cvapict's picture
End of training
f52379d verified
raw
history blame
27.9 kB
{
"best_metric": 0.8221343873517787,
"best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-fe8x31a1/checkpoint-1600",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 1600,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.025,
"grad_norm": 2.465484380722046,
"learning_rate": 1.0183825327238303e-05,
"loss": 0.6569,
"step": 10
},
{
"epoch": 0.05,
"grad_norm": 2.43125319480896,
"learning_rate": 1.0119776111343723e-05,
"loss": 0.602,
"step": 20
},
{
"epoch": 0.075,
"grad_norm": 3.516777753829956,
"learning_rate": 1.0055726895449141e-05,
"loss": 0.5564,
"step": 30
},
{
"epoch": 0.1,
"grad_norm": 3.9462332725524902,
"learning_rate": 9.99167767955456e-06,
"loss": 0.5128,
"step": 40
},
{
"epoch": 0.125,
"grad_norm": 5.612371444702148,
"learning_rate": 9.92762846365998e-06,
"loss": 0.5192,
"step": 50
},
{
"epoch": 0.15,
"grad_norm": 6.378769397735596,
"learning_rate": 9.863579247765402e-06,
"loss": 0.4211,
"step": 60
},
{
"epoch": 0.175,
"grad_norm": 11.276257514953613,
"learning_rate": 9.799530031870821e-06,
"loss": 0.546,
"step": 70
},
{
"epoch": 0.2,
"grad_norm": 3.064713478088379,
"learning_rate": 9.735480815976239e-06,
"loss": 0.498,
"step": 80
},
{
"epoch": 0.225,
"grad_norm": 9.063024520874023,
"learning_rate": 9.671431600081659e-06,
"loss": 0.5396,
"step": 90
},
{
"epoch": 0.25,
"grad_norm": 4.74234676361084,
"learning_rate": 9.607382384187078e-06,
"loss": 0.4042,
"step": 100
},
{
"epoch": 0.275,
"grad_norm": 7.316481113433838,
"learning_rate": 9.543333168292498e-06,
"loss": 0.4045,
"step": 110
},
{
"epoch": 0.3,
"grad_norm": 22.763166427612305,
"learning_rate": 9.479283952397918e-06,
"loss": 0.5125,
"step": 120
},
{
"epoch": 0.325,
"grad_norm": 3.7233777046203613,
"learning_rate": 9.415234736503336e-06,
"loss": 0.3518,
"step": 130
},
{
"epoch": 0.35,
"grad_norm": 7.468355655670166,
"learning_rate": 9.351185520608755e-06,
"loss": 0.4669,
"step": 140
},
{
"epoch": 0.375,
"grad_norm": 11.998982429504395,
"learning_rate": 9.287136304714177e-06,
"loss": 0.5277,
"step": 150
},
{
"epoch": 0.4,
"grad_norm": 7.883176326751709,
"learning_rate": 9.223087088819596e-06,
"loss": 0.5429,
"step": 160
},
{
"epoch": 0.425,
"grad_norm": 4.340709686279297,
"learning_rate": 9.159037872925016e-06,
"loss": 0.3975,
"step": 170
},
{
"epoch": 0.45,
"grad_norm": 20.57011604309082,
"learning_rate": 9.094988657030434e-06,
"loss": 0.5238,
"step": 180
},
{
"epoch": 0.475,
"grad_norm": 9.75264835357666,
"learning_rate": 9.030939441135854e-06,
"loss": 0.3218,
"step": 190
},
{
"epoch": 0.5,
"grad_norm": 6.691798686981201,
"learning_rate": 8.966890225241273e-06,
"loss": 0.4217,
"step": 200
},
{
"epoch": 0.525,
"grad_norm": 18.962495803833008,
"learning_rate": 8.902841009346693e-06,
"loss": 0.4099,
"step": 210
},
{
"epoch": 0.55,
"grad_norm": 19.744651794433594,
"learning_rate": 8.838791793452112e-06,
"loss": 0.4664,
"step": 220
},
{
"epoch": 0.575,
"grad_norm": 2.020491361618042,
"learning_rate": 8.77474257755753e-06,
"loss": 0.4978,
"step": 230
},
{
"epoch": 0.6,
"grad_norm": 1.9042363166809082,
"learning_rate": 8.71069336166295e-06,
"loss": 0.7353,
"step": 240
},
{
"epoch": 0.625,
"grad_norm": 0.9909853935241699,
"learning_rate": 8.64664414576837e-06,
"loss": 0.2968,
"step": 250
},
{
"epoch": 0.65,
"grad_norm": 42.648502349853516,
"learning_rate": 8.582594929873791e-06,
"loss": 0.5019,
"step": 260
},
{
"epoch": 0.675,
"grad_norm": 25.46623992919922,
"learning_rate": 8.51854571397921e-06,
"loss": 0.5053,
"step": 270
},
{
"epoch": 0.7,
"grad_norm": 0.3692927658557892,
"learning_rate": 8.454496498084629e-06,
"loss": 0.3831,
"step": 280
},
{
"epoch": 0.725,
"grad_norm": 0.7488847970962524,
"learning_rate": 8.390447282190048e-06,
"loss": 0.398,
"step": 290
},
{
"epoch": 0.75,
"grad_norm": 17.168367385864258,
"learning_rate": 8.326398066295468e-06,
"loss": 0.2452,
"step": 300
},
{
"epoch": 0.775,
"grad_norm": 1.7695820331573486,
"learning_rate": 8.262348850400888e-06,
"loss": 0.542,
"step": 310
},
{
"epoch": 0.8,
"grad_norm": 65.51653289794922,
"learning_rate": 8.198299634506307e-06,
"loss": 0.5008,
"step": 320
},
{
"epoch": 0.825,
"grad_norm": 44.33673095703125,
"learning_rate": 8.134250418611725e-06,
"loss": 0.6469,
"step": 330
},
{
"epoch": 0.85,
"grad_norm": 0.41344940662384033,
"learning_rate": 8.070201202717145e-06,
"loss": 0.2898,
"step": 340
},
{
"epoch": 0.875,
"grad_norm": 3.3205506801605225,
"learning_rate": 8.006151986822566e-06,
"loss": 0.1732,
"step": 350
},
{
"epoch": 0.9,
"grad_norm": 14.04995059967041,
"learning_rate": 7.942102770927986e-06,
"loss": 0.2073,
"step": 360
},
{
"epoch": 0.925,
"grad_norm": 41.5389289855957,
"learning_rate": 7.878053555033405e-06,
"loss": 0.7956,
"step": 370
},
{
"epoch": 0.95,
"grad_norm": 6.405807018280029,
"learning_rate": 7.814004339138823e-06,
"loss": 0.1996,
"step": 380
},
{
"epoch": 0.975,
"grad_norm": 6.849510669708252,
"learning_rate": 7.749955123244243e-06,
"loss": 0.676,
"step": 390
},
{
"epoch": 1.0,
"grad_norm": 2.162174701690674,
"learning_rate": 7.685905907349663e-06,
"loss": 0.4163,
"step": 400
},
{
"epoch": 1.0,
"eval_accuracy": 0.875,
"eval_f1": 0.782608695652174,
"eval_loss": 0.4506184458732605,
"eval_precision": 0.8411214953271028,
"eval_recall": 0.7317073170731707,
"eval_runtime": 1.5181,
"eval_samples_per_second": 263.486,
"eval_steps_per_second": 16.468,
"step": 400
},
{
"epoch": 1.025,
"grad_norm": 2.081864595413208,
"learning_rate": 7.621856691455082e-06,
"loss": 0.4658,
"step": 410
},
{
"epoch": 1.05,
"grad_norm": 22.64581871032715,
"learning_rate": 7.557807475560502e-06,
"loss": 0.5153,
"step": 420
},
{
"epoch": 1.075,
"grad_norm": 0.2620379626750946,
"learning_rate": 7.493758259665921e-06,
"loss": 0.4354,
"step": 430
},
{
"epoch": 1.1,
"grad_norm": 10.08032512664795,
"learning_rate": 7.4297090437713405e-06,
"loss": 0.532,
"step": 440
},
{
"epoch": 1.125,
"grad_norm": 14.143264770507812,
"learning_rate": 7.36565982787676e-06,
"loss": 0.4678,
"step": 450
},
{
"epoch": 1.15,
"grad_norm": 1.1635172367095947,
"learning_rate": 7.30161061198218e-06,
"loss": 0.3581,
"step": 460
},
{
"epoch": 1.175,
"grad_norm": 0.33979693055152893,
"learning_rate": 7.237561396087599e-06,
"loss": 0.3167,
"step": 470
},
{
"epoch": 1.2,
"grad_norm": 76.80068969726562,
"learning_rate": 7.173512180193018e-06,
"loss": 0.7472,
"step": 480
},
{
"epoch": 1.225,
"grad_norm": 2.206153631210327,
"learning_rate": 7.109462964298438e-06,
"loss": 0.1161,
"step": 490
},
{
"epoch": 1.25,
"grad_norm": 0.474626749753952,
"learning_rate": 7.0454137484038575e-06,
"loss": 0.8155,
"step": 500
},
{
"epoch": 1.275,
"grad_norm": 0.23399832844734192,
"learning_rate": 6.981364532509277e-06,
"loss": 0.0966,
"step": 510
},
{
"epoch": 1.3,
"grad_norm": 0.5017552375793457,
"learning_rate": 6.917315316614697e-06,
"loss": 0.3474,
"step": 520
},
{
"epoch": 1.325,
"grad_norm": 0.15660956501960754,
"learning_rate": 6.853266100720116e-06,
"loss": 0.2475,
"step": 530
},
{
"epoch": 1.35,
"grad_norm": 0.13862070441246033,
"learning_rate": 6.789216884825535e-06,
"loss": 0.1474,
"step": 540
},
{
"epoch": 1.375,
"grad_norm": 0.12236533313989639,
"learning_rate": 6.725167668930955e-06,
"loss": 0.6624,
"step": 550
},
{
"epoch": 1.4,
"grad_norm": 0.17981773614883423,
"learning_rate": 6.6611184530363745e-06,
"loss": 0.5006,
"step": 560
},
{
"epoch": 1.425,
"grad_norm": 47.974552154541016,
"learning_rate": 6.597069237141794e-06,
"loss": 0.6282,
"step": 570
},
{
"epoch": 1.45,
"grad_norm": 33.56760025024414,
"learning_rate": 6.533020021247213e-06,
"loss": 0.3801,
"step": 580
},
{
"epoch": 1.475,
"grad_norm": 43.71825408935547,
"learning_rate": 6.468970805352633e-06,
"loss": 0.2156,
"step": 590
},
{
"epoch": 1.5,
"grad_norm": 8.383208274841309,
"learning_rate": 6.404921589458052e-06,
"loss": 0.5187,
"step": 600
},
{
"epoch": 1.525,
"grad_norm": 29.942264556884766,
"learning_rate": 6.340872373563472e-06,
"loss": 0.715,
"step": 610
},
{
"epoch": 1.55,
"grad_norm": 36.5871467590332,
"learning_rate": 6.2768231576688916e-06,
"loss": 0.3923,
"step": 620
},
{
"epoch": 1.575,
"grad_norm": 6.348372936248779,
"learning_rate": 6.21277394177431e-06,
"loss": 0.2363,
"step": 630
},
{
"epoch": 1.6,
"grad_norm": 0.7240210771560669,
"learning_rate": 6.14872472587973e-06,
"loss": 0.5193,
"step": 640
},
{
"epoch": 1.625,
"grad_norm": 17.27436065673828,
"learning_rate": 6.08467550998515e-06,
"loss": 0.4842,
"step": 650
},
{
"epoch": 1.65,
"grad_norm": 0.9968159794807434,
"learning_rate": 6.020626294090569e-06,
"loss": 0.3314,
"step": 660
},
{
"epoch": 1.675,
"grad_norm": 19.745121002197266,
"learning_rate": 5.956577078195989e-06,
"loss": 0.5173,
"step": 670
},
{
"epoch": 1.7,
"grad_norm": 25.66410255432129,
"learning_rate": 5.892527862301408e-06,
"loss": 0.3552,
"step": 680
},
{
"epoch": 1.725,
"grad_norm": 25.031274795532227,
"learning_rate": 5.828478646406827e-06,
"loss": 0.0588,
"step": 690
},
{
"epoch": 1.75,
"grad_norm": 38.753299713134766,
"learning_rate": 5.764429430512247e-06,
"loss": 0.2827,
"step": 700
},
{
"epoch": 1.775,
"grad_norm": 0.19221529364585876,
"learning_rate": 5.700380214617667e-06,
"loss": 0.3315,
"step": 710
},
{
"epoch": 1.8,
"grad_norm": 0.20989102125167847,
"learning_rate": 5.636330998723086e-06,
"loss": 0.4643,
"step": 720
},
{
"epoch": 1.825,
"grad_norm": 28.042871475219727,
"learning_rate": 5.572281782828505e-06,
"loss": 0.2059,
"step": 730
},
{
"epoch": 1.85,
"grad_norm": 0.9901361465454102,
"learning_rate": 5.508232566933925e-06,
"loss": 0.355,
"step": 740
},
{
"epoch": 1.875,
"grad_norm": 13.503495216369629,
"learning_rate": 5.4441833510393444e-06,
"loss": 0.2597,
"step": 750
},
{
"epoch": 1.9,
"grad_norm": 0.23809027671813965,
"learning_rate": 5.380134135144764e-06,
"loss": 0.0945,
"step": 760
},
{
"epoch": 1.925,
"grad_norm": 36.807735443115234,
"learning_rate": 5.316084919250184e-06,
"loss": 0.3779,
"step": 770
},
{
"epoch": 1.95,
"grad_norm": 27.212745666503906,
"learning_rate": 5.2520357033556025e-06,
"loss": 0.6778,
"step": 780
},
{
"epoch": 1.975,
"grad_norm": 6.413946628570557,
"learning_rate": 5.187986487461022e-06,
"loss": 0.4058,
"step": 790
},
{
"epoch": 2.0,
"grad_norm": 0.1529124528169632,
"learning_rate": 5.123937271566442e-06,
"loss": 0.3493,
"step": 800
},
{
"epoch": 2.0,
"eval_accuracy": 0.87,
"eval_f1": 0.803030303030303,
"eval_loss": 0.4885742962360382,
"eval_precision": 0.75177304964539,
"eval_recall": 0.8617886178861789,
"eval_runtime": 1.5266,
"eval_samples_per_second": 262.025,
"eval_steps_per_second": 16.377,
"step": 800
},
{
"epoch": 2.025,
"grad_norm": 9.217399597167969,
"learning_rate": 5.0598880556718615e-06,
"loss": 0.3507,
"step": 810
},
{
"epoch": 2.05,
"grad_norm": 0.30253663659095764,
"learning_rate": 4.99583883977728e-06,
"loss": 0.5887,
"step": 820
},
{
"epoch": 2.075,
"grad_norm": 64.33631896972656,
"learning_rate": 4.931789623882701e-06,
"loss": 0.3498,
"step": 830
},
{
"epoch": 2.1,
"grad_norm": 85.37213134765625,
"learning_rate": 4.8677404079881196e-06,
"loss": 0.4155,
"step": 840
},
{
"epoch": 2.125,
"grad_norm": 0.8680962324142456,
"learning_rate": 4.803691192093539e-06,
"loss": 0.3435,
"step": 850
},
{
"epoch": 2.15,
"grad_norm": 0.12275892496109009,
"learning_rate": 4.739641976198959e-06,
"loss": 0.3271,
"step": 860
},
{
"epoch": 2.175,
"grad_norm": 70.70037841796875,
"learning_rate": 4.675592760304378e-06,
"loss": 0.166,
"step": 870
},
{
"epoch": 2.2,
"grad_norm": 56.94752883911133,
"learning_rate": 4.611543544409798e-06,
"loss": 0.2044,
"step": 880
},
{
"epoch": 2.225,
"grad_norm": 1.558278203010559,
"learning_rate": 4.547494328515217e-06,
"loss": 0.2045,
"step": 890
},
{
"epoch": 2.25,
"grad_norm": 60.74308395385742,
"learning_rate": 4.483445112620637e-06,
"loss": 0.3747,
"step": 900
},
{
"epoch": 2.275,
"grad_norm": 4.4130167961120605,
"learning_rate": 4.419395896726056e-06,
"loss": 0.2812,
"step": 910
},
{
"epoch": 2.3,
"grad_norm": 0.4344184398651123,
"learning_rate": 4.355346680831475e-06,
"loss": 0.5069,
"step": 920
},
{
"epoch": 2.325,
"grad_norm": 1.5964275598526,
"learning_rate": 4.2912974649368955e-06,
"loss": 0.3639,
"step": 930
},
{
"epoch": 2.35,
"grad_norm": 0.10798884928226471,
"learning_rate": 4.227248249042314e-06,
"loss": 0.4477,
"step": 940
},
{
"epoch": 2.375,
"grad_norm": 0.1452270895242691,
"learning_rate": 4.163199033147734e-06,
"loss": 0.0609,
"step": 950
},
{
"epoch": 2.4,
"grad_norm": 1.5391632318496704,
"learning_rate": 4.099149817253154e-06,
"loss": 0.4871,
"step": 960
},
{
"epoch": 2.425,
"grad_norm": 0.310716450214386,
"learning_rate": 4.035100601358572e-06,
"loss": 0.3586,
"step": 970
},
{
"epoch": 2.45,
"grad_norm": 0.0929633229970932,
"learning_rate": 3.971051385463993e-06,
"loss": 0.142,
"step": 980
},
{
"epoch": 2.475,
"grad_norm": 72.40925598144531,
"learning_rate": 3.907002169569412e-06,
"loss": 0.2806,
"step": 990
},
{
"epoch": 2.5,
"grad_norm": 11.580459594726562,
"learning_rate": 3.842952953674831e-06,
"loss": 0.2034,
"step": 1000
},
{
"epoch": 2.525,
"grad_norm": 0.12087017297744751,
"learning_rate": 3.778903737780251e-06,
"loss": 0.2401,
"step": 1010
},
{
"epoch": 2.55,
"grad_norm": 19.90984344482422,
"learning_rate": 3.7148545218856702e-06,
"loss": 0.5233,
"step": 1020
},
{
"epoch": 2.575,
"grad_norm": 7.508769512176514,
"learning_rate": 3.65080530599109e-06,
"loss": 0.3914,
"step": 1030
},
{
"epoch": 2.6,
"grad_norm": 0.2051800787448883,
"learning_rate": 3.586756090096509e-06,
"loss": 0.1612,
"step": 1040
},
{
"epoch": 2.625,
"grad_norm": 0.07582038640975952,
"learning_rate": 3.5227068742019287e-06,
"loss": 0.2666,
"step": 1050
},
{
"epoch": 2.65,
"grad_norm": 8.369606971740723,
"learning_rate": 3.4586576583073484e-06,
"loss": 0.3709,
"step": 1060
},
{
"epoch": 2.675,
"grad_norm": 1.155171275138855,
"learning_rate": 3.3946084424127676e-06,
"loss": 0.1559,
"step": 1070
},
{
"epoch": 2.7,
"grad_norm": 0.2200879603624344,
"learning_rate": 3.3305592265181873e-06,
"loss": 0.4052,
"step": 1080
},
{
"epoch": 2.725,
"grad_norm": 0.4829643964767456,
"learning_rate": 3.2665100106236065e-06,
"loss": 0.2918,
"step": 1090
},
{
"epoch": 2.75,
"grad_norm": 56.13560485839844,
"learning_rate": 3.202460794729026e-06,
"loss": 0.5361,
"step": 1100
},
{
"epoch": 2.775,
"grad_norm": 90.05322265625,
"learning_rate": 3.1384115788344458e-06,
"loss": 0.2005,
"step": 1110
},
{
"epoch": 2.8,
"grad_norm": 7.227364540100098,
"learning_rate": 3.074362362939865e-06,
"loss": 0.3012,
"step": 1120
},
{
"epoch": 2.825,
"grad_norm": 2.593374490737915,
"learning_rate": 3.0103131470452847e-06,
"loss": 0.3023,
"step": 1130
},
{
"epoch": 2.85,
"grad_norm": 0.11675723642110825,
"learning_rate": 2.946263931150704e-06,
"loss": 0.5068,
"step": 1140
},
{
"epoch": 2.875,
"grad_norm": 18.220458984375,
"learning_rate": 2.8822147152561235e-06,
"loss": 0.7038,
"step": 1150
},
{
"epoch": 2.9,
"grad_norm": 24.797286987304688,
"learning_rate": 2.818165499361543e-06,
"loss": 0.2784,
"step": 1160
},
{
"epoch": 2.925,
"grad_norm": 0.1621352583169937,
"learning_rate": 2.7541162834669624e-06,
"loss": 0.3992,
"step": 1170
},
{
"epoch": 2.95,
"grad_norm": 5.978437423706055,
"learning_rate": 2.690067067572382e-06,
"loss": 0.2153,
"step": 1180
},
{
"epoch": 2.975,
"grad_norm": 3.2128543853759766,
"learning_rate": 2.6260178516778013e-06,
"loss": 0.0851,
"step": 1190
},
{
"epoch": 3.0,
"grad_norm": 0.09984573721885681,
"learning_rate": 2.561968635783221e-06,
"loss": 0.185,
"step": 1200
},
{
"epoch": 3.0,
"eval_accuracy": 0.8825,
"eval_f1": 0.8097165991902834,
"eval_loss": 0.44865548610687256,
"eval_precision": 0.8064516129032258,
"eval_recall": 0.8130081300813008,
"eval_runtime": 1.5206,
"eval_samples_per_second": 263.061,
"eval_steps_per_second": 16.441,
"step": 1200
},
{
"epoch": 3.025,
"grad_norm": 0.31235378980636597,
"learning_rate": 2.49791941988864e-06,
"loss": 0.1404,
"step": 1210
},
{
"epoch": 3.05,
"grad_norm": 0.2695654034614563,
"learning_rate": 2.4338702039940598e-06,
"loss": 0.008,
"step": 1220
},
{
"epoch": 3.075,
"grad_norm": 1.723610758781433,
"learning_rate": 2.3698209880994794e-06,
"loss": 0.4498,
"step": 1230
},
{
"epoch": 3.1,
"grad_norm": 16.759214401245117,
"learning_rate": 2.305771772204899e-06,
"loss": 0.328,
"step": 1240
},
{
"epoch": 3.125,
"grad_norm": 1.0185809135437012,
"learning_rate": 2.2417225563103183e-06,
"loss": 0.3204,
"step": 1250
},
{
"epoch": 3.15,
"grad_norm": 55.74982833862305,
"learning_rate": 2.1776733404157375e-06,
"loss": 0.3453,
"step": 1260
},
{
"epoch": 3.175,
"grad_norm": 1.2274974584579468,
"learning_rate": 2.113624124521157e-06,
"loss": 0.0774,
"step": 1270
},
{
"epoch": 3.2,
"grad_norm": 5.082088470458984,
"learning_rate": 2.049574908626577e-06,
"loss": 0.3043,
"step": 1280
},
{
"epoch": 3.225,
"grad_norm": 0.10691297054290771,
"learning_rate": 1.9855256927319965e-06,
"loss": 0.3526,
"step": 1290
},
{
"epoch": 3.25,
"grad_norm": 0.19949033856391907,
"learning_rate": 1.9214764768374157e-06,
"loss": 0.4051,
"step": 1300
},
{
"epoch": 3.275,
"grad_norm": 0.6929848790168762,
"learning_rate": 1.8574272609428351e-06,
"loss": 0.3021,
"step": 1310
},
{
"epoch": 3.3,
"grad_norm": 0.11993855237960815,
"learning_rate": 1.7933780450482546e-06,
"loss": 0.1488,
"step": 1320
},
{
"epoch": 3.325,
"grad_norm": 66.17958068847656,
"learning_rate": 1.7293288291536742e-06,
"loss": 0.5091,
"step": 1330
},
{
"epoch": 3.35,
"grad_norm": 0.1274821162223816,
"learning_rate": 1.6652796132590936e-06,
"loss": 0.1949,
"step": 1340
},
{
"epoch": 3.375,
"grad_norm": 31.55275535583496,
"learning_rate": 1.601230397364513e-06,
"loss": 0.0591,
"step": 1350
},
{
"epoch": 3.4,
"grad_norm": 0.058220572769641876,
"learning_rate": 1.5371811814699325e-06,
"loss": 0.1784,
"step": 1360
},
{
"epoch": 3.425,
"grad_norm": 0.42207491397857666,
"learning_rate": 1.473131965575352e-06,
"loss": 0.224,
"step": 1370
},
{
"epoch": 3.45,
"grad_norm": 3.044186592102051,
"learning_rate": 1.4090827496807716e-06,
"loss": 0.0545,
"step": 1380
},
{
"epoch": 3.475,
"grad_norm": 0.08542516827583313,
"learning_rate": 1.345033533786191e-06,
"loss": 0.2772,
"step": 1390
},
{
"epoch": 3.5,
"grad_norm": 0.05780614912509918,
"learning_rate": 1.2809843178916105e-06,
"loss": 0.1839,
"step": 1400
},
{
"epoch": 3.525,
"grad_norm": 0.17887786030769348,
"learning_rate": 1.2169351019970299e-06,
"loss": 0.4968,
"step": 1410
},
{
"epoch": 3.55,
"grad_norm": 8.942314147949219,
"learning_rate": 1.1528858861024495e-06,
"loss": 0.2654,
"step": 1420
},
{
"epoch": 3.575,
"grad_norm": 0.060382865369319916,
"learning_rate": 1.0888366702078688e-06,
"loss": 0.3845,
"step": 1430
},
{
"epoch": 3.6,
"grad_norm": 0.06488844007253647,
"learning_rate": 1.0247874543132884e-06,
"loss": 0.2024,
"step": 1440
},
{
"epoch": 3.625,
"grad_norm": 0.14169873297214508,
"learning_rate": 9.607382384187078e-07,
"loss": 0.0238,
"step": 1450
},
{
"epoch": 3.65,
"grad_norm": 0.2857815623283386,
"learning_rate": 8.966890225241273e-07,
"loss": 0.0512,
"step": 1460
},
{
"epoch": 3.675,
"grad_norm": 2.5256128311157227,
"learning_rate": 8.326398066295468e-07,
"loss": 0.5249,
"step": 1470
},
{
"epoch": 3.7,
"grad_norm": 0.10582108050584793,
"learning_rate": 7.685905907349663e-07,
"loss": 0.2432,
"step": 1480
},
{
"epoch": 3.725,
"grad_norm": 0.14601752161979675,
"learning_rate": 7.045413748403858e-07,
"loss": 0.0423,
"step": 1490
},
{
"epoch": 3.75,
"grad_norm": 0.12057498842477798,
"learning_rate": 6.404921589458052e-07,
"loss": 0.3617,
"step": 1500
},
{
"epoch": 3.775,
"grad_norm": 0.3876931965351105,
"learning_rate": 5.764429430512248e-07,
"loss": 0.3447,
"step": 1510
},
{
"epoch": 3.8,
"grad_norm": 0.1493206024169922,
"learning_rate": 5.123937271566442e-07,
"loss": 0.1157,
"step": 1520
},
{
"epoch": 3.825,
"grad_norm": 0.06613587588071823,
"learning_rate": 4.4834451126206364e-07,
"loss": 0.0055,
"step": 1530
},
{
"epoch": 3.85,
"grad_norm": 1.067234992980957,
"learning_rate": 3.842952953674831e-07,
"loss": 0.2564,
"step": 1540
},
{
"epoch": 3.875,
"grad_norm": 0.3370356559753418,
"learning_rate": 3.202460794729026e-07,
"loss": 0.4938,
"step": 1550
},
{
"epoch": 3.9,
"grad_norm": 36.366207122802734,
"learning_rate": 2.561968635783221e-07,
"loss": 0.7624,
"step": 1560
},
{
"epoch": 3.925,
"grad_norm": 2.3503971099853516,
"learning_rate": 1.9214764768374156e-07,
"loss": 0.6955,
"step": 1570
},
{
"epoch": 3.95,
"grad_norm": 0.06582440435886383,
"learning_rate": 1.2809843178916105e-07,
"loss": 0.1656,
"step": 1580
},
{
"epoch": 3.975,
"grad_norm": 0.24124383926391602,
"learning_rate": 6.404921589458053e-08,
"loss": 0.1119,
"step": 1590
},
{
"epoch": 4.0,
"grad_norm": 26.87814712524414,
"learning_rate": 0.0,
"loss": 0.1595,
"step": 1600
},
{
"epoch": 4.0,
"eval_accuracy": 0.8875,
"eval_f1": 0.8221343873517787,
"eval_loss": 0.48518621921539307,
"eval_precision": 0.8,
"eval_recall": 0.8455284552845529,
"eval_runtime": 1.5632,
"eval_samples_per_second": 255.89,
"eval_steps_per_second": 15.993,
"step": 1600
}
],
"logging_steps": 10,
"max_steps": 1600,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 847261481803776.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": {
"_wandb": {},
"assignments": {},
"learning_rate": 1.0247874543132884e-05,
"metric": "eval/loss",
"num_train_epochs": 4,
"per_device_train_batch_size": 4,
"seed": 13
}
}