abhinavp's picture
Training in progress, epoch 0, checkpoint
a3b2d5f verified
raw
history blame
130 kB
{
"best_metric": 3.864755153656006,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl/transformer/2/checkpoints/checkpoint-534233",
"epoch": 0.025000278439663435,
"eval_steps": 10,
"global_step": 534233,
"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": 10.9748,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8335,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1931,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9727,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8231,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7041,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6016,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5361,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4785,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4027,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3692,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3265,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2678,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 5.218,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 5.1917,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 5.1596,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1264,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0807,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0634,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0329,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0061,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9914,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9694,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.943,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9239,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.9086,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8847,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8743,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8388,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8435,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8097,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.8009,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.8019,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.7844,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7601,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7462,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7482,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.7292,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7189,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.7026,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6858,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6757,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964790485618428e-05,
"loss": 4.6629,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 4.6644,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6533,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6474,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6327,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.9605991497435414e-05,
"loss": 4.6294,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 4.6336,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.6089,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.6038,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.5928,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.6029,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5665,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.586,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5609,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.5566,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5588,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5506,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5343,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949702331620985e-05,
"loss": 4.5269,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 4.5172,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5281,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.5142,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.5029,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.5038,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4942,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4746,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4968,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.475,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4703,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4823,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.46,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388055134984274e-05,
"loss": 4.4737,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4683,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4587,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4621,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.436,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4327,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4363,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4363,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4316,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4156,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.406,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.4098,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928747290126923e-05,
"loss": 4.4097,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927908695375871e-05,
"loss": 4.4103,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927070100624819e-05,
"loss": 4.4131,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.4071,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3936,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3799,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3803,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.3867,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3824,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3645,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3697,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.37,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3722,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.3687,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3638,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.3654,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.3557,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914496093000158e-05,
"loss": 4.3526,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913657498249106e-05,
"loss": 4.3604,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912820541378427e-05,
"loss": 4.3435,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911981946627375e-05,
"loss": 4.3519,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3299,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3253,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3249,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3355,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.9077906107524886e-05,
"loss": 4.3297,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.9069520160014366e-05,
"loss": 4.3067,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.9061134212503846e-05,
"loss": 4.3096,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3205,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3266,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3129,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027606801265495e-05,
"loss": 4.3187,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.311,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.3126,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.3018,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.3001,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.2924,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.3002,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2838,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2938,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2868,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2966,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2701,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.2823,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2914,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2696,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890186672501889e-05,
"loss": 4.2881,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889348077750837e-05,
"loss": 4.2756,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888509482999785e-05,
"loss": 4.2764,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.2686,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886833931378054e-05,
"loss": 4.2626,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885995336627002e-05,
"loss": 4.2618,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.2698,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.8843197850052706e-05,
"loss": 4.2741,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.8834811902542186e-05,
"loss": 4.2628,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.8826425955031666e-05,
"loss": 4.2681,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.8818040007521146e-05,
"loss": 4.2596,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809654060010626e-05,
"loss": 4.2473,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801268112500106e-05,
"loss": 4.2546,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2431,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87845125962828e-05,
"loss": 4.2456,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877612664877228e-05,
"loss": 4.2451,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876774070126176e-05,
"loss": 4.2405,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875935475375124e-05,
"loss": 4.2369,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875096880624072e-05,
"loss": 4.2371,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.200362205505371,
"eval_runtime": 608.2164,
"eval_samples_per_second": 627.393,
"eval_steps_per_second": 19.607,
"step": 76319
},
{
"epoch": 0.0,
"learning_rate": 4.874259923753393e-05,
"loss": 4.2423,
"step": 76800
},
{
"epoch": 0.0,
"learning_rate": 4.873421329002341e-05,
"loss": 4.238,
"step": 77312
},
{
"epoch": 0.0,
"learning_rate": 4.872582734251289e-05,
"loss": 4.2301,
"step": 77824
},
{
"epoch": 0.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.2275,
"step": 78336
},
{
"epoch": 0.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.2279,
"step": 78848
},
{
"epoch": 0.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.2038,
"step": 79360
},
{
"epoch": 0.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.2201,
"step": 79872
},
{
"epoch": 0.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.219,
"step": 80384
},
{
"epoch": 0.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2098,
"step": 80896
},
{
"epoch": 0.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.2178,
"step": 81408
},
{
"epoch": 0.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.22,
"step": 81920
},
{
"epoch": 0.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2048,
"step": 82432
},
{
"epoch": 0.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.2033,
"step": 82944
},
{
"epoch": 0.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.2042,
"step": 83456
},
{
"epoch": 0.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.2046,
"step": 83968
},
{
"epoch": 0.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.1923,
"step": 84480
},
{
"epoch": 0.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.1931,
"step": 84992
},
{
"epoch": 0.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.196,
"step": 85504
},
{
"epoch": 0.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.1929,
"step": 86016
},
{
"epoch": 0.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.197,
"step": 86528
},
{
"epoch": 0.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.195,
"step": 87040
},
{
"epoch": 0.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.1953,
"step": 87552
},
{
"epoch": 0.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.1899,
"step": 88064
},
{
"epoch": 0.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.1902,
"step": 88576
},
{
"epoch": 0.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.1878,
"step": 89088
},
{
"epoch": 0.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.1821,
"step": 89600
},
{
"epoch": 0.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.1875,
"step": 90112
},
{
"epoch": 0.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.1686,
"step": 90624
},
{
"epoch": 0.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.1817,
"step": 91136
},
{
"epoch": 0.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.166,
"step": 91648
},
{
"epoch": 0.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.1705,
"step": 92160
},
{
"epoch": 0.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.1808,
"step": 92672
},
{
"epoch": 0.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1779,
"step": 93184
},
{
"epoch": 0.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.1653,
"step": 93696
},
{
"epoch": 0.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.1602,
"step": 94208
},
{
"epoch": 0.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.1722,
"step": 94720
},
{
"epoch": 0.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.165,
"step": 95232
},
{
"epoch": 0.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.1654,
"step": 95744
},
{
"epoch": 0.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.1591,
"step": 96256
},
{
"epoch": 0.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.1445,
"step": 96768
},
{
"epoch": 0.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.1454,
"step": 97280
},
{
"epoch": 0.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.1457,
"step": 97792
},
{
"epoch": 0.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.1544,
"step": 98304
},
{
"epoch": 0.01,
"learning_rate": 4.8382134525011416e-05,
"loss": 4.1438,
"step": 98816
},
{
"epoch": 0.01,
"learning_rate": 4.83737485775009e-05,
"loss": 4.1486,
"step": 99328
},
{
"epoch": 0.01,
"learning_rate": 4.836536262999038e-05,
"loss": 4.1451,
"step": 99840
},
{
"epoch": 0.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1474,
"step": 100352
},
{
"epoch": 0.01,
"learning_rate": 4.834860711377307e-05,
"loss": 4.1558,
"step": 100864
},
{
"epoch": 0.01,
"learning_rate": 4.834022116626255e-05,
"loss": 4.1358,
"step": 101376
},
{
"epoch": 0.01,
"learning_rate": 4.833183521875203e-05,
"loss": 4.1389,
"step": 101888
},
{
"epoch": 0.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.1301,
"step": 102400
},
{
"epoch": 0.01,
"learning_rate": 4.831507970253472e-05,
"loss": 4.1523,
"step": 102912
},
{
"epoch": 0.01,
"learning_rate": 4.83066937550242e-05,
"loss": 4.1226,
"step": 103424
},
{
"epoch": 0.01,
"learning_rate": 4.829830780751368e-05,
"loss": 4.1426,
"step": 103936
},
{
"epoch": 0.01,
"learning_rate": 4.828992186000316e-05,
"loss": 4.1235,
"step": 104448
},
{
"epoch": 0.01,
"learning_rate": 4.828153591249264e-05,
"loss": 4.1306,
"step": 104960
},
{
"epoch": 0.01,
"learning_rate": 4.8273166343785856e-05,
"loss": 4.1336,
"step": 105472
},
{
"epoch": 0.01,
"learning_rate": 4.8264780396275336e-05,
"loss": 4.1312,
"step": 105984
},
{
"epoch": 0.01,
"learning_rate": 4.8256394448764816e-05,
"loss": 4.1202,
"step": 106496
},
{
"epoch": 0.01,
"learning_rate": 4.8248008501254296e-05,
"loss": 4.1232,
"step": 107008
},
{
"epoch": 0.01,
"learning_rate": 4.8239638932547505e-05,
"loss": 4.1081,
"step": 107520
},
{
"epoch": 0.01,
"learning_rate": 4.8231252985036985e-05,
"loss": 4.1266,
"step": 108032
},
{
"epoch": 0.01,
"learning_rate": 4.8222867037526465e-05,
"loss": 4.1214,
"step": 108544
},
{
"epoch": 0.01,
"learning_rate": 4.8214481090015945e-05,
"loss": 4.1146,
"step": 109056
},
{
"epoch": 0.01,
"learning_rate": 4.8206111521309154e-05,
"loss": 4.1128,
"step": 109568
},
{
"epoch": 0.01,
"learning_rate": 4.8197725573798634e-05,
"loss": 4.1157,
"step": 110080
},
{
"epoch": 0.01,
"learning_rate": 4.8189339626288114e-05,
"loss": 4.0966,
"step": 110592
},
{
"epoch": 0.01,
"learning_rate": 4.8180953678777594e-05,
"loss": 4.1189,
"step": 111104
},
{
"epoch": 0.01,
"learning_rate": 4.817258411007081e-05,
"loss": 4.1041,
"step": 111616
},
{
"epoch": 0.01,
"learning_rate": 4.816419816256029e-05,
"loss": 4.108,
"step": 112128
},
{
"epoch": 0.01,
"learning_rate": 4.815581221504977e-05,
"loss": 4.1165,
"step": 112640
},
{
"epoch": 0.01,
"learning_rate": 4.814742626753924e-05,
"loss": 4.1026,
"step": 113152
},
{
"epoch": 0.01,
"learning_rate": 4.813905669883246e-05,
"loss": 4.1143,
"step": 113664
},
{
"epoch": 0.01,
"learning_rate": 4.813067075132194e-05,
"loss": 4.1194,
"step": 114176
},
{
"epoch": 0.01,
"learning_rate": 4.812228480381141e-05,
"loss": 4.1118,
"step": 114688
},
{
"epoch": 0.01,
"learning_rate": 4.811389885630089e-05,
"loss": 4.1143,
"step": 115200
},
{
"epoch": 0.01,
"learning_rate": 4.810552928759411e-05,
"loss": 4.0969,
"step": 115712
},
{
"epoch": 0.01,
"learning_rate": 4.809714334008359e-05,
"loss": 4.0922,
"step": 116224
},
{
"epoch": 0.01,
"learning_rate": 4.808875739257306e-05,
"loss": 4.1002,
"step": 116736
},
{
"epoch": 0.01,
"learning_rate": 4.808037144506255e-05,
"loss": 4.1069,
"step": 117248
},
{
"epoch": 0.01,
"learning_rate": 4.807200187635576e-05,
"loss": 4.1005,
"step": 117760
},
{
"epoch": 0.01,
"learning_rate": 4.8063615928845243e-05,
"loss": 4.0915,
"step": 118272
},
{
"epoch": 0.01,
"learning_rate": 4.8055229981334717e-05,
"loss": 4.0801,
"step": 118784
},
{
"epoch": 0.01,
"learning_rate": 4.8046844033824197e-05,
"loss": 4.0844,
"step": 119296
},
{
"epoch": 0.01,
"learning_rate": 4.803847446511741e-05,
"loss": 4.0877,
"step": 119808
},
{
"epoch": 0.01,
"learning_rate": 4.8030088517606886e-05,
"loss": 4.0906,
"step": 120320
},
{
"epoch": 0.01,
"learning_rate": 4.8021702570096366e-05,
"loss": 4.1005,
"step": 120832
},
{
"epoch": 0.01,
"learning_rate": 4.8013316622585846e-05,
"loss": 4.0974,
"step": 121344
},
{
"epoch": 0.01,
"learning_rate": 4.800494705387906e-05,
"loss": 4.0852,
"step": 121856
},
{
"epoch": 0.02,
"learning_rate": 4.799657748517227e-05,
"loss": 4.0801,
"step": 122368
},
{
"epoch": 0.02,
"learning_rate": 4.798819153766175e-05,
"loss": 4.0757,
"step": 122880
},
{
"epoch": 0.02,
"learning_rate": 4.797980559015123e-05,
"loss": 4.083,
"step": 123392
},
{
"epoch": 0.02,
"learning_rate": 4.797141964264071e-05,
"loss": 4.0825,
"step": 123904
},
{
"epoch": 0.02,
"learning_rate": 4.796303369513019e-05,
"loss": 4.0777,
"step": 124416
},
{
"epoch": 0.02,
"learning_rate": 4.795464774761967e-05,
"loss": 4.074,
"step": 124928
},
{
"epoch": 0.02,
"learning_rate": 4.7946278178912886e-05,
"loss": 4.0807,
"step": 125440
},
{
"epoch": 0.02,
"learning_rate": 4.793789223140236e-05,
"loss": 4.0849,
"step": 125952
},
{
"epoch": 0.02,
"learning_rate": 4.792950628389184e-05,
"loss": 4.0799,
"step": 126464
},
{
"epoch": 0.02,
"learning_rate": 4.792112033638132e-05,
"loss": 4.08,
"step": 126976
},
{
"epoch": 0.02,
"learning_rate": 4.79127343888708e-05,
"loss": 4.0852,
"step": 127488
},
{
"epoch": 0.02,
"learning_rate": 4.790434844136028e-05,
"loss": 4.0754,
"step": 128000
},
{
"epoch": 0.02,
"learning_rate": 4.789596249384976e-05,
"loss": 4.0736,
"step": 128512
},
{
"epoch": 0.02,
"learning_rate": 4.788759292514297e-05,
"loss": 4.088,
"step": 129024
},
{
"epoch": 0.02,
"learning_rate": 4.7879223356436184e-05,
"loss": 4.0704,
"step": 129536
},
{
"epoch": 0.02,
"learning_rate": 4.7870837408925664e-05,
"loss": 4.0828,
"step": 130048
},
{
"epoch": 0.02,
"learning_rate": 4.7862451461415144e-05,
"loss": 4.0661,
"step": 130560
},
{
"epoch": 0.02,
"learning_rate": 4.7854065513904624e-05,
"loss": 4.0564,
"step": 131072
},
{
"epoch": 0.02,
"learning_rate": 4.7845679566394104e-05,
"loss": 4.0651,
"step": 131584
},
{
"epoch": 0.02,
"learning_rate": 4.7837293618883584e-05,
"loss": 4.072,
"step": 132096
},
{
"epoch": 0.02,
"learning_rate": 4.782892405017679e-05,
"loss": 4.0652,
"step": 132608
},
{
"epoch": 0.02,
"learning_rate": 4.782053810266627e-05,
"loss": 4.0527,
"step": 133120
},
{
"epoch": 0.02,
"learning_rate": 4.781215215515575e-05,
"loss": 4.0499,
"step": 133632
},
{
"epoch": 0.02,
"learning_rate": 4.780376620764523e-05,
"loss": 4.0634,
"step": 134144
},
{
"epoch": 0.02,
"learning_rate": 4.779538026013471e-05,
"loss": 4.0729,
"step": 134656
},
{
"epoch": 0.02,
"learning_rate": 4.778699431262419e-05,
"loss": 4.0601,
"step": 135168
},
{
"epoch": 0.02,
"learning_rate": 4.77786247439174e-05,
"loss": 4.0732,
"step": 135680
},
{
"epoch": 0.02,
"learning_rate": 4.777023879640689e-05,
"loss": 4.0602,
"step": 136192
},
{
"epoch": 0.02,
"learning_rate": 4.776185284889637e-05,
"loss": 4.062,
"step": 136704
},
{
"epoch": 0.02,
"learning_rate": 4.775346690138585e-05,
"loss": 4.0607,
"step": 137216
},
{
"epoch": 0.02,
"learning_rate": 4.774508095387533e-05,
"loss": 4.0542,
"step": 137728
},
{
"epoch": 0.02,
"learning_rate": 4.773671138516854e-05,
"loss": 4.0475,
"step": 138240
},
{
"epoch": 0.02,
"learning_rate": 4.772832543765802e-05,
"loss": 4.0611,
"step": 138752
},
{
"epoch": 0.02,
"learning_rate": 4.77199394901475e-05,
"loss": 4.0477,
"step": 139264
},
{
"epoch": 0.02,
"learning_rate": 4.771155354263698e-05,
"loss": 4.0496,
"step": 139776
},
{
"epoch": 0.02,
"learning_rate": 4.770316759512646e-05,
"loss": 4.0524,
"step": 140288
},
{
"epoch": 0.02,
"learning_rate": 4.769478164761594e-05,
"loss": 4.0615,
"step": 140800
},
{
"epoch": 0.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.0392,
"step": 141312
},
{
"epoch": 0.02,
"learning_rate": 4.7678026131398626e-05,
"loss": 4.0441,
"step": 141824
},
{
"epoch": 0.02,
"learning_rate": 4.7669640183888106e-05,
"loss": 4.0641,
"step": 142336
},
{
"epoch": 0.02,
"learning_rate": 4.7661254236377586e-05,
"loss": 4.0422,
"step": 142848
},
{
"epoch": 0.02,
"learning_rate": 4.765286828886707e-05,
"loss": 4.062,
"step": 143360
},
{
"epoch": 0.02,
"learning_rate": 4.764448234135655e-05,
"loss": 4.0452,
"step": 143872
},
{
"epoch": 0.02,
"learning_rate": 4.7636096393846026e-05,
"loss": 4.0542,
"step": 144384
},
{
"epoch": 0.02,
"learning_rate": 4.7627710446335506e-05,
"loss": 4.042,
"step": 144896
},
{
"epoch": 0.02,
"learning_rate": 4.7619324498824986e-05,
"loss": 4.0371,
"step": 145408
},
{
"epoch": 0.02,
"learning_rate": 4.7610954930118195e-05,
"loss": 4.0418,
"step": 145920
},
{
"epoch": 0.02,
"learning_rate": 4.7602568982607675e-05,
"loss": 4.0476,
"step": 146432
},
{
"epoch": 0.02,
"learning_rate": 4.7594183035097155e-05,
"loss": 4.0581,
"step": 146944
},
{
"epoch": 0.02,
"learning_rate": 4.7585797087586635e-05,
"loss": 4.0495,
"step": 147456
},
{
"epoch": 0.02,
"learning_rate": 4.7577427518879844e-05,
"loss": 4.0492,
"step": 147968
},
{
"epoch": 0.02,
"learning_rate": 4.7569041571369324e-05,
"loss": 4.0435,
"step": 148480
},
{
"epoch": 0.02,
"learning_rate": 4.756065562385881e-05,
"loss": 4.0301,
"step": 148992
},
{
"epoch": 0.02,
"learning_rate": 4.755226967634829e-05,
"loss": 4.0441,
"step": 149504
},
{
"epoch": 0.02,
"learning_rate": 4.75439001076415e-05,
"loss": 4.0312,
"step": 150016
},
{
"epoch": 0.02,
"learning_rate": 4.753551416013098e-05,
"loss": 4.0346,
"step": 150528
},
{
"epoch": 0.02,
"learning_rate": 4.752712821262046e-05,
"loss": 4.0387,
"step": 151040
},
{
"epoch": 0.02,
"learning_rate": 4.751874226510994e-05,
"loss": 4.0264,
"step": 151552
},
{
"epoch": 0.02,
"learning_rate": 4.751035631759942e-05,
"loss": 4.0335,
"step": 152064
},
{
"epoch": 0.02,
"learning_rate": 4.75019703700889e-05,
"loss": 4.0294,
"step": 152576
},
{
"epoch": 0.03,
"eval_loss": 4.031442642211914,
"eval_runtime": 575.8524,
"eval_samples_per_second": 662.654,
"eval_steps_per_second": 20.708,
"step": 152638
},
{
"epoch": 0.0,
"learning_rate": 4.749360080138211e-05,
"loss": 4.0398,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748521485387159e-05,
"loss": 4.0362,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747682890636107e-05,
"loss": 4.03,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746844295885055e-05,
"loss": 4.0269,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.746005701134003e-05,
"loss": 4.0301,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745167106382951e-05,
"loss": 4.0118,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744328511631899e-05,
"loss": 4.0276,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434899168808475e-05,
"loss": 4.0213,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426529600101684e-05,
"loss": 4.0126,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418143652591164e-05,
"loss": 4.0265,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409757705080644e-05,
"loss": 4.0314,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401371757570124e-05,
"loss": 4.0126,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739300218886333e-05,
"loss": 4.0112,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738461624135281e-05,
"loss": 4.0155,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737623029384229e-05,
"loss": 4.0168,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736784434633177e-05,
"loss": 4.008,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735945839882125e-05,
"loss": 4.0077,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735107245131073e-05,
"loss": 4.0094,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734270288260394e-05,
"loss": 4.0119,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733431693509343e-05,
"loss": 4.0168,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732593098758291e-05,
"loss": 4.0117,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731754504007238e-05,
"loss": 4.0176,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73091754713656e-05,
"loss": 4.0135,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730078952385508e-05,
"loss": 4.0085,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729240357634456e-05,
"loss": 4.0116,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728401762883403e-05,
"loss": 4.0082,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727563168132351e-05,
"loss": 4.013,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726724573381299e-05,
"loss": 3.996,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725887616510621e-05,
"loss": 4.0076,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725049021759568e-05,
"loss": 3.9948,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724210427008517e-05,
"loss": 3.9992,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233718322574647e-05,
"loss": 4.0122,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225348753867856e-05,
"loss": 4.0069,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216962806357336e-05,
"loss": 3.9986,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208576858846816e-05,
"loss": 3.9928,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200190911336296e-05,
"loss": 4.0095,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191821342629505e-05,
"loss": 3.9936,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183435395118985e-05,
"loss": 3.9999,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175049447608465e-05,
"loss": 3.9953,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166663500097945e-05,
"loss": 3.9797,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158277552587424e-05,
"loss": 3.9833,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149907983880634e-05,
"loss": 3.9812,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714152203637012e-05,
"loss": 3.9985,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71331360888596e-05,
"loss": 3.9863,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712475014134908e-05,
"loss": 3.9881,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711636419383856e-05,
"loss": 3.9854,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710799462513177e-05,
"loss": 3.9856,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709960867762125e-05,
"loss": 4.0006,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709122273011073e-05,
"loss": 3.9796,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708283678260021e-05,
"loss": 3.9789,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707446721389342e-05,
"loss": 3.9779,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.70660812663829e-05,
"loss": 3.9984,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705769531887238e-05,
"loss": 3.9708,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704930937136186e-05,
"loss": 3.9898,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040939802655074e-05,
"loss": 3.9693,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032553855144554e-05,
"loss": 3.9821,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024167907634034e-05,
"loss": 3.9853,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015781960123514e-05,
"loss": 3.973,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700741239141672e-05,
"loss": 3.9799,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.69990264439062e-05,
"loss": 3.9751,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699064049639568e-05,
"loss": 3.9561,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698225454888516e-05,
"loss": 3.9771,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697388498017837e-05,
"loss": 3.9765,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696549903266785e-05,
"loss": 3.9693,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695711308515733e-05,
"loss": 3.9662,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694872713764681e-05,
"loss": 3.9721,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694034119013629e-05,
"loss": 3.9545,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693197162142951e-05,
"loss": 3.9762,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692358567391899e-05,
"loss": 3.9576,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691519972640847e-05,
"loss": 3.9659,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690681377889795e-05,
"loss": 3.9738,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898444210191157e-05,
"loss": 3.9634,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890058262680636e-05,
"loss": 3.9733,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881672315170116e-05,
"loss": 3.9838,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873286367659596e-05,
"loss": 3.9699,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864916798952806e-05,
"loss": 3.9782,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856530851442285e-05,
"loss": 3.9602,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848144903931765e-05,
"loss": 3.9518,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839758956421245e-05,
"loss": 3.9608,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683138938771446e-05,
"loss": 3.9745,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682300344020394e-05,
"loss": 3.964,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681461749269342e-05,
"loss": 3.9541,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.68062315451829e-05,
"loss": 3.9491,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679786197647611e-05,
"loss": 3.9516,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678947602896559e-05,
"loss": 3.9493,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678109008145507e-05,
"loss": 3.958,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677270413394455e-05,
"loss": 3.9665,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676433456523776e-05,
"loss": 3.9645,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675594861772724e-05,
"loss": 3.9548,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674756267021672e-05,
"loss": 3.9509,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.67391767227062e-05,
"loss": 3.9458,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730807153999415e-05,
"loss": 3.9533,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722421206488895e-05,
"loss": 3.9496,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6714035258978375e-05,
"loss": 3.9521,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705649311467855e-05,
"loss": 3.9451,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697279742761064e-05,
"loss": 3.9548,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688893795250544e-05,
"loss": 3.9552,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680507847740024e-05,
"loss": 3.9563,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6672121900229504e-05,
"loss": 3.9547,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666375233152271e-05,
"loss": 3.9583,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665536638401219e-05,
"loss": 3.9521,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664698043650167e-05,
"loss": 3.9466,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663859448899115e-05,
"loss": 3.9645,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663022492028437e-05,
"loss": 3.9411,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662183897277385e-05,
"loss": 3.9634,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661345302526333e-05,
"loss": 3.9396,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660506707775281e-05,
"loss": 3.935,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659669750904602e-05,
"loss": 3.9424,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.65883115615355e-05,
"loss": 3.9519,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657992561402498e-05,
"loss": 3.9455,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657153966651446e-05,
"loss": 3.9324,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6563170097807667e-05,
"loss": 3.9317,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554784150297146e-05,
"loss": 3.9399,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546398202786626e-05,
"loss": 3.9539,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6538012255276106e-05,
"loss": 3.9392,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652964268656932e-05,
"loss": 3.9534,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.65212567390588e-05,
"loss": 3.9419,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651287079154828e-05,
"loss": 3.9429,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650448484403776e-05,
"loss": 3.9464,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649611527533097e-05,
"loss": 3.9335,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648772932782045e-05,
"loss": 3.9335,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647934338030993e-05,
"loss": 3.9399,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470957432799404e-05,
"loss": 3.9299,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646258786409262e-05,
"loss": 3.9364,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.64542019165821e-05,
"loss": 3.9368,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644581596907158e-05,
"loss": 3.9435,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643743002156106e-05,
"loss": 3.9267,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429060452854276e-05,
"loss": 3.9256,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420674505343756e-05,
"loss": 3.9516,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412288557833236e-05,
"loss": 3.9291,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640390261032271e-05,
"loss": 3.943,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395533041615925e-05,
"loss": 3.9359,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387147094105405e-05,
"loss": 3.9389,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637876114659488e-05,
"loss": 3.9306,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637037519908436e-05,
"loss": 3.9284,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6362005630377574e-05,
"loss": 3.9334,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353619682867054e-05,
"loss": 3.9332,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634523373535653e-05,
"loss": 3.9462,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336847787846014e-05,
"loss": 3.9401,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632847821913923e-05,
"loss": 3.9384,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632009227162871e-05,
"loss": 3.9318,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631170632411818e-05,
"loss": 3.9229,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630332037660766e-05,
"loss": 3.9331,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629495080790088e-05,
"loss": 3.9243,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628656486039035e-05,
"loss": 3.9271,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627817891287983e-05,
"loss": 3.9279,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626979296536931e-05,
"loss": 3.9191,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626142339666253e-05,
"loss": 3.9267,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.6253037449152e-05,
"loss": 3.9211,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9574191570281982,
"eval_runtime": 569.6837,
"eval_samples_per_second": 669.83,
"eval_steps_per_second": 20.933,
"step": 228957
},
{
"epoch": 0.0,
"learning_rate": 4.624465150164148e-05,
"loss": 3.9284,
"step": 229376
},
{
"epoch": 0.0,
"learning_rate": 4.623626555413097e-05,
"loss": 3.9338,
"step": 229888
},
{
"epoch": 0.0,
"learning_rate": 4.622787960662045e-05,
"loss": 3.922,
"step": 230400
},
{
"epoch": 0.0,
"learning_rate": 4.621949365910993e-05,
"loss": 3.9224,
"step": 230912
},
{
"epoch": 0.0,
"learning_rate": 4.621110771159941e-05,
"loss": 3.9264,
"step": 231424
},
{
"epoch": 0.0,
"learning_rate": 4.620272176408889e-05,
"loss": 3.9065,
"step": 231936
},
{
"epoch": 0.0,
"learning_rate": 4.619433581657837e-05,
"loss": 3.9218,
"step": 232448
},
{
"epoch": 0.0,
"learning_rate": 4.618594986906785e-05,
"loss": 3.9193,
"step": 232960
},
{
"epoch": 0.0,
"learning_rate": 4.6177580300361056e-05,
"loss": 3.9113,
"step": 233472
},
{
"epoch": 0.0,
"learning_rate": 4.6169194352850536e-05,
"loss": 3.9205,
"step": 233984
},
{
"epoch": 0.0,
"learning_rate": 4.6160808405340016e-05,
"loss": 3.9275,
"step": 234496
},
{
"epoch": 0.0,
"learning_rate": 4.6152438836633225e-05,
"loss": 3.9077,
"step": 235008
},
{
"epoch": 0.0,
"learning_rate": 4.6144052889122705e-05,
"loss": 3.9105,
"step": 235520
},
{
"epoch": 0.0,
"learning_rate": 4.6135666941612185e-05,
"loss": 3.9152,
"step": 236032
},
{
"epoch": 0.0,
"learning_rate": 4.6127280994101665e-05,
"loss": 3.9149,
"step": 236544
},
{
"epoch": 0.0,
"learning_rate": 4.611891142539488e-05,
"loss": 3.9048,
"step": 237056
},
{
"epoch": 0.0,
"learning_rate": 4.611052547788436e-05,
"loss": 3.9052,
"step": 237568
},
{
"epoch": 0.0,
"learning_rate": 4.610213953037384e-05,
"loss": 3.907,
"step": 238080
},
{
"epoch": 0.0,
"learning_rate": 4.609375358286332e-05,
"loss": 3.9106,
"step": 238592
},
{
"epoch": 0.0,
"learning_rate": 4.608538401415653e-05,
"loss": 3.9176,
"step": 239104
},
{
"epoch": 0.0,
"learning_rate": 4.607699806664601e-05,
"loss": 3.9081,
"step": 239616
},
{
"epoch": 0.0,
"learning_rate": 4.606861211913549e-05,
"loss": 3.9199,
"step": 240128
},
{
"epoch": 0.0,
"learning_rate": 4.606022617162497e-05,
"loss": 3.9148,
"step": 240640
},
{
"epoch": 0.0,
"learning_rate": 4.605185660291818e-05,
"loss": 3.9109,
"step": 241152
},
{
"epoch": 0.0,
"learning_rate": 4.604347065540766e-05,
"loss": 3.9086,
"step": 241664
},
{
"epoch": 0.0,
"learning_rate": 4.603508470789714e-05,
"loss": 3.9067,
"step": 242176
},
{
"epoch": 0.0,
"learning_rate": 4.602669876038662e-05,
"loss": 3.9156,
"step": 242688
},
{
"epoch": 0.0,
"learning_rate": 4.6018329191679835e-05,
"loss": 3.9026,
"step": 243200
},
{
"epoch": 0.0,
"learning_rate": 4.6009959622973044e-05,
"loss": 3.9102,
"step": 243712
},
{
"epoch": 0.01,
"learning_rate": 4.6001573675462524e-05,
"loss": 3.8984,
"step": 244224
},
{
"epoch": 0.01,
"learning_rate": 4.5993187727952004e-05,
"loss": 3.9013,
"step": 244736
},
{
"epoch": 0.01,
"learning_rate": 4.5984801780441484e-05,
"loss": 3.915,
"step": 245248
},
{
"epoch": 0.01,
"learning_rate": 4.5976415832930964e-05,
"loss": 3.9101,
"step": 245760
},
{
"epoch": 0.01,
"learning_rate": 4.5968029885420443e-05,
"loss": 3.9047,
"step": 246272
},
{
"epoch": 0.01,
"learning_rate": 4.5959643937909923e-05,
"loss": 3.8996,
"step": 246784
},
{
"epoch": 0.01,
"learning_rate": 4.5951257990399403e-05,
"loss": 3.9091,
"step": 247296
},
{
"epoch": 0.01,
"learning_rate": 4.594288842169261e-05,
"loss": 3.8991,
"step": 247808
},
{
"epoch": 0.01,
"learning_rate": 4.593450247418209e-05,
"loss": 3.9079,
"step": 248320
},
{
"epoch": 0.01,
"learning_rate": 4.592611652667157e-05,
"loss": 3.8997,
"step": 248832
},
{
"epoch": 0.01,
"learning_rate": 4.591773057916105e-05,
"loss": 3.8856,
"step": 249344
},
{
"epoch": 0.01,
"learning_rate": 4.590936101045427e-05,
"loss": 3.8923,
"step": 249856
},
{
"epoch": 0.01,
"learning_rate": 4.590097506294375e-05,
"loss": 3.8897,
"step": 250368
},
{
"epoch": 0.01,
"learning_rate": 4.589258911543323e-05,
"loss": 3.9022,
"step": 250880
},
{
"epoch": 0.01,
"learning_rate": 4.588420316792271e-05,
"loss": 3.8926,
"step": 251392
},
{
"epoch": 0.01,
"learning_rate": 4.587583359921592e-05,
"loss": 3.895,
"step": 251904
},
{
"epoch": 0.01,
"learning_rate": 4.58674476517054e-05,
"loss": 3.8925,
"step": 252416
},
{
"epoch": 0.01,
"learning_rate": 4.585906170419488e-05,
"loss": 3.8964,
"step": 252928
},
{
"epoch": 0.01,
"learning_rate": 4.585067575668436e-05,
"loss": 3.9082,
"step": 253440
},
{
"epoch": 0.01,
"learning_rate": 4.5842306187977566e-05,
"loss": 3.8873,
"step": 253952
},
{
"epoch": 0.01,
"learning_rate": 4.5833920240467046e-05,
"loss": 3.887,
"step": 254464
},
{
"epoch": 0.01,
"learning_rate": 4.5825534292956526e-05,
"loss": 3.8925,
"step": 254976
},
{
"epoch": 0.01,
"learning_rate": 4.581716472424974e-05,
"loss": 3.9032,
"step": 255488
},
{
"epoch": 0.01,
"learning_rate": 4.580877877673922e-05,
"loss": 3.8826,
"step": 256000
},
{
"epoch": 0.01,
"learning_rate": 4.58003928292287e-05,
"loss": 3.8962,
"step": 256512
},
{
"epoch": 0.01,
"learning_rate": 4.579200688171818e-05,
"loss": 3.8796,
"step": 257024
},
{
"epoch": 0.01,
"learning_rate": 4.578362093420766e-05,
"loss": 3.8867,
"step": 257536
},
{
"epoch": 0.01,
"learning_rate": 4.5775234986697135e-05,
"loss": 3.8978,
"step": 258048
},
{
"epoch": 0.01,
"learning_rate": 4.5766849039186615e-05,
"loss": 3.8797,
"step": 258560
},
{
"epoch": 0.01,
"learning_rate": 4.5758463091676095e-05,
"loss": 3.8978,
"step": 259072
},
{
"epoch": 0.01,
"learning_rate": 4.575009352296931e-05,
"loss": 3.889,
"step": 259584
},
{
"epoch": 0.01,
"learning_rate": 4.5741707575458784e-05,
"loss": 3.868,
"step": 260096
},
{
"epoch": 0.01,
"learning_rate": 4.5733321627948264e-05,
"loss": 3.8844,
"step": 260608
},
{
"epoch": 0.01,
"learning_rate": 4.5724935680437744e-05,
"loss": 3.8869,
"step": 261120
},
{
"epoch": 0.01,
"learning_rate": 4.571656611173096e-05,
"loss": 3.885,
"step": 261632
},
{
"epoch": 0.01,
"learning_rate": 4.570818016422044e-05,
"loss": 3.8784,
"step": 262144
},
{
"epoch": 0.01,
"learning_rate": 4.569979421670992e-05,
"loss": 3.8841,
"step": 262656
},
{
"epoch": 0.01,
"learning_rate": 4.56914082691994e-05,
"loss": 3.868,
"step": 263168
},
{
"epoch": 0.01,
"learning_rate": 4.568303870049261e-05,
"loss": 3.8894,
"step": 263680
},
{
"epoch": 0.01,
"learning_rate": 4.567465275298209e-05,
"loss": 3.8704,
"step": 264192
},
{
"epoch": 0.01,
"learning_rate": 4.566626680547157e-05,
"loss": 3.8804,
"step": 264704
},
{
"epoch": 0.01,
"learning_rate": 4.565788085796105e-05,
"loss": 3.8867,
"step": 265216
},
{
"epoch": 0.01,
"learning_rate": 4.564951128925426e-05,
"loss": 3.8786,
"step": 265728
},
{
"epoch": 0.01,
"learning_rate": 4.564112534174374e-05,
"loss": 3.8857,
"step": 266240
},
{
"epoch": 0.01,
"learning_rate": 4.563273939423322e-05,
"loss": 3.8933,
"step": 266752
},
{
"epoch": 0.01,
"learning_rate": 4.56243534467227e-05,
"loss": 3.887,
"step": 267264
},
{
"epoch": 0.01,
"learning_rate": 4.561598387801591e-05,
"loss": 3.8934,
"step": 267776
},
{
"epoch": 0.01,
"learning_rate": 4.560759793050539e-05,
"loss": 3.874,
"step": 268288
},
{
"epoch": 0.01,
"learning_rate": 4.559921198299487e-05,
"loss": 3.8699,
"step": 268800
},
{
"epoch": 0.01,
"learning_rate": 4.559082603548435e-05,
"loss": 3.873,
"step": 269312
},
{
"epoch": 0.01,
"learning_rate": 4.558245646677756e-05,
"loss": 3.8929,
"step": 269824
},
{
"epoch": 0.01,
"learning_rate": 4.557407051926704e-05,
"loss": 3.88,
"step": 270336
},
{
"epoch": 0.01,
"learning_rate": 4.556568457175652e-05,
"loss": 3.8679,
"step": 270848
},
{
"epoch": 0.01,
"learning_rate": 4.5557298624246e-05,
"loss": 3.8639,
"step": 271360
},
{
"epoch": 0.01,
"learning_rate": 4.554892905553921e-05,
"loss": 3.8711,
"step": 271872
},
{
"epoch": 0.01,
"learning_rate": 4.554054310802869e-05,
"loss": 3.868,
"step": 272384
},
{
"epoch": 0.01,
"learning_rate": 4.553215716051817e-05,
"loss": 3.8708,
"step": 272896
},
{
"epoch": 0.01,
"learning_rate": 4.552377121300765e-05,
"loss": 3.8805,
"step": 273408
},
{
"epoch": 0.01,
"learning_rate": 4.551540164430087e-05,
"loss": 3.8843,
"step": 273920
},
{
"epoch": 0.01,
"learning_rate": 4.550701569679035e-05,
"loss": 3.8711,
"step": 274432
},
{
"epoch": 0.02,
"learning_rate": 4.549862974927983e-05,
"loss": 3.8728,
"step": 274944
},
{
"epoch": 0.02,
"learning_rate": 4.549024380176931e-05,
"loss": 3.8612,
"step": 275456
},
{
"epoch": 0.02,
"learning_rate": 4.5481874233062516e-05,
"loss": 3.8703,
"step": 275968
},
{
"epoch": 0.02,
"learning_rate": 4.5473488285551996e-05,
"loss": 3.873,
"step": 276480
},
{
"epoch": 0.02,
"learning_rate": 4.5465102338041476e-05,
"loss": 3.8703,
"step": 276992
},
{
"epoch": 0.02,
"learning_rate": 4.5456716390530956e-05,
"loss": 3.8634,
"step": 277504
},
{
"epoch": 0.02,
"learning_rate": 4.5448346821824165e-05,
"loss": 3.8758,
"step": 278016
},
{
"epoch": 0.02,
"learning_rate": 4.5439960874313645e-05,
"loss": 3.8703,
"step": 278528
},
{
"epoch": 0.02,
"learning_rate": 4.5431574926803125e-05,
"loss": 3.8829,
"step": 279040
},
{
"epoch": 0.02,
"learning_rate": 4.5423188979292605e-05,
"loss": 3.8718,
"step": 279552
},
{
"epoch": 0.02,
"learning_rate": 4.541481941058582e-05,
"loss": 3.878,
"step": 280064
},
{
"epoch": 0.02,
"learning_rate": 4.54064334630753e-05,
"loss": 3.8718,
"step": 280576
},
{
"epoch": 0.02,
"learning_rate": 4.539804751556478e-05,
"loss": 3.8667,
"step": 281088
},
{
"epoch": 0.02,
"learning_rate": 4.538966156805426e-05,
"loss": 3.8837,
"step": 281600
},
{
"epoch": 0.02,
"learning_rate": 4.538129199934747e-05,
"loss": 3.8636,
"step": 282112
},
{
"epoch": 0.02,
"learning_rate": 4.537290605183695e-05,
"loss": 3.8852,
"step": 282624
},
{
"epoch": 0.02,
"learning_rate": 4.536452010432643e-05,
"loss": 3.8589,
"step": 283136
},
{
"epoch": 0.02,
"learning_rate": 4.535613415681591e-05,
"loss": 3.8591,
"step": 283648
},
{
"epoch": 0.02,
"learning_rate": 4.534776458810912e-05,
"loss": 3.8619,
"step": 284160
},
{
"epoch": 0.02,
"learning_rate": 4.53393786405986e-05,
"loss": 3.8756,
"step": 284672
},
{
"epoch": 0.02,
"learning_rate": 4.5331009071891814e-05,
"loss": 3.8666,
"step": 285184
},
{
"epoch": 0.02,
"learning_rate": 4.5322623124381294e-05,
"loss": 3.8518,
"step": 285696
},
{
"epoch": 0.02,
"learning_rate": 4.5314237176870774e-05,
"loss": 3.8502,
"step": 286208
},
{
"epoch": 0.02,
"learning_rate": 4.5305851229360254e-05,
"loss": 3.8613,
"step": 286720
},
{
"epoch": 0.02,
"learning_rate": 4.5297465281849734e-05,
"loss": 3.8788,
"step": 287232
},
{
"epoch": 0.02,
"learning_rate": 4.5289079334339214e-05,
"loss": 3.8619,
"step": 287744
},
{
"epoch": 0.02,
"learning_rate": 4.5280693386828694e-05,
"loss": 3.8774,
"step": 288256
},
{
"epoch": 0.02,
"learning_rate": 4.5272307439318174e-05,
"loss": 3.8641,
"step": 288768
},
{
"epoch": 0.02,
"learning_rate": 4.526393787061138e-05,
"loss": 3.8675,
"step": 289280
},
{
"epoch": 0.02,
"learning_rate": 4.525555192310086e-05,
"loss": 3.867,
"step": 289792
},
{
"epoch": 0.02,
"learning_rate": 4.524716597559034e-05,
"loss": 3.8578,
"step": 290304
},
{
"epoch": 0.02,
"learning_rate": 4.523879640688355e-05,
"loss": 3.8562,
"step": 290816
},
{
"epoch": 0.02,
"learning_rate": 4.523041045937303e-05,
"loss": 3.861,
"step": 291328
},
{
"epoch": 0.02,
"learning_rate": 4.522202451186251e-05,
"loss": 3.8554,
"step": 291840
},
{
"epoch": 0.02,
"learning_rate": 4.5213638564352e-05,
"loss": 3.859,
"step": 292352
},
{
"epoch": 0.02,
"learning_rate": 4.520525261684148e-05,
"loss": 3.8629,
"step": 292864
},
{
"epoch": 0.02,
"learning_rate": 4.519686666933096e-05,
"loss": 3.8624,
"step": 293376
},
{
"epoch": 0.02,
"learning_rate": 4.518848072182044e-05,
"loss": 3.8527,
"step": 293888
},
{
"epoch": 0.02,
"learning_rate": 4.518011115311365e-05,
"loss": 3.8511,
"step": 294400
},
{
"epoch": 0.02,
"learning_rate": 4.517172520560313e-05,
"loss": 3.8732,
"step": 294912
},
{
"epoch": 0.02,
"learning_rate": 4.516333925809261e-05,
"loss": 3.8536,
"step": 295424
},
{
"epoch": 0.02,
"learning_rate": 4.515495331058209e-05,
"loss": 3.8677,
"step": 295936
},
{
"epoch": 0.02,
"learning_rate": 4.514656736307156e-05,
"loss": 3.8605,
"step": 296448
},
{
"epoch": 0.02,
"learning_rate": 4.513818141556104e-05,
"loss": 3.863,
"step": 296960
},
{
"epoch": 0.02,
"learning_rate": 4.512979546805052e-05,
"loss": 3.8543,
"step": 297472
},
{
"epoch": 0.02,
"learning_rate": 4.512140952054e-05,
"loss": 3.8583,
"step": 297984
},
{
"epoch": 0.02,
"learning_rate": 4.511303995183322e-05,
"loss": 3.8575,
"step": 298496
},
{
"epoch": 0.02,
"learning_rate": 4.5104654004322697e-05,
"loss": 3.8614,
"step": 299008
},
{
"epoch": 0.02,
"learning_rate": 4.5096268056812177e-05,
"loss": 3.8746,
"step": 299520
},
{
"epoch": 0.02,
"learning_rate": 4.5087882109301657e-05,
"loss": 3.8609,
"step": 300032
},
{
"epoch": 0.02,
"learning_rate": 4.5079512540594866e-05,
"loss": 3.8671,
"step": 300544
},
{
"epoch": 0.02,
"learning_rate": 4.5071126593084346e-05,
"loss": 3.8634,
"step": 301056
},
{
"epoch": 0.02,
"learning_rate": 4.5062740645573826e-05,
"loss": 3.8491,
"step": 301568
},
{
"epoch": 0.02,
"learning_rate": 4.5054354698063305e-05,
"loss": 3.8581,
"step": 302080
},
{
"epoch": 0.02,
"learning_rate": 4.5045968750552785e-05,
"loss": 3.8502,
"step": 302592
},
{
"epoch": 0.02,
"learning_rate": 4.5037582803042265e-05,
"loss": 3.8533,
"step": 303104
},
{
"epoch": 0.02,
"learning_rate": 4.5029196855531745e-05,
"loss": 3.8538,
"step": 303616
},
{
"epoch": 0.02,
"learning_rate": 4.5020827286824954e-05,
"loss": 3.8508,
"step": 304128
},
{
"epoch": 0.02,
"learning_rate": 4.5012441339314434e-05,
"loss": 3.8488,
"step": 304640
},
{
"epoch": 0.02,
"learning_rate": 4.5004055391803914e-05,
"loss": 3.8523,
"step": 305152
},
{
"epoch": 0.03,
"eval_loss": 3.9163527488708496,
"eval_runtime": 553.4248,
"eval_samples_per_second": 689.508,
"eval_steps_per_second": 21.548,
"step": 305276
},
{
"epoch": 0.0,
"learning_rate": 4.499568582309713e-05,
"loss": 3.8584,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498729987558661e-05,
"loss": 3.8584,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497891392807609e-05,
"loss": 3.853,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497052798056557e-05,
"loss": 3.8496,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496214203305505e-05,
"loss": 3.8596,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495375608554453e-05,
"loss": 3.8357,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494538651683774e-05,
"loss": 3.8525,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493700056932722e-05,
"loss": 3.844,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.49286146218167e-05,
"loss": 3.8429,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.492022867430618e-05,
"loss": 3.8501,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491184272679566e-05,
"loss": 3.8533,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490345677928514e-05,
"loss": 3.8379,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489507083177462e-05,
"loss": 3.8427,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.48866848842641e-05,
"loss": 3.8429,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4878315315557315e-05,
"loss": 3.848,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.4869929368046795e-05,
"loss": 3.8314,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.4861559799340004e-05,
"loss": 3.8365,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.4853173851829484e-05,
"loss": 3.8372,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.4844787904318964e-05,
"loss": 3.8407,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.4836401956808444e-05,
"loss": 3.8525,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.4828016009297924e-05,
"loss": 3.8405,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.48196300617874e-05,
"loss": 3.853,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481124411427688e-05,
"loss": 3.8469,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480285816676636e-05,
"loss": 3.8448,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479448859805957e-05,
"loss": 3.8389,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478610265054905e-05,
"loss": 3.8393,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477771670303853e-05,
"loss": 3.8484,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476933075552801e-05,
"loss": 3.8377,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476096118682122e-05,
"loss": 3.839,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.47525752393107e-05,
"loss": 3.8375,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474418929180018e-05,
"loss": 3.8285,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473580334428966e-05,
"loss": 3.8445,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472743377558287e-05,
"loss": 3.8482,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471904782807235e-05,
"loss": 3.8386,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471066188056183e-05,
"loss": 3.8331,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470227593305131e-05,
"loss": 3.841,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469388998554079e-05,
"loss": 3.8386,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468550403803028e-05,
"loss": 3.8367,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467711809051976e-05,
"loss": 3.8332,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466873214300924e-05,
"loss": 3.821,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660362574302446e-05,
"loss": 3.828,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651976626791926e-05,
"loss": 3.8218,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.4643590679281406e-05,
"loss": 3.8386,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4635204731770886e-05,
"loss": 3.828,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626835163064095e-05,
"loss": 3.8286,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618449215553575e-05,
"loss": 3.8285,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4610063268043055e-05,
"loss": 3.8303,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601677320532535e-05,
"loss": 3.8446,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4593307751825744e-05,
"loss": 3.8245,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584921804315224e-05,
"loss": 3.8214,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457653585680471e-05,
"loss": 3.8316,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456816628809792e-05,
"loss": 3.8338,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.45597803405874e-05,
"loss": 3.8243,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455139439307688e-05,
"loss": 3.8271,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454300844556636e-05,
"loss": 3.8209,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453463887685957e-05,
"loss": 3.8242,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452625292934905e-05,
"loss": 3.833,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451786698183853e-05,
"loss": 3.8148,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450948103432801e-05,
"loss": 3.8361,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450111146562122e-05,
"loss": 3.8238,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.44927255181107e-05,
"loss": 3.8085,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448433957060018e-05,
"loss": 3.8199,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.4475953623089664e-05,
"loss": 3.8239,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446758405438287e-05,
"loss": 3.8292,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445919810687235e-05,
"loss": 3.815,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445081215936183e-05,
"loss": 3.8226,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444242621185131e-05,
"loss": 3.8018,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443405664314452e-05,
"loss": 3.8277,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.4425670695634e-05,
"loss": 3.8114,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441728474812348e-05,
"loss": 3.8177,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440889880061296e-05,
"loss": 3.8244,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440051285310244e-05,
"loss": 3.8161,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439212690559192e-05,
"loss": 3.8213,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.43837409580814e-05,
"loss": 3.8313,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437535501057088e-05,
"loss": 3.8262,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.43669854418641e-05,
"loss": 3.8306,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435859949435358e-05,
"loss": 3.8154,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435021354684306e-05,
"loss": 3.8079,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434182759933253e-05,
"loss": 3.8163,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433345803062575e-05,
"loss": 3.8301,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4325088461918956e-05,
"loss": 3.8191,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316702514408436e-05,
"loss": 3.8113,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4308316566897916e-05,
"loss": 3.8019,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299930619387396e-05,
"loss": 3.811,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291544671876876e-05,
"loss": 3.8048,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4283158724366356e-05,
"loss": 3.8156,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274772776855836e-05,
"loss": 3.8163,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266386829345316e-05,
"loss": 3.8265,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425801726063853e-05,
"loss": 3.8124,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249631313128005e-05,
"loss": 3.8144,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4241245365617485e-05,
"loss": 3.8021,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.42328757969107e-05,
"loss": 3.8115,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422448984940018e-05,
"loss": 3.8146,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4216103901889654e-05,
"loss": 3.8088,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207717954379134e-05,
"loss": 3.8041,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.4199332006868614e-05,
"loss": 3.8186,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190946059358094e-05,
"loss": 3.8081,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182560111847573e-05,
"loss": 3.8302,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417419054314079e-05,
"loss": 3.8091,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416580459563027e-05,
"loss": 3.8189,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415741864811975e-05,
"loss": 3.8107,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414903270060923e-05,
"loss": 3.8092,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414064675309871e-05,
"loss": 3.8263,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413226080558819e-05,
"loss": 3.806,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412387485807767e-05,
"loss": 3.8229,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411548891056715e-05,
"loss": 3.8043,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410711934186036e-05,
"loss": 3.8032,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409873339434984e-05,
"loss": 3.8017,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409034744683932e-05,
"loss": 3.8137,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408197787813253e-05,
"loss": 3.8113,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407359193062201e-05,
"loss": 3.8003,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.4065205983111494e-05,
"loss": 3.7903,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.4056820035600974e-05,
"loss": 3.8049,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404845046689418e-05,
"loss": 3.8206,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.404006451938366e-05,
"loss": 3.8023,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403167857187314e-05,
"loss": 3.8213,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402329262436262e-05,
"loss": 3.8081,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.40149066768521e-05,
"loss": 3.8107,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400652072934158e-05,
"loss": 3.812,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399815116063479e-05,
"loss": 3.8016,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398976521312427e-05,
"loss": 3.7984,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398137926561375e-05,
"loss": 3.8031,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397299331810323e-05,
"loss": 3.8029,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396460737059271e-05,
"loss": 3.8045,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395622142308219e-05,
"loss": 3.8056,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394785185437541e-05,
"loss": 3.8061,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393946590686489e-05,
"loss": 3.7964,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393107995935437e-05,
"loss": 3.7982,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392269401184384e-05,
"loss": 3.8138,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3914324443137056e-05,
"loss": 3.7992,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905938495626536e-05,
"loss": 3.8135,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897552548116016e-05,
"loss": 3.8081,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388916660060549e-05,
"loss": 3.8055,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388078065309497e-05,
"loss": 3.8015,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387239470558445e-05,
"loss": 3.803,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386400875807393e-05,
"loss": 3.8037,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855639189367145e-05,
"loss": 3.8037,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3847253241856625e-05,
"loss": 3.819,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.3838867294346105e-05,
"loss": 3.8097,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830481346835585e-05,
"loss": 3.8117,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3822111778128794e-05,
"loss": 3.8092,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813725830618274e-05,
"loss": 3.7981,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3805339883107754e-05,
"loss": 3.8029,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796953935597234e-05,
"loss": 3.7952,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788567988086714e-05,
"loss": 3.799,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3780182040576194e-05,
"loss": 3.8019,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.37718124718694e-05,
"loss": 3.7944,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376342652435888e-05,
"loss": 3.7909,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375504057684836e-05,
"loss": 3.8001,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.89127779006958,
"eval_runtime": 565.2585,
"eval_samples_per_second": 675.073,
"eval_steps_per_second": 21.097,
"step": 381595
},
{
"epoch": 0.0,
"learning_rate": 4.374665462933785e-05,
"loss": 3.8091,
"step": 381952
},
{
"epoch": 0.0,
"learning_rate": 4.373826868182733e-05,
"loss": 3.8003,
"step": 382464
},
{
"epoch": 0.0,
"learning_rate": 4.372988273431681e-05,
"loss": 3.8,
"step": 382976
},
{
"epoch": 0.0,
"learning_rate": 4.372149678680629e-05,
"loss": 3.7992,
"step": 383488
},
{
"epoch": 0.0,
"learning_rate": 4.37131272180995e-05,
"loss": 3.8003,
"step": 384000
},
{
"epoch": 0.0,
"learning_rate": 4.370474127058898e-05,
"loss": 3.787,
"step": 384512
},
{
"epoch": 0.0,
"learning_rate": 4.369635532307846e-05,
"loss": 3.7983,
"step": 385024
},
{
"epoch": 0.0,
"learning_rate": 4.368796937556794e-05,
"loss": 3.7879,
"step": 385536
},
{
"epoch": 0.0,
"learning_rate": 4.367959980686115e-05,
"loss": 3.7951,
"step": 386048
},
{
"epoch": 0.0,
"learning_rate": 4.367121385935063e-05,
"loss": 3.7968,
"step": 386560
},
{
"epoch": 0.0,
"learning_rate": 4.366282791184011e-05,
"loss": 3.7984,
"step": 387072
},
{
"epoch": 0.0,
"learning_rate": 4.365444196432959e-05,
"loss": 3.7833,
"step": 387584
},
{
"epoch": 0.0,
"learning_rate": 4.364605601681907e-05,
"loss": 3.7915,
"step": 388096
},
{
"epoch": 0.0,
"learning_rate": 4.363768644811228e-05,
"loss": 3.7897,
"step": 388608
},
{
"epoch": 0.0,
"learning_rate": 4.362930050060176e-05,
"loss": 3.7944,
"step": 389120
},
{
"epoch": 0.0,
"learning_rate": 4.362091455309124e-05,
"loss": 3.7805,
"step": 389632
},
{
"epoch": 0.0,
"learning_rate": 4.361252860558072e-05,
"loss": 3.7817,
"step": 390144
},
{
"epoch": 0.0,
"learning_rate": 4.36041426580702e-05,
"loss": 3.7863,
"step": 390656
},
{
"epoch": 0.0,
"learning_rate": 4.359577308936341e-05,
"loss": 3.7897,
"step": 391168
},
{
"epoch": 0.0,
"learning_rate": 4.358738714185289e-05,
"loss": 3.8009,
"step": 391680
},
{
"epoch": 0.0,
"learning_rate": 4.357900119434237e-05,
"loss": 3.7863,
"step": 392192
},
{
"epoch": 0.0,
"learning_rate": 4.3570615246831845e-05,
"loss": 3.8038,
"step": 392704
},
{
"epoch": 0.0,
"learning_rate": 4.3562229299321325e-05,
"loss": 3.793,
"step": 393216
},
{
"epoch": 0.0,
"learning_rate": 4.3553843351810805e-05,
"loss": 3.7956,
"step": 393728
},
{
"epoch": 0.0,
"learning_rate": 4.354547378310402e-05,
"loss": 3.7864,
"step": 394240
},
{
"epoch": 0.0,
"learning_rate": 4.35370878355935e-05,
"loss": 3.7886,
"step": 394752
},
{
"epoch": 0.0,
"learning_rate": 4.352870188808298e-05,
"loss": 3.7983,
"step": 395264
},
{
"epoch": 0.0,
"learning_rate": 4.352031594057246e-05,
"loss": 3.7853,
"step": 395776
},
{
"epoch": 0.0,
"learning_rate": 4.351192999306194e-05,
"loss": 3.79,
"step": 396288
},
{
"epoch": 0.0,
"learning_rate": 4.350356042435515e-05,
"loss": 3.7852,
"step": 396800
},
{
"epoch": 0.01,
"learning_rate": 4.349517447684463e-05,
"loss": 3.7764,
"step": 397312
},
{
"epoch": 0.01,
"learning_rate": 4.348678852933411e-05,
"loss": 3.7969,
"step": 397824
},
{
"epoch": 0.01,
"learning_rate": 4.347840258182359e-05,
"loss": 3.7948,
"step": 398336
},
{
"epoch": 0.01,
"learning_rate": 4.347001663431307e-05,
"loss": 3.792,
"step": 398848
},
{
"epoch": 0.01,
"learning_rate": 4.346164706560628e-05,
"loss": 3.7797,
"step": 399360
},
{
"epoch": 0.01,
"learning_rate": 4.345326111809576e-05,
"loss": 3.7934,
"step": 399872
},
{
"epoch": 0.01,
"learning_rate": 4.344487517058524e-05,
"loss": 3.7831,
"step": 400384
},
{
"epoch": 0.01,
"learning_rate": 4.3436489223074726e-05,
"loss": 3.7908,
"step": 400896
},
{
"epoch": 0.01,
"learning_rate": 4.3428103275564206e-05,
"loss": 3.784,
"step": 401408
},
{
"epoch": 0.01,
"learning_rate": 4.3419733706857415e-05,
"loss": 3.7708,
"step": 401920
},
{
"epoch": 0.01,
"learning_rate": 4.3411347759346895e-05,
"loss": 3.7792,
"step": 402432
},
{
"epoch": 0.01,
"learning_rate": 4.3402961811836375e-05,
"loss": 3.769,
"step": 402944
},
{
"epoch": 0.01,
"learning_rate": 4.3394575864325854e-05,
"loss": 3.7931,
"step": 403456
},
{
"epoch": 0.01,
"learning_rate": 4.3386189916815334e-05,
"loss": 3.7781,
"step": 403968
},
{
"epoch": 0.01,
"learning_rate": 4.3377803969304814e-05,
"loss": 3.7754,
"step": 404480
},
{
"epoch": 0.01,
"learning_rate": 4.3369434400598024e-05,
"loss": 3.7823,
"step": 404992
},
{
"epoch": 0.01,
"learning_rate": 4.3361048453087503e-05,
"loss": 3.7818,
"step": 405504
},
{
"epoch": 0.01,
"learning_rate": 4.3352662505576983e-05,
"loss": 3.7932,
"step": 406016
},
{
"epoch": 0.01,
"learning_rate": 4.334427655806646e-05,
"loss": 3.7715,
"step": 406528
},
{
"epoch": 0.01,
"learning_rate": 4.333590698935968e-05,
"loss": 3.774,
"step": 407040
},
{
"epoch": 0.01,
"learning_rate": 4.332752104184916e-05,
"loss": 3.7832,
"step": 407552
},
{
"epoch": 0.01,
"learning_rate": 4.331913509433864e-05,
"loss": 3.7806,
"step": 408064
},
{
"epoch": 0.01,
"learning_rate": 4.331074914682812e-05,
"loss": 3.7757,
"step": 408576
},
{
"epoch": 0.01,
"learning_rate": 4.33023631993176e-05,
"loss": 3.7747,
"step": 409088
},
{
"epoch": 0.01,
"learning_rate": 4.329399363061081e-05,
"loss": 3.7716,
"step": 409600
},
{
"epoch": 0.01,
"learning_rate": 4.328560768310029e-05,
"loss": 3.7766,
"step": 410112
},
{
"epoch": 0.01,
"learning_rate": 4.327722173558977e-05,
"loss": 3.7787,
"step": 410624
},
{
"epoch": 0.01,
"learning_rate": 4.326883578807925e-05,
"loss": 3.7731,
"step": 411136
},
{
"epoch": 0.01,
"learning_rate": 4.326044984056873e-05,
"loss": 3.7867,
"step": 411648
},
{
"epoch": 0.01,
"learning_rate": 4.325206389305821e-05,
"loss": 3.7737,
"step": 412160
},
{
"epoch": 0.01,
"learning_rate": 4.324367794554768e-05,
"loss": 3.7649,
"step": 412672
},
{
"epoch": 0.01,
"learning_rate": 4.323529199803716e-05,
"loss": 3.7709,
"step": 413184
},
{
"epoch": 0.01,
"learning_rate": 4.322692242933038e-05,
"loss": 3.7703,
"step": 413696
},
{
"epoch": 0.01,
"learning_rate": 4.321855286062359e-05,
"loss": 3.7891,
"step": 414208
},
{
"epoch": 0.01,
"learning_rate": 4.321016691311307e-05,
"loss": 3.7655,
"step": 414720
},
{
"epoch": 0.01,
"learning_rate": 4.320178096560255e-05,
"loss": 3.774,
"step": 415232
},
{
"epoch": 0.01,
"learning_rate": 4.319339501809203e-05,
"loss": 3.7582,
"step": 415744
},
{
"epoch": 0.01,
"learning_rate": 4.318502544938524e-05,
"loss": 3.775,
"step": 416256
},
{
"epoch": 0.01,
"learning_rate": 4.317663950187472e-05,
"loss": 3.765,
"step": 416768
},
{
"epoch": 0.01,
"learning_rate": 4.31682535543642e-05,
"loss": 3.7671,
"step": 417280
},
{
"epoch": 0.01,
"learning_rate": 4.315986760685368e-05,
"loss": 3.7781,
"step": 417792
},
{
"epoch": 0.01,
"learning_rate": 4.315149803814689e-05,
"loss": 3.7712,
"step": 418304
},
{
"epoch": 0.01,
"learning_rate": 4.314311209063637e-05,
"loss": 3.7736,
"step": 418816
},
{
"epoch": 0.01,
"learning_rate": 4.313472614312585e-05,
"loss": 3.7836,
"step": 419328
},
{
"epoch": 0.01,
"learning_rate": 4.312634019561533e-05,
"loss": 3.7771,
"step": 419840
},
{
"epoch": 0.01,
"learning_rate": 4.311795424810481e-05,
"loss": 3.7859,
"step": 420352
},
{
"epoch": 0.01,
"learning_rate": 4.310956830059429e-05,
"loss": 3.7679,
"step": 420864
},
{
"epoch": 0.01,
"learning_rate": 4.3101198731887506e-05,
"loss": 3.7617,
"step": 421376
},
{
"epoch": 0.01,
"learning_rate": 4.309281278437698e-05,
"loss": 3.7669,
"step": 421888
},
{
"epoch": 0.01,
"learning_rate": 4.308442683686646e-05,
"loss": 3.7833,
"step": 422400
},
{
"epoch": 0.01,
"learning_rate": 4.307604088935594e-05,
"loss": 3.7708,
"step": 422912
},
{
"epoch": 0.01,
"learning_rate": 4.306765494184542e-05,
"loss": 3.7653,
"step": 423424
},
{
"epoch": 0.01,
"learning_rate": 4.30592689943349e-05,
"loss": 3.7558,
"step": 423936
},
{
"epoch": 0.01,
"learning_rate": 4.305088304682438e-05,
"loss": 3.7671,
"step": 424448
},
{
"epoch": 0.01,
"learning_rate": 4.304251347811759e-05,
"loss": 3.7552,
"step": 424960
},
{
"epoch": 0.01,
"learning_rate": 4.303412753060707e-05,
"loss": 3.7692,
"step": 425472
},
{
"epoch": 0.01,
"learning_rate": 4.302574158309655e-05,
"loss": 3.7709,
"step": 425984
},
{
"epoch": 0.01,
"learning_rate": 4.3017372014389764e-05,
"loss": 3.7762,
"step": 426496
},
{
"epoch": 0.01,
"learning_rate": 4.3008986066879244e-05,
"loss": 3.7672,
"step": 427008
},
{
"epoch": 0.02,
"learning_rate": 4.3000600119368724e-05,
"loss": 3.768,
"step": 427520
},
{
"epoch": 0.02,
"learning_rate": 4.2992214171858204e-05,
"loss": 3.7552,
"step": 428032
},
{
"epoch": 0.02,
"learning_rate": 4.298384460315141e-05,
"loss": 3.7645,
"step": 428544
},
{
"epoch": 0.02,
"learning_rate": 4.297545865564089e-05,
"loss": 3.7664,
"step": 429056
},
{
"epoch": 0.02,
"learning_rate": 4.296707270813037e-05,
"loss": 3.7636,
"step": 429568
},
{
"epoch": 0.02,
"learning_rate": 4.295868676061985e-05,
"loss": 3.7574,
"step": 430080
},
{
"epoch": 0.02,
"learning_rate": 4.295030081310933e-05,
"loss": 3.7737,
"step": 430592
},
{
"epoch": 0.02,
"learning_rate": 4.294193124440254e-05,
"loss": 3.7601,
"step": 431104
},
{
"epoch": 0.02,
"learning_rate": 4.293354529689202e-05,
"loss": 3.7852,
"step": 431616
},
{
"epoch": 0.02,
"learning_rate": 4.29251593493815e-05,
"loss": 3.7583,
"step": 432128
},
{
"epoch": 0.02,
"learning_rate": 4.291677340187099e-05,
"loss": 3.775,
"step": 432640
},
{
"epoch": 0.02,
"learning_rate": 4.290838745436047e-05,
"loss": 3.7635,
"step": 433152
},
{
"epoch": 0.02,
"learning_rate": 4.290001788565368e-05,
"loss": 3.7642,
"step": 433664
},
{
"epoch": 0.02,
"learning_rate": 4.289163193814316e-05,
"loss": 3.7826,
"step": 434176
},
{
"epoch": 0.02,
"learning_rate": 4.288324599063264e-05,
"loss": 3.7575,
"step": 434688
},
{
"epoch": 0.02,
"learning_rate": 4.287486004312212e-05,
"loss": 3.7784,
"step": 435200
},
{
"epoch": 0.02,
"learning_rate": 4.28664740956116e-05,
"loss": 3.7588,
"step": 435712
},
{
"epoch": 0.02,
"learning_rate": 4.285810452690481e-05,
"loss": 3.7586,
"step": 436224
},
{
"epoch": 0.02,
"learning_rate": 4.284971857939429e-05,
"loss": 3.756,
"step": 436736
},
{
"epoch": 0.02,
"learning_rate": 4.284133263188377e-05,
"loss": 3.7692,
"step": 437248
},
{
"epoch": 0.02,
"learning_rate": 4.2832946684373247e-05,
"loss": 3.7682,
"step": 437760
},
{
"epoch": 0.02,
"learning_rate": 4.2824560736862727e-05,
"loss": 3.7595,
"step": 438272
},
{
"epoch": 0.02,
"learning_rate": 4.281619116815594e-05,
"loss": 3.7414,
"step": 438784
},
{
"epoch": 0.02,
"learning_rate": 4.280780522064542e-05,
"loss": 3.7607,
"step": 439296
},
{
"epoch": 0.02,
"learning_rate": 4.27994192731349e-05,
"loss": 3.7744,
"step": 439808
},
{
"epoch": 0.02,
"learning_rate": 4.279103332562438e-05,
"loss": 3.7657,
"step": 440320
},
{
"epoch": 0.02,
"learning_rate": 4.278264737811386e-05,
"loss": 3.7709,
"step": 440832
},
{
"epoch": 0.02,
"learning_rate": 4.277426143060334e-05,
"loss": 3.7642,
"step": 441344
},
{
"epoch": 0.02,
"learning_rate": 4.276589186189655e-05,
"loss": 3.7655,
"step": 441856
},
{
"epoch": 0.02,
"learning_rate": 4.275750591438603e-05,
"loss": 3.7692,
"step": 442368
},
{
"epoch": 0.02,
"learning_rate": 4.274911996687551e-05,
"loss": 3.7606,
"step": 442880
},
{
"epoch": 0.02,
"learning_rate": 4.274073401936499e-05,
"loss": 3.752,
"step": 443392
},
{
"epoch": 0.02,
"learning_rate": 4.27323644506582e-05,
"loss": 3.7574,
"step": 443904
},
{
"epoch": 0.02,
"learning_rate": 4.272397850314768e-05,
"loss": 3.7562,
"step": 444416
},
{
"epoch": 0.02,
"learning_rate": 4.271559255563716e-05,
"loss": 3.7604,
"step": 444928
},
{
"epoch": 0.02,
"learning_rate": 4.270720660812664e-05,
"loss": 3.7588,
"step": 445440
},
{
"epoch": 0.02,
"learning_rate": 4.269882066061612e-05,
"loss": 3.7613,
"step": 445952
},
{
"epoch": 0.02,
"learning_rate": 4.2690451091909336e-05,
"loss": 3.7545,
"step": 446464
},
{
"epoch": 0.02,
"learning_rate": 4.2682065144398816e-05,
"loss": 3.7522,
"step": 446976
},
{
"epoch": 0.02,
"learning_rate": 4.267367919688829e-05,
"loss": 3.7671,
"step": 447488
},
{
"epoch": 0.02,
"learning_rate": 4.266529324937777e-05,
"loss": 3.7565,
"step": 448000
},
{
"epoch": 0.02,
"learning_rate": 4.265690730186725e-05,
"loss": 3.768,
"step": 448512
},
{
"epoch": 0.02,
"learning_rate": 4.2648537733160465e-05,
"loss": 3.7677,
"step": 449024
},
{
"epoch": 0.02,
"learning_rate": 4.264015178564994e-05,
"loss": 3.7608,
"step": 449536
},
{
"epoch": 0.02,
"learning_rate": 4.263176583813942e-05,
"loss": 3.7598,
"step": 450048
},
{
"epoch": 0.02,
"learning_rate": 4.26233798906289e-05,
"loss": 3.7594,
"step": 450560
},
{
"epoch": 0.02,
"learning_rate": 4.261499394311838e-05,
"loss": 3.757,
"step": 451072
},
{
"epoch": 0.02,
"learning_rate": 4.2606624374411594e-05,
"loss": 3.758,
"step": 451584
},
{
"epoch": 0.02,
"learning_rate": 4.2598238426901074e-05,
"loss": 3.7742,
"step": 452096
},
{
"epoch": 0.02,
"learning_rate": 4.2589852479390554e-05,
"loss": 3.7703,
"step": 452608
},
{
"epoch": 0.02,
"learning_rate": 4.2581466531880034e-05,
"loss": 3.7627,
"step": 453120
},
{
"epoch": 0.02,
"learning_rate": 4.257309696317324e-05,
"loss": 3.7647,
"step": 453632
},
{
"epoch": 0.02,
"learning_rate": 4.256471101566272e-05,
"loss": 3.7567,
"step": 454144
},
{
"epoch": 0.02,
"learning_rate": 4.25563250681522e-05,
"loss": 3.7611,
"step": 454656
},
{
"epoch": 0.02,
"learning_rate": 4.254793912064168e-05,
"loss": 3.7551,
"step": 455168
},
{
"epoch": 0.02,
"learning_rate": 4.253956955193489e-05,
"loss": 3.7484,
"step": 455680
},
{
"epoch": 0.02,
"learning_rate": 4.253118360442437e-05,
"loss": 3.7619,
"step": 456192
},
{
"epoch": 0.02,
"learning_rate": 4.252279765691385e-05,
"loss": 3.753,
"step": 456704
},
{
"epoch": 0.02,
"learning_rate": 4.251441170940333e-05,
"loss": 3.7476,
"step": 457216
},
{
"epoch": 0.02,
"learning_rate": 4.250604214069655e-05,
"loss": 3.7553,
"step": 457728
},
{
"epoch": 0.03,
"eval_loss": 3.8747153282165527,
"eval_runtime": 566.4256,
"eval_samples_per_second": 673.683,
"eval_steps_per_second": 21.053,
"step": 457914
},
{
"epoch": 0.0,
"learning_rate": 4.249765619318603e-05,
"loss": 3.7664,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.248927024567551e-05,
"loss": 3.7575,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.248088429816499e-05,
"loss": 3.7565,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.247249835065447e-05,
"loss": 3.7585,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.2464128781947676e-05,
"loss": 3.7576,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.2455742834437156e-05,
"loss": 3.7472,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.2447356886926636e-05,
"loss": 3.7551,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.2438970939416116e-05,
"loss": 3.7452,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.2430584991905596e-05,
"loss": 3.7504,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.2422215423198805e-05,
"loss": 3.7544,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.2413829475688285e-05,
"loss": 3.7601,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.2405443528177765e-05,
"loss": 3.7382,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239705758066725e-05,
"loss": 3.7535,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238868801196046e-05,
"loss": 3.7483,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.238030206444994e-05,
"loss": 3.7565,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237191611693942e-05,
"loss": 3.7365,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.23635301694289e-05,
"loss": 3.741,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.235516060072211e-05,
"loss": 3.7475,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.234677465321159e-05,
"loss": 3.7442,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.233838870570107e-05,
"loss": 3.7564,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.233000275819055e-05,
"loss": 3.747,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.232161681068003e-05,
"loss": 3.7597,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.231323086316951e-05,
"loss": 3.7516,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.230486129446272e-05,
"loss": 3.7529,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.2296475346952206e-05,
"loss": 3.7445,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.2288089399441686e-05,
"loss": 3.7484,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.2279719830734895e-05,
"loss": 3.7564,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.2271333883224375e-05,
"loss": 3.7487,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.2262947935713855e-05,
"loss": 3.7446,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.2254561988203335e-05,
"loss": 3.7478,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.2246176040692814e-05,
"loss": 3.737,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.2237790093182294e-05,
"loss": 3.7521,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.2229420524475504e-05,
"loss": 3.7547,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.2221034576964983e-05,
"loss": 3.7501,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.2212648629454463e-05,
"loss": 3.7394,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.2204262681943943e-05,
"loss": 3.7529,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.219589311323716e-05,
"loss": 3.7412,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.218750716572664e-05,
"loss": 3.7491,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.217912121821612e-05,
"loss": 3.7463,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.21707352707056e-05,
"loss": 3.7326,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.216234932319507e-05,
"loss": 3.7339,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.215396337568455e-05,
"loss": 3.7271,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.214559380697777e-05,
"loss": 3.7568,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.213720785946725e-05,
"loss": 3.7359,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.212882191195672e-05,
"loss": 3.7327,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.21204359644462e-05,
"loss": 3.7458,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.211206639573942e-05,
"loss": 3.7397,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.21036804482289e-05,
"loss": 3.7492,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.209529450071838e-05,
"loss": 3.736,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.208690855320786e-05,
"loss": 3.7381,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.207852260569734e-05,
"loss": 3.7394,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.2070153036990546e-05,
"loss": 3.742,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.2061767089480026e-05,
"loss": 3.7381,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.2053381141969506e-05,
"loss": 3.7292,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.2044995194458986e-05,
"loss": 3.7342,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.2036609246948466e-05,
"loss": 3.742,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.2028239678241675e-05,
"loss": 3.7376,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.2019853730731155e-05,
"loss": 3.7323,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.2011467783220635e-05,
"loss": 3.7459,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.2003081835710115e-05,
"loss": 3.7352,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.1994695888199595e-05,
"loss": 3.7245,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.1986309940689075e-05,
"loss": 3.7296,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.197794037198229e-05,
"loss": 3.7314,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.196955442447177e-05,
"loss": 3.7507,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196116847696125e-05,
"loss": 3.7279,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195278252945073e-05,
"loss": 3.7325,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.194441296074394e-05,
"loss": 3.7191,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.193602701323342e-05,
"loss": 3.7363,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.19276410657229e-05,
"loss": 3.7275,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.191925511821238e-05,
"loss": 3.7288,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.191086917070186e-05,
"loss": 3.7374,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.190249960199507e-05,
"loss": 3.732,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.189411365448455e-05,
"loss": 3.7379,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.188572770697403e-05,
"loss": 3.743,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.1877341759463515e-05,
"loss": 3.7384,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.1868955811952995e-05,
"loss": 3.7453,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.1860586243246204e-05,
"loss": 3.736,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.1852200295735684e-05,
"loss": 3.7218,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.1843814348225164e-05,
"loss": 3.7288,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.1835428400714644e-05,
"loss": 3.7389,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.182705883200785e-05,
"loss": 3.7378,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.181867288449733e-05,
"loss": 3.7294,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.181028693698681e-05,
"loss": 3.7127,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.180190098947629e-05,
"loss": 3.7319,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.179351504196577e-05,
"loss": 3.717,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.178514547325898e-05,
"loss": 3.7328,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.177675952574847e-05,
"loss": 3.7302,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.176837357823795e-05,
"loss": 3.7382,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.175998763072743e-05,
"loss": 3.7288,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.175161806202064e-05,
"loss": 3.729,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.174323211451012e-05,
"loss": 3.7202,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.17348461669996e-05,
"loss": 3.7313,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.172646021948908e-05,
"loss": 3.7243,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.171809065078229e-05,
"loss": 3.7284,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.170970470327177e-05,
"loss": 3.7197,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.170131875576125e-05,
"loss": 3.732,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.169293280825073e-05,
"loss": 3.7252,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.1684563239543936e-05,
"loss": 3.7507,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.167617729203342e-05,
"loss": 3.7224,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.16677913445229e-05,
"loss": 3.7387,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.165940539701238e-05,
"loss": 3.7276,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.165103582830559e-05,
"loss": 3.7249,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.164264988079507e-05,
"loss": 3.7443,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.163426393328455e-05,
"loss": 3.7241,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.1625877985774025e-05,
"loss": 3.7386,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.161750841706724e-05,
"loss": 3.7252,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.160912246955672e-05,
"loss": 3.7166,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.16007365220462e-05,
"loss": 3.7183,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.1592350574535674e-05,
"loss": 3.7312,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.158396462702516e-05,
"loss": 3.73,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.1575595058318376e-05,
"loss": 3.7264,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.1567209110807856e-05,
"loss": 3.7012,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.155882316329733e-05,
"loss": 3.7236,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.155043721578681e-05,
"loss": 3.7375,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.154205126827629e-05,
"loss": 3.7261,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.15336816995695e-05,
"loss": 3.734,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.152529575205898e-05,
"loss": 3.7288,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.151690980454846e-05,
"loss": 3.7291,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.150852385703794e-05,
"loss": 3.7308,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.150013790952742e-05,
"loss": 3.7239,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.149176834082063e-05,
"loss": 3.7143,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.1483382393310114e-05,
"loss": 3.7199,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.1474996445799594e-05,
"loss": 3.7219,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.1466610498289074e-05,
"loss": 3.7223,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.145824092958228e-05,
"loss": 3.7235,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.144985498207176e-05,
"loss": 3.7263,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.144146903456124e-05,
"loss": 3.7186,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.143308308705072e-05,
"loss": 3.7168,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.14246971395402e-05,
"loss": 3.7304,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.141632757083341e-05,
"loss": 3.7184,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.140794162332289e-05,
"loss": 3.7323,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.139955567581237e-05,
"loss": 3.7295,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.139116972830185e-05,
"loss": 3.7248,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.138280015959507e-05,
"loss": 3.7239,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.137441421208455e-05,
"loss": 3.7256,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.136602826457403e-05,
"loss": 3.7196,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.135764231706351e-05,
"loss": 3.7219,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.1349272748356717e-05,
"loss": 3.7387,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.1340886800846197e-05,
"loss": 3.7318,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.1332500853335676e-05,
"loss": 3.7301,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.1324114905825156e-05,
"loss": 3.7294,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.1315745337118366e-05,
"loss": 3.7178,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.1307359389607845e-05,
"loss": 3.7233,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.1298973442097325e-05,
"loss": 3.7204,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.1290587494586805e-05,
"loss": 3.7116,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.128221792588002e-05,
"loss": 3.7299,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.12738319783695e-05,
"loss": 3.7159,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.126544603085898e-05,
"loss": 3.711,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.125706008334846e-05,
"loss": 3.7228,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 3.864755153656006,
"eval_runtime": 566.8215,
"eval_samples_per_second": 673.212,
"eval_steps_per_second": 21.038,
"step": 534233
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.644393059920937e+17,
"trial_name": null,
"trial_params": null
}