abhinavp's picture
Training in progress, epoch 0, checkpoint
7bfd9c0 verified
{
"best_metric": 3.9340226650238037,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/transformer/4/checkpoints/checkpoint-381595",
"epoch": 0.025000278439663435,
"eval_steps": 10,
"global_step": 381595,
"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": 11.0005,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.849,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1928,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.969,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.818,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.6938,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6036,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.528,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4669,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3968,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3531,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3092,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.276,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2132,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1737,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1452,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1033,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0758,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0546,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0218,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983231380739706e-05,
"loss": 5.0072,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9812,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9481,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9428,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.913,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8886,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8751,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.866,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8306,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8223,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7984,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7886,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.79,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7668,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7559,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7431,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7353,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.723,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.708,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6985,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6794,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6781,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964790485618428e-05,
"loss": 4.6498,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 4.6591,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6542,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6418,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.9614377444945934e-05,
"loss": 4.6241,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.9605991497435414e-05,
"loss": 4.6233,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 4.618,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.6003,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.588,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957248046500079e-05,
"loss": 4.5828,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956409451749027e-05,
"loss": 4.5931,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955570856997975e-05,
"loss": 4.5609,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 4.5819,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 4.5458,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.5538,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5441,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5404,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5321,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949702331620985e-05,
"loss": 4.526,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 4.5087,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5206,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.5004,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946349590497149e-05,
"loss": 4.5066,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.498,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4885,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4713,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.9429968493733145e-05,
"loss": 4.4851,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421598925026354e-05,
"loss": 4.475,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941321297751584e-05,
"loss": 4.4599,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940482703000532e-05,
"loss": 4.466,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396441082494794e-05,
"loss": 4.4575,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388055134984274e-05,
"loss": 4.4561,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4584,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4502,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4416,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4269,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4338,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4308,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4331,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4258,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4131,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.3969,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.4015,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.4024,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.4031,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.3985,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.3939,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3819,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3787,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3765,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.3835,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922041807879253e-05,
"loss": 4.3755,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921203213128201e-05,
"loss": 4.352,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3571,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3629,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3642,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.357,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3497,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.3493,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.3437,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3472,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913657498249106e-05,
"loss": 4.3456,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3269,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3363,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.314,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3246,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.3239,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.3164,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3199,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3052,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3023,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3077,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3207,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.2925,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.2872,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.2898,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.3038,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.2917,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899407939002715e-05,
"loss": 4.2946,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985693442516624e-05,
"loss": 4.288,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2907,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.281,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2814,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2757,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.286,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2639,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.2767,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2724,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2598,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2711,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889348077750837e-05,
"loss": 4.2657,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888509482999785e-05,
"loss": 4.2699,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.2659,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.2481,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.2447,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2488,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2588,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2597,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2515,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2403,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2414,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801268112500106e-05,
"loss": 4.2444,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2404,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2354,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.2504,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876774070126176e-05,
"loss": 4.2379,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875935475375124e-05,
"loss": 4.2296,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875096880624072e-05,
"loss": 4.2271,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.243750095367432,
"eval_runtime": 568.7385,
"eval_samples_per_second": 670.943,
"eval_steps_per_second": 20.967,
"step": 76319
},
{
"epoch": 0.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.2337,
"step": 76800
},
{
"epoch": 0.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.2297,
"step": 77312
},
{
"epoch": 0.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2167,
"step": 77824
},
{
"epoch": 0.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2169,
"step": 78336
},
{
"epoch": 0.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2103,
"step": 78848
},
{
"epoch": 0.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2082,
"step": 79360
},
{
"epoch": 0.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2012,
"step": 79872
},
{
"epoch": 0.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.2031,
"step": 80384
},
{
"epoch": 0.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.2089,
"step": 80896
},
{
"epoch": 0.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.2071,
"step": 81408
},
{
"epoch": 0.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.2035,
"step": 81920
},
{
"epoch": 0.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.2064,
"step": 82432
},
{
"epoch": 0.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.1982,
"step": 82944
},
{
"epoch": 0.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.1931,
"step": 83456
},
{
"epoch": 0.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.1904,
"step": 83968
},
{
"epoch": 0.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.1642,
"step": 84480
},
{
"epoch": 0.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.1869,
"step": 84992
},
{
"epoch": 0.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.1843,
"step": 85504
},
{
"epoch": 0.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.1838,
"step": 86016
},
{
"epoch": 0.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.1949,
"step": 86528
},
{
"epoch": 0.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.1788,
"step": 87040
},
{
"epoch": 0.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.1812,
"step": 87552
},
{
"epoch": 0.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.1798,
"step": 88064
},
{
"epoch": 0.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.179,
"step": 88576
},
{
"epoch": 0.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.1698,
"step": 89088
},
{
"epoch": 0.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.1698,
"step": 89600
},
{
"epoch": 0.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.1761,
"step": 90112
},
{
"epoch": 0.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.1589,
"step": 90624
},
{
"epoch": 0.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.164,
"step": 91136
},
{
"epoch": 0.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.1519,
"step": 91648
},
{
"epoch": 0.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.1558,
"step": 92160
},
{
"epoch": 0.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.1671,
"step": 92672
},
{
"epoch": 0.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1595,
"step": 93184
},
{
"epoch": 0.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.1597,
"step": 93696
},
{
"epoch": 0.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.158,
"step": 94208
},
{
"epoch": 0.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.1576,
"step": 94720
},
{
"epoch": 0.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.1567,
"step": 95232
},
{
"epoch": 0.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.1539,
"step": 95744
},
{
"epoch": 0.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.1513,
"step": 96256
},
{
"epoch": 0.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.1398,
"step": 96768
},
{
"epoch": 0.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.1477,
"step": 97280
},
{
"epoch": 0.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.1316,
"step": 97792
},
{
"epoch": 0.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.1432,
"step": 98304
},
{
"epoch": 0.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.1481,
"step": 98816
},
{
"epoch": 0.01,
"learning_rate": 4.83737485775009e-05,
"loss": 4.1433,
"step": 99328
},
{
"epoch": 0.01,
"learning_rate": 4.836536262999038e-05,
"loss": 4.1356,
"step": 99840
},
{
"epoch": 0.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1377,
"step": 100352
},
{
"epoch": 0.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.1425,
"step": 100864
},
{
"epoch": 0.01,
"learning_rate": 4.834022116626255e-05,
"loss": 4.1222,
"step": 101376
},
{
"epoch": 0.01,
"learning_rate": 4.833183521875203e-05,
"loss": 4.1254,
"step": 101888
},
{
"epoch": 0.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.1251,
"step": 102400
},
{
"epoch": 0.01,
"learning_rate": 4.831506332373099e-05,
"loss": 4.1396,
"step": 102912
},
{
"epoch": 0.01,
"learning_rate": 4.83066937550242e-05,
"loss": 4.1173,
"step": 103424
},
{
"epoch": 0.01,
"learning_rate": 4.829830780751368e-05,
"loss": 4.1383,
"step": 103936
},
{
"epoch": 0.01,
"learning_rate": 4.828992186000316e-05,
"loss": 4.1073,
"step": 104448
},
{
"epoch": 0.01,
"learning_rate": 4.828153591249264e-05,
"loss": 4.1229,
"step": 104960
},
{
"epoch": 0.01,
"learning_rate": 4.8273166343785856e-05,
"loss": 4.1215,
"step": 105472
},
{
"epoch": 0.01,
"learning_rate": 4.8264780396275336e-05,
"loss": 4.1249,
"step": 105984
},
{
"epoch": 0.01,
"learning_rate": 4.8256394448764816e-05,
"loss": 4.1156,
"step": 106496
},
{
"epoch": 0.01,
"learning_rate": 4.8248008501254296e-05,
"loss": 4.1191,
"step": 107008
},
{
"epoch": 0.01,
"learning_rate": 4.8239638932547505e-05,
"loss": 4.1065,
"step": 107520
},
{
"epoch": 0.01,
"learning_rate": 4.8231252985036985e-05,
"loss": 4.1168,
"step": 108032
},
{
"epoch": 0.01,
"learning_rate": 4.8222867037526465e-05,
"loss": 4.1083,
"step": 108544
},
{
"epoch": 0.01,
"learning_rate": 4.8214481090015945e-05,
"loss": 4.1133,
"step": 109056
},
{
"epoch": 0.01,
"learning_rate": 4.8206111521309154e-05,
"loss": 4.1083,
"step": 109568
},
{
"epoch": 0.01,
"learning_rate": 4.8197725573798634e-05,
"loss": 4.1046,
"step": 110080
},
{
"epoch": 0.01,
"learning_rate": 4.8189339626288114e-05,
"loss": 4.0879,
"step": 110592
},
{
"epoch": 0.01,
"learning_rate": 4.8180953678777594e-05,
"loss": 4.1127,
"step": 111104
},
{
"epoch": 0.01,
"learning_rate": 4.817258411007081e-05,
"loss": 4.1025,
"step": 111616
},
{
"epoch": 0.01,
"learning_rate": 4.816419816256029e-05,
"loss": 4.0941,
"step": 112128
},
{
"epoch": 0.01,
"learning_rate": 4.815581221504977e-05,
"loss": 4.1016,
"step": 112640
},
{
"epoch": 0.01,
"learning_rate": 4.814742626753924e-05,
"loss": 4.0982,
"step": 113152
},
{
"epoch": 0.01,
"learning_rate": 4.813905669883246e-05,
"loss": 4.0995,
"step": 113664
},
{
"epoch": 0.01,
"learning_rate": 4.813067075132194e-05,
"loss": 4.1085,
"step": 114176
},
{
"epoch": 0.01,
"learning_rate": 4.812228480381141e-05,
"loss": 4.1035,
"step": 114688
},
{
"epoch": 0.01,
"learning_rate": 4.811389885630089e-05,
"loss": 4.0942,
"step": 115200
},
{
"epoch": 0.01,
"learning_rate": 4.810552928759411e-05,
"loss": 4.0869,
"step": 115712
},
{
"epoch": 0.01,
"learning_rate": 4.809714334008359e-05,
"loss": 4.0926,
"step": 116224
},
{
"epoch": 0.01,
"learning_rate": 4.808875739257306e-05,
"loss": 4.095,
"step": 116736
},
{
"epoch": 0.01,
"learning_rate": 4.808037144506255e-05,
"loss": 4.1045,
"step": 117248
},
{
"epoch": 0.01,
"learning_rate": 4.807200187635576e-05,
"loss": 4.0934,
"step": 117760
},
{
"epoch": 0.01,
"learning_rate": 4.8063615928845243e-05,
"loss": 4.0882,
"step": 118272
},
{
"epoch": 0.01,
"learning_rate": 4.8055229981334717e-05,
"loss": 4.0731,
"step": 118784
},
{
"epoch": 0.01,
"learning_rate": 4.804686041262793e-05,
"loss": 4.0785,
"step": 119296
},
{
"epoch": 0.01,
"learning_rate": 4.803847446511741e-05,
"loss": 4.0815,
"step": 119808
},
{
"epoch": 0.01,
"learning_rate": 4.8030088517606886e-05,
"loss": 4.0834,
"step": 120320
},
{
"epoch": 0.01,
"learning_rate": 4.8021702570096366e-05,
"loss": 4.0908,
"step": 120832
},
{
"epoch": 0.01,
"learning_rate": 4.801333300138958e-05,
"loss": 4.0829,
"step": 121344
},
{
"epoch": 0.01,
"learning_rate": 4.800494705387906e-05,
"loss": 4.0749,
"step": 121856
},
{
"epoch": 0.02,
"learning_rate": 4.7996561106368535e-05,
"loss": 4.0793,
"step": 122368
},
{
"epoch": 0.02,
"learning_rate": 4.7988175158858015e-05,
"loss": 4.071,
"step": 122880
},
{
"epoch": 0.02,
"learning_rate": 4.797980559015123e-05,
"loss": 4.0805,
"step": 123392
},
{
"epoch": 0.02,
"learning_rate": 4.797141964264071e-05,
"loss": 4.0798,
"step": 123904
},
{
"epoch": 0.02,
"learning_rate": 4.796303369513019e-05,
"loss": 4.0608,
"step": 124416
},
{
"epoch": 0.02,
"learning_rate": 4.795464774761967e-05,
"loss": 4.0623,
"step": 124928
},
{
"epoch": 0.02,
"learning_rate": 4.7946278178912886e-05,
"loss": 4.0697,
"step": 125440
},
{
"epoch": 0.02,
"learning_rate": 4.793789223140236e-05,
"loss": 4.0802,
"step": 125952
},
{
"epoch": 0.02,
"learning_rate": 4.7929522662695575e-05,
"loss": 4.0656,
"step": 126464
},
{
"epoch": 0.02,
"learning_rate": 4.7921136715185055e-05,
"loss": 4.0741,
"step": 126976
},
{
"epoch": 0.02,
"learning_rate": 4.7912750767674535e-05,
"loss": 4.0662,
"step": 127488
},
{
"epoch": 0.02,
"learning_rate": 4.790436482016401e-05,
"loss": 4.0645,
"step": 128000
},
{
"epoch": 0.02,
"learning_rate": 4.789597887265349e-05,
"loss": 4.0701,
"step": 128512
},
{
"epoch": 0.02,
"learning_rate": 4.788759292514297e-05,
"loss": 4.069,
"step": 129024
},
{
"epoch": 0.02,
"learning_rate": 4.7879223356436184e-05,
"loss": 4.0562,
"step": 129536
},
{
"epoch": 0.02,
"learning_rate": 4.7870837408925664e-05,
"loss": 4.0683,
"step": 130048
},
{
"epoch": 0.02,
"learning_rate": 4.7862451461415144e-05,
"loss": 4.0479,
"step": 130560
},
{
"epoch": 0.02,
"learning_rate": 4.7854065513904624e-05,
"loss": 4.055,
"step": 131072
},
{
"epoch": 0.02,
"learning_rate": 4.7845679566394104e-05,
"loss": 4.0617,
"step": 131584
},
{
"epoch": 0.02,
"learning_rate": 4.7837293618883584e-05,
"loss": 4.0502,
"step": 132096
},
{
"epoch": 0.02,
"learning_rate": 4.7828907671373064e-05,
"loss": 4.0558,
"step": 132608
},
{
"epoch": 0.02,
"learning_rate": 4.7820521723862544e-05,
"loss": 4.0497,
"step": 133120
},
{
"epoch": 0.02,
"learning_rate": 4.781215215515575e-05,
"loss": 4.0453,
"step": 133632
},
{
"epoch": 0.02,
"learning_rate": 4.780378258644896e-05,
"loss": 4.0511,
"step": 134144
},
{
"epoch": 0.02,
"learning_rate": 4.779539663893844e-05,
"loss": 4.0662,
"step": 134656
},
{
"epoch": 0.02,
"learning_rate": 4.778701069142792e-05,
"loss": 4.0424,
"step": 135168
},
{
"epoch": 0.02,
"learning_rate": 4.77786247439174e-05,
"loss": 4.0417,
"step": 135680
},
{
"epoch": 0.02,
"learning_rate": 4.777023879640689e-05,
"loss": 4.0404,
"step": 136192
},
{
"epoch": 0.02,
"learning_rate": 4.776185284889637e-05,
"loss": 4.0507,
"step": 136704
},
{
"epoch": 0.02,
"learning_rate": 4.775346690138585e-05,
"loss": 4.0486,
"step": 137216
},
{
"epoch": 0.02,
"learning_rate": 4.774509733267906e-05,
"loss": 4.0463,
"step": 137728
},
{
"epoch": 0.02,
"learning_rate": 4.773671138516854e-05,
"loss": 4.0474,
"step": 138240
},
{
"epoch": 0.02,
"learning_rate": 4.772832543765802e-05,
"loss": 4.0481,
"step": 138752
},
{
"epoch": 0.02,
"learning_rate": 4.77199394901475e-05,
"loss": 4.0442,
"step": 139264
},
{
"epoch": 0.02,
"learning_rate": 4.771155354263698e-05,
"loss": 4.0392,
"step": 139776
},
{
"epoch": 0.02,
"learning_rate": 4.770316759512646e-05,
"loss": 4.0412,
"step": 140288
},
{
"epoch": 0.02,
"learning_rate": 4.769478164761594e-05,
"loss": 4.0511,
"step": 140800
},
{
"epoch": 0.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.0341,
"step": 141312
},
{
"epoch": 0.02,
"learning_rate": 4.7678026131398626e-05,
"loss": 4.0374,
"step": 141824
},
{
"epoch": 0.02,
"learning_rate": 4.7669640183888106e-05,
"loss": 4.0487,
"step": 142336
},
{
"epoch": 0.02,
"learning_rate": 4.7661254236377586e-05,
"loss": 4.0249,
"step": 142848
},
{
"epoch": 0.02,
"learning_rate": 4.765286828886707e-05,
"loss": 4.0421,
"step": 143360
},
{
"epoch": 0.02,
"learning_rate": 4.764451509896401e-05,
"loss": 4.0354,
"step": 143872
},
{
"epoch": 0.02,
"learning_rate": 4.763612915145349e-05,
"loss": 4.047,
"step": 144384
},
{
"epoch": 0.02,
"learning_rate": 4.762774320394297e-05,
"loss": 4.0394,
"step": 144896
},
{
"epoch": 0.02,
"learning_rate": 4.761935725643245e-05,
"loss": 4.0266,
"step": 145408
},
{
"epoch": 0.02,
"learning_rate": 4.761097130892193e-05,
"loss": 4.0248,
"step": 145920
},
{
"epoch": 0.02,
"learning_rate": 4.760258536141141e-05,
"loss": 4.0304,
"step": 146432
},
{
"epoch": 0.02,
"learning_rate": 4.759421579270462e-05,
"loss": 4.0399,
"step": 146944
},
{
"epoch": 0.02,
"learning_rate": 4.75858298451941e-05,
"loss": 4.0414,
"step": 147456
},
{
"epoch": 0.02,
"learning_rate": 4.757744389768358e-05,
"loss": 4.0377,
"step": 147968
},
{
"epoch": 0.02,
"learning_rate": 4.756905795017306e-05,
"loss": 4.0228,
"step": 148480
},
{
"epoch": 0.02,
"learning_rate": 4.756067200266254e-05,
"loss": 4.0271,
"step": 148992
},
{
"epoch": 0.02,
"learning_rate": 4.755228605515202e-05,
"loss": 4.0346,
"step": 149504
},
{
"epoch": 0.02,
"learning_rate": 4.75439001076415e-05,
"loss": 4.0287,
"step": 150016
},
{
"epoch": 0.02,
"learning_rate": 4.7535530538934716e-05,
"loss": 4.0246,
"step": 150528
},
{
"epoch": 0.02,
"learning_rate": 4.7527144591424196e-05,
"loss": 4.0425,
"step": 151040
},
{
"epoch": 0.02,
"learning_rate": 4.751875864391367e-05,
"loss": 4.0232,
"step": 151552
},
{
"epoch": 0.02,
"learning_rate": 4.751037269640315e-05,
"loss": 4.0267,
"step": 152064
},
{
"epoch": 0.02,
"learning_rate": 4.750198674889263e-05,
"loss": 4.0211,
"step": 152576
},
{
"epoch": 0.03,
"eval_loss": 4.073619365692139,
"eval_runtime": 572.2917,
"eval_samples_per_second": 666.777,
"eval_steps_per_second": 20.837,
"step": 152638
},
{
"epoch": 0.0,
"learning_rate": 4.7493617180185845e-05,
"loss": 4.0314,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748523123267532e-05,
"loss": 4.027,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.74768452851648e-05,
"loss": 4.0185,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746845933765428e-05,
"loss": 4.016,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460073390143764e-05,
"loss": 4.0105,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451687442633244e-05,
"loss": 4.0113,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443301495122724e-05,
"loss": 4.0091,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434915547612204e-05,
"loss": 4.0082,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426545978905413e-05,
"loss": 4.0131,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741816003139489e-05,
"loss": 4.0143,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740977408388437e-05,
"loss": 4.0136,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740138813637385e-05,
"loss": 4.014,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739301856766706e-05,
"loss": 4.0086,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738463262015654e-05,
"loss": 4.0035,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737624667264602e-05,
"loss": 4.0048,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.73678607251355e-05,
"loss": 3.9782,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735947477762498e-05,
"loss": 4.0035,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735108883011446e-05,
"loss": 4.0003,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734270288260394e-05,
"loss": 3.9989,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733433331389716e-05,
"loss": 4.0165,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732594736638664e-05,
"loss": 3.9985,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731756141887612e-05,
"loss": 4.004,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73091754713656e-05,
"loss": 4.0009,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730078952385508e-05,
"loss": 3.9989,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729241995514829e-05,
"loss": 3.9932,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728403400763777e-05,
"loss": 3.9925,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727564806012725e-05,
"loss": 4.0005,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726726211261673e-05,
"loss": 3.9855,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725887616510621e-05,
"loss": 3.9913,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725049021759568e-05,
"loss": 3.9783,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7242120648888896e-05,
"loss": 3.9875,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723373470137838e-05,
"loss": 3.9964,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225348753867856e-05,
"loss": 3.9858,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216962806357336e-05,
"loss": 3.9933,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720859323765055e-05,
"loss": 3.9882,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720020729014003e-05,
"loss": 3.9907,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191821342629505e-05,
"loss": 3.9938,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183435395118985e-05,
"loss": 3.9892,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175049447608465e-05,
"loss": 3.9855,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716667987890168e-05,
"loss": 3.9746,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158293931391154e-05,
"loss": 3.9852,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149907983880634e-05,
"loss": 3.9711,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714152203637012e-05,
"loss": 3.9873,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71331360888596e-05,
"loss": 3.9839,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712475014134908e-05,
"loss": 3.9855,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711638057264229e-05,
"loss": 3.9764,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710799462513177e-05,
"loss": 3.9774,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709960867762125e-05,
"loss": 3.9849,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709122273011073e-05,
"loss": 3.9654,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708285316140394e-05,
"loss": 3.9712,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707446721389342e-05,
"loss": 3.9664,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.70660812663829e-05,
"loss": 3.9847,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705769531887238e-05,
"loss": 3.9653,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704930937136186e-05,
"loss": 3.9848,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040939802655074e-05,
"loss": 3.9562,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032553855144554e-05,
"loss": 3.9683,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024167907634034e-05,
"loss": 3.9729,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015781960123514e-05,
"loss": 3.9714,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700741239141672e-05,
"loss": 3.9675,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.69990264439062e-05,
"loss": 3.9809,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699064049639568e-05,
"loss": 3.95,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698225454888516e-05,
"loss": 3.9665,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697386860137464e-05,
"loss": 3.9617,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696549903266785e-05,
"loss": 3.9703,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695711308515733e-05,
"loss": 3.9581,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694872713764681e-05,
"loss": 3.9615,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694034119013629e-05,
"loss": 3.9449,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693197162142951e-05,
"loss": 3.9678,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692358567391899e-05,
"loss": 3.9583,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691519972640847e-05,
"loss": 3.9551,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690681377889795e-05,
"loss": 3.96,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898444210191157e-05,
"loss": 3.9585,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890058262680636e-05,
"loss": 3.9563,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881672315170116e-05,
"loss": 3.971,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873286367659596e-05,
"loss": 3.9653,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864916798952806e-05,
"loss": 3.9575,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856530851442285e-05,
"loss": 3.9497,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848144903931765e-05,
"loss": 3.9519,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839758956421245e-05,
"loss": 3.9594,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831373008910725e-05,
"loss": 3.9669,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682300344020394e-05,
"loss": 3.9544,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681461749269342e-05,
"loss": 3.9572,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.68062315451829e-05,
"loss": 3.9387,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679784559767238e-05,
"loss": 3.9484,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678945965016186e-05,
"loss": 3.9406,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678109008145507e-05,
"loss": 3.9499,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677270413394455e-05,
"loss": 3.9578,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676431818643403e-05,
"loss": 3.9499,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9422,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674756267021672e-05,
"loss": 3.948,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.67391767227062e-05,
"loss": 3.9404,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673079077519568e-05,
"loss": 3.9511,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672240482768516e-05,
"loss": 3.9478,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6714035258978375e-05,
"loss": 3.9334,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705649311467855e-05,
"loss": 3.9339,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697263363957335e-05,
"loss": 3.9408,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688877416446815e-05,
"loss": 3.9506,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668049146893629e-05,
"loss": 3.9399,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6672121900229504e-05,
"loss": 3.9491,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663735952718984e-05,
"loss": 3.9375,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665535000520846e-05,
"loss": 3.9383,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664696405769794e-05,
"loss": 3.9432,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663859448899115e-05,
"loss": 3.9436,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663020854148063e-05,
"loss": 3.9319,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662182259397011e-05,
"loss": 3.9479,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661343664645959e-05,
"loss": 3.9241,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660506707775281e-05,
"loss": 3.9281,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659668113024229e-05,
"loss": 3.9403,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658829518273176e-05,
"loss": 3.9251,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657990923522124e-05,
"loss": 3.9378,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657153966651446e-05,
"loss": 3.9273,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656315371900393e-05,
"loss": 3.9222,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655476777149341e-05,
"loss": 3.927,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654638182398289e-05,
"loss": 3.9477,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6538012255276106e-05,
"loss": 3.9236,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.6529626307765586e-05,
"loss": 3.9264,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521240360255066e-05,
"loss": 3.9186,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512854412744546e-05,
"loss": 3.9278,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650448484403776e-05,
"loss": 3.9354,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6496098896527235e-05,
"loss": 3.9288,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487712949016715e-05,
"loss": 3.9266,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479327001506195e-05,
"loss": 3.928,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470957432799404e-05,
"loss": 3.9269,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462571485288884e-05,
"loss": 3.9262,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454185537778364e-05,
"loss": 3.9242,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445799590267844e-05,
"loss": 3.9338,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437413642757324e-05,
"loss": 3.9209,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642904407405054e-05,
"loss": 3.9204,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642065812654002e-05,
"loss": 3.9352,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.64122721790295e-05,
"loss": 3.912,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640388623151898e-05,
"loss": 3.9253,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639551666281219e-05,
"loss": 3.9236,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638713071530167e-05,
"loss": 3.934,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637874476779115e-05,
"loss": 3.9249,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637035882028063e-05,
"loss": 3.9197,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636198925157384e-05,
"loss": 3.9108,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635360330406332e-05,
"loss": 3.9162,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.63452173565528e-05,
"loss": 3.9275,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633683140904228e-05,
"loss": 3.9305,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328461840335494e-05,
"loss": 3.9262,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320075892824974e-05,
"loss": 3.915,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311689945314454e-05,
"loss": 3.9144,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303303997803934e-05,
"loss": 3.9286,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629493442909714e-05,
"loss": 3.9156,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628654848158662e-05,
"loss": 3.9166,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.62781625340761e-05,
"loss": 3.9303,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626977658656558e-05,
"loss": 3.9154,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626140701785879e-05,
"loss": 3.9199,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625302107034827e-05,
"loss": 3.9159,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.0001678466796875,
"eval_runtime": 585.2038,
"eval_samples_per_second": 652.065,
"eval_steps_per_second": 20.378,
"step": 228957
},
{
"epoch": 0.0,
"learning_rate": 4.624463512283775e-05,
"loss": 3.9246,
"step": 229376
},
{
"epoch": 0.0,
"learning_rate": 4.623624917532723e-05,
"loss": 3.9203,
"step": 229888
},
{
"epoch": 0.0,
"learning_rate": 4.622786322781671e-05,
"loss": 3.9119,
"step": 230400
},
{
"epoch": 0.0,
"learning_rate": 4.62194772803062e-05,
"loss": 3.9105,
"step": 230912
},
{
"epoch": 0.0,
"learning_rate": 4.621109133279568e-05,
"loss": 3.9081,
"step": 231424
},
{
"epoch": 0.0,
"learning_rate": 4.620270538528516e-05,
"loss": 3.9044,
"step": 231936
},
{
"epoch": 0.0,
"learning_rate": 4.619431943777464e-05,
"loss": 3.9074,
"step": 232448
},
{
"epoch": 0.0,
"learning_rate": 4.618593349026412e-05,
"loss": 3.9021,
"step": 232960
},
{
"epoch": 0.0,
"learning_rate": 4.617756392155733e-05,
"loss": 3.9096,
"step": 233472
},
{
"epoch": 0.0,
"learning_rate": 4.616917797404681e-05,
"loss": 3.9161,
"step": 233984
},
{
"epoch": 0.0,
"learning_rate": 4.616079202653629e-05,
"loss": 3.9076,
"step": 234496
},
{
"epoch": 0.0,
"learning_rate": 4.615240607902577e-05,
"loss": 3.9071,
"step": 235008
},
{
"epoch": 0.0,
"learning_rate": 4.6144036510318976e-05,
"loss": 3.9075,
"step": 235520
},
{
"epoch": 0.0,
"learning_rate": 4.6135650562808456e-05,
"loss": 3.9042,
"step": 236032
},
{
"epoch": 0.0,
"learning_rate": 4.6127264615297936e-05,
"loss": 3.901,
"step": 236544
},
{
"epoch": 0.0,
"learning_rate": 4.6118878667787416e-05,
"loss": 3.8802,
"step": 237056
},
{
"epoch": 0.0,
"learning_rate": 4.611050909908063e-05,
"loss": 3.8977,
"step": 237568
},
{
"epoch": 0.0,
"learning_rate": 4.610212315157011e-05,
"loss": 3.899,
"step": 238080
},
{
"epoch": 0.0,
"learning_rate": 4.609373720405959e-05,
"loss": 3.9005,
"step": 238592
},
{
"epoch": 0.0,
"learning_rate": 4.6085351256549065e-05,
"loss": 3.9142,
"step": 239104
},
{
"epoch": 0.0,
"learning_rate": 4.607698168784228e-05,
"loss": 3.8995,
"step": 239616
},
{
"epoch": 0.0,
"learning_rate": 4.606859574033176e-05,
"loss": 3.9076,
"step": 240128
},
{
"epoch": 0.0,
"learning_rate": 4.606020979282124e-05,
"loss": 3.8965,
"step": 240640
},
{
"epoch": 0.0,
"learning_rate": 4.605184022411445e-05,
"loss": 3.8974,
"step": 241152
},
{
"epoch": 0.0,
"learning_rate": 4.604345427660393e-05,
"loss": 3.896,
"step": 241664
},
{
"epoch": 0.0,
"learning_rate": 4.603506832909341e-05,
"loss": 3.8981,
"step": 242176
},
{
"epoch": 0.0,
"learning_rate": 4.602668238158289e-05,
"loss": 3.8992,
"step": 242688
},
{
"epoch": 0.0,
"learning_rate": 4.60183128128761e-05,
"loss": 3.8885,
"step": 243200
},
{
"epoch": 0.0,
"learning_rate": 4.6009926865365585e-05,
"loss": 3.8909,
"step": 243712
},
{
"epoch": 0.01,
"learning_rate": 4.6001540917855065e-05,
"loss": 3.8819,
"step": 244224
},
{
"epoch": 0.01,
"learning_rate": 4.599315497034454e-05,
"loss": 3.8913,
"step": 244736
},
{
"epoch": 0.01,
"learning_rate": 4.598476902283402e-05,
"loss": 3.899,
"step": 245248
},
{
"epoch": 0.01,
"learning_rate": 4.5976399454127234e-05,
"loss": 3.8937,
"step": 245760
},
{
"epoch": 0.01,
"learning_rate": 4.5968013506616714e-05,
"loss": 3.8955,
"step": 246272
},
{
"epoch": 0.01,
"learning_rate": 4.595962755910619e-05,
"loss": 3.8936,
"step": 246784
},
{
"epoch": 0.01,
"learning_rate": 4.5951257990399403e-05,
"loss": 3.8949,
"step": 247296
},
{
"epoch": 0.01,
"learning_rate": 4.594287204288888e-05,
"loss": 3.8959,
"step": 247808
},
{
"epoch": 0.01,
"learning_rate": 4.593448609537836e-05,
"loss": 3.8968,
"step": 248320
},
{
"epoch": 0.01,
"learning_rate": 4.5926100147867836e-05,
"loss": 3.8883,
"step": 248832
},
{
"epoch": 0.01,
"learning_rate": 4.591773057916105e-05,
"loss": 3.8805,
"step": 249344
},
{
"epoch": 0.01,
"learning_rate": 4.590934463165054e-05,
"loss": 3.8909,
"step": 249856
},
{
"epoch": 0.01,
"learning_rate": 4.590095868414001e-05,
"loss": 3.8738,
"step": 250368
},
{
"epoch": 0.01,
"learning_rate": 4.589257273662949e-05,
"loss": 3.8977,
"step": 250880
},
{
"epoch": 0.01,
"learning_rate": 4.588420316792271e-05,
"loss": 3.8916,
"step": 251392
},
{
"epoch": 0.01,
"learning_rate": 4.587581722041219e-05,
"loss": 3.8904,
"step": 251904
},
{
"epoch": 0.01,
"learning_rate": 4.586743127290166e-05,
"loss": 3.8835,
"step": 252416
},
{
"epoch": 0.01,
"learning_rate": 4.585904532539114e-05,
"loss": 3.8835,
"step": 252928
},
{
"epoch": 0.01,
"learning_rate": 4.585067575668436e-05,
"loss": 3.8957,
"step": 253440
},
{
"epoch": 0.01,
"learning_rate": 4.584228980917384e-05,
"loss": 3.8722,
"step": 253952
},
{
"epoch": 0.01,
"learning_rate": 4.583390386166331e-05,
"loss": 3.8779,
"step": 254464
},
{
"epoch": 0.01,
"learning_rate": 4.582551791415279e-05,
"loss": 3.8791,
"step": 254976
},
{
"epoch": 0.01,
"learning_rate": 4.5817148345446006e-05,
"loss": 3.8902,
"step": 255488
},
{
"epoch": 0.01,
"learning_rate": 4.5808762397935486e-05,
"loss": 3.8723,
"step": 256000
},
{
"epoch": 0.01,
"learning_rate": 4.5800376450424966e-05,
"loss": 3.8931,
"step": 256512
},
{
"epoch": 0.01,
"learning_rate": 4.5791990502914446e-05,
"loss": 3.8707,
"step": 257024
},
{
"epoch": 0.01,
"learning_rate": 4.578362093420766e-05,
"loss": 3.8716,
"step": 257536
},
{
"epoch": 0.01,
"learning_rate": 4.5775234986697135e-05,
"loss": 3.8867,
"step": 258048
},
{
"epoch": 0.01,
"learning_rate": 4.5766849039186615e-05,
"loss": 3.874,
"step": 258560
},
{
"epoch": 0.01,
"learning_rate": 4.5758463091676095e-05,
"loss": 3.8863,
"step": 259072
},
{
"epoch": 0.01,
"learning_rate": 4.575009352296931e-05,
"loss": 3.8918,
"step": 259584
},
{
"epoch": 0.01,
"learning_rate": 4.5741707575458784e-05,
"loss": 3.8653,
"step": 260096
},
{
"epoch": 0.01,
"learning_rate": 4.5733321627948264e-05,
"loss": 3.8725,
"step": 260608
},
{
"epoch": 0.01,
"learning_rate": 4.5724935680437744e-05,
"loss": 3.8754,
"step": 261120
},
{
"epoch": 0.01,
"learning_rate": 4.571656611173096e-05,
"loss": 3.8805,
"step": 261632
},
{
"epoch": 0.01,
"learning_rate": 4.570818016422044e-05,
"loss": 3.8697,
"step": 262144
},
{
"epoch": 0.01,
"learning_rate": 4.569979421670992e-05,
"loss": 3.8735,
"step": 262656
},
{
"epoch": 0.01,
"learning_rate": 4.56914082691994e-05,
"loss": 3.8568,
"step": 263168
},
{
"epoch": 0.01,
"learning_rate": 4.568303870049261e-05,
"loss": 3.8805,
"step": 263680
},
{
"epoch": 0.01,
"learning_rate": 4.567465275298209e-05,
"loss": 3.8711,
"step": 264192
},
{
"epoch": 0.01,
"learning_rate": 4.566626680547157e-05,
"loss": 3.8672,
"step": 264704
},
{
"epoch": 0.01,
"learning_rate": 4.565788085796105e-05,
"loss": 3.8717,
"step": 265216
},
{
"epoch": 0.01,
"learning_rate": 4.564951128925426e-05,
"loss": 3.8724,
"step": 265728
},
{
"epoch": 0.01,
"learning_rate": 4.564112534174374e-05,
"loss": 3.8714,
"step": 266240
},
{
"epoch": 0.01,
"learning_rate": 4.563273939423322e-05,
"loss": 3.8829,
"step": 266752
},
{
"epoch": 0.01,
"learning_rate": 4.56243534467227e-05,
"loss": 3.8802,
"step": 267264
},
{
"epoch": 0.01,
"learning_rate": 4.561598387801591e-05,
"loss": 3.874,
"step": 267776
},
{
"epoch": 0.01,
"learning_rate": 4.560759793050539e-05,
"loss": 3.867,
"step": 268288
},
{
"epoch": 0.01,
"learning_rate": 4.559921198299487e-05,
"loss": 3.8681,
"step": 268800
},
{
"epoch": 0.01,
"learning_rate": 4.559082603548435e-05,
"loss": 3.871,
"step": 269312
},
{
"epoch": 0.01,
"learning_rate": 4.558245646677756e-05,
"loss": 3.8833,
"step": 269824
},
{
"epoch": 0.01,
"learning_rate": 4.557407051926704e-05,
"loss": 3.8726,
"step": 270336
},
{
"epoch": 0.01,
"learning_rate": 4.556568457175652e-05,
"loss": 3.8659,
"step": 270848
},
{
"epoch": 0.01,
"learning_rate": 4.5557298624246e-05,
"loss": 3.86,
"step": 271360
},
{
"epoch": 0.01,
"learning_rate": 4.554892905553921e-05,
"loss": 3.8646,
"step": 271872
},
{
"epoch": 0.01,
"learning_rate": 4.554054310802869e-05,
"loss": 3.8588,
"step": 272384
},
{
"epoch": 0.01,
"learning_rate": 4.553215716051817e-05,
"loss": 3.8657,
"step": 272896
},
{
"epoch": 0.01,
"learning_rate": 4.552377121300765e-05,
"loss": 3.8681,
"step": 273408
},
{
"epoch": 0.01,
"learning_rate": 4.551540164430087e-05,
"loss": 3.8672,
"step": 273920
},
{
"epoch": 0.01,
"learning_rate": 4.550701569679035e-05,
"loss": 3.8613,
"step": 274432
},
{
"epoch": 0.02,
"learning_rate": 4.549862974927983e-05,
"loss": 3.8701,
"step": 274944
},
{
"epoch": 0.02,
"learning_rate": 4.549024380176931e-05,
"loss": 3.859,
"step": 275456
},
{
"epoch": 0.02,
"learning_rate": 4.5481874233062516e-05,
"loss": 3.8636,
"step": 275968
},
{
"epoch": 0.02,
"learning_rate": 4.5473488285551996e-05,
"loss": 3.8643,
"step": 276480
},
{
"epoch": 0.02,
"learning_rate": 4.5465102338041476e-05,
"loss": 3.8522,
"step": 276992
},
{
"epoch": 0.02,
"learning_rate": 4.5456716390530956e-05,
"loss": 3.8508,
"step": 277504
},
{
"epoch": 0.02,
"learning_rate": 4.5448346821824165e-05,
"loss": 3.8648,
"step": 278016
},
{
"epoch": 0.02,
"learning_rate": 4.5439960874313645e-05,
"loss": 3.862,
"step": 278528
},
{
"epoch": 0.02,
"learning_rate": 4.5431574926803125e-05,
"loss": 3.868,
"step": 279040
},
{
"epoch": 0.02,
"learning_rate": 4.5423188979292605e-05,
"loss": 3.8632,
"step": 279552
},
{
"epoch": 0.02,
"learning_rate": 4.541481941058582e-05,
"loss": 3.8568,
"step": 280064
},
{
"epoch": 0.02,
"learning_rate": 4.54064334630753e-05,
"loss": 3.8565,
"step": 280576
},
{
"epoch": 0.02,
"learning_rate": 4.539804751556478e-05,
"loss": 3.8654,
"step": 281088
},
{
"epoch": 0.02,
"learning_rate": 4.538966156805426e-05,
"loss": 3.8646,
"step": 281600
},
{
"epoch": 0.02,
"learning_rate": 4.538129199934747e-05,
"loss": 3.8516,
"step": 282112
},
{
"epoch": 0.02,
"learning_rate": 4.537290605183695e-05,
"loss": 3.869,
"step": 282624
},
{
"epoch": 0.02,
"learning_rate": 4.536452010432643e-05,
"loss": 3.8431,
"step": 283136
},
{
"epoch": 0.02,
"learning_rate": 4.535613415681591e-05,
"loss": 3.8524,
"step": 283648
},
{
"epoch": 0.02,
"learning_rate": 4.534776458810912e-05,
"loss": 3.8605,
"step": 284160
},
{
"epoch": 0.02,
"learning_rate": 4.53393786405986e-05,
"loss": 3.847,
"step": 284672
},
{
"epoch": 0.02,
"learning_rate": 4.533099269308808e-05,
"loss": 3.8602,
"step": 285184
},
{
"epoch": 0.02,
"learning_rate": 4.532260674557756e-05,
"loss": 3.8454,
"step": 285696
},
{
"epoch": 0.02,
"learning_rate": 4.5314237176870774e-05,
"loss": 3.8418,
"step": 286208
},
{
"epoch": 0.02,
"learning_rate": 4.5305851229360254e-05,
"loss": 3.8496,
"step": 286720
},
{
"epoch": 0.02,
"learning_rate": 4.5297465281849734e-05,
"loss": 3.8695,
"step": 287232
},
{
"epoch": 0.02,
"learning_rate": 4.5289079334339214e-05,
"loss": 3.8486,
"step": 287744
},
{
"epoch": 0.02,
"learning_rate": 4.528070976563242e-05,
"loss": 3.8484,
"step": 288256
},
{
"epoch": 0.02,
"learning_rate": 4.52723238181219e-05,
"loss": 3.8419,
"step": 288768
},
{
"epoch": 0.02,
"learning_rate": 4.526393787061138e-05,
"loss": 3.8506,
"step": 289280
},
{
"epoch": 0.02,
"learning_rate": 4.525555192310086e-05,
"loss": 3.857,
"step": 289792
},
{
"epoch": 0.02,
"learning_rate": 4.524718235439407e-05,
"loss": 3.8533,
"step": 290304
},
{
"epoch": 0.02,
"learning_rate": 4.523879640688355e-05,
"loss": 3.8446,
"step": 290816
},
{
"epoch": 0.02,
"learning_rate": 4.523041045937303e-05,
"loss": 3.8561,
"step": 291328
},
{
"epoch": 0.02,
"learning_rate": 4.522202451186251e-05,
"loss": 3.8503,
"step": 291840
},
{
"epoch": 0.02,
"learning_rate": 4.521365494315573e-05,
"loss": 3.851,
"step": 292352
},
{
"epoch": 0.02,
"learning_rate": 4.520526899564521e-05,
"loss": 3.8456,
"step": 292864
},
{
"epoch": 0.02,
"learning_rate": 4.519688304813469e-05,
"loss": 3.8576,
"step": 293376
},
{
"epoch": 0.02,
"learning_rate": 4.518849710062417e-05,
"loss": 3.8462,
"step": 293888
},
{
"epoch": 0.02,
"learning_rate": 4.518012753191738e-05,
"loss": 3.8458,
"step": 294400
},
{
"epoch": 0.02,
"learning_rate": 4.517174158440686e-05,
"loss": 3.8599,
"step": 294912
},
{
"epoch": 0.02,
"learning_rate": 4.516335563689634e-05,
"loss": 3.8362,
"step": 295424
},
{
"epoch": 0.02,
"learning_rate": 4.515496968938582e-05,
"loss": 3.8494,
"step": 295936
},
{
"epoch": 0.02,
"learning_rate": 4.5146600120679026e-05,
"loss": 3.8517,
"step": 296448
},
{
"epoch": 0.02,
"learning_rate": 4.5138214173168506e-05,
"loss": 3.8567,
"step": 296960
},
{
"epoch": 0.02,
"learning_rate": 4.5129828225657986e-05,
"loss": 3.849,
"step": 297472
},
{
"epoch": 0.02,
"learning_rate": 4.5121442278147466e-05,
"loss": 3.8474,
"step": 297984
},
{
"epoch": 0.02,
"learning_rate": 4.511307270944068e-05,
"loss": 3.8374,
"step": 298496
},
{
"epoch": 0.02,
"learning_rate": 4.510468676193016e-05,
"loss": 3.8415,
"step": 299008
},
{
"epoch": 0.02,
"learning_rate": 4.509630081441964e-05,
"loss": 3.8513,
"step": 299520
},
{
"epoch": 0.02,
"learning_rate": 4.508791486690912e-05,
"loss": 3.8564,
"step": 300032
},
{
"epoch": 0.02,
"learning_rate": 4.507954529820233e-05,
"loss": 3.8545,
"step": 300544
},
{
"epoch": 0.02,
"learning_rate": 4.507115935069181e-05,
"loss": 3.8439,
"step": 301056
},
{
"epoch": 0.02,
"learning_rate": 4.506277340318129e-05,
"loss": 3.8378,
"step": 301568
},
{
"epoch": 0.02,
"learning_rate": 4.505438745567077e-05,
"loss": 3.854,
"step": 302080
},
{
"epoch": 0.02,
"learning_rate": 4.504601788696398e-05,
"loss": 3.843,
"step": 302592
},
{
"epoch": 0.02,
"learning_rate": 4.503763193945346e-05,
"loss": 3.8447,
"step": 303104
},
{
"epoch": 0.02,
"learning_rate": 4.502924599194294e-05,
"loss": 3.8556,
"step": 303616
},
{
"epoch": 0.02,
"learning_rate": 4.5020876423236155e-05,
"loss": 3.8464,
"step": 304128
},
{
"epoch": 0.02,
"learning_rate": 4.5012490475725635e-05,
"loss": 3.8461,
"step": 304640
},
{
"epoch": 0.02,
"learning_rate": 4.5004104528215115e-05,
"loss": 3.8439,
"step": 305152
},
{
"epoch": 0.03,
"eval_loss": 3.9584410190582275,
"eval_runtime": 567.4578,
"eval_samples_per_second": 672.457,
"eval_steps_per_second": 21.015,
"step": 305276
},
{
"epoch": 0.0,
"learning_rate": 4.4995718580704595e-05,
"loss": 3.8527,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987332633194075e-05,
"loss": 3.8476,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978946685683555e-05,
"loss": 3.8394,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970560738173035e-05,
"loss": 3.8381,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496217479066251e-05,
"loss": 3.838,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495378884315199e-05,
"loss": 3.8335,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494540289564147e-05,
"loss": 3.8376,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493701694813095e-05,
"loss": 3.83,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492864737942416e-05,
"loss": 3.8396,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.492027781071737e-05,
"loss": 3.8461,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491189186320685e-05,
"loss": 3.8329,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490350591569633e-05,
"loss": 3.8342,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489513634698955e-05,
"loss": 3.8393,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488675039947903e-05,
"loss": 3.835,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487836445196851e-05,
"loss": 3.8332,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486997850445798e-05,
"loss": 3.8105,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486159255694746e-05,
"loss": 3.8275,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485320660943694e-05,
"loss": 3.8306,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484482066192642e-05,
"loss": 3.8311,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.48364347144159e-05,
"loss": 3.8493,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482804876690538e-05,
"loss": 3.8264,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481966281939486e-05,
"loss": 3.8397,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481127687188434e-05,
"loss": 3.8257,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480290730317756e-05,
"loss": 3.8324,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479452135566704e-05,
"loss": 3.8238,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478613540815652e-05,
"loss": 3.8305,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.4777749460646e-05,
"loss": 3.8314,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.4769379891939207e-05,
"loss": 3.8244,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.4760993944428687e-05,
"loss": 3.8225,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.4752607996918166e-05,
"loss": 3.8166,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.4744222049407646e-05,
"loss": 3.8183,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.4735852480700856e-05,
"loss": 3.8307,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.4727466533190335e-05,
"loss": 3.8272,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.4719080585679815e-05,
"loss": 3.8313,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710694638169295e-05,
"loss": 3.8261,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470232506946251e-05,
"loss": 3.8296,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469393912195199e-05,
"loss": 3.828,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468555317444147e-05,
"loss": 3.8298,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467716722693095e-05,
"loss": 3.8245,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466879765822416e-05,
"loss": 3.8148,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466041171071364e-05,
"loss": 3.8295,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465202576320312e-05,
"loss": 3.8086,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.46436398156926e-05,
"loss": 3.8284,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463527024698581e-05,
"loss": 3.8243,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462688429947529e-05,
"loss": 3.8302,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461849835196477e-05,
"loss": 3.8193,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.461011240445425e-05,
"loss": 3.8167,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601742835747465e-05,
"loss": 3.8301,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4593356888236945e-05,
"loss": 3.811,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584970940726425e-05,
"loss": 3.8128,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576584993215905e-05,
"loss": 3.8157,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4568215424509114e-05,
"loss": 3.8203,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559829476998594e-05,
"loss": 3.8119,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551443529488074e-05,
"loss": 3.8246,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4543057581977554e-05,
"loss": 3.8073,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453468801327076e-05,
"loss": 3.8109,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452630206576024e-05,
"loss": 3.8213,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451791611824972e-05,
"loss": 3.8071,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.45095301707392e-05,
"loss": 3.8261,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450116060203242e-05,
"loss": 3.831,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.44927746545219e-05,
"loss": 3.7996,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448438870701138e-05,
"loss": 3.8079,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447600275950086e-05,
"loss": 3.8134,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446763319079407e-05,
"loss": 3.8226,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445924724328355e-05,
"loss": 3.8069,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445086129577303e-05,
"loss": 3.8078,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444247534826251e-05,
"loss": 3.7981,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.4434105779555717e-05,
"loss": 3.8145,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.4425719832045196e-05,
"loss": 3.8098,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.4417333884534676e-05,
"loss": 3.8025,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.4408947937024156e-05,
"loss": 3.8112,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440057836831737e-05,
"loss": 3.8099,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439219242080685e-05,
"loss": 3.8091,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438380647329633e-05,
"loss": 3.8213,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437543690458954e-05,
"loss": 3.8183,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436705095707902e-05,
"loss": 3.8131,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.43586650095685e-05,
"loss": 3.8078,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435027906205798e-05,
"loss": 3.8104,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434190949335119e-05,
"loss": 3.805,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433352354584067e-05,
"loss": 3.8279,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432513759833015e-05,
"loss": 3.8094,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431675165081963e-05,
"loss": 3.807,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430838208211284e-05,
"loss": 3.7959,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4300012513406055e-05,
"loss": 3.8106,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291626565895535e-05,
"loss": 3.7961,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4283240618385015e-05,
"loss": 3.8083,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274854670874495e-05,
"loss": 3.8067,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266468723363975e-05,
"loss": 3.8056,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4258082775853455e-05,
"loss": 3.8024,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249696828342935e-05,
"loss": 3.8116,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4241327259636144e-05,
"loss": 3.7984,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232941312125624e-05,
"loss": 3.8047,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224555364615104e-05,
"loss": 3.8078,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4216169417104584e-05,
"loss": 3.7899,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420779984839779e-05,
"loss": 3.7936,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419941390088728e-05,
"loss": 3.8082,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419102795337676e-05,
"loss": 3.7993,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418264200586624e-05,
"loss": 3.8147,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417427243715945e-05,
"loss": 3.8011,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416590286845266e-05,
"loss": 3.7934,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415751692094214e-05,
"loss": 3.7991,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414913097343162e-05,
"loss": 3.8052,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.41407450259211e-05,
"loss": 3.8063,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413235907841058e-05,
"loss": 3.7956,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412397313090006e-05,
"loss": 3.8089,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411558718338953e-05,
"loss": 3.785,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4107217614682747e-05,
"loss": 3.793,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409883166717223e-05,
"loss": 3.804,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409044571966171e-05,
"loss": 3.7861,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4082059772151186e-05,
"loss": 3.8018,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.40736902034444e-05,
"loss": 3.7973,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406532063473761e-05,
"loss": 3.7789,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405693468722709e-05,
"loss": 3.7933,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404854873971657e-05,
"loss": 3.8113,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.404016279220605e-05,
"loss": 3.7903,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403177684469553e-05,
"loss": 3.7929,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.4023390897185004e-05,
"loss": 3.7864,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.4015004949674484e-05,
"loss": 3.7913,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400661900216397e-05,
"loss": 3.8028,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399824943345719e-05,
"loss": 3.7962,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398986348594666e-05,
"loss": 3.7887,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398147753843614e-05,
"loss": 3.7944,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397309159092562e-05,
"loss": 3.7962,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.3964738401022565e-05,
"loss": 3.7932,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3956352453512045e-05,
"loss": 3.7921,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.3947966506001525e-05,
"loss": 3.8002,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939580558491005e-05,
"loss": 3.7864,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393119461098048e-05,
"loss": 3.795,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392280866346996e-05,
"loss": 3.799,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391442271595944e-05,
"loss": 3.7845,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3906036768448925e-05,
"loss": 3.7901,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897667199742134e-05,
"loss": 3.7978,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.3889281252231614e-05,
"loss": 3.7978,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.3880895304721094e-05,
"loss": 3.7974,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872509357210574e-05,
"loss": 3.7909,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386413978850378e-05,
"loss": 3.7821,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385575384099326e-05,
"loss": 3.7864,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384736789348274e-05,
"loss": 3.7941,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383898194597222e-05,
"loss": 3.8014,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383061237726543e-05,
"loss": 3.8019,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382222642975491e-05,
"loss": 3.7914,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381384048224439e-05,
"loss": 3.7805,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380547091353761e-05,
"loss": 3.7986,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379708496602709e-05,
"loss": 3.7855,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378869901851657e-05,
"loss": 3.7909,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378031307100605e-05,
"loss": 3.8031,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377192712349553e-05,
"loss": 3.793,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376354117598501e-05,
"loss": 3.7864,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375515522847449e-05,
"loss": 3.7926,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.9340226650238037,
"eval_runtime": 557.6516,
"eval_samples_per_second": 684.282,
"eval_steps_per_second": 21.384,
"step": 381595
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 2.4737298354123264e+17,
"trial_name": null,
"trial_params": null
}