 0.840057636887608,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004937636086692336,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.2209983617067337,
|
|
"num_tokens": 20052285.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.310549259185791,
|
|
"epoch": 0.840537944284342,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000493755590348449,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.21089137941598893,
|
|
"num_tokens": 20065113.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.42260856628418,
|
|
"epoch": 0.8410182516810759,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004937475669488091,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.21910454481840133,
|
|
"num_tokens": 20076151.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.260375308990478,
|
|
"epoch": 0.8414985590778098,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004937395384705004,
|
|
"loss": 5.0748,
|
|
"mean_token_accuracy": 0.21145062148571014,
|
|
"num_tokens": 20088195.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.233353757858277,
|
|
"epoch": 0.8419788664745437,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004937315049137089,
|
|
"loss": 4.9429,
|
|
"mean_token_accuracy": 0.22518647760152816,
|
|
"num_tokens": 20098576.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.389544868469239,
|
|
"epoch": 0.8424591738712777,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004937234662786216,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.20495210886001586,
|
|
"num_tokens": 20110176.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.330946350097657,
|
|
"epoch": 0.8429394812680115,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004937154225654246,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.21761274039745332,
|
|
"num_tokens": 20121713.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.38185715675354,
|
|
"epoch": 0.8434197886647454,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004937073737743051,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.2096487194299698,
|
|
"num_tokens": 20134126.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.2658624172210695,
|
|
"epoch": 0.8439000960614793,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004936993199054499,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.21947723925113677,
|
|
"num_tokens": 20144791.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.370013427734375,
|
|
"epoch": 0.8443804034582133,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004936912609590458,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.21194605380296708,
|
|
"num_tokens": 20157214.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.4294819831848145,
|
|
"epoch": 0.8448607108549472,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00049368319693528,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.20246653705835344,
|
|
"num_tokens": 20168952.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.3150876522064205,
|
|
"epoch": 0.8453410182516811,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004936751278343397,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.2139264240860939,
|
|
"num_tokens": 20181829.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.376411628723145,
|
|
"epoch": 0.845821325648415,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004936670536564123,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.19499314427375794,
|
|
"num_tokens": 20193362.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.334952402114868,
|
|
"epoch": 0.8463016330451489,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004936589744016853,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.21454751193523408,
|
|
"num_tokens": 20205159.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.299839925765991,
|
|
"epoch": 0.8467819404418828,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000493650890070346,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.2200593590736389,
|
|
"num_tokens": 20217075.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.293173170089721,
|
|
"epoch": 0.8472622478386167,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004936428006625824,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.21470960974693298,
|
|
"num_tokens": 20227901.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.319810628890991,
|
|
"epoch": 0.8477425552353506,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004936347061785823,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.2155350401997566,
|
|
"num_tokens": 20239945.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.354758548736572,
|
|
"epoch": 0.8482228626320846,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004936266066185334,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.2104931354522705,
|
|
"num_tokens": 20251503.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.282928800582885,
|
|
"epoch": 0.8487031700288185,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004936185019826239,
|
|
"loss": 5.0391,
|
|
"mean_token_accuracy": 0.21541307866573334,
|
|
"num_tokens": 20263044.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.328686380386353,
|
|
"epoch": 0.8491834774255523,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004936103922710419,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.21722408384084702,
|
|
"num_tokens": 20273563.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.276285982131958,
|
|
"epoch": 0.8496637848222862,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004936022774839759,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.21417783200740814,
|
|
"num_tokens": 20285482.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.399579095840454,
|
|
"epoch": 0.8501440922190202,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004935941576216141,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.20590045154094697,
|
|
"num_tokens": 20296666.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.235482835769654,
|
|
"epoch": 0.8506243996157541,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000493586032684145,
|
|
"loss": 4.9434,
|
|
"mean_token_accuracy": 0.22310832291841506,
|
|
"num_tokens": 20308978.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.259793424606324,
|
|
"epoch": 0.851104707012488,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004935779026717573,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.2138133704662323,
|
|
"num_tokens": 20321488.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.216874647140503,
|
|
"epoch": 0.8515850144092219,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004935697675846396,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.2299219101667404,
|
|
"num_tokens": 20332938.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.230583333969117,
|
|
"epoch": 0.8520653218059558,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004935616274229811,
|
|
"loss": 4.9818,
|
|
"mean_token_accuracy": 0.22525002360343932,
|
|
"num_tokens": 20342986.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.284406518936157,
|
|
"epoch": 0.8525456292026897,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004935534821869705,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.2141647070646286,
|
|
"num_tokens": 20355791.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.203439950942993,
|
|
"epoch": 0.8530259365994236,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004935453318767971,
|
|
"loss": 4.9133,
|
|
"mean_token_accuracy": 0.2205710992217064,
|
|
"num_tokens": 20367080.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.325229930877685,
|
|
"epoch": 0.8535062439961575,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049353717649265,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.2246568202972412,
|
|
"num_tokens": 20376697.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.326195812225341,
|
|
"epoch": 0.8539865513928915,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004935290160347185,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.2180757850408554,
|
|
"num_tokens": 20387430.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.257937669754028,
|
|
"epoch": 0.8544668587896254,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004935208505031922,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.21423773616552352,
|
|
"num_tokens": 20398488.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.200484323501587,
|
|
"epoch": 0.8549471661863592,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004935126798982606,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.21688165962696077,
|
|
"num_tokens": 20410316.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.285229969024658,
|
|
"epoch": 0.8554274735830932,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004935045042201135,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.22495245039463044,
|
|
"num_tokens": 20421645.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.360074520111084,
|
|
"epoch": 0.8559077809798271,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004934963234689407,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.2081121250987053,
|
|
"num_tokens": 20433397.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.260632276535034,
|
|
"epoch": 0.856388088376561,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000493488137644932,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.2203802779316902,
|
|
"num_tokens": 20446218.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.333844804763794,
|
|
"epoch": 0.8568683957732949,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004934799467482774,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.21161514967679979,
|
|
"num_tokens": 20457265.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.287130737304688,
|
|
"epoch": 0.8573487031700289,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004934717507791673,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.21309166997671128,
|
|
"num_tokens": 20468748.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.329586601257324,
|
|
"epoch": 0.8578290105667628,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004934635497377919,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.2072741463780403,
|
|
"num_tokens": 20481416.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.24630913734436,
|
|
"epoch": 0.8583093179634966,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004934553436243415,
|
|
"loss": 5.0019,
|
|
"mean_token_accuracy": 0.21930938810110093,
|
|
"num_tokens": 20493063.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.213432550430298,
|
|
"epoch": 0.8587896253602305,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004934471324390067,
|
|
"loss": 4.9873,
|
|
"mean_token_accuracy": 0.21791360080242156,
|
|
"num_tokens": 20504000.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.317112588882447,
|
|
"epoch": 0.8592699327569645,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004934389161819783,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.2180857315659523,
|
|
"num_tokens": 20516419.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.269755411148071,
|
|
"epoch": 0.8597502401536984,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004934306948534467,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.2144977107644081,
|
|
"num_tokens": 20527385.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.268268680572509,
|
|
"epoch": 0.8602305475504323,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004934224684536031,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.21895914226770402,
|
|
"num_tokens": 20538051.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.307522583007812,
|
|
"epoch": 0.8607108549471661,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004934142369826382,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.21212247163057327,
|
|
"num_tokens": 20550321.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.3252583026885985,
|
|
"epoch": 0.8611911623439001,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004934060004407434,
|
|
"loss": 5.0429,
|
|
"mean_token_accuracy": 0.21834986060857772,
|
|
"num_tokens": 20561229.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.257746934890747,
|
|
"epoch": 0.861671469740634,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004933977588281099,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.21840566098690034,
|
|
"num_tokens": 20572040.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.220415210723877,
|
|
"epoch": 0.8621517771373679,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004933895121449288,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.21771437376737596,
|
|
"num_tokens": 20583110.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.246572065353393,
|
|
"epoch": 0.8626320845341018,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004933812603913917,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.21518482267856598,
|
|
"num_tokens": 20593647.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.202943229675293,
|
|
"epoch": 0.8631123919308358,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004933730035676903,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.23275296092033387,
|
|
"num_tokens": 20604428.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.192376565933228,
|
|
"epoch": 0.8635926993275697,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004933647416740161,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.2246390014886856,
|
|
"num_tokens": 20615811.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.336459970474243,
|
|
"epoch": 0.8640730067243035,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000493356474710561,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.21630200743675232,
|
|
"num_tokens": 20627679.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.357700300216675,
|
|
"epoch": 0.8645533141210374,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000493348202677517,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.2130083382129669,
|
|
"num_tokens": 20638879.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.8645533141210374,
|
|
"eval_entropy": 5.09952763230088,
|
|
"eval_loss": 5.063816070556641,
|
|
"eval_mean_token_accuracy": 0.22313115184264815,
|
|
"eval_num_tokens": 20638879.0,
|
|
"eval_runtime": 20.6986,
|
|
"eval_samples_per_second": 1585.372,
|
|
"eval_steps_per_second": 198.178,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.275961780548096,
|
|
"epoch": 0.8650336215177714,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004933399255750761,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.219720821082592,
|
|
"num_tokens": 20649729.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.318403005599976,
|
|
"epoch": 0.8655139289145053,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004933316434034304,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.21900081485509873,
|
|
"num_tokens": 20660473.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.354868984222412,
|
|
"epoch": 0.8659942363112392,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004933233561627723,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.21625189036130904,
|
|
"num_tokens": 20671776.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.28105936050415,
|
|
"epoch": 0.866474543707973,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004933150638532942,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.21608456820249558,
|
|
"num_tokens": 20684147.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.282857179641724,
|
|
"epoch": 0.866954851104707,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004933067664751885,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.2147336944937706,
|
|
"num_tokens": 20695248.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.283448982238769,
|
|
"epoch": 0.8674351585014409,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000493298464028648,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.21722276955842973,
|
|
"num_tokens": 20707772.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.291160774230957,
|
|
"epoch": 0.8679154658981748,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004932901565138653,
|
|
"loss": 5.0143,
|
|
"mean_token_accuracy": 0.2133553460240364,
|
|
"num_tokens": 20718813.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.228615617752075,
|
|
"epoch": 0.8683957732949087,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004932818439310334,
|
|
"loss": 5.0032,
|
|
"mean_token_accuracy": 0.22223004698753357,
|
|
"num_tokens": 20730939.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.35224232673645,
|
|
"epoch": 0.8688760806916427,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004932735262803452,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.2111290842294693,
|
|
"num_tokens": 20742990.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.23276653289795,
|
|
"epoch": 0.8693563880883766,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004932652035619939,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.2185356765985489,
|
|
"num_tokens": 20754076.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.29207034111023,
|
|
"epoch": 0.8698366954851104,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004932568757761727,
|
|
"loss": 5.0054,
|
|
"mean_token_accuracy": 0.22211582213640213,
|
|
"num_tokens": 20765538.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.334879398345947,
|
|
"epoch": 0.8703170028818443,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004932485429230748,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.211406147480011,
|
|
"num_tokens": 20776359.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.2680652141571045,
|
|
"epoch": 0.8707973102785783,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000493240205002894,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.2201646402478218,
|
|
"num_tokens": 20787581.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.334187412261963,
|
|
"epoch": 0.8712776176753122,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004932318620158235,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.21241996735334395,
|
|
"num_tokens": 20799904.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.325835514068603,
|
|
"epoch": 0.8717579250720461,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004932235139620574,
|
|
"loss": 5.014,
|
|
"mean_token_accuracy": 0.21864811480045318,
|
|
"num_tokens": 20810238.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.258591938018799,
|
|
"epoch": 0.8722382324687801,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004932151608417892,
|
|
"loss": 4.9756,
|
|
"mean_token_accuracy": 0.22118595540523528,
|
|
"num_tokens": 20821349.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.214950275421143,
|
|
"epoch": 0.872718539865514,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004932068026552127,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.21536519825458528,
|
|
"num_tokens": 20834788.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.313766670227051,
|
|
"epoch": 0.8731988472622478,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004931984394025224,
|
|
"loss": 5.0866,
|
|
"mean_token_accuracy": 0.21473322212696075,
|
|
"num_tokens": 20845571.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.35056791305542,
|
|
"epoch": 0.8736791546589817,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004931900710839123,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.21386340260505676,
|
|
"num_tokens": 20857209.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.363465023040772,
|
|
"epoch": 0.8741594620557157,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004931816976995766,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.21253460496664048,
|
|
"num_tokens": 20870624.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.2711201190948485,
|
|
"epoch": 0.8746397694524496,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004931733192497097,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.22064325511455535,
|
|
"num_tokens": 20881769.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.22776312828064,
|
|
"epoch": 0.8751200768491835,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004931649357345062,
|
|
"loss": 4.9976,
|
|
"mean_token_accuracy": 0.2130696341395378,
|
|
"num_tokens": 20892817.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.288740587234497,
|
|
"epoch": 0.8756003842459174,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004931565471541606,
|
|
"loss": 4.9719,
|
|
"mean_token_accuracy": 0.22544212341308595,
|
|
"num_tokens": 20903042.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.227994728088379,
|
|
"epoch": 0.8760806916426513,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004931481535088679,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.2286444276571274,
|
|
"num_tokens": 20914684.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.225664138793945,
|
|
"epoch": 0.8765609990393852,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004931397547988229,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.22618058919906617,
|
|
"num_tokens": 20926585.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.3330024719238285,
|
|
"epoch": 0.8770413064361191,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004931313510242204,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.21715231686830522,
|
|
"num_tokens": 20939729.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.256030321121216,
|
|
"epoch": 0.877521613832853,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004931229421852557,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.2193952441215515,
|
|
"num_tokens": 20951697.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.296226263046265,
|
|
"epoch": 0.878001921229587,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000493114528282124,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.21304744184017183,
|
|
"num_tokens": 20962729.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.252359914779663,
|
|
"epoch": 0.8784822286263209,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004931061093150206,
|
|
"loss": 4.9656,
|
|
"mean_token_accuracy": 0.22306902557611466,
|
|
"num_tokens": 20973331.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.237087297439575,
|
|
"epoch": 0.8789625360230547,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004930976852841409,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.2152834415435791,
|
|
"num_tokens": 20985609.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.243382787704467,
|
|
"epoch": 0.8794428434197886,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004930892561896806,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.21254609972238542,
|
|
"num_tokens": 20997231.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.308042573928833,
|
|
"epoch": 0.8799231508165226,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004930808220318354,
|
|
"loss": 5.0157,
|
|
"mean_token_accuracy": 0.21969407051801682,
|
|
"num_tokens": 21008511.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.257471323013306,
|
|
"epoch": 0.8804034582132565,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004930723828108012,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.2184320420026779,
|
|
"num_tokens": 21019108.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.252701902389527,
|
|
"epoch": 0.8808837656099904,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004930639385267736,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.2219120129942894,
|
|
"num_tokens": 21030621.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.273743295669556,
|
|
"epoch": 0.8813640730067243,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000493055489179949,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.2200742095708847,
|
|
"num_tokens": 21041778.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.273216104507446,
|
|
"epoch": 0.8818443804034583,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004930470347705234,
|
|
"loss": 5.009,
|
|
"mean_token_accuracy": 0.22305000722408294,
|
|
"num_tokens": 21054257.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.306494283676147,
|
|
"epoch": 0.8823246878001921,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000493038575298693,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.21175634264945983,
|
|
"num_tokens": 21066378.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.216196060180664,
|
|
"epoch": 0.882804995196926,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004930301107646545,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.21421182304620742,
|
|
"num_tokens": 21078913.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.282477235794067,
|
|
"epoch": 0.8832853025936599,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004930216411686042,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.20952652841806413,
|
|
"num_tokens": 21090500.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.275503540039063,
|
|
"epoch": 0.8837656099903939,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004930131665107387,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.21479604095220567,
|
|
"num_tokens": 21102793.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.373411655426025,
|
|
"epoch": 0.8842459173871278,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000493004686791255,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.21017527282238008,
|
|
"num_tokens": 21114504.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.269224405288696,
|
|
"epoch": 0.8847262247838616,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004929962020103496,
|
|
"loss": 4.9833,
|
|
"mean_token_accuracy": 0.21784576624631882,
|
|
"num_tokens": 21126733.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.23415994644165,
|
|
"epoch": 0.8852065321805955,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004929877121682198,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.21848627924919128,
|
|
"num_tokens": 21138045.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.258844518661499,
|
|
"epoch": 0.8856868395773295,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004929792172650627,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.21126711666584014,
|
|
"num_tokens": 21151562.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.296943283081054,
|
|
"epoch": 0.8861671469740634,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004929707173010753,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.21046533137559892,
|
|
"num_tokens": 21162943.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.2792332649230955,
|
|
"epoch": 0.8866474543707973,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004929622122764552,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.21485553234815596,
|
|
"num_tokens": 21174392.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.227682876586914,
|
|
"epoch": 0.8871277617675313,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004929537021913997,
|
|
"loss": 4.9007,
|
|
"mean_token_accuracy": 0.22950513809919357,
|
|
"num_tokens": 21185372.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.275816869735718,
|
|
"epoch": 0.8876080691642652,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004929451870461064,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.2113460347056389,
|
|
"num_tokens": 21197044.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.239752006530762,
|
|
"epoch": 0.888088376560999,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004929366668407731,
|
|
"loss": 4.99,
|
|
"mean_token_accuracy": 0.22700745910406112,
|
|
"num_tokens": 21207729.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.314344978332519,
|
|
"epoch": 0.8885686839577329,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004929281415755974,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.21649389266967772,
|
|
"num_tokens": 21218909.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.340578269958496,
|
|
"epoch": 0.8890489913544669,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004929196112507775,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.21111754775047303,
|
|
"num_tokens": 21230543.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.297629165649414,
|
|
"epoch": 0.8895292987512008,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004929110758665112,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.21511633396148683,
|
|
"num_tokens": 21242064.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.303161668777466,
|
|
"epoch": 0.8900096061479347,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004929025354229969,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.21636799722909927,
|
|
"num_tokens": 21254321.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.187288618087768,
|
|
"epoch": 0.8904899135446686,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004928939899204326,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.22594969272613524,
|
|
"num_tokens": 21264741.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.31791205406189,
|
|
"epoch": 0.8909702209414025,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000492885439359017,
|
|
"loss": 5.0164,
|
|
"mean_token_accuracy": 0.21543063521385192,
|
|
"num_tokens": 21276834.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.233167314529419,
|
|
"epoch": 0.8914505283381364,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004928768837389485,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.22092292010784148,
|
|
"num_tokens": 21287108.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.2286313533782955,
|
|
"epoch": 0.8919308357348703,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004928683230604257,
|
|
"loss": 5.0045,
|
|
"mean_token_accuracy": 0.2186286047101021,
|
|
"num_tokens": 21299942.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.405380344390869,
|
|
"epoch": 0.8924111431316042,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004928597573236474,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.2088737189769745,
|
|
"num_tokens": 21311243.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.310605001449585,
|
|
"epoch": 0.8928914505283382,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004928511865288123,
|
|
"loss": 4.9805,
|
|
"mean_token_accuracy": 0.22331418246030807,
|
|
"num_tokens": 21322291.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.283558702468872,
|
|
"epoch": 0.8933717579250721,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004928426106761197,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.21648231893777847,
|
|
"num_tokens": 21333257.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.224516820907593,
|
|
"epoch": 0.8938520653218059,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004928340297657685,
|
|
"loss": 4.9831,
|
|
"mean_token_accuracy": 0.21495548784732818,
|
|
"num_tokens": 21345848.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.296548891067505,
|
|
"epoch": 0.8943323727185398,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004928254437979578,
|
|
"loss": 5.0165,
|
|
"mean_token_accuracy": 0.2184055417776108,
|
|
"num_tokens": 21357693.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.273598766326904,
|
|
"epoch": 0.8948126801152738,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004928168527728873,
|
|
"loss": 5.1255,
|
|
"mean_token_accuracy": 0.21267225593328476,
|
|
"num_tokens": 21369653.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.358665990829468,
|
|
"epoch": 0.8952929875120077,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004928082566907562,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.21815236955881118,
|
|
"num_tokens": 21383924.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.314771413803101,
|
|
"epoch": 0.8957732949087416,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004927996555517642,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.21375614851713182,
|
|
"num_tokens": 21395963.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.281578779220581,
|
|
"epoch": 0.8962536023054755,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004927910493561109,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.21775185763835908,
|
|
"num_tokens": 21408200.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.351464796066284,
|
|
"epoch": 0.8967339097022095,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000492782438103996,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.20740824490785598,
|
|
"num_tokens": 21419963.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.336421394348145,
|
|
"epoch": 0.8972142170989433,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004927738217956197,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.214196614921093,
|
|
"num_tokens": 21431824.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.192102336883545,
|
|
"epoch": 0.8976945244956772,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004927652004311819,
|
|
"loss": 4.8601,
|
|
"mean_token_accuracy": 0.22789789885282516,
|
|
"num_tokens": 21442354.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.302257823944092,
|
|
"epoch": 0.8981748318924111,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004927565740108828,
|
|
"loss": 5.0246,
|
|
"mean_token_accuracy": 0.21304932832717896,
|
|
"num_tokens": 21453734.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.293565988540649,
|
|
"epoch": 0.8986551392891451,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004927479425349226,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.21963883489370345,
|
|
"num_tokens": 21465471.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.346841669082641,
|
|
"epoch": 0.899135446685879,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004927393060035018,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.2076309561729431,
|
|
"num_tokens": 21477775.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.21389799118042,
|
|
"epoch": 0.8996157540826129,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004927306644168207,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.22712403088808059,
|
|
"num_tokens": 21489319.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.385450458526611,
|
|
"epoch": 0.9000960614793467,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004927220177750803,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.21272541135549544,
|
|
"num_tokens": 21499742.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.272635746002197,
|
|
"epoch": 0.9005763688760807,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004927133660784811,
|
|
"loss": 4.9769,
|
|
"mean_token_accuracy": 0.22372090816497803,
|
|
"num_tokens": 21511063.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.269239664077759,
|
|
"epoch": 0.9010566762728146,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004927047093272241,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.21752334386110306,
|
|
"num_tokens": 21522500.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.312640619277954,
|
|
"epoch": 0.9015369836695485,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049269604752151,
|
|
"loss": 5.0672,
|
|
"mean_token_accuracy": 0.21184938102960588,
|
|
"num_tokens": 21533578.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.277040815353393,
|
|
"epoch": 0.9020172910662824,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004926873806615403,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.20969802588224412,
|
|
"num_tokens": 21544296.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.300060558319092,
|
|
"epoch": 0.9024975984630164,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004926787087475158,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.20543698966503143,
|
|
"num_tokens": 21555386.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.256591033935547,
|
|
"epoch": 0.9029779058597502,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004926700317796382,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.2336789771914482,
|
|
"num_tokens": 21566527.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.360135650634765,
|
|
"epoch": 0.9034582132564841,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004926613497581088,
|
|
"loss": 5.039,
|
|
"mean_token_accuracy": 0.2152058631181717,
|
|
"num_tokens": 21576870.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.275247097015381,
|
|
"epoch": 0.9039385206532181,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004926526626831292,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.21933796852827073,
|
|
"num_tokens": 21588113.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.256653499603272,
|
|
"epoch": 0.904418828049952,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004926439705549011,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.2163578286767006,
|
|
"num_tokens": 21599307.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.275369644165039,
|
|
"epoch": 0.9048991354466859,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004926352733736262,
|
|
"loss": 4.9861,
|
|
"mean_token_accuracy": 0.22366381734609603,
|
|
"num_tokens": 21609961.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.240253543853759,
|
|
"epoch": 0.9053794428434198,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004926265711395065,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.21548174619674682,
|
|
"num_tokens": 21622222.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.257960414886474,
|
|
"epoch": 0.9058597502401537,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000492617863852744,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.2248610481619835,
|
|
"num_tokens": 21632843.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.2882537841796875,
|
|
"epoch": 0.9063400576368876,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004926091515135409,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.21369160562753678,
|
|
"num_tokens": 21645387.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.267239332199097,
|
|
"epoch": 0.9068203650336215,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004926004341220995,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.22084719091653823,
|
|
"num_tokens": 21656787.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.329501962661743,
|
|
"epoch": 0.9073006724303554,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004925917116786222,
|
|
"loss": 5.0323,
|
|
"mean_token_accuracy": 0.21977902501821517,
|
|
"num_tokens": 21667800.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.309007215499878,
|
|
"epoch": 0.9077809798270894,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004925829841833114,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.21218023598194122,
|
|
"num_tokens": 21679297.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.273968982696533,
|
|
"epoch": 0.9082612872238233,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004925742516363699,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.20879530906677246,
|
|
"num_tokens": 21692956.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.255225658416748,
|
|
"epoch": 0.9087415946205571,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004925655140380002,
|
|
"loss": 4.869,
|
|
"mean_token_accuracy": 0.22657041251659393,
|
|
"num_tokens": 21704852.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.309493637084961,
|
|
"epoch": 0.909221902017291,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004925567713884054,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.21910935789346694,
|
|
"num_tokens": 21715886.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.236155891418457,
|
|
"epoch": 0.909702209414025,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004925480236877884,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.22265698313713073,
|
|
"num_tokens": 21727157.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.252168321609497,
|
|
"epoch": 0.9101825168107589,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004925392709363522,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.21956454664468766,
|
|
"num_tokens": 21738232.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.249209022521972,
|
|
"epoch": 0.9106628242074928,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004925305131343001,
|
|
"loss": 5.0343,
|
|
"mean_token_accuracy": 0.21398487985134124,
|
|
"num_tokens": 21749029.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.329716444015503,
|
|
"epoch": 0.9111431316042267,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004925217502818355,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.2130681172013283,
|
|
"num_tokens": 21761243.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.252294445037842,
|
|
"epoch": 0.9116234390009607,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004925129823791616,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.21370399594306946,
|
|
"num_tokens": 21772623.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.332067346572876,
|
|
"epoch": 0.9121037463976945,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004925042094264822,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.21759025752544403,
|
|
"num_tokens": 21782611.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.203507804870606,
|
|
"epoch": 0.9125840537944284,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492495431424001,
|
|
"loss": 4.9162,
|
|
"mean_token_accuracy": 0.22751926332712175,
|
|
"num_tokens": 21793946.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.3564716339111325,
|
|
"epoch": 0.9130643611911623,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004924866483719216,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.21058327555656434,
|
|
"num_tokens": 21803878.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.282685089111328,
|
|
"epoch": 0.9135446685878963,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004924778602704481,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.21769251078367233,
|
|
"num_tokens": 21815187.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.288547515869141,
|
|
"epoch": 0.9140249759846302,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004924690671197845,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.2239673689007759,
|
|
"num_tokens": 21825597.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.22894024848938,
|
|
"epoch": 0.914505283381364,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004924602689201348,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.22132650017738342,
|
|
"num_tokens": 21837110.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.465541505813599,
|
|
"epoch": 0.9149855907780979,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004924514656717034,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.2109512597322464,
|
|
"num_tokens": 21847754.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.249364519119263,
|
|
"epoch": 0.9154658981748319,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004924426573746948,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.21390101462602615,
|
|
"num_tokens": 21859162.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.286064147949219,
|
|
"epoch": 0.9159462055715658,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004924338440293131,
|
|
"loss": 5.0008,
|
|
"mean_token_accuracy": 0.21862683892250062,
|
|
"num_tokens": 21870826.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.27528486251831,
|
|
"epoch": 0.9164265129682997,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004924250256357635,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.21287347972393036,
|
|
"num_tokens": 21882003.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.264393663406372,
|
|
"epoch": 0.9169068203650336,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004924162021942502,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.21821916699409485,
|
|
"num_tokens": 21894132.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.22781343460083,
|
|
"epoch": 0.9173871277617676,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004924073737049784,
|
|
"loss": 4.974,
|
|
"mean_token_accuracy": 0.2241566598415375,
|
|
"num_tokens": 21904951.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.239073276519775,
|
|
"epoch": 0.9178674351585014,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004923985401681528,
|
|
"loss": 5.0213,
|
|
"mean_token_accuracy": 0.22006384879350663,
|
|
"num_tokens": 21917100.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.313463640213013,
|
|
"epoch": 0.9183477425552353,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004923897015839788,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.2168206363916397,
|
|
"num_tokens": 21927541.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.293189191818238,
|
|
"epoch": 0.9188280499519692,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004923808579526613,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.21795238554477692,
|
|
"num_tokens": 21938723.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.224343633651733,
|
|
"epoch": 0.9193083573487032,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004923720092744059,
|
|
"loss": 4.8948,
|
|
"mean_token_accuracy": 0.2270112782716751,
|
|
"num_tokens": 21950424.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.271740055084228,
|
|
"epoch": 0.9197886647454371,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004923631555494179,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.22152447700500488,
|
|
"num_tokens": 21961030.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.296582174301148,
|
|
"epoch": 0.920268972142171,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923542967779028,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.22273160815238952,
|
|
"num_tokens": 21971625.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.313235950469971,
|
|
"epoch": 0.920749279538905,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004923454329600664,
|
|
"loss": 4.9936,
|
|
"mean_token_accuracy": 0.22215207517147065,
|
|
"num_tokens": 21983733.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.2137689113616945,
|
|
"epoch": 0.9212295869356388,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004923365640961143,
|
|
"loss": 4.9456,
|
|
"mean_token_accuracy": 0.22720693051815033,
|
|
"num_tokens": 21995621.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.310101556777954,
|
|
"epoch": 0.9217098943323727,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004923276901862526,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.21649552136659622,
|
|
"num_tokens": 22007325.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.293409967422486,
|
|
"epoch": 0.9221902017291066,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004923188112306874,
|
|
"loss": 4.9853,
|
|
"mean_token_accuracy": 0.21534916013479233,
|
|
"num_tokens": 22017733.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.26995439529419,
|
|
"epoch": 0.9226705091258406,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004923099272296246,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.2223100945353508,
|
|
"num_tokens": 22030451.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.263484334945678,
|
|
"epoch": 0.9231508165225745,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004923010381832706,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.21055614501237868,
|
|
"num_tokens": 22042626.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.2446061134338375,
|
|
"epoch": 0.9236311239193083,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004922921440918318,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.21793048679828644,
|
|
"num_tokens": 22053314.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.368663930892945,
|
|
"epoch": 0.9241114313160422,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004922832449555144,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.20827221274375915,
|
|
"num_tokens": 22064395.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.2703649520874025,
|
|
"epoch": 0.9245917387127762,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004922743407745255,
|
|
"loss": 4.978,
|
|
"mean_token_accuracy": 0.21472820341587068,
|
|
"num_tokens": 22075960.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.31541805267334,
|
|
"epoch": 0.9250720461095101,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004922654315490714,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.21747578531503678,
|
|
"num_tokens": 22086034.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.295312595367432,
|
|
"epoch": 0.925552353506244,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004922565172793593,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.2151724874973297,
|
|
"num_tokens": 22096184.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.302003860473633,
|
|
"epoch": 0.9260326609029779,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004922475979655958,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.21663730591535568,
|
|
"num_tokens": 22108795.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.254413747787476,
|
|
"epoch": 0.9265129682997119,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004922386736079883,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.21520925909280778,
|
|
"num_tokens": 22119608.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.278695297241211,
|
|
"epoch": 0.9269932756964457,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004922297442067438,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.22592408508062362,
|
|
"num_tokens": 22131621.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.330060148239136,
|
|
"epoch": 0.9274735830931796,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004922208097620697,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.22365908324718475,
|
|
"num_tokens": 22142745.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.249020385742187,
|
|
"epoch": 0.9279538904899135,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004922118702741735,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.21266472041606904,
|
|
"num_tokens": 22155457.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.345229911804199,
|
|
"epoch": 0.9284341978866475,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004922029257432625,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.2287702515721321,
|
|
"num_tokens": 22165955.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.28854513168335,
|
|
"epoch": 0.9289145052833814,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921939761695446,
|
|
"loss": 4.9594,
|
|
"mean_token_accuracy": 0.21616602540016175,
|
|
"num_tokens": 22178142.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.190385627746582,
|
|
"epoch": 0.9293948126801153,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004921850215532275,
|
|
"loss": 4.9331,
|
|
"mean_token_accuracy": 0.22006936371326447,
|
|
"num_tokens": 22190315.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.232425832748413,
|
|
"epoch": 0.9298751200768491,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004921760618945192,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.22309097051620483,
|
|
"num_tokens": 22201785.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.303860521316528,
|
|
"epoch": 0.9303554274735831,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921670971936276,
|
|
"loss": 4.9556,
|
|
"mean_token_accuracy": 0.22083207815885544,
|
|
"num_tokens": 22212471.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.3013979434967045,
|
|
"epoch": 0.930835734870317,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004921581274507607,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.22386121451854707,
|
|
"num_tokens": 22223188.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.21935715675354,
|
|
"epoch": 0.9313160422670509,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492149152666127,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.21629127115011215,
|
|
"num_tokens": 22233978.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.2537843704223635,
|
|
"epoch": 0.9317963496637848,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004921401728399348,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.22612797021865844,
|
|
"num_tokens": 22244713.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.294991779327392,
|
|
"epoch": 0.9322766570605188,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004921311879723926,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.21627774238586425,
|
|
"num_tokens": 22256192.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.3255462646484375,
|
|
"epoch": 0.9327569644572526,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004921221980637088,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.2136331245303154,
|
|
"num_tokens": 22268294.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.313583946228027,
|
|
"epoch": 0.9332372718539865,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004921132031140925,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.22147811502218245,
|
|
"num_tokens": 22278952.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.262536573410034,
|
|
"epoch": 0.9337175792507204,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004921042031237521,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.21746194660663604,
|
|
"num_tokens": 22291057.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.350217485427857,
|
|
"epoch": 0.9341978866474544,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004920951980928969,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.21769094318151475,
|
|
"num_tokens": 22302479.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.382465982437134,
|
|
"epoch": 0.9346781940441883,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004920861880217359,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.2126326158642769,
|
|
"num_tokens": 22315116.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.3078125,
|
|
"epoch": 0.9351585014409222,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004920771729104781,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.2142432764172554,
|
|
"num_tokens": 22327548.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.2881035804748535,
|
|
"epoch": 0.9356388088376562,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004920681527593329,
|
|
"loss": 4.9462,
|
|
"mean_token_accuracy": 0.22308652251958846,
|
|
"num_tokens": 22339154.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.2584796905517575,
|
|
"epoch": 0.93611911623439,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004920591275685098,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.22078343629837036,
|
|
"num_tokens": 22350781.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.298837900161743,
|
|
"epoch": 0.9365994236311239,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004920500973382184,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.21960995495319366,
|
|
"num_tokens": 22361990.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.314497470855713,
|
|
"epoch": 0.9370797310278578,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004920410620686682,
|
|
"loss": 4.9368,
|
|
"mean_token_accuracy": 0.2288723722100258,
|
|
"num_tokens": 22372973.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.209956073760987,
|
|
"epoch": 0.9375600384245918,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004920320217600689,
|
|
"loss": 4.9515,
|
|
"mean_token_accuracy": 0.2249452903866768,
|
|
"num_tokens": 22384369.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.259726858139038,
|
|
"epoch": 0.9380403458213257,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004920229764126306,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.22025755792856216,
|
|
"num_tokens": 22395792.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.309612464904785,
|
|
"epoch": 0.9385206532180596,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004920139260265632,
|
|
"loss": 5.0261,
|
|
"mean_token_accuracy": 0.2167820855975151,
|
|
"num_tokens": 22408182.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.391679382324218,
|
|
"epoch": 0.9390009606147934,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004920048706020769,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.2068209633231163,
|
|
"num_tokens": 22419774.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.190526628494263,
|
|
"epoch": 0.9394812680115274,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004919958101393817,
|
|
"loss": 4.874,
|
|
"mean_token_accuracy": 0.22302304208278656,
|
|
"num_tokens": 22430210.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.292817544937134,
|
|
"epoch": 0.9399615754082613,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004919867446386883,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.2201724797487259,
|
|
"num_tokens": 22442444.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.232239055633545,
|
|
"epoch": 0.9404418828049952,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000491977674100207,
|
|
"loss": 4.9915,
|
|
"mean_token_accuracy": 0.22096169888973236,
|
|
"num_tokens": 22455521.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.309940671920776,
|
|
"epoch": 0.9409221902017291,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004919685985241483,
|
|
"loss": 5.0488,
|
|
"mean_token_accuracy": 0.21883592754602432,
|
|
"num_tokens": 22466997.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.268366909027099,
|
|
"epoch": 0.9414024975984631,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000491959517910723,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.22694261372089386,
|
|
"num_tokens": 22477851.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.206273555755615,
|
|
"epoch": 0.9418828049951969,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004919504322601421,
|
|
"loss": 5.0579,
|
|
"mean_token_accuracy": 0.2156046524643898,
|
|
"num_tokens": 22489319.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.177804946899414,
|
|
"epoch": 0.9423631123919308,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004919413415726162,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.22635700404644013,
|
|
"num_tokens": 22500847.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.3129349708557125,
|
|
"epoch": 0.9428434197886647,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004919322458483566,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.22045049518346788,
|
|
"num_tokens": 22512719.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.230278873443604,
|
|
"epoch": 0.9433237271853987,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004919231450875745,
|
|
"loss": 4.9389,
|
|
"mean_token_accuracy": 0.22585716843605042,
|
|
"num_tokens": 22522984.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.251847934722901,
|
|
"epoch": 0.9438040345821326,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004919140392904809,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.22210351824760438,
|
|
"num_tokens": 22534816.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.2458123683929445,
|
|
"epoch": 0.9442843419788665,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004919049284572875,
|
|
"loss": 4.9825,
|
|
"mean_token_accuracy": 0.21554143726825714,
|
|
"num_tokens": 22545753.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.334679174423218,
|
|
"epoch": 0.9447646493756003,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004918958125882058,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.2130831941962242,
|
|
"num_tokens": 22557237.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.293295860290527,
|
|
"epoch": 0.9452449567723343,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004918866916834474,
|
|
"loss": 4.9847,
|
|
"mean_token_accuracy": 0.21890626102685928,
|
|
"num_tokens": 22568909.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.365793514251709,
|
|
"epoch": 0.9457252641690682,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004918775657432239,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.20735300928354264,
|
|
"num_tokens": 22582162.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.237175178527832,
|
|
"epoch": 0.9462055715658021,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004918684347677474,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.21742402911186218,
|
|
"num_tokens": 22592405.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.296424627304077,
|
|
"epoch": 0.946685878962536,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004918592987572298,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.2168272390961647,
|
|
"num_tokens": 22603588.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.407385063171387,
|
|
"epoch": 0.94716618635927,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004918501577118832,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.21735931783914567,
|
|
"num_tokens": 22614995.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.285481071472168,
|
|
"epoch": 0.9476464937560038,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00049184101163192,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.21201010644435883,
|
|
"num_tokens": 22627556.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.324817323684693,
|
|
"epoch": 0.9481268011527377,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004918318605175522,
|
|
"loss": 5.0208,
|
|
"mean_token_accuracy": 0.22445139437913894,
|
|
"num_tokens": 22638339.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.3253514766693115,
|
|
"epoch": 0.9486071085494716,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004918227043689924,
|
|
"loss": 4.9768,
|
|
"mean_token_accuracy": 0.22335925400257112,
|
|
"num_tokens": 22648922.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.2410728454589846,
|
|
"epoch": 0.9490874159462056,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004918135431864534,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.22066012471914292,
|
|
"num_tokens": 22662006.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.216451406478882,
|
|
"epoch": 0.9495677233429395,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004918043769701478,
|
|
"loss": 4.9633,
|
|
"mean_token_accuracy": 0.22412959784269332,
|
|
"num_tokens": 22674649.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.352089738845825,
|
|
"epoch": 0.9500480307396734,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004917952057202882,
|
|
"loss": 5.0572,
|
|
"mean_token_accuracy": 0.2129005089402199,
|
|
"num_tokens": 22685971.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.279277515411377,
|
|
"epoch": 0.9505283381364072,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004917860294370877,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.22526732087135315,
|
|
"num_tokens": 22696174.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.315207052230835,
|
|
"epoch": 0.9510086455331412,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004917768481207593,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.2200968846678734,
|
|
"num_tokens": 22706983.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.310713863372802,
|
|
"epoch": 0.9514889529298751,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004917676617715162,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.2188078910112381,
|
|
"num_tokens": 22718251.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.218424701690674,
|
|
"epoch": 0.951969260326609,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004917584703895717,
|
|
"loss": 4.9715,
|
|
"mean_token_accuracy": 0.227272130548954,
|
|
"num_tokens": 22730071.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.250689363479614,
|
|
"epoch": 0.952449567723343,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004917492739751391,
|
|
"loss": 5.0097,
|
|
"mean_token_accuracy": 0.21611586213111877,
|
|
"num_tokens": 22742027.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.224556589126587,
|
|
"epoch": 0.9529298751200769,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000491740072528432,
|
|
"loss": 4.906,
|
|
"mean_token_accuracy": 0.2316231444478035,
|
|
"num_tokens": 22752946.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.3047041416168215,
|
|
"epoch": 0.9534101825168108,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000491730866049664,
|
|
"loss": 4.99,
|
|
"mean_token_accuracy": 0.22021090537309645,
|
|
"num_tokens": 22763944.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.2356555461883545,
|
|
"epoch": 0.9538904899135446,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004917216545390489,
|
|
"loss": 4.957,
|
|
"mean_token_accuracy": 0.22548570930957795,
|
|
"num_tokens": 22774414.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.229720401763916,
|
|
"epoch": 0.9543707973102786,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004917124379968004,
|
|
"loss": 4.8998,
|
|
"mean_token_accuracy": 0.23052207231521607,
|
|
"num_tokens": 22785533.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.214996576309204,
|
|
"epoch": 0.9548511047070125,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004917032164231327,
|
|
"loss": 4.851,
|
|
"mean_token_accuracy": 0.23044895827770234,
|
|
"num_tokens": 22795809.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.268262195587158,
|
|
"epoch": 0.9553314121037464,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004916939898182598,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.21662921607494354,
|
|
"num_tokens": 22807705.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.322963428497315,
|
|
"epoch": 0.9558117195004803,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004916847581823958,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.2204671248793602,
|
|
"num_tokens": 22818852.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.252047204971314,
|
|
"epoch": 0.9562920268972143,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004916755215157552,
|
|
"loss": 4.9027,
|
|
"mean_token_accuracy": 0.22474018335342408,
|
|
"num_tokens": 22829146.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.237692785263062,
|
|
"epoch": 0.9567723342939481,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004916662798185524,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.22866752445697786,
|
|
"num_tokens": 22840088.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.269695711135864,
|
|
"epoch": 0.957252641690682,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004916570330910019,
|
|
"loss": 5.0164,
|
|
"mean_token_accuracy": 0.2274025246500969,
|
|
"num_tokens": 22852470.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.327831745147705,
|
|
"epoch": 0.9577329490874159,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004916477813333185,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.21092079132795333,
|
|
"num_tokens": 22863673.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.253059434890747,
|
|
"epoch": 0.9582132564841499,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004916385245457168,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.21443782299757003,
|
|
"num_tokens": 22874888.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.270570945739746,
|
|
"epoch": 0.9586935638808838,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000491629262728412,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.21091512590646744,
|
|
"num_tokens": 22886811.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.333252477645874,
|
|
"epoch": 0.9591738712776177,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004916199958816188,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.21687838435173035,
|
|
"num_tokens": 22898777.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.302281188964844,
|
|
"epoch": 0.9596541786743515,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004916107240055527,
|
|
"loss": 4.9597,
|
|
"mean_token_accuracy": 0.22339343279600143,
|
|
"num_tokens": 22910804.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.317459630966186,
|
|
"epoch": 0.9601344860710855,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004916014471004287,
|
|
"loss": 5.1104,
|
|
"mean_token_accuracy": 0.2199084520339966,
|
|
"num_tokens": 22922002.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.299905061721802,
|
|
"epoch": 0.9606147934678194,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004915921651664622,
|
|
"loss": 4.9985,
|
|
"mean_token_accuracy": 0.21688541918992996,
|
|
"num_tokens": 22933471.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.200297498703003,
|
|
"epoch": 0.9610951008645533,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000491582878203869,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.22504227608442307,
|
|
"num_tokens": 22945303.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.238185453414917,
|
|
"epoch": 0.9615754082612872,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004915735862128643,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.2127025917172432,
|
|
"num_tokens": 22956620.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.314497995376587,
|
|
"epoch": 0.9620557156580212,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004915642891936641,
|
|
"loss": 5.0465,
|
|
"mean_token_accuracy": 0.21933964937925338,
|
|
"num_tokens": 22968941.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.32964186668396,
|
|
"epoch": 0.962536023054755,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004915549871464841,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.2148846358060837,
|
|
"num_tokens": 22980222.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.329556703567505,
|
|
"epoch": 0.9630163304514889,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004915456800715403,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.21293448209762572,
|
|
"num_tokens": 22991156.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.339330101013184,
|
|
"epoch": 0.9634966378482228,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000491536367969049,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.20958519876003265,
|
|
"num_tokens": 23002939.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.383946752548217,
|
|
"epoch": 0.9639769452449568,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004915270508392261,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.21836361289024353,
|
|
"num_tokens": 23015590.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.2001707553863525,
|
|
"epoch": 0.9644572526416907,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000491517728682288,
|
|
"loss": 4.908,
|
|
"mean_token_accuracy": 0.2255134701728821,
|
|
"num_tokens": 23026387.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.171950578689575,
|
|
"epoch": 0.9649375600384246,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004915084014984512,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.22336099445819854,
|
|
"num_tokens": 23037475.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.248710346221924,
|
|
"epoch": 0.9654178674351584,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004914990692879322,
|
|
"loss": 4.9539,
|
|
"mean_token_accuracy": 0.22828294187784196,
|
|
"num_tokens": 23049305.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.296443319320678,
|
|
"epoch": 0.9658981748318924,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004914897320509478,
|
|
"loss": 4.9683,
|
|
"mean_token_accuracy": 0.22198242992162703,
|
|
"num_tokens": 23061765.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.221637773513794,
|
|
"epoch": 0.9663784822286263,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004914803897877146,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.21211671084165573,
|
|
"num_tokens": 23072355.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.309389686584472,
|
|
"epoch": 0.9668587896253602,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004914710424984495,
|
|
"loss": 4.997,
|
|
"mean_token_accuracy": 0.21252110302448274,
|
|
"num_tokens": 23085583.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.340275287628174,
|
|
"epoch": 0.9673390970220941,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004914616901833696,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.2156083181500435,
|
|
"num_tokens": 23095942.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.243502807617188,
|
|
"epoch": 0.9678194044188281,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000491452332842692,
|
|
"loss": 4.9623,
|
|
"mean_token_accuracy": 0.22689363807439805,
|
|
"num_tokens": 23106540.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.269853830337524,
|
|
"epoch": 0.968299711815562,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000491442970476634,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.22504184693098067,
|
|
"num_tokens": 23118006.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.247406387329102,
|
|
"epoch": 0.9687800192122958,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004914336030854129,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.22886505872011184,
|
|
"num_tokens": 23129103.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.205692768096924,
|
|
"epoch": 0.9692603266090298,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004914242306692461,
|
|
"loss": 4.9415,
|
|
"mean_token_accuracy": 0.22711916714906694,
|
|
"num_tokens": 23140009.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.260742330551148,
|
|
"epoch": 0.9697406340057637,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004914148532283516,
|
|
"loss": 4.9949,
|
|
"mean_token_accuracy": 0.22203567028045654,
|
|
"num_tokens": 23150982.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.300123643875122,
|
|
"epoch": 0.9702209414024976,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004914054707629466,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.2162649765610695,
|
|
"num_tokens": 23161834.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.306209993362427,
|
|
"epoch": 0.9707012487992315,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004913960832732493,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.2124180629849434,
|
|
"num_tokens": 23173355.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.306587505340576,
|
|
"epoch": 0.9711815561959655,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004913866907594774,
|
|
"loss": 5.0572,
|
|
"mean_token_accuracy": 0.21493452936410903,
|
|
"num_tokens": 23185075.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.278501987457275,
|
|
"epoch": 0.9716618635926993,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004913772932218491,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.22556180357933045,
|
|
"num_tokens": 23195590.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.310996961593628,
|
|
"epoch": 0.9721421709894332,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004913678906605825,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.21865737140178682,
|
|
"num_tokens": 23207668.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.226266670227051,
|
|
"epoch": 0.9726224783861671,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004913584830758961,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.23079055100679396,
|
|
"num_tokens": 23218497.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.356466436386109,
|
|
"epoch": 0.9731027857829011,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004913490704680081,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.21443286836147307,
|
|
"num_tokens": 23230575.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.304587697982788,
|
|
"epoch": 0.973583093179635,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004913396528371371,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.21829638183116912,
|
|
"num_tokens": 23242348.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.294364261627197,
|
|
"epoch": 0.9740634005763689,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004913302301835018,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.21942730247974396,
|
|
"num_tokens": 23253297.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.244136905670166,
|
|
"epoch": 0.9745437079731027,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000491320802507321,
|
|
"loss": 4.9625,
|
|
"mean_token_accuracy": 0.22819057404994963,
|
|
"num_tokens": 23265830.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.309697675704956,
|
|
"epoch": 0.9750240153698367,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004913113698088133,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.21807650923728944,
|
|
"num_tokens": 23275591.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.262397241592407,
|
|
"epoch": 0.9755043227665706,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000491301932088198,
|
|
"loss": 4.941,
|
|
"mean_token_accuracy": 0.22249893248081207,
|
|
"num_tokens": 23286685.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.216834354400635,
|
|
"epoch": 0.9759846301633045,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004912924893456942,
|
|
"loss": 4.9471,
|
|
"mean_token_accuracy": 0.22529801577329636,
|
|
"num_tokens": 23298776.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.239245653152466,
|
|
"epoch": 0.9764649375600384,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000491283041581521,
|
|
"loss": 4.9325,
|
|
"mean_token_accuracy": 0.22041333615779876,
|
|
"num_tokens": 23310498.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.278992366790772,
|
|
"epoch": 0.9769452449567724,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004912735887958978,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.22294555008411407,
|
|
"num_tokens": 23321089.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.278607797622681,
|
|
"epoch": 0.9774255523535063,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004912641309890441,
|
|
"loss": 4.9773,
|
|
"mean_token_accuracy": 0.22036618441343309,
|
|
"num_tokens": 23332142.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.205700206756592,
|
|
"epoch": 0.9779058597502401,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004912546681611794,
|
|
"loss": 4.9428,
|
|
"mean_token_accuracy": 0.2297223225235939,
|
|
"num_tokens": 23343014.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.277859115600586,
|
|
"epoch": 0.978386167146974,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004912452003125234,
|
|
"loss": 4.9384,
|
|
"mean_token_accuracy": 0.2263363406062126,
|
|
"num_tokens": 23354611.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.273922157287598,
|
|
"epoch": 0.978866474543708,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000491235727443296,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.2161739006638527,
|
|
"num_tokens": 23365608.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.288276243209839,
|
|
"epoch": 0.9793467819404419,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004912262495537171,
|
|
"loss": 5.0096,
|
|
"mean_token_accuracy": 0.2223093569278717,
|
|
"num_tokens": 23377884.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.184326696395874,
|
|
"epoch": 0.9798270893371758,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004912167666440068,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.22272637337446213,
|
|
"num_tokens": 23389553.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.211463260650635,
|
|
"epoch": 0.9803073967339097,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004912072787143852,
|
|
"loss": 4.8969,
|
|
"mean_token_accuracy": 0.22205393761396408,
|
|
"num_tokens": 23401079.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.23992509841919,
|
|
"epoch": 0.9807877041306436,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004911977857650725,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.221847040951252,
|
|
"num_tokens": 23412886.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.308433580398559,
|
|
"epoch": 0.9812680115273775,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004911882877962893,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.21274041682481765,
|
|
"num_tokens": 23424758.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.220535373687744,
|
|
"epoch": 0.9817483189241114,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004911787848082559,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.23109544515609742,
|
|
"num_tokens": 23435552.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.188296937942505,
|
|
"epoch": 0.9822286263208453,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004911692768011931,
|
|
"loss": 4.909,
|
|
"mean_token_accuracy": 0.22794807702302933,
|
|
"num_tokens": 23446584.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.351886177062989,
|
|
"epoch": 0.9827089337175793,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004911597637753217,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.20629780739545822,
|
|
"num_tokens": 23458452.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.298908948898315,
|
|
"epoch": 0.9831892411143132,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004911502457308623,
|
|
"loss": 5.005,
|
|
"mean_token_accuracy": 0.2151845797896385,
|
|
"num_tokens": 23470310.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.344496870040894,
|
|
"epoch": 0.983669548511047,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000491140722668036,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.22020720392465593,
|
|
"num_tokens": 23481166.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.268197011947632,
|
|
"epoch": 0.984149855907781,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000491131194587064,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.22076378464698793,
|
|
"num_tokens": 23493134.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.2058045864105225,
|
|
"epoch": 0.9846301633045149,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004911216614881675,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.2243533819913864,
|
|
"num_tokens": 23504983.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.317254447937012,
|
|
"epoch": 0.9851104707012488,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004911121233715677,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.22312158197164536,
|
|
"num_tokens": 23516119.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.348520135879516,
|
|
"epoch": 0.9855907780979827,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004911025802374861,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.21397202908992768,
|
|
"num_tokens": 23528242.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.210879993438721,
|
|
"epoch": 0.9860710854947167,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004910930320861442,
|
|
"loss": 4.916,
|
|
"mean_token_accuracy": 0.23077184706926346,
|
|
"num_tokens": 23539738.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.127011775970459,
|
|
"epoch": 0.9865513928914506,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004910834789177639,
|
|
"loss": 4.9322,
|
|
"mean_token_accuracy": 0.224748694896698,
|
|
"num_tokens": 23551228.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.303711557388306,
|
|
"epoch": 0.9870317002881844,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004910739207325668,
|
|
"loss": 4.9876,
|
|
"mean_token_accuracy": 0.22397853881120683,
|
|
"num_tokens": 23563084.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.270771455764771,
|
|
"epoch": 0.9875120076849183,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004910643575307749,
|
|
"loss": 4.9513,
|
|
"mean_token_accuracy": 0.2266560062766075,
|
|
"num_tokens": 23574328.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.1867015838623045,
|
|
"epoch": 0.9879923150816523,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004910547893126102,
|
|
"loss": 4.9598,
|
|
"mean_token_accuracy": 0.225901797413826,
|
|
"num_tokens": 23585230.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.22535891532898,
|
|
"epoch": 0.9884726224783862,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004910452160782948,
|
|
"loss": 4.9763,
|
|
"mean_token_accuracy": 0.21333660036325455,
|
|
"num_tokens": 23596951.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.326337051391602,
|
|
"epoch": 0.9889529298751201,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000491035637828051,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.2236792489886284,
|
|
"num_tokens": 23607759.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.289549160003662,
|
|
"epoch": 0.989433237271854,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004910260545621012,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.21728943884372712,
|
|
"num_tokens": 23619631.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.241495561599732,
|
|
"epoch": 0.9899135446685879,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004910164662806679,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.22212643921375275,
|
|
"num_tokens": 23630601.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.301242208480835,
|
|
"epoch": 0.9903938520653218,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004910068729839736,
|
|
"loss": 4.9332,
|
|
"mean_token_accuracy": 0.22495593279600143,
|
|
"num_tokens": 23641330.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.301807260513305,
|
|
"epoch": 0.9908741594620557,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004909972746722413,
|
|
"loss": 5.0198,
|
|
"mean_token_accuracy": 0.21776878833770752,
|
|
"num_tokens": 23651492.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.211068248748779,
|
|
"epoch": 0.9913544668587896,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004909876713456935,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.22746839225292206,
|
|
"num_tokens": 23661773.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.259599733352661,
|
|
"epoch": 0.9918347742555236,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004909780630045534,
|
|
"loss": 4.9605,
|
|
"mean_token_accuracy": 0.2244741290807724,
|
|
"num_tokens": 23673534.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.300588703155517,
|
|
"epoch": 0.9923150816522575,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000490968449649044,
|
|
"loss": 5.0549,
|
|
"mean_token_accuracy": 0.22067267298698426,
|
|
"num_tokens": 23684892.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.330635261535645,
|
|
"epoch": 0.9927953890489913,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004909588312793884,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.21706904023885726,
|
|
"num_tokens": 23696076.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.325946092605591,
|
|
"epoch": 0.9932756964457252,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004909492078958101,
|
|
"loss": 5.0261,
|
|
"mean_token_accuracy": 0.21531579941511153,
|
|
"num_tokens": 23707795.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.249337148666382,
|
|
"epoch": 0.9937560038424592,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004909395794985324,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.2242613449692726,
|
|
"num_tokens": 23720802.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.248753881454467,
|
|
"epoch": 0.9942363112391931,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004909299460877788,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.21588589549064635,
|
|
"num_tokens": 23732854.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.310943174362182,
|
|
"epoch": 0.994716618635927,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004909203076637732,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.21553382277488708,
|
|
"num_tokens": 23743593.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.303987073898315,
|
|
"epoch": 0.9951969260326609,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004909106642267392,
|
|
"loss": 5.0243,
|
|
"mean_token_accuracy": 0.21632853001356125,
|
|
"num_tokens": 23755447.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.241162872314453,
|
|
"epoch": 0.9956772334293948,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004909010157769006,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.21970560401678085,
|
|
"num_tokens": 23767181.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.399766731262207,
|
|
"epoch": 0.9961575408261287,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004908913623144814,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.2096856191754341,
|
|
"num_tokens": 23776356.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.27275276184082,
|
|
"epoch": 0.9966378482228626,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000490881703839706,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.2227531149983406,
|
|
"num_tokens": 23787965.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.205696630477905,
|
|
"epoch": 0.9971181556195965,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004908720403527984,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.2274794787168503,
|
|
"num_tokens": 23800327.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.243367147445679,
|
|
"epoch": 0.9975984630163305,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000490862371853983,
|
|
"loss": 4.9199,
|
|
"mean_token_accuracy": 0.22548123598098754,
|
|
"num_tokens": 23812845.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.353694248199463,
|
|
"epoch": 0.9980787704130644,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004908526983434844,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.2143431007862091,
|
|
"num_tokens": 23824831.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.27176308631897,
|
|
"epoch": 0.9985590778097982,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000490843019821527,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.22548753172159194,
|
|
"num_tokens": 23836697.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.225878715515137,
|
|
"epoch": 0.9990393852065321,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004908333362883358,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.2244037002325058,
|
|
"num_tokens": 23847112.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.3030657291412355,
|
|
"epoch": 0.9995196926032661,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004908236477441353,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.22107020318508147,
|
|
"num_tokens": 23858185.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.167287015914917,
|
|
"epoch": 1.0,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004908139541891505,
|
|
"loss": 4.8275,
|
|
"mean_token_accuracy": 0.23650120943784714,
|
|
"num_tokens": 23868536.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.274187660217285,
|
|
"epoch": 1.0004803073967339,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004908042556236066,
|
|
"loss": 4.8823,
|
|
"mean_token_accuracy": 0.23181226551532746,
|
|
"num_tokens": 23880283.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.309299087524414,
|
|
"epoch": 1.0009606147934678,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004907945520477286,
|
|
"loss": 4.9602,
|
|
"mean_token_accuracy": 0.22216319739818574,
|
|
"num_tokens": 23892413.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.365721607208252,
|
|
"epoch": 1.0014409221902016,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004907848434617419,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.21287601441144943,
|
|
"num_tokens": 23903977.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.333603477478027,
|
|
"epoch": 1.0019212295869357,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000490775129865872,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.2165704056620598,
|
|
"num_tokens": 23915153.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.2360066890716555,
|
|
"epoch": 1.0024015369836696,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004907654112603442,
|
|
"loss": 4.9033,
|
|
"mean_token_accuracy": 0.2211843192577362,
|
|
"num_tokens": 23926043.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.193376445770264,
|
|
"epoch": 1.0028818443804035,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004907556876453843,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.23309382051229477,
|
|
"num_tokens": 23936658.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.263293027877808,
|
|
"epoch": 1.0033621517771374,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000490745959021218,
|
|
"loss": 4.9178,
|
|
"mean_token_accuracy": 0.21794203966856002,
|
|
"num_tokens": 23947676.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.253292465209961,
|
|
"epoch": 1.0038424591738713,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004907362253880711,
|
|
"loss": 4.901,
|
|
"mean_token_accuracy": 0.22251911461353302,
|
|
"num_tokens": 23959130.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.35165114402771,
|
|
"epoch": 1.0043227665706052,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004907264867461697,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.21690160930156707,
|
|
"num_tokens": 23969905.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.225652074813842,
|
|
"epoch": 1.004803073967339,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004907167430957399,
|
|
"loss": 4.8772,
|
|
"mean_token_accuracy": 0.22616911083459854,
|
|
"num_tokens": 23982016.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.268946123123169,
|
|
"epoch": 1.005283381364073,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004907069944370077,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.22152279764413835,
|
|
"num_tokens": 23994200.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.368046569824219,
|
|
"epoch": 1.005763688760807,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004906972407701998,
|
|
"loss": 4.9216,
|
|
"mean_token_accuracy": 0.23149920254945755,
|
|
"num_tokens": 24004695.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.236816310882569,
|
|
"epoch": 1.006243996157541,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004906874820955423,
|
|
"loss": 4.869,
|
|
"mean_token_accuracy": 0.2293284609913826,
|
|
"num_tokens": 24015922.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.195282602310181,
|
|
"epoch": 1.0067243035542748,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004906777184132621,
|
|
"loss": 4.8784,
|
|
"mean_token_accuracy": 0.22464821636676788,
|
|
"num_tokens": 24026759.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.286918687820434,
|
|
"epoch": 1.0072046109510087,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004906679497235856,
|
|
"loss": 4.9534,
|
|
"mean_token_accuracy": 0.21885820776224135,
|
|
"num_tokens": 24037988.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.320085763931274,
|
|
"epoch": 1.0076849183477425,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004906581760267397,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.22248762249946594,
|
|
"num_tokens": 24050837.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.268432140350342,
|
|
"epoch": 1.0081652257444764,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004906483973229513,
|
|
"loss": 4.8544,
|
|
"mean_token_accuracy": 0.2319096013903618,
|
|
"num_tokens": 24063085.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.209267330169678,
|
|
"epoch": 1.0086455331412103,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004906386136124476,
|
|
"loss": 4.9102,
|
|
"mean_token_accuracy": 0.22396856397390366,
|
|
"num_tokens": 24074082.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.32150444984436,
|
|
"epoch": 1.0091258405379442,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004906288248954554,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.22197814285755157,
|
|
"num_tokens": 24085050.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.264161014556885,
|
|
"epoch": 1.0096061479346783,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004906190311722023,
|
|
"loss": 4.938,
|
|
"mean_token_accuracy": 0.23015548437833785,
|
|
"num_tokens": 24095523.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.207053565979004,
|
|
"epoch": 1.0100864553314122,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004906092324429155,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.21892459243535994,
|
|
"num_tokens": 24107157.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.304631280899048,
|
|
"epoch": 1.010566762728146,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004905994287078227,
|
|
"loss": 4.9049,
|
|
"mean_token_accuracy": 0.22785793095827103,
|
|
"num_tokens": 24118668.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.28090009689331,
|
|
"epoch": 1.01104707012488,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004905896199671512,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.22385577261447906,
|
|
"num_tokens": 24129563.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.362709951400757,
|
|
"epoch": 1.0115273775216138,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000490579806221129,
|
|
"loss": 4.9781,
|
|
"mean_token_accuracy": 0.21373135298490525,
|
|
"num_tokens": 24139965.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.3374659538269045,
|
|
"epoch": 1.0120076849183477,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004905699874699838,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.22102486491203308,
|
|
"num_tokens": 24152109.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.257688045501709,
|
|
"epoch": 1.0124879923150816,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004905601637139436,
|
|
"loss": 4.9285,
|
|
"mean_token_accuracy": 0.2160330221056938,
|
|
"num_tokens": 24162558.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.183422565460205,
|
|
"epoch": 1.0129682997118155,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004905503349532365,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.2374105155467987,
|
|
"num_tokens": 24173963.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.246429920196533,
|
|
"epoch": 1.0134486071085496,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004905405011880906,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.23231059908866883,
|
|
"num_tokens": 24184369.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.336789512634278,
|
|
"epoch": 1.0139289145052834,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004905306624187343,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.21425141245126725,
|
|
"num_tokens": 24194692.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.306349563598633,
|
|
"epoch": 1.0144092219020173,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004905208186453961,
|
|
"loss": 4.9549,
|
|
"mean_token_accuracy": 0.2222945660352707,
|
|
"num_tokens": 24205363.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.330207252502442,
|
|
"epoch": 1.0148895292987512,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004905109698683044,
|
|
"loss": 4.9484,
|
|
"mean_token_accuracy": 0.21622021049261092,
|
|
"num_tokens": 24216678.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.200223541259765,
|
|
"epoch": 1.015369836695485,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004905011160876878,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.2206648886203766,
|
|
"num_tokens": 24227541.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.2698938846588135,
|
|
"epoch": 1.015850144092219,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004904912573037753,
|
|
"loss": 4.8805,
|
|
"mean_token_accuracy": 0.22845771312713622,
|
|
"num_tokens": 24238118.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.286724519729614,
|
|
"epoch": 1.0163304514889528,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004904813935167957,
|
|
"loss": 4.99,
|
|
"mean_token_accuracy": 0.21181708872318267,
|
|
"num_tokens": 24250044.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.321779775619507,
|
|
"epoch": 1.0168107588856867,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004904715247269779,
|
|
"loss": 4.9959,
|
|
"mean_token_accuracy": 0.21287375539541245,
|
|
"num_tokens": 24262805.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.270455360412598,
|
|
"epoch": 1.0172910662824208,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004904616509345514,
|
|
"loss": 4.9238,
|
|
"mean_token_accuracy": 0.21490428298711778,
|
|
"num_tokens": 24274287.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.169078636169433,
|
|
"epoch": 1.0177713736791547,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004904517721397449,
|
|
"loss": 4.8153,
|
|
"mean_token_accuracy": 0.22800626754760742,
|
|
"num_tokens": 24284839.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.241527700424195,
|
|
"epoch": 1.0182516810758886,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004904418883427881,
|
|
"loss": 4.9239,
|
|
"mean_token_accuracy": 0.2220812037587166,
|
|
"num_tokens": 24295812.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.2704771041870115,
|
|
"epoch": 1.0187319884726225,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004904319995439104,
|
|
"loss": 4.899,
|
|
"mean_token_accuracy": 0.2299889162182808,
|
|
"num_tokens": 24306365.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.291464614868164,
|
|
"epoch": 1.0192122958693564,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004904221057433412,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.2234057828783989,
|
|
"num_tokens": 24317557.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.23344349861145,
|
|
"epoch": 1.0196926032660902,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004904122069413105,
|
|
"loss": 4.8446,
|
|
"mean_token_accuracy": 0.23403415977954864,
|
|
"num_tokens": 24328874.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.362671613693237,
|
|
"epoch": 1.0201729106628241,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000490402303138048,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.21525761783123015,
|
|
"num_tokens": 24340918.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.290171432495117,
|
|
"epoch": 1.0206532180595582,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004903923943337836,
|
|
"loss": 4.9566,
|
|
"mean_token_accuracy": 0.2204394206404686,
|
|
"num_tokens": 24352642.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.225270366668701,
|
|
"epoch": 1.021133525456292,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004903824805287475,
|
|
"loss": 4.8615,
|
|
"mean_token_accuracy": 0.22953014224767684,
|
|
"num_tokens": 24364874.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.22464771270752,
|
|
"epoch": 1.021613832853026,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004903725617231696,
|
|
"loss": 4.9547,
|
|
"mean_token_accuracy": 0.22557385563850402,
|
|
"num_tokens": 24376566.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.261400747299194,
|
|
"epoch": 1.0220941402497599,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004903626379172805,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.23345146626234053,
|
|
"num_tokens": 24387283.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.336586952209473,
|
|
"epoch": 1.0225744476464937,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004903527091113102,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.21613558977842331,
|
|
"num_tokens": 24397970.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.252213621139527,
|
|
"epoch": 1.0230547550432276,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004903427753054897,
|
|
"loss": 4.9388,
|
|
"mean_token_accuracy": 0.2184563547372818,
|
|
"num_tokens": 24411223.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.291300868988037,
|
|
"epoch": 1.0235350624399615,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004903328365000492,
|
|
"loss": 4.9626,
|
|
"mean_token_accuracy": 0.22010653764009475,
|
|
"num_tokens": 24422117.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.272748899459839,
|
|
"epoch": 1.0240153698366954,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004903228926952199,
|
|
"loss": 4.9162,
|
|
"mean_token_accuracy": 0.22435684502124786,
|
|
"num_tokens": 24434142.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.26851863861084,
|
|
"epoch": 1.0244956772334295,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004903129438912322,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.2322851151227951,
|
|
"num_tokens": 24445295.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.244488048553467,
|
|
"epoch": 1.0249759846301634,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004903029900883174,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.23116625994443893,
|
|
"num_tokens": 24456092.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.240031433105469,
|
|
"epoch": 1.0254562920268973,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004902930312867063,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.21438848972320557,
|
|
"num_tokens": 24467653.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.302840900421143,
|
|
"epoch": 1.0259365994236311,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004902830674866306,
|
|
"loss": 4.9445,
|
|
"mean_token_accuracy": 0.2225495994091034,
|
|
"num_tokens": 24479164.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.234032011032104,
|
|
"epoch": 1.026416906820365,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004902730986883211,
|
|
"loss": 4.8289,
|
|
"mean_token_accuracy": 0.2315092533826828,
|
|
"num_tokens": 24489785.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.274800729751587,
|
|
"epoch": 1.026897214217099,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004902631248920096,
|
|
"loss": 4.9075,
|
|
"mean_token_accuracy": 0.2291500523686409,
|
|
"num_tokens": 24500158.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.3104212284088135,
|
|
"epoch": 1.0273775216138328,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004902531460979274,
|
|
"loss": 5.0214,
|
|
"mean_token_accuracy": 0.2151598334312439,
|
|
"num_tokens": 24512851.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.27370138168335,
|
|
"epoch": 1.0278578290105667,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004902431623063065,
|
|
"loss": 4.9658,
|
|
"mean_token_accuracy": 0.2228020891547203,
|
|
"num_tokens": 24524016.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.190254259109497,
|
|
"epoch": 1.0283381364073008,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004902331735173785,
|
|
"loss": 4.8372,
|
|
"mean_token_accuracy": 0.22253914773464203,
|
|
"num_tokens": 24536348.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.226603221893311,
|
|
"epoch": 1.0288184438040346,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004902231797313752,
|
|
"loss": 4.9206,
|
|
"mean_token_accuracy": 0.22179499566555022,
|
|
"num_tokens": 24548718.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.2236779689788815,
|
|
"epoch": 1.0292987512007685,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004902131809485288,
|
|
"loss": 4.8245,
|
|
"mean_token_accuracy": 0.23917854726314544,
|
|
"num_tokens": 24560567.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.2486608028411865,
|
|
"epoch": 1.0297790585975024,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004902031771690713,
|
|
"loss": 4.8685,
|
|
"mean_token_accuracy": 0.22624286711215974,
|
|
"num_tokens": 24572610.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.261171913146972,
|
|
"epoch": 1.0302593659942363,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004901931683932352,
|
|
"loss": 4.9067,
|
|
"mean_token_accuracy": 0.22562562972307204,
|
|
"num_tokens": 24584738.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.307566785812378,
|
|
"epoch": 1.0307396733909702,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004901831546212526,
|
|
"loss": 4.9623,
|
|
"mean_token_accuracy": 0.22423602491617203,
|
|
"num_tokens": 24596603.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.238448238372802,
|
|
"epoch": 1.031219980787704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004901731358533562,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.22502353191375732,
|
|
"num_tokens": 24607061.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.194182538986206,
|
|
"epoch": 1.031700288184438,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004901631120897785,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.22342673391103746,
|
|
"num_tokens": 24619177.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.192566633224487,
|
|
"epoch": 1.032180595581172,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004901530833307522,
|
|
"loss": 4.8309,
|
|
"mean_token_accuracy": 0.2271680235862732,
|
|
"num_tokens": 24631336.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.222535276412964,
|
|
"epoch": 1.032660902977906,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004901430495765103,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.23529910743236543,
|
|
"num_tokens": 24641743.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.248483800888062,
|
|
"epoch": 1.0331412103746398,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004901330108272855,
|
|
"loss": 4.8505,
|
|
"mean_token_accuracy": 0.22924480587244034,
|
|
"num_tokens": 24652318.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.2008123874664305,
|
|
"epoch": 1.0336215177713737,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004901229670833111,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.22193673402070999,
|
|
"num_tokens": 24664129.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.303077459335327,
|
|
"epoch": 1.0341018251681076,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004901129183448201,
|
|
"loss": 4.9418,
|
|
"mean_token_accuracy": 0.21791775077581405,
|
|
"num_tokens": 24674921.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.22287335395813,
|
|
"epoch": 1.0345821325648414,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004901028646120459,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.22063460499048232,
|
|
"num_tokens": 24686052.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.230008888244629,
|
|
"epoch": 1.0350624399615753,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000490092805885222,
|
|
"loss": 4.8845,
|
|
"mean_token_accuracy": 0.22437179386615752,
|
|
"num_tokens": 24698625.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.222806644439697,
|
|
"epoch": 1.0355427473583094,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004900827421645816,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.2338532879948616,
|
|
"num_tokens": 24709322.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.190197324752807,
|
|
"epoch": 1.0360230547550433,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004900726734503589,
|
|
"loss": 4.829,
|
|
"mean_token_accuracy": 0.22988853305578233,
|
|
"num_tokens": 24719512.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.211903429031372,
|
|
"epoch": 1.0365033621517772,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004900625997427872,
|
|
"loss": 4.8657,
|
|
"mean_token_accuracy": 0.22865433245897293,
|
|
"num_tokens": 24729947.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.167942047119141,
|
|
"epoch": 1.036983669548511,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004900525210421006,
|
|
"loss": 4.8633,
|
|
"mean_token_accuracy": 0.2347295880317688,
|
|
"num_tokens": 24741423.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.264333057403564,
|
|
"epoch": 1.037463976945245,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004900424373485329,
|
|
"loss": 4.8974,
|
|
"mean_token_accuracy": 0.22298837453126907,
|
|
"num_tokens": 24753403.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.3256793975830075,
|
|
"epoch": 1.0379442843419788,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004900323486623185,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.22211142927408217,
|
|
"num_tokens": 24763660.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.284540367126465,
|
|
"epoch": 1.0384245917387127,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004900222549836914,
|
|
"loss": 4.9145,
|
|
"mean_token_accuracy": 0.22663730531930923,
|
|
"num_tokens": 24775061.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.263784599304199,
|
|
"epoch": 1.0389048991354466,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000490012156312886,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.21866078823804855,
|
|
"num_tokens": 24785248.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.20162935256958,
|
|
"epoch": 1.0393852065321807,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004900020526501369,
|
|
"loss": 4.8024,
|
|
"mean_token_accuracy": 0.2338803619146347,
|
|
"num_tokens": 24797024.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.363827180862427,
|
|
"epoch": 1.0398655139289146,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004899919439956785,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.21360716521739959,
|
|
"num_tokens": 24808500.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.3585193157196045,
|
|
"epoch": 1.0403458213256485,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004899818303497455,
|
|
"loss": 5.0008,
|
|
"mean_token_accuracy": 0.21760460287332534,
|
|
"num_tokens": 24818805.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.300438928604126,
|
|
"epoch": 1.0408261287223823,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004899717117125728,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.2188895270228386,
|
|
"num_tokens": 24829247.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.183730602264404,
|
|
"epoch": 1.0413064361191162,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004899615880843953,
|
|
"loss": 4.8636,
|
|
"mean_token_accuracy": 0.2305304154753685,
|
|
"num_tokens": 24840139.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.299179220199585,
|
|
"epoch": 1.04178674351585,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004899514594654481,
|
|
"loss": 4.9729,
|
|
"mean_token_accuracy": 0.21626512110233306,
|
|
"num_tokens": 24851734.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.278581333160401,
|
|
"epoch": 1.042267050912584,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004899413258559662,
|
|
"loss": 4.9303,
|
|
"mean_token_accuracy": 0.2247483789920807,
|
|
"num_tokens": 24863424.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.249710273742676,
|
|
"epoch": 1.0427473583093179,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004899311872561849,
|
|
"loss": 4.9471,
|
|
"mean_token_accuracy": 0.22249127179384232,
|
|
"num_tokens": 24875086.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.219966316223145,
|
|
"epoch": 1.043227665706052,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004899210436663398,
|
|
"loss": 4.8892,
|
|
"mean_token_accuracy": 0.22666616588830948,
|
|
"num_tokens": 24888408.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.19952621459961,
|
|
"epoch": 1.0437079731027858,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004899108950866661,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.23532017916440964,
|
|
"num_tokens": 24900357.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.25680947303772,
|
|
"epoch": 1.0441882804995197,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004899007415173997,
|
|
"loss": 4.9164,
|
|
"mean_token_accuracy": 0.22540972828865052,
|
|
"num_tokens": 24910790.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.246063089370727,
|
|
"epoch": 1.0446685878962536,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004898905829587762,
|
|
"loss": 4.8961,
|
|
"mean_token_accuracy": 0.22390599101781844,
|
|
"num_tokens": 24922124.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.181507158279419,
|
|
"epoch": 1.0451488952929875,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004898804194110313,
|
|
"loss": 4.8044,
|
|
"mean_token_accuracy": 0.2386482760310173,
|
|
"num_tokens": 24933591.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.237972736358643,
|
|
"epoch": 1.0456292026897214,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004898702508744012,
|
|
"loss": 4.8277,
|
|
"mean_token_accuracy": 0.2282120779156685,
|
|
"num_tokens": 24944708.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.1982612133026125,
|
|
"epoch": 1.0461095100864553,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004898600773491221,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.23107136338949202,
|
|
"num_tokens": 24955966.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.274428415298462,
|
|
"epoch": 1.0465898174831891,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004898498988354297,
|
|
"loss": 4.9062,
|
|
"mean_token_accuracy": 0.22845429033041,
|
|
"num_tokens": 24967292.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.278221225738525,
|
|
"epoch": 1.0470701248799232,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004898397153335608,
|
|
"loss": 4.9649,
|
|
"mean_token_accuracy": 0.22311765402555467,
|
|
"num_tokens": 24977407.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.357841444015503,
|
|
"epoch": 1.0475504322766571,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004898295268437517,
|
|
"loss": 5.0209,
|
|
"mean_token_accuracy": 0.22102802693843843,
|
|
"num_tokens": 24988804.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.270384407043457,
|
|
"epoch": 1.048030739673391,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004898193333662388,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.2215827852487564,
|
|
"num_tokens": 25000297.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.260179901123047,
|
|
"epoch": 1.0485110470701249,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004898091349012588,
|
|
"loss": 4.8837,
|
|
"mean_token_accuracy": 0.228547041118145,
|
|
"num_tokens": 25012135.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.176730966567993,
|
|
"epoch": 1.0489913544668588,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004897989314490486,
|
|
"loss": 4.869,
|
|
"mean_token_accuracy": 0.2326307326555252,
|
|
"num_tokens": 25023572.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.258727645874023,
|
|
"epoch": 1.0494716618635926,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004897887230098451,
|
|
"loss": 4.9229,
|
|
"mean_token_accuracy": 0.22730273008346558,
|
|
"num_tokens": 25035015.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.2376354217529295,
|
|
"epoch": 1.0499519692603265,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004897785095838852,
|
|
"loss": 4.8785,
|
|
"mean_token_accuracy": 0.2296762079000473,
|
|
"num_tokens": 25045931.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.290501642227173,
|
|
"epoch": 1.0504322766570606,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004897682911714061,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.22674432545900344,
|
|
"num_tokens": 25056767.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.188278007507324,
|
|
"epoch": 1.0509125840537945,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000489758067772645,
|
|
"loss": 4.8756,
|
|
"mean_token_accuracy": 0.2343797877430916,
|
|
"num_tokens": 25068731.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.278168725967407,
|
|
"epoch": 1.0513928914505284,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004897478393878392,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.22133503407239913,
|
|
"num_tokens": 25081268.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.189077520370484,
|
|
"epoch": 1.0518731988472623,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004897376060172264,
|
|
"loss": 4.8395,
|
|
"mean_token_accuracy": 0.23504106402397157,
|
|
"num_tokens": 25093105.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.204558372497559,
|
|
"epoch": 1.0523535062439962,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004897273676610438,
|
|
"loss": 4.8555,
|
|
"mean_token_accuracy": 0.2320477247238159,
|
|
"num_tokens": 25103766.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.262063694000244,
|
|
"epoch": 1.05283381364073,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004897171243195295,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.22442621737718582,
|
|
"num_tokens": 25115675.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.246082544326782,
|
|
"epoch": 1.053314121037464,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000489706875992921,
|
|
"loss": 4.8513,
|
|
"mean_token_accuracy": 0.22830186188220977,
|
|
"num_tokens": 25127907.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.251580810546875,
|
|
"epoch": 1.0537944284341978,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004896966226814565,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.2297168716788292,
|
|
"num_tokens": 25139675.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.2940576553344725,
|
|
"epoch": 1.054274735830932,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004896863643853739,
|
|
"loss": 4.995,
|
|
"mean_token_accuracy": 0.22323969900608062,
|
|
"num_tokens": 25150960.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.31819224357605,
|
|
"epoch": 1.0547550432276658,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004896761011049114,
|
|
"loss": 4.9801,
|
|
"mean_token_accuracy": 0.22037239670753478,
|
|
"num_tokens": 25163676.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.2066856861114506,
|
|
"epoch": 1.0552353506243997,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004896658328403074,
|
|
"loss": 4.906,
|
|
"mean_token_accuracy": 0.22275177836418153,
|
|
"num_tokens": 25174317.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.205246210098267,
|
|
"epoch": 1.0557156580211335,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004896555595918001,
|
|
"loss": 4.9207,
|
|
"mean_token_accuracy": 0.22735002189874648,
|
|
"num_tokens": 25186585.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.289089775085449,
|
|
"epoch": 1.0561959654178674,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004896452813596281,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.2227770507335663,
|
|
"num_tokens": 25199014.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.314134168624878,
|
|
"epoch": 1.0566762728146013,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004896349981440301,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.21744184345006942,
|
|
"num_tokens": 25210544.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.251679992675781,
|
|
"epoch": 1.0571565802113352,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004896247099452447,
|
|
"loss": 4.9118,
|
|
"mean_token_accuracy": 0.23253205567598342,
|
|
"num_tokens": 25221583.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.29381537437439,
|
|
"epoch": 1.057636887608069,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004896144167635108,
|
|
"loss": 4.8912,
|
|
"mean_token_accuracy": 0.23377034217119216,
|
|
"num_tokens": 25231724.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.290861701965332,
|
|
"epoch": 1.0581171950048032,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004896041185990675,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.22005500942468642,
|
|
"num_tokens": 25243021.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.2868507385253904,
|
|
"epoch": 1.058597502401537,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004895938154521538,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.22316930890083314,
|
|
"num_tokens": 25254189.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.305389165878296,
|
|
"epoch": 1.059077809798271,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004895835073230089,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.226844684779644,
|
|
"num_tokens": 25265556.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.1989898681640625,
|
|
"epoch": 1.0595581171950048,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004895731942118722,
|
|
"loss": 4.8287,
|
|
"mean_token_accuracy": 0.22370388060808183,
|
|
"num_tokens": 25276789.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.278147459030151,
|
|
"epoch": 1.0600384245917387,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004895628761189829,
|
|
"loss": 4.9954,
|
|
"mean_token_accuracy": 0.21584384590387345,
|
|
"num_tokens": 25288505.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.210616397857666,
|
|
"epoch": 1.0605187319884726,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004895525530445809,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.23931586146354675,
|
|
"num_tokens": 25301490.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.234191465377807,
|
|
"epoch": 1.0609990393852065,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004895422249889057,
|
|
"loss": 4.9357,
|
|
"mean_token_accuracy": 0.22233884483575822,
|
|
"num_tokens": 25313303.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.342378234863281,
|
|
"epoch": 1.0614793467819403,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004895318919521971,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.21327349841594695,
|
|
"num_tokens": 25324379.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.2233179092407225,
|
|
"epoch": 1.0619596541786744,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004895215539346949,
|
|
"loss": 4.8428,
|
|
"mean_token_accuracy": 0.22978077530860902,
|
|
"num_tokens": 25335834.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.226367568969726,
|
|
"epoch": 1.0624399615754083,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004895112109366393,
|
|
"loss": 4.9035,
|
|
"mean_token_accuracy": 0.22513044476509095,
|
|
"num_tokens": 25347591.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.234711599349976,
|
|
"epoch": 1.0629202689721422,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004895008629582703,
|
|
"loss": 4.8848,
|
|
"mean_token_accuracy": 0.224392306804657,
|
|
"num_tokens": 25358483.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.222918605804443,
|
|
"epoch": 1.063400576368876,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004894905099998283,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.22331410497426987,
|
|
"num_tokens": 25369434.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.255740737915039,
|
|
"epoch": 1.06388088376561,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004894801520615535,
|
|
"loss": 4.8988,
|
|
"mean_token_accuracy": 0.2277396261692047,
|
|
"num_tokens": 25381007.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.2619866847991945,
|
|
"epoch": 1.0643611911623438,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004894697891436863,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.22221987098455429,
|
|
"num_tokens": 25393809.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.287129640579224,
|
|
"epoch": 1.0648414985590777,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004894594212464676,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.22959400564432145,
|
|
"num_tokens": 25404967.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.2617950439453125,
|
|
"epoch": 1.0653218059558118,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004894490483701381,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.2364131838083267,
|
|
"num_tokens": 25417092.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.294598245620728,
|
|
"epoch": 1.0658021133525457,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004894386705149382,
|
|
"loss": 4.9763,
|
|
"mean_token_accuracy": 0.21499801874160768,
|
|
"num_tokens": 25428425.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.234216403961182,
|
|
"epoch": 1.0662824207492796,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004894282876811093,
|
|
"loss": 4.8071,
|
|
"mean_token_accuracy": 0.2386219844222069,
|
|
"num_tokens": 25440134.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.215627288818359,
|
|
"epoch": 1.0667627281460135,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004894178998688921,
|
|
"loss": 4.8922,
|
|
"mean_token_accuracy": 0.22861060202121736,
|
|
"num_tokens": 25452222.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.251913261413574,
|
|
"epoch": 1.0672430355427474,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004894075070785281,
|
|
"loss": 4.9409,
|
|
"mean_token_accuracy": 0.2259517028927803,
|
|
"num_tokens": 25464541.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.331733274459839,
|
|
"epoch": 1.0677233429394812,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004893971093102585,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.21849103271961212,
|
|
"num_tokens": 25476537.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.355682849884033,
|
|
"epoch": 1.0682036503362151,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004893867065643245,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.21579207926988603,
|
|
"num_tokens": 25486737.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.243563938140869,
|
|
"epoch": 1.068683957732949,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004893762988409678,
|
|
"loss": 4.9235,
|
|
"mean_token_accuracy": 0.22094615548849106,
|
|
"num_tokens": 25497278.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.267231082916259,
|
|
"epoch": 1.069164265129683,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004893658861404301,
|
|
"loss": 4.8872,
|
|
"mean_token_accuracy": 0.22320848256349562,
|
|
"num_tokens": 25508716.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.318556690216065,
|
|
"epoch": 1.069644572526417,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004893554684629529,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.21895406544208526,
|
|
"num_tokens": 25519439.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.219156265258789,
|
|
"epoch": 1.0701248799231509,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004893450458087784,
|
|
"loss": 4.7853,
|
|
"mean_token_accuracy": 0.2339973643422127,
|
|
"num_tokens": 25530911.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.298265838623047,
|
|
"epoch": 1.0706051873198847,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004893346181781483,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.2111084207892418,
|
|
"num_tokens": 25542452.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.267034435272217,
|
|
"epoch": 1.0710854947166186,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004893241855713048,
|
|
"loss": 4.9304,
|
|
"mean_token_accuracy": 0.21265296787023544,
|
|
"num_tokens": 25554105.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.371748208999634,
|
|
"epoch": 1.0715658021133525,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004893137479884903,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.22250245362520218,
|
|
"num_tokens": 25564806.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.215398979187012,
|
|
"epoch": 1.0720461095100864,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004893033054299468,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.22798677235841752,
|
|
"num_tokens": 25575664.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.232505559921265,
|
|
"epoch": 1.0725264169068203,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000489292857895917,
|
|
"loss": 4.8181,
|
|
"mean_token_accuracy": 0.23367771804332732,
|
|
"num_tokens": 25586227.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.2712836265563965,
|
|
"epoch": 1.0730067243035544,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004892824053866432,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.2226012423634529,
|
|
"num_tokens": 25597475.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.205050897598267,
|
|
"epoch": 1.0734870317002883,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004892719479023683,
|
|
"loss": 4.8628,
|
|
"mean_token_accuracy": 0.23120887726545333,
|
|
"num_tokens": 25608098.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.3060407638549805,
|
|
"epoch": 1.0739673390970221,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000489261485443335,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.21792962700128554,
|
|
"num_tokens": 25620053.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.287705707550049,
|
|
"epoch": 1.074447646493756,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004892510180097863,
|
|
"loss": 4.9003,
|
|
"mean_token_accuracy": 0.22067270129919053,
|
|
"num_tokens": 25630534.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.293157434463501,
|
|
"epoch": 1.07492795389049,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004892405456019651,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.2270430624485016,
|
|
"num_tokens": 25641413.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.20750880241394,
|
|
"epoch": 1.0754082612872238,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004892300682201147,
|
|
"loss": 4.8632,
|
|
"mean_token_accuracy": 0.23234288692474364,
|
|
"num_tokens": 25652081.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.2989599227905275,
|
|
"epoch": 1.0758885686839577,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004892195858644782,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.22862013876438142,
|
|
"num_tokens": 25664282.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.295254325866699,
|
|
"epoch": 1.0763688760806915,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000489209098535299,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.21955449730157853,
|
|
"num_tokens": 25675310.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.364900398254394,
|
|
"epoch": 1.0768491834774256,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004891986062328205,
|
|
"loss": 5.0151,
|
|
"mean_token_accuracy": 0.22300100177526475,
|
|
"num_tokens": 25686895.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.261716699600219,
|
|
"epoch": 1.0773294908741595,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004891881089572865,
|
|
"loss": 4.8142,
|
|
"mean_token_accuracy": 0.22860780954360962,
|
|
"num_tokens": 25697778.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.217953538894653,
|
|
"epoch": 1.0778097982708934,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004891776067089406,
|
|
"loss": 4.9539,
|
|
"mean_token_accuracy": 0.2138178676366806,
|
|
"num_tokens": 25708602.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.242786598205567,
|
|
"epoch": 1.0782901056676273,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004891670994880266,
|
|
"loss": 4.855,
|
|
"mean_token_accuracy": 0.22719742059707643,
|
|
"num_tokens": 25719671.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.341251707077026,
|
|
"epoch": 1.0787704130643612,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004891565872947888,
|
|
"loss": 5.018,
|
|
"mean_token_accuracy": 0.2188740625977516,
|
|
"num_tokens": 25731797.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.228974342346191,
|
|
"epoch": 1.079250720461095,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004891460701294706,
|
|
"loss": 4.8879,
|
|
"mean_token_accuracy": 0.23104191869497298,
|
|
"num_tokens": 25743984.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.178681135177612,
|
|
"epoch": 1.079731027857829,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004891355479923167,
|
|
"loss": 4.8753,
|
|
"mean_token_accuracy": 0.2300044924020767,
|
|
"num_tokens": 25755252.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.184259462356567,
|
|
"epoch": 1.080211335254563,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004891250208835712,
|
|
"loss": 4.8056,
|
|
"mean_token_accuracy": 0.2283560663461685,
|
|
"num_tokens": 25765715.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.317605352401733,
|
|
"epoch": 1.080691642651297,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004891144888034784,
|
|
"loss": 4.9321,
|
|
"mean_token_accuracy": 0.22156814038753508,
|
|
"num_tokens": 25777866.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.257466983795166,
|
|
"epoch": 1.0811719500480308,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004891039517522832,
|
|
"loss": 4.8463,
|
|
"mean_token_accuracy": 0.22886780947446822,
|
|
"num_tokens": 25791199.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.160863161087036,
|
|
"epoch": 1.0816522574447647,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004890934097302299,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.2412295773625374,
|
|
"num_tokens": 25802979.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.1385103225708,
|
|
"epoch": 1.0821325648414986,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004890828627375632,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.22546306103467942,
|
|
"num_tokens": 25814696.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.28546257019043,
|
|
"epoch": 1.0826128722382324,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004890723107745283,
|
|
"loss": 4.9374,
|
|
"mean_token_accuracy": 0.21339473724365235,
|
|
"num_tokens": 25825376.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.291554737091064,
|
|
"epoch": 1.0830931796349663,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004890617538413699,
|
|
"loss": 4.8958,
|
|
"mean_token_accuracy": 0.22395792454481125,
|
|
"num_tokens": 25835491.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.279152345657349,
|
|
"epoch": 1.0835734870317002,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004890511919383333,
|
|
"loss": 4.9562,
|
|
"mean_token_accuracy": 0.2216746136546135,
|
|
"num_tokens": 25848154.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.224534606933593,
|
|
"epoch": 1.084053794428434,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004890406250656636,
|
|
"loss": 4.9256,
|
|
"mean_token_accuracy": 0.22763658910989762,
|
|
"num_tokens": 25859471.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.227497577667236,
|
|
"epoch": 1.0845341018251682,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004890300532236062,
|
|
"loss": 4.8515,
|
|
"mean_token_accuracy": 0.22896967828273773,
|
|
"num_tokens": 25869460.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.255751848220825,
|
|
"epoch": 1.085014409221902,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004890194764124064,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.23003373444080352,
|
|
"num_tokens": 25881892.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.284740686416626,
|
|
"epoch": 1.085494716618636,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004890088946323099,
|
|
"loss": 4.9876,
|
|
"mean_token_accuracy": 0.21472073644399642,
|
|
"num_tokens": 25893774.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.202382373809814,
|
|
"epoch": 1.0859750240153698,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004889983078835623,
|
|
"loss": 4.805,
|
|
"mean_token_accuracy": 0.23075173795223236,
|
|
"num_tokens": 25904758.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.222729444503784,
|
|
"epoch": 1.0864553314121037,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004889877161664096,
|
|
"loss": 4.9119,
|
|
"mean_token_accuracy": 0.2221290424466133,
|
|
"num_tokens": 25917013.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.358620548248291,
|
|
"epoch": 1.0869356388088376,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004889771194810974,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.22622882276773454,
|
|
"num_tokens": 25927780.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.213243627548218,
|
|
"epoch": 1.0874159462055715,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004889665178278719,
|
|
"loss": 4.8567,
|
|
"mean_token_accuracy": 0.232503642141819,
|
|
"num_tokens": 25939339.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.239845132827758,
|
|
"epoch": 1.0878962536023056,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004889559112069792,
|
|
"loss": 4.8635,
|
|
"mean_token_accuracy": 0.22841319888830186,
|
|
"num_tokens": 25950440.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.264793491363525,
|
|
"epoch": 1.0883765609990395,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004889452996186657,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.2217724710702896,
|
|
"num_tokens": 25962849.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.277474021911621,
|
|
"epoch": 1.0888568683957733,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004889346830631774,
|
|
"loss": 4.9357,
|
|
"mean_token_accuracy": 0.2179882138967514,
|
|
"num_tokens": 25973616.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.24298791885376,
|
|
"epoch": 1.0893371757925072,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000488924061540761,
|
|
"loss": 4.8344,
|
|
"mean_token_accuracy": 0.23404917269945144,
|
|
"num_tokens": 25984727.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.262585687637329,
|
|
"epoch": 1.089817483189241,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004889134350516633,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.232413649559021,
|
|
"num_tokens": 25996431.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.283836746215821,
|
|
"epoch": 1.090297790585975,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004889028035961308,
|
|
"loss": 4.8988,
|
|
"mean_token_accuracy": 0.22559195756912231,
|
|
"num_tokens": 26008936.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.338031148910522,
|
|
"epoch": 1.0907780979827089,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004888921671744103,
|
|
"loss": 4.9659,
|
|
"mean_token_accuracy": 0.21589563488960267,
|
|
"num_tokens": 26019308.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.268791151046753,
|
|
"epoch": 1.0912584053794427,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004888815257867488,
|
|
"loss": 4.8543,
|
|
"mean_token_accuracy": 0.23384385108947753,
|
|
"num_tokens": 26030705.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.261903476715088,
|
|
"epoch": 1.0917387127761768,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004888708794333934,
|
|
"loss": 4.8808,
|
|
"mean_token_accuracy": 0.2257483884692192,
|
|
"num_tokens": 26042759.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.264266586303711,
|
|
"epoch": 1.0922190201729107,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004888602281145913,
|
|
"loss": 4.9282,
|
|
"mean_token_accuracy": 0.2276270568370819,
|
|
"num_tokens": 26054719.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.243171834945679,
|
|
"epoch": 1.0926993275696446,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004888495718305897,
|
|
"loss": 4.9446,
|
|
"mean_token_accuracy": 0.2174038767814636,
|
|
"num_tokens": 26065765.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.152737092971802,
|
|
"epoch": 1.0931796349663785,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000488838910581636,
|
|
"loss": 4.8333,
|
|
"mean_token_accuracy": 0.228248430788517,
|
|
"num_tokens": 26077719.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.312730216979981,
|
|
"epoch": 1.0936599423631124,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004888282443679777,
|
|
"loss": 4.9773,
|
|
"mean_token_accuracy": 0.21503383815288543,
|
|
"num_tokens": 26089924.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.389603757858277,
|
|
"epoch": 1.0941402497598463,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004888175731898627,
|
|
"loss": 5.0433,
|
|
"mean_token_accuracy": 0.21609580963850022,
|
|
"num_tokens": 26100312.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.243638277053833,
|
|
"epoch": 1.0946205571565801,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004888068970475384,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.22016473710536957,
|
|
"num_tokens": 26111932.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.270091867446899,
|
|
"epoch": 1.0951008645533142,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004887962159412529,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.2285095825791359,
|
|
"num_tokens": 26123989.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.328083324432373,
|
|
"epoch": 1.0955811719500481,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004887855298712541,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.2235036998987198,
|
|
"num_tokens": 26135589.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.1671537399292,
|
|
"epoch": 1.096061479346782,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048877483883779,
|
|
"loss": 4.8558,
|
|
"mean_token_accuracy": 0.22971481829881668,
|
|
"num_tokens": 26147069.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.232102155685425,
|
|
"epoch": 1.0965417867435159,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004887641428411091,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.22444375306367875,
|
|
"num_tokens": 26159331.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.292403268814087,
|
|
"epoch": 1.0970220941402498,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004887534418814595,
|
|
"loss": 4.9111,
|
|
"mean_token_accuracy": 0.22335042506456376,
|
|
"num_tokens": 26169863.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.2318507671356205,
|
|
"epoch": 1.0975024015369836,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004887427359590897,
|
|
"loss": 4.8905,
|
|
"mean_token_accuracy": 0.22035748213529588,
|
|
"num_tokens": 26182888.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.2402245044708256,
|
|
"epoch": 1.0979827089337175,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004887320250742482,
|
|
"loss": 4.8945,
|
|
"mean_token_accuracy": 0.23108669072389604,
|
|
"num_tokens": 26194979.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.206297588348389,
|
|
"epoch": 1.0984630163304514,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004887213092271838,
|
|
"loss": 4.9064,
|
|
"mean_token_accuracy": 0.23503292351961136,
|
|
"num_tokens": 26207309.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.232964611053466,
|
|
"epoch": 1.0989433237271853,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004887105884181451,
|
|
"loss": 4.9328,
|
|
"mean_token_accuracy": 0.22167981863021852,
|
|
"num_tokens": 26219231.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.325558423995972,
|
|
"epoch": 1.0994236311239194,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004886998626473813,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.22034439891576768,
|
|
"num_tokens": 26229355.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.289998388290405,
|
|
"epoch": 1.0999039385206533,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004886891319151411,
|
|
"loss": 4.8502,
|
|
"mean_token_accuracy": 0.23249689042568206,
|
|
"num_tokens": 26239069.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.289576053619385,
|
|
"epoch": 1.1003842459173871,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004886783962216738,
|
|
"loss": 4.991,
|
|
"mean_token_accuracy": 0.22010688334703446,
|
|
"num_tokens": 26250403.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.30884370803833,
|
|
"epoch": 1.100864553314121,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004886676555672287,
|
|
"loss": 4.8782,
|
|
"mean_token_accuracy": 0.2255308985710144,
|
|
"num_tokens": 26262926.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.352726078033447,
|
|
"epoch": 1.101344860710855,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004886569099520551,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.21332792341709136,
|
|
"num_tokens": 26274030.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.215978574752808,
|
|
"epoch": 1.1018251681075888,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004886461593764024,
|
|
"loss": 4.9111,
|
|
"mean_token_accuracy": 0.23133158385753633,
|
|
"num_tokens": 26284799.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.126020431518555,
|
|
"epoch": 1.1023054755043227,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004886354038405204,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.2370050370693207,
|
|
"num_tokens": 26295154.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.291110277175903,
|
|
"epoch": 1.1027857829010568,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004886246433446586,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.21937124729156493,
|
|
"num_tokens": 26306181.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.3846197605133055,
|
|
"epoch": 1.1032660902977907,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004886138778890669,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.21463223397731782,
|
|
"num_tokens": 26318674.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.335513257980347,
|
|
"epoch": 1.1037463976945245,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004886031074739953,
|
|
"loss": 4.9417,
|
|
"mean_token_accuracy": 0.2109510198235512,
|
|
"num_tokens": 26330257.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.264688491821289,
|
|
"epoch": 1.1042267050912584,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004885923320996938,
|
|
"loss": 4.8871,
|
|
"mean_token_accuracy": 0.2251171126961708,
|
|
"num_tokens": 26342035.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.261469888687134,
|
|
"epoch": 1.1047070124879923,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004885815517664127,
|
|
"loss": 4.9231,
|
|
"mean_token_accuracy": 0.2246149256825447,
|
|
"num_tokens": 26352703.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.302320957183838,
|
|
"epoch": 1.1051873198847262,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000488570766474402,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.22746830582618713,
|
|
"num_tokens": 26362324.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.297534322738647,
|
|
"epoch": 1.10566762728146,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004885599762239124,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.21410372108221054,
|
|
"num_tokens": 26373540.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.244863557815552,
|
|
"epoch": 1.106147934678194,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004885491810151943,
|
|
"loss": 4.9329,
|
|
"mean_token_accuracy": 0.22253721952438354,
|
|
"num_tokens": 26384259.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.199947309494019,
|
|
"epoch": 1.106628242074928,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004885383808484982,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.22784973531961442,
|
|
"num_tokens": 26395193.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.213193607330322,
|
|
"epoch": 1.107108549471662,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004885275757240751,
|
|
"loss": 4.84,
|
|
"mean_token_accuracy": 0.22606273591518403,
|
|
"num_tokens": 26408556.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.235076475143432,
|
|
"epoch": 1.1075888568683958,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004885167656421757,
|
|
"loss": 4.9185,
|
|
"mean_token_accuracy": 0.2248816281557083,
|
|
"num_tokens": 26420066.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.230745935440064,
|
|
"epoch": 1.1080691642651297,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000488505950603051,
|
|
"loss": 4.8903,
|
|
"mean_token_accuracy": 0.2255407989025116,
|
|
"num_tokens": 26432533.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.232820320129394,
|
|
"epoch": 1.1085494716618636,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000488495130606952,
|
|
"loss": 4.8753,
|
|
"mean_token_accuracy": 0.22794847041368485,
|
|
"num_tokens": 26443878.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.286282634735107,
|
|
"epoch": 1.1090297790585975,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004884843056541302,
|
|
"loss": 4.9013,
|
|
"mean_token_accuracy": 0.2211151286959648,
|
|
"num_tokens": 26455111.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.258453893661499,
|
|
"epoch": 1.1095100864553313,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004884734757448367,
|
|
"loss": 4.9243,
|
|
"mean_token_accuracy": 0.22411396354436874,
|
|
"num_tokens": 26466577.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.239039278030395,
|
|
"epoch": 1.1099903938520654,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000488462640879323,
|
|
"loss": 4.8448,
|
|
"mean_token_accuracy": 0.22907019406557083,
|
|
"num_tokens": 26479637.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.212899684906006,
|
|
"epoch": 1.1104707012487993,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004884518010578405,
|
|
"loss": 4.8755,
|
|
"mean_token_accuracy": 0.2268904745578766,
|
|
"num_tokens": 26489923.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.283234930038452,
|
|
"epoch": 1.1109510086455332,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004884409562806411,
|
|
"loss": 4.9852,
|
|
"mean_token_accuracy": 0.2160591796040535,
|
|
"num_tokens": 26501236.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.244903326034546,
|
|
"epoch": 1.111431316042267,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004884301065479765,
|
|
"loss": 4.8444,
|
|
"mean_token_accuracy": 0.22698431164026261,
|
|
"num_tokens": 26511509.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.16862301826477,
|
|
"epoch": 1.111911623439001,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004884192518600986,
|
|
"loss": 4.8086,
|
|
"mean_token_accuracy": 0.23667658120393753,
|
|
"num_tokens": 26520931.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.181065940856934,
|
|
"epoch": 1.1123919308357348,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004884083922172593,
|
|
"loss": 4.8313,
|
|
"mean_token_accuracy": 0.23801038414239883,
|
|
"num_tokens": 26531333.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.203880310058594,
|
|
"epoch": 1.1128722382324687,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004883975276197108,
|
|
"loss": 4.9011,
|
|
"mean_token_accuracy": 0.2308025598526001,
|
|
"num_tokens": 26543696.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.258868551254272,
|
|
"epoch": 1.1133525456292026,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004883866580677055,
|
|
"loss": 4.8515,
|
|
"mean_token_accuracy": 0.23199667185544967,
|
|
"num_tokens": 26556292.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.273058319091797,
|
|
"epoch": 1.1138328530259365,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004883757835614956,
|
|
"loss": 4.8834,
|
|
"mean_token_accuracy": 0.2188606083393097,
|
|
"num_tokens": 26568023.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.1909692764282225,
|
|
"epoch": 1.1143131604226706,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004883649041013335,
|
|
"loss": 4.881,
|
|
"mean_token_accuracy": 0.22893589735031128,
|
|
"num_tokens": 26579469.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.339939546585083,
|
|
"epoch": 1.1147934678194045,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000488354019687472,
|
|
"loss": 4.9226,
|
|
"mean_token_accuracy": 0.2237112268805504,
|
|
"num_tokens": 26591592.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.281352519989014,
|
|
"epoch": 1.1152737752161384,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004883431303201636,
|
|
"loss": 4.8901,
|
|
"mean_token_accuracy": 0.2264537200331688,
|
|
"num_tokens": 26604075.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.163708019256592,
|
|
"epoch": 1.1157540826128722,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004883322359996613,
|
|
"loss": 4.8209,
|
|
"mean_token_accuracy": 0.23240430355072023,
|
|
"num_tokens": 26616448.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.236646556854248,
|
|
"epoch": 1.1162343900096061,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004883213367262179,
|
|
"loss": 4.9014,
|
|
"mean_token_accuracy": 0.23349083364009857,
|
|
"num_tokens": 26628749.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.25415997505188,
|
|
"epoch": 1.11671469740634,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004883104325000866,
|
|
"loss": 4.853,
|
|
"mean_token_accuracy": 0.23319512754678726,
|
|
"num_tokens": 26640163.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.266146850585938,
|
|
"epoch": 1.1171950048030739,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004882995233215203,
|
|
"loss": 4.9055,
|
|
"mean_token_accuracy": 0.2249453768134117,
|
|
"num_tokens": 26650729.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.220187854766846,
|
|
"epoch": 1.117675312199808,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004882886091907726,
|
|
"loss": 4.9242,
|
|
"mean_token_accuracy": 0.22713975459337235,
|
|
"num_tokens": 26661995.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.230469131469727,
|
|
"epoch": 1.1181556195965419,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048827769010809666,
|
|
"loss": 4.8524,
|
|
"mean_token_accuracy": 0.23094468265771867,
|
|
"num_tokens": 26673224.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.265944719314575,
|
|
"epoch": 1.1186359269932757,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048826676607374606,
|
|
"loss": 4.8795,
|
|
"mean_token_accuracy": 0.21974054276943206,
|
|
"num_tokens": 26686331.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.346266746520996,
|
|
"epoch": 1.1191162343900096,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048825583708797434,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.22869265377521514,
|
|
"num_tokens": 26696816.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.233740711212159,
|
|
"epoch": 1.1195965417867435,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004882449031510354,
|
|
"loss": 4.884,
|
|
"mean_token_accuracy": 0.2303701013326645,
|
|
"num_tokens": 26708126.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.319062805175781,
|
|
"epoch": 1.1200768491834774,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000488233964263183,
|
|
"loss": 4.9947,
|
|
"mean_token_accuracy": 0.2256132334470749,
|
|
"num_tokens": 26718951.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.2943941116333,
|
|
"epoch": 1.1205571565802113,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048822302042467115,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.21830258518457413,
|
|
"num_tokens": 26730550.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.1769775390625,
|
|
"epoch": 1.1210374639769451,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004882120716357539,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.23301633447408676,
|
|
"num_tokens": 26741485.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.151652574539185,
|
|
"epoch": 1.1215177713736793,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004882011178966854,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.23126445859670638,
|
|
"num_tokens": 26753947.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.2239611625671385,
|
|
"epoch": 1.1219980787704131,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004881901592077201,
|
|
"loss": 4.8507,
|
|
"mean_token_accuracy": 0.2377290904521942,
|
|
"num_tokens": 26764921.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.252098941802979,
|
|
"epoch": 1.122478386167147,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004881791955691123,
|
|
"loss": 4.8273,
|
|
"mean_token_accuracy": 0.2292026996612549,
|
|
"num_tokens": 26777384.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.255926132202148,
|
|
"epoch": 1.122958693563881,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048816822698111655,
|
|
"loss": 4.9438,
|
|
"mean_token_accuracy": 0.22267890870571136,
|
|
"num_tokens": 26789916.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.233464622497559,
|
|
"epoch": 1.1234390009606148,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048815725344398766,
|
|
"loss": 4.8444,
|
|
"mean_token_accuracy": 0.22951712608337402,
|
|
"num_tokens": 26801167.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.3065758228302,
|
|
"epoch": 1.1239193083573487,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048814627495798017,
|
|
"loss": 4.9508,
|
|
"mean_token_accuracy": 0.22306582778692247,
|
|
"num_tokens": 26813235.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.308640480041504,
|
|
"epoch": 1.1243996157540825,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004881352915233492,
|
|
"loss": 4.9403,
|
|
"mean_token_accuracy": 0.2272568464279175,
|
|
"num_tokens": 26824758.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.2614795684814455,
|
|
"epoch": 1.1248799231508164,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048812430314034956,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.22273175567388534,
|
|
"num_tokens": 26836877.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.163290023803711,
|
|
"epoch": 1.1253602305475505,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004881133098092365,
|
|
"loss": 4.7673,
|
|
"mean_token_accuracy": 0.23946761190891266,
|
|
"num_tokens": 26848394.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.1863288402557375,
|
|
"epoch": 1.1258405379442844,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004881023115302652,
|
|
"loss": 4.8954,
|
|
"mean_token_accuracy": 0.22795673161745073,
|
|
"num_tokens": 26859064.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.326487922668457,
|
|
"epoch": 1.1263208453410183,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000488091308303691,
|
|
"loss": 5.0177,
|
|
"mean_token_accuracy": 0.20961594432592393,
|
|
"num_tokens": 26870401.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.293287754058838,
|
|
"epoch": 1.1268011527377522,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004880803001297694,
|
|
"loss": 4.8975,
|
|
"mean_token_accuracy": 0.22611468732357026,
|
|
"num_tokens": 26881767.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.207429265975952,
|
|
"epoch": 1.127281460134486,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004880692870087559,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.22658294290304185,
|
|
"num_tokens": 26892854.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.326664876937866,
|
|
"epoch": 1.12776176753122,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048805826894090626,
|
|
"loss": 4.9742,
|
|
"mean_token_accuracy": 0.2178993284702301,
|
|
"num_tokens": 26905079.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.351021432876587,
|
|
"epoch": 1.1282420749279538,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048804724592647626,
|
|
"loss": 5.006,
|
|
"mean_token_accuracy": 0.21630996465682983,
|
|
"num_tokens": 26915640.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.237456655502319,
|
|
"epoch": 1.1287223823246877,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004880362179657218,
|
|
"loss": 4.8761,
|
|
"mean_token_accuracy": 0.2279524624347687,
|
|
"num_tokens": 26927039.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.234236383438111,
|
|
"epoch": 1.1292026897214218,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048802518505889904,
|
|
"loss": 4.8594,
|
|
"mean_token_accuracy": 0.2271624818444252,
|
|
"num_tokens": 26939368.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.237351179122925,
|
|
"epoch": 1.1296829971181557,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048801414720626404,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.20983987897634507,
|
|
"num_tokens": 26952051.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.223706579208374,
|
|
"epoch": 1.1301633045148896,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048800310440807294,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.22461564540863038,
|
|
"num_tokens": 26963680.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.188236951828003,
|
|
"epoch": 1.1306436119116234,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004879920566645823,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.23430795967578888,
|
|
"num_tokens": 26973899.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.226254081726074,
|
|
"epoch": 1.1311239193083573,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004879810039760486,
|
|
"loss": 4.9116,
|
|
"mean_token_accuracy": 0.2183161422610283,
|
|
"num_tokens": 26985692.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.268548631668091,
|
|
"epoch": 1.1316042267050912,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004879699463427284,
|
|
"loss": 4.8469,
|
|
"mean_token_accuracy": 0.23019198179244996,
|
|
"num_tokens": 26996354.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.292991399765015,
|
|
"epoch": 1.132084534101825,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004879588837648785,
|
|
"loss": 4.8849,
|
|
"mean_token_accuracy": 0.22216602563858032,
|
|
"num_tokens": 27007925.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.18213119506836,
|
|
"epoch": 1.1325648414985592,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048794781624275554,
|
|
"loss": 4.8468,
|
|
"mean_token_accuracy": 0.23503227680921554,
|
|
"num_tokens": 27019222.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.159797048568725,
|
|
"epoch": 1.133045148895293,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048793674377661664,
|
|
"loss": 4.8414,
|
|
"mean_token_accuracy": 0.23339744210243224,
|
|
"num_tokens": 27029973.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.3194386005401615,
|
|
"epoch": 1.133525456292027,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048792566636671886,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.22451780438423158,
|
|
"num_tokens": 27042002.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.263101720809937,
|
|
"epoch": 1.1340057636887608,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004879145840133194,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.23220417648553848,
|
|
"num_tokens": 27052770.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.26320161819458,
|
|
"epoch": 1.1344860710854947,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004879034967166755,
|
|
"loss": 4.9325,
|
|
"mean_token_accuracy": 0.22670873254537582,
|
|
"num_tokens": 27063375.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.202679204940796,
|
|
"epoch": 1.1349663784822286,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004878924044770446,
|
|
"loss": 4.8754,
|
|
"mean_token_accuracy": 0.2284083142876625,
|
|
"num_tokens": 27075908.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.247083282470703,
|
|
"epoch": 1.1354466858789625,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004878813072946843,
|
|
"loss": 4.9198,
|
|
"mean_token_accuracy": 0.22700789868831633,
|
|
"num_tokens": 27087590.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.254173612594604,
|
|
"epoch": 1.1359269932756964,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048787020516985203,
|
|
"loss": 4.8397,
|
|
"mean_token_accuracy": 0.23286038488149643,
|
|
"num_tokens": 27098076.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.217121601104736,
|
|
"epoch": 1.1364073006724302,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048785909810280576,
|
|
"loss": 4.8469,
|
|
"mean_token_accuracy": 0.2364824041724205,
|
|
"num_tokens": 27109851.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.219685983657837,
|
|
"epoch": 1.1368876080691643,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004878479860938033,
|
|
"loss": 4.8028,
|
|
"mean_token_accuracy": 0.23431069999933243,
|
|
"num_tokens": 27121288.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.230327129364014,
|
|
"epoch": 1.1373679154658982,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048783686914310266,
|
|
"loss": 4.8922,
|
|
"mean_token_accuracy": 0.2252708852291107,
|
|
"num_tokens": 27133877.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.105851125717163,
|
|
"epoch": 1.137848222862632,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004878257472509619,
|
|
"loss": 4.7175,
|
|
"mean_token_accuracy": 0.24098218977451324,
|
|
"num_tokens": 27145616.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.155728530883789,
|
|
"epoch": 1.138328530259366,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004878146204176392,
|
|
"loss": 4.851,
|
|
"mean_token_accuracy": 0.22704108208417892,
|
|
"num_tokens": 27157182.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.282539892196655,
|
|
"epoch": 1.1388088376560999,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000487803488643393,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.2355527713894844,
|
|
"num_tokens": 27167609.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.316936397552491,
|
|
"epoch": 1.1392891450528337,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048779235192848166,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.2221071556210518,
|
|
"num_tokens": 27180043.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.167005109786987,
|
|
"epoch": 1.1397694524495678,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004877812102731638,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.23531264215707778,
|
|
"num_tokens": 27191870.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.255460786819458,
|
|
"epoch": 1.1402497598463017,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048777006367769804,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.22846313267946244,
|
|
"num_tokens": 27203291.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.2547942161560055,
|
|
"epoch": 1.1407300672430356,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004877589121423432,
|
|
"loss": 4.9081,
|
|
"mean_token_accuracy": 0.22856287509202958,
|
|
"num_tokens": 27214607.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.221647453308106,
|
|
"epoch": 1.1412103746397695,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004877477556673582,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.23272537738084792,
|
|
"num_tokens": 27224658.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.19312801361084,
|
|
"epoch": 1.1416906820365034,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000487736594253002,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.22440452128648758,
|
|
"num_tokens": 27235306.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.280982494354248,
|
|
"epoch": 1.1421709894332372,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048772542789953384,
|
|
"loss": 4.8838,
|
|
"mean_token_accuracy": 0.22780535817146302,
|
|
"num_tokens": 27246679.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.3368322372436525,
|
|
"epoch": 1.1426512968299711,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048771425660721284,
|
|
"loss": 4.9311,
|
|
"mean_token_accuracy": 0.21749826222658158,
|
|
"num_tokens": 27257799.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.220373678207397,
|
|
"epoch": 1.143131604226705,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048770308037629853,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.22285577952861785,
|
|
"num_tokens": 27268651.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.212119436264038,
|
|
"epoch": 1.143611911623439,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004876918992070502,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.2291291117668152,
|
|
"num_tokens": 27280655.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.309642267227173,
|
|
"epoch": 1.144092219020173,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004876807130997276,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.22083690464496614,
|
|
"num_tokens": 27292664.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.260783433914185,
|
|
"epoch": 1.1445725264169069,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004876695220545903,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.22563991397619249,
|
|
"num_tokens": 27306143.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.235976982116699,
|
|
"epoch": 1.1450528338136408,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048765832607189824,
|
|
"loss": 4.818,
|
|
"mean_token_accuracy": 0.23104555159807205,
|
|
"num_tokens": 27316926.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.339642763137817,
|
|
"epoch": 1.1455331412103746,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048764712515191136,
|
|
"loss": 4.94,
|
|
"mean_token_accuracy": 0.2277303606271744,
|
|
"num_tokens": 27327472.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.31283745765686,
|
|
"epoch": 1.1460134486071085,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048763591929488966,
|
|
"loss": 4.9223,
|
|
"mean_token_accuracy": 0.2293119341135025,
|
|
"num_tokens": 27338388.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.228753757476807,
|
|
"epoch": 1.1464937560038424,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004876247085010933,
|
|
"loss": 4.8377,
|
|
"mean_token_accuracy": 0.22910197377204894,
|
|
"num_tokens": 27349879.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.22907018661499,
|
|
"epoch": 1.1469740634005763,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048761349277078253,
|
|
"loss": 4.8428,
|
|
"mean_token_accuracy": 0.23338637948036195,
|
|
"num_tokens": 27361226.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.237310695648193,
|
|
"epoch": 1.1474543707973104,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048760227210421775,
|
|
"loss": 4.82,
|
|
"mean_token_accuracy": 0.23125654309988022,
|
|
"num_tokens": 27373512.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.171060943603516,
|
|
"epoch": 1.1479346781940443,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004875910465016596,
|
|
"loss": 4.8741,
|
|
"mean_token_accuracy": 0.23239589631557464,
|
|
"num_tokens": 27384950.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.350432443618774,
|
|
"epoch": 1.1484149855907781,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004875798159633686,
|
|
"loss": 4.9365,
|
|
"mean_token_accuracy": 0.22146188467741013,
|
|
"num_tokens": 27395877.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.278548526763916,
|
|
"epoch": 1.148895292987512,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004875685804896055,
|
|
"loss": 4.9718,
|
|
"mean_token_accuracy": 0.22865064293146134,
|
|
"num_tokens": 27407783.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.2086889266967775,
|
|
"epoch": 1.149375600384246,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004875573400806312,
|
|
"loss": 4.862,
|
|
"mean_token_accuracy": 0.22700949013233185,
|
|
"num_tokens": 27420598.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.262592887878418,
|
|
"epoch": 1.1498559077809798,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048754609473670654,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.22339701354503633,
|
|
"num_tokens": 27431961.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.240012741088867,
|
|
"epoch": 1.1503362151777137,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004875348444580927,
|
|
"loss": 4.7994,
|
|
"mean_token_accuracy": 0.23154822289943694,
|
|
"num_tokens": 27444010.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.26583571434021,
|
|
"epoch": 1.1508165225744476,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000487523589245051,
|
|
"loss": 4.8698,
|
|
"mean_token_accuracy": 0.2296842008829117,
|
|
"num_tokens": 27455576.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.228506135940552,
|
|
"epoch": 1.1512968299711814,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004875123290978425,
|
|
"loss": 4.8921,
|
|
"mean_token_accuracy": 0.22496830374002458,
|
|
"num_tokens": 27468957.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.23967170715332,
|
|
"epoch": 1.1517771373679155,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048750106401672876,
|
|
"loss": 4.8838,
|
|
"mean_token_accuracy": 0.2303827092051506,
|
|
"num_tokens": 27479992.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.316565418243409,
|
|
"epoch": 1.1522574447646494,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048748979400197134,
|
|
"loss": 4.9501,
|
|
"mean_token_accuracy": 0.22238598614931107,
|
|
"num_tokens": 27490878.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.193116998672485,
|
|
"epoch": 1.1527377521613833,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048747851905383183,
|
|
"loss": 4.7884,
|
|
"mean_token_accuracy": 0.2362989977002144,
|
|
"num_tokens": 27502009.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.1527377521613833,
|
|
"eval_entropy": 5.038512420910036,
|
|
"eval_loss": 4.977294921875,
|
|
"eval_mean_token_accuracy": 0.23085267144799784,
|
|
"eval_num_tokens": 27502009.0,
|
|
"eval_runtime": 20.4494,
|
|
"eval_samples_per_second": 1604.696,
|
|
"eval_steps_per_second": 200.593,
|
|
"step": 12000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 104090,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 6235717956802560.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|