det-noun-lstm-1 / checkpoint-381600 /trainer_state.json
abhinavp's picture
Training in progress, epoch 0, checkpoint
f952cb9 verified
{
"best_metric": 4.206528663635254,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/lstm/1/checkpoints/checkpoint-381600",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 381600,
"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": 10.8218,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5559,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0623,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9945,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9491,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.9228,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7544,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994131474623009e-05,
"loss": 6.6386,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993292879871958e-05,
"loss": 6.5403,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992454285120906e-05,
"loss": 6.4647,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.991615690369854e-05,
"loss": 6.4038,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990777095618801e-05,
"loss": 6.3434,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 6.2793,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 6.2147,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 6.1649,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 6.0996,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 6.0694,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 6.0129,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.9691,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9354,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8995,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8604,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8316,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.7974,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798786396158716e-05,
"loss": 5.7765,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 5.7421,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 5.7218,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 5.6898,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6659,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6491,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6283,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 5.6119,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 5.5908,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.574,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5583,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5421,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5269,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.9689785457325684e-05,
"loss": 5.4978,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.9681399509815164e-05,
"loss": 5.4933,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4545,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4558,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.445,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 5.4419,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.4048,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.4049,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3946,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 5.3861,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.3844,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 5.3497,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3443,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3484,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3376,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.3186,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2987,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.3032,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2832,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.3044,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 5.2538,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 5.2642,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.253,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2493,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.2461,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948021866358134e-05,
"loss": 5.2242,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947183271607082e-05,
"loss": 5.2066,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.94634467685603e-05,
"loss": 5.2112,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945506082104978e-05,
"loss": 5.2224,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.1926,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943830530483247e-05,
"loss": 5.1914,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942991935732195e-05,
"loss": 5.1679,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942153340981143e-05,
"loss": 5.1679,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1796,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940477789359412e-05,
"loss": 5.1781,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.93963919460836e-05,
"loss": 5.1515,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938800599857309e-05,
"loss": 5.1636,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1613,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 5.1499,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 5.121,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 5.1278,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346109018627945e-05,
"loss": 5.1168,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.1111,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329337123606905e-05,
"loss": 5.109,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 5.1038,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.1043,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 5.0934,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295809712368554e-05,
"loss": 5.0764,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.0762,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.077,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.0674,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262265922326474e-05,
"loss": 5.0644,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.9253879974815954e-05,
"loss": 5.047,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.9245494027305433e-05,
"loss": 5.049,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923712445859864e-05,
"loss": 5.0377,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922873851108812e-05,
"loss": 5.0459,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92203525635776e-05,
"loss": 5.0333,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921196661606708e-05,
"loss": 5.0326,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920359704736029e-05,
"loss": 5.0295,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 5.0158,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918682515233926e-05,
"loss": 5.0114,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917843920482874e-05,
"loss": 5.004,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917005325731822e-05,
"loss": 4.9997,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916168368861143e-05,
"loss": 5.0019,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915329774110091e-05,
"loss": 4.9841,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914491179359039e-05,
"loss": 4.9896,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913652584607987e-05,
"loss": 4.9849,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912813989856935e-05,
"loss": 4.9712,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9678,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9627,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9615,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.953,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908624291862421e-05,
"loss": 4.9556,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907785697111369e-05,
"loss": 4.9472,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906947102360317e-05,
"loss": 4.9346,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906108507609265e-05,
"loss": 4.9471,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905269912858213e-05,
"loss": 4.9293,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904431318107161e-05,
"loss": 4.9351,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903592723356109e-05,
"loss": 4.9294,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.90275576648543e-05,
"loss": 4.9237,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.9188,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901080214863699e-05,
"loss": 4.9147,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.9282,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899403025361595e-05,
"loss": 4.9155,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.898564430610543e-05,
"loss": 4.8993,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897725835859491e-05,
"loss": 4.8952,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968872411084396e-05,
"loss": 4.893,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.896048646357387e-05,
"loss": 4.8866,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.8806,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.8835,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.8701,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8704,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8653,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.8835,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890181758860769e-05,
"loss": 4.8765,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889343164109717e-05,
"loss": 4.8585,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888504569358665e-05,
"loss": 4.8557,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.8876659746076134e-05,
"loss": 4.8507,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.8606,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885990422985882e-05,
"loss": 4.8516,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515182823483e-05,
"loss": 4.8508,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.8454,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883474638732726e-05,
"loss": 4.8408,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882637681862047e-05,
"loss": 4.8373,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881799087110995e-05,
"loss": 4.8266,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880960492359943e-05,
"loss": 4.8327,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880121897608891e-05,
"loss": 4.8233,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.8119,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.8241,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.8191,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876769156485057e-05,
"loss": 4.8206,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875930561734005e-05,
"loss": 4.8077,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875091966982953e-05,
"loss": 4.8048,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.769217491149902,
"eval_runtime": 294.8081,
"eval_samples_per_second": 1294.371,
"eval_steps_per_second": 40.45,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.8008,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873416415361222e-05,
"loss": 4.7957,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.87257782061017e-05,
"loss": 4.8091,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871739225859118e-05,
"loss": 4.7935,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.7987,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.7799,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.7946,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.777,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.7792,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.7773,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7844,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.778,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.7601,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.7635,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.755,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.7554,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.757,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.7495,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.7524,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858326623483405e-05,
"loss": 4.7629,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857488028732352e-05,
"loss": 4.749,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856649433981301e-05,
"loss": 4.747,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855810839230249e-05,
"loss": 4.741,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.85497388235957e-05,
"loss": 4.7554,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.7237,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.7378,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.7252,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851621141235735e-05,
"loss": 4.7271,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850782546484683e-05,
"loss": 4.7218,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849943951733631e-05,
"loss": 4.7151,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.7219,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.729,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.7163,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.7204,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.7054,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.7144,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844077064237013e-05,
"loss": 4.6999,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.7091,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842399874734909e-05,
"loss": 4.6844,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841561279983857e-05,
"loss": 4.6963,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840722685232805e-05,
"loss": 4.6912,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839884090481753e-05,
"loss": 4.7056,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839045495730701e-05,
"loss": 4.6776,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.6938,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.6894,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836531349357918e-05,
"loss": 4.6822,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835692754606866e-05,
"loss": 4.6928,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.6675,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.6694,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.685,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.6719,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.6686,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.6622,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.6671,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.6565,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.6766,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.6456,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.6555,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.6529,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.653,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.6605,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.6484,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822281790111527e-05,
"loss": 4.6284,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821443195360475e-05,
"loss": 4.6356,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.6593,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819766005858371e-05,
"loss": 4.633,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.634,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818092092117013e-05,
"loss": 4.626,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817253497365961e-05,
"loss": 4.627,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816416540495282e-05,
"loss": 4.6428,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155779457442305e-05,
"loss": 4.6425,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147393509931785e-05,
"loss": 4.6273,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.6378,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.6419,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122235667400224e-05,
"loss": 4.6384,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.612,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105463772379184e-05,
"loss": 4.6269,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809707782486866e-05,
"loss": 4.6184,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808869187735814e-05,
"loss": 4.6192,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.6158,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.6171,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.6241,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.6164,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804677851860927e-05,
"loss": 4.6002,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803839257109875e-05,
"loss": 4.6036,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803002300239196e-05,
"loss": 4.6063,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802163705488144e-05,
"loss": 4.609,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801325110737092e-05,
"loss": 4.6084,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.80048651598604e-05,
"loss": 4.5947,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799649559115361e-05,
"loss": 4.6027,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798810964364309e-05,
"loss": 4.5868,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797972369613257e-05,
"loss": 4.6027,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797133774862205e-05,
"loss": 4.5969,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796295180111153e-05,
"loss": 4.5919,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795456585360101e-05,
"loss": 4.5989,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794619628489423e-05,
"loss": 4.5896,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.5859,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792942438987319e-05,
"loss": 4.5872,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.5894,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.5834,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790426654734163e-05,
"loss": 4.5766,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895880599831107e-05,
"loss": 4.5792,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887494652320587e-05,
"loss": 4.5813,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879125083613796e-05,
"loss": 4.578,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870739136103276e-05,
"loss": 4.5621,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862369567396485e-05,
"loss": 4.5738,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853983619885965e-05,
"loss": 4.5753,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845597672375445e-05,
"loss": 4.5678,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.5664,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.5666,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782045620864762e-05,
"loss": 4.5549,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.78120702611371e-05,
"loss": 4.5741,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780368431362658e-05,
"loss": 4.5594,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779529836611606e-05,
"loss": 4.563,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778692879740927e-05,
"loss": 4.5595,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777854284989875e-05,
"loss": 4.5659,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777015690238823e-05,
"loss": 4.557,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776177095487771e-05,
"loss": 4.5579,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775338500736719e-05,
"loss": 4.569,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450154386604e-05,
"loss": 4.5598,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773662949114988e-05,
"loss": 4.5484,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772824354363936e-05,
"loss": 4.5491,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719857596128845e-05,
"loss": 4.5439,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771147164861832e-05,
"loss": 4.5418,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.77030857011078e-05,
"loss": 4.5452,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769469975359728e-05,
"loss": 4.5427,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686330184890494e-05,
"loss": 4.5332,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767794423737997e-05,
"loss": 4.5382,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766955828986945e-05,
"loss": 4.5341,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766117234235893e-05,
"loss": 4.5505,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.5539,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764440044733789e-05,
"loss": 4.5389,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763601449982737e-05,
"loss": 4.5285,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762762855231685e-05,
"loss": 4.5356,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761924260480633e-05,
"loss": 4.5409,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610856657295813e-05,
"loss": 4.5396,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760248708858902e-05,
"loss": 4.5331,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941011410785e-05,
"loss": 4.538,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758571519356798e-05,
"loss": 4.5285,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757734562486119e-05,
"loss": 4.53,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756895967735067e-05,
"loss": 4.5254,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756057372984015e-05,
"loss": 4.5282,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755218778232963e-05,
"loss": 4.5226,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754380183481911e-05,
"loss": 4.517,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753541588730859e-05,
"loss": 4.5241,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752702993979807e-05,
"loss": 4.5262,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751864399228755e-05,
"loss": 4.5277,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751025804477703e-05,
"loss": 4.5153,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750188847607025e-05,
"loss": 4.5159,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.485238552093506,
"eval_runtime": 295.8472,
"eval_samples_per_second": 1289.824,
"eval_steps_per_second": 40.308,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749350252855973e-05,
"loss": 4.5114,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748511658104921e-05,
"loss": 4.5072,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747673063353868e-05,
"loss": 4.5231,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746834468602816e-05,
"loss": 4.5127,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745995873851764e-05,
"loss": 4.5197,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745157279100712e-05,
"loss": 4.5012,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.74431868434966e-05,
"loss": 4.5153,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743480089598608e-05,
"loss": 4.5023,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742641494847556e-05,
"loss": 4.51,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741802900096504e-05,
"loss": 4.5053,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740964305345452e-05,
"loss": 4.5141,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401257105944e-05,
"loss": 4.5086,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392887537237216e-05,
"loss": 4.4931,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384501589726696e-05,
"loss": 4.5,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376115642216176e-05,
"loss": 4.4925,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367729694705656e-05,
"loss": 4.4959,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359343747195135e-05,
"loss": 4.4969,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350957799684615e-05,
"loss": 4.4887,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342571852174095e-05,
"loss": 4.4943,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733418590466357e-05,
"loss": 4.5106,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325816335956784e-05,
"loss": 4.4974,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317430388446264e-05,
"loss": 4.4922,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730904444093574e-05,
"loss": 4.4926,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730065849342522e-05,
"loss": 4.5003,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292288924718433e-05,
"loss": 4.475,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728390297720791e-05,
"loss": 4.4862,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727551702969739e-05,
"loss": 4.485,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726713108218687e-05,
"loss": 4.4796,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725876151348009e-05,
"loss": 4.4768,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725037556596957e-05,
"loss": 4.4731,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724198961845904e-05,
"loss": 4.4822,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723360367094852e-05,
"loss": 4.4904,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225217723438e-05,
"loss": 4.4805,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721686453353495e-05,
"loss": 4.4798,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720847858602443e-05,
"loss": 4.4744,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720010901731764e-05,
"loss": 4.477,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719172306980712e-05,
"loss": 4.4647,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71833371222966e-05,
"loss": 4.482,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717495117478608e-05,
"loss": 4.455,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716656522727556e-05,
"loss": 4.4683,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715817927976504e-05,
"loss": 4.4615,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149793332254516e-05,
"loss": 4.4768,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141407384743996e-05,
"loss": 4.4552,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713303781603721e-05,
"loss": 4.4681,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124651868526685e-05,
"loss": 4.468,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116265921016165e-05,
"loss": 4.4602,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107879973505645e-05,
"loss": 4.4695,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099494025995125e-05,
"loss": 4.451,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091108078484605e-05,
"loss": 4.4501,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708273850977782e-05,
"loss": 4.469,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.70743525622673e-05,
"loss": 4.4542,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706596661475678e-05,
"loss": 4.4531,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705758066724626e-05,
"loss": 4.449,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704919471973574e-05,
"loss": 4.457,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704082515102895e-05,
"loss": 4.4426,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703243920351843e-05,
"loss": 4.4617,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702405325600791e-05,
"loss": 4.4342,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701566730849739e-05,
"loss": 4.4487,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700728136098687e-05,
"loss": 4.4505,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699889541347635e-05,
"loss": 4.443,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699050946596583e-05,
"loss": 4.4503,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698212351845531e-05,
"loss": 4.4493,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697373757094479e-05,
"loss": 4.4246,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965351623434276e-05,
"loss": 4.4359,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956982054727485e-05,
"loss": 4.447,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.6948596107216965e-05,
"loss": 4.4374,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.6940226538510174e-05,
"loss": 4.4374,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931840590999654e-05,
"loss": 4.4222,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.6923454643489134e-05,
"loss": 4.4285,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915068695978614e-05,
"loss": 4.4465,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906682748468094e-05,
"loss": 4.4452,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898296800957574e-05,
"loss": 4.4287,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688991085344705e-05,
"loss": 4.4451,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688152490593653e-05,
"loss": 4.4489,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687315533722974e-05,
"loss": 4.4491,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686476938971923e-05,
"loss": 4.4159,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.68563834422087e-05,
"loss": 4.4372,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684799749469818e-05,
"loss": 4.4303,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683961154718766e-05,
"loss": 4.4256,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683122559967714e-05,
"loss": 4.4309,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682283965216662e-05,
"loss": 4.4301,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.68144537046561e-05,
"loss": 4.4337,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680608413594931e-05,
"loss": 4.4351,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679769818843879e-05,
"loss": 4.412,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789328619732e-05,
"loss": 4.4225,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678094267222148e-05,
"loss": 4.4206,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677255672471097e-05,
"loss": 4.4266,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676417077720045e-05,
"loss": 4.4275,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675578482968993e-05,
"loss": 4.4115,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674739888217941e-05,
"loss": 4.4213,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673901293466889e-05,
"loss": 4.4092,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673062698715837e-05,
"loss": 4.4219,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672224103964785e-05,
"loss": 4.4164,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671385509213733e-05,
"loss": 4.4146,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670546914462681e-05,
"loss": 4.4213,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669708319711629e-05,
"loss": 4.4185,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688713628409496e-05,
"loss": 4.4086,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680327680898976e-05,
"loss": 4.4127,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6671941733388456e-05,
"loss": 4.4164,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663555785877936e-05,
"loss": 4.4123,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655186217171145e-05,
"loss": 4.3996,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664680026966063e-05,
"loss": 4.4086,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663841432215011e-05,
"loss": 4.4121,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663002837463959e-05,
"loss": 4.4089,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.66216588059328e-05,
"loss": 4.3892,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661328923722601e-05,
"loss": 4.4035,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660490328971549e-05,
"loss": 4.4095,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659651734220497e-05,
"loss": 4.3995,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658813139469445e-05,
"loss": 4.3989,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657976182598766e-05,
"loss": 4.4009,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657137587847714e-05,
"loss": 4.3904,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656298993096662e-05,
"loss": 4.4076,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.65546039834561e-05,
"loss": 4.3927,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546218035945586e-05,
"loss": 4.4025,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6537848467238795e-05,
"loss": 4.4008,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.6529462519728275e-05,
"loss": 4.4032,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521076572217755e-05,
"loss": 4.3935,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512690624707234e-05,
"loss": 4.401,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.6504321056000444e-05,
"loss": 4.4071,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6495935108489924e-05,
"loss": 4.3996,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487549160979403e-05,
"loss": 4.3871,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479163213468883e-05,
"loss": 4.3897,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647077726595836e-05,
"loss": 4.3848,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462391318447837e-05,
"loss": 4.3889,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645400537093732e-05,
"loss": 4.3862,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.64456194234268e-05,
"loss": 4.3889,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643723347591628e-05,
"loss": 4.376,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642886390720949e-05,
"loss": 4.3844,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642047795969897e-05,
"loss": 4.3782,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641209201218845e-05,
"loss": 4.3963,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640370606467793e-05,
"loss": 4.3968,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639533649597114e-05,
"loss": 4.3893,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638695054846062e-05,
"loss": 4.375,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.63785646009501e-05,
"loss": 4.3828,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637017865343958e-05,
"loss": 4.3908,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636179270592906e-05,
"loss": 4.3861,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635342313722228e-05,
"loss": 4.3824,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634503718971176e-05,
"loss": 4.3872,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633665124220124e-05,
"loss": 4.3806,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632826529469072e-05,
"loss": 4.3864,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6319895725983926e-05,
"loss": 4.3705,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311509778473406e-05,
"loss": 4.3837,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303123830962886e-05,
"loss": 4.376,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294737883452366e-05,
"loss": 4.3682,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286351935941846e-05,
"loss": 4.3768,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277998746038784e-05,
"loss": 4.3823,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.6269612798528264e-05,
"loss": 4.3782,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.6261226851017744e-05,
"loss": 4.3716,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625284090350723e-05,
"loss": 4.3691,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.347572326660156,
"eval_runtime": 302.0433,
"eval_samples_per_second": 1263.365,
"eval_steps_per_second": 39.481,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624445495599671e-05,
"loss": 4.3777,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623606900848619e-05,
"loss": 4.3627,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622768306097567e-05,
"loss": 4.3802,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621929711346515e-05,
"loss": 4.3679,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621091116595463e-05,
"loss": 4.3822,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620254159724784e-05,
"loss": 4.3581,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619415564973732e-05,
"loss": 4.3771,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.61857697022268e-05,
"loss": 4.3603,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617738375471628e-05,
"loss": 4.373,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616901418600949e-05,
"loss": 4.3677,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616062823849897e-05,
"loss": 4.3688,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.6152258669792184e-05,
"loss": 4.3756,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6143872722281664e-05,
"loss": 4.3546,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135486774771144e-05,
"loss": 4.3623,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.6127100827260624e-05,
"loss": 4.3562,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.6118714879750104e-05,
"loss": 4.3609,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.6110328932239584e-05,
"loss": 4.3581,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.6101942984729064e-05,
"loss": 4.3566,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.6093557037218544e-05,
"loss": 4.3594,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608517108970802e-05,
"loss": 4.3765,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.60767851421975e-05,
"loss": 4.3611,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606841557349071e-05,
"loss": 4.3596,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606002962598019e-05,
"loss": 4.3621,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051643678469666e-05,
"loss": 4.365,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604325773095915e-05,
"loss": 4.3449,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603488816225236e-05,
"loss": 4.3619,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602650221474184e-05,
"loss": 4.3474,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601811626723132e-05,
"loss": 4.3484,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.60097303197208e-05,
"loss": 4.3439,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600136075101402e-05,
"loss": 4.3509,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599297480350349e-05,
"loss": 4.3489,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598458885599297e-05,
"loss": 4.3627,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597620290848245e-05,
"loss": 4.3531,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596781696097193e-05,
"loss": 4.3517,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595943101346141e-05,
"loss": 4.3425,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595104506595089e-05,
"loss": 4.3526,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594265911844037e-05,
"loss": 4.3362,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593427317092985e-05,
"loss": 4.3572,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.5925903602223066e-05,
"loss": 4.3293,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.5917517654712546e-05,
"loss": 4.3408,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.5909131707202026e-05,
"loss": 4.3397,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900745759691506e-05,
"loss": 4.3519,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.5892359812180986e-05,
"loss": 4.3334,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5883973864670466e-05,
"loss": 4.34,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.5875604295963675e-05,
"loss": 4.3423,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867218348453155e-05,
"loss": 4.3382,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858848779746364e-05,
"loss": 4.3461,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.5850462832235844e-05,
"loss": 4.3303,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.5842076884725324e-05,
"loss": 4.3246,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.5833690937214804e-05,
"loss": 4.3451,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.5825304989704284e-05,
"loss": 4.3344,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581691904219377e-05,
"loss": 4.3311,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580853309468325e-05,
"loss": 4.3316,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580014714717273e-05,
"loss": 4.3343,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791761199662204e-05,
"loss": 4.3208,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578340800975915e-05,
"loss": 4.3426,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577502206224863e-05,
"loss": 4.315,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576663611473811e-05,
"loss": 4.3303,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575825016722759e-05,
"loss": 4.3278,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.574986421971707e-05,
"loss": 4.3327,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574147827220655e-05,
"loss": 4.3265,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573310870349976e-05,
"loss": 4.3316,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572472275598924e-05,
"loss": 4.3066,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716336808478725e-05,
"loss": 4.3248,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5707950860968205e-05,
"loss": 4.3286,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569956491345768e-05,
"loss": 4.3243,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569117896594716e-05,
"loss": 4.3168,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5682809397240374e-05,
"loss": 4.3133,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.5674423449729854e-05,
"loss": 4.3124,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566603750221933e-05,
"loss": 4.3274,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565765155470881e-05,
"loss": 4.3325,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564928198600202e-05,
"loss": 4.3165,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.5640896038491496e-05,
"loss": 4.3293,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.5632510090980976e-05,
"loss": 4.3346,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562412414347046e-05,
"loss": 4.3399,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561573819595994e-05,
"loss": 4.3016,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560735224844942e-05,
"loss": 4.3222,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.55989663009389e-05,
"loss": 4.3216,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559058035342838e-05,
"loss": 4.3112,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558221078472159e-05,
"loss": 4.3204,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557382483721107e-05,
"loss": 4.3235,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556543888970055e-05,
"loss": 4.3259,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555705294219003e-05,
"loss": 4.3166,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554866699467951e-05,
"loss": 4.3096,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554028104716899e-05,
"loss": 4.3111,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553189509965847e-05,
"loss": 4.3111,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552352553095168e-05,
"loss": 4.3185,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551513958344116e-05,
"loss": 4.3209,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.5506770014734376e-05,
"loss": 4.3046,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.5498384067223856e-05,
"loss": 4.3112,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.5489998119713336e-05,
"loss": 4.301,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.5481612172202816e-05,
"loss": 4.3111,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.5473226224692296e-05,
"loss": 4.3116,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.5464840277181776e-05,
"loss": 4.307,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.5456454329671256e-05,
"loss": 4.3165,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448068382160736e-05,
"loss": 4.3108,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.5439682434650216e-05,
"loss": 4.3044,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.5431312865943425e-05,
"loss": 4.307,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.5422926918432905e-05,
"loss": 4.3097,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.5414540970922385e-05,
"loss": 4.3121,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406155023411865e-05,
"loss": 4.2929,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5397769075901345e-05,
"loss": 4.3045,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538939950719456e-05,
"loss": 4.3087,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538101355968404e-05,
"loss": 4.3079,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372627612173514e-05,
"loss": 4.2902,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364241664662994e-05,
"loss": 4.2948,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5355855717152473e-05,
"loss": 4.3077,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347469769641953e-05,
"loss": 4.2987,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533908382213143e-05,
"loss": 4.2957,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533069787462091e-05,
"loss": 4.2957,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532232830591412e-05,
"loss": 4.2967,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.53139423584036e-05,
"loss": 4.2992,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530557278969682e-05,
"loss": 4.2945,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297203220990034e-05,
"loss": 4.2939,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.5288817273479514e-05,
"loss": 4.3022,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528043132596899e-05,
"loss": 4.3041,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527204537845847e-05,
"loss": 4.3016,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526365943094795e-05,
"loss": 4.2927,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525527348343743e-05,
"loss": 4.3092,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524688753592691e-05,
"loss": 4.3008,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523850158841639e-05,
"loss": 4.2868,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523011564090587e-05,
"loss": 4.2937,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522172969339535e-05,
"loss": 4.2882,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521334374588483e-05,
"loss": 4.2926,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.5204974177178036e-05,
"loss": 4.2834,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519660460847125e-05,
"loss": 4.2938,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518821866096073e-05,
"loss": 4.2786,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517983271345021e-05,
"loss": 4.2875,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517144676593969e-05,
"loss": 4.28,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516306081842917e-05,
"loss": 4.3015,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515467487091865e-05,
"loss": 4.2962,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514628892340813e-05,
"loss": 4.2948,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513790297589761e-05,
"loss": 4.2787,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512953340719082e-05,
"loss": 4.2903,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512116383848403e-05,
"loss": 4.2985,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511277789097351e-05,
"loss": 4.2879,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510439194346299e-05,
"loss": 4.286,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509600599595247e-05,
"loss": 4.295,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087620048441956e-05,
"loss": 4.2867,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079234100931436e-05,
"loss": 4.2931,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070864532224645e-05,
"loss": 4.2739,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062478584714125e-05,
"loss": 4.2905,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.5054092637203605e-05,
"loss": 4.28,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.5045706689693085e-05,
"loss": 4.2803,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.5037320742182565e-05,
"loss": 4.2824,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5028934794672045e-05,
"loss": 4.2913,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502054884716152e-05,
"loss": 4.2823,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012162899651e-05,
"loss": 4.278,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.5003793330944214e-05,
"loss": 4.2797,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.263718605041504,
"eval_runtime": 296.8429,
"eval_samples_per_second": 1285.498,
"eval_steps_per_second": 40.173,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.4995407383433694e-05,
"loss": 4.2779,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987021435923174e-05,
"loss": 4.2736,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978635488412654e-05,
"loss": 4.2848,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970249540902134e-05,
"loss": 4.2781,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4961863593391614e-05,
"loss": 4.2911,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953477645881094e-05,
"loss": 4.2747,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945091698370574e-05,
"loss": 4.2807,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936705750860054e-05,
"loss": 4.2703,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492833618215326e-05,
"loss": 4.2795,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.491995023464274e-05,
"loss": 4.2818,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491156428713222e-05,
"loss": 4.2783,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.49031783396217e-05,
"loss": 4.2818,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489479239211118e-05,
"loss": 4.2669,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488640644460066e-05,
"loss": 4.2747,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487802049709014e-05,
"loss": 4.2698,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486963454957962e-05,
"loss": 4.2684,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.48612486020691e-05,
"loss": 4.2714,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485286265455859e-05,
"loss": 4.2699,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484447670704806e-05,
"loss": 4.2699,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483609075953754e-05,
"loss": 4.2834,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482772119083076e-05,
"loss": 4.2779,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481933524332024e-05,
"loss": 4.2717,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481094929580971e-05,
"loss": 4.2755,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480257972710293e-05,
"loss": 4.28,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479419377959241e-05,
"loss": 4.2569,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478580783208188e-05,
"loss": 4.2741,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477742188457136e-05,
"loss": 4.2626,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476903593706084e-05,
"loss": 4.2591,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476064998955033e-05,
"loss": 4.2581,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475226404203981e-05,
"loss": 4.2669,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474387809452929e-05,
"loss": 4.2638,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473549214701877e-05,
"loss": 4.276,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.4727122578311976e-05,
"loss": 4.2677,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.4718736630801456e-05,
"loss": 4.2655,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710350683290936e-05,
"loss": 4.2592,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.4701964735780416e-05,
"loss": 4.2671,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693578788269896e-05,
"loss": 4.2594,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.4685209219563105e-05,
"loss": 4.2679,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4676823272052585e-05,
"loss": 4.2461,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668437324542065e-05,
"loss": 4.2561,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466006775583528e-05,
"loss": 4.2555,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465168180832476e-05,
"loss": 4.2692,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464329586081424e-05,
"loss": 4.2558,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463490991330372e-05,
"loss": 4.2575,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.46265239657932e-05,
"loss": 4.2594,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461813801828268e-05,
"loss": 4.2555,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460976844957589e-05,
"loss": 4.2633,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.46013988808691e-05,
"loss": 4.2509,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459301293335858e-05,
"loss": 4.2423,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.458462698584806e-05,
"loss": 4.2632,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457624103833754e-05,
"loss": 4.2523,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456785509082702e-05,
"loss": 4.2511,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.45594691433165e-05,
"loss": 4.2486,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455108319580598e-05,
"loss": 4.257,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542697248295465e-05,
"loss": 4.2415,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534311300784945e-05,
"loss": 4.2555,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4525925353274425e-05,
"loss": 4.2397,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.45175394057639e-05,
"loss": 4.2475,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450915345825338e-05,
"loss": 4.2522,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450076751074286e-05,
"loss": 4.2505,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449238156323234e-05,
"loss": 4.2468,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448401199452555e-05,
"loss": 4.2573,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447562604701503e-05,
"loss": 4.2294,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446725647830824e-05,
"loss": 4.2407,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.4458870530797716e-05,
"loss": 4.2513,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.44504845832872e-05,
"loss": 4.2434,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444209863577668e-05,
"loss": 4.2439,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443371268826616e-05,
"loss": 4.2352,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442532674075564e-05,
"loss": 4.2327,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441694079324512e-05,
"loss": 4.2477,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.44085548457346e-05,
"loss": 4.2545,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440016889822408e-05,
"loss": 4.2441,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439178295071356e-05,
"loss": 4.2508,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438339700320304e-05,
"loss": 4.2572,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437502743449625e-05,
"loss": 4.2663,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436664148698573e-05,
"loss": 4.2298,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435825553947521e-05,
"loss": 4.242,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.434986959196469e-05,
"loss": 4.2526,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434148364445417e-05,
"loss": 4.2301,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433311407574738e-05,
"loss": 4.2469,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432472812823687e-05,
"loss": 4.2449,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431634218072635e-05,
"loss": 4.2495,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430795623321583e-05,
"loss": 4.245,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429957028570531e-05,
"loss": 4.2306,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291200716998516e-05,
"loss": 4.2375,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4282814769487996e-05,
"loss": 4.2343,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274428821977476e-05,
"loss": 4.2422,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266042874466956e-05,
"loss": 4.2469,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257673305760165e-05,
"loss": 4.2287,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249287358249645e-05,
"loss": 4.2374,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4240901410739125e-05,
"loss": 4.228,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232515463228605e-05,
"loss": 4.2358,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224129515718085e-05,
"loss": 4.2379,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4215743568207565e-05,
"loss": 4.2362,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207357620697045e-05,
"loss": 4.2445,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.4198971673186525e-05,
"loss": 4.2336,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190585725676005e-05,
"loss": 4.2346,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418223253577295e-05,
"loss": 4.2322,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417386296706616e-05,
"loss": 4.2346,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416547701955564e-05,
"loss": 4.2421,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415709107204512e-05,
"loss": 4.222,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.41487051245346e-05,
"loss": 4.2333,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414031917702408e-05,
"loss": 4.235,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413193322951356e-05,
"loss": 4.2357,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412354728200304e-05,
"loss": 4.2178,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411516133449252e-05,
"loss": 4.2248,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106775386982e-05,
"loss": 4.2355,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409838943947148e-05,
"loss": 4.2293,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409000349196096e-05,
"loss": 4.2219,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408161754445044e-05,
"loss": 4.2294,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407324797574365e-05,
"loss": 4.2205,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406486202823313e-05,
"loss": 4.2339,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405647608072261e-05,
"loss": 4.2241,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404809013321209e-05,
"loss": 4.2198,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.40397205645053e-05,
"loss": 4.233,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.4031334616994777e-05,
"loss": 4.2377,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402296504828799e-05,
"loss": 4.2289,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401457910077747e-05,
"loss": 4.2257,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400619315326695e-05,
"loss": 4.2311,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399782358456016e-05,
"loss": 4.2311,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398943763704964e-05,
"loss": 4.2208,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398105168953912e-05,
"loss": 4.2304,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.39726657420286e-05,
"loss": 4.2178,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396427979451808e-05,
"loss": 4.2224,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395589384700756e-05,
"loss": 4.2167,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394750789949704e-05,
"loss": 4.2243,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393912195198652e-05,
"loss": 4.2112,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3930736004476e-05,
"loss": 4.2153,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392235005696548e-05,
"loss": 4.2174,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391396410945496e-05,
"loss": 4.2291,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390557816194444e-05,
"loss": 4.231,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389719221443392e-05,
"loss": 4.2271,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.38888062669234e-05,
"loss": 4.2098,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388043669821662e-05,
"loss": 4.227,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387205075070609e-05,
"loss": 4.2295,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3863681181999306e-05,
"loss": 4.2231,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855295234488786e-05,
"loss": 4.2186,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3846909286978266e-05,
"loss": 4.2316,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383852333946774e-05,
"loss": 4.2171,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383013739195722e-05,
"loss": 4.2276,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.38217514444467e-05,
"loss": 4.204,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381336549693618e-05,
"loss": 4.2286,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380497954942566e-05,
"loss": 4.2104,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796593601915145e-05,
"loss": 4.2137,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788207654404625e-05,
"loss": 4.219,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3779821706894105e-05,
"loss": 4.2194,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771435759383585e-05,
"loss": 4.2214,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763066190676794e-05,
"loss": 4.2069,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3754680243166274e-05,
"loss": 4.2204,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.206528663635254,
"eval_runtime": 291.1655,
"eval_samples_per_second": 1310.564,
"eval_steps_per_second": 40.956,
"step": 381600
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.5770413818740627e+17,
"trial_name": null,
"trial_params": null
}