abhinavp's picture
Training in progress, epoch 0, checkpoint
6944d0a verified
raw
history blame contribute delete
No virus
19 kB
{
"best_metric": 4.807467460632324,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/lstm/4/checkpoints/checkpoint-76319",
"epoch": 0.025000278439663435,
"eval_steps": 10,
"global_step": 76319,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.8203,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5858,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0564,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9814,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9507,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8259,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.677,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.5732,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5007,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4261,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3802,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3211,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2596,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.1876,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1243,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0805,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0353,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 5.9862,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.954,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9125,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8839,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.847,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8118,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.7882,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7578,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7294,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7056,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6831,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6504,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.975684027980238e-05,
"loss": 5.6354,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.974845433229186e-05,
"loss": 5.6081,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974006838478134e-05,
"loss": 5.5898,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5751,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.5586,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714926921053515e-05,
"loss": 5.537,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706540973542995e-05,
"loss": 5.5273,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5134,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.9689785457325684e-05,
"loss": 5.4933,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4748,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4653,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4374,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4368,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.4078,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.4081,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963110020355577e-05,
"loss": 5.4001,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962271425604525e-05,
"loss": 5.3892,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961432830853473e-05,
"loss": 5.3635,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960595873982795e-05,
"loss": 5.3616,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959757279231743e-05,
"loss": 5.3566,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958918684480691e-05,
"loss": 5.3346,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958080089729639e-05,
"loss": 5.3186,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3159,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956404538107908e-05,
"loss": 5.3217,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955565943356856e-05,
"loss": 5.2884,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954727348605804e-05,
"loss": 5.3088,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953888753854752e-05,
"loss": 5.2688,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530501591037e-05,
"loss": 5.2788,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952211564352648e-05,
"loss": 5.2563,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951372969601596e-05,
"loss": 5.2536,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.9505360127309166e-05,
"loss": 5.2447,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.9496974179798646e-05,
"loss": 5.2383,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.2191,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948021866358134e-05,
"loss": 5.2251,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.2083,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.2142,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.1957,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.1863,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943830530483247e-05,
"loss": 5.171,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942991935732195e-05,
"loss": 5.1783,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942153340981143e-05,
"loss": 5.171,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413147462300904e-05,
"loss": 5.1507,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404761514790384e-05,
"loss": 5.1532,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.93963919460836e-05,
"loss": 5.1456,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938800599857309e-05,
"loss": 5.1426,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.937962005106256e-05,
"loss": 5.1385,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.937123410355204e-05,
"loss": 5.1328,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1197,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935447858733473e-05,
"loss": 5.1023,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934609263982421e-05,
"loss": 5.1096,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.1014,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329337123606905e-05,
"loss": 5.1026,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932095117609638e-05,
"loss": 5.0947,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931256522858586e-05,
"loss": 5.0829,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930417928107534e-05,
"loss": 5.0623,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295793333564825e-05,
"loss": 5.0691,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287407386054305e-05,
"loss": 5.0699,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279021438543785e-05,
"loss": 5.0664,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270635491033264e-05,
"loss": 5.0555,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262249543522744e-05,
"loss": 5.0486,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.9253863596012224e-05,
"loss": 5.0377,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.9245494027305433e-05,
"loss": 5.0314,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923712445859864e-05,
"loss": 5.0285,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922873851108812e-05,
"loss": 5.036,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92203525635776e-05,
"loss": 5.0258,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921196661606708e-05,
"loss": 5.001,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920358066855656e-05,
"loss": 5.0041,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 5.0092,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918682515233926e-05,
"loss": 5.0057,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917843920482874e-05,
"loss": 4.9939,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917005325731822e-05,
"loss": 4.9939,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.91616673098077e-05,
"loss": 4.9805,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915328136229718e-05,
"loss": 4.9795,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914489541478666e-05,
"loss": 4.9856,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913650946727614e-05,
"loss": 4.9799,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912812351976562e-05,
"loss": 4.9539,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911973757225509e-05,
"loss": 4.9633,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911136800354831e-05,
"loss": 4.9453,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910298205603779e-05,
"loss": 4.9493,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909459610852727e-05,
"loss": 4.9463,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908621016101675e-05,
"loss": 4.9355,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907784059230996e-05,
"loss": 4.9335,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906945464479944e-05,
"loss": 4.9238,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906106869728892e-05,
"loss": 4.9227,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905269912858213e-05,
"loss": 4.9195,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904431318107161e-05,
"loss": 4.9317,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903592723356109e-05,
"loss": 4.9073,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027541286050565e-05,
"loss": 4.8913,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019155338540045e-05,
"loss": 4.9003,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010769391029525e-05,
"loss": 4.9118,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002383443519005e-05,
"loss": 4.8951,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8993997496008485e-05,
"loss": 4.902,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985611548497965e-05,
"loss": 4.8905,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977225600987445e-05,
"loss": 4.8913,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968839653476924e-05,
"loss": 4.8753,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.896045370596641e-05,
"loss": 4.8795,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895208413725962e-05,
"loss": 4.8731,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.89436981897491e-05,
"loss": 4.8774,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893532862104231e-05,
"loss": 4.8563,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892694267353179e-05,
"loss": 4.8654,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891855672602127e-05,
"loss": 4.8617,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891017077851075e-05,
"loss": 4.8474,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890178483100023e-05,
"loss": 4.8574,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889341526229344e-05,
"loss": 4.8488,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888502931478292e-05,
"loss": 4.8536,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766433672724e-05,
"loss": 4.849,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886825741976188e-05,
"loss": 4.8315,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.8859871472251365e-05,
"loss": 4.8282,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.8851485524740845e-05,
"loss": 4.826,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.8843099577230325e-05,
"loss": 4.8316,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.8834713629719805e-05,
"loss": 4.8389,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.8826344061013014e-05,
"loss": 4.8268,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.8817958113502494e-05,
"loss": 4.8165,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809572165991974e-05,
"loss": 4.8127,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801186218481454e-05,
"loss": 4.8129,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879281664977466e-05,
"loss": 4.8089,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878443070226414e-05,
"loss": 4.8047,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877604475475362e-05,
"loss": 4.8191,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876767518604683e-05,
"loss": 4.8028,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875928923853632e-05,
"loss": 4.7948,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.87509032910258e-05,
"loss": 4.7906,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.807467460632324,
"eval_runtime": 553.5364,
"eval_samples_per_second": 689.369,
"eval_steps_per_second": 21.543,
"step": 76319
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 2.9368961346747852e+16,
"trial_name": null,
"trial_params": null
}