abhinavp's picture
Training in progress, epoch 1, checkpoint
2cdf0c1 verified
{
"best_metric": 3.869717836380005,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/transformer/0/checkpoints/checkpoint-457920",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 457920,
"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": 10.9402,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8272,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1901,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9741,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8089,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7087,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5936,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5251,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4409,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3928,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3412,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3021,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2523,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2013,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1676,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1251,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.097,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.075,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0453,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0127,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0017,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9631,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9463,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9236,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9129,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8836,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8671,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8459,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8271,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8133,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7946,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7908,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7707,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.7631,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7571,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7389,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969820416244367e-05,
"loss": 4.7307,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7035,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.6986,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6811,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6804,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6683,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6592,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6375,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6483,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6339,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6276,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.621,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5898,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 4.5885,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.5932,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.5853,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5673,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5487,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 4.5516,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 4.5366,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.564,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5197,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5349,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5282,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5056,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5105,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.4995,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.483,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4835,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.502,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4789,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4688,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4589,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4607,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4728,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4682,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4569,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4626,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4649,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4491,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4373,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4282,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4274,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4201,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4157,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.418,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4189,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.4145,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.3895,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.3879,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.3972,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.4005,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3816,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3833,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.388,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3728,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.369,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3723,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3629,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3675,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3589,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3442,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3522,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.353,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3479,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3472,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.3415,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.3384,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3383,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3137,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3176,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3223,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.3199,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.3105,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.3065,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.3039,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.3084,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.303,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3037,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.2976,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.3028,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.2989,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901080214863699e-05,
"loss": 4.2949,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.2981,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.2965,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.285,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.2916,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.2792,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2861,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.264,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2766,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.2625,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2671,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2521,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.2818,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2687,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.2551,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.2565,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.2617,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.2646,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2605,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2494,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2561,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2434,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2566,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.2391,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.2418,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.2418,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2315,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.2366,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2352,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.2335,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.2347,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2251,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.1916117668151855,
"eval_runtime": 306.2873,
"eval_samples_per_second": 1245.86,
"eval_steps_per_second": 38.934,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.21,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.2084,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.2256,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.2102,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2279,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2004,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2057,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.1917,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2061,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.1993,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.2053,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.201,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.187,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.1871,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.1836,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.178,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.1853,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.1823,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.1787,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.1977,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.1695,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.1811,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.177,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.1852,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.1614,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.1699,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.1634,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.1678,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.152,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.1549,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.1647,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.1587,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.1582,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.1631,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.1567,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.156,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.1441,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.1506,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.1361,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.1446,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840725960993552e-05,
"loss": 4.1445,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398873662425e-05,
"loss": 4.1443,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.131,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.1418,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.1444,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365346251186646e-05,
"loss": 4.1378,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1415,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.1123,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834020478745882e-05,
"loss": 4.1183,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331818839948295e-05,
"loss": 4.1369,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.1288,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831506332373099e-05,
"loss": 4.1241,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830667737622047e-05,
"loss": 4.1072,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298291428709944e-05,
"loss": 4.1122,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828992186000316e-05,
"loss": 4.1054,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828153591249264e-05,
"loss": 4.1295,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827314996498212e-05,
"loss": 4.1043,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.82647640174716e-05,
"loss": 4.1174,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256394448764816e-05,
"loss": 4.1219,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248008501254296e-05,
"loss": 4.1011,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823962255374377e-05,
"loss": 4.1084,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823123660623325e-05,
"loss": 4.0997,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222867037526465e-05,
"loss": 4.0961,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214481090015945e-05,
"loss": 4.0947,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820609514250542e-05,
"loss": 4.1132,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.81977091949949e-05,
"loss": 4.1023,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818932324748438e-05,
"loss": 4.0926,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180953678777594e-05,
"loss": 4.0899,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172567731267074e-05,
"loss": 4.0915,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164181783756554e-05,
"loss": 4.1056,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155795836246034e-05,
"loss": 4.1072,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814742626753924e-05,
"loss": 4.1014,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813904032002872e-05,
"loss": 4.11,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.81306543725182e-05,
"loss": 4.1085,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812226842500768e-05,
"loss": 4.104,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811389885630089e-05,
"loss": 4.0933,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810551290879037e-05,
"loss": 4.0905,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809712696127985e-05,
"loss": 4.0904,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808874101376933e-05,
"loss": 4.0884,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808037144506255e-05,
"loss": 4.0851,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807198549755203e-05,
"loss": 4.0917,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806359955004151e-05,
"loss": 4.0961,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805521360253099e-05,
"loss": 4.0878,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046844033824197e-05,
"loss": 4.074,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.8038458086313677e-05,
"loss": 4.0735,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8030072138803156e-05,
"loss": 4.0808,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.8021702570096366e-05,
"loss": 4.0884,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013316622585846e-05,
"loss": 4.0734,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004930675075325e-05,
"loss": 4.0766,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996544727564805e-05,
"loss": 4.0848,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988175158858015e-05,
"loss": 4.0733,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979789211347494e-05,
"loss": 4.072,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797140326383698e-05,
"loss": 4.0731,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796301731632646e-05,
"loss": 4.0731,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795464774761967e-05,
"loss": 4.0757,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794626180010915e-05,
"loss": 4.0743,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793787585259863e-05,
"loss": 4.0586,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792948990508811e-05,
"loss": 4.0699,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792110395757759e-05,
"loss": 4.0665,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791271801006707e-05,
"loss": 4.075,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790433206255655e-05,
"loss": 4.0663,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789594611504603e-05,
"loss": 4.0667,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788757654633924e-05,
"loss": 4.0638,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787919059882872e-05,
"loss": 4.0699,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870821030121935e-05,
"loss": 4.0456,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862435082611415e-05,
"loss": 4.0516,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854049135100895e-05,
"loss": 4.0574,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845663187590375e-05,
"loss": 4.0536,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837277240079855e-05,
"loss": 4.0487,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828891292569335e-05,
"loss": 4.0478,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820505345058815e-05,
"loss": 4.0469,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812119397548295e-05,
"loss": 4.0532,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803749828841504e-05,
"loss": 4.0483,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795363881330984e-05,
"loss": 4.0492,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786977933820464e-05,
"loss": 4.0518,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778591986309944e-05,
"loss": 4.0556,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770206038799423e-05,
"loss": 4.0519,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776183647009263e-05,
"loss": 4.0495,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775345052258212e-05,
"loss": 4.0555,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450645750716e-05,
"loss": 4.0551,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773667862756108e-05,
"loss": 4.0423,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772829268005055e-05,
"loss": 4.0532,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771990673254003e-05,
"loss": 4.0402,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771152078502951e-05,
"loss": 4.0528,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770313483751899e-05,
"loss": 4.0277,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.76947652688122e-05,
"loss": 4.045,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.0278,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76780097525949e-05,
"loss": 4.0333,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766962380508437e-05,
"loss": 4.0237,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766123785757386e-05,
"loss": 4.0533,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765285191006334e-05,
"loss": 4.0424,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764446596255282e-05,
"loss": 4.0345,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.76360800150423e-05,
"loss": 4.0288,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762769406753178e-05,
"loss": 4.0392,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.7619324498824986e-05,
"loss": 4.0425,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610938551314466e-05,
"loss": 4.0401,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602552603803946e-05,
"loss": 4.0335,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594166656293426e-05,
"loss": 4.0358,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.7585797087586635e-05,
"loss": 4.0281,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577411140076115e-05,
"loss": 4.0437,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569025192565595e-05,
"loss": 4.0239,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560639245055075e-05,
"loss": 4.0291,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755226967634829e-05,
"loss": 4.0274,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754388372883777e-05,
"loss": 4.0224,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753551416013098e-05,
"loss": 4.0317,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752712821262046e-05,
"loss": 4.0243,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751874226510994e-05,
"loss": 4.029,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751035631759942e-05,
"loss": 4.025,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.75019703700889e-05,
"loss": 4.0212,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.0242791175842285,
"eval_runtime": 309.0459,
"eval_samples_per_second": 1234.739,
"eval_steps_per_second": 38.587,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749358442257838e-05,
"loss": 4.0084,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748519847506786e-05,
"loss": 4.0066,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747681252755734e-05,
"loss": 4.0256,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746842658004682e-05,
"loss": 4.0107,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.74600406325363e-05,
"loss": 4.0352,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745165468502578e-05,
"loss": 4.0031,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744326873751526e-05,
"loss": 4.0124,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743488279000474e-05,
"loss": 3.9956,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426513221297955e-05,
"loss": 4.0151,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418127273787435e-05,
"loss": 4.0088,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740974132627691e-05,
"loss": 4.0119,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740135537876639e-05,
"loss": 4.0097,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392985810059604e-05,
"loss": 3.9977,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384599862549084e-05,
"loss": 4.0036,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737621391503856e-05,
"loss": 3.9992,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736782796752804e-05,
"loss": 3.9955,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735944202001752e-05,
"loss": 3.9959,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7351056072507e-05,
"loss": 4.0005,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734267012499648e-05,
"loss": 3.9953,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733428417748596e-05,
"loss": 4.0182,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732591460877917e-05,
"loss": 3.9932,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731752866126865e-05,
"loss": 4.0009,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730914271375813e-05,
"loss": 3.9991,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730075676624761e-05,
"loss": 4.0074,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729238719754082e-05,
"loss": 3.987,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.72840012500303e-05,
"loss": 3.9994,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727561530251978e-05,
"loss": 3.9897,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726722935500926e-05,
"loss": 3.9941,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725884340749874e-05,
"loss": 3.9794,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725045745998822e-05,
"loss": 3.9842,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.72420715124777e-05,
"loss": 3.9931,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723370194377091e-05,
"loss": 3.9923,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.72253159962604e-05,
"loss": 3.9931,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721693004874988e-05,
"loss": 3.9956,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720854410123936e-05,
"loss": 3.9879,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720015815372884e-05,
"loss": 3.9903,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191788585022046e-05,
"loss": 3.9772,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183402637511526e-05,
"loss": 3.9911,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175016690001006e-05,
"loss": 3.9725,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166630742490486e-05,
"loss": 3.982,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158244794979966e-05,
"loss": 3.9796,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149858847469446e-05,
"loss": 3.9881,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714147289995892e-05,
"loss": 3.9789,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133103331252135e-05,
"loss": 3.9773,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124717383741615e-05,
"loss": 3.9873,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116331436231095e-05,
"loss": 3.9818,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107945488720575e-05,
"loss": 3.9814,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709957592001379e-05,
"loss": 3.9655,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709118997250327e-05,
"loss": 3.9608,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082804024992744e-05,
"loss": 3.9779,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074418077482224e-05,
"loss": 3.9725,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706604850877544e-05,
"loss": 3.9722,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705766256126492e-05,
"loss": 3.9544,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704927661375439e-05,
"loss": 3.9598,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704089066624387e-05,
"loss": 3.9588,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703252109753709e-05,
"loss": 3.9715,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702413515002657e-05,
"loss": 3.9574,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701574920251605e-05,
"loss": 3.9701,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700736325500553e-05,
"loss": 3.969,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998993686298745e-05,
"loss": 3.9565,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699060773878822e-05,
"loss": 3.9598,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.69822217912777e-05,
"loss": 3.9561,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697383584376718e-05,
"loss": 3.9469,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696544989625666e-05,
"loss": 3.9573,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695708032754987e-05,
"loss": 3.9623,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694869438003935e-05,
"loss": 3.9673,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694030843252883e-05,
"loss": 3.9444,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931922485018307e-05,
"loss": 3.9496,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.6923536537507787e-05,
"loss": 3.9479,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915166968801e-05,
"loss": 3.9707,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690678102129048e-05,
"loss": 3.9582,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689839507377996e-05,
"loss": 3.9606,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689000912626944e-05,
"loss": 3.9725,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688162317875892e-05,
"loss": 3.9699,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.68732372312484e-05,
"loss": 3.9659,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686485128373788e-05,
"loss": 3.9543,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685646533622736e-05,
"loss": 3.9579,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.68481121463243e-05,
"loss": 3.9537,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683972619881378e-05,
"loss": 3.9516,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683134025130326e-05,
"loss": 3.9535,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682295430379274e-05,
"loss": 3.9539,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681456835628222e-05,
"loss": 3.9615,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680618240877171e-05,
"loss": 3.9522,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797812840064916e-05,
"loss": 3.9454,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789426892554396e-05,
"loss": 3.9385,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.6781040945043876e-05,
"loss": 3.9513,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772654997533356e-05,
"loss": 3.9561,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764285428826565e-05,
"loss": 3.9441,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755899481316045e-05,
"loss": 3.9433,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747513533805525e-05,
"loss": 3.9555,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739127586295005e-05,
"loss": 3.9365,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730758017588214e-05,
"loss": 3.945,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722372070077694e-05,
"loss": 3.9438,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713986122567174e-05,
"loss": 3.9486,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670561655386039e-05,
"loss": 3.9493,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669723060634987e-05,
"loss": 3.9419,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668884465883935e-05,
"loss": 3.9331,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668045871132883e-05,
"loss": 3.9458,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667207276381831e-05,
"loss": 3.9374,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666368681630779e-05,
"loss": 3.9522,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665530086879727e-05,
"loss": 3.9428,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664691492128675e-05,
"loss": 3.9445,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663854535257996e-05,
"loss": 3.936,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663015940506944e-05,
"loss": 3.9487,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662177345755892e-05,
"loss": 3.9215,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.66133875100484e-05,
"loss": 3.9291,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6605017941341614e-05,
"loss": 3.9343,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596631993831094e-05,
"loss": 3.9331,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588246046320574e-05,
"loss": 3.9246,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579860098810054e-05,
"loss": 3.9283,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657149053010326e-05,
"loss": 3.9258,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656310458259274e-05,
"loss": 3.935,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655471863508222e-05,
"loss": 3.9295,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.65463326875717e-05,
"loss": 3.926,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653796311886491e-05,
"loss": 3.937,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652957717135439e-05,
"loss": 3.939,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652119122384387e-05,
"loss": 3.9377,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651280527633335e-05,
"loss": 3.9274,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650443570762657e-05,
"loss": 3.9392,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649604976011605e-05,
"loss": 3.9351,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648766381260553e-05,
"loss": 3.9269,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479277865095e-05,
"loss": 3.9398,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647090829638822e-05,
"loss": 3.9207,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.64625223488777e-05,
"loss": 3.9363,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645413640136718e-05,
"loss": 3.9146,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644575045385665e-05,
"loss": 3.9296,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437380885149866e-05,
"loss": 3.9133,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428994937639346e-05,
"loss": 3.9187,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642060899012882e-05,
"loss": 3.9129,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412223042618306e-05,
"loss": 3.9371,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640385347391152e-05,
"loss": 3.9272,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395467526401e-05,
"loss": 3.9257,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387081578890475e-05,
"loss": 3.917,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378695631379955e-05,
"loss": 3.9251,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637032606267317e-05,
"loss": 3.9353,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636194011516265e-05,
"loss": 3.926,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353554167652124e-05,
"loss": 3.9213,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345168220141604e-05,
"loss": 3.9314,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633679865143482e-05,
"loss": 3.9211,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632841270392429e-05,
"loss": 3.9263,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632002675641377e-05,
"loss": 3.916,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631164080890326e-05,
"loss": 3.9222,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303271240196475e-05,
"loss": 3.9173,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629488529268595e-05,
"loss": 3.9163,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628649934517543e-05,
"loss": 3.9179,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627811339766491e-05,
"loss": 3.9233,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626972745015439e-05,
"loss": 3.9161,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.62613578814476e-05,
"loss": 3.9174,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625297193393708e-05,
"loss": 3.9155,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9504966735839844,
"eval_runtime": 309.784,
"eval_samples_per_second": 1231.797,
"eval_steps_per_second": 38.495,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624458598642656e-05,
"loss": 3.9086,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623620003891604e-05,
"loss": 3.9037,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.6227830470209246e-05,
"loss": 3.919,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219444522698726e-05,
"loss": 3.9051,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621105857518821e-05,
"loss": 3.9327,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620267262767769e-05,
"loss": 3.8971,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.61943030589709e-05,
"loss": 3.9087,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618591711146038e-05,
"loss": 3.8918,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617753116394986e-05,
"loss": 3.9105,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616914521643934e-05,
"loss": 3.9094,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616077564773255e-05,
"loss": 3.9049,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615238970022203e-05,
"loss": 3.9078,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614402013151524e-05,
"loss": 3.8962,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613563418400472e-05,
"loss": 3.9046,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.61272482364942e-05,
"loss": 3.8991,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611886228898368e-05,
"loss": 3.8985,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611047634147316e-05,
"loss": 3.8961,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610209039396265e-05,
"loss": 3.8987,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609370444645213e-05,
"loss": 3.8987,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.6085318498941607e-05,
"loss": 3.9156,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076948930234816e-05,
"loss": 3.8944,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068562982724296e-05,
"loss": 3.9007,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6060177035213776e-05,
"loss": 3.8994,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051791087703256e-05,
"loss": 3.9095,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.6043421518996465e-05,
"loss": 3.8879,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.6035035571485945e-05,
"loss": 3.9029,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.6026649623975425e-05,
"loss": 3.8922,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018263676464904e-05,
"loss": 3.8932,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009894107758114e-05,
"loss": 3.8818,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.60015081602476e-05,
"loss": 3.8937,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599312221273708e-05,
"loss": 3.8941,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598473626522656e-05,
"loss": 3.898,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597636669651977e-05,
"loss": 3.896,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596798074900925e-05,
"loss": 3.9022,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595959480149873e-05,
"loss": 3.8902,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595120885398821e-05,
"loss": 3.8973,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594283928528142e-05,
"loss": 3.8847,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.59344533377709e-05,
"loss": 3.8939,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592606739026038e-05,
"loss": 3.8779,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591768144274986e-05,
"loss": 3.8889,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590931187404307e-05,
"loss": 3.8875,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900925926532554e-05,
"loss": 3.8966,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.5892539979022034e-05,
"loss": 3.8866,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5884154031511514e-05,
"loss": 3.8867,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587578446280472e-05,
"loss": 3.8917,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.58673985152942e-05,
"loss": 3.8901,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585901256778368e-05,
"loss": 3.8905,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585062662027316e-05,
"loss": 3.8777,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584225705156637e-05,
"loss": 3.8638,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583387110405585e-05,
"loss": 3.8885,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582548515654533e-05,
"loss": 3.8809,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581709920903481e-05,
"loss": 3.8788,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580872964032802e-05,
"loss": 3.8702,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580034369281751e-05,
"loss": 3.8684,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579195774530699e-05,
"loss": 3.8649,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.57835881766002e-05,
"loss": 3.8829,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577520222908968e-05,
"loss": 3.8694,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576681628157916e-05,
"loss": 3.8769,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758430334068637e-05,
"loss": 3.8845,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5750044386558117e-05,
"loss": 3.8687,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741658439047596e-05,
"loss": 3.8712,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733272491537076e-05,
"loss": 3.8741,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572488654402655e-05,
"loss": 3.855,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716516975319765e-05,
"loss": 3.8699,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5708131027809245e-05,
"loss": 3.8787,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.5699745080298725e-05,
"loss": 3.8767,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.5691359132788205e-05,
"loss": 3.8608,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568298956408142e-05,
"loss": 3.8645,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.56746036165709e-05,
"loss": 3.8614,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.5666217669060374e-05,
"loss": 3.8786,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.5657831721549854e-05,
"loss": 3.8745,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564946215284307e-05,
"loss": 3.8772,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564107620533255e-05,
"loss": 3.8854,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563269025782202e-05,
"loss": 3.8852,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.56243043103115e-05,
"loss": 3.8852,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561593474160472e-05,
"loss": 3.8654,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.56075487940942e-05,
"loss": 3.8749,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559916284658368e-05,
"loss": 3.8737,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559077689907316e-05,
"loss": 3.8668,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582407330366375e-05,
"loss": 3.8742,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557402138285585e-05,
"loss": 3.869,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556563543534533e-05,
"loss": 3.8763,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555724948783481e-05,
"loss": 3.8705,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.5548879919128024e-05,
"loss": 3.8544,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.55404939716175e-05,
"loss": 3.8583,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553210802410698e-05,
"loss": 3.8683,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552372207659646e-05,
"loss": 3.8729,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515352507889666e-05,
"loss": 3.8637,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550696656037915e-05,
"loss": 3.8598,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549858061286863e-05,
"loss": 3.8716,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549019466535811e-05,
"loss": 3.8572,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548182509665132e-05,
"loss": 3.8592,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.54734391491408e-05,
"loss": 3.8647,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546505320163028e-05,
"loss": 3.8701,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.54566836329235e-05,
"loss": 3.8711,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544829768541297e-05,
"loss": 3.8615,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543991173790245e-05,
"loss": 3.8492,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543152579039193e-05,
"loss": 3.8687,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542313984288141e-05,
"loss": 3.855,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541475389537089e-05,
"loss": 3.8746,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540636794786037e-05,
"loss": 3.8662,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539798200034985e-05,
"loss": 3.8622,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389612431643066e-05,
"loss": 3.8578,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5381226484132546e-05,
"loss": 3.8698,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372856915425755e-05,
"loss": 3.8451,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364470967915235e-05,
"loss": 3.8527,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5356085020404715e-05,
"loss": 3.8511,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347699072894195e-05,
"loss": 3.8566,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339313125383675e-05,
"loss": 3.8466,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330927177873155e-05,
"loss": 3.8527,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322541230362635e-05,
"loss": 3.8519,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314155282852115e-05,
"loss": 3.8502,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.5305785714145324e-05,
"loss": 3.8561,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297399766634804e-05,
"loss": 3.8462,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.5289013819124284e-05,
"loss": 3.8638,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528062787161377e-05,
"loss": 3.8607,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527225830290698e-05,
"loss": 3.8612,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526387235539646e-05,
"loss": 3.8518,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525548640788594e-05,
"loss": 3.8616,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524710046037542e-05,
"loss": 3.8612,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523873089166863e-05,
"loss": 3.8489,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523034494415811e-05,
"loss": 3.8627,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522195899664759e-05,
"loss": 3.8463,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521357304913707e-05,
"loss": 3.8591,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520520348043028e-05,
"loss": 3.8422,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519681753291976e-05,
"loss": 3.8539,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518843158540924e-05,
"loss": 3.8374,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5180045637898725e-05,
"loss": 3.8452,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171676069191934e-05,
"loss": 3.8414,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163290121681414e-05,
"loss": 3.8577,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.5154904174170894e-05,
"loss": 3.849,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146518226660373e-05,
"loss": 3.8557,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513814865795358e-05,
"loss": 3.8431,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512976271044306e-05,
"loss": 3.8517,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512137676293254e-05,
"loss": 3.8594,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511299081542202e-05,
"loss": 3.8531,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510462124671523e-05,
"loss": 3.8491,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509623529920471e-05,
"loss": 3.8558,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508784935169419e-05,
"loss": 3.8485,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507946340418368e-05,
"loss": 3.8589,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507109383547689e-05,
"loss": 3.839,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506270788796637e-05,
"loss": 3.8517,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505432194045585e-05,
"loss": 3.8434,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504593599294533e-05,
"loss": 3.8433,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.5037566424238536e-05,
"loss": 3.85,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5029180476728016e-05,
"loss": 3.8475,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020794529217496e-05,
"loss": 3.846,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012408581706976e-05,
"loss": 3.8419,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.5004039013000185e-05,
"loss": 3.8486,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.909996747970581,
"eval_runtime": 309.6063,
"eval_samples_per_second": 1232.504,
"eval_steps_per_second": 38.517,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.4995653065489665e-05,
"loss": 3.8344,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987267117979145e-05,
"loss": 3.8315,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497888117046863e-05,
"loss": 3.8476,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970495222958105e-05,
"loss": 3.8364,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4962109275447585e-05,
"loss": 3.8607,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953723327937065e-05,
"loss": 3.834,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945337380426545e-05,
"loss": 3.834,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936951432916025e-05,
"loss": 3.8216,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928581864209234e-05,
"loss": 3.8393,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4920195916698714e-05,
"loss": 3.8424,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911809969188194e-05,
"loss": 3.8336,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903424021677674e-05,
"loss": 3.8359,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489507083177462e-05,
"loss": 3.8275,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.48866848842641e-05,
"loss": 3.8348,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487829893675358e-05,
"loss": 3.8314,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486991298924306e-05,
"loss": 3.8272,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486152704173254e-05,
"loss": 3.8262,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485314109422202e-05,
"loss": 3.8337,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.48447551467115e-05,
"loss": 3.8284,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483636919920098e-05,
"loss": 3.8432,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.4828016009297924e-05,
"loss": 3.831,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.48196300617874e-05,
"loss": 3.835,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481124411427688e-05,
"loss": 3.8323,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480285816676636e-05,
"loss": 3.8401,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.4794472219255837e-05,
"loss": 3.8206,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478608627174532e-05,
"loss": 3.8341,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.47777003242348e-05,
"loss": 3.8274,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476933075552801e-05,
"loss": 3.8242,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476094480801749e-05,
"loss": 3.816,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475255886050697e-05,
"loss": 3.8235,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474417291299645e-05,
"loss": 3.8315,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473580334428966e-05,
"loss": 3.8311,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472741739677914e-05,
"loss": 3.8321,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471903144926862e-05,
"loss": 3.8332,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.47106455017581e-05,
"loss": 3.8249,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470227593305131e-05,
"loss": 3.8305,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469388998554079e-05,
"loss": 3.8234,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468550403803028e-05,
"loss": 3.8262,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467711809051976e-05,
"loss": 3.8154,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668748521812966e-05,
"loss": 3.8246,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660362574302446e-05,
"loss": 3.8213,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651976626791926e-05,
"loss": 3.8294,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.4643590679281406e-05,
"loss": 3.8224,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4635221110574615e-05,
"loss": 3.8217,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626835163064095e-05,
"loss": 3.8323,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618449215553575e-05,
"loss": 3.8233,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4610063268043055e-05,
"loss": 3.8232,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601693699336264e-05,
"loss": 3.8145,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4593307751825744e-05,
"loss": 3.7998,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584921804315224e-05,
"loss": 3.8252,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457653585680471e-05,
"loss": 3.8183,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456816628809792e-05,
"loss": 3.8173,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455979671939113e-05,
"loss": 3.8017,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455141077188061e-05,
"loss": 3.8081,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454302482437009e-05,
"loss": 3.7999,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453463887685957e-05,
"loss": 3.8214,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452625292934905e-05,
"loss": 3.8077,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451786698183853e-05,
"loss": 3.8109,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450948103432801e-05,
"loss": 3.8225,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450111146562122e-05,
"loss": 3.806,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.4492741896914433e-05,
"loss": 3.8098,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.4484355949403913e-05,
"loss": 3.8149,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.4475970001893393e-05,
"loss": 3.7934,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446758405438287e-05,
"loss": 3.81,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445919810687235e-05,
"loss": 3.8118,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445081215936183e-05,
"loss": 3.8177,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444242621185131e-05,
"loss": 3.7981,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443404026434079e-05,
"loss": 3.8046,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.4425670695634e-05,
"loss": 3.7966,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441728474812348e-05,
"loss": 3.8208,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440889880061296e-05,
"loss": 3.8129,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440051285310244e-05,
"loss": 3.811,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439214328439565e-05,
"loss": 3.8261,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438375733688513e-05,
"loss": 3.8186,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437537138937462e-05,
"loss": 3.8328,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.43669854418641e-05,
"loss": 3.8067,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435861587315731e-05,
"loss": 3.8113,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435022992564679e-05,
"loss": 3.8124,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434184397813627e-05,
"loss": 3.8034,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333474409429476e-05,
"loss": 3.8161,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4325088461918956e-05,
"loss": 3.8086,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316702514408436e-05,
"loss": 3.8165,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4308316566897916e-05,
"loss": 3.8082,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299930619387396e-05,
"loss": 3.7966,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291544671876876e-05,
"loss": 3.8091,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4283158724366356e-05,
"loss": 3.7997,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427478915565957e-05,
"loss": 3.815,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426640320814905e-05,
"loss": 3.806,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425801726063853e-05,
"loss": 3.7992,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249631313128005e-05,
"loss": 3.8116,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4241245365617485e-05,
"loss": 3.8046,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232859418106965e-05,
"loss": 3.7964,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224473470596445e-05,
"loss": 3.8041,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4216087523085925e-05,
"loss": 3.8144,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207717954379134e-05,
"loss": 3.8102,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.4199332006868614e-05,
"loss": 3.8082,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190946059358094e-05,
"loss": 3.7894,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182560111847573e-05,
"loss": 3.8077,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4174174164337053e-05,
"loss": 3.7985,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416578821682654e-05,
"loss": 3.8131,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415740226931602e-05,
"loss": 3.8111,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.41490163218055e-05,
"loss": 3.8047,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414064675309871e-05,
"loss": 3.7996,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413227718439192e-05,
"loss": 3.8143,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.41238912368814e-05,
"loss": 3.7832,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411550528937088e-05,
"loss": 3.7967,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410711934186036e-05,
"loss": 3.791,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409873339434984e-05,
"loss": 3.8063,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409034744683932e-05,
"loss": 3.7847,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.40819614993288e-05,
"loss": 3.7934,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407357555181828e-05,
"loss": 3.7969,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.4065205983111494e-05,
"loss": 3.7948,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.4056820035600974e-05,
"loss": 3.7973,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.4048434088090454e-05,
"loss": 3.794,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.4040048140579934e-05,
"loss": 3.8062,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403167857187314e-05,
"loss": 3.8045,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402329262436262e-05,
"loss": 3.8028,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401492305565583e-05,
"loss": 3.7931,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400653710814531e-05,
"loss": 3.8062,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399815116063479e-05,
"loss": 3.8005,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398976521312427e-05,
"loss": 3.7912,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398137926561375e-05,
"loss": 3.8083,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397299331810323e-05,
"loss": 3.7895,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396462374939645e-05,
"loss": 3.8009,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395623780188593e-05,
"loss": 3.7878,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394785185437541e-05,
"loss": 3.7979,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393946590686489e-05,
"loss": 3.785,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393107995935437e-05,
"loss": 3.7868,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392269401184384e-05,
"loss": 3.7902,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3914324443137056e-05,
"loss": 3.8016,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905938495626536e-05,
"loss": 3.7955,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897552548116016e-05,
"loss": 3.7984,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388916660060549e-05,
"loss": 3.7854,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388078065309497e-05,
"loss": 3.7989,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387239470558445e-05,
"loss": 3.8038,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386400875807393e-05,
"loss": 3.7987,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855639189367145e-05,
"loss": 3.7943,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3847253241856625e-05,
"loss": 3.8005,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.3838867294346105e-05,
"loss": 3.7931,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830481346835585e-05,
"loss": 3.802,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3822111778128794e-05,
"loss": 3.7871,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813725830618274e-05,
"loss": 3.796,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3805339883107754e-05,
"loss": 3.7909,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796953935597234e-05,
"loss": 3.7906,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378858436689044e-05,
"loss": 3.7946,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378019841937992e-05,
"loss": 3.7928,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377182885067313e-05,
"loss": 3.7946,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376344290316262e-05,
"loss": 3.7831,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.37550569556521e-05,
"loss": 3.798,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.885251045227051,
"eval_runtime": 305.6198,
"eval_samples_per_second": 1248.581,
"eval_steps_per_second": 39.019,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.374667100814158e-05,
"loss": 3.7864,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.373828506063106e-05,
"loss": 3.7763,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.372989911312054e-05,
"loss": 3.7951,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.372151316561002e-05,
"loss": 3.7843,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.371314359690323e-05,
"loss": 3.8045,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.370475764939271e-05,
"loss": 3.7843,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.369638808068592e-05,
"loss": 3.7743,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.36880021331754e-05,
"loss": 3.7755,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367961618566488e-05,
"loss": 3.7812,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367123023815436e-05,
"loss": 3.7906,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366284429064384e-05,
"loss": 3.781,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.365445834313332e-05,
"loss": 3.7858,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.364608877442653e-05,
"loss": 3.7768,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.363770282691601e-05,
"loss": 3.7785,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.362931687940549e-05,
"loss": 3.7832,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.362093093189497e-05,
"loss": 3.774,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.361254498438445e-05,
"loss": 3.7733,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.360415903687393e-05,
"loss": 3.7815,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.359577308936341e-05,
"loss": 3.7798,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.358738714185289e-05,
"loss": 3.791,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.357903395194983e-05,
"loss": 3.7823,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.357064800443931e-05,
"loss": 3.7838,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.356226205692879e-05,
"loss": 3.7806,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.355387610941827e-05,
"loss": 3.7854,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.354549016190776e-05,
"loss": 3.7689,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.353710421439724e-05,
"loss": 3.7875,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.352871826688672e-05,
"loss": 3.7719,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.35203323193762e-05,
"loss": 3.7735,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.3511962750669406e-05,
"loss": 3.7684,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.3503576803158886e-05,
"loss": 3.7716,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.3495190855648366e-05,
"loss": 3.7814,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.3486821286941575e-05,
"loss": 3.7766,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.3478435339431055e-05,
"loss": 3.7855,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.3470049391920535e-05,
"loss": 3.7858,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.3461663444410015e-05,
"loss": 3.7734,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.3453277496899495e-05,
"loss": 3.7783,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344490792819271e-05,
"loss": 3.7748,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.343652198068219e-05,
"loss": 3.7733,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.342813603317167e-05,
"loss": 3.7689,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.341975008566115e-05,
"loss": 3.7722,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.3411364138150624e-05,
"loss": 3.7757,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.3402978190640104e-05,
"loss": 3.7818,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.339460862193332e-05,
"loss": 3.7692,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338622267442279e-05,
"loss": 3.773,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337783672691227e-05,
"loss": 3.7781,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.336945077940175e-05,
"loss": 3.7756,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.336108121069497e-05,
"loss": 3.7741,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.335269526318445e-05,
"loss": 3.7674,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334430931567393e-05,
"loss": 3.7456,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.333592336816341e-05,
"loss": 3.7805,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.332753742065289e-05,
"loss": 3.7693,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.331915147314237e-05,
"loss": 3.7691,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331078190443558e-05,
"loss": 3.7593,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.330239595692506e-05,
"loss": 3.7538,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.329401000941454e-05,
"loss": 3.7527,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328562406190402e-05,
"loss": 3.7685,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.32772381143935e-05,
"loss": 3.7606,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326885216688298e-05,
"loss": 3.7652,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.3260482598176186e-05,
"loss": 3.7703,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.3252096650665666e-05,
"loss": 3.7593,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.3243710703155146e-05,
"loss": 3.7619,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.3235324755644626e-05,
"loss": 3.7681,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322693880813411e-05,
"loss": 3.7481,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.321855286062359e-05,
"loss": 3.7591,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.321016691311307e-05,
"loss": 3.7631,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.320179734440628e-05,
"loss": 3.77,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.319341139689576e-05,
"loss": 3.7478,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.318502544938524e-05,
"loss": 3.7583,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.317663950187472e-05,
"loss": 3.7494,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.31682535543642e-05,
"loss": 3.7698,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.315986760685368e-05,
"loss": 3.766,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.3151481659343155e-05,
"loss": 3.7631,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.3143095711832635e-05,
"loss": 3.7767,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313472614312585e-05,
"loss": 3.7714,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.312634019561533e-05,
"loss": 3.7852,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311795424810481e-05,
"loss": 3.7621,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310956830059429e-05,
"loss": 3.7646,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.3101198731887506e-05,
"loss": 3.7617,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.3092829163180715e-05,
"loss": 3.7538,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.3084443215670195e-05,
"loss": 3.7721,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.3076057268159675e-05,
"loss": 3.7609,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.3067671320649155e-05,
"loss": 3.7692,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.305928537313863e-05,
"loss": 3.7633,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.305089942562811e-05,
"loss": 3.7503,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.3042529856921324e-05,
"loss": 3.7599,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.3034143909410804e-05,
"loss": 3.7529,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.3025757961900284e-05,
"loss": 3.7699,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.3017372014389764e-05,
"loss": 3.763,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.3008986066879244e-05,
"loss": 3.7472,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.3000600119368724e-05,
"loss": 3.77,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.2992214171858204e-05,
"loss": 3.7573,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.2983828224347684e-05,
"loss": 3.7498,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.297545865564089e-05,
"loss": 3.7583,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.296707270813037e-05,
"loss": 3.7697,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.295870313942358e-05,
"loss": 3.7625,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.295031719191306e-05,
"loss": 3.766,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294193124440254e-05,
"loss": 3.7467,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293354529689202e-05,
"loss": 3.76,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.29251593493815e-05,
"loss": 3.7517,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.291677340187099e-05,
"loss": 3.7648,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.290838745436047e-05,
"loss": 3.7667,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.290000150684995e-05,
"loss": 3.755,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289163193814316e-05,
"loss": 3.7594,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288324599063264e-05,
"loss": 3.7659,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.287487642192585e-05,
"loss": 3.74,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286649047441533e-05,
"loss": 3.7512,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.285810452690481e-05,
"loss": 3.7442,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.284971857939429e-05,
"loss": 3.7582,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284133263188377e-05,
"loss": 3.7436,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.2832963063176976e-05,
"loss": 3.7524,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.2824577115666456e-05,
"loss": 3.7499,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281619116815594e-05,
"loss": 3.7513,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.280780522064542e-05,
"loss": 3.7547,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.27994192731349e-05,
"loss": 3.7476,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.279103332562438e-05,
"loss": 3.7601,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.278266375691759e-05,
"loss": 3.7587,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.277427780940707e-05,
"loss": 3.7586,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276589186189655e-05,
"loss": 3.7484,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.275750591438603e-05,
"loss": 3.7595,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.274913634567924e-05,
"loss": 3.7602,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.274075039816872e-05,
"loss": 3.746,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.27323644506582e-05,
"loss": 3.7673,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.272397850314768e-05,
"loss": 3.7419,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.271559255563716e-05,
"loss": 3.7593,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.270720660812664e-05,
"loss": 3.7412,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.2698837039419856e-05,
"loss": 3.7564,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.2690451091909336e-05,
"loss": 3.741,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.2682065144398816e-05,
"loss": 3.7447,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.267367919688829e-05,
"loss": 3.7411,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.2665309628181505e-05,
"loss": 3.7613,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.2656923680670985e-05,
"loss": 3.7481,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.2648537733160465e-05,
"loss": 3.7573,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.264015178564994e-05,
"loss": 3.743,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.2631782216943154e-05,
"loss": 3.757,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.2623396269432634e-05,
"loss": 3.7568,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.2615010321922114e-05,
"loss": 3.755,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.2606624374411594e-05,
"loss": 3.7541,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.2598238426901074e-05,
"loss": 3.7502,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.258986885819429e-05,
"loss": 3.7502,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.258148291068376e-05,
"loss": 3.761,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.257309696317324e-05,
"loss": 3.7457,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256471101566272e-05,
"loss": 3.7535,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.25563250681522e-05,
"loss": 3.748,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254793912064168e-05,
"loss": 3.7492,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253955317313116e-05,
"loss": 3.7529,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253116722562064e-05,
"loss": 3.7452,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252279765691385e-05,
"loss": 3.7604,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251441170940333e-05,
"loss": 3.7342,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250602576189281e-05,
"loss": 3.7567,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 3.869717836380005,
"eval_runtime": 305.4028,
"eval_samples_per_second": 1249.468,
"eval_steps_per_second": 39.047,
"step": 457920
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.1846510665575424e+17,
"trial_name": null,
"trial_params": null
}