abhinavp's picture
Training in progress, epoch 1, checkpoint
ad4916d verified
raw
history blame
No virus
37.5 kB
{
"best_metric": 4.028327941894531,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sim-ques/transformer/1/checkpoints/checkpoint-152640",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 152640,
"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": 10.9382,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.826,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1933,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9815,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8161,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7147,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6058,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5348,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4544,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4065,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3447,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3244,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2734,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2075,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1803,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1381,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1198,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0787,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0487,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0242,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0053,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 4.9826,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 4.9623,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9436,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9222,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.9004,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 4.8719,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8583,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8359,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8294,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 4.8119,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7943,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7855,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7653,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.762,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7567,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7372,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.7022,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 4.7115,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 4.6834,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 4.6802,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6767,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6705,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6538,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6545,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6442,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6358,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6269,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6037,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5997,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.6056,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.59,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5756,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5619,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.567,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5488,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5649,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5377,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5431,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5365,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5124,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5203,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5076,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4985,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4938,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5108,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4864,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4767,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4631,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4641,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4802,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4789,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.452,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4699,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4646,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4497,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4352,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4412,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4291,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4237,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4241,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4196,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4237,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.4206,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.4004,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928747290126923e-05,
"loss": 4.4059,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927908695375871e-05,
"loss": 4.406,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927070100624819e-05,
"loss": 4.3959,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.3922,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3894,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3909,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3782,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3787,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3736,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3766,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3702,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3642,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3493,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.3549,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3581,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.363,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.91533468775121e-05,
"loss": 4.3484,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914497730880531e-05,
"loss": 4.3387,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913659136129479e-05,
"loss": 4.3349,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912820541378427e-05,
"loss": 4.342,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911981946627375e-05,
"loss": 4.313,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111449897566966e-05,
"loss": 4.3225,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103063950056446e-05,
"loss": 4.3247,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.9094678002545926e-05,
"loss": 4.3234,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.9086292055035406e-05,
"loss": 4.315,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.9077906107524886e-05,
"loss": 4.3224,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.9069520160014366e-05,
"loss": 4.304,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.9061134212503846e-05,
"loss": 4.3314,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052764643797055e-05,
"loss": 4.3106,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.9044378696286535e-05,
"loss": 4.3122,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.9035992748776015e-05,
"loss": 4.3161,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027606801265495e-05,
"loss": 4.3239,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901925361136244e-05,
"loss": 4.3014,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901086766385192e-05,
"loss": 4.2956,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024817163414e-05,
"loss": 4.3012,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899409576883088e-05,
"loss": 4.2905,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.898570982132036e-05,
"loss": 4.296,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897732387380984e-05,
"loss": 4.2919,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.896893792629932e-05,
"loss": 4.2813,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.89605519787888e-05,
"loss": 4.2991,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895216603127827e-05,
"loss": 4.2806,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.894378008376775e-05,
"loss": 4.2753,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893539413625723e-05,
"loss": 4.2735,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892702456755045e-05,
"loss": 4.2789,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891863862003992e-05,
"loss": 4.2657,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891025267252941e-05,
"loss": 4.2818,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890186672501889e-05,
"loss": 4.2754,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889348077750837e-05,
"loss": 4.2619,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888511120880158e-05,
"loss": 4.2563,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887672526129106e-05,
"loss": 4.2654,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886833931378054e-05,
"loss": 4.2615,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885995336627002e-05,
"loss": 4.2658,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.2614,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2621,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2574,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.8826425955031666e-05,
"loss": 4.2517,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.8818040007521146e-05,
"loss": 4.2434,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809654060010626e-05,
"loss": 4.2421,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801268112500106e-05,
"loss": 4.2489,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879289854379332e-05,
"loss": 4.2279,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87845125962828e-05,
"loss": 4.2491,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877612664877228e-05,
"loss": 4.2438,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876774070126176e-05,
"loss": 4.235,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875937113255497e-05,
"loss": 4.2363,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875098518504445e-05,
"loss": 4.2375,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.197122573852539,
"eval_runtime": 304.6949,
"eval_samples_per_second": 1252.371,
"eval_steps_per_second": 39.138,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874259923753393e-05,
"loss": 4.2118,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873421329002341e-05,
"loss": 4.2212,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872582734251289e-05,
"loss": 4.2319,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.2169,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870907182629558e-05,
"loss": 4.2223,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870068587878506e-05,
"loss": 4.2114,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869229993127454e-05,
"loss": 4.2099,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683913983764027e-05,
"loss": 4.2038,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675544415057236e-05,
"loss": 4.2136,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667158467546716e-05,
"loss": 4.2008,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658772520036196e-05,
"loss": 4.2208,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.8650386572525676e-05,
"loss": 4.2138,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642017003818885e-05,
"loss": 4.1972,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633631056308365e-05,
"loss": 4.1927,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625245108797845e-05,
"loss": 4.1911,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616859161287324e-05,
"loss": 4.1901,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608473213776804e-05,
"loss": 4.1857,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860008726626628e-05,
"loss": 4.1877,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591701318755764e-05,
"loss": 4.1811,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583315371245244e-05,
"loss": 4.1961,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857494580253846e-05,
"loss": 4.187,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856655985502793e-05,
"loss": 4.1907,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855817390751741e-05,
"loss": 4.1848,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854978796000689e-05,
"loss": 4.193,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854141839130011e-05,
"loss": 4.1705,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853303244378958e-05,
"loss": 4.1724,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852464649627906e-05,
"loss": 4.1686,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851626054876854e-05,
"loss": 4.1664,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850787460125802e-05,
"loss": 4.1681,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849950503255123e-05,
"loss": 4.1642,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849111908504072e-05,
"loss": 4.1682,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.84827331375302e-05,
"loss": 4.1683,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847434719001968e-05,
"loss": 4.1558,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846596124250916e-05,
"loss": 4.1638,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845759167380237e-05,
"loss": 4.1717,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844920572629185e-05,
"loss": 4.1582,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844081977878133e-05,
"loss": 4.142,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843243383127081e-05,
"loss": 4.1544,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842404788376029e-05,
"loss": 4.1361,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.8415678315053496e-05,
"loss": 4.1461,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.8407292367542976e-05,
"loss": 4.1464,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398906420032456e-05,
"loss": 4.1525,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.8390520472521936e-05,
"loss": 4.141,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838215090381515e-05,
"loss": 4.1467,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837376495630463e-05,
"loss": 4.1494,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836537900879411e-05,
"loss": 4.1421,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835699306128359e-05,
"loss": 4.1426,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.83486234925768e-05,
"loss": 4.1252,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834023754506628e-05,
"loss": 4.1329,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833185159755576e-05,
"loss": 4.1394,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832346565004524e-05,
"loss": 4.1323,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831509608133845e-05,
"loss": 4.1257,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830671013382793e-05,
"loss": 4.1142,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829832418631741e-05,
"loss": 4.1276,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828993823880689e-05,
"loss": 4.1141,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281568670100105e-05,
"loss": 4.1299,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273182722589585e-05,
"loss": 4.1168,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264796775079065e-05,
"loss": 4.1247,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256410827568545e-05,
"loss": 4.1261,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248024880058025e-05,
"loss": 4.1024,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239655311351234e-05,
"loss": 4.1144,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231269363840714e-05,
"loss": 4.1134,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222883416330194e-05,
"loss": 4.1049,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214497468819674e-05,
"loss": 4.105,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820612790011288e-05,
"loss": 4.1212,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819774195260236e-05,
"loss": 4.1081,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818935600509184e-05,
"loss": 4.0982,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818097005758132e-05,
"loss": 4.0898,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817260048887454e-05,
"loss": 4.0973,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816421454136402e-05,
"loss": 4.1121,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.81558285938535e-05,
"loss": 4.1155,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814744264634298e-05,
"loss": 4.0991,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813907307763619e-05,
"loss": 4.1138,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813068713012567e-05,
"loss": 4.1089,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812230118261515e-05,
"loss": 4.1027,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811391523510463e-05,
"loss": 4.0885,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810554566639784e-05,
"loss": 4.1034,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809715971888732e-05,
"loss": 4.0917,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887737713768e-05,
"loss": 4.0896,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808038782386628e-05,
"loss": 4.0942,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807201825515949e-05,
"loss": 4.0887,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806363230764897e-05,
"loss": 4.1018,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805524636013845e-05,
"loss": 4.0919,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804686041262793e-05,
"loss": 4.0834,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803849084392114e-05,
"loss": 4.0878,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803010489641062e-05,
"loss": 4.09,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.80217189489001e-05,
"loss": 4.0854,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801333300138958e-05,
"loss": 4.0848,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800496343268279e-05,
"loss": 4.0746,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799657748517227e-05,
"loss": 4.0909,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798819153766175e-05,
"loss": 4.0738,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797980559015123e-05,
"loss": 4.0786,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971436021444446e-05,
"loss": 4.0713,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7963050073933926e-05,
"loss": 4.0855,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954664126423406e-05,
"loss": 4.0821,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946278178912886e-05,
"loss": 4.0757,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937908610206095e-05,
"loss": 4.0631,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929522662695575e-05,
"loss": 4.071,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921136715185055e-05,
"loss": 4.073,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912750767674535e-05,
"loss": 4.0808,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904381198967744e-05,
"loss": 4.0726,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895995251457224e-05,
"loss": 4.0636,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887609303946704e-05,
"loss": 4.0581,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787923973523992e-05,
"loss": 4.0709,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.78708537877294e-05,
"loss": 4.0419,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786248421902261e-05,
"loss": 4.0572,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785409827151209e-05,
"loss": 4.0599,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784571232400157e-05,
"loss": 4.0589,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783732637649105e-05,
"loss": 4.0488,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782894042898053e-05,
"loss": 4.0587,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782055448147001e-05,
"loss": 4.0508,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781216853395948e-05,
"loss": 4.0702,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780378258644896e-05,
"loss": 4.0558,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779541301774218e-05,
"loss": 4.0523,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778702707023166e-05,
"loss": 4.0688,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777864112272114e-05,
"loss": 4.0718,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770271554014354e-05,
"loss": 4.0525,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761885606503834e-05,
"loss": 4.0477,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775349965899331e-05,
"loss": 4.0572,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774511371148279e-05,
"loss": 4.0463,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773672776397227e-05,
"loss": 4.0485,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728341816461747e-05,
"loss": 4.0545,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719955868951227e-05,
"loss": 4.0415,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711586300244436e-05,
"loss": 4.0611,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703200352733916e-05,
"loss": 4.0431,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694814405223396e-05,
"loss": 4.0438,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686428457712876e-05,
"loss": 4.0374,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767805888900609e-05,
"loss": 4.0455,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766967294149557e-05,
"loss": 4.0374,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766128699398505e-05,
"loss": 4.052,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765290104647453e-05,
"loss": 4.0492,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764453147776774e-05,
"loss": 4.0394,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763614553025722e-05,
"loss": 4.0246,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.76277595827467e-05,
"loss": 4.0464,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761937363523618e-05,
"loss": 4.0367,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761100406652939e-05,
"loss": 4.0448,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760261811901887e-05,
"loss": 4.0398,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759423217150835e-05,
"loss": 4.0421,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758584622399783e-05,
"loss": 4.0397,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577476655291045e-05,
"loss": 4.0424,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569090707780525e-05,
"loss": 4.0271,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560704760270005e-05,
"loss": 4.0254,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552318812759485e-05,
"loss": 4.038,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543949244052694e-05,
"loss": 4.0205,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.75355796753459e-05,
"loss": 4.0363,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752719372783538e-05,
"loss": 4.0414,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751880778032486e-05,
"loss": 4.0256,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751042183281434e-05,
"loss": 4.025,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750203588530382e-05,
"loss": 4.0282,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.028327941894531,
"eval_runtime": 305.0036,
"eval_samples_per_second": 1251.103,
"eval_steps_per_second": 39.098,
"step": 152640
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.0697475489568358e+17,
"trial_name": null,
"trial_params": null
}