abhinavp's picture
Training in progress, epoch 0, checkpoint
0de4c4e verified
raw
history blame
No virus
56.1 kB
{
"best_metric": 4.33865213394165,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/lstm/1/checkpoints/checkpoint-228960",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 228960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.8197,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5528,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0561,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.988,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9411,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8638,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7072,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6023,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5067,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4371,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3821,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3225,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2538,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.1921,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1397,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0809,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0353,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 5.995,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9573,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9186,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8836,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8425,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8192,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.783,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7615,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7324,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7096,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 5.6814,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6558,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6382,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6134,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 5.6064,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 5.5742,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5654,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5565,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5338,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5198,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.485,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 5.4779,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 5.455,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 5.4511,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 5.4318,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 5.4222,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.3904,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.4006,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3891,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 5.38,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.3673,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959762192872862e-05,
"loss": 5.3404,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 5.3316,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 5.3344,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 5.3189,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 5.3073,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 5.2821,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 5.2828,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 5.2693,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 5.2947,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 5.2472,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 5.2523,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 5.2467,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 5.2257,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 5.2271,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 5.2106,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 5.1959,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 5.1943,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2108,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 5.1835,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 5.1748,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 5.1584,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 5.1584,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 5.1685,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1638,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.1502,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.1576,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.15,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371250482355776e-05,
"loss": 5.1383,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1195,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935447858733473e-05,
"loss": 5.109,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934609263982421e-05,
"loss": 5.1061,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.098,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 5.0952,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 5.0912,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.093,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 5.0833,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 5.0581,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 5.0535,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 5.0634,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 5.065,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 5.0402,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 5.0432,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.92455267849129e-05,
"loss": 5.043,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.0279,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.0217,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 5.0204,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921198299487081e-05,
"loss": 5.0101,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920359704736029e-05,
"loss": 5.0149,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 5.0038,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 4.9882,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.988,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 4.9869,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.9838,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.9838,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.9734,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.9698,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.9615,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.9412,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9458,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9436,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.9415,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908624291862421e-05,
"loss": 4.9325,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907785697111369e-05,
"loss": 4.9277,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9212,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.921,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.9153,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.9151,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.9074,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.9044,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.9063,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901080214863699e-05,
"loss": 4.8977,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.9033,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.903,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.8858,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.8916,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.8765,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.8826,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.8576,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.8691,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893534499984604e-05,
"loss": 4.8542,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892695905233552e-05,
"loss": 4.8566,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918573104825e-05,
"loss": 4.8378,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891018715731448e-05,
"loss": 4.8689,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890181758860769e-05,
"loss": 4.856,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889343164109717e-05,
"loss": 4.8439,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888504569358665e-05,
"loss": 4.8417,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.8876659746076134e-05,
"loss": 4.8379,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.8868273798565614e-05,
"loss": 4.8464,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885990422985882e-05,
"loss": 4.8405,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515182823483e-05,
"loss": 4.8302,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.8344,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883474638732726e-05,
"loss": 4.8193,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882636043981674e-05,
"loss": 4.8295,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881797449230622e-05,
"loss": 4.8135,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88095885447957e-05,
"loss": 4.8142,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880120259728518e-05,
"loss": 4.8106,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879283302857839e-05,
"loss": 4.7999,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878444708106787e-05,
"loss": 4.8022,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877606113355735e-05,
"loss": 4.8025,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876767518604683e-05,
"loss": 4.7974,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875928923853632e-05,
"loss": 4.8013,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875091966982953e-05,
"loss": 4.7897,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.75280237197876,
"eval_runtime": 299.9661,
"eval_samples_per_second": 1272.114,
"eval_steps_per_second": 39.754,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874253372231901e-05,
"loss": 4.7784,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873414777480849e-05,
"loss": 4.7745,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872576182729797e-05,
"loss": 4.791,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871739225859118e-05,
"loss": 4.7733,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709006311080657e-05,
"loss": 4.7904,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700620363570137e-05,
"loss": 4.7598,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.7729,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.7509,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.7632,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.7606,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.765,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.7602,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864195148860396e-05,
"loss": 4.7426,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863356554109344e-05,
"loss": 4.7447,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862517959358292e-05,
"loss": 4.7376,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.86167936460724e-05,
"loss": 4.7349,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608407698561874e-05,
"loss": 4.7435,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.8600021751051354e-05,
"loss": 4.7403,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591635803540834e-05,
"loss": 4.735,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583249856030314e-05,
"loss": 4.7498,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857488028732352e-05,
"loss": 4.7238,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856649433981301e-05,
"loss": 4.7326,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855810839230249e-05,
"loss": 4.7259,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854972244479197e-05,
"loss": 4.7356,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854135287608518e-05,
"loss": 4.7115,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853296692857466e-05,
"loss": 4.7195,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852458098106414e-05,
"loss": 4.7098,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851619503355362e-05,
"loss": 4.7168,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.85078090860431e-05,
"loss": 4.6981,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849943951733631e-05,
"loss": 4.7007,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849105356982579e-05,
"loss": 4.7112,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848266762231527e-05,
"loss": 4.7037,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.7031,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.8465912106097964e-05,
"loss": 4.7096,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.8457526158587444e-05,
"loss": 4.7014,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.8449140211076924e-05,
"loss": 4.7008,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.8440754263566404e-05,
"loss": 4.6825,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.8432368316055884e-05,
"loss": 4.6913,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.8423982368545363e-05,
"loss": 4.6766,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.8415596421034843e-05,
"loss": 4.6862,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840721047352432e-05,
"loss": 4.6825,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839884090481753e-05,
"loss": 4.6801,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.6655,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838210176740395e-05,
"loss": 4.681,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.6802,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.6745,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.6787,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.6486,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.651,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833178608234084e-05,
"loss": 4.6691,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832340013483032e-05,
"loss": 4.6566,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.83150141873198e-05,
"loss": 4.6554,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830662823980928e-05,
"loss": 4.6363,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829824229229876e-05,
"loss": 4.6432,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828985634478824e-05,
"loss": 4.6375,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828147039727771e-05,
"loss": 4.6637,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273100828570926e-05,
"loss": 4.6335,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.6423,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.6469,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.6269,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.6338,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.6271,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222801522311535e-05,
"loss": 4.6169,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214415574801015e-05,
"loss": 4.623,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.6379,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.6253,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.6127,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.6129,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817251859485588e-05,
"loss": 4.6123,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.6294,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815574669983483e-05,
"loss": 4.6304,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814736075232432e-05,
"loss": 4.6192,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.81389748048138e-05,
"loss": 4.6323,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813058885730328e-05,
"loss": 4.6282,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812220290979276e-05,
"loss": 4.6253,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811383334108597e-05,
"loss": 4.6093,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810544739357545e-05,
"loss": 4.6084,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809706144606493e-05,
"loss": 4.604,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808867549855441e-05,
"loss": 4.6057,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808028955104389e-05,
"loss": 4.599,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807190360353337e-05,
"loss": 4.6066,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806353403482658e-05,
"loss": 4.6126,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805514808731606e-05,
"loss": 4.6009,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804677851860927e-05,
"loss": 4.5865,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803839257109875e-05,
"loss": 4.5863,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.5921,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802162067607771e-05,
"loss": 4.6047,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801323472856719e-05,
"loss": 4.5861,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800484878105667e-05,
"loss": 4.592,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799646283354615e-05,
"loss": 4.5928,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798807688603563e-05,
"loss": 4.5862,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797969093852511e-05,
"loss": 4.5809,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797130499101459e-05,
"loss": 4.5788,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796291904350407e-05,
"loss": 4.5789,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954533095993546e-05,
"loss": 4.5817,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794616352728676e-05,
"loss": 4.5816,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793777757977624e-05,
"loss": 4.5663,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792942438987319e-05,
"loss": 4.5732,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.5696,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.5779,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790426654734163e-05,
"loss": 4.5713,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895880599831107e-05,
"loss": 4.5705,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887511031124316e-05,
"loss": 4.5683,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879125083613796e-05,
"loss": 4.5661,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870739136103276e-05,
"loss": 4.5503,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862353188592756e-05,
"loss": 4.5529,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853967241082236e-05,
"loss": 4.5589,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845581293571715e-05,
"loss": 4.5553,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837195346061195e-05,
"loss": 4.5532,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828809398550675e-05,
"loss": 4.5479,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820423451040155e-05,
"loss": 4.5461,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812037503529635e-05,
"loss": 4.5483,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803651556019115e-05,
"loss": 4.5457,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795265608508595e-05,
"loss": 4.5446,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786879660998075e-05,
"loss": 4.5474,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778493713487555e-05,
"loss": 4.5475,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770124144780764e-05,
"loss": 4.5474,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761738197270244e-05,
"loss": 4.5426,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.7753352249759724e-05,
"loss": 4.5516,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7744966302249204e-05,
"loss": 4.5519,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736580354738684e-05,
"loss": 4.5364,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728194407228164e-05,
"loss": 4.547,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719808459717644e-05,
"loss": 4.5356,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771145526981459e-05,
"loss": 4.5435,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770306932230407e-05,
"loss": 4.5182,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769468337479355e-05,
"loss": 4.5362,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768629742728303e-05,
"loss": 4.5191,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767791147977251e-05,
"loss": 4.5269,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766952553226199e-05,
"loss": 4.5137,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766113958475147e-05,
"loss": 4.5434,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765275363724095e-05,
"loss": 4.5355,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764436768973043e-05,
"loss": 4.5269,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.76359817422199e-05,
"loss": 4.52,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762761217351312e-05,
"loss": 4.5235,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.76192262260026e-05,
"loss": 4.5316,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761084027849208e-05,
"loss": 4.5267,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602470709785293e-05,
"loss": 4.5219,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594084762274773e-05,
"loss": 4.5245,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758569881476425e-05,
"loss": 4.5147,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757731286725373e-05,
"loss": 4.5282,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7568926919743206e-05,
"loss": 4.5105,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560540972232686e-05,
"loss": 4.5144,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552155024722166e-05,
"loss": 4.5098,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543769077211646e-05,
"loss": 4.5072,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535399508504855e-05,
"loss": 4.5106,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527013560994335e-05,
"loss": 4.5094,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518627613483815e-05,
"loss": 4.5104,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510241665973295e-05,
"loss": 4.5083,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750185571846278e-05,
"loss": 4.5051,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.473276138305664,
"eval_runtime": 299.3602,
"eval_samples_per_second": 1274.689,
"eval_steps_per_second": 39.835,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749346977095226e-05,
"loss": 4.4963,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748508382344174e-05,
"loss": 4.4896,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747669787593122e-05,
"loss": 4.5098,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.74683119284207e-05,
"loss": 4.4938,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745992598091018e-05,
"loss": 4.5152,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745154003339966e-05,
"loss": 4.4834,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744315408588914e-05,
"loss": 4.4972,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743476813837862e-05,
"loss": 4.4806,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426382190868095e-05,
"loss": 4.4951,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7417996243357575e-05,
"loss": 4.4927,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409610295847055e-05,
"loss": 4.4959,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401224348336535e-05,
"loss": 4.4934,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739285477962975e-05,
"loss": 4.4763,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738446883211923e-05,
"loss": 4.4864,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737608288460871e-05,
"loss": 4.4787,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736769693709819e-05,
"loss": 4.4765,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735931098958767e-05,
"loss": 4.4796,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735092504207715e-05,
"loss": 4.4828,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734253909456663e-05,
"loss": 4.4771,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733416952585984e-05,
"loss": 4.4976,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732578357834932e-05,
"loss": 4.4722,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.73173976308388e-05,
"loss": 4.4783,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730901168332828e-05,
"loss": 4.4768,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730064211462149e-05,
"loss": 4.4863,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729225616711097e-05,
"loss": 4.4663,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728387021960045e-05,
"loss": 4.4764,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727548427208993e-05,
"loss": 4.4667,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267098324579415e-05,
"loss": 4.4724,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258712377068895e-05,
"loss": 4.4592,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250326429558375e-05,
"loss": 4.4607,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7241940482047855e-05,
"loss": 4.4708,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233554534537335e-05,
"loss": 4.4698,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722516858702681e-05,
"loss": 4.4695,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721678263951629e-05,
"loss": 4.4709,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720839669200577e-05,
"loss": 4.4652,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720001074449525e-05,
"loss": 4.471,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719165755459219e-05,
"loss": 4.4514,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718327160708167e-05,
"loss": 4.4671,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717488565957115e-05,
"loss": 4.4497,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716649971206063e-05,
"loss": 4.4593,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715811376455011e-05,
"loss": 4.4548,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714972781703959e-05,
"loss": 4.4587,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714135824833281e-05,
"loss": 4.451,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713297230082228e-05,
"loss": 4.4519,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712458635331176e-05,
"loss": 4.4604,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711620040580124e-05,
"loss": 4.4539,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710781445829072e-05,
"loss": 4.4566,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.70994285107802e-05,
"loss": 4.4388,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709104256326968e-05,
"loss": 4.4302,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708265661575916e-05,
"loss": 4.4497,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707428704705237e-05,
"loss": 4.4437,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706590109954185e-05,
"loss": 4.4441,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705751515203134e-05,
"loss": 4.4266,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704912920452082e-05,
"loss": 4.4315,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.70407432570103e-05,
"loss": 4.4333,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032373688303506e-05,
"loss": 4.4467,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024004119596715e-05,
"loss": 4.4254,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015618172086195e-05,
"loss": 4.4361,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007232224575675e-05,
"loss": 4.4395,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998846277065155e-05,
"loss": 4.4255,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990460329554635e-05,
"loss": 4.4296,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982074382044115e-05,
"loss": 4.4257,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973688434533595e-05,
"loss": 4.4144,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965302487023075e-05,
"loss": 4.4278,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956916539512555e-05,
"loss": 4.4291,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.6948530592002035e-05,
"loss": 4.4324,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.6940144644491515e-05,
"loss": 4.4124,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931758696980995e-05,
"loss": 4.4179,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692338912827421e-05,
"loss": 4.4147,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691503593837115e-05,
"loss": 4.4406,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690664999086063e-05,
"loss": 4.4284,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689826404335011e-05,
"loss": 4.4276,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688987809583959e-05,
"loss": 4.4402,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688149214832907e-05,
"loss": 4.4381,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687310620081855e-05,
"loss": 4.4311,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686472025330803e-05,
"loss": 4.42,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685633430579751e-05,
"loss": 4.4218,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6847964737090725e-05,
"loss": 4.4195,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839578789580204e-05,
"loss": 4.4155,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831192842069684e-05,
"loss": 4.4156,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822806894559164e-05,
"loss": 4.4187,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814420947048644e-05,
"loss": 4.4277,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680603499953812e-05,
"loss": 4.4171,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.67976490520276e-05,
"loss": 4.4073,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678929586212454e-05,
"loss": 4.4018,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678090991461402e-05,
"loss": 4.4119,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.67725239671035e-05,
"loss": 4.4196,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676413801959298e-05,
"loss": 4.4099,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675575207208246e-05,
"loss": 4.4093,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674736612457194e-05,
"loss": 4.4183,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673898017706142e-05,
"loss": 4.4003,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.67305942295509e-05,
"loss": 4.4078,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672220828204038e-05,
"loss": 4.4013,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671382233452986e-05,
"loss": 4.4081,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670545276582307e-05,
"loss": 4.4086,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669706681831255e-05,
"loss": 4.4033,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668868087080203e-05,
"loss": 4.396,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668029492329151e-05,
"loss": 4.4039,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667192535458472e-05,
"loss": 4.3956,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.66635394070742e-05,
"loss": 4.411,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665515345956368e-05,
"loss": 4.4014,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664676751205316e-05,
"loss": 4.4011,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.6638397943346376e-05,
"loss": 4.3939,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.6630011995835856e-05,
"loss": 4.4029,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621626048325336e-05,
"loss": 4.38,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613240100814816e-05,
"loss": 4.3871,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6604854153304296e-05,
"loss": 4.3911,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596484584597505e-05,
"loss": 4.3921,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588098637086985e-05,
"loss": 4.3852,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579712689576465e-05,
"loss": 4.3868,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571326742065945e-05,
"loss": 4.3795,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6562940794555425e-05,
"loss": 4.3884,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554571225848634e-05,
"loss": 4.3846,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546185278338114e-05,
"loss": 4.3784,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.65377993308276e-05,
"loss": 4.3933,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652941338331708e-05,
"loss": 4.3899,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652104381461029e-05,
"loss": 4.3906,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651265786709977e-05,
"loss": 4.382,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650427191958925e-05,
"loss": 4.3916,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649588597207873e-05,
"loss": 4.3899,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648750002456821e-05,
"loss": 4.3812,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647911407705769e-05,
"loss": 4.3968,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.64707445083509e-05,
"loss": 4.3766,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646235856084038e-05,
"loss": 4.3873,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645397261332986e-05,
"loss": 4.3664,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644558666581934e-05,
"loss": 4.3818,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437217097112554e-05,
"loss": 4.3637,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428831149602034e-05,
"loss": 4.3751,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420445202091514e-05,
"loss": 4.3626,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412059254580994e-05,
"loss": 4.3882,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.64036896858742e-05,
"loss": 4.3794,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639530373836368e-05,
"loss": 4.3806,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638691779085316e-05,
"loss": 4.3701,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637853184334264e-05,
"loss": 4.371,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637016227463585e-05,
"loss": 4.3875,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636177632712533e-05,
"loss": 4.3763,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635339037961481e-05,
"loss": 4.3706,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634500443210429e-05,
"loss": 4.3818,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633661848459377e-05,
"loss": 4.3697,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632823253708325e-05,
"loss": 4.3763,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631986296837647e-05,
"loss": 4.3643,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631147702086595e-05,
"loss": 4.3705,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630309107335542e-05,
"loss": 4.365,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.62947051258449e-05,
"loss": 4.3671,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628631917833438e-05,
"loss": 4.3623,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627793323082386e-05,
"loss": 4.3707,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626954728331334e-05,
"loss": 4.3613,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626117771460655e-05,
"loss": 4.3661,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625279176709603e-05,
"loss": 4.3636,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.33865213394165,
"eval_runtime": 441.3072,
"eval_samples_per_second": 864.683,
"eval_steps_per_second": 27.022,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 9.45231495550706e+16,
"trial_name": null,
"trial_params": null
}