84f5e6da74
Model: fpadovani/hin-deva-10mb-after-ppt-Dp-100mb-ckpt500_seed455 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2881844380403458,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.227891731262207,
|
|
"epoch": 0.0004803073967339097,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.7116,
|
|
"mean_token_accuracy": 0.12639277800917625,
|
|
"num_tokens": 10821.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.243266201019287,
|
|
"epoch": 0.0009606147934678194,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.6481,
|
|
"mean_token_accuracy": 0.12706964686512948,
|
|
"num_tokens": 21838.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.221618175506592,
|
|
"epoch": 0.001440922190201729,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.7012,
|
|
"mean_token_accuracy": 0.12022195979952813,
|
|
"num_tokens": 33483.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.250268363952637,
|
|
"epoch": 0.0019212295869356388,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.7805,
|
|
"mean_token_accuracy": 0.12316789031028748,
|
|
"num_tokens": 45150.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.207002735137939,
|
|
"epoch": 0.0024015369836695487,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.6792,
|
|
"mean_token_accuracy": 0.11827812790870666,
|
|
"num_tokens": 55862.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.20290994644165,
|
|
"epoch": 0.002881844380403458,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.8032,
|
|
"mean_token_accuracy": 0.12267392575740814,
|
|
"num_tokens": 66766.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.144218921661377,
|
|
"epoch": 0.0033621517771373678,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.5389,
|
|
"mean_token_accuracy": 0.13368295580148698,
|
|
"num_tokens": 77012.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.158500909805298,
|
|
"epoch": 0.0038424591738712775,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.7614,
|
|
"mean_token_accuracy": 0.12391667440533638,
|
|
"num_tokens": 89034.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.117870426177978,
|
|
"epoch": 0.004322766570605188,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.6403,
|
|
"mean_token_accuracy": 0.12876288816332818,
|
|
"num_tokens": 100341.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.142163562774658,
|
|
"epoch": 0.004803073967339097,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.6103,
|
|
"mean_token_accuracy": 0.12874003127217293,
|
|
"num_tokens": 111997.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.155911827087403,
|
|
"epoch": 0.005283381364073006,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.6601,
|
|
"mean_token_accuracy": 0.1270666964352131,
|
|
"num_tokens": 123705.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.139102792739868,
|
|
"epoch": 0.005763688760806916,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.5978,
|
|
"mean_token_accuracy": 0.13043108433485032,
|
|
"num_tokens": 134091.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.0543046474456785,
|
|
"epoch": 0.006243996157540826,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.7086,
|
|
"mean_token_accuracy": 0.1285567693412304,
|
|
"num_tokens": 145731.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.078891086578369,
|
|
"epoch": 0.0067243035542747355,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.6207,
|
|
"mean_token_accuracy": 0.1347151793539524,
|
|
"num_tokens": 156979.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.112874746322632,
|
|
"epoch": 0.007204610951008645,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.6131,
|
|
"mean_token_accuracy": 0.1301887921988964,
|
|
"num_tokens": 167021.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.118173456192016,
|
|
"epoch": 0.007684918347742555,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.6258,
|
|
"mean_token_accuracy": 0.1291635274887085,
|
|
"num_tokens": 179269.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.088387060165405,
|
|
"epoch": 0.008165225744476465,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.6018,
|
|
"mean_token_accuracy": 0.13118657022714614,
|
|
"num_tokens": 190328.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.0138716220855715,
|
|
"epoch": 0.008645533141210375,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.4816,
|
|
"mean_token_accuracy": 0.13541511297225953,
|
|
"num_tokens": 201522.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.05142731666565,
|
|
"epoch": 0.009125840537944284,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.5891,
|
|
"mean_token_accuracy": 0.13322217017412186,
|
|
"num_tokens": 212963.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.128700685501099,
|
|
"epoch": 0.009606147934678195,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.8104,
|
|
"mean_token_accuracy": 0.11415100917220115,
|
|
"num_tokens": 224446.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.176903247833252,
|
|
"epoch": 0.010086455331412104,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.6453,
|
|
"mean_token_accuracy": 0.13400980979204177,
|
|
"num_tokens": 235334.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.227095699310302,
|
|
"epoch": 0.010566762728146013,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.712,
|
|
"mean_token_accuracy": 0.11989362239837646,
|
|
"num_tokens": 247024.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.07423882484436,
|
|
"epoch": 0.011047070124879923,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.6255,
|
|
"mean_token_accuracy": 0.1259888932108879,
|
|
"num_tokens": 258354.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 6.989333200454712,
|
|
"epoch": 0.011527377521613832,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.6793,
|
|
"mean_token_accuracy": 0.12834338322281838,
|
|
"num_tokens": 271202.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.106875991821289,
|
|
"epoch": 0.012007684918347743,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.6777,
|
|
"mean_token_accuracy": 0.12354658171534538,
|
|
"num_tokens": 282405.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.062946128845215,
|
|
"epoch": 0.012487992315081652,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.6353,
|
|
"mean_token_accuracy": 0.12684911414980887,
|
|
"num_tokens": 294211.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.124184036254883,
|
|
"epoch": 0.012968299711815562,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.6772,
|
|
"mean_token_accuracy": 0.11896728649735451,
|
|
"num_tokens": 305420.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.085195732116699,
|
|
"epoch": 0.013448607108549471,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.5818,
|
|
"mean_token_accuracy": 0.1283716782927513,
|
|
"num_tokens": 316430.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.063561677932739,
|
|
"epoch": 0.013928914505283382,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.6082,
|
|
"mean_token_accuracy": 0.13248678371310235,
|
|
"num_tokens": 328406.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.072713708877563,
|
|
"epoch": 0.01440922190201729,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.5784,
|
|
"mean_token_accuracy": 0.13202109262347222,
|
|
"num_tokens": 339051.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.053579998016358,
|
|
"epoch": 0.014889529298751201,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.5612,
|
|
"mean_token_accuracy": 0.13085259720683098,
|
|
"num_tokens": 350308.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.130250310897827,
|
|
"epoch": 0.01536983669548511,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.5937,
|
|
"mean_token_accuracy": 0.12741485759615898,
|
|
"num_tokens": 362159.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.091244792938232,
|
|
"epoch": 0.01585014409221902,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.6467,
|
|
"mean_token_accuracy": 0.12987646758556365,
|
|
"num_tokens": 375157.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.02424430847168,
|
|
"epoch": 0.01633045148895293,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.4838,
|
|
"mean_token_accuracy": 0.1344938911497593,
|
|
"num_tokens": 387318.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 6.999642038345337,
|
|
"epoch": 0.01681075888568684,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.5663,
|
|
"mean_token_accuracy": 0.13669942170381547,
|
|
"num_tokens": 398933.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.019154787063599,
|
|
"epoch": 0.01729106628242075,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.5536,
|
|
"mean_token_accuracy": 0.1361289769411087,
|
|
"num_tokens": 410460.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.02680025100708,
|
|
"epoch": 0.01777137367915466,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.5731,
|
|
"mean_token_accuracy": 0.13559282198548317,
|
|
"num_tokens": 421894.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.089911031723022,
|
|
"epoch": 0.01825168107588857,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.6183,
|
|
"mean_token_accuracy": 0.12840212360024453,
|
|
"num_tokens": 432976.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.079966688156128,
|
|
"epoch": 0.018731988472622477,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.6682,
|
|
"mean_token_accuracy": 0.13189114406704902,
|
|
"num_tokens": 444859.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.1056396007537845,
|
|
"epoch": 0.01921229586935639,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.582,
|
|
"mean_token_accuracy": 0.1382762998342514,
|
|
"num_tokens": 456508.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.003632974624634,
|
|
"epoch": 0.0196926032660903,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.6044,
|
|
"mean_token_accuracy": 0.12909564301371573,
|
|
"num_tokens": 469064.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.1269261837005615,
|
|
"epoch": 0.020172910662824207,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.5451,
|
|
"mean_token_accuracy": 0.13477757573127747,
|
|
"num_tokens": 480743.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.030986785888672,
|
|
"epoch": 0.020653218059558116,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.5874,
|
|
"mean_token_accuracy": 0.13419262766838075,
|
|
"num_tokens": 493378.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.058184576034546,
|
|
"epoch": 0.021133525456292025,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.5813,
|
|
"mean_token_accuracy": 0.12972840294241905,
|
|
"num_tokens": 505641.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.053190851211548,
|
|
"epoch": 0.021613832853025938,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.6461,
|
|
"mean_token_accuracy": 0.1300312601029873,
|
|
"num_tokens": 517783.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.0220287322998045,
|
|
"epoch": 0.022094140249759846,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.4915,
|
|
"mean_token_accuracy": 0.1375163048505783,
|
|
"num_tokens": 528407.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.136337566375732,
|
|
"epoch": 0.022574447646493755,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.6536,
|
|
"mean_token_accuracy": 0.13205716013908386,
|
|
"num_tokens": 539974.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 6.980577278137207,
|
|
"epoch": 0.023054755043227664,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.4986,
|
|
"mean_token_accuracy": 0.13339756950736045,
|
|
"num_tokens": 551127.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 6.999716663360596,
|
|
"epoch": 0.023535062439961577,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.5402,
|
|
"mean_token_accuracy": 0.13888919427990915,
|
|
"num_tokens": 561980.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.093811845779419,
|
|
"epoch": 0.024015369836695485,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.587,
|
|
"mean_token_accuracy": 0.1365107201039791,
|
|
"num_tokens": 573840.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 6.957034015655518,
|
|
"epoch": 0.024495677233429394,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.5359,
|
|
"mean_token_accuracy": 0.13650909885764123,
|
|
"num_tokens": 585110.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 6.963628101348877,
|
|
"epoch": 0.024975984630163303,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.4158,
|
|
"mean_token_accuracy": 0.13956196010112762,
|
|
"num_tokens": 596902.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.003592777252197,
|
|
"epoch": 0.025456292026897216,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.6084,
|
|
"mean_token_accuracy": 0.13234634920954705,
|
|
"num_tokens": 608738.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.03656964302063,
|
|
"epoch": 0.025936599423631124,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.527,
|
|
"mean_token_accuracy": 0.13383049592375756,
|
|
"num_tokens": 621078.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.060523128509521,
|
|
"epoch": 0.026416906820365033,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.6203,
|
|
"mean_token_accuracy": 0.13373518884181976,
|
|
"num_tokens": 632333.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 6.994757175445557,
|
|
"epoch": 0.026897214217098942,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.4486,
|
|
"mean_token_accuracy": 0.13340532183647155,
|
|
"num_tokens": 644474.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 6.9266692161560055,
|
|
"epoch": 0.027377521613832854,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.5437,
|
|
"mean_token_accuracy": 0.13545908331871032,
|
|
"num_tokens": 655608.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.043833541870117,
|
|
"epoch": 0.027857829010566763,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.5544,
|
|
"mean_token_accuracy": 0.13327746465802193,
|
|
"num_tokens": 667371.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.025187253952026,
|
|
"epoch": 0.028338136407300672,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.5713,
|
|
"mean_token_accuracy": 0.12935664281249046,
|
|
"num_tokens": 679152.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.939578628540039,
|
|
"epoch": 0.02881844380403458,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.4936,
|
|
"mean_token_accuracy": 0.1386971041560173,
|
|
"num_tokens": 690359.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.998729133605957,
|
|
"epoch": 0.029298751200768493,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.4871,
|
|
"mean_token_accuracy": 0.13214991092681885,
|
|
"num_tokens": 701819.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.02758297920227,
|
|
"epoch": 0.029779058597502402,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.5132,
|
|
"mean_token_accuracy": 0.13222344741225242,
|
|
"num_tokens": 711048.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.924132680892944,
|
|
"epoch": 0.03025936599423631,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.4272,
|
|
"mean_token_accuracy": 0.14279273226857186,
|
|
"num_tokens": 721399.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 6.975829458236694,
|
|
"epoch": 0.03073967339097022,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.4467,
|
|
"mean_token_accuracy": 0.14665683656930922,
|
|
"num_tokens": 732144.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 6.8750978946685795,
|
|
"epoch": 0.03121998078770413,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.439,
|
|
"mean_token_accuracy": 0.13812113925814629,
|
|
"num_tokens": 743962.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.067961740493774,
|
|
"epoch": 0.03170028818443804,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.5958,
|
|
"mean_token_accuracy": 0.13596020564436911,
|
|
"num_tokens": 755641.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 6.8925072193145756,
|
|
"epoch": 0.03218059558117195,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.4498,
|
|
"mean_token_accuracy": 0.14140594229102135,
|
|
"num_tokens": 766798.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.949503374099732,
|
|
"epoch": 0.03266090297790586,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.5306,
|
|
"mean_token_accuracy": 0.1402709811925888,
|
|
"num_tokens": 778097.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.915549230575562,
|
|
"epoch": 0.03314121037463977,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.458,
|
|
"mean_token_accuracy": 0.14018686711788178,
|
|
"num_tokens": 789775.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.000381278991699,
|
|
"epoch": 0.03362151777137368,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.5205,
|
|
"mean_token_accuracy": 0.134874277561903,
|
|
"num_tokens": 800155.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.96249566078186,
|
|
"epoch": 0.034101825168107586,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.5313,
|
|
"mean_token_accuracy": 0.13899640440940858,
|
|
"num_tokens": 811213.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.033797121047973,
|
|
"epoch": 0.0345821325648415,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.5259,
|
|
"mean_token_accuracy": 0.12905024066567422,
|
|
"num_tokens": 822832.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 6.906823778152466,
|
|
"epoch": 0.03506243996157541,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.5062,
|
|
"mean_token_accuracy": 0.13670841753482818,
|
|
"num_tokens": 834824.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 6.941941642761231,
|
|
"epoch": 0.03554274735830932,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.5528,
|
|
"mean_token_accuracy": 0.1321589730679989,
|
|
"num_tokens": 846969.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.095604753494262,
|
|
"epoch": 0.03602305475504323,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.6279,
|
|
"mean_token_accuracy": 0.12456684783101082,
|
|
"num_tokens": 859271.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.995700550079346,
|
|
"epoch": 0.03650336215177714,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.5165,
|
|
"mean_token_accuracy": 0.13592087998986244,
|
|
"num_tokens": 869754.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.893608093261719,
|
|
"epoch": 0.036983669548511046,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.465,
|
|
"mean_token_accuracy": 0.1396843321621418,
|
|
"num_tokens": 880519.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 6.874870157241821,
|
|
"epoch": 0.037463976945244955,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.4312,
|
|
"mean_token_accuracy": 0.13749386817216874,
|
|
"num_tokens": 890765.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.942132997512817,
|
|
"epoch": 0.037944284341978864,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.4429,
|
|
"mean_token_accuracy": 0.1352140188217163,
|
|
"num_tokens": 901717.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.989188814163208,
|
|
"epoch": 0.03842459173871278,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.527,
|
|
"mean_token_accuracy": 0.13658951371908187,
|
|
"num_tokens": 913334.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.002504158020019,
|
|
"epoch": 0.03890489913544669,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.5367,
|
|
"mean_token_accuracy": 0.13638701885938645,
|
|
"num_tokens": 924753.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.9172460556030275,
|
|
"epoch": 0.0393852065321806,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.4758,
|
|
"mean_token_accuracy": 0.13802975565195083,
|
|
"num_tokens": 935692.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.995597171783447,
|
|
"epoch": 0.039865513928914506,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.5407,
|
|
"mean_token_accuracy": 0.13431550040841103,
|
|
"num_tokens": 947902.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.920178604125977,
|
|
"epoch": 0.040345821325648415,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.5029,
|
|
"mean_token_accuracy": 0.14091430008411407,
|
|
"num_tokens": 959437.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.818842840194702,
|
|
"epoch": 0.040826128722382324,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.325,
|
|
"mean_token_accuracy": 0.14433388337492942,
|
|
"num_tokens": 970191.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.920823621749878,
|
|
"epoch": 0.04130643611911623,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.4527,
|
|
"mean_token_accuracy": 0.13763294816017152,
|
|
"num_tokens": 981811.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.8866934299469,
|
|
"epoch": 0.04178674351585014,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.5686,
|
|
"mean_token_accuracy": 0.13008847534656526,
|
|
"num_tokens": 994034.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.982378435134888,
|
|
"epoch": 0.04226705091258405,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.5232,
|
|
"mean_token_accuracy": 0.1318051353096962,
|
|
"num_tokens": 1005506.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.865565204620362,
|
|
"epoch": 0.042747358309317966,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.4801,
|
|
"mean_token_accuracy": 0.12741892486810685,
|
|
"num_tokens": 1017103.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.912385082244873,
|
|
"epoch": 0.043227665706051875,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.5681,
|
|
"mean_token_accuracy": 0.13292499631643295,
|
|
"num_tokens": 1029606.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.989826202392578,
|
|
"epoch": 0.043707973102785784,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.5356,
|
|
"mean_token_accuracy": 0.12916895225644112,
|
|
"num_tokens": 1041899.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.912504577636719,
|
|
"epoch": 0.04418828049951969,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.4378,
|
|
"mean_token_accuracy": 0.14383152276277542,
|
|
"num_tokens": 1053577.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.913370943069458,
|
|
"epoch": 0.0446685878962536,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.4929,
|
|
"mean_token_accuracy": 0.13895317614078523,
|
|
"num_tokens": 1065541.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.934657716751099,
|
|
"epoch": 0.04514889529298751,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.4416,
|
|
"mean_token_accuracy": 0.137308207154274,
|
|
"num_tokens": 1076138.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.862859153747559,
|
|
"epoch": 0.04562920268972142,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.5041,
|
|
"mean_token_accuracy": 0.13841527476906776,
|
|
"num_tokens": 1087620.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.862703037261963,
|
|
"epoch": 0.04610951008645533,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.3943,
|
|
"mean_token_accuracy": 0.142742570489645,
|
|
"num_tokens": 1099493.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.874656057357788,
|
|
"epoch": 0.046589817483189244,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.4578,
|
|
"mean_token_accuracy": 0.13684100583195685,
|
|
"num_tokens": 1110559.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.856756639480591,
|
|
"epoch": 0.04707012487992315,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.4327,
|
|
"mean_token_accuracy": 0.13060991689562798,
|
|
"num_tokens": 1121051.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.838518524169922,
|
|
"epoch": 0.04755043227665706,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.3931,
|
|
"mean_token_accuracy": 0.14155778735876084,
|
|
"num_tokens": 1132305.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.8174115180969235,
|
|
"epoch": 0.04803073967339097,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.4016,
|
|
"mean_token_accuracy": 0.1437266267836094,
|
|
"num_tokens": 1142979.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.89087495803833,
|
|
"epoch": 0.04851104707012488,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.411,
|
|
"mean_token_accuracy": 0.1463697850704193,
|
|
"num_tokens": 1153889.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.875075244903565,
|
|
"epoch": 0.04899135446685879,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.4292,
|
|
"mean_token_accuracy": 0.13723334297537804,
|
|
"num_tokens": 1166030.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.966767072677612,
|
|
"epoch": 0.0494716618635927,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.6142,
|
|
"mean_token_accuracy": 0.1286202512681484,
|
|
"num_tokens": 1177545.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.8341772079467775,
|
|
"epoch": 0.049951969260326606,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.4176,
|
|
"mean_token_accuracy": 0.1422701135277748,
|
|
"num_tokens": 1188944.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.770974016189575,
|
|
"epoch": 0.05043227665706052,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.4883,
|
|
"mean_token_accuracy": 0.13371295407414435,
|
|
"num_tokens": 1199517.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.8674828052520756,
|
|
"epoch": 0.05091258405379443,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.4133,
|
|
"mean_token_accuracy": 0.13357224985957145,
|
|
"num_tokens": 1211536.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.761517667770386,
|
|
"epoch": 0.05139289145052834,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.14621875584125518,
|
|
"num_tokens": 1224159.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.808783054351807,
|
|
"epoch": 0.05187319884726225,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.4059,
|
|
"mean_token_accuracy": 0.14924411177635194,
|
|
"num_tokens": 1235226.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.741241598129273,
|
|
"epoch": 0.05235350624399616,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.3238,
|
|
"mean_token_accuracy": 0.1498336486518383,
|
|
"num_tokens": 1245862.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.785985374450684,
|
|
"epoch": 0.052833813640730067,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.3347,
|
|
"mean_token_accuracy": 0.14524050951004028,
|
|
"num_tokens": 1257512.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.758766126632691,
|
|
"epoch": 0.053314121037463975,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.4508,
|
|
"mean_token_accuracy": 0.13895726203918457,
|
|
"num_tokens": 1269317.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.7143903255462645,
|
|
"epoch": 0.053794428434197884,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.3328,
|
|
"mean_token_accuracy": 0.13423674702644348,
|
|
"num_tokens": 1281878.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.754738235473633,
|
|
"epoch": 0.05427473583093179,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.3475,
|
|
"mean_token_accuracy": 0.14375446885824203,
|
|
"num_tokens": 1293178.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.717558813095093,
|
|
"epoch": 0.05475504322766571,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.3412,
|
|
"mean_token_accuracy": 0.14117253720760345,
|
|
"num_tokens": 1304969.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.835646152496338,
|
|
"epoch": 0.05523535062439962,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.3772,
|
|
"mean_token_accuracy": 0.1407823756337166,
|
|
"num_tokens": 1317301.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.74691801071167,
|
|
"epoch": 0.05571565802113353,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.363,
|
|
"mean_token_accuracy": 0.1412644602358341,
|
|
"num_tokens": 1327688.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.738905239105224,
|
|
"epoch": 0.056195965417867436,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.3153,
|
|
"mean_token_accuracy": 0.13932914063334464,
|
|
"num_tokens": 1338750.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.783087301254272,
|
|
"epoch": 0.056676272814601344,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.46,
|
|
"mean_token_accuracy": 0.13216890692710875,
|
|
"num_tokens": 1350899.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.860762405395508,
|
|
"epoch": 0.05715658021133525,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.3102,
|
|
"mean_token_accuracy": 0.14398529529571533,
|
|
"num_tokens": 1363184.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.663176107406616,
|
|
"epoch": 0.05763688760806916,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.2972,
|
|
"mean_token_accuracy": 0.1460181102156639,
|
|
"num_tokens": 1374192.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.650053453445435,
|
|
"epoch": 0.05811719500480307,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.327,
|
|
"mean_token_accuracy": 0.14458349198102952,
|
|
"num_tokens": 1384888.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.893434619903564,
|
|
"epoch": 0.05859750240153699,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.4132,
|
|
"mean_token_accuracy": 0.14370108693838118,
|
|
"num_tokens": 1395139.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.52349820137024,
|
|
"epoch": 0.059077809798270896,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.2221,
|
|
"mean_token_accuracy": 0.14337074458599092,
|
|
"num_tokens": 1407219.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.780193042755127,
|
|
"epoch": 0.059558117195004805,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.14062620624899863,
|
|
"num_tokens": 1418917.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.667874813079834,
|
|
"epoch": 0.060038424591738714,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.3008,
|
|
"mean_token_accuracy": 0.14137485176324843,
|
|
"num_tokens": 1430792.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.647404527664184,
|
|
"epoch": 0.06051873198847262,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.3181,
|
|
"mean_token_accuracy": 0.14391812160611153,
|
|
"num_tokens": 1442825.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.798049831390381,
|
|
"epoch": 0.06099903938520653,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.4112,
|
|
"mean_token_accuracy": 0.14235697835683822,
|
|
"num_tokens": 1454078.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.718965768814087,
|
|
"epoch": 0.06147934678194044,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.3395,
|
|
"mean_token_accuracy": 0.14023290127515792,
|
|
"num_tokens": 1465164.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.73060793876648,
|
|
"epoch": 0.06195965417867435,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.14530042111873626,
|
|
"num_tokens": 1476813.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.674618053436279,
|
|
"epoch": 0.06243996157540826,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.3688,
|
|
"mean_token_accuracy": 0.14241051748394967,
|
|
"num_tokens": 1488547.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.862033843994141,
|
|
"epoch": 0.06292026897214217,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.366,
|
|
"mean_token_accuracy": 0.13735537007451057,
|
|
"num_tokens": 1500714.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.628754711151123,
|
|
"epoch": 0.06340057636887608,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.3567,
|
|
"mean_token_accuracy": 0.1390194483101368,
|
|
"num_tokens": 1512212.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.675348711013794,
|
|
"epoch": 0.06388088376560999,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.3282,
|
|
"mean_token_accuracy": 0.1440582610666752,
|
|
"num_tokens": 1523610.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.641611242294312,
|
|
"epoch": 0.0643611911623439,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.2809,
|
|
"mean_token_accuracy": 0.1418041206896305,
|
|
"num_tokens": 1535543.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.843907260894776,
|
|
"epoch": 0.06484149855907781,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.506,
|
|
"mean_token_accuracy": 0.13386593759059906,
|
|
"num_tokens": 1547183.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.615519618988037,
|
|
"epoch": 0.06532180595581172,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.2559,
|
|
"mean_token_accuracy": 0.14652696400880813,
|
|
"num_tokens": 1559265.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.744142818450928,
|
|
"epoch": 0.06580211335254563,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.2822,
|
|
"mean_token_accuracy": 0.141647919267416,
|
|
"num_tokens": 1569774.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.5239664077758786,
|
|
"epoch": 0.06628242074927954,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.14382586181163787,
|
|
"num_tokens": 1579408.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.593590784072876,
|
|
"epoch": 0.06676272814601344,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.2627,
|
|
"mean_token_accuracy": 0.1462230786681175,
|
|
"num_tokens": 1591849.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.682480907440185,
|
|
"epoch": 0.06724303554274735,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.3308,
|
|
"mean_token_accuracy": 0.14186072424054147,
|
|
"num_tokens": 1603269.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.747530841827393,
|
|
"epoch": 0.06772334293948126,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.3629,
|
|
"mean_token_accuracy": 0.1359557554125786,
|
|
"num_tokens": 1613639.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.725496768951416,
|
|
"epoch": 0.06820365033621517,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.3855,
|
|
"mean_token_accuracy": 0.13674816712737084,
|
|
"num_tokens": 1625393.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.64970293045044,
|
|
"epoch": 0.0686839577329491,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.2215,
|
|
"mean_token_accuracy": 0.14604979306459426,
|
|
"num_tokens": 1636355.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.653625917434693,
|
|
"epoch": 0.069164265129683,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.2686,
|
|
"mean_token_accuracy": 0.14605910181999207,
|
|
"num_tokens": 1646157.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.578489160537719,
|
|
"epoch": 0.06964457252641691,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.2573,
|
|
"mean_token_accuracy": 0.13798193708062173,
|
|
"num_tokens": 1657827.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.660614967346191,
|
|
"epoch": 0.07012487992315082,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.3351,
|
|
"mean_token_accuracy": 0.14547959491610526,
|
|
"num_tokens": 1669023.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.684601163864135,
|
|
"epoch": 0.07060518731988473,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.2928,
|
|
"mean_token_accuracy": 0.14130547940731047,
|
|
"num_tokens": 1680048.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.750500679016113,
|
|
"epoch": 0.07108549471661864,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4804,
|
|
"mean_token_accuracy": 0.1312839813530445,
|
|
"num_tokens": 1690907.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.736449241638184,
|
|
"epoch": 0.07156580211335255,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3008,
|
|
"mean_token_accuracy": 0.14280984848737716,
|
|
"num_tokens": 1702337.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.587835311889648,
|
|
"epoch": 0.07204610951008646,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.2527,
|
|
"mean_token_accuracy": 0.1450270913541317,
|
|
"num_tokens": 1713242.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.592082738876343,
|
|
"epoch": 0.07252641690682037,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.2289,
|
|
"mean_token_accuracy": 0.1451099433004856,
|
|
"num_tokens": 1724939.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.562298393249511,
|
|
"epoch": 0.07300672430355427,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.1847,
|
|
"mean_token_accuracy": 0.1562918320298195,
|
|
"num_tokens": 1737311.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.704523372650146,
|
|
"epoch": 0.07348703170028818,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3322,
|
|
"mean_token_accuracy": 0.14251347556710242,
|
|
"num_tokens": 1749528.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.5230649471282955,
|
|
"epoch": 0.07396733909702209,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.2065,
|
|
"mean_token_accuracy": 0.15109387934207916,
|
|
"num_tokens": 1760304.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.557912874221802,
|
|
"epoch": 0.074447646493756,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.19,
|
|
"mean_token_accuracy": 0.14943440705537797,
|
|
"num_tokens": 1772014.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.584811496734619,
|
|
"epoch": 0.07492795389048991,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.2511,
|
|
"mean_token_accuracy": 0.13997316658496856,
|
|
"num_tokens": 1784585.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.545004224777221,
|
|
"epoch": 0.07540826128722382,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.1812,
|
|
"mean_token_accuracy": 0.1486555442214012,
|
|
"num_tokens": 1795246.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.489949035644531,
|
|
"epoch": 0.07588856868395773,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.15014512687921525,
|
|
"num_tokens": 1806826.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.623802709579468,
|
|
"epoch": 0.07636887608069164,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.3092,
|
|
"mean_token_accuracy": 0.14633476734161377,
|
|
"num_tokens": 1818766.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.531846284866333,
|
|
"epoch": 0.07684918347742556,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.15384283810853958,
|
|
"num_tokens": 1830824.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.457365274429321,
|
|
"epoch": 0.07732949087415947,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.2466,
|
|
"mean_token_accuracy": 0.14449433609843254,
|
|
"num_tokens": 1841792.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.584504079818726,
|
|
"epoch": 0.07780979827089338,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.2006,
|
|
"mean_token_accuracy": 0.14591929987072944,
|
|
"num_tokens": 1854683.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.556228065490723,
|
|
"epoch": 0.07829010566762729,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2938,
|
|
"mean_token_accuracy": 0.1405360147356987,
|
|
"num_tokens": 1865826.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.604849815368652,
|
|
"epoch": 0.0787704130643612,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.2419,
|
|
"mean_token_accuracy": 0.14705629646778107,
|
|
"num_tokens": 1876759.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.513918781280518,
|
|
"epoch": 0.0792507204610951,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.2797,
|
|
"mean_token_accuracy": 0.14388945400714875,
|
|
"num_tokens": 1888013.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.682355451583862,
|
|
"epoch": 0.07973102785782901,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2876,
|
|
"mean_token_accuracy": 0.14284019619226457,
|
|
"num_tokens": 1898964.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.492662382125855,
|
|
"epoch": 0.08021133525456292,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.1948,
|
|
"mean_token_accuracy": 0.15035689398646354,
|
|
"num_tokens": 1909728.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.471567058563233,
|
|
"epoch": 0.08069164265129683,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.1331,
|
|
"mean_token_accuracy": 0.15249202400445938,
|
|
"num_tokens": 1919895.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.498814487457276,
|
|
"epoch": 0.08117195004803074,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.0557,
|
|
"mean_token_accuracy": 0.1550162822008133,
|
|
"num_tokens": 1930839.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.456363201141357,
|
|
"epoch": 0.08165225744476465,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2616,
|
|
"mean_token_accuracy": 0.14432529211044312,
|
|
"num_tokens": 1942605.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.504123783111572,
|
|
"epoch": 0.08213256484149856,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.2458,
|
|
"mean_token_accuracy": 0.1410786345601082,
|
|
"num_tokens": 1954863.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.629303932189941,
|
|
"epoch": 0.08261287223823247,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.14509388506412507,
|
|
"num_tokens": 1966088.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.504941749572754,
|
|
"epoch": 0.08309317963496637,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.1511,
|
|
"mean_token_accuracy": 0.148190413415432,
|
|
"num_tokens": 1978081.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.559056520462036,
|
|
"epoch": 0.08357348703170028,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2224,
|
|
"mean_token_accuracy": 0.13891531452536582,
|
|
"num_tokens": 1991212.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.578066205978393,
|
|
"epoch": 0.08405379442843419,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.2084,
|
|
"mean_token_accuracy": 0.1503169298171997,
|
|
"num_tokens": 2002074.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.426190519332886,
|
|
"epoch": 0.0845341018251681,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.1402,
|
|
"mean_token_accuracy": 0.15407513976097106,
|
|
"num_tokens": 2013039.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.500976419448852,
|
|
"epoch": 0.08501440922190202,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.2778,
|
|
"mean_token_accuracy": 0.14543393701314927,
|
|
"num_tokens": 2024744.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.499779176712036,
|
|
"epoch": 0.08549471661863593,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.151559966057539,
|
|
"num_tokens": 2035587.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.507718563079834,
|
|
"epoch": 0.08597502401536984,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.2209,
|
|
"mean_token_accuracy": 0.14204468578100204,
|
|
"num_tokens": 2047924.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.472938013076782,
|
|
"epoch": 0.08645533141210375,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.1499,
|
|
"mean_token_accuracy": 0.1465149611234665,
|
|
"num_tokens": 2060161.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.479418230056763,
|
|
"epoch": 0.08693563880883766,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.1678,
|
|
"mean_token_accuracy": 0.14912493750452996,
|
|
"num_tokens": 2071674.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.49160099029541,
|
|
"epoch": 0.08741594620557157,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2996,
|
|
"mean_token_accuracy": 0.14318522065877914,
|
|
"num_tokens": 2084025.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.563802194595337,
|
|
"epoch": 0.08789625360230548,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2327,
|
|
"mean_token_accuracy": 0.14436741322278976,
|
|
"num_tokens": 2094501.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.505239629745484,
|
|
"epoch": 0.08837656099903939,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.2167,
|
|
"mean_token_accuracy": 0.15397917181253434,
|
|
"num_tokens": 2106207.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.44503755569458,
|
|
"epoch": 0.0888568683957733,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.1276,
|
|
"mean_token_accuracy": 0.15853458568453788,
|
|
"num_tokens": 2116879.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.479341220855713,
|
|
"epoch": 0.0893371757925072,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.1848,
|
|
"mean_token_accuracy": 0.1470620773732662,
|
|
"num_tokens": 2128884.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.402610540390015,
|
|
"epoch": 0.08981748318924111,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.1305,
|
|
"mean_token_accuracy": 0.14514548182487488,
|
|
"num_tokens": 2140810.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.536736297607422,
|
|
"epoch": 0.09029779058597502,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.1911,
|
|
"mean_token_accuracy": 0.14236362800002098,
|
|
"num_tokens": 2152312.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.351864624023437,
|
|
"epoch": 0.09077809798270893,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.1298,
|
|
"mean_token_accuracy": 0.144212955981493,
|
|
"num_tokens": 2164408.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.436456298828125,
|
|
"epoch": 0.09125840537944284,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.1547,
|
|
"mean_token_accuracy": 0.15071666985750198,
|
|
"num_tokens": 2176050.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.357456064224243,
|
|
"epoch": 0.09173871277617675,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.0357,
|
|
"mean_token_accuracy": 0.1549798734486103,
|
|
"num_tokens": 2187354.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.294004631042481,
|
|
"epoch": 0.09221902017291066,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.14669691622257233,
|
|
"num_tokens": 2198686.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.354834318161011,
|
|
"epoch": 0.09269932756964457,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.14863732010126113,
|
|
"num_tokens": 2209780.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.404127836227417,
|
|
"epoch": 0.09317963496637849,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.1929,
|
|
"mean_token_accuracy": 0.15277946293354033,
|
|
"num_tokens": 2221760.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.414715957641602,
|
|
"epoch": 0.0936599423631124,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.2016,
|
|
"mean_token_accuracy": 0.1440224066376686,
|
|
"num_tokens": 2233767.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.447878742218018,
|
|
"epoch": 0.0941402497598463,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.1245,
|
|
"mean_token_accuracy": 0.1480201542377472,
|
|
"num_tokens": 2244841.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.362892484664917,
|
|
"epoch": 0.09462055715658022,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 5.9922,
|
|
"mean_token_accuracy": 0.15667022168636321,
|
|
"num_tokens": 2255620.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.3917787075042725,
|
|
"epoch": 0.09510086455331412,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.1894,
|
|
"mean_token_accuracy": 0.15466750115156175,
|
|
"num_tokens": 2266345.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.318432140350342,
|
|
"epoch": 0.09558117195004803,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.1248,
|
|
"mean_token_accuracy": 0.15534795224666595,
|
|
"num_tokens": 2277190.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.3766883373260494,
|
|
"epoch": 0.09606147934678194,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 5.9979,
|
|
"mean_token_accuracy": 0.15411072820425034,
|
|
"num_tokens": 2288241.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.409312772750854,
|
|
"epoch": 0.09654178674351585,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999999983283737,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.14942025095224382,
|
|
"num_tokens": 2301092.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.327887964248657,
|
|
"epoch": 0.09702209414024976,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999915373924,
|
|
"loss": 6.0533,
|
|
"mean_token_accuracy": 0.14707459956407548,
|
|
"num_tokens": 2313622.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.297283601760864,
|
|
"epoch": 0.09750240153698367,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999999795225793,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.1562737464904785,
|
|
"num_tokens": 2325699.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.347620439529419,
|
|
"epoch": 0.09798270893371758,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999999622839347,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.15067264884710313,
|
|
"num_tokens": 2337816.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.497613906860352,
|
|
"epoch": 0.09846301633045149,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999999398214593,
|
|
"loss": 6.2175,
|
|
"mean_token_accuracy": 0.1453450456261635,
|
|
"num_tokens": 2348793.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.378514766693115,
|
|
"epoch": 0.0989433237271854,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999999121351532,
|
|
"loss": 6.1278,
|
|
"mean_token_accuracy": 0.14934940189123153,
|
|
"num_tokens": 2360209.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.435119342803955,
|
|
"epoch": 0.0994236311239193,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999998792250173,
|
|
"loss": 6.1277,
|
|
"mean_token_accuracy": 0.1459425002336502,
|
|
"num_tokens": 2370597.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.408862972259522,
|
|
"epoch": 0.09990393852065321,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999998410910524,
|
|
"loss": 6.1716,
|
|
"mean_token_accuracy": 0.14220923334360122,
|
|
"num_tokens": 2381466.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.488006258010865,
|
|
"epoch": 0.10038424591738712,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999997977332592,
|
|
"loss": 6.2657,
|
|
"mean_token_accuracy": 0.14426247775554657,
|
|
"num_tokens": 2394507.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.375166702270508,
|
|
"epoch": 0.10086455331412104,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999997491516389,
|
|
"loss": 6.1158,
|
|
"mean_token_accuracy": 0.14977992326021194,
|
|
"num_tokens": 2406367.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.362482166290283,
|
|
"epoch": 0.10134486071085495,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999996953461925,
|
|
"loss": 6.0791,
|
|
"mean_token_accuracy": 0.15088748335838317,
|
|
"num_tokens": 2416962.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.437332439422607,
|
|
"epoch": 0.10182516810758886,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999996363169212,
|
|
"loss": 6.1431,
|
|
"mean_token_accuracy": 0.14360424429178237,
|
|
"num_tokens": 2429441.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.327810049057007,
|
|
"epoch": 0.10230547550432277,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999995720638266,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.15362217277288437,
|
|
"num_tokens": 2441360.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.267141437530517,
|
|
"epoch": 0.10278578290105668,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00049999950258691,
|
|
"loss": 6.0527,
|
|
"mean_token_accuracy": 0.14622927457094193,
|
|
"num_tokens": 2452928.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.3083587169647215,
|
|
"epoch": 0.10326609029779059,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999994278861731,
|
|
"loss": 5.9817,
|
|
"mean_token_accuracy": 0.15528771579265593,
|
|
"num_tokens": 2464218.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.301430654525757,
|
|
"epoch": 0.1037463976945245,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999993479616175,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.15502351075410842,
|
|
"num_tokens": 2475084.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.31117525100708,
|
|
"epoch": 0.1042267050912584,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004999992628132451,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.14931347519159316,
|
|
"num_tokens": 2486845.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.348042297363281,
|
|
"epoch": 0.10470701248799232,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999991724410582,
|
|
"loss": 6.1471,
|
|
"mean_token_accuracy": 0.14322768971323968,
|
|
"num_tokens": 2498049.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.270689201354981,
|
|
"epoch": 0.10518731988472622,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999990768450583,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.15236250758171083,
|
|
"num_tokens": 2509511.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.438291072845459,
|
|
"epoch": 0.10566762728146013,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999989760252482,
|
|
"loss": 6.0404,
|
|
"mean_token_accuracy": 0.1563153713941574,
|
|
"num_tokens": 2521518.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.131235933303833,
|
|
"epoch": 0.10614793467819404,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999988699816299,
|
|
"loss": 5.8906,
|
|
"mean_token_accuracy": 0.15999584943056105,
|
|
"num_tokens": 2533141.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.186205959320068,
|
|
"epoch": 0.10662824207492795,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999987587142058,
|
|
"loss": 5.8889,
|
|
"mean_token_accuracy": 0.15622006207704545,
|
|
"num_tokens": 2542907.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.262308979034424,
|
|
"epoch": 0.10710854947166186,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999986422229789,
|
|
"loss": 6.0278,
|
|
"mean_token_accuracy": 0.1462012603878975,
|
|
"num_tokens": 2554497.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.411641597747803,
|
|
"epoch": 0.10758885686839577,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999985205079514,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.1471574440598488,
|
|
"num_tokens": 2567035.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.178546047210693,
|
|
"epoch": 0.10806916426512968,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999983935691265,
|
|
"loss": 5.9343,
|
|
"mean_token_accuracy": 0.16074804067611695,
|
|
"num_tokens": 2578003.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.447769737243652,
|
|
"epoch": 0.10854947166186359,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499998261406507,
|
|
"loss": 6.2329,
|
|
"mean_token_accuracy": 0.1447854146361351,
|
|
"num_tokens": 2590272.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.202875328063965,
|
|
"epoch": 0.10902977905859751,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999981240200958,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.14931458830833436,
|
|
"num_tokens": 2602874.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.29072413444519,
|
|
"epoch": 0.10951008645533142,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999979814098966,
|
|
"loss": 6.0127,
|
|
"mean_token_accuracy": 0.15842576026916505,
|
|
"num_tokens": 2613835.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.339123868942261,
|
|
"epoch": 0.10999039385206533,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999978335759121,
|
|
"loss": 6.1187,
|
|
"mean_token_accuracy": 0.1503593236207962,
|
|
"num_tokens": 2624986.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.3845244407653805,
|
|
"epoch": 0.11047070124879924,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999976805181461,
|
|
"loss": 6.1242,
|
|
"mean_token_accuracy": 0.14067715033888817,
|
|
"num_tokens": 2637654.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.253936910629273,
|
|
"epoch": 0.11095100864553314,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499997522236602,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.15293926745653152,
|
|
"num_tokens": 2648947.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.260978364944458,
|
|
"epoch": 0.11143131604226705,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999973587312837,
|
|
"loss": 6.031,
|
|
"mean_token_accuracy": 0.151402048766613,
|
|
"num_tokens": 2659573.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.191074228286743,
|
|
"epoch": 0.11191162343900096,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999971900021947,
|
|
"loss": 6.0048,
|
|
"mean_token_accuracy": 0.15867563784122468,
|
|
"num_tokens": 2671491.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.292398309707641,
|
|
"epoch": 0.11239193083573487,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999970160493391,
|
|
"loss": 5.9964,
|
|
"mean_token_accuracy": 0.1500651329755783,
|
|
"num_tokens": 2682705.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.1503791332244875,
|
|
"epoch": 0.11287223823246878,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999968368727209,
|
|
"loss": 5.9329,
|
|
"mean_token_accuracy": 0.15546464920043945,
|
|
"num_tokens": 2693539.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.208331108093262,
|
|
"epoch": 0.11335254562920269,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999966524723442,
|
|
"loss": 5.9794,
|
|
"mean_token_accuracy": 0.1552668482065201,
|
|
"num_tokens": 2705403.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.37642993927002,
|
|
"epoch": 0.1138328530259366,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999964628482135,
|
|
"loss": 6.0783,
|
|
"mean_token_accuracy": 0.15211726650595664,
|
|
"num_tokens": 2717320.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.221129989624023,
|
|
"epoch": 0.1143131604226705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999962680003328,
|
|
"loss": 6.0448,
|
|
"mean_token_accuracy": 0.14739547073841094,
|
|
"num_tokens": 2730056.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.283902359008789,
|
|
"epoch": 0.11479346781940442,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499996067928707,
|
|
"loss": 5.922,
|
|
"mean_token_accuracy": 0.15959976464509965,
|
|
"num_tokens": 2741399.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.31879243850708,
|
|
"epoch": 0.11527377521613832,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999958626333406,
|
|
"loss": 6.155,
|
|
"mean_token_accuracy": 0.1457771949470043,
|
|
"num_tokens": 2752277.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.301510620117187,
|
|
"epoch": 0.11575408261287223,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999956521142383,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.15469708293676376,
|
|
"num_tokens": 2763172.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.277292966842651,
|
|
"epoch": 0.11623439000960614,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999954363714051,
|
|
"loss": 6.054,
|
|
"mean_token_accuracy": 0.15491107255220413,
|
|
"num_tokens": 2775096.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.317543888092041,
|
|
"epoch": 0.11671469740634005,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999952154048459,
|
|
"loss": 6.1321,
|
|
"mean_token_accuracy": 0.1500074803829193,
|
|
"num_tokens": 2786007.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.216952800750732,
|
|
"epoch": 0.11719500480307397,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499994989214566,
|
|
"loss": 5.9516,
|
|
"mean_token_accuracy": 0.163367360830307,
|
|
"num_tokens": 2797265.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.273515462875366,
|
|
"epoch": 0.11767531219980788,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999947578005705,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.15390106439590454,
|
|
"num_tokens": 2809427.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.245223760604858,
|
|
"epoch": 0.11815561959654179,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999945211628648,
|
|
"loss": 6.0295,
|
|
"mean_token_accuracy": 0.15515164881944657,
|
|
"num_tokens": 2822880.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.3243988990783695,
|
|
"epoch": 0.1186359269932757,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999942793014544,
|
|
"loss": 6.1043,
|
|
"mean_token_accuracy": 0.14880725666880606,
|
|
"num_tokens": 2834760.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.2938329696655275,
|
|
"epoch": 0.11911623439000961,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499994032216345,
|
|
"loss": 6.0577,
|
|
"mean_token_accuracy": 0.14785425141453742,
|
|
"num_tokens": 2846517.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.187609577178955,
|
|
"epoch": 0.11959654178674352,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999937799075422,
|
|
"loss": 5.9381,
|
|
"mean_token_accuracy": 0.1608589246869087,
|
|
"num_tokens": 2857280.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.250182056427002,
|
|
"epoch": 0.12007684918347743,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499993522375052,
|
|
"loss": 5.9878,
|
|
"mean_token_accuracy": 0.15561182498931886,
|
|
"num_tokens": 2869735.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.238501167297363,
|
|
"epoch": 0.12055715658021134,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999932596188802,
|
|
"loss": 5.9806,
|
|
"mean_token_accuracy": 0.15750712007284165,
|
|
"num_tokens": 2881681.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.122741842269898,
|
|
"epoch": 0.12103746397694524,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999929916390331,
|
|
"loss": 5.9974,
|
|
"mean_token_accuracy": 0.15890538841485977,
|
|
"num_tokens": 2893828.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.121092176437378,
|
|
"epoch": 0.12151777137367915,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999927184355169,
|
|
"loss": 5.9548,
|
|
"mean_token_accuracy": 0.15334596037864684,
|
|
"num_tokens": 2905804.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.387607383728027,
|
|
"epoch": 0.12199807877041306,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999924400083377,
|
|
"loss": 6.0998,
|
|
"mean_token_accuracy": 0.14984989315271377,
|
|
"num_tokens": 2918709.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.2461841106414795,
|
|
"epoch": 0.12247838616714697,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999921563575022,
|
|
"loss": 6.0112,
|
|
"mean_token_accuracy": 0.15625457540154458,
|
|
"num_tokens": 2930589.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.19944920539856,
|
|
"epoch": 0.12295869356388088,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999918674830169,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.1594749942421913,
|
|
"num_tokens": 2940635.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.171869897842408,
|
|
"epoch": 0.12343900096061479,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999915733848886,
|
|
"loss": 5.9354,
|
|
"mean_token_accuracy": 0.16207429766654968,
|
|
"num_tokens": 2952731.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.2040815353393555,
|
|
"epoch": 0.1239193083573487,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499991274063124,
|
|
"loss": 5.9461,
|
|
"mean_token_accuracy": 0.15291942954063414,
|
|
"num_tokens": 2964544.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.162799215316772,
|
|
"epoch": 0.12439961575408261,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999909695177301,
|
|
"loss": 5.8843,
|
|
"mean_token_accuracy": 0.1602574333548546,
|
|
"num_tokens": 2974996.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.114618587493896,
|
|
"epoch": 0.12487992315081652,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499990659748714,
|
|
"loss": 5.8875,
|
|
"mean_token_accuracy": 0.15879584103822708,
|
|
"num_tokens": 2986496.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.153219079971313,
|
|
"epoch": 0.12536023054755044,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999903447560828,
|
|
"loss": 5.9601,
|
|
"mean_token_accuracy": 0.1546933814883232,
|
|
"num_tokens": 2997693.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.1417900085449215,
|
|
"epoch": 0.12584053794428435,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999900245398439,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.159236279129982,
|
|
"num_tokens": 3009155.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.1472837924957275,
|
|
"epoch": 0.12632084534101826,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999896991000047,
|
|
"loss": 5.8526,
|
|
"mean_token_accuracy": 0.16511083841323854,
|
|
"num_tokens": 3020944.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.132077980041504,
|
|
"epoch": 0.12680115273775217,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999893684365729,
|
|
"loss": 5.9347,
|
|
"mean_token_accuracy": 0.15706215500831605,
|
|
"num_tokens": 3032893.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.187384700775146,
|
|
"epoch": 0.12728146013448607,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999890325495559,
|
|
"loss": 5.9891,
|
|
"mean_token_accuracy": 0.15579385310411453,
|
|
"num_tokens": 3044937.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.1738560676574705,
|
|
"epoch": 0.12776176753121998,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999886914389617,
|
|
"loss": 5.8937,
|
|
"mean_token_accuracy": 0.1595969796180725,
|
|
"num_tokens": 3056071.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.156427192687988,
|
|
"epoch": 0.1282420749279539,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004999883451047981,
|
|
"loss": 6.0543,
|
|
"mean_token_accuracy": 0.15404095351696015,
|
|
"num_tokens": 3067724.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.2366071224212645,
|
|
"epoch": 0.1287223823246878,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999879935470733,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.1608007699251175,
|
|
"num_tokens": 3080779.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.148285913467407,
|
|
"epoch": 0.1292026897214217,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999876367657954,
|
|
"loss": 5.9385,
|
|
"mean_token_accuracy": 0.15236368924379348,
|
|
"num_tokens": 3091991.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.128611755371094,
|
|
"epoch": 0.12968299711815562,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999872747609725,
|
|
"loss": 5.9266,
|
|
"mean_token_accuracy": 0.15997803062200547,
|
|
"num_tokens": 3103713.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.109859609603882,
|
|
"epoch": 0.13016330451488953,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999869075326132,
|
|
"loss": 5.9504,
|
|
"mean_token_accuracy": 0.15759862959384918,
|
|
"num_tokens": 3115891.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.09540114402771,
|
|
"epoch": 0.13064361191162344,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499986535080726,
|
|
"loss": 5.8154,
|
|
"mean_token_accuracy": 0.16952185183763505,
|
|
"num_tokens": 3126223.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.197498035430908,
|
|
"epoch": 0.13112391930835735,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999861574053196,
|
|
"loss": 5.9901,
|
|
"mean_token_accuracy": 0.1543188914656639,
|
|
"num_tokens": 3137537.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.249709987640381,
|
|
"epoch": 0.13160422670509125,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999857745064027,
|
|
"loss": 6.0021,
|
|
"mean_token_accuracy": 0.15779454112052918,
|
|
"num_tokens": 3150126.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.143283319473267,
|
|
"epoch": 0.13208453410182516,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499985386383984,
|
|
"loss": 5.9765,
|
|
"mean_token_accuracy": 0.1616181269288063,
|
|
"num_tokens": 3161684.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.0805628299713135,
|
|
"epoch": 0.13256484149855907,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999849930380729,
|
|
"loss": 5.8674,
|
|
"mean_token_accuracy": 0.16023531705141067,
|
|
"num_tokens": 3172342.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.236843204498291,
|
|
"epoch": 0.13304514889529298,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999845944686781,
|
|
"loss": 6.0028,
|
|
"mean_token_accuracy": 0.16236832588911057,
|
|
"num_tokens": 3183681.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.0158531188964846,
|
|
"epoch": 0.1335254562920269,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999841906758093,
|
|
"loss": 5.8018,
|
|
"mean_token_accuracy": 0.16931295841932298,
|
|
"num_tokens": 3194122.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.141476392745972,
|
|
"epoch": 0.1340057636887608,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999837816594757,
|
|
"loss": 5.8629,
|
|
"mean_token_accuracy": 0.16289830058813096,
|
|
"num_tokens": 3205719.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.072001695632935,
|
|
"epoch": 0.1344860710854947,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999833674196865,
|
|
"loss": 5.8931,
|
|
"mean_token_accuracy": 0.1596195340156555,
|
|
"num_tokens": 3216262.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.219841957092285,
|
|
"epoch": 0.13496637848222862,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999829479564518,
|
|
"loss": 5.9352,
|
|
"mean_token_accuracy": 0.1537438616156578,
|
|
"num_tokens": 3228035.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.063015413284302,
|
|
"epoch": 0.13544668587896252,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499982523269781,
|
|
"loss": 5.813,
|
|
"mean_token_accuracy": 0.16350635886192322,
|
|
"num_tokens": 3239643.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.081555032730103,
|
|
"epoch": 0.13592699327569643,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999820933596842,
|
|
"loss": 5.8878,
|
|
"mean_token_accuracy": 0.1632865384221077,
|
|
"num_tokens": 3250293.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.233055973052979,
|
|
"epoch": 0.13640730067243034,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499981658226171,
|
|
"loss": 6.0138,
|
|
"mean_token_accuracy": 0.14861609488725663,
|
|
"num_tokens": 3262448.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.011493682861328,
|
|
"epoch": 0.13688760806916425,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499981217869252,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.15858830362558365,
|
|
"num_tokens": 3274041.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.152698564529419,
|
|
"epoch": 0.1373679154658982,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499980772288937,
|
|
"loss": 5.9147,
|
|
"mean_token_accuracy": 0.15459389835596085,
|
|
"num_tokens": 3285063.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.150080776214599,
|
|
"epoch": 0.1378482228626321,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999803214852367,
|
|
"loss": 5.9305,
|
|
"mean_token_accuracy": 0.16173136979341507,
|
|
"num_tokens": 3297031.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.131770992279053,
|
|
"epoch": 0.138328530259366,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999798654581613,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.156547848880291,
|
|
"num_tokens": 3308187.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.07386417388916,
|
|
"epoch": 0.13880883765609991,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999794042077214,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.16056945770978928,
|
|
"num_tokens": 3319439.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.1171587944030765,
|
|
"epoch": 0.13928914505283382,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999789377339279,
|
|
"loss": 5.9105,
|
|
"mean_token_accuracy": 0.15625833347439766,
|
|
"num_tokens": 3331715.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.126484775543213,
|
|
"epoch": 0.13976945244956773,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999784660367915,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.16759593337774276,
|
|
"num_tokens": 3342281.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.233757495880127,
|
|
"epoch": 0.14024975984630164,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999779891163231,
|
|
"loss": 5.9932,
|
|
"mean_token_accuracy": 0.1566716194152832,
|
|
"num_tokens": 3353530.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.097651147842408,
|
|
"epoch": 0.14073006724303555,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999775069725339,
|
|
"loss": 5.9691,
|
|
"mean_token_accuracy": 0.15415023267269135,
|
|
"num_tokens": 3365083.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.1879171371459964,
|
|
"epoch": 0.14121037463976946,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499977019605435,
|
|
"loss": 5.9113,
|
|
"mean_token_accuracy": 0.15917533934116362,
|
|
"num_tokens": 3378143.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.168327140808105,
|
|
"epoch": 0.14169068203650337,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999765270150378,
|
|
"loss": 5.8914,
|
|
"mean_token_accuracy": 0.15909557938575744,
|
|
"num_tokens": 3388438.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.007050275802612,
|
|
"epoch": 0.14217098943323728,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999760292013536,
|
|
"loss": 5.8862,
|
|
"mean_token_accuracy": 0.15672476589679718,
|
|
"num_tokens": 3400150.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.030299091339112,
|
|
"epoch": 0.14265129682997119,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999755261643941,
|
|
"loss": 5.7668,
|
|
"mean_token_accuracy": 0.16843343377113343,
|
|
"num_tokens": 3411073.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.067905569076538,
|
|
"epoch": 0.1431316042267051,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999750179041709,
|
|
"loss": 5.8339,
|
|
"mean_token_accuracy": 0.17172128707170486,
|
|
"num_tokens": 3422196.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.1059250831604,
|
|
"epoch": 0.143611911623439,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999745044206959,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.15575093105435373,
|
|
"num_tokens": 3432568.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.113522005081177,
|
|
"epoch": 0.1440922190201729,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999739857139809,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.15804980993270873,
|
|
"num_tokens": 3444096.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 5.95184359550476,
|
|
"epoch": 0.14457252641690682,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499973461784038,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.16874846071004868,
|
|
"num_tokens": 3455502.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.154258155822754,
|
|
"epoch": 0.14505283381364073,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999729326308792,
|
|
"loss": 5.9156,
|
|
"mean_token_accuracy": 0.15503724962472915,
|
|
"num_tokens": 3467753.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.040020275115967,
|
|
"epoch": 0.14553314121037464,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499972398254517,
|
|
"loss": 5.7886,
|
|
"mean_token_accuracy": 0.1608596622943878,
|
|
"num_tokens": 3479206.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.036813592910766,
|
|
"epoch": 0.14601344860710855,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499971858654964,
|
|
"loss": 5.822,
|
|
"mean_token_accuracy": 0.16021780669689178,
|
|
"num_tokens": 3490914.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.045322847366333,
|
|
"epoch": 0.14649375600384246,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999713138322321,
|
|
"loss": 5.8726,
|
|
"mean_token_accuracy": 0.15877723693847656,
|
|
"num_tokens": 3502932.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.995212125778198,
|
|
"epoch": 0.14697406340057637,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999707637863346,
|
|
"loss": 5.801,
|
|
"mean_token_accuracy": 0.16770601868629456,
|
|
"num_tokens": 3515071.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.137019300460816,
|
|
"epoch": 0.14745437079731027,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999702085172838,
|
|
"loss": 5.9119,
|
|
"mean_token_accuracy": 0.15909691900014877,
|
|
"num_tokens": 3526845.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.070224285125732,
|
|
"epoch": 0.14793467819404418,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999696480250929,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.15973274111747743,
|
|
"num_tokens": 3538810.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.158443641662598,
|
|
"epoch": 0.1484149855907781,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999690823097747,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.16933712512254714,
|
|
"num_tokens": 3549570.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.8632913589477536,
|
|
"epoch": 0.148895292987512,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999685113713426,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.1719530537724495,
|
|
"num_tokens": 3560937.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.06872525215149,
|
|
"epoch": 0.1493756003842459,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999679352098096,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.15944236814975737,
|
|
"num_tokens": 3573603.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.972690153121948,
|
|
"epoch": 0.14985590778097982,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999673538251891,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.15244044810533525,
|
|
"num_tokens": 3586034.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.002362155914307,
|
|
"epoch": 0.15033621517771373,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999667672174947,
|
|
"loss": 5.7819,
|
|
"mean_token_accuracy": 0.16955426633358,
|
|
"num_tokens": 3597305.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.131285715103149,
|
|
"epoch": 0.15081652257444764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049996617538674,
|
|
"loss": 5.9327,
|
|
"mean_token_accuracy": 0.15085813403129578,
|
|
"num_tokens": 3608758.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.118503046035767,
|
|
"epoch": 0.15129682997118155,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999655783329386,
|
|
"loss": 5.9296,
|
|
"mean_token_accuracy": 0.15356628447771073,
|
|
"num_tokens": 3621508.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.0756830215454105,
|
|
"epoch": 0.15177713736791545,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999649760561046,
|
|
"loss": 5.891,
|
|
"mean_token_accuracy": 0.1630493327975273,
|
|
"num_tokens": 3634826.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.9437319278717045,
|
|
"epoch": 0.15225744476464936,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999643685562519,
|
|
"loss": 5.7229,
|
|
"mean_token_accuracy": 0.17993323653936386,
|
|
"num_tokens": 3646427.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.94010214805603,
|
|
"epoch": 0.15273775216138327,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999637558333945,
|
|
"loss": 5.8497,
|
|
"mean_token_accuracy": 0.16093539148569108,
|
|
"num_tokens": 3658157.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.139387130737305,
|
|
"epoch": 0.15321805955811718,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999631378875467,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.1610818549990654,
|
|
"num_tokens": 3670695.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.97409348487854,
|
|
"epoch": 0.15369836695485112,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999625147187228,
|
|
"loss": 5.809,
|
|
"mean_token_accuracy": 0.15726363956928252,
|
|
"num_tokens": 3683379.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.979640197753906,
|
|
"epoch": 0.15417867435158503,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999618863269373,
|
|
"loss": 5.7012,
|
|
"mean_token_accuracy": 0.17374149709939957,
|
|
"num_tokens": 3694411.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.935902690887451,
|
|
"epoch": 0.15465898174831894,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999612527122049,
|
|
"loss": 5.762,
|
|
"mean_token_accuracy": 0.1684124767780304,
|
|
"num_tokens": 3703833.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.048168516159057,
|
|
"epoch": 0.15513928914505284,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999606138745402,
|
|
"loss": 5.8406,
|
|
"mean_token_accuracy": 0.1746752843260765,
|
|
"num_tokens": 3714702.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.089325952529907,
|
|
"epoch": 0.15561959654178675,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999599698139581,
|
|
"loss": 5.9244,
|
|
"mean_token_accuracy": 0.1633257105946541,
|
|
"num_tokens": 3726000.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.040888738632202,
|
|
"epoch": 0.15609990393852066,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999593205304734,
|
|
"loss": 5.7988,
|
|
"mean_token_accuracy": 0.15986983478069305,
|
|
"num_tokens": 3737681.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.123997163772583,
|
|
"epoch": 0.15658021133525457,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999586660241012,
|
|
"loss": 5.9075,
|
|
"mean_token_accuracy": 0.16165615245699883,
|
|
"num_tokens": 3749477.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.087912082672119,
|
|
"epoch": 0.15706051873198848,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999580062948569,
|
|
"loss": 5.8909,
|
|
"mean_token_accuracy": 0.16025447547435762,
|
|
"num_tokens": 3759946.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.989850997924805,
|
|
"epoch": 0.1575408261287224,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999573413427556,
|
|
"loss": 5.7826,
|
|
"mean_token_accuracy": 0.16652001142501832,
|
|
"num_tokens": 3770147.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.966318368911743,
|
|
"epoch": 0.1580211335254563,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999566711678128,
|
|
"loss": 5.7355,
|
|
"mean_token_accuracy": 0.16983530521392823,
|
|
"num_tokens": 3781028.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.011458206176758,
|
|
"epoch": 0.1585014409221902,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999559957700442,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.15967805832624435,
|
|
"num_tokens": 3792529.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.144451379776001,
|
|
"epoch": 0.15898174831892412,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999553151494653,
|
|
"loss": 5.9237,
|
|
"mean_token_accuracy": 0.16285151839256287,
|
|
"num_tokens": 3804630.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.864691495895386,
|
|
"epoch": 0.15946205571565802,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999546293060919,
|
|
"loss": 5.6858,
|
|
"mean_token_accuracy": 0.1718939796090126,
|
|
"num_tokens": 3815019.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.973699855804443,
|
|
"epoch": 0.15994236311239193,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049995393823994,
|
|
"loss": 5.7936,
|
|
"mean_token_accuracy": 0.16477740556001663,
|
|
"num_tokens": 3825648.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.009506607055664,
|
|
"epoch": 0.16042267050912584,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999532419510255,
|
|
"loss": 5.7815,
|
|
"mean_token_accuracy": 0.16592843681573868,
|
|
"num_tokens": 3836779.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.950329399108886,
|
|
"epoch": 0.16090297790585975,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499952540439365,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.16188324987888336,
|
|
"num_tokens": 3848350.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.050455141067505,
|
|
"epoch": 0.16138328530259366,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999518337049743,
|
|
"loss": 5.8283,
|
|
"mean_token_accuracy": 0.16736475825309755,
|
|
"num_tokens": 3859792.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.972486734390259,
|
|
"epoch": 0.16186359269932757,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049995112174787,
|
|
"loss": 5.7611,
|
|
"mean_token_accuracy": 0.16538213193416595,
|
|
"num_tokens": 3871539.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.93617525100708,
|
|
"epoch": 0.16234390009606148,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999504045680687,
|
|
"loss": 5.7937,
|
|
"mean_token_accuracy": 0.16570636183023452,
|
|
"num_tokens": 3885025.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.037606048583984,
|
|
"epoch": 0.1628242074927954,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999496821655869,
|
|
"loss": 5.9112,
|
|
"mean_token_accuracy": 0.15885820835828782,
|
|
"num_tokens": 3896519.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.961896991729736,
|
|
"epoch": 0.1633045148895293,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999489545404414,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.16855804473161698,
|
|
"num_tokens": 3907636.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.917847633361816,
|
|
"epoch": 0.1637848222862632,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999482216926493,
|
|
"loss": 5.8151,
|
|
"mean_token_accuracy": 0.16696375161409377,
|
|
"num_tokens": 3917746.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.967260789871216,
|
|
"epoch": 0.1642651296829971,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999474836222273,
|
|
"loss": 5.7212,
|
|
"mean_token_accuracy": 0.17350309789180757,
|
|
"num_tokens": 3928901.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.922950553894043,
|
|
"epoch": 0.16474543707973102,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999467403291928,
|
|
"loss": 5.8411,
|
|
"mean_token_accuracy": 0.17054857611656188,
|
|
"num_tokens": 3940094.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.958613348007202,
|
|
"epoch": 0.16522574447646493,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999459918135628,
|
|
"loss": 5.7596,
|
|
"mean_token_accuracy": 0.16999174505472184,
|
|
"num_tokens": 3952714.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.936737680435181,
|
|
"epoch": 0.16570605187319884,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499945238075355,
|
|
"loss": 5.7413,
|
|
"mean_token_accuracy": 0.17201962023973466,
|
|
"num_tokens": 3963107.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.932821226119995,
|
|
"epoch": 0.16618635926993275,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999444791145865,
|
|
"loss": 5.6878,
|
|
"mean_token_accuracy": 0.17226921916007995,
|
|
"num_tokens": 3973454.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.937837934494018,
|
|
"epoch": 0.16666666666666666,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004999437149312754,
|
|
"loss": 5.8047,
|
|
"mean_token_accuracy": 0.16127632111310958,
|
|
"num_tokens": 3985352.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.028000020980835,
|
|
"epoch": 0.16714697406340057,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499942945525439,
|
|
"loss": 5.769,
|
|
"mean_token_accuracy": 0.1692960739135742,
|
|
"num_tokens": 3997088.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.931283950805664,
|
|
"epoch": 0.16762728146013448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999421708970954,
|
|
"loss": 5.7969,
|
|
"mean_token_accuracy": 0.16781435459852218,
|
|
"num_tokens": 4008551.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.948990726470948,
|
|
"epoch": 0.16810758885686838,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999413910462625,
|
|
"loss": 5.8268,
|
|
"mean_token_accuracy": 0.16457579284906387,
|
|
"num_tokens": 4020886.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.006660127639771,
|
|
"epoch": 0.1685878962536023,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999406059729586,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.1626640737056732,
|
|
"num_tokens": 4032811.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.967091226577759,
|
|
"epoch": 0.1690682036503362,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999398156772016,
|
|
"loss": 5.747,
|
|
"mean_token_accuracy": 0.17119821906089783,
|
|
"num_tokens": 4044102.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.9318421363830565,
|
|
"epoch": 0.16954851104707014,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049993902015901,
|
|
"loss": 5.7835,
|
|
"mean_token_accuracy": 0.17211457341909409,
|
|
"num_tokens": 4056849.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.943634080886841,
|
|
"epoch": 0.17002881844380405,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999382194184023,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.16628441363573074,
|
|
"num_tokens": 4068392.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.970344209671021,
|
|
"epoch": 0.17050912584053796,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999374134553972,
|
|
"loss": 5.6582,
|
|
"mean_token_accuracy": 0.17245645970106124,
|
|
"num_tokens": 4078949.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.9032188892364506,
|
|
"epoch": 0.17098943323727187,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999366022700131,
|
|
"loss": 5.7916,
|
|
"mean_token_accuracy": 0.16414022147655488,
|
|
"num_tokens": 4091432.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.925055408477784,
|
|
"epoch": 0.17146974063400577,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999357858622691,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.17122484147548675,
|
|
"num_tokens": 4103001.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.929124546051026,
|
|
"epoch": 0.17195004803073968,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999349642321842,
|
|
"loss": 5.7667,
|
|
"mean_token_accuracy": 0.1666597157716751,
|
|
"num_tokens": 4113570.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.980472898483276,
|
|
"epoch": 0.1724303554274736,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999341373797772,
|
|
"loss": 5.8077,
|
|
"mean_token_accuracy": 0.16480496674776077,
|
|
"num_tokens": 4125658.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.8866361618042,
|
|
"epoch": 0.1729106628242075,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999333053050675,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.16817544847726823,
|
|
"num_tokens": 4137424.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.941749000549317,
|
|
"epoch": 0.1733909702209414,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999324680080744,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.16792946606874465,
|
|
"num_tokens": 4149772.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.8657555103302,
|
|
"epoch": 0.17387127761767532,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999316254888172,
|
|
"loss": 5.7335,
|
|
"mean_token_accuracy": 0.17179457992315292,
|
|
"num_tokens": 4162246.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.883719253540039,
|
|
"epoch": 0.17435158501440923,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999307777473157,
|
|
"loss": 5.701,
|
|
"mean_token_accuracy": 0.17882005274295806,
|
|
"num_tokens": 4173449.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.866553688049317,
|
|
"epoch": 0.17483189241114314,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999299247835893,
|
|
"loss": 5.7518,
|
|
"mean_token_accuracy": 0.16288111954927445,
|
|
"num_tokens": 4185560.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.952811813354492,
|
|
"epoch": 0.17531219980787704,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499929066597658,
|
|
"loss": 5.8043,
|
|
"mean_token_accuracy": 0.15593840181827545,
|
|
"num_tokens": 4197843.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.971073150634766,
|
|
"epoch": 0.17579250720461095,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999282031895418,
|
|
"loss": 5.6586,
|
|
"mean_token_accuracy": 0.16830604374408722,
|
|
"num_tokens": 4210009.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.914163827896118,
|
|
"epoch": 0.17627281460134486,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999273345592604,
|
|
"loss": 5.8931,
|
|
"mean_token_accuracy": 0.15920523107051848,
|
|
"num_tokens": 4222213.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.962227725982666,
|
|
"epoch": 0.17675312199807877,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999264607068343,
|
|
"loss": 5.7543,
|
|
"mean_token_accuracy": 0.16375723034143447,
|
|
"num_tokens": 4234159.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.948575210571289,
|
|
"epoch": 0.17723342939481268,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999255816322837,
|
|
"loss": 5.8124,
|
|
"mean_token_accuracy": 0.1582082837820053,
|
|
"num_tokens": 4246358.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.0558061599731445,
|
|
"epoch": 0.1777137367915466,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499924697335629,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.16516841500997542,
|
|
"num_tokens": 4256698.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.875409936904907,
|
|
"epoch": 0.1781940441882805,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999238078168906,
|
|
"loss": 5.6677,
|
|
"mean_token_accuracy": 0.18177317082881927,
|
|
"num_tokens": 4268007.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.906381893157959,
|
|
"epoch": 0.1786743515850144,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999229130760894,
|
|
"loss": 5.7785,
|
|
"mean_token_accuracy": 0.16978150457143784,
|
|
"num_tokens": 4278583.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.020100021362305,
|
|
"epoch": 0.17915465898174832,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499922013113246,
|
|
"loss": 5.8081,
|
|
"mean_token_accuracy": 0.1636409193277359,
|
|
"num_tokens": 4290267.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.916716623306274,
|
|
"epoch": 0.17963496637848222,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999211079283814,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.17464031428098678,
|
|
"num_tokens": 4302177.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.793494367599488,
|
|
"epoch": 0.18011527377521613,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004999201975215164,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.17644754350185393,
|
|
"num_tokens": 4312420.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.989563703536987,
|
|
"epoch": 0.18059558117195004,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999192818926725,
|
|
"loss": 5.7904,
|
|
"mean_token_accuracy": 0.1659339353442192,
|
|
"num_tokens": 4324050.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.9014684677124025,
|
|
"epoch": 0.18107588856868395,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999183610418706,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.17169519364833832,
|
|
"num_tokens": 4335336.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.792817640304565,
|
|
"epoch": 0.18155619596541786,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999174349691322,
|
|
"loss": 5.6589,
|
|
"mean_token_accuracy": 0.17302853614091873,
|
|
"num_tokens": 4346239.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.912134981155395,
|
|
"epoch": 0.18203650336215177,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999165036744788,
|
|
"loss": 5.7356,
|
|
"mean_token_accuracy": 0.16781715154647828,
|
|
"num_tokens": 4357195.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.846279335021973,
|
|
"epoch": 0.18251681075888568,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999155671579322,
|
|
"loss": 5.6776,
|
|
"mean_token_accuracy": 0.17427498400211333,
|
|
"num_tokens": 4368905.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.962751770019532,
|
|
"epoch": 0.1829971181556196,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499914625419514,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.16602100878953935,
|
|
"num_tokens": 4381708.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.798335075378418,
|
|
"epoch": 0.1834774255523535,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999136784592459,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.18304169028997422,
|
|
"num_tokens": 4393199.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.928949308395386,
|
|
"epoch": 0.1839577329490874,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999127262771502,
|
|
"loss": 5.8242,
|
|
"mean_token_accuracy": 0.16348036080598832,
|
|
"num_tokens": 4403986.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.974527883529663,
|
|
"epoch": 0.1844380403458213,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999117688732487,
|
|
"loss": 5.677,
|
|
"mean_token_accuracy": 0.1677529901266098,
|
|
"num_tokens": 4415574.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.840640020370484,
|
|
"epoch": 0.18491834774255522,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999108062475638,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.17418631464242934,
|
|
"num_tokens": 4427579.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.920491027832031,
|
|
"epoch": 0.18539865513928913,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499909838400118,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.1702801316976547,
|
|
"num_tokens": 4440045.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.875643730163574,
|
|
"epoch": 0.18587896253602307,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999088653309334,
|
|
"loss": 5.7865,
|
|
"mean_token_accuracy": 0.16631472557783128,
|
|
"num_tokens": 4450129.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.843389463424683,
|
|
"epoch": 0.18635926993275698,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999078870400329,
|
|
"loss": 5.6529,
|
|
"mean_token_accuracy": 0.1726601541042328,
|
|
"num_tokens": 4461378.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.898785829544067,
|
|
"epoch": 0.18683957732949089,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999069035274391,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.17404537796974182,
|
|
"num_tokens": 4472249.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.829293203353882,
|
|
"epoch": 0.1873198847262248,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999059147931747,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.16566374748945237,
|
|
"num_tokens": 4484243.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.932005405426025,
|
|
"epoch": 0.1878001921229587,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999049208372629,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.1711133375763893,
|
|
"num_tokens": 4495776.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.815832805633545,
|
|
"epoch": 0.1882804995196926,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999039216597267,
|
|
"loss": 5.731,
|
|
"mean_token_accuracy": 0.17108235955238343,
|
|
"num_tokens": 4508581.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.915356016159057,
|
|
"epoch": 0.18876080691642652,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999029172605892,
|
|
"loss": 5.6688,
|
|
"mean_token_accuracy": 0.16956983059644698,
|
|
"num_tokens": 4519753.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.870398330688476,
|
|
"epoch": 0.18924111431316043,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999019076398738,
|
|
"loss": 5.7318,
|
|
"mean_token_accuracy": 0.1767261579632759,
|
|
"num_tokens": 4529957.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.917528676986694,
|
|
"epoch": 0.18972142170989434,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499900892797604,
|
|
"loss": 5.7002,
|
|
"mean_token_accuracy": 0.17024850398302077,
|
|
"num_tokens": 4541181.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.877421092987061,
|
|
"epoch": 0.19020172910662825,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998998727338031,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.17142467349767684,
|
|
"num_tokens": 4552235.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.848327493667602,
|
|
"epoch": 0.19068203650336216,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998988474484952,
|
|
"loss": 5.6808,
|
|
"mean_token_accuracy": 0.17754830718040465,
|
|
"num_tokens": 4564045.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.832021617889405,
|
|
"epoch": 0.19116234390009607,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998978169417038,
|
|
"loss": 5.587,
|
|
"mean_token_accuracy": 0.18072767406702042,
|
|
"num_tokens": 4575141.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.814238882064819,
|
|
"epoch": 0.19164265129682997,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998967812134529,
|
|
"loss": 5.6878,
|
|
"mean_token_accuracy": 0.1720028355717659,
|
|
"num_tokens": 4586491.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.894739389419556,
|
|
"epoch": 0.19212295869356388,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998957402637664,
|
|
"loss": 5.6897,
|
|
"mean_token_accuracy": 0.17228867560625077,
|
|
"num_tokens": 4598421.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.837182331085205,
|
|
"epoch": 0.1926032660902978,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998946940926687,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.18361353129148483,
|
|
"num_tokens": 4609688.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.837462520599365,
|
|
"epoch": 0.1930835734870317,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499893642700184,
|
|
"loss": 5.7614,
|
|
"mean_token_accuracy": 0.1679168865084648,
|
|
"num_tokens": 4621169.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.882701253890991,
|
|
"epoch": 0.1935638808837656,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998925860863368,
|
|
"loss": 5.6982,
|
|
"mean_token_accuracy": 0.1753264084458351,
|
|
"num_tokens": 4632512.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.8722984313964846,
|
|
"epoch": 0.19404418828049952,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998915242511516,
|
|
"loss": 5.7468,
|
|
"mean_token_accuracy": 0.16945238560438156,
|
|
"num_tokens": 4644356.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.9419224739074705,
|
|
"epoch": 0.19452449567723343,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998904571946528,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.16765568107366563,
|
|
"num_tokens": 4655601.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.848211431503296,
|
|
"epoch": 0.19500480307396734,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998893849168655,
|
|
"loss": 5.7448,
|
|
"mean_token_accuracy": 0.16884764283895493,
|
|
"num_tokens": 4666813.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.902902412414551,
|
|
"epoch": 0.19548511047070125,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998883074178144,
|
|
"loss": 5.7389,
|
|
"mean_token_accuracy": 0.16699665933847427,
|
|
"num_tokens": 4679123.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.874791812896729,
|
|
"epoch": 0.19596541786743515,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998872246975247,
|
|
"loss": 5.6311,
|
|
"mean_token_accuracy": 0.17366175949573517,
|
|
"num_tokens": 4690485.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.7398899555206295,
|
|
"epoch": 0.19644572526416906,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998861367560213,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.17550230622291565,
|
|
"num_tokens": 4702573.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.889365386962891,
|
|
"epoch": 0.19692603266090297,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998850435933296,
|
|
"loss": 5.6907,
|
|
"mean_token_accuracy": 0.16575469076633453,
|
|
"num_tokens": 4715653.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.819795274734497,
|
|
"epoch": 0.19740634005763688,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998839452094749,
|
|
"loss": 5.6751,
|
|
"mean_token_accuracy": 0.1743623748421669,
|
|
"num_tokens": 4726051.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.900219297409057,
|
|
"epoch": 0.1978866474543708,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998828416044829,
|
|
"loss": 5.8183,
|
|
"mean_token_accuracy": 0.16225597262382507,
|
|
"num_tokens": 4738176.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.914799547195434,
|
|
"epoch": 0.1983669548511047,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499881732778379,
|
|
"loss": 5.7246,
|
|
"mean_token_accuracy": 0.1708556368947029,
|
|
"num_tokens": 4749547.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.816590356826782,
|
|
"epoch": 0.1988472622478386,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499880618731189,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.17196280360221863,
|
|
"num_tokens": 4761967.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.815549898147583,
|
|
"epoch": 0.19932756964457252,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998794994629388,
|
|
"loss": 5.6193,
|
|
"mean_token_accuracy": 0.17873595058918,
|
|
"num_tokens": 4772847.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.846785545349121,
|
|
"epoch": 0.19980787704130643,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998783749736545,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.17165183573961257,
|
|
"num_tokens": 4785049.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.838068294525146,
|
|
"epoch": 0.20028818443804033,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998772452633619,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.16461516320705413,
|
|
"num_tokens": 4797484.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.804093217849731,
|
|
"epoch": 0.20076849183477424,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998761103320876,
|
|
"loss": 5.6499,
|
|
"mean_token_accuracy": 0.16633011251688004,
|
|
"num_tokens": 4809422.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.889832544326782,
|
|
"epoch": 0.20124879923150815,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998749701798577,
|
|
"loss": 5.8256,
|
|
"mean_token_accuracy": 0.1649285450577736,
|
|
"num_tokens": 4822340.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.832509899139405,
|
|
"epoch": 0.2017291066282421,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998738248066986,
|
|
"loss": 5.6039,
|
|
"mean_token_accuracy": 0.17457860857248306,
|
|
"num_tokens": 4833382.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.753271865844726,
|
|
"epoch": 0.202209414024976,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998726742126372,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.17748918682336806,
|
|
"num_tokens": 4843916.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.860424470901489,
|
|
"epoch": 0.2026897214217099,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998715183976999,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.17942588478326799,
|
|
"num_tokens": 4855420.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.8845704078674315,
|
|
"epoch": 0.20317002881844382,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998703573619137,
|
|
"loss": 5.6902,
|
|
"mean_token_accuracy": 0.16863269060850145,
|
|
"num_tokens": 4866540.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.844192361831665,
|
|
"epoch": 0.20365033621517772,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998691911053056,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.17058192938566208,
|
|
"num_tokens": 4878860.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.910974168777466,
|
|
"epoch": 0.20413064361191163,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998680196279026,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.1690535604953766,
|
|
"num_tokens": 4889692.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.937790060043335,
|
|
"epoch": 0.20461095100864554,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998668429297319,
|
|
"loss": 5.7047,
|
|
"mean_token_accuracy": 0.1704765021800995,
|
|
"num_tokens": 4901337.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.702803325653076,
|
|
"epoch": 0.20509125840537945,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998656610108208,
|
|
"loss": 5.6129,
|
|
"mean_token_accuracy": 0.17906004935503006,
|
|
"num_tokens": 4912340.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.85637321472168,
|
|
"epoch": 0.20557156580211336,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998644738711969,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.1815409779548645,
|
|
"num_tokens": 4923429.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.828443336486816,
|
|
"epoch": 0.20605187319884727,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998632815108874,
|
|
"loss": 5.6722,
|
|
"mean_token_accuracy": 0.17124899476766586,
|
|
"num_tokens": 4934826.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.8796604633331295,
|
|
"epoch": 0.20653218059558118,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998620839299203,
|
|
"loss": 5.7412,
|
|
"mean_token_accuracy": 0.17052844166755676,
|
|
"num_tokens": 4945189.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.883285331726074,
|
|
"epoch": 0.2070124879923151,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998608811283233,
|
|
"loss": 5.6215,
|
|
"mean_token_accuracy": 0.17871106863021852,
|
|
"num_tokens": 4956060.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.798979902267456,
|
|
"epoch": 0.207492795389049,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998596731061244,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.17223062068223954,
|
|
"num_tokens": 4967710.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.831351280212402,
|
|
"epoch": 0.2079731027857829,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998584598633516,
|
|
"loss": 5.6595,
|
|
"mean_token_accuracy": 0.1707835465669632,
|
|
"num_tokens": 4978716.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.831381130218506,
|
|
"epoch": 0.2084534101825168,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998572414000329,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.16959594637155534,
|
|
"num_tokens": 4990742.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.919949722290039,
|
|
"epoch": 0.20893371757925072,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998560177161969,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.17193486988544465,
|
|
"num_tokens": 5001217.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.807414817810058,
|
|
"epoch": 0.20941402497598463,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998547888118718,
|
|
"loss": 5.6645,
|
|
"mean_token_accuracy": 0.17050760686397554,
|
|
"num_tokens": 5012750.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.836668300628662,
|
|
"epoch": 0.20989433237271854,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998535546870862,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.18007341921329498,
|
|
"num_tokens": 5023818.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.917913913726807,
|
|
"epoch": 0.21037463976945245,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998523153418687,
|
|
"loss": 5.6925,
|
|
"mean_token_accuracy": 0.1711179181933403,
|
|
"num_tokens": 5035060.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.815863227844238,
|
|
"epoch": 0.21085494716618636,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998510707762481,
|
|
"loss": 5.733,
|
|
"mean_token_accuracy": 0.16495421826839446,
|
|
"num_tokens": 5046780.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.850568675994873,
|
|
"epoch": 0.21133525456292027,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998498209902533,
|
|
"loss": 5.6982,
|
|
"mean_token_accuracy": 0.16920250058174133,
|
|
"num_tokens": 5059152.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.817641115188598,
|
|
"epoch": 0.21181556195965417,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998485659839134,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.17348035871982576,
|
|
"num_tokens": 5069971.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.805312061309815,
|
|
"epoch": 0.21229586935638808,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998473057572575,
|
|
"loss": 5.6181,
|
|
"mean_token_accuracy": 0.17668834328651428,
|
|
"num_tokens": 5080640.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.8015978813171385,
|
|
"epoch": 0.212776176753122,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998460403103146,
|
|
"loss": 5.6379,
|
|
"mean_token_accuracy": 0.17368897497653962,
|
|
"num_tokens": 5091240.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.724646091461182,
|
|
"epoch": 0.2132564841498559,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998447696431146,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.17121760100126265,
|
|
"num_tokens": 5102920.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.8558906555175785,
|
|
"epoch": 0.2137367915465898,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998434937556865,
|
|
"loss": 5.6784,
|
|
"mean_token_accuracy": 0.16950192004442216,
|
|
"num_tokens": 5114240.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.941771984100342,
|
|
"epoch": 0.21421709894332372,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998422126480602,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.16069666296243668,
|
|
"num_tokens": 5126653.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.9492322444915775,
|
|
"epoch": 0.21469740634005763,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998409263202653,
|
|
"loss": 5.7472,
|
|
"mean_token_accuracy": 0.1665404573082924,
|
|
"num_tokens": 5138778.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.845252323150635,
|
|
"epoch": 0.21517771373679154,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998396347723318,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.17824865579605104,
|
|
"num_tokens": 5148670.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.624603366851806,
|
|
"epoch": 0.21565802113352545,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998383380042895,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.17016488909721375,
|
|
"num_tokens": 5159617.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.844017457962036,
|
|
"epoch": 0.21613832853025935,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998370360161688,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.17508894503116607,
|
|
"num_tokens": 5171225.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.878959703445434,
|
|
"epoch": 0.21661863592699326,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998357288079996,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.16998043954372405,
|
|
"num_tokens": 5184586.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.834930086135865,
|
|
"epoch": 0.21709894332372717,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998344163798125,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.16968356519937516,
|
|
"num_tokens": 5196089.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.834982538223267,
|
|
"epoch": 0.21757925072046108,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998330987316379,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.17092847377061843,
|
|
"num_tokens": 5207581.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.78864893913269,
|
|
"epoch": 0.21805955811719502,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998317758635062,
|
|
"loss": 5.6454,
|
|
"mean_token_accuracy": 0.17239997535943985,
|
|
"num_tokens": 5219108.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.828027296066284,
|
|
"epoch": 0.21853986551392893,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998304477754484,
|
|
"loss": 5.5916,
|
|
"mean_token_accuracy": 0.17449767142534256,
|
|
"num_tokens": 5231137.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.926539087295533,
|
|
"epoch": 0.21902017291066284,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998291144674952,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.1777758538722992,
|
|
"num_tokens": 5243528.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.6308393478393555,
|
|
"epoch": 0.21950048030739674,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998277759396776,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.17822325676679612,
|
|
"num_tokens": 5254869.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.7623279094696045,
|
|
"epoch": 0.21998078770413065,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998264321920265,
|
|
"loss": 5.6039,
|
|
"mean_token_accuracy": 0.1737493708729744,
|
|
"num_tokens": 5265370.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.752946853637695,
|
|
"epoch": 0.22046109510086456,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998250832245734,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.17435249984264373,
|
|
"num_tokens": 5277812.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.7676074504852295,
|
|
"epoch": 0.22094140249759847,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998237290373494,
|
|
"loss": 5.5722,
|
|
"mean_token_accuracy": 0.1777767837047577,
|
|
"num_tokens": 5289107.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.785541439056397,
|
|
"epoch": 0.22142170989433238,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499822369630386,
|
|
"loss": 5.6088,
|
|
"mean_token_accuracy": 0.16769287288188933,
|
|
"num_tokens": 5301489.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.68263053894043,
|
|
"epoch": 0.2219020172910663,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998210050037148,
|
|
"loss": 5.5856,
|
|
"mean_token_accuracy": 0.1790359228849411,
|
|
"num_tokens": 5313273.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.8171937465667725,
|
|
"epoch": 0.2223823246878002,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998196351573674,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.17444271743297576,
|
|
"num_tokens": 5324227.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.752804708480835,
|
|
"epoch": 0.2228626320845341,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998182600913757,
|
|
"loss": 5.5654,
|
|
"mean_token_accuracy": 0.17911654710769653,
|
|
"num_tokens": 5335138.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.734329175949097,
|
|
"epoch": 0.22334293948126802,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998168798057715,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.17262459695339202,
|
|
"num_tokens": 5345652.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.882148027420044,
|
|
"epoch": 0.22382324687800192,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499815494300587,
|
|
"loss": 5.7368,
|
|
"mean_token_accuracy": 0.16915619671344756,
|
|
"num_tokens": 5357999.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.817476558685303,
|
|
"epoch": 0.22430355427473583,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998141035758542,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.17220452576875686,
|
|
"num_tokens": 5369032.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.754540586471558,
|
|
"epoch": 0.22478386167146974,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998127076316054,
|
|
"loss": 5.5625,
|
|
"mean_token_accuracy": 0.17929039448499678,
|
|
"num_tokens": 5380692.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.843355941772461,
|
|
"epoch": 0.22526416906820365,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998113064678734,
|
|
"loss": 5.6892,
|
|
"mean_token_accuracy": 0.16779275834560395,
|
|
"num_tokens": 5392320.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.837249851226806,
|
|
"epoch": 0.22574447646493756,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998099000846901,
|
|
"loss": 5.6634,
|
|
"mean_token_accuracy": 0.17556915134191514,
|
|
"num_tokens": 5404374.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.825764131546021,
|
|
"epoch": 0.22622478386167147,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998084884820887,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.17142031490802764,
|
|
"num_tokens": 5415471.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.676828861236572,
|
|
"epoch": 0.22670509125840538,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998070716601016,
|
|
"loss": 5.5019,
|
|
"mean_token_accuracy": 0.1765056163072586,
|
|
"num_tokens": 5425971.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.79780216217041,
|
|
"epoch": 0.2271853986551393,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998056496187618,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.1789500296115875,
|
|
"num_tokens": 5437638.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.821310758590698,
|
|
"epoch": 0.2276657060518732,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998042223581025,
|
|
"loss": 5.6528,
|
|
"mean_token_accuracy": 0.1725280314683914,
|
|
"num_tokens": 5449463.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.799275064468384,
|
|
"epoch": 0.2281460134486071,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998027898781565,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.17100997567176818,
|
|
"num_tokens": 5460972.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.948947763442993,
|
|
"epoch": 0.228626320845341,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998013521789574,
|
|
"loss": 5.7269,
|
|
"mean_token_accuracy": 0.1655080497264862,
|
|
"num_tokens": 5471575.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.700678491592408,
|
|
"epoch": 0.22910662824207492,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997999092605384,
|
|
"loss": 5.5654,
|
|
"mean_token_accuracy": 0.17265488654375077,
|
|
"num_tokens": 5483041.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.7677713394165036,
|
|
"epoch": 0.22958693563880883,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499798461122933,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.17628835141658783,
|
|
"num_tokens": 5494040.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.69358229637146,
|
|
"epoch": 0.23006724303554274,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997970077661748,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.18428827673196793,
|
|
"num_tokens": 5504217.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.819785404205322,
|
|
"epoch": 0.23054755043227665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997955491902977,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.17342882454395295,
|
|
"num_tokens": 5517180.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.78384485244751,
|
|
"epoch": 0.23102785782901056,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997940853953354,
|
|
"loss": 5.5816,
|
|
"mean_token_accuracy": 0.17583905160427094,
|
|
"num_tokens": 5529626.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.810919857025146,
|
|
"epoch": 0.23150816522574447,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499792616381322,
|
|
"loss": 5.6114,
|
|
"mean_token_accuracy": 0.1800064906477928,
|
|
"num_tokens": 5540844.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.803003025054932,
|
|
"epoch": 0.23198847262247838,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997911421482914,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.17990489304065704,
|
|
"num_tokens": 5551732.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.806057739257812,
|
|
"epoch": 0.23246878001921228,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499789662696278,
|
|
"loss": 5.6818,
|
|
"mean_token_accuracy": 0.17363432347774505,
|
|
"num_tokens": 5562692.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.837599229812622,
|
|
"epoch": 0.2329490874159462,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997881780253162,
|
|
"loss": 5.6658,
|
|
"mean_token_accuracy": 0.17378875017166137,
|
|
"num_tokens": 5574884.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.689996194839478,
|
|
"epoch": 0.2334293948126801,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997866881354403,
|
|
"loss": 5.5141,
|
|
"mean_token_accuracy": 0.1813263177871704,
|
|
"num_tokens": 5585335.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.813428974151611,
|
|
"epoch": 0.23390970220941404,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499785193026685,
|
|
"loss": 5.666,
|
|
"mean_token_accuracy": 0.1711764082312584,
|
|
"num_tokens": 5597621.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.675594329833984,
|
|
"epoch": 0.23439000960614795,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997836926990851,
|
|
"loss": 5.5147,
|
|
"mean_token_accuracy": 0.1748025432229042,
|
|
"num_tokens": 5609795.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.757413482666015,
|
|
"epoch": 0.23487031700288186,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997821871526752,
|
|
"loss": 5.6207,
|
|
"mean_token_accuracy": 0.17631727755069732,
|
|
"num_tokens": 5621473.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.846551418304443,
|
|
"epoch": 0.23535062439961577,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997806763874905,
|
|
"loss": 5.7071,
|
|
"mean_token_accuracy": 0.1744229331612587,
|
|
"num_tokens": 5635064.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.882826089859009,
|
|
"epoch": 0.23583093179634967,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997791604035659,
|
|
"loss": 5.7063,
|
|
"mean_token_accuracy": 0.1706729456782341,
|
|
"num_tokens": 5647382.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.769627428054809,
|
|
"epoch": 0.23631123919308358,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997776392009366,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.1790638193488121,
|
|
"num_tokens": 5658417.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.74236798286438,
|
|
"epoch": 0.2367915465898175,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997761127796381,
|
|
"loss": 5.5629,
|
|
"mean_token_accuracy": 0.1808903470635414,
|
|
"num_tokens": 5672190.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.736099815368652,
|
|
"epoch": 0.2372718539865514,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997745811397056,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.1817570447921753,
|
|
"num_tokens": 5684259.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.679139423370361,
|
|
"epoch": 0.2377521613832853,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997730442811748,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.17837475389242172,
|
|
"num_tokens": 5696505.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.720158481597901,
|
|
"epoch": 0.23823246878001922,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997715022040814,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.1807715639472008,
|
|
"num_tokens": 5707638.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.720221424102784,
|
|
"epoch": 0.23871277617675313,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499769954908461,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.18572808802127838,
|
|
"num_tokens": 5719098.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.92160997390747,
|
|
"epoch": 0.23919308357348704,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997684023943498,
|
|
"loss": 5.742,
|
|
"mean_token_accuracy": 0.15980200469493866,
|
|
"num_tokens": 5731345.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.600750160217285,
|
|
"epoch": 0.23967339097022095,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997668446617837,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.17794736325740815,
|
|
"num_tokens": 5742604.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.677820205688477,
|
|
"epoch": 0.24015369836695485,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997652817107989,
|
|
"loss": 5.5214,
|
|
"mean_token_accuracy": 0.18534122705459594,
|
|
"num_tokens": 5754620.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.7748322010040285,
|
|
"epoch": 0.24063400576368876,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997637135414315,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.17856863886117935,
|
|
"num_tokens": 5764764.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.605795955657959,
|
|
"epoch": 0.24111431316042267,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997621401537183,
|
|
"loss": 5.4975,
|
|
"mean_token_accuracy": 0.18817870914936066,
|
|
"num_tokens": 5776341.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.8177571296691895,
|
|
"epoch": 0.24159462055715658,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997605615476955,
|
|
"loss": 5.717,
|
|
"mean_token_accuracy": 0.1655554562807083,
|
|
"num_tokens": 5788604.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.782369232177734,
|
|
"epoch": 0.2420749279538905,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997589777234,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.17745051085948943,
|
|
"num_tokens": 5800194.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.723162698745727,
|
|
"epoch": 0.2425552353506244,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997573886808684,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.1841670349240303,
|
|
"num_tokens": 5812978.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.698678493499756,
|
|
"epoch": 0.2430355427473583,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997557944201375,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.18675288707017898,
|
|
"num_tokens": 5824591.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.7060136795043945,
|
|
"epoch": 0.24351585014409222,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997541949412445,
|
|
"loss": 5.6051,
|
|
"mean_token_accuracy": 0.17518853545188903,
|
|
"num_tokens": 5835970.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.779909896850586,
|
|
"epoch": 0.24399615754082613,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997525902442266,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.17169417887926103,
|
|
"num_tokens": 5848687.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.723712730407715,
|
|
"epoch": 0.24447646493756003,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997509803291207,
|
|
"loss": 5.6057,
|
|
"mean_token_accuracy": 0.1737314537167549,
|
|
"num_tokens": 5860820.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.723750114440918,
|
|
"epoch": 0.24495677233429394,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997493651959647,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.18182809501886368,
|
|
"num_tokens": 5872172.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.743210744857788,
|
|
"epoch": 0.24543707973102785,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997477448447955,
|
|
"loss": 5.5897,
|
|
"mean_token_accuracy": 0.1766476571559906,
|
|
"num_tokens": 5883574.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.840282154083252,
|
|
"epoch": 0.24591738712776176,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997461192756512,
|
|
"loss": 5.6828,
|
|
"mean_token_accuracy": 0.17689221501350402,
|
|
"num_tokens": 5895223.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.701527786254883,
|
|
"epoch": 0.24639769452449567,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997444884885694,
|
|
"loss": 5.5116,
|
|
"mean_token_accuracy": 0.178897462785244,
|
|
"num_tokens": 5907448.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.728735780715942,
|
|
"epoch": 0.24687800192122958,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997428524835879,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.17883744686841965,
|
|
"num_tokens": 5918906.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.740764522552491,
|
|
"epoch": 0.2473583093179635,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997412112607446,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.18324243873357773,
|
|
"num_tokens": 5930619.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.808829116821289,
|
|
"epoch": 0.2478386167146974,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997395648200778,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.1694455027580261,
|
|
"num_tokens": 5941554.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.767109441757202,
|
|
"epoch": 0.2483189241114313,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997379131616257,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.18047072738409042,
|
|
"num_tokens": 5953309.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.707102966308594,
|
|
"epoch": 0.24879923150816521,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997362562854266,
|
|
"loss": 5.5915,
|
|
"mean_token_accuracy": 0.17505357414484024,
|
|
"num_tokens": 5965286.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.772854042053223,
|
|
"epoch": 0.24927953890489912,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997345941915187,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.18021601289510727,
|
|
"num_tokens": 5976558.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.757956790924072,
|
|
"epoch": 0.24975984630163303,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997329268799412,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.16917790919542314,
|
|
"num_tokens": 5988793.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.767512655258178,
|
|
"epoch": 0.25024015369836694,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997312543507322,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.16811801493167877,
|
|
"num_tokens": 5999825.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.757353258132935,
|
|
"epoch": 0.2507204610951009,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997295766039309,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.17652266919612886,
|
|
"num_tokens": 6010408.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.77374758720398,
|
|
"epoch": 0.25120076849183476,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997278936395761,
|
|
"loss": 5.6168,
|
|
"mean_token_accuracy": 0.17355270236730574,
|
|
"num_tokens": 6021161.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.654427337646484,
|
|
"epoch": 0.2516810758885687,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997262054577071,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.18697400987148285,
|
|
"num_tokens": 6032646.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.742709732055664,
|
|
"epoch": 0.2521613832853026,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997245120583627,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.17707106322050095,
|
|
"num_tokens": 6045019.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.6496696949005125,
|
|
"epoch": 0.2526416906820365,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997228134415825,
|
|
"loss": 5.5044,
|
|
"mean_token_accuracy": 0.18557969927787782,
|
|
"num_tokens": 6055644.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.749445962905884,
|
|
"epoch": 0.2531219980787704,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997211096074059,
|
|
"loss": 5.5559,
|
|
"mean_token_accuracy": 0.1822674036026001,
|
|
"num_tokens": 6066488.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.750200700759888,
|
|
"epoch": 0.25360230547550433,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997194005558722,
|
|
"loss": 5.5778,
|
|
"mean_token_accuracy": 0.1778818905353546,
|
|
"num_tokens": 6078300.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.687224864959717,
|
|
"epoch": 0.2540826128722382,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997176862870216,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.17298152297735214,
|
|
"num_tokens": 6089180.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.736628150939941,
|
|
"epoch": 0.25456292026897215,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997159668008933,
|
|
"loss": 5.5897,
|
|
"mean_token_accuracy": 0.18671621829271318,
|
|
"num_tokens": 6099093.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.749474334716797,
|
|
"epoch": 0.25504322766570603,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997142420975277,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.17849962413311005,
|
|
"num_tokens": 6109161.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.838236284255982,
|
|
"epoch": 0.25552353506243997,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997125121769647,
|
|
"loss": 5.7148,
|
|
"mean_token_accuracy": 0.16754066944122314,
|
|
"num_tokens": 6120031.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.6778631687164305,
|
|
"epoch": 0.25600384245917385,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997107770392444,
|
|
"loss": 5.5715,
|
|
"mean_token_accuracy": 0.17843878418207168,
|
|
"num_tokens": 6132398.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.6774248600006105,
|
|
"epoch": 0.2564841498559078,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499709036684407,
|
|
"loss": 5.5453,
|
|
"mean_token_accuracy": 0.17298439741134644,
|
|
"num_tokens": 6143099.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.722945070266723,
|
|
"epoch": 0.25696445725264166,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997072911124932,
|
|
"loss": 5.5244,
|
|
"mean_token_accuracy": 0.1837367057800293,
|
|
"num_tokens": 6154815.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.701107454299927,
|
|
"epoch": 0.2574447646493756,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997055403235432,
|
|
"loss": 5.5811,
|
|
"mean_token_accuracy": 0.18124920427799224,
|
|
"num_tokens": 6165696.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.690740966796875,
|
|
"epoch": 0.2579250720461095,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997037843175978,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.17476513981819153,
|
|
"num_tokens": 6177042.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.786804866790772,
|
|
"epoch": 0.2584053794428434,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997020230946978,
|
|
"loss": 5.5954,
|
|
"mean_token_accuracy": 0.17359965294599533,
|
|
"num_tokens": 6188691.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.580425882339478,
|
|
"epoch": 0.25888568683957736,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997002566548841,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.18495422154664992,
|
|
"num_tokens": 6199931.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.656063985824585,
|
|
"epoch": 0.25936599423631124,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996984849981976,
|
|
"loss": 5.5481,
|
|
"mean_token_accuracy": 0.18747731745243074,
|
|
"num_tokens": 6211493.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.758135843276977,
|
|
"epoch": 0.2598463016330452,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996967081246794,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.18370969891548156,
|
|
"num_tokens": 6221505.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.605699253082276,
|
|
"epoch": 0.26032660902977905,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996949260343711,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.18868651241064072,
|
|
"num_tokens": 6233058.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.705110359191894,
|
|
"epoch": 0.260806916426513,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996931387273137,
|
|
"loss": 5.6101,
|
|
"mean_token_accuracy": 0.1747105076909065,
|
|
"num_tokens": 6244713.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.716080856323242,
|
|
"epoch": 0.2612872238232469,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996913462035487,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.17616876363754272,
|
|
"num_tokens": 6256624.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.65197606086731,
|
|
"epoch": 0.2617675312199808,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499689548463118,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.17669420540332795,
|
|
"num_tokens": 6271134.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.815130949020386,
|
|
"epoch": 0.2622478386167147,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996877455060631,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.1788387343287468,
|
|
"num_tokens": 6282082.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.766822576522827,
|
|
"epoch": 0.2627281460134486,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996859373324259,
|
|
"loss": 5.6059,
|
|
"mean_token_accuracy": 0.17674000561237335,
|
|
"num_tokens": 6293869.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.676133012771606,
|
|
"epoch": 0.2632084534101825,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996841239422485,
|
|
"loss": 5.6232,
|
|
"mean_token_accuracy": 0.17271844148635865,
|
|
"num_tokens": 6304858.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.713190507888794,
|
|
"epoch": 0.26368876080691644,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996823053355729,
|
|
"loss": 5.5515,
|
|
"mean_token_accuracy": 0.18129074424505234,
|
|
"num_tokens": 6316738.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.679355955123901,
|
|
"epoch": 0.2641690682036503,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996804815124413,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.17863013297319413,
|
|
"num_tokens": 6327691.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.720383548736573,
|
|
"epoch": 0.26464937560038426,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996786524728962,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.1802159935235977,
|
|
"num_tokens": 6337964.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.613131427764893,
|
|
"epoch": 0.26512968299711814,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996768182169797,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.17915034890174866,
|
|
"num_tokens": 6349764.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.7847541809082035,
|
|
"epoch": 0.2656099903938521,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996749787447349,
|
|
"loss": 5.5324,
|
|
"mean_token_accuracy": 0.18092670440673828,
|
|
"num_tokens": 6360538.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.733683729171753,
|
|
"epoch": 0.26609029779058596,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499673134056204,
|
|
"loss": 5.5823,
|
|
"mean_token_accuracy": 0.1780352845788002,
|
|
"num_tokens": 6372489.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.526462173461914,
|
|
"epoch": 0.2665706051873199,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996712841514303,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.18955876380205156,
|
|
"num_tokens": 6383080.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.735677242279053,
|
|
"epoch": 0.2670509125840538,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996694290304563,
|
|
"loss": 5.5797,
|
|
"mean_token_accuracy": 0.17862945348024367,
|
|
"num_tokens": 6394033.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.6970155239105225,
|
|
"epoch": 0.2675312199807877,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996675686933255,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.17881778180599212,
|
|
"num_tokens": 6404990.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.6988551139831545,
|
|
"epoch": 0.2680115273775216,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996657031400807,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.18443361967802047,
|
|
"num_tokens": 6416337.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.689300441741944,
|
|
"epoch": 0.26849183477425553,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996638323707655,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.17969592064619064,
|
|
"num_tokens": 6427892.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.668305397033691,
|
|
"epoch": 0.2689721421709894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996619563854232,
|
|
"loss": 5.5535,
|
|
"mean_token_accuracy": 0.1804644450545311,
|
|
"num_tokens": 6440300.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.702674102783203,
|
|
"epoch": 0.26945244956772335,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996600751840974,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.184764464199543,
|
|
"num_tokens": 6451499.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.6231475353240965,
|
|
"epoch": 0.26993275696445723,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996581887668317,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.18376342356204986,
|
|
"num_tokens": 6462882.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.676126384735108,
|
|
"epoch": 0.27041306436119117,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049965629713367,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.1827904239296913,
|
|
"num_tokens": 6475042.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.673922348022461,
|
|
"epoch": 0.27089337175792505,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996544002846561,
|
|
"loss": 5.5345,
|
|
"mean_token_accuracy": 0.18013176023960115,
|
|
"num_tokens": 6486245.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.65201621055603,
|
|
"epoch": 0.271373679154659,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996524982198343,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.18405921012163162,
|
|
"num_tokens": 6497705.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.646395635604859,
|
|
"epoch": 0.27185398655139287,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996505909392485,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.18815743029117585,
|
|
"num_tokens": 6508193.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.656166219711304,
|
|
"epoch": 0.2723342939481268,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996486784429429,
|
|
"loss": 5.5878,
|
|
"mean_token_accuracy": 0.17944951206445695,
|
|
"num_tokens": 6519228.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.720212316513061,
|
|
"epoch": 0.2728146013448607,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996467607309622,
|
|
"loss": 5.5327,
|
|
"mean_token_accuracy": 0.1800275057554245,
|
|
"num_tokens": 6530743.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.637170839309692,
|
|
"epoch": 0.2732949087415946,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996448378033507,
|
|
"loss": 5.4248,
|
|
"mean_token_accuracy": 0.17780370265245438,
|
|
"num_tokens": 6542588.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.768726253509522,
|
|
"epoch": 0.2737752161383285,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996429096601532,
|
|
"loss": 5.6334,
|
|
"mean_token_accuracy": 0.1724066972732544,
|
|
"num_tokens": 6554002.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.740063047409057,
|
|
"epoch": 0.27425552353506244,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996409763014144,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.1790720894932747,
|
|
"num_tokens": 6563358.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.677773904800415,
|
|
"epoch": 0.2747358309317964,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996390377271791,
|
|
"loss": 5.5653,
|
|
"mean_token_accuracy": 0.17528493255376815,
|
|
"num_tokens": 6574986.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.6705268859863285,
|
|
"epoch": 0.27521613832853026,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996370939374924,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.18047979474067688,
|
|
"num_tokens": 6587407.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.591242885589599,
|
|
"epoch": 0.2756964457252642,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996351449323994,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.18611672520637512,
|
|
"num_tokens": 6598483.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.6495672225952145,
|
|
"epoch": 0.2761767531219981,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996331907119455,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.17973967641592026,
|
|
"num_tokens": 6610749.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.750370597839355,
|
|
"epoch": 0.276657060518732,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996312312761758,
|
|
"loss": 5.5389,
|
|
"mean_token_accuracy": 0.17384600937366484,
|
|
"num_tokens": 6621762.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.708437776565551,
|
|
"epoch": 0.2771373679154659,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499629266625136,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.17520614564418793,
|
|
"num_tokens": 6632296.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.702244853973388,
|
|
"epoch": 0.27761767531219983,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996272967588715,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.17878043949604033,
|
|
"num_tokens": 6644413.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.613515996932984,
|
|
"epoch": 0.2780979827089337,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996253216774283,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.18331679552793503,
|
|
"num_tokens": 6655634.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.636519432067871,
|
|
"epoch": 0.27857829010566765,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996233413808521,
|
|
"loss": 5.439,
|
|
"mean_token_accuracy": 0.18576697260141373,
|
|
"num_tokens": 6665977.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.716982173919678,
|
|
"epoch": 0.27905859750240153,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996213558691889,
|
|
"loss": 5.5078,
|
|
"mean_token_accuracy": 0.17724172174930572,
|
|
"num_tokens": 6677165.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.662445211410523,
|
|
"epoch": 0.27953890489913547,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996193651424848,
|
|
"loss": 5.6107,
|
|
"mean_token_accuracy": 0.17485882341861725,
|
|
"num_tokens": 6688182.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.6889976978302,
|
|
"epoch": 0.28001921229586935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499617369200786,
|
|
"loss": 5.526,
|
|
"mean_token_accuracy": 0.17932689487934111,
|
|
"num_tokens": 6699259.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.670577478408814,
|
|
"epoch": 0.2804995196926033,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996153680441389,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.1791873812675476,
|
|
"num_tokens": 6710071.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.654937314987182,
|
|
"epoch": 0.28097982708933716,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00049961336167259,
|
|
"loss": 5.5611,
|
|
"mean_token_accuracy": 0.18469414710998536,
|
|
"num_tokens": 6720267.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.754828691482544,
|
|
"epoch": 0.2814601344860711,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996113500861857,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.1751690164208412,
|
|
"num_tokens": 6730919.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.632857036590576,
|
|
"epoch": 0.281940441882805,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996093332849729,
|
|
"loss": 5.546,
|
|
"mean_token_accuracy": 0.18120535612106323,
|
|
"num_tokens": 6741480.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.709432744979859,
|
|
"epoch": 0.2824207492795389,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996073112689983,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.18390992283821106,
|
|
"num_tokens": 6751816.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.61135721206665,
|
|
"epoch": 0.2829010566762728,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996052840383088,
|
|
"loss": 5.5091,
|
|
"mean_token_accuracy": 0.17860084921121597,
|
|
"num_tokens": 6763645.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.656038093566894,
|
|
"epoch": 0.28338136407300674,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996032515929516,
|
|
"loss": 5.4791,
|
|
"mean_token_accuracy": 0.18455523252487183,
|
|
"num_tokens": 6774795.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.625377082824707,
|
|
"epoch": 0.2838616714697406,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996012139329738,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.18535638302564622,
|
|
"num_tokens": 6786833.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.528808164596557,
|
|
"epoch": 0.28434197886647455,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995991710584228,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.18870054185390472,
|
|
"num_tokens": 6798134.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.686023616790772,
|
|
"epoch": 0.28482228626320844,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995971229693459,
|
|
"loss": 5.528,
|
|
"mean_token_accuracy": 0.18367817848920823,
|
|
"num_tokens": 6807918.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.678937149047852,
|
|
"epoch": 0.28530259365994237,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995950696657909,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.17956380695104598,
|
|
"num_tokens": 6818689.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.626307201385498,
|
|
"epoch": 0.28578290105667625,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995930111478051,
|
|
"loss": 5.472,
|
|
"mean_token_accuracy": 0.18589290529489516,
|
|
"num_tokens": 6830871.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.633310222625733,
|
|
"epoch": 0.2862632084534102,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995909474154365,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.1886886775493622,
|
|
"num_tokens": 6842857.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.628792810440063,
|
|
"epoch": 0.28674351585014407,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995888784687331,
|
|
"loss": 5.4875,
|
|
"mean_token_accuracy": 0.18284399956464767,
|
|
"num_tokens": 6853727.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.7017065525054935,
|
|
"epoch": 0.287223823246878,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995868043077428,
|
|
"loss": 5.5282,
|
|
"mean_token_accuracy": 0.18200663477182388,
|
|
"num_tokens": 6864728.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.6810667514801025,
|
|
"epoch": 0.2877041306436119,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995847249325137,
|
|
"loss": 5.5912,
|
|
"mean_token_accuracy": 0.1790914699435234,
|
|
"num_tokens": 6875001.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.5915452003479,
|
|
"epoch": 0.2881844380403458,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995826403430942,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.19052988588809966,
|
|
"num_tokens": 6887026.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2881844380403458,
|
|
"eval_entropy": 5.464870153898614,
|
|
"eval_loss": 5.527435779571533,
|
|
"eval_mean_token_accuracy": 0.18901096377476345,
|
|
"eval_num_tokens": 6887026.0,
|
|
"eval_runtime": 20.7043,
|
|
"eval_samples_per_second": 1584.936,
|
|
"eval_steps_per_second": 198.123,
|
|
"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": 1569715698401280.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|