abhinavp's picture
Training in progress, epoch 0, checkpoint
077ec47 verified
{
"best_metric": 3.95308780670166,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full2/transformer/0/checkpoints/checkpoint-228960",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 228960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 11.0453,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8203,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1803,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.976,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8136,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7055,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6058,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5376,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4512,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.403,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3536,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.33,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2746,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.211,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1872,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1491,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1193,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0928,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0671,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0268,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0218,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.986,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9659,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9377,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9353,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.9084,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8814,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8641,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8465,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8346,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8112,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740117521192533e-05,
"loss": 4.8046,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731731573682013e-05,
"loss": 4.7911,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7771,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7744,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7607,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7448,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.7186,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 4.714,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6948,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6941,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6788,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6731,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.656,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6628,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6451,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6473,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6369,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.609,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 4.602,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.616,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.6008,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5844,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5682,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5748,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5575,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5697,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5357,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5472,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5447,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5208,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 4.5379,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5087,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.5105,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4967,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.513,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.486,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4883,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4747,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4701,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4835,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940482703000532e-05,
"loss": 4.4759,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396441082494794e-05,
"loss": 4.4659,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388055134984274e-05,
"loss": 4.4653,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4719,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.446,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4601,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4346,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4338,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4317,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4345,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4255,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4334,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.418,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.3969,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.3995,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.411,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927070100624819e-05,
"loss": 4.3954,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92623314375414e-05,
"loss": 4.3944,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.3981,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3813,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3868,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.9228804026303046e-05,
"loss": 4.3807,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922041807879253e-05,
"loss": 4.3858,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921203213128201e-05,
"loss": 4.3832,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3773,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3577,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3646,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.3568,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3604,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.3648,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.3437,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3483,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913657498249106e-05,
"loss": 4.3495,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3432,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3316,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.335,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.322,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.3218,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3195,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3196,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.314,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3183,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3097,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3127,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3213,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.3152,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.3094,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.2991,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.2987,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.2997,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.2858,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.2887,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2851,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2893,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2801,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2895,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2816,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2735,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2684,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.2846,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2742,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.2679,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.2691,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.2702,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.2672,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2696,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2588,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2571,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2581,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.25,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.2452,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.245,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.2489,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2394,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.2489,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2412,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.2424,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2462,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2278,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.198204517364502,
"eval_runtime": 302.7571,
"eval_samples_per_second": 1260.387,
"eval_steps_per_second": 39.388,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.2153,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.2138,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.238,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2213,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2241,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2182,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2109,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.202,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2111,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.2031,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.2263,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.2114,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.1925,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.1953,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.1971,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.1843,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.1969,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.1913,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.1805,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.2049,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.1852,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856651071861674e-05,
"loss": 4.186,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.1768,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.1956,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.1737,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.1744,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.1703,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.1688,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.1673,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.166,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.1693,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.1671,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.1652,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.8465912106097964e-05,
"loss": 4.1701,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.1644,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.1653,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844077064237013e-05,
"loss": 4.1492,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.1523,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842399874734909e-05,
"loss": 4.1433,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841561279983857e-05,
"loss": 4.1509,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.1423,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.1517,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.1339,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.1537,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.1457,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836531349357918e-05,
"loss": 4.1453,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.1428,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.1279,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.13,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833178608234084e-05,
"loss": 4.1439,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832340013483032e-05,
"loss": 4.1345,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.83150141873198e-05,
"loss": 4.1282,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830662823980928e-05,
"loss": 4.1195,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.1293,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.1114,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281486776081446e-05,
"loss": 4.137,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273100828570926e-05,
"loss": 4.1076,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264714881060406e-05,
"loss": 4.127,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256328933549886e-05,
"loss": 4.1235,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247942986039366e-05,
"loss": 4.1103,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.1243,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.1121,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222801522311535e-05,
"loss": 4.1111,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214415574801015e-05,
"loss": 4.0977,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206029627290495e-05,
"loss": 4.1234,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197643679779975e-05,
"loss": 4.0986,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189257732269455e-05,
"loss": 4.107,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180888163562664e-05,
"loss": 4.0888,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172502216052144e-05,
"loss": 4.1007,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164116268541624e-05,
"loss": 4.1112,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155730321031104e-05,
"loss": 4.1088,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814736075232432e-05,
"loss": 4.1031,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.81389748048138e-05,
"loss": 4.1086,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813058885730328e-05,
"loss": 4.1114,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812220290979276e-05,
"loss": 4.0973,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811381696228224e-05,
"loss": 4.1069,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810544739357545e-05,
"loss": 4.0937,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809706144606493e-05,
"loss": 4.0938,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808867549855441e-05,
"loss": 4.0892,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808028955104389e-05,
"loss": 4.0989,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.0985,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806353403482658e-05,
"loss": 4.1027,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805514808731606e-05,
"loss": 4.0917,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804676213980554e-05,
"loss": 4.072,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803839257109875e-05,
"loss": 4.0766,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.0888,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802162067607771e-05,
"loss": 4.0822,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801323472856719e-05,
"loss": 4.0807,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.80048651598604e-05,
"loss": 4.0884,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799647921234988e-05,
"loss": 4.0742,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798809326483936e-05,
"loss": 4.0768,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797970731732884e-05,
"loss": 4.0781,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797133774862205e-05,
"loss": 4.0878,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796295180111153e-05,
"loss": 4.0841,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795456585360101e-05,
"loss": 4.0889,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794617990609049e-05,
"loss": 4.0642,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.073,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792942438987319e-05,
"loss": 4.0714,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.0711,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.0835,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790426654734163e-05,
"loss": 4.0634,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895896978634836e-05,
"loss": 4.0669,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887511031124316e-05,
"loss": 4.074,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879125083613796e-05,
"loss": 4.0708,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870739136103276e-05,
"loss": 4.0543,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862369567396485e-05,
"loss": 4.0656,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853983619885965e-05,
"loss": 4.0573,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845597672375445e-05,
"loss": 4.0569,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.0536,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.0531,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782045620864762e-05,
"loss": 4.0534,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.78120702611371e-05,
"loss": 4.0642,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780368431362658e-05,
"loss": 4.0494,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779529836611606e-05,
"loss": 4.0583,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778692879740927e-05,
"loss": 4.0687,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777854284989875e-05,
"loss": 4.0629,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777017328119196e-05,
"loss": 4.0586,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776178733368144e-05,
"loss": 4.0525,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775340138617092e-05,
"loss": 4.0492,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450154386604e-05,
"loss": 4.0526,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773662949114988e-05,
"loss": 4.0443,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728259922443094e-05,
"loss": 4.0453,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719873974932574e-05,
"loss": 4.046,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711488027422054e-05,
"loss": 4.0504,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703102079911534e-05,
"loss": 4.047,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694716132401014e-05,
"loss": 4.0485,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686330184890494e-05,
"loss": 4.0481,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767794423737997e-05,
"loss": 4.0367,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766957466867318e-05,
"loss": 4.0365,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766118872116266e-05,
"loss": 4.0551,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.7652802773652136e-05,
"loss": 4.0489,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.7644416826141616e-05,
"loss": 4.044,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.7636030878631096e-05,
"loss": 4.0391,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762766130992431e-05,
"loss": 4.0439,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761927536241379e-05,
"loss": 4.0417,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761088941490327e-05,
"loss": 4.0507,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760250346739275e-05,
"loss": 4.0414,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759413389868596e-05,
"loss": 4.0368,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758574795117544e-05,
"loss": 4.0389,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757736200366492e-05,
"loss": 4.0347,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.75689760561544e-05,
"loss": 4.0279,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756060648744761e-05,
"loss": 4.0322,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755222053993709e-05,
"loss": 4.0382,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754383459242657e-05,
"loss": 4.0225,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753544864491605e-05,
"loss": 4.0408,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527079076209266e-05,
"loss": 4.0322,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518693128698745e-05,
"loss": 4.0297,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510307181188225e-05,
"loss": 4.0355,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501921233677705e-05,
"loss": 4.022,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.027729034423828,
"eval_runtime": 302.5198,
"eval_samples_per_second": 1261.375,
"eval_steps_per_second": 39.419,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493535286167185e-05,
"loss": 4.0091,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485149338656665e-05,
"loss": 4.0107,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476763391146145e-05,
"loss": 4.0363,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468377443635625e-05,
"loss": 4.0207,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7459991496125105e-05,
"loss": 4.0299,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451605548614585e-05,
"loss": 4.0155,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443219601104065e-05,
"loss": 4.0168,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434833653593545e-05,
"loss": 4.0049,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426447706083025e-05,
"loss": 4.0167,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418061758572505e-05,
"loss": 4.0108,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409675811061985e-05,
"loss": 4.0314,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401289863551465e-05,
"loss": 4.0211,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739293667364841e-05,
"loss": 3.9997,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738455072613789e-05,
"loss": 4.0054,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737616477862737e-05,
"loss": 4.0103,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736777883111685e-05,
"loss": 3.9944,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735939288360632e-05,
"loss": 4.0083,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.73510069360958e-05,
"loss": 4.0086,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734262098858528e-05,
"loss": 3.9988,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733423504107476e-05,
"loss": 4.0262,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732586547236797e-05,
"loss": 4.0019,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731747952485746e-05,
"loss": 4.0083,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730909357734694e-05,
"loss": 3.999,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730070762983642e-05,
"loss": 4.0161,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729233806112963e-05,
"loss": 3.9915,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728395211361911e-05,
"loss": 4.0005,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727556616610859e-05,
"loss": 3.9929,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726718021859807e-05,
"loss": 3.998,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258810649891277e-05,
"loss": 3.9925,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250424702380757e-05,
"loss": 3.9929,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7242038754870237e-05,
"loss": 3.9991,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233652807359716e-05,
"loss": 3.997,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225283238652926e-05,
"loss": 3.9921,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721689729114241e-05,
"loss": 4.0027,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720851134363189e-05,
"loss": 3.9928,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720012539612137e-05,
"loss": 3.9981,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719175582741458e-05,
"loss": 3.9835,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718336987990406e-05,
"loss": 3.9878,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717498393239354e-05,
"loss": 3.9749,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716659798488302e-05,
"loss": 3.9898,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715822841617623e-05,
"loss": 3.9765,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714984246866571e-05,
"loss": 3.9905,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714145652115519e-05,
"loss": 3.9759,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713307057364467e-05,
"loss": 3.9871,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712470100493788e-05,
"loss": 3.9899,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116315057427366e-05,
"loss": 3.9842,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107929109916846e-05,
"loss": 3.9856,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099543162406326e-05,
"loss": 3.9708,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091173593699535e-05,
"loss": 3.9721,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082787646189015e-05,
"loss": 3.9872,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074401698678495e-05,
"loss": 3.9778,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7066015751167975e-05,
"loss": 3.9775,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057646182461184e-05,
"loss": 3.9644,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704927661375439e-05,
"loss": 3.9781,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704089066624387e-05,
"loss": 3.9544,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703250471873335e-05,
"loss": 3.9878,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702411877122283e-05,
"loss": 3.9558,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701573282371232e-05,
"loss": 3.9763,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.70073468762018e-05,
"loss": 3.9773,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699896092869128e-05,
"loss": 3.9599,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699057498118076e-05,
"loss": 3.9784,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698220541247397e-05,
"loss": 3.9628,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697381946496345e-05,
"loss": 3.964,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696543351745293e-05,
"loss": 3.952,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695704756994241e-05,
"loss": 3.9766,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694867800123562e-05,
"loss": 3.9557,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.69402920537251e-05,
"loss": 3.9609,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693190610621458e-05,
"loss": 3.9473,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692352015870406e-05,
"loss": 3.9563,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915150589997267e-05,
"loss": 3.9664,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690676464248675e-05,
"loss": 3.9695,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689837869497623e-05,
"loss": 3.9581,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688999274746571e-05,
"loss": 3.9721,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688162317875892e-05,
"loss": 3.9701,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.68732372312484e-05,
"loss": 3.9617,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686485128373788e-05,
"loss": 3.9624,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685646533622736e-05,
"loss": 3.9597,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684809576752057e-05,
"loss": 3.9542,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683970982001005e-05,
"loss": 3.954,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683132387249953e-05,
"loss": 3.96,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682293792498901e-05,
"loss": 3.9627,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681456835628222e-05,
"loss": 3.9699,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680618240877171e-05,
"loss": 3.9544,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679779646126119e-05,
"loss": 3.9353,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678941051375067e-05,
"loss": 3.9439,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.6781040945043876e-05,
"loss": 3.9539,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772654997533356e-05,
"loss": 3.9505,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764269050022836e-05,
"loss": 3.9479,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755883102512316e-05,
"loss": 3.9543,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747513533805525e-05,
"loss": 3.9489,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739127586295005e-05,
"loss": 3.9393,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730741638784485e-05,
"loss": 3.9497,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722355691273965e-05,
"loss": 3.9589,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713986122567174e-05,
"loss": 3.9531,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670560017505666e-05,
"loss": 3.9583,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669721422754614e-05,
"loss": 3.9415,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668882828003562e-05,
"loss": 3.9446,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668045871132883e-05,
"loss": 3.9413,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667207276381831e-05,
"loss": 3.9457,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666368681630779e-05,
"loss": 3.9545,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665530086879727e-05,
"loss": 3.9385,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664693130009048e-05,
"loss": 3.9397,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663854535257996e-05,
"loss": 3.9476,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663015940506944e-05,
"loss": 3.9488,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662177345755892e-05,
"loss": 3.9306,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613420267655863e-05,
"loss": 3.9381,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660503432014534e-05,
"loss": 3.9392,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659664837263482e-05,
"loss": 3.9339,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.65882624251243e-05,
"loss": 3.9298,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657987647761378e-05,
"loss": 3.9321,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657149053010326e-05,
"loss": 3.9358,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656310458259274e-05,
"loss": 3.938,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655471863508222e-05,
"loss": 3.929,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654634906637543e-05,
"loss": 3.9371,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653796311886491e-05,
"loss": 3.9474,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652957717135439e-05,
"loss": 3.949,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.65212076026476e-05,
"loss": 3.9373,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651282165513708e-05,
"loss": 3.9367,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650443570762657e-05,
"loss": 3.9314,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649604976011605e-05,
"loss": 3.9355,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648766381260553e-05,
"loss": 3.9252,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647929424389874e-05,
"loss": 3.9278,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647090829638822e-05,
"loss": 3.9285,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.64625223488777e-05,
"loss": 3.938,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645413640136718e-05,
"loss": 3.9302,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644575045385665e-05,
"loss": 3.9327,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643736450634613e-05,
"loss": 3.9322,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642897855883561e-05,
"loss": 3.9229,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642059261132509e-05,
"loss": 3.9205,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412223042618306e-05,
"loss": 3.9408,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403837095107786e-05,
"loss": 3.9383,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395451147597266e-05,
"loss": 3.9303,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387081578890475e-05,
"loss": 3.9268,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637871201018369e-05,
"loss": 3.9271,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637032606267317e-05,
"loss": 3.9306,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636194011516265e-05,
"loss": 3.9418,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353554167652124e-05,
"loss": 3.929,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345168220141604e-05,
"loss": 3.9228,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336782272631084e-05,
"loss": 3.9264,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328396325120564e-05,
"loss": 3.9232,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320010377610043e-05,
"loss": 3.9204,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631164080890326e-05,
"loss": 3.9203,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630325486139274e-05,
"loss": 3.9275,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629486891388222e-05,
"loss": 3.9163,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.62864829663717e-05,
"loss": 3.9289,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627811339766491e-05,
"loss": 3.9262,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626972745015439e-05,
"loss": 3.9209,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626134150264387e-05,
"loss": 3.9269,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625295555513335e-05,
"loss": 3.9114,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.95308780670166,
"eval_runtime": 304.6541,
"eval_samples_per_second": 1252.539,
"eval_steps_per_second": 39.143,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.593503783284009e+17,
"trial_name": null,
"trial_params": null
}