abhinavp's picture
Training in progress, epoch 0, checkpoint
701f95a verified
raw
history blame
No virus
112 kB
{
"best_metric": 3.8695147037506104,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sim-ques/transformer/1/checkpoints/checkpoint-457920",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 457920,
"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
},
{
"epoch": 0.0,
"learning_rate": 4.74936499377933e-05,
"loss": 4.0102,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748526399028278e-05,
"loss": 4.019,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747687804277226e-05,
"loss": 4.0284,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746849209526175e-05,
"loss": 4.0216,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.746010614775123e-05,
"loss": 4.0264,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745172020024071e-05,
"loss": 4.0081,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744333425273019e-05,
"loss": 4.0217,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743494830521967e-05,
"loss": 4.0055,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742656235770914e-05,
"loss": 4.0191,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741817641019862e-05,
"loss": 4.0134,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740980684149184e-05,
"loss": 4.0227,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740142089398132e-05,
"loss": 4.0237,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739303494647079e-05,
"loss": 4.0051,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738464899896027e-05,
"loss": 4.0063,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737626305144975e-05,
"loss": 4.0067,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736787710393923e-05,
"loss": 4.0025,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735949115642871e-05,
"loss": 3.9991,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.73511052089182e-05,
"loss": 4.0029,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734273564021141e-05,
"loss": 3.9979,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733434969270089e-05,
"loss": 4.0207,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732596374519037e-05,
"loss": 4.0019,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731757779767985e-05,
"loss": 4.0144,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7309208228973056e-05,
"loss": 4.0086,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300838660266265e-05,
"loss": 4.015,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292452712755745e-05,
"loss": 3.9878,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7284066765245225e-05,
"loss": 3.999,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275680817734705e-05,
"loss": 3.9896,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267294870224185e-05,
"loss": 3.9986,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258908922713665e-05,
"loss": 3.9903,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725052297520315e-05,
"loss": 3.992,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724215340649636e-05,
"loss": 4.0023,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723376745898584e-05,
"loss": 3.999,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722538151147532e-05,
"loss": 3.9854,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.72169955639648e-05,
"loss": 3.9989,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720860961645428e-05,
"loss": 3.996,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720022366894376e-05,
"loss": 3.993,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719183772143324e-05,
"loss": 3.9803,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718345177392272e-05,
"loss": 3.9898,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717508220521593e-05,
"loss": 3.9716,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716669625770541e-05,
"loss": 3.9871,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715831031019489e-05,
"loss": 3.9811,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714992436268437e-05,
"loss": 3.9908,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141554793977585e-05,
"loss": 3.9843,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133168846467065e-05,
"loss": 3.9859,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124782898956545e-05,
"loss": 3.9899,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116396951446025e-05,
"loss": 3.9867,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7108027382739234e-05,
"loss": 3.985,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099641435228714e-05,
"loss": 3.9679,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091255487718194e-05,
"loss": 3.9743,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082869540207674e-05,
"loss": 3.985,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707449997150088e-05,
"loss": 3.9777,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706611402399036e-05,
"loss": 3.9702,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705772807647984e-05,
"loss": 3.9651,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704934212896932e-05,
"loss": 3.9753,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704097256026254e-05,
"loss": 3.9587,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703260299155575e-05,
"loss": 3.9781,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702421704404523e-05,
"loss": 3.9658,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701583109653471e-05,
"loss": 3.9777,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700744514902419e-05,
"loss": 3.9745,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699905920151367e-05,
"loss": 3.9582,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699067325400315e-05,
"loss": 3.964,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698228730649263e-05,
"loss": 3.9668,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.69739013589821e-05,
"loss": 3.9572,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696553179027532e-05,
"loss": 3.9647,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69571458427648e-05,
"loss": 3.9712,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694877627405801e-05,
"loss": 3.9668,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694039032654749e-05,
"loss": 3.9552,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693200437903697e-05,
"loss": 3.946,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692361843152645e-05,
"loss": 3.9527,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915232484015926e-05,
"loss": 3.9677,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906846536505406e-05,
"loss": 3.9744,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898460588994886e-05,
"loss": 3.9579,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890091020288095e-05,
"loss": 3.9718,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881705072777575e-05,
"loss": 3.9693,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873319125267055e-05,
"loss": 3.9678,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864933177756535e-05,
"loss": 3.9445,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856547230246015e-05,
"loss": 3.9684,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684817766153923e-05,
"loss": 3.958,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683979171402871e-05,
"loss": 3.9518,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683140576651819e-05,
"loss": 3.9595,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682301981900767e-05,
"loss": 3.9542,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681463387149715e-05,
"loss": 3.9664,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680624792398663e-05,
"loss": 3.9585,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679786197647611e-05,
"loss": 3.947,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678949240776932e-05,
"loss": 3.954,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.67811064602588e-05,
"loss": 3.9552,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677272051274828e-05,
"loss": 3.9531,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676433456523776e-05,
"loss": 3.9509,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675594861772724e-05,
"loss": 3.9442,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674756267021672e-05,
"loss": 3.9564,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739193101509935e-05,
"loss": 3.9446,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730807153999415e-05,
"loss": 3.9481,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722421206488895e-05,
"loss": 3.9417,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6714035258978375e-05,
"loss": 3.9578,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705649311467855e-05,
"loss": 3.9523,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697263363957335e-05,
"loss": 3.9464,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688877416446815e-05,
"loss": 3.9388,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680507847740024e-05,
"loss": 3.9469,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667213827903323e-05,
"loss": 3.9382,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666375233152271e-05,
"loss": 3.9592,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665536638401219e-05,
"loss": 3.9433,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664698043650167e-05,
"loss": 3.9398,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663859448899115e-05,
"loss": 3.934,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663020854148063e-05,
"loss": 3.9448,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662182259397011e-05,
"loss": 3.9211,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661345302526333e-05,
"loss": 3.9361,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660506707775281e-05,
"loss": 3.9378,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659668113024229e-05,
"loss": 3.9368,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658829518273176e-05,
"loss": 3.9243,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657992561402498e-05,
"loss": 3.9412,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657153966651446e-05,
"loss": 3.9262,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656315371900393e-05,
"loss": 3.9509,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655476777149341e-05,
"loss": 3.9355,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654638182398289e-05,
"loss": 3.9303,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653799587647237e-05,
"loss": 3.9481,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652960992896185e-05,
"loss": 3.9551,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521240360255066e-05,
"loss": 3.9344,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512854412744546e-05,
"loss": 3.9279,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.6504468465234026e-05,
"loss": 3.9368,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6496082517723506e-05,
"loss": 3.93,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487696570212986e-05,
"loss": 3.9291,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479327001506195e-05,
"loss": 3.9421,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470941053995675e-05,
"loss": 3.9212,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462555106485155e-05,
"loss": 3.944,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454169158974635e-05,
"loss": 3.9288,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445783211464115e-05,
"loss": 3.9278,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437413642757324e-05,
"loss": 3.9212,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429027695246804e-05,
"loss": 3.9326,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642064174773629e-05,
"loss": 3.9196,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641225580022577e-05,
"loss": 3.9409,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640386985271525e-05,
"loss": 3.9312,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639548390520473e-05,
"loss": 3.9284,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638709795769421e-05,
"loss": 3.9111,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637871201018369e-05,
"loss": 3.9347,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.63703424414769e-05,
"loss": 3.928,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636195649396638e-05,
"loss": 3.9274,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635357054645586e-05,
"loss": 3.924,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634520097774907e-05,
"loss": 3.9333,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633681503023855e-05,
"loss": 3.9289,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632842908272803e-05,
"loss": 3.9343,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632004313521751e-05,
"loss": 3.9163,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311673566510724e-05,
"loss": 3.9168,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303287619000204e-05,
"loss": 3.9261,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294901671489684e-05,
"loss": 3.9099,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286515723979164e-05,
"loss": 3.9263,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6278129776468644e-05,
"loss": 3.9329,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626976020776185e-05,
"loss": 3.9182,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626137426025133e-05,
"loss": 3.915,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625298831274081e-05,
"loss": 3.9236,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.952652931213379,
"eval_runtime": 308.9364,
"eval_samples_per_second": 1235.177,
"eval_steps_per_second": 38.6,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624460236523029e-05,
"loss": 3.9113,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.62362327965235e-05,
"loss": 3.9117,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622784684901298e-05,
"loss": 3.9211,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621946090150246e-05,
"loss": 3.9106,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621107495399194e-05,
"loss": 3.925,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620268900648142e-05,
"loss": 3.9044,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619431943777464e-05,
"loss": 3.9183,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618593349026412e-05,
"loss": 3.9022,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617754754275359e-05,
"loss": 3.9146,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616916159524307e-05,
"loss": 3.9073,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616079202653629e-05,
"loss": 3.919,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615240607902577e-05,
"loss": 3.9187,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614402013151524e-05,
"loss": 3.9016,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613563418400472e-05,
"loss": 3.906,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.61272482364942e-05,
"loss": 3.9028,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.6118878667787416e-05,
"loss": 3.9031,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.6110492720276896e-05,
"loss": 3.8973,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.6102106772766376e-05,
"loss": 3.9023,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.6093720825255856e-05,
"loss": 3.8976,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.6085334877745336e-05,
"loss": 3.9238,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076965309038545e-05,
"loss": 3.902,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068579361528025e-05,
"loss": 3.9091,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6060193414017505e-05,
"loss": 3.9123,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051807466506985e-05,
"loss": 3.9123,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.6043437897800194e-05,
"loss": 3.8905,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.6035051950289674e-05,
"loss": 3.9011,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.6026666002779154e-05,
"loss": 3.8935,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018280055268634e-05,
"loss": 3.8994,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009894107758114e-05,
"loss": 3.8909,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600152453905133e-05,
"loss": 3.8934,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599313859154081e-05,
"loss": 3.9036,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598476902283402e-05,
"loss": 3.9022,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.59763830753235e-05,
"loss": 3.8954,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596799712781298e-05,
"loss": 3.9009,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595961118030246e-05,
"loss": 3.9015,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595122523279194e-05,
"loss": 3.8971,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594283928528142e-05,
"loss": 3.8842,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.59344533377709e-05,
"loss": 3.8968,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592606739026038e-05,
"loss": 3.8743,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591769782155359e-05,
"loss": 3.8926,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590931187404307e-05,
"loss": 3.8869,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900925926532554e-05,
"loss": 3.8998,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.5892539979022034e-05,
"loss": 3.8959,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5884154031511514e-05,
"loss": 3.8889,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587578446280472e-05,
"loss": 3.8975,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.58673985152942e-05,
"loss": 3.8967,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585901256778368e-05,
"loss": 3.8926,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585062662027316e-05,
"loss": 3.878,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584224067276264e-05,
"loss": 3.8812,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583387110405585e-05,
"loss": 3.8961,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582548515654533e-05,
"loss": 3.8818,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581709920903481e-05,
"loss": 3.8781,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580871326152429e-05,
"loss": 3.8758,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580034369281751e-05,
"loss": 3.888,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579195774530699e-05,
"loss": 3.8707,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578357179779647e-05,
"loss": 3.8856,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577518585028595e-05,
"loss": 3.8792,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576679990277543e-05,
"loss": 3.8846,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758430334068637e-05,
"loss": 3.8858,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5750044386558117e-05,
"loss": 3.8727,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741658439047596e-05,
"loss": 3.8717,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733272491537076e-05,
"loss": 3.884,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572488654402655e-05,
"loss": 3.8676,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716516975319765e-05,
"loss": 3.8761,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5708131027809245e-05,
"loss": 3.8834,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.5699745080298725e-05,
"loss": 3.8828,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.5691359132788205e-05,
"loss": 3.8656,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5682973185277685e-05,
"loss": 3.8616,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.5674587237767165e-05,
"loss": 3.8638,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.5666201290256645e-05,
"loss": 3.8774,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.5657815342746125e-05,
"loss": 3.8872,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.5649445774039334e-05,
"loss": 3.8725,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.5641059826528814e-05,
"loss": 3.8856,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.5632673879018294e-05,
"loss": 3.8862,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624287931507774e-05,
"loss": 3.8812,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615901983997254e-05,
"loss": 3.8628,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560753241529046e-05,
"loss": 3.8807,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559914646777994e-05,
"loss": 3.8747,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559076052026943e-05,
"loss": 3.8673,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558237457275891e-05,
"loss": 3.8735,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557398862524839e-05,
"loss": 3.8745,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556560267773787e-05,
"loss": 3.8784,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555723310903108e-05,
"loss": 3.8748,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554884716152056e-05,
"loss": 3.8664,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554046121401004e-05,
"loss": 3.872,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553207526649952e-05,
"loss": 3.8691,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523689318989e-05,
"loss": 3.8706,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551531975028221e-05,
"loss": 3.8685,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550693380277169e-05,
"loss": 3.8609,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549854785526117e-05,
"loss": 3.8737,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549016190775065e-05,
"loss": 3.868,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548177596024013e-05,
"loss": 3.8622,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.5473406391533343e-05,
"loss": 3.8609,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.5465020444022823e-05,
"loss": 3.8783,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.54566344965123e-05,
"loss": 3.8709,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544824854900178e-05,
"loss": 3.8645,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543987898029499e-05,
"loss": 3.8555,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543149303278447e-05,
"loss": 3.8657,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542310708527395e-05,
"loss": 3.857,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541472113776343e-05,
"loss": 3.8788,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540635156905664e-05,
"loss": 3.8641,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539796562154612e-05,
"loss": 3.8605,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.53895796740356e-05,
"loss": 3.8565,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538119372652508e-05,
"loss": 3.8658,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.53728241578183e-05,
"loss": 3.8386,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536443821030778e-05,
"loss": 3.8575,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535605226279726e-05,
"loss": 3.8575,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534766631528674e-05,
"loss": 3.859,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339296746579946e-05,
"loss": 3.8455,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330910799069426e-05,
"loss": 3.863,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322524851558906e-05,
"loss": 3.8478,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314138904048386e-05,
"loss": 3.8689,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.5305769335341595e-05,
"loss": 3.8598,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297383387831075e-05,
"loss": 3.8503,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.5288997440320555e-05,
"loss": 3.8697,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.5280611492810035e-05,
"loss": 3.8767,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527224192410325e-05,
"loss": 3.8614,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526385597659273e-05,
"loss": 3.8505,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525547002908221e-05,
"loss": 3.8612,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.5247084081571684e-05,
"loss": 3.8513,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.52387145128649e-05,
"loss": 3.8516,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523032856535438e-05,
"loss": 3.8658,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522194261784386e-05,
"loss": 3.8473,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521355667033333e-05,
"loss": 3.8643,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520518710162655e-05,
"loss": 3.8539,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519680115411603e-05,
"loss": 3.8566,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518841520660551e-05,
"loss": 3.8407,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.518002925909499e-05,
"loss": 3.8593,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517164331158447e-05,
"loss": 3.8458,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163273742877684e-05,
"loss": 3.8625,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515488779536716e-05,
"loss": 3.8545,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514650184785664e-05,
"loss": 3.8579,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513811590034612e-05,
"loss": 3.8361,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.5129746331639333e-05,
"loss": 3.8622,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.5121360384128807e-05,
"loss": 3.8512,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.5112974436618287e-05,
"loss": 3.855,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104588489107766e-05,
"loss": 3.8504,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5096218920400976e-05,
"loss": 3.8599,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508783297289046e-05,
"loss": 3.8564,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507944702537994e-05,
"loss": 3.8583,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507106107786942e-05,
"loss": 3.844,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506269150916263e-05,
"loss": 3.8471,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505430556165211e-05,
"loss": 3.8493,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504591961414159e-05,
"loss": 3.8399,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503753366663107e-05,
"loss": 3.8533,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502916409792428e-05,
"loss": 3.8582,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502077815041376e-05,
"loss": 3.8475,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501239220290324e-05,
"loss": 3.8404,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500400625539272e-05,
"loss": 3.8528,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.911623001098633,
"eval_runtime": 305.2751,
"eval_samples_per_second": 1249.991,
"eval_steps_per_second": 39.063,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.49956203078822e-05,
"loss": 3.8317,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498723436037168e-05,
"loss": 3.8407,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497884841286116e-05,
"loss": 3.8462,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497046246535065e-05,
"loss": 3.8452,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496207651784013e-05,
"loss": 3.8541,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495369057032961e-05,
"loss": 3.8328,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945304622819087e-05,
"loss": 3.8448,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936918675308567e-05,
"loss": 3.8298,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928549106601776e-05,
"loss": 3.8476,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4920163159091256e-05,
"loss": 3.8387,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911777211580736e-05,
"loss": 3.844,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903391264070216e-05,
"loss": 3.8525,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.4895021695363425e-05,
"loss": 3.829,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.4886635747852905e-05,
"loss": 3.8415,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4878249800342385e-05,
"loss": 3.8336,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.4869863852831864e-05,
"loss": 3.8351,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486149428412508e-05,
"loss": 3.8267,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485310833661456e-05,
"loss": 3.8344,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484472238910404e-05,
"loss": 3.8307,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483633644159352e-05,
"loss": 3.8524,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482796687288673e-05,
"loss": 3.8319,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481958092537621e-05,
"loss": 3.8412,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481119497786569e-05,
"loss": 3.8439,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480280903035516e-05,
"loss": 3.8448,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479443946164838e-05,
"loss": 3.823,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478605351413786e-05,
"loss": 3.8372,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477766756662734e-05,
"loss": 3.8239,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476928161911682e-05,
"loss": 3.8333,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.47608956716063e-05,
"loss": 3.8213,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.4752526102899514e-05,
"loss": 3.8268,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.4744140155388994e-05,
"loss": 3.8364,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.47357705866822e-05,
"loss": 3.8366,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472738463917168e-05,
"loss": 3.8265,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471899869166116e-05,
"loss": 3.8371,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710612744150636e-05,
"loss": 3.8287,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.4702226796640116e-05,
"loss": 3.8371,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693840849129596e-05,
"loss": 3.8176,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.4685454901619076e-05,
"loss": 3.8305,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4677068954108556e-05,
"loss": 3.8132,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466869938540177e-05,
"loss": 3.8239,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466031343789125e-05,
"loss": 3.8203,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465192749038073e-05,
"loss": 3.8348,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464354154287021e-05,
"loss": 3.8302,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463517197416342e-05,
"loss": 3.8277,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.46267860266529e-05,
"loss": 3.8316,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461840007914238e-05,
"loss": 3.8309,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.461001413163186e-05,
"loss": 3.827,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460164456292507e-05,
"loss": 3.8203,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459325861541455e-05,
"loss": 3.81,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.458487266790403e-05,
"loss": 3.8315,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457648672039351e-05,
"loss": 3.8207,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4568117151686725e-05,
"loss": 3.8141,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559731204176205e-05,
"loss": 3.8162,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551345256665685e-05,
"loss": 3.8233,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542959309155165e-05,
"loss": 3.8078,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534589740448374e-05,
"loss": 3.8159,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4526203792937854e-05,
"loss": 3.8163,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.4517817845427334e-05,
"loss": 3.8176,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.4509431897916814e-05,
"loss": 3.8277,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.4501062329210023e-05,
"loss": 3.8085,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.44926763816995e-05,
"loss": 3.8103,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448429043418898e-05,
"loss": 3.822,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447590448667846e-05,
"loss": 3.8081,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446753491797168e-05,
"loss": 3.8126,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445914897046116e-05,
"loss": 3.821,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445076302295064e-05,
"loss": 3.8206,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444237707544012e-05,
"loss": 3.8046,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.44339911279296e-05,
"loss": 3.7986,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442562155922281e-05,
"loss": 3.7997,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441723561171229e-05,
"loss": 3.8135,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440884966420177e-05,
"loss": 3.8269,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440046371669125e-05,
"loss": 3.8094,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439209414798446e-05,
"loss": 3.8224,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438370820047394e-05,
"loss": 3.8215,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437532225296342e-05,
"loss": 3.8239,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.43669363054529e-05,
"loss": 3.8032,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435856673674611e-05,
"loss": 3.8192,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435018078923559e-05,
"loss": 3.8113,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434179484172507e-05,
"loss": 3.8045,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433340889421455e-05,
"loss": 3.8181,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432503932550776e-05,
"loss": 3.8122,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431665337799724e-05,
"loss": 3.8126,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430826743048672e-05,
"loss": 3.8141,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.42998814829762e-05,
"loss": 3.8104,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429151191426941e-05,
"loss": 3.8128,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428312596675889e-05,
"loss": 3.8077,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427474001924837e-05,
"loss": 3.8113,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426635407173785e-05,
"loss": 3.8049,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257984503031066e-05,
"loss": 3.8049,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249598555520546e-05,
"loss": 3.8115,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4241212608010026e-05,
"loss": 3.8113,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232826660499506e-05,
"loss": 3.8014,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224457091792715e-05,
"loss": 3.8011,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4216071144282195e-05,
"loss": 3.8178,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207685196771675e-05,
"loss": 3.8123,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.4199299249261155e-05,
"loss": 3.8073,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190929680554364e-05,
"loss": 3.7966,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182543733043844e-05,
"loss": 3.8039,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4174157785533324e-05,
"loss": 3.8003,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.4165771838022804e-05,
"loss": 3.8144,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415740226931602e-05,
"loss": 3.8121,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.41490163218055e-05,
"loss": 3.802,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414063037429498e-05,
"loss": 3.7956,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413224442678446e-05,
"loss": 3.809,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412387485807767e-05,
"loss": 3.7775,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411548891056715e-05,
"loss": 3.8039,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410710296305663e-05,
"loss": 3.7948,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409871701554611e-05,
"loss": 3.8017,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409034744683932e-05,
"loss": 3.7878,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.40819614993288e-05,
"loss": 3.805,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407357555181828e-05,
"loss": 3.7971,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406518960430776e-05,
"loss": 3.8031,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.4056820035600974e-05,
"loss": 3.8069,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.4048434088090454e-05,
"loss": 3.7923,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.4040048140579934e-05,
"loss": 3.8129,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.4031662193069414e-05,
"loss": 3.8202,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402329262436262e-05,
"loss": 3.803,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.40149066768521e-05,
"loss": 3.7918,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400652072934158e-05,
"loss": 3.8061,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399813478183106e-05,
"loss": 3.7983,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398976521312427e-05,
"loss": 3.7912,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398137926561375e-05,
"loss": 3.8105,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397299331810323e-05,
"loss": 3.7907,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396460737059271e-05,
"loss": 3.8046,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395623780188593e-05,
"loss": 3.799,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394785185437541e-05,
"loss": 3.8013,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393946590686489e-05,
"loss": 3.7919,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393107995935437e-05,
"loss": 3.7963,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.3922710390647576e-05,
"loss": 3.795,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3914324443137056e-05,
"loss": 3.808,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905938495626536e-05,
"loss": 3.7974,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897552548116016e-05,
"loss": 3.8012,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.3889182979409225e-05,
"loss": 3.7805,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.3880797031898705e-05,
"loss": 3.8071,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872411084388185e-05,
"loss": 3.7944,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3864025136877665e-05,
"loss": 3.803,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385565556817088e-05,
"loss": 3.7935,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384726962066036e-05,
"loss": 3.8048,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383888367314984e-05,
"loss": 3.7995,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830497725639314e-05,
"loss": 3.808,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382212815693253e-05,
"loss": 3.7859,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381374220942201e-05,
"loss": 3.7956,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380535626191148e-05,
"loss": 3.7932,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379697031440096e-05,
"loss": 3.7872,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378860074569418e-05,
"loss": 3.8014,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378021479818366e-05,
"loss": 3.8009,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377182885067313e-05,
"loss": 3.799,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376344290316262e-05,
"loss": 3.7796,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3755073334455835e-05,
"loss": 3.7989,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.886021614074707,
"eval_runtime": 314.3717,
"eval_samples_per_second": 1213.821,
"eval_steps_per_second": 37.933,
"step": 381600
},
{
"epoch": 0.0,
"learning_rate": 4.3746687386945315e-05,
"loss": 3.7813,
"step": 381952
},
{
"epoch": 0.0,
"learning_rate": 4.373830143943479e-05,
"loss": 3.7831,
"step": 382464
},
{
"epoch": 0.0,
"learning_rate": 4.372991549192427e-05,
"loss": 3.7951,
"step": 382976
},
{
"epoch": 0.0,
"learning_rate": 4.372152954441375e-05,
"loss": 3.7933,
"step": 383488
},
{
"epoch": 0.0,
"learning_rate": 4.371314359690323e-05,
"loss": 3.795,
"step": 384000
},
{
"epoch": 0.0,
"learning_rate": 4.370475764939271e-05,
"loss": 3.7829,
"step": 384512
},
{
"epoch": 0.0,
"learning_rate": 4.369637170188219e-05,
"loss": 3.7882,
"step": 385024
},
{
"epoch": 0.0,
"learning_rate": 4.368798575437167e-05,
"loss": 3.7789,
"step": 385536
},
{
"epoch": 0.0,
"learning_rate": 4.367961618566488e-05,
"loss": 3.7913,
"step": 386048
},
{
"epoch": 0.0,
"learning_rate": 4.367123023815436e-05,
"loss": 3.7865,
"step": 386560
},
{
"epoch": 0.0,
"learning_rate": 4.366284429064384e-05,
"loss": 3.7889,
"step": 387072
},
{
"epoch": 0.0,
"learning_rate": 4.365445834313332e-05,
"loss": 3.798,
"step": 387584
},
{
"epoch": 0.0,
"learning_rate": 4.364608877442653e-05,
"loss": 3.7787,
"step": 388096
},
{
"epoch": 0.0,
"learning_rate": 4.363770282691601e-05,
"loss": 3.7897,
"step": 388608
},
{
"epoch": 0.0,
"learning_rate": 4.362931687940549e-05,
"loss": 3.7834,
"step": 389120
},
{
"epoch": 0.0,
"learning_rate": 4.362093093189497e-05,
"loss": 3.7817,
"step": 389632
},
{
"epoch": 0.0,
"learning_rate": 4.361256136318818e-05,
"loss": 3.7742,
"step": 390144
},
{
"epoch": 0.0,
"learning_rate": 4.360417541567766e-05,
"loss": 3.7843,
"step": 390656
},
{
"epoch": 0.0,
"learning_rate": 4.359578946816714e-05,
"loss": 3.7758,
"step": 391168
},
{
"epoch": 0.0,
"learning_rate": 4.358740352065662e-05,
"loss": 3.7977,
"step": 391680
},
{
"epoch": 0.0,
"learning_rate": 4.357903395194983e-05,
"loss": 3.785,
"step": 392192
},
{
"epoch": 0.0,
"learning_rate": 4.357064800443931e-05,
"loss": 3.7875,
"step": 392704
},
{
"epoch": 0.0,
"learning_rate": 4.356226205692879e-05,
"loss": 3.7931,
"step": 393216
},
{
"epoch": 0.0,
"learning_rate": 4.355387610941827e-05,
"loss": 3.7924,
"step": 393728
},
{
"epoch": 0.0,
"learning_rate": 4.3545506540711486e-05,
"loss": 3.7697,
"step": 394240
},
{
"epoch": 0.0,
"learning_rate": 4.3537120593200966e-05,
"loss": 3.784,
"step": 394752
},
{
"epoch": 0.0,
"learning_rate": 4.3528734645690446e-05,
"loss": 3.7774,
"step": 395264
},
{
"epoch": 0.0,
"learning_rate": 4.3520348698179926e-05,
"loss": 3.7802,
"step": 395776
},
{
"epoch": 0.0,
"learning_rate": 4.3511979129473135e-05,
"loss": 3.7707,
"step": 396288
},
{
"epoch": 0.0,
"learning_rate": 4.3503593181962615e-05,
"loss": 3.7743,
"step": 396800
},
{
"epoch": 0.01,
"learning_rate": 4.3495207234452095e-05,
"loss": 3.7862,
"step": 397312
},
{
"epoch": 0.01,
"learning_rate": 4.3486837665745304e-05,
"loss": 3.7829,
"step": 397824
},
{
"epoch": 0.01,
"learning_rate": 4.3478451718234784e-05,
"loss": 3.7792,
"step": 398336
},
{
"epoch": 0.01,
"learning_rate": 4.3470065770724264e-05,
"loss": 3.7829,
"step": 398848
},
{
"epoch": 0.01,
"learning_rate": 4.3461679823213744e-05,
"loss": 3.7809,
"step": 399360
},
{
"epoch": 0.01,
"learning_rate": 4.3453293875703224e-05,
"loss": 3.7829,
"step": 399872
},
{
"epoch": 0.01,
"learning_rate": 4.344490792819271e-05,
"loss": 3.7713,
"step": 400384
},
{
"epoch": 0.01,
"learning_rate": 4.343652198068219e-05,
"loss": 3.7717,
"step": 400896
},
{
"epoch": 0.01,
"learning_rate": 4.342813603317167e-05,
"loss": 3.7684,
"step": 401408
},
{
"epoch": 0.01,
"learning_rate": 4.341976646446488e-05,
"loss": 3.7718,
"step": 401920
},
{
"epoch": 0.01,
"learning_rate": 4.341138051695436e-05,
"loss": 3.7702,
"step": 402432
},
{
"epoch": 0.01,
"learning_rate": 4.340299456944384e-05,
"loss": 3.7826,
"step": 402944
},
{
"epoch": 0.01,
"learning_rate": 4.339460862193332e-05,
"loss": 3.7809,
"step": 403456
},
{
"epoch": 0.01,
"learning_rate": 4.338623905322653e-05,
"loss": 3.7771,
"step": 403968
},
{
"epoch": 0.01,
"learning_rate": 4.337785310571601e-05,
"loss": 3.7856,
"step": 404480
},
{
"epoch": 0.01,
"learning_rate": 4.336946715820549e-05,
"loss": 3.7772,
"step": 404992
},
{
"epoch": 0.01,
"learning_rate": 4.336108121069497e-05,
"loss": 3.7794,
"step": 405504
},
{
"epoch": 0.01,
"learning_rate": 4.335271164198818e-05,
"loss": 3.7689,
"step": 406016
},
{
"epoch": 0.01,
"learning_rate": 4.3344325694477664e-05,
"loss": 3.7575,
"step": 406528
},
{
"epoch": 0.01,
"learning_rate": 4.3335939746967144e-05,
"loss": 3.7828,
"step": 407040
},
{
"epoch": 0.01,
"learning_rate": 4.3327553799456624e-05,
"loss": 3.7716,
"step": 407552
},
{
"epoch": 0.01,
"learning_rate": 4.331918423074983e-05,
"loss": 3.7688,
"step": 408064
},
{
"epoch": 0.01,
"learning_rate": 4.331079828323931e-05,
"loss": 3.7669,
"step": 408576
},
{
"epoch": 0.01,
"learning_rate": 4.330241233572879e-05,
"loss": 3.7711,
"step": 409088
},
{
"epoch": 0.01,
"learning_rate": 4.3294026388218266e-05,
"loss": 3.7587,
"step": 409600
},
{
"epoch": 0.01,
"learning_rate": 4.328565681951148e-05,
"loss": 3.7676,
"step": 410112
},
{
"epoch": 0.01,
"learning_rate": 4.327727087200096e-05,
"loss": 3.7693,
"step": 410624
},
{
"epoch": 0.01,
"learning_rate": 4.326888492449044e-05,
"loss": 3.7662,
"step": 411136
},
{
"epoch": 0.01,
"learning_rate": 4.3260498976979915e-05,
"loss": 3.7763,
"step": 411648
},
{
"epoch": 0.01,
"learning_rate": 4.325212940827313e-05,
"loss": 3.7585,
"step": 412160
},
{
"epoch": 0.01,
"learning_rate": 4.324374346076261e-05,
"loss": 3.7631,
"step": 412672
},
{
"epoch": 0.01,
"learning_rate": 4.32353575132521e-05,
"loss": 3.7738,
"step": 413184
},
{
"epoch": 0.01,
"learning_rate": 4.322697156574157e-05,
"loss": 3.7606,
"step": 413696
},
{
"epoch": 0.01,
"learning_rate": 4.321860199703479e-05,
"loss": 3.763,
"step": 414208
},
{
"epoch": 0.01,
"learning_rate": 4.321021604952427e-05,
"loss": 3.7686,
"step": 414720
},
{
"epoch": 0.01,
"learning_rate": 4.320183010201374e-05,
"loss": 3.7728,
"step": 415232
},
{
"epoch": 0.01,
"learning_rate": 4.3193460533306956e-05,
"loss": 3.7564,
"step": 415744
},
{
"epoch": 0.01,
"learning_rate": 4.3185074585796436e-05,
"loss": 3.757,
"step": 416256
},
{
"epoch": 0.01,
"learning_rate": 4.3176688638285916e-05,
"loss": 3.7483,
"step": 416768
},
{
"epoch": 0.01,
"learning_rate": 4.316830269077539e-05,
"loss": 3.7668,
"step": 417280
},
{
"epoch": 0.01,
"learning_rate": 4.3159933122068605e-05,
"loss": 3.7793,
"step": 417792
},
{
"epoch": 0.01,
"learning_rate": 4.3151547174558085e-05,
"loss": 3.7633,
"step": 418304
},
{
"epoch": 0.01,
"learning_rate": 4.3143161227047565e-05,
"loss": 3.7704,
"step": 418816
},
{
"epoch": 0.01,
"learning_rate": 4.3134775279537045e-05,
"loss": 3.7734,
"step": 419328
},
{
"epoch": 0.01,
"learning_rate": 4.312640571083026e-05,
"loss": 3.78,
"step": 419840
},
{
"epoch": 0.01,
"learning_rate": 4.311801976331974e-05,
"loss": 3.7556,
"step": 420352
},
{
"epoch": 0.01,
"learning_rate": 4.3109633815809214e-05,
"loss": 3.7708,
"step": 420864
},
{
"epoch": 0.01,
"learning_rate": 4.3101247868298694e-05,
"loss": 3.7666,
"step": 421376
},
{
"epoch": 0.01,
"learning_rate": 4.309287829959191e-05,
"loss": 3.7545,
"step": 421888
},
{
"epoch": 0.01,
"learning_rate": 4.308449235208139e-05,
"loss": 3.7715,
"step": 422400
},
{
"epoch": 0.01,
"learning_rate": 4.307610640457086e-05,
"loss": 3.7673,
"step": 422912
},
{
"epoch": 0.01,
"learning_rate": 4.306772045706034e-05,
"loss": 3.7646,
"step": 423424
},
{
"epoch": 0.01,
"learning_rate": 4.305935088835356e-05,
"loss": 3.7688,
"step": 423936
},
{
"epoch": 0.01,
"learning_rate": 4.305096494084304e-05,
"loss": 3.7636,
"step": 424448
},
{
"epoch": 0.01,
"learning_rate": 4.304257899333252e-05,
"loss": 3.758,
"step": 424960
},
{
"epoch": 0.01,
"learning_rate": 4.3034193045822e-05,
"loss": 3.7632,
"step": 425472
},
{
"epoch": 0.01,
"learning_rate": 4.3025823477115214e-05,
"loss": 3.7653,
"step": 425984
},
{
"epoch": 0.01,
"learning_rate": 4.301743752960469e-05,
"loss": 3.7539,
"step": 426496
},
{
"epoch": 0.01,
"learning_rate": 4.300905158209417e-05,
"loss": 3.7586,
"step": 427008
},
{
"epoch": 0.02,
"learning_rate": 4.300066563458365e-05,
"loss": 3.7671,
"step": 427520
},
{
"epoch": 0.02,
"learning_rate": 4.299229606587686e-05,
"loss": 3.7654,
"step": 428032
},
{
"epoch": 0.02,
"learning_rate": 4.2983910118366337e-05,
"loss": 3.7538,
"step": 428544
},
{
"epoch": 0.02,
"learning_rate": 4.2975524170855817e-05,
"loss": 3.7564,
"step": 429056
},
{
"epoch": 0.02,
"learning_rate": 4.2967138223345296e-05,
"loss": 3.7737,
"step": 429568
},
{
"epoch": 0.02,
"learning_rate": 4.295876865463851e-05,
"loss": 3.766,
"step": 430080
},
{
"epoch": 0.02,
"learning_rate": 4.295038270712799e-05,
"loss": 3.7634,
"step": 430592
},
{
"epoch": 0.02,
"learning_rate": 4.294199675961747e-05,
"loss": 3.7475,
"step": 431104
},
{
"epoch": 0.02,
"learning_rate": 4.293361081210695e-05,
"loss": 3.7606,
"step": 431616
},
{
"epoch": 0.02,
"learning_rate": 4.292524124340016e-05,
"loss": 3.7568,
"step": 432128
},
{
"epoch": 0.02,
"learning_rate": 4.291685529588964e-05,
"loss": 3.7663,
"step": 432640
},
{
"epoch": 0.02,
"learning_rate": 4.290846934837912e-05,
"loss": 3.7678,
"step": 433152
},
{
"epoch": 0.02,
"learning_rate": 4.29000834008686e-05,
"loss": 3.757,
"step": 433664
},
{
"epoch": 0.02,
"learning_rate": 4.289171383216181e-05,
"loss": 3.749,
"step": 434176
},
{
"epoch": 0.02,
"learning_rate": 4.288332788465129e-05,
"loss": 3.7622,
"step": 434688
},
{
"epoch": 0.02,
"learning_rate": 4.287494193714077e-05,
"loss": 3.7349,
"step": 435200
},
{
"epoch": 0.02,
"learning_rate": 4.286655598963025e-05,
"loss": 3.7571,
"step": 435712
},
{
"epoch": 0.02,
"learning_rate": 4.2858186420923466e-05,
"loss": 3.7464,
"step": 436224
},
{
"epoch": 0.02,
"learning_rate": 4.2849800473412946e-05,
"loss": 3.7608,
"step": 436736
},
{
"epoch": 0.02,
"learning_rate": 4.2841414525902426e-05,
"loss": 3.7432,
"step": 437248
},
{
"epoch": 0.02,
"learning_rate": 4.2833028578391906e-05,
"loss": 3.7602,
"step": 437760
},
{
"epoch": 0.02,
"learning_rate": 4.2824659009685115e-05,
"loss": 3.7508,
"step": 438272
},
{
"epoch": 0.02,
"learning_rate": 4.2816273062174595e-05,
"loss": 3.759,
"step": 438784
},
{
"epoch": 0.02,
"learning_rate": 4.2807887114664075e-05,
"loss": 3.7622,
"step": 439296
},
{
"epoch": 0.02,
"learning_rate": 4.2799501167153555e-05,
"loss": 3.7517,
"step": 439808
},
{
"epoch": 0.02,
"learning_rate": 4.2791131598446764e-05,
"loss": 3.7638,
"step": 440320
},
{
"epoch": 0.02,
"learning_rate": 4.2782745650936244e-05,
"loss": 3.7726,
"step": 440832
},
{
"epoch": 0.02,
"learning_rate": 4.2774359703425724e-05,
"loss": 3.7581,
"step": 441344
},
{
"epoch": 0.02,
"learning_rate": 4.2765973755915204e-05,
"loss": 3.7521,
"step": 441856
},
{
"epoch": 0.02,
"learning_rate": 4.275760418720842e-05,
"loss": 3.7565,
"step": 442368
},
{
"epoch": 0.02,
"learning_rate": 4.27492182396979e-05,
"loss": 3.7573,
"step": 442880
},
{
"epoch": 0.02,
"learning_rate": 4.274083229218738e-05,
"loss": 3.7433,
"step": 443392
},
{
"epoch": 0.02,
"learning_rate": 4.273244634467686e-05,
"loss": 3.7707,
"step": 443904
},
{
"epoch": 0.02,
"learning_rate": 4.272407677597007e-05,
"loss": 3.7435,
"step": 444416
},
{
"epoch": 0.02,
"learning_rate": 4.271569082845955e-05,
"loss": 3.7635,
"step": 444928
},
{
"epoch": 0.02,
"learning_rate": 4.270730488094903e-05,
"loss": 3.7547,
"step": 445440
},
{
"epoch": 0.02,
"learning_rate": 4.269891893343851e-05,
"loss": 3.7566,
"step": 445952
},
{
"epoch": 0.02,
"learning_rate": 4.269054936473172e-05,
"loss": 3.7496,
"step": 446464
},
{
"epoch": 0.02,
"learning_rate": 4.26821634172212e-05,
"loss": 3.7553,
"step": 446976
},
{
"epoch": 0.02,
"learning_rate": 4.267377746971068e-05,
"loss": 3.7495,
"step": 447488
},
{
"epoch": 0.02,
"learning_rate": 4.266539152220016e-05,
"loss": 3.7648,
"step": 448000
},
{
"epoch": 0.02,
"learning_rate": 4.265702195349337e-05,
"loss": 3.7522,
"step": 448512
},
{
"epoch": 0.02,
"learning_rate": 4.264863600598285e-05,
"loss": 3.7593,
"step": 449024
},
{
"epoch": 0.02,
"learning_rate": 4.264025005847233e-05,
"loss": 3.7392,
"step": 449536
},
{
"epoch": 0.02,
"learning_rate": 4.263186411096181e-05,
"loss": 3.7636,
"step": 450048
},
{
"epoch": 0.02,
"learning_rate": 4.262349454225502e-05,
"loss": 3.7498,
"step": 450560
},
{
"epoch": 0.02,
"learning_rate": 4.26151085947445e-05,
"loss": 3.7586,
"step": 451072
},
{
"epoch": 0.02,
"learning_rate": 4.260672264723398e-05,
"loss": 3.7527,
"step": 451584
},
{
"epoch": 0.02,
"learning_rate": 4.259833669972346e-05,
"loss": 3.7572,
"step": 452096
},
{
"epoch": 0.02,
"learning_rate": 4.258996713101667e-05,
"loss": 3.7542,
"step": 452608
},
{
"epoch": 0.02,
"learning_rate": 4.258158118350615e-05,
"loss": 3.7686,
"step": 453120
},
{
"epoch": 0.02,
"learning_rate": 4.257319523599563e-05,
"loss": 3.7407,
"step": 453632
},
{
"epoch": 0.02,
"learning_rate": 4.256480928848511e-05,
"loss": 3.7534,
"step": 454144
},
{
"epoch": 0.02,
"learning_rate": 4.255643971977833e-05,
"loss": 3.7483,
"step": 454656
},
{
"epoch": 0.02,
"learning_rate": 4.254805377226781e-05,
"loss": 3.7482,
"step": 455168
},
{
"epoch": 0.02,
"learning_rate": 4.253966782475729e-05,
"loss": 3.7515,
"step": 455680
},
{
"epoch": 0.02,
"learning_rate": 4.253128187724677e-05,
"loss": 3.7593,
"step": 456192
},
{
"epoch": 0.02,
"learning_rate": 4.2522912308539976e-05,
"loss": 3.7585,
"step": 456704
},
{
"epoch": 0.02,
"learning_rate": 4.2514526361029456e-05,
"loss": 3.7374,
"step": 457216
},
{
"epoch": 0.02,
"learning_rate": 4.2506140413518936e-05,
"loss": 3.7596,
"step": 457728
},
{
"epoch": 0.03,
"eval_loss": 3.8695147037506104,
"eval_runtime": 304.879,
"eval_samples_per_second": 1251.615,
"eval_steps_per_second": 39.114,
"step": 457920
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.2092426468705075e+17,
"trial_name": null,
"trial_params": null
}