374d25c765
Model: fpadovani/hin-deva-10mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2881844380403458,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 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
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 104090,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1562945946255360.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|