abhinavp's picture
Training in progress, epoch 0, checkpoint
5fa692c verified
{
"best_metric": 3.8445518016815186,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-adj-noun/transformer/4/checkpoints/checkpoint-839520",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 992160,
"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": 10.9699,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8333,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1915,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9762,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8051,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7004,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6002,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5238,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4428,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3986,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3429,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3049,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.255,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2022,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1641,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1276,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.0973,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0754,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0379,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0079,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0009,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 4.9578,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9484,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9217,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9131,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.879,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8581,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.842,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8322,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8109,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7959,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740117521192533e-05,
"loss": 4.7883,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731731573682013e-05,
"loss": 4.7654,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7593,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7441,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7329,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969820416244367e-05,
"loss": 4.7208,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.6899,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.697,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6698,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6776,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6614,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6617,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6444,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6349,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6338,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6225,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6154,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5971,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5826,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.5945,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.5805,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5742,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5517,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.557,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.537,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.557,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5272,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 4.5382,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5228,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5036,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5106,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 4.5024,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 4.4829,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4822,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.4959,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.4733,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 4.4669,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4558,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4597,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4732,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 4.4608,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4465,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4504,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4515,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4347,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.426,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4296,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4162,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4179,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4154,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4131,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4163,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930422841748654e-05,
"loss": 4.4083,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.3882,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.3929,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.3895,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.3956,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3842,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.384,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3816,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3745,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3731,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 4.367,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.3586,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3663,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3533,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3511,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3507,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3546,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.352,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3407,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.3336,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3323,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3286,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3136,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3136,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3254,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.32,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.3061,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.3027,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.3076,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3158,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3117,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3016,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3045,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.3067,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.2909,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.287,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.2923,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.2911,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.2732,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.2773,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2753,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2729,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2744,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2809,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.2651,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2666,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2569,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.2737,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2649,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.2554,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.2554,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.2631,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.2591,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2531,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2493,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2519,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2511,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2501,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.2313,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2401,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.228,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2187,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.2442,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2314,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.2325,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.2327,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2118,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.194186210632324,
"eval_runtime": 304.0468,
"eval_samples_per_second": 1255.04,
"eval_steps_per_second": 39.221,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.2128,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.2101,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.2298,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2109,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2187,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2003,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2017,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.1957,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2026,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.2008,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.2079,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.2057,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.1871,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.1865,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.1825,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.1761,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.186,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.173,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.1726,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.1988,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.1736,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856651071861674e-05,
"loss": 4.1741,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558124771106226e-05,
"loss": 4.1762,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.1773,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.167,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.1635,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.1602,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851621141235735e-05,
"loss": 4.1681,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.1508,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.1593,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.1595,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.1545,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.1581,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.1487,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.1504,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.1509,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844077064237013e-05,
"loss": 4.1319,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.141,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.1287,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.1372,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.1403,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.1444,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839048771491447e-05,
"loss": 4.1355,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838210176740395e-05,
"loss": 4.1316,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.1395,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.1341,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.1257,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.8348574356165606e-05,
"loss": 4.1223,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.1151,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.1301,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.1238,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315046944927255e-05,
"loss": 4.1216,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306660997416735e-05,
"loss": 4.1145,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.1207,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.1041,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281519533688904e-05,
"loss": 4.125,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273133586178384e-05,
"loss": 4.1065,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826474763866787e-05,
"loss": 4.1235,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.1131,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824799212245056e-05,
"loss": 4.0988,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823960617494004e-05,
"loss": 4.1037,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823122022742952e-05,
"loss": 4.1068,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222834279919e-05,
"loss": 4.0899,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821446471121221e-05,
"loss": 4.092,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820607876370169e-05,
"loss": 4.1081,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819769281619117e-05,
"loss": 4.0966,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818930686868065e-05,
"loss": 4.0902,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818093729997386e-05,
"loss": 4.0857,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817255135246334e-05,
"loss": 4.0904,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816416540495282e-05,
"loss": 4.1045,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155779457442305e-05,
"loss": 4.0998,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147393509931785e-05,
"loss": 4.0933,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139023941224994e-05,
"loss": 4.0976,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130637993714474e-05,
"loss": 4.0958,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122252046203954e-05,
"loss": 4.0912,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811388247749716e-05,
"loss": 4.0784,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810549652998664e-05,
"loss": 4.0925,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809711058247612e-05,
"loss": 4.0834,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887246349656e-05,
"loss": 4.0827,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808035506625881e-05,
"loss": 4.0901,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807196911874829e-05,
"loss": 4.0832,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806358317123777e-05,
"loss": 4.0906,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805519722372726e-05,
"loss": 4.0864,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804681127621674e-05,
"loss": 4.062,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803842532870622e-05,
"loss": 4.0769,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.80300393811957e-05,
"loss": 4.0747,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802165343368518e-05,
"loss": 4.0817,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801328386497839e-05,
"loss": 4.0773,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004914296271596e-05,
"loss": 4.0765,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996528348761076e-05,
"loss": 4.0765,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988142401250556e-05,
"loss": 4.073,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979756453740036e-05,
"loss": 4.0754,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971370506229516e-05,
"loss": 4.0725,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7962984558718996e-05,
"loss": 4.0637,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795461499001221e-05,
"loss": 4.0744,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794622904250169e-05,
"loss": 4.0693,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793784309499117e-05,
"loss": 4.0615,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792945714748065e-05,
"loss": 4.0704,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792107119997013e-05,
"loss": 4.0694,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912685252459605e-05,
"loss": 4.0754,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904299304949085e-05,
"loss": 4.0638,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895913357438565e-05,
"loss": 4.0562,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887543788731774e-05,
"loss": 4.0605,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879157841221254e-05,
"loss": 4.0597,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870771893710734e-05,
"loss": 4.038,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786240232500395e-05,
"loss": 4.0547,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785401637749343e-05,
"loss": 4.0572,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784563042998291e-05,
"loss": 4.0564,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783724448247239e-05,
"loss": 4.0447,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782885853496187e-05,
"loss": 4.0406,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782047258745135e-05,
"loss": 4.0505,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781208663994083e-05,
"loss": 4.0614,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780370069243031e-05,
"loss": 4.0544,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779533112372352e-05,
"loss": 4.0534,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786945176213e-05,
"loss": 4.0519,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777855922870248e-05,
"loss": 4.0636,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777017328119196e-05,
"loss": 4.0402,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776180371248517e-05,
"loss": 4.0408,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775341776497465e-05,
"loss": 4.0476,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7745031817464134e-05,
"loss": 4.0495,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736645869953614e-05,
"loss": 4.0318,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772827630124682e-05,
"loss": 4.0333,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.77198903537363e-05,
"loss": 4.0411,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771150440622578e-05,
"loss": 4.0379,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770311845871526e-05,
"loss": 4.0407,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769473251120474e-05,
"loss": 4.0469,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768634656369422e-05,
"loss": 4.0286,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76779606161837e-05,
"loss": 4.0366,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766959104747691e-05,
"loss": 4.0273,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766120509996639e-05,
"loss": 4.0479,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765281915245587e-05,
"loss": 4.0445,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764443320494535e-05,
"loss": 4.0284,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763606363623857e-05,
"loss": 4.0327,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762767768872805e-05,
"loss": 4.0371,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761929174121753e-05,
"loss": 4.0398,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761090579370701e-05,
"loss": 4.0357,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760253622500022e-05,
"loss": 4.0314,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941502774897e-05,
"loss": 4.0312,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758576432997918e-05,
"loss": 4.0332,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757737838246866e-05,
"loss": 4.0343,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569008813761866e-05,
"loss": 4.021,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560622866251346e-05,
"loss": 4.0289,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552236918740826e-05,
"loss": 4.021,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543867350034035e-05,
"loss": 4.0077,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753548140252352e-05,
"loss": 4.0357,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527095455013e-05,
"loss": 4.0221,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751870950750248e-05,
"loss": 4.0262,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751032355999196e-05,
"loss": 4.027,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501937612481435e-05,
"loss": 4.0104,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.0266523361206055,
"eval_runtime": 302.859,
"eval_samples_per_second": 1259.962,
"eval_steps_per_second": 39.375,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493551664970914e-05,
"loss": 4.0125,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485165717460394e-05,
"loss": 4.006,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476779769949874e-05,
"loss": 4.0322,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468393822439354e-05,
"loss": 4.0098,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460007874928834e-05,
"loss": 4.0254,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451621927418314e-05,
"loss": 4.0054,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443235979907794e-05,
"loss": 4.0059,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434850032397274e-05,
"loss": 3.9981,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426464084886754e-05,
"loss": 4.0129,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418078137376234e-05,
"loss": 4.0086,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740969218986572e-05,
"loss": 4.015,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740132262115893e-05,
"loss": 4.0155,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739295305245214e-05,
"loss": 4.0013,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738456710494162e-05,
"loss": 4.0012,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.73761811574311e-05,
"loss": 3.9953,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736779520992058e-05,
"loss": 3.9924,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735940926241006e-05,
"loss": 4.0004,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735102331489954e-05,
"loss": 3.9936,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734263736738902e-05,
"loss": 3.9908,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.73342514198785e-05,
"loss": 4.0118,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732588185117171e-05,
"loss": 3.9954,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731749590366119e-05,
"loss": 3.9955,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7309109956150674e-05,
"loss": 3.9983,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300740387443884e-05,
"loss": 4.0026,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292354439933364e-05,
"loss": 3.9906,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7283968492422844e-05,
"loss": 3.9912,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275582544912323e-05,
"loss": 3.9897,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726721297620553e-05,
"loss": 3.9903,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725882702869501e-05,
"loss": 3.9801,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725044108118449e-05,
"loss": 3.9893,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724205513367397e-05,
"loss": 3.9887,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723368556496718e-05,
"loss": 3.9866,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722529961745666e-05,
"loss": 3.9926,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721691366994614e-05,
"loss": 3.9824,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720852772243563e-05,
"loss": 3.983,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.72001417749251e-05,
"loss": 3.9838,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719175582741458e-05,
"loss": 3.9703,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718336987990406e-05,
"loss": 3.9737,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717500031119727e-05,
"loss": 3.967,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716661436368675e-05,
"loss": 3.9731,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715822841617623e-05,
"loss": 3.9806,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714984246866571e-05,
"loss": 3.9833,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714147289995892e-05,
"loss": 3.9756,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71330869524484e-05,
"loss": 3.9727,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712470100493788e-05,
"loss": 3.9852,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116315057427366e-05,
"loss": 3.9724,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107945488720575e-05,
"loss": 3.9701,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099559541210055e-05,
"loss": 3.9706,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091173593699535e-05,
"loss": 3.9565,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082804024992744e-05,
"loss": 3.9753,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074418077482224e-05,
"loss": 3.9675,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7066032129971704e-05,
"loss": 3.9708,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057646182461184e-05,
"loss": 3.9632,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704927661375439e-05,
"loss": 3.9668,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704089066624387e-05,
"loss": 3.9514,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703250471873335e-05,
"loss": 3.9759,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702411877122283e-05,
"loss": 3.955,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701573282371232e-05,
"loss": 3.9745,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.70073468762018e-05,
"loss": 3.9625,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699896092869128e-05,
"loss": 3.9557,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699057498118076e-05,
"loss": 3.9532,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698220541247397e-05,
"loss": 3.964,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697381946496345e-05,
"loss": 3.9439,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696543351745293e-05,
"loss": 3.9511,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695704756994241e-05,
"loss": 3.9632,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694867800123562e-05,
"loss": 3.9567,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.69402920537251e-05,
"loss": 3.9466,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693190610621458e-05,
"loss": 3.9423,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692352015870406e-05,
"loss": 3.9465,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915150589997267e-05,
"loss": 3.9674,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690676464248675e-05,
"loss": 3.9561,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689837869497623e-05,
"loss": 3.952,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688999274746571e-05,
"loss": 3.9623,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688162317875892e-05,
"loss": 3.9562,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.68732372312484e-05,
"loss": 3.9538,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686485128373788e-05,
"loss": 3.9369,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685646533622736e-05,
"loss": 3.9566,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684809576752057e-05,
"loss": 3.9507,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683970982001005e-05,
"loss": 3.9434,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683134025130326e-05,
"loss": 3.9585,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682295430379274e-05,
"loss": 3.9476,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681456835628222e-05,
"loss": 3.9529,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680618240877171e-05,
"loss": 3.9512,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679779646126119e-05,
"loss": 3.9342,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789426892554396e-05,
"loss": 3.944,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.6781040945043876e-05,
"loss": 3.9424,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772654997533356e-05,
"loss": 3.9478,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764269050022836e-05,
"loss": 3.9471,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755883102512316e-05,
"loss": 3.943,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747513533805525e-05,
"loss": 3.9466,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739127586295005e-05,
"loss": 3.944,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730741638784485e-05,
"loss": 3.9425,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722355691273965e-05,
"loss": 3.9387,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713986122567174e-05,
"loss": 3.9421,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670561655386039e-05,
"loss": 3.9485,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669723060634987e-05,
"loss": 3.9388,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668884465883935e-05,
"loss": 3.9341,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668045871132883e-05,
"loss": 3.9448,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667207276381831e-05,
"loss": 3.9445,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666368681630779e-05,
"loss": 3.9507,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665530086879727e-05,
"loss": 3.9374,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664691492128675e-05,
"loss": 3.9349,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663852897377623e-05,
"loss": 3.9358,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663015940506944e-05,
"loss": 3.9381,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662177345755892e-05,
"loss": 3.9145,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.66133875100484e-05,
"loss": 3.9322,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660500156253788e-05,
"loss": 3.9357,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596631993831094e-05,
"loss": 3.9299,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588246046320574e-05,
"loss": 3.9276,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579860098810054e-05,
"loss": 3.921,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657147415129953e-05,
"loss": 3.9271,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656308820378901e-05,
"loss": 3.9446,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655470225627849e-05,
"loss": 3.9305,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654631630876797e-05,
"loss": 3.9386,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6537946740061176e-05,
"loss": 3.931,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.6529560792550656e-05,
"loss": 3.9438,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521174845040136e-05,
"loss": 3.9264,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512788897529616e-05,
"loss": 3.9223,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.6504402950019096e-05,
"loss": 3.928,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649601700250858e-05,
"loss": 3.9308,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648764743380179e-05,
"loss": 3.9128,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647926148629127e-05,
"loss": 3.9169,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647087553878075e-05,
"loss": 3.9215,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646248959127023e-05,
"loss": 3.9277,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645410364375971e-05,
"loss": 3.9271,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644573407505292e-05,
"loss": 3.9316,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.64373481275424e-05,
"loss": 3.912,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642896218003188e-05,
"loss": 3.9198,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642057623252136e-05,
"loss": 3.9139,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641219028501084e-05,
"loss": 3.9347,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640380433750032e-05,
"loss": 3.9346,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.63954183899898e-05,
"loss": 3.9182,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638703244247928e-05,
"loss": 3.9152,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378662873772496e-05,
"loss": 3.924,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370276926261976e-05,
"loss": 3.9259,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6361890978751456e-05,
"loss": 3.9278,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353521410044665e-05,
"loss": 3.9172,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345135462534145e-05,
"loss": 3.9222,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336749515023625e-05,
"loss": 3.9219,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328363567513105e-05,
"loss": 3.9279,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6319977620002585e-05,
"loss": 3.9132,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631159167249206e-05,
"loss": 3.9153,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303222103785274e-05,
"loss": 3.9143,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294836156274754e-05,
"loss": 3.8968,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286450208764234e-05,
"loss": 3.9277,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627808064005745e-05,
"loss": 3.9161,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626969469254693e-05,
"loss": 3.9183,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626130874503641e-05,
"loss": 3.9189,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625292279752589e-05,
"loss": 3.9029,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9524450302124023,
"eval_runtime": 304.3336,
"eval_samples_per_second": 1253.858,
"eval_steps_per_second": 39.184,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624453685001536e-05,
"loss": 3.9099,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623615090250484e-05,
"loss": 3.8997,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622778133379806e-05,
"loss": 3.924,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621939538628753e-05,
"loss": 3.9045,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621100943877701e-05,
"loss": 3.9291,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620262349126649e-05,
"loss": 3.8944,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619423754375597e-05,
"loss": 3.9053,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618585159624545e-05,
"loss": 3.8893,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617746564873494e-05,
"loss": 3.9116,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616907970122442e-05,
"loss": 3.9054,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616071013251763e-05,
"loss": 3.9069,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615234056381084e-05,
"loss": 3.9194,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614397099510405e-05,
"loss": 3.8956,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613558504759353e-05,
"loss": 3.9007,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.6127199100083006e-05,
"loss": 3.8919,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.6118813152572486e-05,
"loss": 3.893,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.6110427205061966e-05,
"loss": 3.8991,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.6102041257551446e-05,
"loss": 3.893,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.6093655310040926e-05,
"loss": 3.8934,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.6085269362530406e-05,
"loss": 3.9095,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607688341501989e-05,
"loss": 3.8981,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606849746750937e-05,
"loss": 3.8963,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606011151999885e-05,
"loss": 3.9031,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605174195129206e-05,
"loss": 3.9032,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604335600378154e-05,
"loss": 3.8902,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603497005627102e-05,
"loss": 3.8947,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.60265841087605e-05,
"loss": 3.894,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601819816124998e-05,
"loss": 3.8885,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.600981221373946e-05,
"loss": 3.8859,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600142626622894e-05,
"loss": 3.8865,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599304031871842e-05,
"loss": 3.8993,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598467075001163e-05,
"loss": 3.8895,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597628480250111e-05,
"loss": 3.9004,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596789885499059e-05,
"loss": 3.8887,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595951290748008e-05,
"loss": 3.8868,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595112695996955e-05,
"loss": 3.8874,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.5942757391262766e-05,
"loss": 3.8803,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.5934371443752246e-05,
"loss": 3.8785,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.5925985496241726e-05,
"loss": 3.8722,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.59175995487312e-05,
"loss": 3.8792,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.5909229980024415e-05,
"loss": 3.887,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900844032513895e-05,
"loss": 3.8882,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589245808500337e-05,
"loss": 3.8839,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588407213749285e-05,
"loss": 3.8836,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587568618998233e-05,
"loss": 3.8939,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867300242471815e-05,
"loss": 3.8796,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858914294961295e-05,
"loss": 3.8785,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.5850544726254504e-05,
"loss": 3.8769,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.5842158778743984e-05,
"loss": 3.8654,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.5833772831233464e-05,
"loss": 3.8872,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.5825386883722943e-05,
"loss": 3.8758,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.5817000936212423e-05,
"loss": 3.8786,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.58086149887019e-05,
"loss": 3.8711,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580024541999511e-05,
"loss": 3.8824,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579185947248459e-05,
"loss": 3.8585,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578347352497407e-05,
"loss": 3.885,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577508757746355e-05,
"loss": 3.8699,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576670162995303e-05,
"loss": 3.8812,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575831568244251e-05,
"loss": 3.8805,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.574992973493199e-05,
"loss": 3.864,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574156016622521e-05,
"loss": 3.864,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573317421871469e-05,
"loss": 3.8819,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572478827120417e-05,
"loss": 3.8581,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571640232369365e-05,
"loss": 3.8587,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570803275498686e-05,
"loss": 3.8773,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569964680747634e-05,
"loss": 3.8715,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569126085996582e-05,
"loss": 3.8571,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.56828749124553e-05,
"loss": 3.858,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567448896494478e-05,
"loss": 3.8597,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566610301743426e-05,
"loss": 3.878,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565771706992373e-05,
"loss": 3.8693,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564933112241322e-05,
"loss": 3.8664,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564096155370643e-05,
"loss": 3.8751,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563257560619591e-05,
"loss": 3.8752,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624189658685386e-05,
"loss": 3.8727,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615803711174866e-05,
"loss": 3.8543,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.5607417763664346e-05,
"loss": 3.8694,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.5599031816153826e-05,
"loss": 3.8641,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.5590645868643306e-05,
"loss": 3.8582,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582276299936515e-05,
"loss": 3.8776,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.5573890352425995e-05,
"loss": 3.8638,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.5565504404915475e-05,
"loss": 3.8699,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.5557118457404955e-05,
"loss": 3.8676,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.5548732509894434e-05,
"loss": 3.8537,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554036294118765e-05,
"loss": 3.8602,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553197699367713e-05,
"loss": 3.8587,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552359104616661e-05,
"loss": 3.8612,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551520509865609e-05,
"loss": 3.8656,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.55068355299493e-05,
"loss": 3.8584,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549844958243878e-05,
"loss": 3.866,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549006363492826e-05,
"loss": 3.8658,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548167768741774e-05,
"loss": 3.8576,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547330811871095e-05,
"loss": 3.8586,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546492217120043e-05,
"loss": 3.8607,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545655260249364e-05,
"loss": 3.8725,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448166654983124e-05,
"loss": 3.8589,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.5439780707472604e-05,
"loss": 3.8544,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.5431394759962084e-05,
"loss": 3.8635,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.5423008812451564e-05,
"loss": 3.8586,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.5414622864941044e-05,
"loss": 3.8717,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406236917430524e-05,
"loss": 3.8579,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5397850969920004e-05,
"loss": 3.8573,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538948140121321e-05,
"loss": 3.8535,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538109545370269e-05,
"loss": 3.8609,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537270950619217e-05,
"loss": 3.8369,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536432355868165e-05,
"loss": 3.8498,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535595398997486e-05,
"loss": 3.8593,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534756804246434e-05,
"loss": 3.8528,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533919847375756e-05,
"loss": 3.8449,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533081252624704e-05,
"loss": 3.8462,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532242657873652e-05,
"loss": 3.8483,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314040631226e-05,
"loss": 3.8705,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530565468371548e-05,
"loss": 3.8482,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529726873620496e-05,
"loss": 3.8587,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528888278869444e-05,
"loss": 3.8548,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528049684118392e-05,
"loss": 3.8675,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.5272127272477126e-05,
"loss": 3.8522,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.5263741324966606e-05,
"loss": 3.8431,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.5255355377456086e-05,
"loss": 3.8546,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.5246969429945566e-05,
"loss": 3.8558,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.5238599861238775e-05,
"loss": 3.837,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.5230213913728255e-05,
"loss": 3.8407,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522182796621774e-05,
"loss": 3.8486,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521344201870722e-05,
"loss": 3.8514,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520507245000043e-05,
"loss": 3.8463,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519668650248991e-05,
"loss": 3.861,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518830055497939e-05,
"loss": 3.837,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5179914607468864e-05,
"loss": 3.8448,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171528659958344e-05,
"loss": 3.837,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516315909125156e-05,
"loss": 3.8601,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515477314374104e-05,
"loss": 3.8592,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514638719623051e-05,
"loss": 3.8458,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513800124872e-05,
"loss": 3.8386,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512963168001321e-05,
"loss": 3.8521,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512124573250269e-05,
"loss": 3.8521,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511285978499217e-05,
"loss": 3.851,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510447383748165e-05,
"loss": 3.8464,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5096104268774865e-05,
"loss": 3.8464,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508771832126434e-05,
"loss": 3.8491,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507933237375382e-05,
"loss": 3.8586,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.50709464262433e-05,
"loss": 3.8382,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506256047873278e-05,
"loss": 3.8382,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505419091002599e-05,
"loss": 3.8413,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504580496251547e-05,
"loss": 3.8296,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503741901500495e-05,
"loss": 3.8518,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5029033067494434e-05,
"loss": 3.844,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502066349878764e-05,
"loss": 3.8459,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501227755127712e-05,
"loss": 3.8425,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.50038916037666e-05,
"loss": 3.8382,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.910917043685913,
"eval_runtime": 305.7735,
"eval_samples_per_second": 1247.953,
"eval_steps_per_second": 38.999,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499550565625608e-05,
"loss": 3.8372,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498711970874556e-05,
"loss": 3.828,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497873376123504e-05,
"loss": 3.85,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497034781372452e-05,
"loss": 3.8367,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4961961866214e-05,
"loss": 3.8543,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495357591870348e-05,
"loss": 3.8327,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494518997119296e-05,
"loss": 3.8311,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493680402368244e-05,
"loss": 3.8211,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492841807617192e-05,
"loss": 3.8378,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.49200321286614e-05,
"loss": 3.8398,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491166255995462e-05,
"loss": 3.8379,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.49032766124441e-05,
"loss": 3.8456,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489490704373731e-05,
"loss": 3.8297,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488652109622679e-05,
"loss": 3.8315,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487813514871627e-05,
"loss": 3.8246,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486974920120575e-05,
"loss": 3.8215,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486136325369523e-05,
"loss": 3.8314,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.48529773061847e-05,
"loss": 3.8287,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484459135867418e-05,
"loss": 3.8227,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483620541116366e-05,
"loss": 3.84,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482781946365314e-05,
"loss": 3.8318,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481943351614262e-05,
"loss": 3.8304,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.4811063947435836e-05,
"loss": 3.8337,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.4802677999925316e-05,
"loss": 3.8353,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.4794292052414796e-05,
"loss": 3.8187,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.4785906104904276e-05,
"loss": 3.8341,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.4777536536197485e-05,
"loss": 3.8214,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.4769150588686965e-05,
"loss": 3.8232,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.4760764641176445e-05,
"loss": 3.8193,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.4752378693665925e-05,
"loss": 3.8233,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.4743992746155405e-05,
"loss": 3.8303,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.4735623177448614e-05,
"loss": 3.8276,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.4727237229938094e-05,
"loss": 3.8333,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.4718851282427574e-05,
"loss": 3.8221,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710465334917054e-05,
"loss": 3.8202,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470209576621027e-05,
"loss": 3.8238,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469370981869975e-05,
"loss": 3.8179,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468532387118923e-05,
"loss": 3.8094,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467693792367871e-05,
"loss": 3.8098,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466856835497192e-05,
"loss": 3.8126,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.46601824074614e-05,
"loss": 3.8194,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465179645995088e-05,
"loss": 3.8245,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464341051244036e-05,
"loss": 3.8196,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463502456492984e-05,
"loss": 3.8154,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462663861741932e-05,
"loss": 3.8273,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461826904871253e-05,
"loss": 3.8184,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460988310120201e-05,
"loss": 3.8141,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460149715369149e-05,
"loss": 3.8119,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4593111206180974e-05,
"loss": 3.8006,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584725258670454e-05,
"loss": 3.8255,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457635568996366e-05,
"loss": 3.8108,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456796974245314e-05,
"loss": 3.8169,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455958379494262e-05,
"loss": 3.8123,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.45511978474321e-05,
"loss": 3.8094,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454282827872531e-05,
"loss": 3.8005,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453444233121479e-05,
"loss": 3.8158,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452605638370427e-05,
"loss": 3.8096,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451767043619375e-05,
"loss": 3.8213,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450928448868323e-05,
"loss": 3.8164,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450091491997644e-05,
"loss": 3.8063,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449252897246593e-05,
"loss": 3.8005,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448414302495541e-05,
"loss": 3.8181,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447575707744489e-05,
"loss": 3.8001,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446737112993436e-05,
"loss": 3.7955,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.4459001561227577e-05,
"loss": 3.8146,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.4450615613717056e-05,
"loss": 3.813,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.4442229666206536e-05,
"loss": 3.7968,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443384371869601e-05,
"loss": 3.7964,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.4425474149989225e-05,
"loss": 3.7957,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.4417088202478705e-05,
"loss": 3.8143,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440870225496818e-05,
"loss": 3.8086,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.4400316307457665e-05,
"loss": 3.8061,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.4391930359947145e-05,
"loss": 3.8126,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438356079124036e-05,
"loss": 3.8104,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.4375174843729834e-05,
"loss": 3.8149,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.4366788896219314e-05,
"loss": 3.7975,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.4358402948708794e-05,
"loss": 3.8058,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435003338000201e-05,
"loss": 3.806,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434164743249148e-05,
"loss": 3.7947,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433326148498096e-05,
"loss": 3.8207,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432487553747044e-05,
"loss": 3.8034,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431648958995992e-05,
"loss": 3.8091,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430812002125313e-05,
"loss": 3.8142,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429973407374262e-05,
"loss": 3.795,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.42913481262321e-05,
"loss": 3.7995,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428296217872158e-05,
"loss": 3.8001,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427459261001479e-05,
"loss": 3.802,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426620666250427e-05,
"loss": 3.8039,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425782071499375e-05,
"loss": 3.8021,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424943476748323e-05,
"loss": 3.8054,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424106519877644e-05,
"loss": 3.8069,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423269563006965e-05,
"loss": 3.796,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224309682559126e-05,
"loss": 3.801,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4215923735048606e-05,
"loss": 3.8026,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207537787538086e-05,
"loss": 3.8138,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419915184002757e-05,
"loss": 3.8018,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419076589251705e-05,
"loss": 3.7945,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418237994500653e-05,
"loss": 3.8058,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417399399749601e-05,
"loss": 3.8001,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416562442878922e-05,
"loss": 3.8171,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.41572384812787e-05,
"loss": 3.8022,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414885253376818e-05,
"loss": 3.7974,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414046658625766e-05,
"loss": 3.7932,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413209701755087e-05,
"loss": 3.8061,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412371107004035e-05,
"loss": 3.7788,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411532512252983e-05,
"loss": 3.7925,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410693917501931e-05,
"loss": 3.7999,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409855322750879e-05,
"loss": 3.7979,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.4090200037605735e-05,
"loss": 3.7866,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081814090095215e-05,
"loss": 3.7878,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.4073428142584695e-05,
"loss": 3.7928,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.4065042195074175e-05,
"loss": 3.8102,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.4056656247563655e-05,
"loss": 3.7969,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.4048270300053135e-05,
"loss": 3.8006,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.4039884352542615e-05,
"loss": 3.8012,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.4031498405032095e-05,
"loss": 3.806,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.4023128836325304e-05,
"loss": 3.7992,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.4014742888814784e-05,
"loss": 3.7859,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.4006356941304264e-05,
"loss": 3.7956,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.3997970993793744e-05,
"loss": 3.8003,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398960142508696e-05,
"loss": 3.7827,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398121547757644e-05,
"loss": 3.7858,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397282953006592e-05,
"loss": 3.7901,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.39644435825554e-05,
"loss": 3.7961,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395607401384861e-05,
"loss": 3.7929,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394768806633809e-05,
"loss": 3.8035,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393930211882757e-05,
"loss": 3.7791,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393091617131705e-05,
"loss": 3.7899,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392254660261026e-05,
"loss": 3.7826,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391416065509974e-05,
"loss": 3.8067,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390577470758922e-05,
"loss": 3.7968,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.38973887600787e-05,
"loss": 3.7974,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388900281256818e-05,
"loss": 3.7789,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.3880633243861394e-05,
"loss": 3.7989,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872247296350874e-05,
"loss": 3.8028,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3863861348840353e-05,
"loss": 3.7915,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855475401329833e-05,
"loss": 3.789,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384710583262304e-05,
"loss": 3.7976,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383871988511252e-05,
"loss": 3.7914,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830333937602e-05,
"loss": 3.8049,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382194799009148e-05,
"loss": 3.7811,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381357842138469e-05,
"loss": 3.7876,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380519247387417e-05,
"loss": 3.7858,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379680652636365e-05,
"loss": 3.7782,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378842057885313e-05,
"loss": 3.7937,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378005101014635e-05,
"loss": 3.7894,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377166506263583e-05,
"loss": 3.7931,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376327911512531e-05,
"loss": 3.7875,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375489316761479e-05,
"loss": 3.7878,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.885859251022339,
"eval_runtime": 310.1674,
"eval_samples_per_second": 1230.275,
"eval_steps_per_second": 38.447,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.3746523598907996e-05,
"loss": 3.783,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.3738137651397476e-05,
"loss": 3.7718,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.3729751703886956e-05,
"loss": 3.7975,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.3721365756376436e-05,
"loss": 3.7858,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.3712996187669645e-05,
"loss": 3.8,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.3704610240159125e-05,
"loss": 3.7811,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.3696224292648605e-05,
"loss": 3.7745,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.3687838345138085e-05,
"loss": 3.7695,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.36794687764313e-05,
"loss": 3.7827,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367108282892078e-05,
"loss": 3.7887,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366269688141026e-05,
"loss": 3.7845,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.3654310933899734e-05,
"loss": 3.7949,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.364594136519295e-05,
"loss": 3.7765,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.363755541768243e-05,
"loss": 3.7824,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.362916947017191e-05,
"loss": 3.7729,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.362078352266138e-05,
"loss": 3.767,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.361239757515086e-05,
"loss": 3.7779,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.360401162764034e-05,
"loss": 3.7765,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.359562568012982e-05,
"loss": 3.7715,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.35872397326193e-05,
"loss": 3.7859,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.357887016391252e-05,
"loss": 3.7836,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.3570484216402e-05,
"loss": 3.78,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.356209826889148e-05,
"loss": 3.7799,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.355371232138096e-05,
"loss": 3.7823,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.354534275267417e-05,
"loss": 3.7688,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.353695680516365e-05,
"loss": 3.7831,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.352857085765313e-05,
"loss": 3.7712,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.352018491014261e-05,
"loss": 3.772,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.3511815341435817e-05,
"loss": 3.7728,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.3503429393925297e-05,
"loss": 3.7687,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.3495043446414777e-05,
"loss": 3.7787,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.3486657498904256e-05,
"loss": 3.7793,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.347828793019747e-05,
"loss": 3.7805,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.346990198268695e-05,
"loss": 3.7705,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.346151603517643e-05,
"loss": 3.7658,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345313008766591e-05,
"loss": 3.7795,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344476051895912e-05,
"loss": 3.7691,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.34363745714486e-05,
"loss": 3.7546,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.342798862393808e-05,
"loss": 3.7646,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.341960267642756e-05,
"loss": 3.7616,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.341123310772077e-05,
"loss": 3.7687,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.340284716021025e-05,
"loss": 3.7767,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.339446121269973e-05,
"loss": 3.7689,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338607526518921e-05,
"loss": 3.771,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.3377705696482426e-05,
"loss": 3.7752,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.3369319748971906e-05,
"loss": 3.7667,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.3360933801461386e-05,
"loss": 3.7689,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.3352547853950866e-05,
"loss": 3.7637,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.3344178285244075e-05,
"loss": 3.7461,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.3335792337733555e-05,
"loss": 3.7772,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.3327406390223035e-05,
"loss": 3.763,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.3319020442712515e-05,
"loss": 3.771,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.3310650874005724e-05,
"loss": 3.7628,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.3302264926495204e-05,
"loss": 3.7602,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.3293878978984684e-05,
"loss": 3.7551,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.3285493031474164e-05,
"loss": 3.7633,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.327712346276738e-05,
"loss": 3.7645,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326873751525686e-05,
"loss": 3.77,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326035156774634e-05,
"loss": 3.7644,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.325196562023582e-05,
"loss": 3.7625,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.324359605152903e-05,
"loss": 3.7504,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.323521010401851e-05,
"loss": 3.7729,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322682415650799e-05,
"loss": 3.7515,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.321843820899747e-05,
"loss": 3.749,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.321006864029068e-05,
"loss": 3.7666,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.320168269278016e-05,
"loss": 3.7639,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.319329674526964e-05,
"loss": 3.7459,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.318491079775912e-05,
"loss": 3.7526,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.317654122905233e-05,
"loss": 3.746,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.316815528154181e-05,
"loss": 3.768,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.315976933403129e-05,
"loss": 3.7604,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.315138338652077e-05,
"loss": 3.7605,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.314301381781398e-05,
"loss": 3.7619,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313462787030346e-05,
"loss": 3.762,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.312624192279294e-05,
"loss": 3.7708,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311785597528242e-05,
"loss": 3.7468,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310948640657563e-05,
"loss": 3.7643,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310110045906511e-05,
"loss": 3.7556,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.309271451155459e-05,
"loss": 3.7475,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308432856404407e-05,
"loss": 3.7661,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.307595899533729e-05,
"loss": 3.762,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.306757304782677e-05,
"loss": 3.7614,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.305918710031625e-05,
"loss": 3.7681,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.305080115280573e-05,
"loss": 3.7482,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.3042431584098936e-05,
"loss": 3.7525,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.3034045636588416e-05,
"loss": 3.7515,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.3025659689077896e-05,
"loss": 3.7564,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.3017273741567376e-05,
"loss": 3.7564,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.3008904172860585e-05,
"loss": 3.758,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.3000518225350065e-05,
"loss": 3.7538,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.2992132277839545e-05,
"loss": 3.7647,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.2983746330329025e-05,
"loss": 3.752,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.297537676162224e-05,
"loss": 3.7541,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.296699081411172e-05,
"loss": 3.7587,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.29586048666012e-05,
"loss": 3.7653,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.295021891909068e-05,
"loss": 3.7596,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294184935038389e-05,
"loss": 3.7457,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293346340287337e-05,
"loss": 3.7605,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.292507745536285e-05,
"loss": 3.7567,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.291669150785233e-05,
"loss": 3.7655,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.290832193914554e-05,
"loss": 3.7567,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.289993599163502e-05,
"loss": 3.7535,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.28915500441245e-05,
"loss": 3.7446,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288316409661398e-05,
"loss": 3.7646,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.2874794527907194e-05,
"loss": 3.7345,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.2866408580396674e-05,
"loss": 3.75,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.2858022632886154e-05,
"loss": 3.7529,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.2849636685375634e-05,
"loss": 3.7505,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284128349547257e-05,
"loss": 3.7449,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.283289754796205e-05,
"loss": 3.7435,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.282451160045153e-05,
"loss": 3.7488,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281612565294101e-05,
"loss": 3.764,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.280773970543049e-05,
"loss": 3.7542,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.279935375791997e-05,
"loss": 3.7507,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.279096781040945e-05,
"loss": 3.759,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.278258186289893e-05,
"loss": 3.7623,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.277421229419215e-05,
"loss": 3.7557,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276582634668163e-05,
"loss": 3.7426,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.275744039917111e-05,
"loss": 3.7521,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.274905445166059e-05,
"loss": 3.7545,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.27406848829538e-05,
"loss": 3.7375,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273229893544328e-05,
"loss": 3.7392,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.272391298793276e-05,
"loss": 3.7493,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.271552704042223e-05,
"loss": 3.7488,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.2707157471715446e-05,
"loss": 3.7489,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.2698771524204926e-05,
"loss": 3.7578,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.2690385576694406e-05,
"loss": 3.7401,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.2681999629183886e-05,
"loss": 3.7435,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.26736300604771e-05,
"loss": 3.7442,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.266524411296658e-05,
"loss": 3.7572,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.2656858165456055e-05,
"loss": 3.7521,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.2648472217945535e-05,
"loss": 3.7529,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.264010264923875e-05,
"loss": 3.7403,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.263171670172823e-05,
"loss": 3.7539,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.2623330754217704e-05,
"loss": 3.7573,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.2614944806707184e-05,
"loss": 3.749,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.26065752380004e-05,
"loss": 3.7462,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.259818929048988e-05,
"loss": 3.7533,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.258980334297936e-05,
"loss": 3.7473,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.258141739546884e-05,
"loss": 3.7654,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.2573047826762055e-05,
"loss": 3.7363,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256466187925153e-05,
"loss": 3.7466,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255627593174101e-05,
"loss": 3.7364,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254788998423049e-05,
"loss": 3.7376,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.2539520415523704e-05,
"loss": 3.7528,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253113446801318e-05,
"loss": 3.7424,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252274852050266e-05,
"loss": 3.7575,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251436257299214e-05,
"loss": 3.7369,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250599300428535e-05,
"loss": 3.7506,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 3.8703465461730957,
"eval_runtime": 308.3851,
"eval_samples_per_second": 1237.385,
"eval_steps_per_second": 38.669,
"step": 457920
},
{
"epoch": 0.0,
"learning_rate": 4.2497607056774826e-05,
"loss": 3.7521,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.248922110926431e-05,
"loss": 3.7261,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.248083516175379e-05,
"loss": 3.7522,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.247244921424327e-05,
"loss": 3.7465,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.246406326673275e-05,
"loss": 3.7556,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.245567731922223e-05,
"loss": 3.7373,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.244729137171171e-05,
"loss": 3.7306,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.243890542420119e-05,
"loss": 3.7301,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.24305358554944e-05,
"loss": 3.7415,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.242214990798388e-05,
"loss": 3.7442,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.241376396047336e-05,
"loss": 3.7436,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.240537801296284e-05,
"loss": 3.7521,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239702482305978e-05,
"loss": 3.739,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238863887554927e-05,
"loss": 3.7388,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.238025292803875e-05,
"loss": 3.7304,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237186698052823e-05,
"loss": 3.7235,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.236348103301771e-05,
"loss": 3.7389,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.235509508550719e-05,
"loss": 3.7325,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.234670913799667e-05,
"loss": 3.7314,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.2338323190486147e-05,
"loss": 3.7443,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.2329953621779356e-05,
"loss": 3.7461,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.2321567674268836e-05,
"loss": 3.7373,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.2313181726758316e-05,
"loss": 3.7375,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.2304795779247796e-05,
"loss": 3.7386,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.2296426210541005e-05,
"loss": 3.7323,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.2288040263030485e-05,
"loss": 3.7382,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.2279654315519965e-05,
"loss": 3.7297,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.227126836800945e-05,
"loss": 3.7336,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.226289879930266e-05,
"loss": 3.7317,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.225451285179214e-05,
"loss": 3.7307,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.224612690428162e-05,
"loss": 3.7325,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.22377409567711e-05,
"loss": 3.7366,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.222937138806431e-05,
"loss": 3.7397,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.222098544055379e-05,
"loss": 3.7351,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.221259949304327e-05,
"loss": 3.7238,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.220421354553275e-05,
"loss": 3.7382,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.219584397682596e-05,
"loss": 3.7322,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.218745802931544e-05,
"loss": 3.7169,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.217907208180492e-05,
"loss": 3.7227,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.21706861342944e-05,
"loss": 3.7219,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.2162316565587614e-05,
"loss": 3.727,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.2153930618077094e-05,
"loss": 3.735,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.2145544670566574e-05,
"loss": 3.7283,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.2137158723056054e-05,
"loss": 3.7349,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.212878915434926e-05,
"loss": 3.7374,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.212040320683874e-05,
"loss": 3.724,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.211201725932822e-05,
"loss": 3.7278,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.21036313118177e-05,
"loss": 3.7282,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.209526174311091e-05,
"loss": 3.7015,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.208687579560039e-05,
"loss": 3.7421,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.207848984808987e-05,
"loss": 3.7212,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.207010390057935e-05,
"loss": 3.7364,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.206173433187257e-05,
"loss": 3.7183,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.205334838436205e-05,
"loss": 3.7246,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.204496243685153e-05,
"loss": 3.7132,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.203657648934101e-05,
"loss": 3.722,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.202820692063422e-05,
"loss": 3.7255,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.20198209731237e-05,
"loss": 3.7342,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.2011435025613177e-05,
"loss": 3.7325,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.2003065456906386e-05,
"loss": 3.7165,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.1994679509395866e-05,
"loss": 3.711,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.1986293561885346e-05,
"loss": 3.7386,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.1977907614374826e-05,
"loss": 3.7102,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.196953804566804e-05,
"loss": 3.7067,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196115209815752e-05,
"loss": 3.726,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.1952766150647e-05,
"loss": 3.7304,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.194438020313648e-05,
"loss": 3.7047,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.193601063442969e-05,
"loss": 3.7139,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.192762468691917e-05,
"loss": 3.7089,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.191923873940865e-05,
"loss": 3.7262,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.191085279189813e-05,
"loss": 3.724,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.190248322319134e-05,
"loss": 3.7224,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.189409727568082e-05,
"loss": 3.72,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.18857113281703e-05,
"loss": 3.7246,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.187732538065978e-05,
"loss": 3.7353,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.1868955811952995e-05,
"loss": 3.708,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.1860569864442475e-05,
"loss": 3.7253,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.1852183916931955e-05,
"loss": 3.7212,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.1843797969421435e-05,
"loss": 3.7089,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.1835428400714644e-05,
"loss": 3.7259,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.1827042453204124e-05,
"loss": 3.7255,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.1818656505693604e-05,
"loss": 3.7238,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.181027055818308e-05,
"loss": 3.7299,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.180190098947629e-05,
"loss": 3.7078,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.179351504196577e-05,
"loss": 3.7164,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.178512909445525e-05,
"loss": 3.7149,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.177674314694473e-05,
"loss": 3.7186,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.176837357823795e-05,
"loss": 3.7169,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.175998763072743e-05,
"loss": 3.7247,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.175160168321691e-05,
"loss": 3.7103,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.174321573570638e-05,
"loss": 3.7289,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.17348461669996e-05,
"loss": 3.7175,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.172646021948908e-05,
"loss": 3.7155,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.171807427197855e-05,
"loss": 3.7224,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.170970470327177e-05,
"loss": 3.7251,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.170131875576125e-05,
"loss": 3.7264,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.169293280825073e-05,
"loss": 3.7077,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.1684546860740207e-05,
"loss": 3.7208,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.1676160913229687e-05,
"loss": 3.7192,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.1667774965719167e-05,
"loss": 3.7259,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.1659389018208646e-05,
"loss": 3.7214,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.1651003070698126e-05,
"loss": 3.7137,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.1642633501991336e-05,
"loss": 3.7123,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.1634247554480815e-05,
"loss": 3.723,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.1625861606970295e-05,
"loss": 3.6985,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.1617475659459775e-05,
"loss": 3.7119,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.1609106090752984e-05,
"loss": 3.7152,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.1600720143242464e-05,
"loss": 3.7156,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.1592350574535674e-05,
"loss": 3.7066,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.158396462702516e-05,
"loss": 3.7103,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.157557867951464e-05,
"loss": 3.7122,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.156719273200412e-05,
"loss": 3.7252,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.15588067844936e-05,
"loss": 3.7201,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.155042083698308e-05,
"loss": 3.7112,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.154205126827629e-05,
"loss": 3.7223,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.153366532076577e-05,
"loss": 3.7255,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.152527937325525e-05,
"loss": 3.7213,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.151689342574473e-05,
"loss": 3.7035,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.150850747823421e-05,
"loss": 3.7145,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.150012153072369e-05,
"loss": 3.7201,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.149173558321317e-05,
"loss": 3.6999,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.148334963570265e-05,
"loss": 3.7029,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.147498006699586e-05,
"loss": 3.7132,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.1466594119485345e-05,
"loss": 3.7085,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.1458208171974825e-05,
"loss": 3.7148,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.1449822224464305e-05,
"loss": 3.7219,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.1441452655757514e-05,
"loss": 3.7073,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.1433066708246994e-05,
"loss": 3.7062,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.1424680760736474e-05,
"loss": 3.7115,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.1416294813225954e-05,
"loss": 3.7196,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.140792524451916e-05,
"loss": 3.714,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.139953929700864e-05,
"loss": 3.7194,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.139115334949812e-05,
"loss": 3.7018,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.13827674019876e-05,
"loss": 3.7175,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.137439783328081e-05,
"loss": 3.721,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.136601188577029e-05,
"loss": 3.712,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.135762593825978e-05,
"loss": 3.7144,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.134923999074926e-05,
"loss": 3.7149,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.134087042204247e-05,
"loss": 3.7097,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.133248447453195e-05,
"loss": 3.7278,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.132409852702143e-05,
"loss": 3.704,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.131571257951091e-05,
"loss": 3.7103,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.1307343010804116e-05,
"loss": 3.703,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.1298957063293596e-05,
"loss": 3.7026,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.1290571115783076e-05,
"loss": 3.713,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.1282185168272556e-05,
"loss": 3.7101,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.1273815599565765e-05,
"loss": 3.7192,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.1265429652055245e-05,
"loss": 3.7031,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.125704370454473e-05,
"loss": 3.7161,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 3.8606925010681152,
"eval_runtime": 312.732,
"eval_samples_per_second": 1220.185,
"eval_steps_per_second": 38.132,
"step": 534240
},
{
"epoch": 1.0,
"learning_rate": 4.124865775703421e-05,
"loss": 3.7031,
"step": 534528
},
{
"epoch": 1.0,
"learning_rate": 4.124028818832742e-05,
"loss": 3.6931,
"step": 535040
},
{
"epoch": 1.0,
"learning_rate": 4.12319022408169e-05,
"loss": 3.714,
"step": 535552
},
{
"epoch": 1.0,
"learning_rate": 4.122351629330638e-05,
"loss": 3.7099,
"step": 536064
},
{
"epoch": 1.0,
"learning_rate": 4.121513034579586e-05,
"loss": 3.7182,
"step": 536576
},
{
"epoch": 1.0,
"learning_rate": 4.120676077708907e-05,
"loss": 3.7051,
"step": 537088
},
{
"epoch": 1.0,
"learning_rate": 4.119837482957855e-05,
"loss": 3.6997,
"step": 537600
},
{
"epoch": 1.0,
"learning_rate": 4.118998888206803e-05,
"loss": 3.6976,
"step": 538112
},
{
"epoch": 1.0,
"learning_rate": 4.118160293455751e-05,
"loss": 3.7067,
"step": 538624
},
{
"epoch": 1.0,
"learning_rate": 4.117323336585072e-05,
"loss": 3.7062,
"step": 539136
},
{
"epoch": 1.0,
"learning_rate": 4.11648474183402e-05,
"loss": 3.7083,
"step": 539648
},
{
"epoch": 1.0,
"learning_rate": 4.1156461470829686e-05,
"loss": 3.7163,
"step": 540160
},
{
"epoch": 1.0,
"learning_rate": 4.1148091902122895e-05,
"loss": 3.7034,
"step": 540672
},
{
"epoch": 1.0,
"learning_rate": 4.1139705954612375e-05,
"loss": 3.7046,
"step": 541184
},
{
"epoch": 1.0,
"learning_rate": 4.1131320007101855e-05,
"loss": 3.6967,
"step": 541696
},
{
"epoch": 1.0,
"learning_rate": 4.1122934059591335e-05,
"loss": 3.6886,
"step": 542208
},
{
"epoch": 1.0,
"learning_rate": 4.111454811208081e-05,
"loss": 3.7031,
"step": 542720
},
{
"epoch": 1.0,
"learning_rate": 4.110616216457029e-05,
"loss": 3.7016,
"step": 543232
},
{
"epoch": 1.0,
"learning_rate": 4.109777621705977e-05,
"loss": 3.6971,
"step": 543744
},
{
"epoch": 1.0,
"learning_rate": 4.108939026954925e-05,
"loss": 3.7009,
"step": 544256
},
{
"epoch": 1.0,
"learning_rate": 4.108102070084246e-05,
"loss": 3.7183,
"step": 544768
},
{
"epoch": 1.0,
"learning_rate": 4.107263475333194e-05,
"loss": 3.7025,
"step": 545280
},
{
"epoch": 1.0,
"learning_rate": 4.1064248805821423e-05,
"loss": 3.7024,
"step": 545792
},
{
"epoch": 1.0,
"learning_rate": 4.1055862858310903e-05,
"loss": 3.7032,
"step": 546304
},
{
"epoch": 1.0,
"learning_rate": 4.104749328960411e-05,
"loss": 3.6998,
"step": 546816
},
{
"epoch": 1.0,
"learning_rate": 4.103910734209359e-05,
"loss": 3.7049,
"step": 547328
},
{
"epoch": 1.0,
"learning_rate": 4.103072139458307e-05,
"loss": 3.6982,
"step": 547840
},
{
"epoch": 1.0,
"learning_rate": 4.102233544707255e-05,
"loss": 3.7031,
"step": 548352
},
{
"epoch": 1.0,
"learning_rate": 4.101396587836576e-05,
"loss": 3.6942,
"step": 548864
},
{
"epoch": 1.0,
"learning_rate": 4.100557993085524e-05,
"loss": 3.6943,
"step": 549376
},
{
"epoch": 1.01,
"learning_rate": 4.099719398334472e-05,
"loss": 3.6981,
"step": 549888
},
{
"epoch": 1.01,
"learning_rate": 4.09888080358342e-05,
"loss": 3.7067,
"step": 550400
},
{
"epoch": 1.01,
"learning_rate": 4.098043846712741e-05,
"loss": 3.7065,
"step": 550912
},
{
"epoch": 1.01,
"learning_rate": 4.097205251961689e-05,
"loss": 3.7007,
"step": 551424
},
{
"epoch": 1.01,
"learning_rate": 4.096366657210638e-05,
"loss": 3.6932,
"step": 551936
},
{
"epoch": 1.01,
"learning_rate": 4.095528062459586e-05,
"loss": 3.6991,
"step": 552448
},
{
"epoch": 1.01,
"learning_rate": 4.0946911055889066e-05,
"loss": 3.7001,
"step": 552960
},
{
"epoch": 1.01,
"learning_rate": 4.0938525108378546e-05,
"loss": 3.6863,
"step": 553472
},
{
"epoch": 1.01,
"learning_rate": 4.0930139160868026e-05,
"loss": 3.6868,
"step": 553984
},
{
"epoch": 1.01,
"learning_rate": 4.0921753213357506e-05,
"loss": 3.6862,
"step": 554496
},
{
"epoch": 1.01,
"learning_rate": 4.0913383644650715e-05,
"loss": 3.694,
"step": 555008
},
{
"epoch": 1.01,
"learning_rate": 4.0904997697140195e-05,
"loss": 3.698,
"step": 555520
},
{
"epoch": 1.01,
"learning_rate": 4.0896611749629675e-05,
"loss": 3.6933,
"step": 556032
},
{
"epoch": 1.01,
"learning_rate": 4.0888225802119155e-05,
"loss": 3.7024,
"step": 556544
},
{
"epoch": 1.01,
"learning_rate": 4.0879856233412364e-05,
"loss": 3.6993,
"step": 557056
},
{
"epoch": 1.01,
"learning_rate": 4.0871470285901844e-05,
"loss": 3.6934,
"step": 557568
},
{
"epoch": 1.01,
"learning_rate": 4.086308433839133e-05,
"loss": 3.6965,
"step": 558080
},
{
"epoch": 1.01,
"learning_rate": 4.085471476968454e-05,
"loss": 3.6933,
"step": 558592
},
{
"epoch": 1.01,
"learning_rate": 4.084632882217402e-05,
"loss": 3.6702,
"step": 559104
},
{
"epoch": 1.01,
"learning_rate": 4.08379428746635e-05,
"loss": 3.7061,
"step": 559616
},
{
"epoch": 1.01,
"learning_rate": 4.082955692715298e-05,
"loss": 3.6858,
"step": 560128
},
{
"epoch": 1.01,
"learning_rate": 4.082118735844619e-05,
"loss": 3.7027,
"step": 560640
},
{
"epoch": 1.01,
"learning_rate": 4.081280141093567e-05,
"loss": 3.6926,
"step": 561152
},
{
"epoch": 1.01,
"learning_rate": 4.080441546342515e-05,
"loss": 3.6895,
"step": 561664
},
{
"epoch": 1.01,
"learning_rate": 4.079602951591463e-05,
"loss": 3.6791,
"step": 562176
},
{
"epoch": 1.01,
"learning_rate": 4.078765994720784e-05,
"loss": 3.6869,
"step": 562688
},
{
"epoch": 1.01,
"learning_rate": 4.077927399969732e-05,
"loss": 3.6965,
"step": 563200
},
{
"epoch": 1.01,
"learning_rate": 4.07708880521868e-05,
"loss": 3.6954,
"step": 563712
},
{
"epoch": 1.01,
"learning_rate": 4.0762502104676284e-05,
"loss": 3.6978,
"step": 564224
},
{
"epoch": 1.01,
"learning_rate": 4.0754132535969494e-05,
"loss": 3.6894,
"step": 564736
},
{
"epoch": 1.01,
"learning_rate": 4.0745746588458974e-05,
"loss": 3.6775,
"step": 565248
},
{
"epoch": 1.01,
"learning_rate": 4.0737360640948453e-05,
"loss": 3.7041,
"step": 565760
},
{
"epoch": 1.01,
"learning_rate": 4.0728974693437933e-05,
"loss": 3.6784,
"step": 566272
},
{
"epoch": 1.01,
"learning_rate": 4.072060512473114e-05,
"loss": 3.669,
"step": 566784
},
{
"epoch": 1.01,
"learning_rate": 4.071221917722062e-05,
"loss": 3.6921,
"step": 567296
},
{
"epoch": 1.01,
"learning_rate": 4.07038332297101e-05,
"loss": 3.6974,
"step": 567808
},
{
"epoch": 1.01,
"learning_rate": 4.069544728219958e-05,
"loss": 3.6757,
"step": 568320
},
{
"epoch": 1.01,
"learning_rate": 4.068707771349279e-05,
"loss": 3.684,
"step": 568832
},
{
"epoch": 1.01,
"learning_rate": 4.067869176598227e-05,
"loss": 3.6748,
"step": 569344
},
{
"epoch": 1.01,
"learning_rate": 4.067030581847175e-05,
"loss": 3.6918,
"step": 569856
},
{
"epoch": 1.01,
"learning_rate": 4.066191987096124e-05,
"loss": 3.6939,
"step": 570368
},
{
"epoch": 1.01,
"learning_rate": 4.065355030225445e-05,
"loss": 3.6885,
"step": 570880
},
{
"epoch": 1.01,
"learning_rate": 4.064516435474393e-05,
"loss": 3.6887,
"step": 571392
},
{
"epoch": 1.01,
"learning_rate": 4.063677840723341e-05,
"loss": 3.6934,
"step": 571904
},
{
"epoch": 1.01,
"learning_rate": 4.062839245972289e-05,
"loss": 3.7014,
"step": 572416
},
{
"epoch": 1.01,
"learning_rate": 4.0620022891016096e-05,
"loss": 3.6768,
"step": 572928
},
{
"epoch": 1.01,
"learning_rate": 4.0611636943505576e-05,
"loss": 3.6941,
"step": 573440
},
{
"epoch": 1.01,
"learning_rate": 4.0603250995995056e-05,
"loss": 3.6819,
"step": 573952
},
{
"epoch": 1.01,
"learning_rate": 4.0594865048484536e-05,
"loss": 3.6806,
"step": 574464
},
{
"epoch": 1.01,
"learning_rate": 4.0586495479777745e-05,
"loss": 3.6944,
"step": 574976
},
{
"epoch": 1.01,
"learning_rate": 4.0578109532267225e-05,
"loss": 3.696,
"step": 575488
},
{
"epoch": 1.01,
"learning_rate": 4.0569723584756705e-05,
"loss": 3.6886,
"step": 576000
},
{
"epoch": 1.01,
"learning_rate": 4.056133763724619e-05,
"loss": 3.701,
"step": 576512
},
{
"epoch": 1.01,
"learning_rate": 4.05529680685394e-05,
"loss": 3.6733,
"step": 577024
},
{
"epoch": 1.01,
"learning_rate": 4.054458212102888e-05,
"loss": 3.6799,
"step": 577536
},
{
"epoch": 1.01,
"learning_rate": 4.053619617351836e-05,
"loss": 3.6838,
"step": 578048
},
{
"epoch": 1.01,
"learning_rate": 4.052781022600784e-05,
"loss": 3.6898,
"step": 578560
},
{
"epoch": 1.01,
"learning_rate": 4.051944065730105e-05,
"loss": 3.6842,
"step": 579072
},
{
"epoch": 1.01,
"learning_rate": 4.051105470979053e-05,
"loss": 3.6929,
"step": 579584
},
{
"epoch": 1.02,
"learning_rate": 4.050266876228001e-05,
"loss": 3.6792,
"step": 580096
},
{
"epoch": 1.02,
"learning_rate": 4.049428281476949e-05,
"loss": 3.6969,
"step": 580608
},
{
"epoch": 1.02,
"learning_rate": 4.04859132460627e-05,
"loss": 3.6894,
"step": 581120
},
{
"epoch": 1.02,
"learning_rate": 4.047752729855218e-05,
"loss": 3.6808,
"step": 581632
},
{
"epoch": 1.02,
"learning_rate": 4.046914135104166e-05,
"loss": 3.6884,
"step": 582144
},
{
"epoch": 1.02,
"learning_rate": 4.0460771782334875e-05,
"loss": 3.6941,
"step": 582656
},
{
"epoch": 1.02,
"learning_rate": 4.0452385834824355e-05,
"loss": 3.6934,
"step": 583168
},
{
"epoch": 1.02,
"learning_rate": 4.0443999887313835e-05,
"loss": 3.68,
"step": 583680
},
{
"epoch": 1.02,
"learning_rate": 4.0435613939803314e-05,
"loss": 3.684,
"step": 584192
},
{
"epoch": 1.02,
"learning_rate": 4.0427227992292794e-05,
"loss": 3.6864,
"step": 584704
},
{
"epoch": 1.02,
"learning_rate": 4.0418842044782274e-05,
"loss": 3.6968,
"step": 585216
},
{
"epoch": 1.02,
"learning_rate": 4.0410456097271754e-05,
"loss": 3.6913,
"step": 585728
},
{
"epoch": 1.02,
"learning_rate": 4.0402070149761234e-05,
"loss": 3.682,
"step": 586240
},
{
"epoch": 1.02,
"learning_rate": 4.039370058105444e-05,
"loss": 3.6819,
"step": 586752
},
{
"epoch": 1.02,
"learning_rate": 4.038531463354392e-05,
"loss": 3.6932,
"step": 587264
},
{
"epoch": 1.02,
"learning_rate": 4.03769286860334e-05,
"loss": 3.6632,
"step": 587776
},
{
"epoch": 1.02,
"learning_rate": 4.036854273852288e-05,
"loss": 3.6819,
"step": 588288
},
{
"epoch": 1.02,
"learning_rate": 4.036017316981609e-05,
"loss": 3.6817,
"step": 588800
},
{
"epoch": 1.02,
"learning_rate": 4.035178722230558e-05,
"loss": 3.6859,
"step": 589312
},
{
"epoch": 1.02,
"learning_rate": 4.034341765359879e-05,
"loss": 3.6731,
"step": 589824
},
{
"epoch": 1.02,
"learning_rate": 4.033503170608827e-05,
"loss": 3.6802,
"step": 590336
},
{
"epoch": 1.02,
"learning_rate": 4.032664575857775e-05,
"loss": 3.6852,
"step": 590848
},
{
"epoch": 1.02,
"learning_rate": 4.031825981106723e-05,
"loss": 3.6909,
"step": 591360
},
{
"epoch": 1.02,
"learning_rate": 4.030987386355671e-05,
"loss": 3.6863,
"step": 591872
},
{
"epoch": 1.02,
"learning_rate": 4.030148791604618e-05,
"loss": 3.6815,
"step": 592384
},
{
"epoch": 1.02,
"learning_rate": 4.02931183473394e-05,
"loss": 3.691,
"step": 592896
},
{
"epoch": 1.02,
"learning_rate": 4.028473239982888e-05,
"loss": 3.6956,
"step": 593408
},
{
"epoch": 1.02,
"learning_rate": 4.027634645231836e-05,
"loss": 3.6884,
"step": 593920
},
{
"epoch": 1.02,
"learning_rate": 4.026796050480783e-05,
"loss": 3.6723,
"step": 594432
},
{
"epoch": 1.02,
"learning_rate": 4.025957455729732e-05,
"loss": 3.6851,
"step": 594944
},
{
"epoch": 1.02,
"learning_rate": 4.02511886097868e-05,
"loss": 3.6887,
"step": 595456
},
{
"epoch": 1.02,
"learning_rate": 4.024280266227628e-05,
"loss": 3.6679,
"step": 595968
},
{
"epoch": 1.02,
"learning_rate": 4.023441671476576e-05,
"loss": 3.6739,
"step": 596480
},
{
"epoch": 1.02,
"learning_rate": 4.0226047146058966e-05,
"loss": 3.6819,
"step": 596992
},
{
"epoch": 1.02,
"learning_rate": 4.0217661198548446e-05,
"loss": 3.6808,
"step": 597504
},
{
"epoch": 1.02,
"learning_rate": 4.0209275251037926e-05,
"loss": 3.6792,
"step": 598016
},
{
"epoch": 1.02,
"learning_rate": 4.0200889303527406e-05,
"loss": 3.6903,
"step": 598528
},
{
"epoch": 1.02,
"learning_rate": 4.0192519734820615e-05,
"loss": 3.6815,
"step": 599040
},
{
"epoch": 1.02,
"learning_rate": 4.0184133787310095e-05,
"loss": 3.6732,
"step": 599552
},
{
"epoch": 1.02,
"learning_rate": 4.0175747839799575e-05,
"loss": 3.6796,
"step": 600064
},
{
"epoch": 1.02,
"learning_rate": 4.0167361892289055e-05,
"loss": 3.6932,
"step": 600576
},
{
"epoch": 1.02,
"learning_rate": 4.015899232358227e-05,
"loss": 3.6804,
"step": 601088
},
{
"epoch": 1.02,
"learning_rate": 4.015060637607175e-05,
"loss": 3.6921,
"step": 601600
},
{
"epoch": 1.02,
"learning_rate": 4.014222042856123e-05,
"loss": 3.6698,
"step": 602112
},
{
"epoch": 1.02,
"learning_rate": 4.013383448105071e-05,
"loss": 3.6866,
"step": 602624
},
{
"epoch": 1.02,
"learning_rate": 4.012546491234392e-05,
"loss": 3.6892,
"step": 603136
},
{
"epoch": 1.02,
"learning_rate": 4.011709534363713e-05,
"loss": 3.6843,
"step": 603648
},
{
"epoch": 1.02,
"learning_rate": 4.010870939612661e-05,
"loss": 3.6815,
"step": 604160
},
{
"epoch": 1.02,
"learning_rate": 4.010032344861609e-05,
"loss": 3.6843,
"step": 604672
},
{
"epoch": 1.02,
"learning_rate": 4.009193750110557e-05,
"loss": 3.6796,
"step": 605184
},
{
"epoch": 1.02,
"learning_rate": 4.008355155359505e-05,
"loss": 3.6979,
"step": 605696
},
{
"epoch": 1.02,
"learning_rate": 4.007516560608453e-05,
"loss": 3.673,
"step": 606208
},
{
"epoch": 1.02,
"learning_rate": 4.006677965857401e-05,
"loss": 3.6814,
"step": 606720
},
{
"epoch": 1.02,
"learning_rate": 4.005839371106349e-05,
"loss": 3.6761,
"step": 607232
},
{
"epoch": 1.02,
"learning_rate": 4.0050024142356704e-05,
"loss": 3.6741,
"step": 607744
},
{
"epoch": 1.02,
"learning_rate": 4.0041638194846184e-05,
"loss": 3.6767,
"step": 608256
},
{
"epoch": 1.02,
"learning_rate": 4.0033252247335664e-05,
"loss": 3.6792,
"step": 608768
},
{
"epoch": 1.02,
"learning_rate": 4.0024866299825144e-05,
"loss": 3.691,
"step": 609280
},
{
"epoch": 1.02,
"learning_rate": 4.001649673111835e-05,
"loss": 3.673,
"step": 609792
},
{
"epoch": 1.02,
"learning_rate": 4.000811078360783e-05,
"loss": 3.6852,
"step": 610304
},
{
"epoch": 1.03,
"eval_loss": 3.8535947799682617,
"eval_runtime": 310.4307,
"eval_samples_per_second": 1229.231,
"eval_steps_per_second": 38.414,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.999972483609731e-05,
"loss": 3.6847,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.999133888858679e-05,
"loss": 3.664,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.998295294107627e-05,
"loss": 3.6856,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.997456699356575e-05,
"loss": 3.682,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.996618104605523e-05,
"loss": 3.6878,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.995779509854471e-05,
"loss": 3.6727,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.994940915103419e-05,
"loss": 3.6746,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.994102320352367e-05,
"loss": 3.665,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.993265363481689e-05,
"loss": 3.6742,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.992426768730637e-05,
"loss": 3.6797,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.991588173979584e-05,
"loss": 3.6751,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.990749579228532e-05,
"loss": 3.6839,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.989914260238227e-05,
"loss": 3.6825,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.989075665487175e-05,
"loss": 3.6673,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.9882370707361227e-05,
"loss": 3.665,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.9873984759850707e-05,
"loss": 3.6637,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.9865598812340187e-05,
"loss": 3.6728,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.9857212864829666e-05,
"loss": 3.672,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.9848826917319146e-05,
"loss": 3.6648,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.9840440969808626e-05,
"loss": 3.6752,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.983207140110184e-05,
"loss": 3.6865,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.9823685453591315e-05,
"loss": 3.6739,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.9815299506080795e-05,
"loss": 3.6762,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.9806913558570275e-05,
"loss": 3.6707,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.979854398986349e-05,
"loss": 3.6714,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.9790158042352964e-05,
"loss": 3.6754,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.9781772094842444e-05,
"loss": 3.664,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.9773386147331924e-05,
"loss": 3.678,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.976501657862514e-05,
"loss": 3.6635,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.975663063111461e-05,
"loss": 3.6623,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.974824468360409e-05,
"loss": 3.6721,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.973985873609358e-05,
"loss": 3.6702,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.973148916738679e-05,
"loss": 3.6753,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.972310321987627e-05,
"loss": 3.6747,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971471727236575e-05,
"loss": 3.6619,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.970633132485523e-05,
"loss": 3.6686,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.969796175614844e-05,
"loss": 3.6755,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.968957580863792e-05,
"loss": 3.6538,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.96811898611274e-05,
"loss": 3.6612,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.967280391361688e-05,
"loss": 3.6599,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.966443434491009e-05,
"loss": 3.6633,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.965604839739957e-05,
"loss": 3.6666,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.964766244988905e-05,
"loss": 3.6665,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.963929288118226e-05,
"loss": 3.6772,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.963090693367174e-05,
"loss": 3.666,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.962252098616122e-05,
"loss": 3.6691,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.96141350386507e-05,
"loss": 3.6653,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.960576546994391e-05,
"loss": 3.6653,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.959737952243339e-05,
"loss": 3.6419,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.958899357492287e-05,
"loss": 3.6779,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.958060762741235e-05,
"loss": 3.6602,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.957223805870556e-05,
"loss": 3.6731,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.956385211119504e-05,
"loss": 3.6629,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.955546616368452e-05,
"loss": 3.6632,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.9547080216174e-05,
"loss": 3.6477,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.9538710647467217e-05,
"loss": 3.6612,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.9530324699956696e-05,
"loss": 3.6714,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.9521938752446176e-05,
"loss": 3.6617,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.9513552804935656e-05,
"loss": 3.6702,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.9505183236228865e-05,
"loss": 3.6642,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.9496797288718345e-05,
"loss": 3.6425,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.9488411341207825e-05,
"loss": 3.6744,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.9480025393697305e-05,
"loss": 3.654,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.9471655824990514e-05,
"loss": 3.6437,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.9463269877479994e-05,
"loss": 3.6682,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.9454883929969474e-05,
"loss": 3.6642,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.9446497982458954e-05,
"loss": 3.6479,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.943812841375217e-05,
"loss": 3.6543,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.942974246624165e-05,
"loss": 3.6507,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.942135651873113e-05,
"loss": 3.6622,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.941297057122061e-05,
"loss": 3.6645,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.940460100251382e-05,
"loss": 3.6599,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.93962150550033e-05,
"loss": 3.664,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.938782910749278e-05,
"loss": 3.6628,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.937944315998226e-05,
"loss": 3.673,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.937107359127547e-05,
"loss": 3.6493,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.936268764376495e-05,
"loss": 3.6638,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.935430169625443e-05,
"loss": 3.6548,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.934591574874391e-05,
"loss": 3.6532,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.9337546180037124e-05,
"loss": 3.6653,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.9329160232526604e-05,
"loss": 3.6652,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.9320774285016084e-05,
"loss": 3.6621,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.9312388337505564e-05,
"loss": 3.6736,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.930401876879877e-05,
"loss": 3.6462,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.929563282128825e-05,
"loss": 3.654,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.928724687377773e-05,
"loss": 3.6544,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.927886092626721e-05,
"loss": 3.6629,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.927049135756042e-05,
"loss": 3.6547,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.92621054100499e-05,
"loss": 3.6641,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.925371946253938e-05,
"loss": 3.6548,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.924533351502886e-05,
"loss": 3.6639,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.923698032512581e-05,
"loss": 3.6612,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.922859437761529e-05,
"loss": 3.6538,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.9220208430104767e-05,
"loss": 3.6626,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.9211822482594247e-05,
"loss": 3.6651,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.9203436535083726e-05,
"loss": 3.6685,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.9195050587573206e-05,
"loss": 3.6526,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.9186664640062686e-05,
"loss": 3.653,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.9178278692552166e-05,
"loss": 3.6621,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.9169909123845375e-05,
"loss": 3.669,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.9161523176334855e-05,
"loss": 3.6607,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.9153137228824335e-05,
"loss": 3.6594,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.9144751281313815e-05,
"loss": 3.6547,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.913638171260703e-05,
"loss": 3.6608,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.912799576509651e-05,
"loss": 3.6399,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.911960981758599e-05,
"loss": 3.6589,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.911122387007547e-05,
"loss": 3.6447,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.910285430136868e-05,
"loss": 3.6599,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.909448473266189e-05,
"loss": 3.6486,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.908609878515137e-05,
"loss": 3.6591,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.907771283764085e-05,
"loss": 3.6545,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.906932689013033e-05,
"loss": 3.664,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.906094094261981e-05,
"loss": 3.6582,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.905255499510929e-05,
"loss": 3.6561,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.904416904759877e-05,
"loss": 3.6645,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.9035799478891985e-05,
"loss": 3.6656,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.9027413531381465e-05,
"loss": 3.6608,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.9019027583870945e-05,
"loss": 3.6512,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.9010641636360425e-05,
"loss": 3.6528,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.9002255688849905e-05,
"loss": 3.6627,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.8993869741339385e-05,
"loss": 3.6467,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.8985483793828865e-05,
"loss": 3.6429,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.8977114225122074e-05,
"loss": 3.6546,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.8968728277611554e-05,
"loss": 3.653,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.8960342330101034e-05,
"loss": 3.6524,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.8951956382590514e-05,
"loss": 3.6637,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.894358681388372e-05,
"loss": 3.6535,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.89352008663732e-05,
"loss": 3.6492,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.892681491886269e-05,
"loss": 3.6495,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.891842897135217e-05,
"loss": 3.6652,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.891005940264538e-05,
"loss": 3.6571,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.890167345513486e-05,
"loss": 3.6598,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.889328750762434e-05,
"loss": 3.6445,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.888490156011381e-05,
"loss": 3.6632,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.887653199140703e-05,
"loss": 3.6625,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.886814604389651e-05,
"loss": 3.6572,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.885976009638599e-05,
"loss": 3.6555,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.885137414887546e-05,
"loss": 3.6534,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884302095897241e-05,
"loss": 3.655,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.883463501146189e-05,
"loss": 3.6721,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.882624906395137e-05,
"loss": 3.6479,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.881786311644085e-05,
"loss": 3.6547,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.880949354773406e-05,
"loss": 3.6492,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.880110760022354e-05,
"loss": 3.6489,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.879272165271302e-05,
"loss": 3.6475,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.87843357052025e-05,
"loss": 3.6536,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.877594975769198e-05,
"loss": 3.6634,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.876756381018146e-05,
"loss": 3.6509,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.8759177862670934e-05,
"loss": 3.6542,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 3.849144697189331,
"eval_runtime": 303.497,
"eval_samples_per_second": 1257.314,
"eval_steps_per_second": 39.292,
"step": 686880
},
{
"epoch": 0.0,
"learning_rate": 3.8750791915160414e-05,
"loss": 3.6581,
"step": 687104
},
{
"epoch": 0.0,
"learning_rate": 3.8742405967649894e-05,
"loss": 3.6392,
"step": 687616
},
{
"epoch": 0.0,
"learning_rate": 3.873402002013938e-05,
"loss": 3.6577,
"step": 688128
},
{
"epoch": 0.0,
"learning_rate": 3.872563407262886e-05,
"loss": 3.654,
"step": 688640
},
{
"epoch": 0.0,
"learning_rate": 3.871724812511834e-05,
"loss": 3.6654,
"step": 689152
},
{
"epoch": 0.0,
"learning_rate": 3.870886217760782e-05,
"loss": 3.6454,
"step": 689664
},
{
"epoch": 0.0,
"learning_rate": 3.87004762300973e-05,
"loss": 3.6479,
"step": 690176
},
{
"epoch": 0.0,
"learning_rate": 3.869209028258678e-05,
"loss": 3.6389,
"step": 690688
},
{
"epoch": 0.0,
"learning_rate": 3.868372071387999e-05,
"loss": 3.6498,
"step": 691200
},
{
"epoch": 0.0,
"learning_rate": 3.867533476636947e-05,
"loss": 3.6535,
"step": 691712
},
{
"epoch": 0.0,
"learning_rate": 3.866694881885895e-05,
"loss": 3.6471,
"step": 692224
},
{
"epoch": 0.0,
"learning_rate": 3.865856287134843e-05,
"loss": 3.6576,
"step": 692736
},
{
"epoch": 0.0,
"learning_rate": 3.865020968144537e-05,
"loss": 3.661,
"step": 693248
},
{
"epoch": 0.0,
"learning_rate": 3.864182373393485e-05,
"loss": 3.6393,
"step": 693760
},
{
"epoch": 0.0,
"learning_rate": 3.8633437786424334e-05,
"loss": 3.6412,
"step": 694272
},
{
"epoch": 0.0,
"learning_rate": 3.8625051838913814e-05,
"loss": 3.6371,
"step": 694784
},
{
"epoch": 0.0,
"learning_rate": 3.8616665891403294e-05,
"loss": 3.6497,
"step": 695296
},
{
"epoch": 0.0,
"learning_rate": 3.8608279943892774e-05,
"loss": 3.6398,
"step": 695808
},
{
"epoch": 0.0,
"learning_rate": 3.8599893996382254e-05,
"loss": 3.6426,
"step": 696320
},
{
"epoch": 0.0,
"learning_rate": 3.8591508048871734e-05,
"loss": 3.6489,
"step": 696832
},
{
"epoch": 0.0,
"learning_rate": 3.858313848016494e-05,
"loss": 3.6585,
"step": 697344
},
{
"epoch": 0.0,
"learning_rate": 3.857475253265442e-05,
"loss": 3.65,
"step": 697856
},
{
"epoch": 0.0,
"learning_rate": 3.856638296394763e-05,
"loss": 3.6483,
"step": 698368
},
{
"epoch": 0.0,
"learning_rate": 3.855799701643711e-05,
"loss": 3.6458,
"step": 698880
},
{
"epoch": 0.0,
"learning_rate": 3.854961106892659e-05,
"loss": 3.6472,
"step": 699392
},
{
"epoch": 0.0,
"learning_rate": 3.854122512141607e-05,
"loss": 3.6508,
"step": 699904
},
{
"epoch": 0.0,
"learning_rate": 3.853283917390555e-05,
"loss": 3.6354,
"step": 700416
},
{
"epoch": 0.0,
"learning_rate": 3.852445322639503e-05,
"loss": 3.6531,
"step": 700928
},
{
"epoch": 0.0,
"learning_rate": 3.851608365768825e-05,
"loss": 3.6392,
"step": 701440
},
{
"epoch": 0.0,
"learning_rate": 3.850769771017773e-05,
"loss": 3.6366,
"step": 701952
},
{
"epoch": 0.01,
"learning_rate": 3.849931176266721e-05,
"loss": 3.6489,
"step": 702464
},
{
"epoch": 0.01,
"learning_rate": 3.849092581515669e-05,
"loss": 3.6458,
"step": 702976
},
{
"epoch": 0.01,
"learning_rate": 3.848253986764617e-05,
"loss": 3.6448,
"step": 703488
},
{
"epoch": 0.01,
"learning_rate": 3.847415392013565e-05,
"loss": 3.6536,
"step": 704000
},
{
"epoch": 0.01,
"learning_rate": 3.846576797262512e-05,
"loss": 3.6369,
"step": 704512
},
{
"epoch": 0.01,
"learning_rate": 3.84573820251146e-05,
"loss": 3.6439,
"step": 705024
},
{
"epoch": 0.01,
"learning_rate": 3.8449028835211546e-05,
"loss": 3.6497,
"step": 705536
},
{
"epoch": 0.01,
"learning_rate": 3.8440642887701026e-05,
"loss": 3.6269,
"step": 706048
},
{
"epoch": 0.01,
"learning_rate": 3.8432256940190506e-05,
"loss": 3.6382,
"step": 706560
},
{
"epoch": 0.01,
"learning_rate": 3.8423870992679986e-05,
"loss": 3.635,
"step": 707072
},
{
"epoch": 0.01,
"learning_rate": 3.84155014239732e-05,
"loss": 3.6369,
"step": 707584
},
{
"epoch": 0.01,
"learning_rate": 3.840711547646268e-05,
"loss": 3.6423,
"step": 708096
},
{
"epoch": 0.01,
"learning_rate": 3.839872952895216e-05,
"loss": 3.6378,
"step": 708608
},
{
"epoch": 0.01,
"learning_rate": 3.839034358144164e-05,
"loss": 3.6528,
"step": 709120
},
{
"epoch": 0.01,
"learning_rate": 3.838195763393112e-05,
"loss": 3.6409,
"step": 709632
},
{
"epoch": 0.01,
"learning_rate": 3.8373571686420595e-05,
"loss": 3.645,
"step": 710144
},
{
"epoch": 0.01,
"learning_rate": 3.8365185738910075e-05,
"loss": 3.6395,
"step": 710656
},
{
"epoch": 0.01,
"learning_rate": 3.8356799791399555e-05,
"loss": 3.6404,
"step": 711168
},
{
"epoch": 0.01,
"learning_rate": 3.834843022269277e-05,
"loss": 3.6205,
"step": 711680
},
{
"epoch": 0.01,
"learning_rate": 3.8340044275182244e-05,
"loss": 3.6477,
"step": 712192
},
{
"epoch": 0.01,
"learning_rate": 3.8331658327671724e-05,
"loss": 3.6332,
"step": 712704
},
{
"epoch": 0.01,
"learning_rate": 3.832327238016121e-05,
"loss": 3.6481,
"step": 713216
},
{
"epoch": 0.01,
"learning_rate": 3.831490281145442e-05,
"loss": 3.6357,
"step": 713728
},
{
"epoch": 0.01,
"learning_rate": 3.83065168639439e-05,
"loss": 3.6367,
"step": 714240
},
{
"epoch": 0.01,
"learning_rate": 3.829813091643338e-05,
"loss": 3.6266,
"step": 714752
},
{
"epoch": 0.01,
"learning_rate": 3.828974496892286e-05,
"loss": 3.6371,
"step": 715264
},
{
"epoch": 0.01,
"learning_rate": 3.828135902141234e-05,
"loss": 3.6451,
"step": 715776
},
{
"epoch": 0.01,
"learning_rate": 3.827297307390182e-05,
"loss": 3.6345,
"step": 716288
},
{
"epoch": 0.01,
"learning_rate": 3.826460350519503e-05,
"loss": 3.6508,
"step": 716800
},
{
"epoch": 0.01,
"learning_rate": 3.825621755768451e-05,
"loss": 3.6395,
"step": 717312
},
{
"epoch": 0.01,
"learning_rate": 3.824783161017399e-05,
"loss": 3.6154,
"step": 717824
},
{
"epoch": 0.01,
"learning_rate": 3.823944566266347e-05,
"loss": 3.6511,
"step": 718336
},
{
"epoch": 0.01,
"learning_rate": 3.823105971515295e-05,
"loss": 3.6314,
"step": 718848
},
{
"epoch": 0.01,
"learning_rate": 3.822267376764243e-05,
"loss": 3.6202,
"step": 719360
},
{
"epoch": 0.01,
"learning_rate": 3.821428782013191e-05,
"loss": 3.6399,
"step": 719872
},
{
"epoch": 0.01,
"learning_rate": 3.820590187262139e-05,
"loss": 3.6426,
"step": 720384
},
{
"epoch": 0.01,
"learning_rate": 3.8197532303914604e-05,
"loss": 3.6247,
"step": 720896
},
{
"epoch": 0.01,
"learning_rate": 3.8189146356404084e-05,
"loss": 3.63,
"step": 721408
},
{
"epoch": 0.01,
"learning_rate": 3.818077678769729e-05,
"loss": 3.624,
"step": 721920
},
{
"epoch": 0.01,
"learning_rate": 3.817239084018677e-05,
"loss": 3.6388,
"step": 722432
},
{
"epoch": 0.01,
"learning_rate": 3.816400489267625e-05,
"loss": 3.64,
"step": 722944
},
{
"epoch": 0.01,
"learning_rate": 3.815561894516573e-05,
"loss": 3.6326,
"step": 723456
},
{
"epoch": 0.01,
"learning_rate": 3.814723299765521e-05,
"loss": 3.6418,
"step": 723968
},
{
"epoch": 0.01,
"learning_rate": 3.813884705014469e-05,
"loss": 3.6366,
"step": 724480
},
{
"epoch": 0.01,
"learning_rate": 3.813046110263417e-05,
"loss": 3.6502,
"step": 724992
},
{
"epoch": 0.01,
"learning_rate": 3.812207515512365e-05,
"loss": 3.6269,
"step": 725504
},
{
"epoch": 0.01,
"learning_rate": 3.811370558641686e-05,
"loss": 3.6381,
"step": 726016
},
{
"epoch": 0.01,
"learning_rate": 3.810531963890634e-05,
"loss": 3.6303,
"step": 726528
},
{
"epoch": 0.01,
"learning_rate": 3.809693369139583e-05,
"loss": 3.63,
"step": 727040
},
{
"epoch": 0.01,
"learning_rate": 3.808854774388531e-05,
"loss": 3.6388,
"step": 727552
},
{
"epoch": 0.01,
"learning_rate": 3.808017817517852e-05,
"loss": 3.6389,
"step": 728064
},
{
"epoch": 0.01,
"learning_rate": 3.8071792227668e-05,
"loss": 3.6435,
"step": 728576
},
{
"epoch": 0.01,
"learning_rate": 3.806340628015748e-05,
"loss": 3.6469,
"step": 729088
},
{
"epoch": 0.01,
"learning_rate": 3.805502033264696e-05,
"loss": 3.6276,
"step": 729600
},
{
"epoch": 0.01,
"learning_rate": 3.8046650763940166e-05,
"loss": 3.6269,
"step": 730112
},
{
"epoch": 0.01,
"learning_rate": 3.8038281195233376e-05,
"loss": 3.6303,
"step": 730624
},
{
"epoch": 0.01,
"learning_rate": 3.8029895247722855e-05,
"loss": 3.6391,
"step": 731136
},
{
"epoch": 0.01,
"learning_rate": 3.8021509300212335e-05,
"loss": 3.6284,
"step": 731648
},
{
"epoch": 0.01,
"learning_rate": 3.8013123352701815e-05,
"loss": 3.6346,
"step": 732160
},
{
"epoch": 0.02,
"learning_rate": 3.8004737405191295e-05,
"loss": 3.6387,
"step": 732672
},
{
"epoch": 0.02,
"learning_rate": 3.799635145768078e-05,
"loss": 3.6366,
"step": 733184
},
{
"epoch": 0.02,
"learning_rate": 3.798798188897399e-05,
"loss": 3.6386,
"step": 733696
},
{
"epoch": 0.02,
"learning_rate": 3.797959594146347e-05,
"loss": 3.6306,
"step": 734208
},
{
"epoch": 0.02,
"learning_rate": 3.797120999395295e-05,
"loss": 3.6399,
"step": 734720
},
{
"epoch": 0.02,
"learning_rate": 3.796282404644243e-05,
"loss": 3.6399,
"step": 735232
},
{
"epoch": 0.02,
"learning_rate": 3.7954438098931904e-05,
"loss": 3.6446,
"step": 735744
},
{
"epoch": 0.02,
"learning_rate": 3.7946052151421384e-05,
"loss": 3.625,
"step": 736256
},
{
"epoch": 0.02,
"learning_rate": 3.7937666203910864e-05,
"loss": 3.634,
"step": 736768
},
{
"epoch": 0.02,
"learning_rate": 3.792929663520407e-05,
"loss": 3.6375,
"step": 737280
},
{
"epoch": 0.02,
"learning_rate": 3.792091068769355e-05,
"loss": 3.6453,
"step": 737792
},
{
"epoch": 0.02,
"learning_rate": 3.791252474018303e-05,
"loss": 3.6375,
"step": 738304
},
{
"epoch": 0.02,
"learning_rate": 3.790413879267252e-05,
"loss": 3.6359,
"step": 738816
},
{
"epoch": 0.02,
"learning_rate": 3.7895752845162e-05,
"loss": 3.6314,
"step": 739328
},
{
"epoch": 0.02,
"learning_rate": 3.788736689765148e-05,
"loss": 3.6345,
"step": 739840
},
{
"epoch": 0.02,
"learning_rate": 3.787898095014096e-05,
"loss": 3.6188,
"step": 740352
},
{
"epoch": 0.02,
"learning_rate": 3.787059500263044e-05,
"loss": 3.6279,
"step": 740864
},
{
"epoch": 0.02,
"learning_rate": 3.786222543392365e-05,
"loss": 3.6224,
"step": 741376
},
{
"epoch": 0.02,
"learning_rate": 3.785383948641313e-05,
"loss": 3.6402,
"step": 741888
},
{
"epoch": 0.02,
"learning_rate": 3.784546991770634e-05,
"loss": 3.6249,
"step": 742400
},
{
"epoch": 0.02,
"learning_rate": 3.783708397019582e-05,
"loss": 3.6296,
"step": 742912
},
{
"epoch": 0.02,
"learning_rate": 3.78286980226853e-05,
"loss": 3.6333,
"step": 743424
},
{
"epoch": 0.02,
"learning_rate": 3.782031207517478e-05,
"loss": 3.6365,
"step": 743936
},
{
"epoch": 0.02,
"learning_rate": 3.781192612766426e-05,
"loss": 3.6389,
"step": 744448
},
{
"epoch": 0.02,
"learning_rate": 3.780354018015374e-05,
"loss": 3.6315,
"step": 744960
},
{
"epoch": 0.02,
"learning_rate": 3.779515423264322e-05,
"loss": 3.6401,
"step": 745472
},
{
"epoch": 0.02,
"learning_rate": 3.7786784663936433e-05,
"loss": 3.6414,
"step": 745984
},
{
"epoch": 0.02,
"learning_rate": 3.7778398716425913e-05,
"loss": 3.6336,
"step": 746496
},
{
"epoch": 0.02,
"learning_rate": 3.777001276891539e-05,
"loss": 3.6326,
"step": 747008
},
{
"epoch": 0.02,
"learning_rate": 3.776162682140487e-05,
"loss": 3.6268,
"step": 747520
},
{
"epoch": 0.02,
"learning_rate": 3.775324087389435e-05,
"loss": 3.6358,
"step": 748032
},
{
"epoch": 0.02,
"learning_rate": 3.774485492638383e-05,
"loss": 3.6293,
"step": 748544
},
{
"epoch": 0.02,
"learning_rate": 3.773646897887331e-05,
"loss": 3.6146,
"step": 749056
},
{
"epoch": 0.02,
"learning_rate": 3.772809941016652e-05,
"loss": 3.63,
"step": 749568
},
{
"epoch": 0.02,
"learning_rate": 3.7719713462656e-05,
"loss": 3.6267,
"step": 750080
},
{
"epoch": 0.02,
"learning_rate": 3.771132751514548e-05,
"loss": 3.6322,
"step": 750592
},
{
"epoch": 0.02,
"learning_rate": 3.770294156763496e-05,
"loss": 3.6366,
"step": 751104
},
{
"epoch": 0.02,
"learning_rate": 3.769457199892817e-05,
"loss": 3.6337,
"step": 751616
},
{
"epoch": 0.02,
"learning_rate": 3.768618605141765e-05,
"loss": 3.6229,
"step": 752128
},
{
"epoch": 0.02,
"learning_rate": 3.767780010390714e-05,
"loss": 3.6269,
"step": 752640
},
{
"epoch": 0.02,
"learning_rate": 3.766941415639662e-05,
"loss": 3.6424,
"step": 753152
},
{
"epoch": 0.02,
"learning_rate": 3.766104458768983e-05,
"loss": 3.6311,
"step": 753664
},
{
"epoch": 0.02,
"learning_rate": 3.765265864017931e-05,
"loss": 3.6388,
"step": 754176
},
{
"epoch": 0.02,
"learning_rate": 3.764427269266879e-05,
"loss": 3.6172,
"step": 754688
},
{
"epoch": 0.02,
"learning_rate": 3.763588674515827e-05,
"loss": 3.6434,
"step": 755200
},
{
"epoch": 0.02,
"learning_rate": 3.7627517176451476e-05,
"loss": 3.6362,
"step": 755712
},
{
"epoch": 0.02,
"learning_rate": 3.7619131228940956e-05,
"loss": 3.6351,
"step": 756224
},
{
"epoch": 0.02,
"learning_rate": 3.7610761660234165e-05,
"loss": 3.6322,
"step": 756736
},
{
"epoch": 0.02,
"learning_rate": 3.7602375712723645e-05,
"loss": 3.6294,
"step": 757248
},
{
"epoch": 0.02,
"learning_rate": 3.7593989765213125e-05,
"loss": 3.6278,
"step": 757760
},
{
"epoch": 0.02,
"learning_rate": 3.7585603817702605e-05,
"loss": 3.6539,
"step": 758272
},
{
"epoch": 0.02,
"learning_rate": 3.757721787019209e-05,
"loss": 3.6216,
"step": 758784
},
{
"epoch": 0.02,
"learning_rate": 3.7568831922681565e-05,
"loss": 3.6327,
"step": 759296
},
{
"epoch": 0.02,
"learning_rate": 3.756046235397478e-05,
"loss": 3.6285,
"step": 759808
},
{
"epoch": 0.02,
"learning_rate": 3.755207640646426e-05,
"loss": 3.62,
"step": 760320
},
{
"epoch": 0.02,
"learning_rate": 3.7543690458953734e-05,
"loss": 3.6287,
"step": 760832
},
{
"epoch": 0.02,
"learning_rate": 3.7535304511443214e-05,
"loss": 3.63,
"step": 761344
},
{
"epoch": 0.02,
"learning_rate": 3.7526918563932694e-05,
"loss": 3.6399,
"step": 761856
},
{
"epoch": 0.02,
"learning_rate": 3.7518532616422174e-05,
"loss": 3.6291,
"step": 762368
},
{
"epoch": 0.02,
"learning_rate": 3.751016304771538e-05,
"loss": 3.6276,
"step": 762880
},
{
"epoch": 0.03,
"eval_loss": 3.846182107925415,
"eval_runtime": 302.64,
"eval_samples_per_second": 1260.874,
"eval_steps_per_second": 39.403,
"step": 763200
},
{
"epoch": 0.0,
"learning_rate": 3.750177710020486e-05,
"loss": 3.6327,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.749339115269434e-05,
"loss": 3.6157,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.748500520518383e-05,
"loss": 3.6342,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.747661925767331e-05,
"loss": 3.6339,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.746823331016279e-05,
"loss": 3.6403,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.745984736265227e-05,
"loss": 3.6253,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.745146141514175e-05,
"loss": 3.6236,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.744307546763123e-05,
"loss": 3.6169,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.743470589892444e-05,
"loss": 3.6219,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.742631995141392e-05,
"loss": 3.6321,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.74179340039034e-05,
"loss": 3.6259,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.740956443519661e-05,
"loss": 3.6364,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.740117848768609e-05,
"loss": 3.6345,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.739279254017557e-05,
"loss": 3.6181,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.738440659266505e-05,
"loss": 3.6161,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.737602064515453e-05,
"loss": 3.6134,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.7367634697644014e-05,
"loss": 3.6297,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.7359248750133494e-05,
"loss": 3.6201,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.7350862802622974e-05,
"loss": 3.6165,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.734249323391618e-05,
"loss": 3.6239,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.733410728640566e-05,
"loss": 3.6366,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.732572133889514e-05,
"loss": 3.625,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.731733539138462e-05,
"loss": 3.6307,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.7308949443874096e-05,
"loss": 3.6215,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.7300563496363576e-05,
"loss": 3.6272,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.7292177548853056e-05,
"loss": 3.626,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.7283791601342536e-05,
"loss": 3.6113,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.727542203263575e-05,
"loss": 3.6319,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.726705246392897e-05,
"loss": 3.6132,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.725866651641845e-05,
"loss": 3.6125,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.725028056890793e-05,
"loss": 3.6315,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.72418946213974e-05,
"loss": 3.6225,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.723350867388688e-05,
"loss": 3.6229,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.722512272637636e-05,
"loss": 3.6303,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.721673677886584e-05,
"loss": 3.6149,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.720835083135532e-05,
"loss": 3.6216,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.7199997641452265e-05,
"loss": 3.627,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.7191611693941745e-05,
"loss": 3.6014,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.718322574643122e-05,
"loss": 3.6173,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.7174839798920705e-05,
"loss": 3.613,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.7166453851410185e-05,
"loss": 3.6124,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.71580842827034e-05,
"loss": 3.6236,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.7149698335192874e-05,
"loss": 3.6156,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.7141312387682354e-05,
"loss": 3.6292,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.7132926440171834e-05,
"loss": 3.6182,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.7124540492661314e-05,
"loss": 3.6226,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.7116154545150794e-05,
"loss": 3.6157,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.7107768597640274e-05,
"loss": 3.6174,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.7099382650129754e-05,
"loss": 3.5996,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.709101308142296e-05,
"loss": 3.6246,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.708262713391244e-05,
"loss": 3.613,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.707424118640192e-05,
"loss": 3.6242,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.706587161769514e-05,
"loss": 3.6162,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.705748567018462e-05,
"loss": 3.6093,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.70490997226741e-05,
"loss": 3.6068,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.704071377516358e-05,
"loss": 3.6132,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.703232782765306e-05,
"loss": 3.6242,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.702394188014254e-05,
"loss": 3.6131,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.701557231143575e-05,
"loss": 3.6306,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.700718636392523e-05,
"loss": 3.619,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.699880041641471e-05,
"loss": 3.5896,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.699041446890419e-05,
"loss": 3.6289,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.698202852139367e-05,
"loss": 3.608,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.697364257388315e-05,
"loss": 3.6007,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.696525662637263e-05,
"loss": 3.6141,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.695687067886211e-05,
"loss": 3.6224,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.694850111015532e-05,
"loss": 3.6027,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.69401151626448e-05,
"loss": 3.6088,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.693172921513428e-05,
"loss": 3.6038,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.6923343267623756e-05,
"loss": 3.6118,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.691497369891697e-05,
"loss": 3.6203,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.690658775140645e-05,
"loss": 3.6088,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.689820180389593e-05,
"loss": 3.6193,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.688983223518914e-05,
"loss": 3.6128,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.688144628767862e-05,
"loss": 3.6258,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.68730603401681e-05,
"loss": 3.6054,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.686467439265758e-05,
"loss": 3.621,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.685628844514706e-05,
"loss": 3.6069,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.684790249763654e-05,
"loss": 3.6067,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.683953292892976e-05,
"loss": 3.6196,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.683114698141923e-05,
"loss": 3.6142,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.682276103390871e-05,
"loss": 3.6178,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.681437508639819e-05,
"loss": 3.6282,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.680598913888767e-05,
"loss": 3.61,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.679761957018088e-05,
"loss": 3.6013,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.678923362267036e-05,
"loss": 3.6079,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.678084767515984e-05,
"loss": 3.6176,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.677246172764932e-05,
"loss": 3.6051,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.676409215894253e-05,
"loss": 3.6167,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.6755706211432015e-05,
"loss": 3.6165,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.6747320263921495e-05,
"loss": 3.6149,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.6738934316410975e-05,
"loss": 3.6134,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.6730548368900455e-05,
"loss": 3.6073,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.6722162421389935e-05,
"loss": 3.6209,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.6713792852683144e-05,
"loss": 3.6169,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.6705406905172624e-05,
"loss": 3.6213,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.6697020957662104e-05,
"loss": 3.6095,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.6688635010151584e-05,
"loss": 3.6096,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.6680249062641064e-05,
"loss": 3.6153,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.667187949393427e-05,
"loss": 3.6229,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.666349354642375e-05,
"loss": 3.615,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.665510759891323e-05,
"loss": 3.613,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.664672165140271e-05,
"loss": 3.6141,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.66383357038922e-05,
"loss": 3.6082,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.662996613518541e-05,
"loss": 3.6013,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.662158018767489e-05,
"loss": 3.6066,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.661319424016437e-05,
"loss": 3.6013,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.660480829265385e-05,
"loss": 3.619,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.659642234514333e-05,
"loss": 3.6054,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.658805277643654e-05,
"loss": 3.6102,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.657966682892602e-05,
"loss": 3.6068,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.65712808814155e-05,
"loss": 3.6186,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.656289493390498e-05,
"loss": 3.6139,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.655450898639446e-05,
"loss": 3.6119,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.6546139417687666e-05,
"loss": 3.6175,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.653775347017715e-05,
"loss": 3.6209,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.652936752266663e-05,
"loss": 3.614,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.652098157515611e-05,
"loss": 3.6081,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.651259562764559e-05,
"loss": 3.6057,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.6504209680135066e-05,
"loss": 3.6161,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.6495823732624546e-05,
"loss": 3.6123,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.648745416391776e-05,
"loss": 3.5886,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.647906821640724e-05,
"loss": 3.6126,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.6470682268896715e-05,
"loss": 3.6086,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.6462296321386195e-05,
"loss": 3.6101,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.6453910373875675e-05,
"loss": 3.617,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.6445524426365155e-05,
"loss": 3.61,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.643715485765837e-05,
"loss": 3.604,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.642876891014785e-05,
"loss": 3.6038,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.642038296263733e-05,
"loss": 3.6232,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.641199701512681e-05,
"loss": 3.609,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.640361106761629e-05,
"loss": 3.6176,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.63952414989095e-05,
"loss": 3.5987,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.638685555139898e-05,
"loss": 3.616,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.637846960388846e-05,
"loss": 3.6152,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.637008365637794e-05,
"loss": 3.6149,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.636169770886742e-05,
"loss": 3.6133,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.635332814016063e-05,
"loss": 3.6035,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.634494219265011e-05,
"loss": 3.6116,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.633655624513959e-05,
"loss": 3.6287,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.632817029762907e-05,
"loss": 3.603,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.6319784350118555e-05,
"loss": 3.6091,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.6311398402608035e-05,
"loss": 3.6054,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.6303028833901244e-05,
"loss": 3.6046,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.6294642886390724e-05,
"loss": 3.6049,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.6286256938880204e-05,
"loss": 3.6093,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.6277870991369684e-05,
"loss": 3.6141,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.626950142266289e-05,
"loss": 3.6162,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.626111547515237e-05,
"loss": 3.6046,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 3.8445518016815186,
"eval_runtime": 304.2826,
"eval_samples_per_second": 1254.068,
"eval_steps_per_second": 39.191,
"step": 839520
},
{
"epoch": 1.0,
"learning_rate": 3.625272952764185e-05,
"loss": 3.5982,
"step": 839680
},
{
"epoch": 1.0,
"learning_rate": 3.624434358013133e-05,
"loss": 3.5942,
"step": 840192
},
{
"epoch": 1.0,
"learning_rate": 3.623595763262081e-05,
"loss": 3.6131,
"step": 840704
},
{
"epoch": 1.0,
"learning_rate": 3.622758806391402e-05,
"loss": 3.6137,
"step": 841216
},
{
"epoch": 1.0,
"learning_rate": 3.621920211640351e-05,
"loss": 3.6181,
"step": 841728
},
{
"epoch": 1.0,
"learning_rate": 3.621081616889299e-05,
"loss": 3.6078,
"step": 842240
},
{
"epoch": 1.0,
"learning_rate": 3.620243022138247e-05,
"loss": 3.6042,
"step": 842752
},
{
"epoch": 1.0,
"learning_rate": 3.619404427387195e-05,
"loss": 3.5955,
"step": 843264
},
{
"epoch": 1.0,
"learning_rate": 3.618565832636143e-05,
"loss": 3.6019,
"step": 843776
},
{
"epoch": 1.0,
"learning_rate": 3.61772723788509e-05,
"loss": 3.6031,
"step": 844288
},
{
"epoch": 1.0,
"learning_rate": 3.616890281014412e-05,
"loss": 3.6113,
"step": 844800
},
{
"epoch": 1.0,
"learning_rate": 3.61605168626336e-05,
"loss": 3.6151,
"step": 845312
},
{
"epoch": 1.0,
"learning_rate": 3.615213091512308e-05,
"loss": 3.6199,
"step": 845824
},
{
"epoch": 1.0,
"learning_rate": 3.614374496761255e-05,
"loss": 3.5923,
"step": 846336
},
{
"epoch": 1.0,
"learning_rate": 3.613535902010203e-05,
"loss": 3.6001,
"step": 846848
},
{
"epoch": 1.0,
"learning_rate": 3.612697307259151e-05,
"loss": 3.5865,
"step": 847360
},
{
"epoch": 1.0,
"learning_rate": 3.611858712508099e-05,
"loss": 3.61,
"step": 847872
},
{
"epoch": 1.0,
"learning_rate": 3.611020117757048e-05,
"loss": 3.5997,
"step": 848384
},
{
"epoch": 1.0,
"learning_rate": 3.6101831608863686e-05,
"loss": 3.5941,
"step": 848896
},
{
"epoch": 1.0,
"learning_rate": 3.60934620401569e-05,
"loss": 3.6019,
"step": 849408
},
{
"epoch": 1.0,
"learning_rate": 3.6085076092646375e-05,
"loss": 3.6195,
"step": 849920
},
{
"epoch": 1.0,
"learning_rate": 3.6076690145135855e-05,
"loss": 3.6015,
"step": 850432
},
{
"epoch": 1.0,
"learning_rate": 3.6068304197625335e-05,
"loss": 3.6105,
"step": 850944
},
{
"epoch": 1.0,
"learning_rate": 3.6059918250114815e-05,
"loss": 3.6006,
"step": 851456
},
{
"epoch": 1.0,
"learning_rate": 3.6051548681408024e-05,
"loss": 3.6069,
"step": 851968
},
{
"epoch": 1.0,
"learning_rate": 3.6043162733897504e-05,
"loss": 3.6034,
"step": 852480
},
{
"epoch": 1.0,
"learning_rate": 3.6034776786386984e-05,
"loss": 3.5939,
"step": 852992
},
{
"epoch": 1.0,
"learning_rate": 3.6026390838876464e-05,
"loss": 3.6075,
"step": 853504
},
{
"epoch": 1.0,
"learning_rate": 3.601802127016968e-05,
"loss": 3.5969,
"step": 854016
},
{
"epoch": 1.0,
"learning_rate": 3.600963532265916e-05,
"loss": 3.5933,
"step": 854528
},
{
"epoch": 1.01,
"learning_rate": 3.600124937514864e-05,
"loss": 3.6065,
"step": 855040
},
{
"epoch": 1.01,
"learning_rate": 3.599286342763812e-05,
"loss": 3.6033,
"step": 855552
},
{
"epoch": 1.01,
"learning_rate": 3.59844774801276e-05,
"loss": 3.6044,
"step": 856064
},
{
"epoch": 1.01,
"learning_rate": 3.597609153261708e-05,
"loss": 3.6102,
"step": 856576
},
{
"epoch": 1.01,
"learning_rate": 3.596770558510656e-05,
"loss": 3.5944,
"step": 857088
},
{
"epoch": 1.01,
"learning_rate": 3.595931963759604e-05,
"loss": 3.6032,
"step": 857600
},
{
"epoch": 1.01,
"learning_rate": 3.595096644769298e-05,
"loss": 3.6041,
"step": 858112
},
{
"epoch": 1.01,
"learning_rate": 3.594258050018246e-05,
"loss": 3.5828,
"step": 858624
},
{
"epoch": 1.01,
"learning_rate": 3.593419455267194e-05,
"loss": 3.5978,
"step": 859136
},
{
"epoch": 1.01,
"learning_rate": 3.592580860516142e-05,
"loss": 3.5898,
"step": 859648
},
{
"epoch": 1.01,
"learning_rate": 3.5917439036454634e-05,
"loss": 3.5907,
"step": 860160
},
{
"epoch": 1.01,
"learning_rate": 3.5909053088944114e-05,
"loss": 3.6032,
"step": 860672
},
{
"epoch": 1.01,
"learning_rate": 3.5900667141433594e-05,
"loss": 3.6045,
"step": 861184
},
{
"epoch": 1.01,
"learning_rate": 3.5892281193923074e-05,
"loss": 3.6019,
"step": 861696
},
{
"epoch": 1.01,
"learning_rate": 3.588391162521628e-05,
"loss": 3.6028,
"step": 862208
},
{
"epoch": 1.01,
"learning_rate": 3.587552567770576e-05,
"loss": 3.6001,
"step": 862720
},
{
"epoch": 1.01,
"learning_rate": 3.586713973019524e-05,
"loss": 3.5965,
"step": 863232
},
{
"epoch": 1.01,
"learning_rate": 3.585875378268472e-05,
"loss": 3.5934,
"step": 863744
},
{
"epoch": 1.01,
"learning_rate": 3.585038421397793e-05,
"loss": 3.5816,
"step": 864256
},
{
"epoch": 1.01,
"learning_rate": 3.584199826646741e-05,
"loss": 3.6012,
"step": 864768
},
{
"epoch": 1.01,
"learning_rate": 3.583361231895689e-05,
"loss": 3.5946,
"step": 865280
},
{
"epoch": 1.01,
"learning_rate": 3.582522637144637e-05,
"loss": 3.6036,
"step": 865792
},
{
"epoch": 1.01,
"learning_rate": 3.581684042393585e-05,
"loss": 3.5988,
"step": 866304
},
{
"epoch": 1.01,
"learning_rate": 3.580847085522907e-05,
"loss": 3.5909,
"step": 866816
},
{
"epoch": 1.01,
"learning_rate": 3.580008490771855e-05,
"loss": 3.5861,
"step": 867328
},
{
"epoch": 1.01,
"learning_rate": 3.579169896020803e-05,
"loss": 3.5899,
"step": 867840
},
{
"epoch": 1.01,
"learning_rate": 3.578331301269751e-05,
"loss": 3.6057,
"step": 868352
},
{
"epoch": 1.01,
"learning_rate": 3.577492706518699e-05,
"loss": 3.5874,
"step": 868864
},
{
"epoch": 1.01,
"learning_rate": 3.5766557496480196e-05,
"loss": 3.6116,
"step": 869376
},
{
"epoch": 1.01,
"learning_rate": 3.5758171548969676e-05,
"loss": 3.5988,
"step": 869888
},
{
"epoch": 1.01,
"learning_rate": 3.5749785601459156e-05,
"loss": 3.5746,
"step": 870400
},
{
"epoch": 1.01,
"learning_rate": 3.5741399653948636e-05,
"loss": 3.6042,
"step": 870912
},
{
"epoch": 1.01,
"learning_rate": 3.5733013706438116e-05,
"loss": 3.5875,
"step": 871424
},
{
"epoch": 1.01,
"learning_rate": 3.5724644137731325e-05,
"loss": 3.5803,
"step": 871936
},
{
"epoch": 1.01,
"learning_rate": 3.5716258190220805e-05,
"loss": 3.5934,
"step": 872448
},
{
"epoch": 1.01,
"learning_rate": 3.5707872242710285e-05,
"loss": 3.6011,
"step": 872960
},
{
"epoch": 1.01,
"learning_rate": 3.569948629519977e-05,
"loss": 3.5817,
"step": 873472
},
{
"epoch": 1.01,
"learning_rate": 3.569111672649298e-05,
"loss": 3.5935,
"step": 873984
},
{
"epoch": 1.01,
"learning_rate": 3.568273077898246e-05,
"loss": 3.5824,
"step": 874496
},
{
"epoch": 1.01,
"learning_rate": 3.567434483147194e-05,
"loss": 3.5916,
"step": 875008
},
{
"epoch": 1.01,
"learning_rate": 3.566595888396142e-05,
"loss": 3.6019,
"step": 875520
},
{
"epoch": 1.01,
"learning_rate": 3.565758931525463e-05,
"loss": 3.5914,
"step": 876032
},
{
"epoch": 1.01,
"learning_rate": 3.564920336774411e-05,
"loss": 3.5992,
"step": 876544
},
{
"epoch": 1.01,
"learning_rate": 3.564081742023359e-05,
"loss": 3.5945,
"step": 877056
},
{
"epoch": 1.01,
"learning_rate": 3.563243147272307e-05,
"loss": 3.6056,
"step": 877568
},
{
"epoch": 1.01,
"learning_rate": 3.562404552521255e-05,
"loss": 3.5878,
"step": 878080
},
{
"epoch": 1.01,
"learning_rate": 3.561565957770203e-05,
"loss": 3.5973,
"step": 878592
},
{
"epoch": 1.01,
"learning_rate": 3.560729000899524e-05,
"loss": 3.5868,
"step": 879104
},
{
"epoch": 1.01,
"learning_rate": 3.5598904061484726e-05,
"loss": 3.5892,
"step": 879616
},
{
"epoch": 1.01,
"learning_rate": 3.5590518113974206e-05,
"loss": 3.6005,
"step": 880128
},
{
"epoch": 1.01,
"learning_rate": 3.5582132166463686e-05,
"loss": 3.5904,
"step": 880640
},
{
"epoch": 1.01,
"learning_rate": 3.5573762597756895e-05,
"loss": 3.5997,
"step": 881152
},
{
"epoch": 1.01,
"learning_rate": 3.5565376650246375e-05,
"loss": 3.6076,
"step": 881664
},
{
"epoch": 1.01,
"learning_rate": 3.5556990702735855e-05,
"loss": 3.5923,
"step": 882176
},
{
"epoch": 1.01,
"learning_rate": 3.554860475522533e-05,
"loss": 3.5768,
"step": 882688
},
{
"epoch": 1.01,
"learning_rate": 3.554021880771481e-05,
"loss": 3.5911,
"step": 883200
},
{
"epoch": 1.01,
"learning_rate": 3.5531849239008024e-05,
"loss": 3.5949,
"step": 883712
},
{
"epoch": 1.01,
"learning_rate": 3.5523463291497504e-05,
"loss": 3.5911,
"step": 884224
},
{
"epoch": 1.01,
"learning_rate": 3.551507734398698e-05,
"loss": 3.5945,
"step": 884736
},
{
"epoch": 1.01,
"learning_rate": 3.5506691396476463e-05,
"loss": 3.6,
"step": 885248
},
{
"epoch": 1.02,
"learning_rate": 3.549830544896594e-05,
"loss": 3.593,
"step": 885760
},
{
"epoch": 1.02,
"learning_rate": 3.548993588025916e-05,
"loss": 3.5967,
"step": 886272
},
{
"epoch": 1.02,
"learning_rate": 3.548154993274863e-05,
"loss": 3.5885,
"step": 886784
},
{
"epoch": 1.02,
"learning_rate": 3.547316398523811e-05,
"loss": 3.5999,
"step": 887296
},
{
"epoch": 1.02,
"learning_rate": 3.546477803772759e-05,
"loss": 3.5963,
"step": 887808
},
{
"epoch": 1.02,
"learning_rate": 3.545639209021707e-05,
"loss": 3.6058,
"step": 888320
},
{
"epoch": 1.02,
"learning_rate": 3.544802252151028e-05,
"loss": 3.5839,
"step": 888832
},
{
"epoch": 1.02,
"learning_rate": 3.543963657399976e-05,
"loss": 3.595,
"step": 889344
},
{
"epoch": 1.02,
"learning_rate": 3.543125062648924e-05,
"loss": 3.5964,
"step": 889856
},
{
"epoch": 1.02,
"learning_rate": 3.542286467897872e-05,
"loss": 3.5971,
"step": 890368
},
{
"epoch": 1.02,
"learning_rate": 3.54144787314682e-05,
"loss": 3.5971,
"step": 890880
},
{
"epoch": 1.02,
"learning_rate": 3.540610916276142e-05,
"loss": 3.591,
"step": 891392
},
{
"epoch": 1.02,
"learning_rate": 3.53977232152509e-05,
"loss": 3.5933,
"step": 891904
},
{
"epoch": 1.02,
"learning_rate": 3.538933726774038e-05,
"loss": 3.5901,
"step": 892416
},
{
"epoch": 1.02,
"learning_rate": 3.538095132022986e-05,
"loss": 3.5867,
"step": 892928
},
{
"epoch": 1.02,
"learning_rate": 3.5372581751523066e-05,
"loss": 3.5832,
"step": 893440
},
{
"epoch": 1.02,
"learning_rate": 3.5364195804012546e-05,
"loss": 3.5861,
"step": 893952
},
{
"epoch": 1.02,
"learning_rate": 3.5355809856502026e-05,
"loss": 3.5981,
"step": 894464
},
{
"epoch": 1.02,
"learning_rate": 3.5347423908991506e-05,
"loss": 3.5898,
"step": 894976
},
{
"epoch": 1.02,
"learning_rate": 3.5339054340284715e-05,
"loss": 3.5851,
"step": 895488
},
{
"epoch": 1.02,
"learning_rate": 3.5330668392774195e-05,
"loss": 3.5848,
"step": 896000
},
{
"epoch": 1.02,
"learning_rate": 3.5322282445263675e-05,
"loss": 3.6001,
"step": 896512
},
{
"epoch": 1.02,
"learning_rate": 3.5313896497753155e-05,
"loss": 3.5961,
"step": 897024
},
{
"epoch": 1.02,
"learning_rate": 3.530552692904637e-05,
"loss": 3.5918,
"step": 897536
},
{
"epoch": 1.02,
"learning_rate": 3.529714098153585e-05,
"loss": 3.5993,
"step": 898048
},
{
"epoch": 1.02,
"learning_rate": 3.528875503402533e-05,
"loss": 3.601,
"step": 898560
},
{
"epoch": 1.02,
"learning_rate": 3.528036908651481e-05,
"loss": 3.592,
"step": 899072
},
{
"epoch": 1.02,
"learning_rate": 3.527198313900429e-05,
"loss": 3.5874,
"step": 899584
},
{
"epoch": 1.02,
"learning_rate": 3.52636135702975e-05,
"loss": 3.5891,
"step": 900096
},
{
"epoch": 1.02,
"learning_rate": 3.525522762278698e-05,
"loss": 3.5914,
"step": 900608
},
{
"epoch": 1.02,
"learning_rate": 3.524684167527646e-05,
"loss": 3.5995,
"step": 901120
},
{
"epoch": 1.02,
"learning_rate": 3.523845572776594e-05,
"loss": 3.5671,
"step": 901632
},
{
"epoch": 1.02,
"learning_rate": 3.523008615905915e-05,
"loss": 3.5911,
"step": 902144
},
{
"epoch": 1.02,
"learning_rate": 3.522170021154863e-05,
"loss": 3.5886,
"step": 902656
},
{
"epoch": 1.02,
"learning_rate": 3.521331426403811e-05,
"loss": 3.5934,
"step": 903168
},
{
"epoch": 1.02,
"learning_rate": 3.520492831652759e-05,
"loss": 3.5954,
"step": 903680
},
{
"epoch": 1.02,
"learning_rate": 3.519654236901707e-05,
"loss": 3.5921,
"step": 904192
},
{
"epoch": 1.02,
"learning_rate": 3.5188172800310284e-05,
"loss": 3.5863,
"step": 904704
},
{
"epoch": 1.02,
"learning_rate": 3.5179786852799764e-05,
"loss": 3.5808,
"step": 905216
},
{
"epoch": 1.02,
"learning_rate": 3.5171400905289244e-05,
"loss": 3.6033,
"step": 905728
},
{
"epoch": 1.02,
"learning_rate": 3.5163014957778724e-05,
"loss": 3.5897,
"step": 906240
},
{
"epoch": 1.02,
"learning_rate": 3.5154629010268204e-05,
"loss": 3.6011,
"step": 906752
},
{
"epoch": 1.02,
"learning_rate": 3.514625944156141e-05,
"loss": 3.5798,
"step": 907264
},
{
"epoch": 1.02,
"learning_rate": 3.513787349405089e-05,
"loss": 3.5948,
"step": 907776
},
{
"epoch": 1.02,
"learning_rate": 3.512948754654037e-05,
"loss": 3.6,
"step": 908288
},
{
"epoch": 1.02,
"learning_rate": 3.512110159902985e-05,
"loss": 3.5908,
"step": 908800
},
{
"epoch": 1.02,
"learning_rate": 3.511273203032306e-05,
"loss": 3.5948,
"step": 909312
},
{
"epoch": 1.02,
"learning_rate": 3.510434608281254e-05,
"loss": 3.586,
"step": 909824
},
{
"epoch": 1.02,
"learning_rate": 3.509596013530202e-05,
"loss": 3.5909,
"step": 910336
},
{
"epoch": 1.02,
"learning_rate": 3.50875741877915e-05,
"loss": 3.6073,
"step": 910848
},
{
"epoch": 1.02,
"learning_rate": 3.507918824028099e-05,
"loss": 3.5878,
"step": 911360
},
{
"epoch": 1.02,
"learning_rate": 3.50708186715742e-05,
"loss": 3.5876,
"step": 911872
},
{
"epoch": 1.02,
"learning_rate": 3.506243272406368e-05,
"loss": 3.5895,
"step": 912384
},
{
"epoch": 1.02,
"learning_rate": 3.505404677655316e-05,
"loss": 3.5835,
"step": 912896
},
{
"epoch": 1.02,
"learning_rate": 3.504566082904264e-05,
"loss": 3.5836,
"step": 913408
},
{
"epoch": 1.02,
"learning_rate": 3.503727488153211e-05,
"loss": 3.5937,
"step": 913920
},
{
"epoch": 1.02,
"learning_rate": 3.502888893402159e-05,
"loss": 3.5887,
"step": 914432
},
{
"epoch": 1.02,
"learning_rate": 3.502051936531481e-05,
"loss": 3.5958,
"step": 914944
},
{
"epoch": 1.02,
"learning_rate": 3.501213341780429e-05,
"loss": 3.587,
"step": 915456
},
{
"epoch": 1.03,
"eval_loss": 3.8449225425720215,
"eval_runtime": 303.5879,
"eval_samples_per_second": 1256.937,
"eval_steps_per_second": 39.28,
"step": 915840
},
{
"epoch": 0.0,
"learning_rate": 3.500374747029376e-05,
"loss": 3.61,
"step": 915968
},
{
"epoch": 0.0,
"learning_rate": 3.499536152278324e-05,
"loss": 3.5724,
"step": 916480
},
{
"epoch": 0.0,
"learning_rate": 3.4986975575272727e-05,
"loss": 3.59,
"step": 916992
},
{
"epoch": 0.0,
"learning_rate": 3.4978589627762207e-05,
"loss": 3.6,
"step": 917504
},
{
"epoch": 0.0,
"learning_rate": 3.4970220059055416e-05,
"loss": 3.5971,
"step": 918016
},
{
"epoch": 0.0,
"learning_rate": 3.4961834111544896e-05,
"loss": 3.5902,
"step": 918528
},
{
"epoch": 0.0,
"learning_rate": 3.4953448164034376e-05,
"loss": 3.5843,
"step": 919040
},
{
"epoch": 0.0,
"learning_rate": 3.4945062216523856e-05,
"loss": 3.5787,
"step": 919552
},
{
"epoch": 0.0,
"learning_rate": 3.4936692647817065e-05,
"loss": 3.5791,
"step": 920064
},
{
"epoch": 0.0,
"learning_rate": 3.4928306700306545e-05,
"loss": 3.585,
"step": 920576
},
{
"epoch": 0.0,
"learning_rate": 3.4919920752796025e-05,
"loss": 3.5909,
"step": 921088
},
{
"epoch": 0.0,
"learning_rate": 3.4911534805285504e-05,
"loss": 3.5955,
"step": 921600
},
{
"epoch": 0.0,
"learning_rate": 3.4903165236578714e-05,
"loss": 3.6036,
"step": 922112
},
{
"epoch": 0.0,
"learning_rate": 3.4894779289068194e-05,
"loss": 3.5706,
"step": 922624
},
{
"epoch": 0.0,
"learning_rate": 3.488639334155768e-05,
"loss": 3.5794,
"step": 923136
},
{
"epoch": 0.0,
"learning_rate": 3.487800739404716e-05,
"loss": 3.567,
"step": 923648
},
{
"epoch": 0.0,
"learning_rate": 3.486962144653664e-05,
"loss": 3.5927,
"step": 924160
},
{
"epoch": 0.0,
"learning_rate": 3.486125187782985e-05,
"loss": 3.5831,
"step": 924672
},
{
"epoch": 0.0,
"learning_rate": 3.485286593031933e-05,
"loss": 3.5759,
"step": 925184
},
{
"epoch": 0.0,
"learning_rate": 3.484447998280881e-05,
"loss": 3.5806,
"step": 925696
},
{
"epoch": 0.0,
"learning_rate": 3.483609403529829e-05,
"loss": 3.5987,
"step": 926208
},
{
"epoch": 0.0,
"learning_rate": 3.482770808778777e-05,
"loss": 3.5839,
"step": 926720
},
{
"epoch": 0.0,
"learning_rate": 3.481933851908098e-05,
"loss": 3.5921,
"step": 927232
},
{
"epoch": 0.0,
"learning_rate": 3.481095257157046e-05,
"loss": 3.5833,
"step": 927744
},
{
"epoch": 0.0,
"learning_rate": 3.480256662405994e-05,
"loss": 3.5943,
"step": 928256
},
{
"epoch": 0.0,
"learning_rate": 3.479418067654942e-05,
"loss": 3.5809,
"step": 928768
},
{
"epoch": 0.0,
"learning_rate": 3.4785811107842634e-05,
"loss": 3.5753,
"step": 929280
},
{
"epoch": 0.0,
"learning_rate": 3.4777425160332114e-05,
"loss": 3.5915,
"step": 929792
},
{
"epoch": 0.0,
"learning_rate": 3.4769039212821594e-05,
"loss": 3.5705,
"step": 930304
},
{
"epoch": 0.0,
"learning_rate": 3.4760653265311074e-05,
"loss": 3.5756,
"step": 930816
},
{
"epoch": 0.01,
"learning_rate": 3.4752267317800554e-05,
"loss": 3.5871,
"step": 931328
},
{
"epoch": 0.01,
"learning_rate": 3.4743881370290034e-05,
"loss": 3.5831,
"step": 931840
},
{
"epoch": 0.01,
"learning_rate": 3.473551180158324e-05,
"loss": 3.584,
"step": 932352
},
{
"epoch": 0.01,
"learning_rate": 3.472712585407272e-05,
"loss": 3.5917,
"step": 932864
},
{
"epoch": 0.01,
"learning_rate": 3.47187399065622e-05,
"loss": 3.5754,
"step": 933376
},
{
"epoch": 0.01,
"learning_rate": 3.471035395905168e-05,
"loss": 3.5824,
"step": 933888
},
{
"epoch": 0.01,
"learning_rate": 3.470198439034489e-05,
"loss": 3.5868,
"step": 934400
},
{
"epoch": 0.01,
"learning_rate": 3.469359844283437e-05,
"loss": 3.5661,
"step": 934912
},
{
"epoch": 0.01,
"learning_rate": 3.468521249532385e-05,
"loss": 3.5805,
"step": 935424
},
{
"epoch": 0.01,
"learning_rate": 3.467682654781333e-05,
"loss": 3.5702,
"step": 935936
},
{
"epoch": 0.01,
"learning_rate": 3.466845697910655e-05,
"loss": 3.5735,
"step": 936448
},
{
"epoch": 0.01,
"learning_rate": 3.466007103159603e-05,
"loss": 3.5807,
"step": 936960
},
{
"epoch": 0.01,
"learning_rate": 3.465168508408551e-05,
"loss": 3.5866,
"step": 937472
},
{
"epoch": 0.01,
"learning_rate": 3.464329913657499e-05,
"loss": 3.5825,
"step": 937984
},
{
"epoch": 0.01,
"learning_rate": 3.4634929567868196e-05,
"loss": 3.5842,
"step": 938496
},
{
"epoch": 0.01,
"learning_rate": 3.4626543620357676e-05,
"loss": 3.5827,
"step": 939008
},
{
"epoch": 0.01,
"learning_rate": 3.4618157672847156e-05,
"loss": 3.5795,
"step": 939520
},
{
"epoch": 0.01,
"learning_rate": 3.4609771725336636e-05,
"loss": 3.5775,
"step": 940032
},
{
"epoch": 0.01,
"learning_rate": 3.4601385777826116e-05,
"loss": 3.5614,
"step": 940544
},
{
"epoch": 0.01,
"learning_rate": 3.4593016209119325e-05,
"loss": 3.5814,
"step": 941056
},
{
"epoch": 0.01,
"learning_rate": 3.4584630261608805e-05,
"loss": 3.5783,
"step": 941568
},
{
"epoch": 0.01,
"learning_rate": 3.4576244314098285e-05,
"loss": 3.581,
"step": 942080
},
{
"epoch": 0.01,
"learning_rate": 3.45678747453915e-05,
"loss": 3.5831,
"step": 942592
},
{
"epoch": 0.01,
"learning_rate": 3.455948879788098e-05,
"loss": 3.571,
"step": 943104
},
{
"epoch": 0.01,
"learning_rate": 3.455110285037046e-05,
"loss": 3.5676,
"step": 943616
},
{
"epoch": 0.01,
"learning_rate": 3.454271690285994e-05,
"loss": 3.5692,
"step": 944128
},
{
"epoch": 0.01,
"learning_rate": 3.453433095534942e-05,
"loss": 3.5876,
"step": 944640
},
{
"epoch": 0.01,
"learning_rate": 3.452596138664263e-05,
"loss": 3.5714,
"step": 945152
},
{
"epoch": 0.01,
"learning_rate": 3.451757543913211e-05,
"loss": 3.5925,
"step": 945664
},
{
"epoch": 0.01,
"learning_rate": 3.450918949162159e-05,
"loss": 3.5765,
"step": 946176
},
{
"epoch": 0.01,
"learning_rate": 3.450080354411106e-05,
"loss": 3.5627,
"step": 946688
},
{
"epoch": 0.01,
"learning_rate": 3.449243397540428e-05,
"loss": 3.5836,
"step": 947200
},
{
"epoch": 0.01,
"learning_rate": 3.448404802789376e-05,
"loss": 3.5692,
"step": 947712
},
{
"epoch": 0.01,
"learning_rate": 3.447566208038324e-05,
"loss": 3.5629,
"step": 948224
},
{
"epoch": 0.01,
"learning_rate": 3.446727613287272e-05,
"loss": 3.5732,
"step": 948736
},
{
"epoch": 0.01,
"learning_rate": 3.4458906564165935e-05,
"loss": 3.5839,
"step": 949248
},
{
"epoch": 0.01,
"learning_rate": 3.4450520616655415e-05,
"loss": 3.5628,
"step": 949760
},
{
"epoch": 0.01,
"learning_rate": 3.4442134669144895e-05,
"loss": 3.5783,
"step": 950272
},
{
"epoch": 0.01,
"learning_rate": 3.443374872163437e-05,
"loss": 3.5599,
"step": 950784
},
{
"epoch": 0.01,
"learning_rate": 3.442536277412385e-05,
"loss": 3.5733,
"step": 951296
},
{
"epoch": 0.01,
"learning_rate": 3.4416993205417064e-05,
"loss": 3.5837,
"step": 951808
},
{
"epoch": 0.01,
"learning_rate": 3.440860725790654e-05,
"loss": 3.5747,
"step": 952320
},
{
"epoch": 0.01,
"learning_rate": 3.440022131039602e-05,
"loss": 3.5791,
"step": 952832
},
{
"epoch": 0.01,
"learning_rate": 3.43918353628855e-05,
"loss": 3.5754,
"step": 953344
},
{
"epoch": 0.01,
"learning_rate": 3.438346579417871e-05,
"loss": 3.5873,
"step": 953856
},
{
"epoch": 0.01,
"learning_rate": 3.437507984666819e-05,
"loss": 3.5684,
"step": 954368
},
{
"epoch": 0.01,
"learning_rate": 3.436669389915767e-05,
"loss": 3.5804,
"step": 954880
},
{
"epoch": 0.01,
"learning_rate": 3.435830795164715e-05,
"loss": 3.5708,
"step": 955392
},
{
"epoch": 0.01,
"learning_rate": 3.434992200413663e-05,
"loss": 3.5702,
"step": 955904
},
{
"epoch": 0.01,
"learning_rate": 3.434155243542984e-05,
"loss": 3.581,
"step": 956416
},
{
"epoch": 0.01,
"learning_rate": 3.433316648791932e-05,
"loss": 3.572,
"step": 956928
},
{
"epoch": 0.01,
"learning_rate": 3.43247805404088e-05,
"loss": 3.5849,
"step": 957440
},
{
"epoch": 0.01,
"learning_rate": 3.431639459289828e-05,
"loss": 3.5867,
"step": 957952
},
{
"epoch": 0.01,
"learning_rate": 3.430800864538776e-05,
"loss": 3.5786,
"step": 958464
},
{
"epoch": 0.01,
"learning_rate": 3.429963907668097e-05,
"loss": 3.5608,
"step": 958976
},
{
"epoch": 0.01,
"learning_rate": 3.429125312917045e-05,
"loss": 3.5722,
"step": 959488
},
{
"epoch": 0.01,
"learning_rate": 3.428286718165993e-05,
"loss": 3.5764,
"step": 960000
},
{
"epoch": 0.01,
"learning_rate": 3.427448123414941e-05,
"loss": 3.5745,
"step": 960512
},
{
"epoch": 0.01,
"learning_rate": 3.4266111665442626e-05,
"loss": 3.5749,
"step": 961024
},
{
"epoch": 0.01,
"learning_rate": 3.4257725717932106e-05,
"loss": 3.5799,
"step": 961536
},
{
"epoch": 0.02,
"learning_rate": 3.4249339770421586e-05,
"loss": 3.5762,
"step": 962048
},
{
"epoch": 0.02,
"learning_rate": 3.4240953822911066e-05,
"loss": 3.5764,
"step": 962560
},
{
"epoch": 0.02,
"learning_rate": 3.4232584254204275e-05,
"loss": 3.5707,
"step": 963072
},
{
"epoch": 0.02,
"learning_rate": 3.4224198306693755e-05,
"loss": 3.5804,
"step": 963584
},
{
"epoch": 0.02,
"learning_rate": 3.4215812359183235e-05,
"loss": 3.5806,
"step": 964096
},
{
"epoch": 0.02,
"learning_rate": 3.4207426411672715e-05,
"loss": 3.587,
"step": 964608
},
{
"epoch": 0.02,
"learning_rate": 3.4199056842965924e-05,
"loss": 3.5633,
"step": 965120
},
{
"epoch": 0.02,
"learning_rate": 3.4190670895455404e-05,
"loss": 3.5756,
"step": 965632
},
{
"epoch": 0.02,
"learning_rate": 3.4182284947944884e-05,
"loss": 3.5794,
"step": 966144
},
{
"epoch": 0.02,
"learning_rate": 3.4173899000434364e-05,
"loss": 3.5791,
"step": 966656
},
{
"epoch": 0.02,
"learning_rate": 3.416551305292385e-05,
"loss": 3.5816,
"step": 967168
},
{
"epoch": 0.02,
"learning_rate": 3.415714348421706e-05,
"loss": 3.5722,
"step": 967680
},
{
"epoch": 0.02,
"learning_rate": 3.414875753670654e-05,
"loss": 3.5731,
"step": 968192
},
{
"epoch": 0.02,
"learning_rate": 3.414037158919602e-05,
"loss": 3.5706,
"step": 968704
},
{
"epoch": 0.02,
"learning_rate": 3.41319856416855e-05,
"loss": 3.5705,
"step": 969216
},
{
"epoch": 0.02,
"learning_rate": 3.412361607297871e-05,
"loss": 3.5633,
"step": 969728
},
{
"epoch": 0.02,
"learning_rate": 3.411523012546819e-05,
"loss": 3.5689,
"step": 970240
},
{
"epoch": 0.02,
"learning_rate": 3.410684417795767e-05,
"loss": 3.5781,
"step": 970752
},
{
"epoch": 0.02,
"learning_rate": 3.409845823044715e-05,
"loss": 3.5738,
"step": 971264
},
{
"epoch": 0.02,
"learning_rate": 3.409008866174036e-05,
"loss": 3.567,
"step": 971776
},
{
"epoch": 0.02,
"learning_rate": 3.408170271422984e-05,
"loss": 3.5643,
"step": 972288
},
{
"epoch": 0.02,
"learning_rate": 3.407331676671932e-05,
"loss": 3.5815,
"step": 972800
},
{
"epoch": 0.02,
"learning_rate": 3.4064930819208804e-05,
"loss": 3.5781,
"step": 973312
},
{
"epoch": 0.02,
"learning_rate": 3.4056561250502014e-05,
"loss": 3.572,
"step": 973824
},
{
"epoch": 0.02,
"learning_rate": 3.4048175302991494e-05,
"loss": 3.5822,
"step": 974336
},
{
"epoch": 0.02,
"learning_rate": 3.4039789355480973e-05,
"loss": 3.5859,
"step": 974848
},
{
"epoch": 0.02,
"learning_rate": 3.4031403407970453e-05,
"loss": 3.5729,
"step": 975360
},
{
"epoch": 0.02,
"learning_rate": 3.402301746045993e-05,
"loss": 3.5706,
"step": 975872
},
{
"epoch": 0.02,
"learning_rate": 3.401464789175314e-05,
"loss": 3.5737,
"step": 976384
},
{
"epoch": 0.02,
"learning_rate": 3.400626194424262e-05,
"loss": 3.5758,
"step": 976896
},
{
"epoch": 0.02,
"learning_rate": 3.39978759967321e-05,
"loss": 3.5798,
"step": 977408
},
{
"epoch": 0.02,
"learning_rate": 3.398949004922158e-05,
"loss": 3.5517,
"step": 977920
},
{
"epoch": 0.02,
"learning_rate": 3.398112048051479e-05,
"loss": 3.5764,
"step": 978432
},
{
"epoch": 0.02,
"learning_rate": 3.397273453300427e-05,
"loss": 3.5711,
"step": 978944
},
{
"epoch": 0.02,
"learning_rate": 3.396434858549376e-05,
"loss": 3.5721,
"step": 979456
},
{
"epoch": 0.02,
"learning_rate": 3.395596263798324e-05,
"loss": 3.5776,
"step": 979968
},
{
"epoch": 0.02,
"learning_rate": 3.394757669047272e-05,
"loss": 3.5734,
"step": 980480
},
{
"epoch": 0.02,
"learning_rate": 3.393920712176593e-05,
"loss": 3.5686,
"step": 980992
},
{
"epoch": 0.02,
"learning_rate": 3.393082117425541e-05,
"loss": 3.564,
"step": 981504
},
{
"epoch": 0.02,
"learning_rate": 3.392243522674489e-05,
"loss": 3.5851,
"step": 982016
},
{
"epoch": 0.02,
"learning_rate": 3.391404927923437e-05,
"loss": 3.5706,
"step": 982528
},
{
"epoch": 0.02,
"learning_rate": 3.3905679710527576e-05,
"loss": 3.5837,
"step": 983040
},
{
"epoch": 0.02,
"learning_rate": 3.3897293763017056e-05,
"loss": 3.5633,
"step": 983552
},
{
"epoch": 0.02,
"learning_rate": 3.3888907815506536e-05,
"loss": 3.5773,
"step": 984064
},
{
"epoch": 0.02,
"learning_rate": 3.3880521867996016e-05,
"loss": 3.5796,
"step": 984576
},
{
"epoch": 0.02,
"learning_rate": 3.3872152299289225e-05,
"loss": 3.5723,
"step": 985088
},
{
"epoch": 0.02,
"learning_rate": 3.386376635177871e-05,
"loss": 3.5759,
"step": 985600
},
{
"epoch": 0.02,
"learning_rate": 3.385538040426819e-05,
"loss": 3.5677,
"step": 986112
},
{
"epoch": 0.02,
"learning_rate": 3.384699445675767e-05,
"loss": 3.5763,
"step": 986624
},
{
"epoch": 0.02,
"learning_rate": 3.383862488805088e-05,
"loss": 3.592,
"step": 987136
},
{
"epoch": 0.02,
"learning_rate": 3.383023894054036e-05,
"loss": 3.5719,
"step": 987648
},
{
"epoch": 0.02,
"learning_rate": 3.382185299302984e-05,
"loss": 3.5681,
"step": 988160
},
{
"epoch": 0.02,
"learning_rate": 3.381346704551932e-05,
"loss": 3.5717,
"step": 988672
},
{
"epoch": 0.02,
"learning_rate": 3.380509747681253e-05,
"loss": 3.5681,
"step": 989184
},
{
"epoch": 0.02,
"learning_rate": 3.379671152930201e-05,
"loss": 3.5634,
"step": 989696
},
{
"epoch": 0.02,
"learning_rate": 3.378832558179149e-05,
"loss": 3.5815,
"step": 990208
},
{
"epoch": 0.02,
"learning_rate": 3.377993963428097e-05,
"loss": 3.5673,
"step": 990720
},
{
"epoch": 0.02,
"learning_rate": 3.377157006557418e-05,
"loss": 3.5768,
"step": 991232
},
{
"epoch": 0.02,
"learning_rate": 3.3763184118063665e-05,
"loss": 3.5718,
"step": 991744
},
{
"epoch": 0.03,
"eval_loss": 3.8450450897216797,
"eval_runtime": 313.352,
"eval_samples_per_second": 1217.771,
"eval_steps_per_second": 38.056,
"step": 992160
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 6.868642313661972e+17,
"trial_name": null,
"trial_params": null
}