abhinavp's picture
Training in progress, epoch 0, checkpoint
2eabdfa verified
raw
history blame
No virus
93.1 kB
{
"best_metric": 3.9349238872528076,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj2/transformer/3/checkpoints/checkpoint-381600",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 381600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.9425,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8235,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1923,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9802,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8087,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.6995,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6031,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5332,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4518,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3997,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3471,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3074,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2692,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2153,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.185,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1314,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1178,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0824,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0454,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0235,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0234,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 4.9771,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9628,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9371,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9122,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.9025,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.866,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8641,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8469,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8185,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8118,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.791,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7909,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.771,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 4.7534,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7477,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969820416244367e-05,
"loss": 4.7503,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7123,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7062,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6993,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.681,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6729,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6742,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6624,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6481,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.64,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6314,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6307,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 4.5992,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5989,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.6077,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.5975,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5835,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5653,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5726,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5519,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5722,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5388,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 4.554,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5335,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5215,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5237,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 4.5101,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 4.5071,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4992,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5077,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.4833,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 4.4775,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4668,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4667,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4852,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4741,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.456,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4545,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4597,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4533,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4367,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4405,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4319,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4307,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4236,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4205,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4253,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.4167,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.3954,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.4055,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.4056,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.3978,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3917,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 4.381,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3884,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3767,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.383,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3707,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3669,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3853,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.35,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3483,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3588,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3572,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3602,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3459,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.3383,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.3371,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3412,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3235,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3204,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3342,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.3223,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.3157,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3089,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3077,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3191,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3047,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3036,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3067,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.3061,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.295,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.3005,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.2977,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2948,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.2796,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.2909,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2832,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2891,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2712,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2812,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.2699,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.274,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2535,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.2799,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2797,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.2619,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.2512,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.2724,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.2591,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2606,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.253,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884314871364151e-05,
"loss": 4.2599,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883476276613099e-05,
"loss": 4.2511,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.25,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.2348,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.2483,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.2441,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2354,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2537,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.231,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2377,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2412,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2304,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.243399143218994,
"eval_runtime": 303.9974,
"eval_samples_per_second": 1255.244,
"eval_steps_per_second": 39.227,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.2151,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.2193,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2303,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2201,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2215,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2072,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.2094,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.2039,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2139,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.2005,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.2069,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2107,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.1944,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.1915,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.1804,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.1889,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.1852,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.1812,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.1806,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.208,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.1785,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.181,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.1853,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.1786,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.1717,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.1633,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.1702,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.1678,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.155,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.1669,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.1566,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.168,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.1627,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.1477,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.1617,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.1706,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.1416,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.153,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.1477,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.1382,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.1427,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.151,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839048771491447e-05,
"loss": 4.1481,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.138,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.1455,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365346251186646e-05,
"loss": 4.1349,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8356960303676126e-05,
"loss": 4.142,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.1218,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834020478745882e-05,
"loss": 4.1245,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331818839948295e-05,
"loss": 4.1396,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323432892437775e-05,
"loss": 4.1387,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831506332373099e-05,
"loss": 4.1265,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830667737622047e-05,
"loss": 4.1184,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298291428709944e-05,
"loss": 4.1304,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289905481199424e-05,
"loss": 4.1109,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281519533688904e-05,
"loss": 4.1368,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827314996498212e-05,
"loss": 4.119,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.82647640174716e-05,
"loss": 4.1335,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825637806996108e-05,
"loss": 4.1199,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824799212245056e-05,
"loss": 4.1107,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823960617494004e-05,
"loss": 4.1142,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823122022742952e-05,
"loss": 4.1167,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822285065872273e-05,
"loss": 4.1057,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821446471121221e-05,
"loss": 4.1041,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820607876370169e-05,
"loss": 4.1183,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819769281619117e-05,
"loss": 4.1043,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818932324748438e-05,
"loss": 4.095,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818093729997386e-05,
"loss": 4.0932,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817255135246334e-05,
"loss": 4.0952,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816416540495282e-05,
"loss": 4.1135,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155795836246034e-05,
"loss": 4.111,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147409888735514e-05,
"loss": 4.095,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139023941224994e-05,
"loss": 4.0995,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130637993714474e-05,
"loss": 4.1037,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122252046203954e-05,
"loss": 4.0995,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811388247749716e-05,
"loss": 4.0918,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810549652998664e-05,
"loss": 4.0995,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809711058247612e-05,
"loss": 4.0915,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887246349656e-05,
"loss": 4.0967,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808035506625881e-05,
"loss": 4.0885,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807196911874829e-05,
"loss": 4.092,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806358317123777e-05,
"loss": 4.0937,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805519722372726e-05,
"loss": 4.0937,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804681127621674e-05,
"loss": 4.075,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803844170750995e-05,
"loss": 4.0877,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803005575999943e-05,
"loss": 4.0848,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802166981248891e-05,
"loss": 4.0859,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801328386497839e-05,
"loss": 4.0827,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800489791746787e-05,
"loss": 4.071,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996528348761076e-05,
"loss": 4.0825,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988142401250556e-05,
"loss": 4.0747,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979756453740036e-05,
"loss": 4.0839,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971370506229516e-05,
"loss": 4.0689,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7963000937522725e-05,
"loss": 4.0738,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795461499001221e-05,
"loss": 4.0846,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794622904250169e-05,
"loss": 4.0717,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793784309499117e-05,
"loss": 4.0523,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792947352628438e-05,
"loss": 4.0703,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792108757877386e-05,
"loss": 4.0735,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791270163126334e-05,
"loss": 4.0742,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790431568375282e-05,
"loss": 4.0678,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789594611504603e-05,
"loss": 4.0617,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788756016753551e-05,
"loss": 4.0574,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787917422002499e-05,
"loss": 4.0692,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.787078827251447e-05,
"loss": 4.0492,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862435082611415e-05,
"loss": 4.0544,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854049135100895e-05,
"loss": 4.0633,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845663187590375e-05,
"loss": 4.0632,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837277240079855e-05,
"loss": 4.0414,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828891292569335e-05,
"loss": 4.0544,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820505345058815e-05,
"loss": 4.0442,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812119397548295e-05,
"loss": 4.0633,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803733450037775e-05,
"loss": 4.049,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795363881330984e-05,
"loss": 4.0424,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786977933820464e-05,
"loss": 4.0616,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778591986309944e-05,
"loss": 4.0546,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777022241760315e-05,
"loss": 4.0466,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776183647009263e-05,
"loss": 4.0528,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775345052258212e-05,
"loss": 4.0479,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450645750716e-05,
"loss": 4.0508,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773667862756108e-05,
"loss": 4.0316,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772829268005055e-05,
"loss": 4.0534,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771990673254003e-05,
"loss": 4.04,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771152078502951e-05,
"loss": 4.0489,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770315121632272e-05,
"loss": 4.0382,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.76947652688122e-05,
"loss": 4.0442,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768637932130168e-05,
"loss": 4.0363,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767799337379116e-05,
"loss": 4.0391,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766962380508437e-05,
"loss": 4.0218,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766123785757386e-05,
"loss": 4.052,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765285191006334e-05,
"loss": 4.0462,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764446596255282e-05,
"loss": 4.0358,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.7636096393846026e-05,
"loss": 4.0259,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.7627710446335506e-05,
"loss": 4.0448,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.7619324498824986e-05,
"loss": 4.0404,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610938551314466e-05,
"loss": 4.0336,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602568982607675e-05,
"loss": 4.029,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594183035097155e-05,
"loss": 4.039,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.7585797087586635e-05,
"loss": 4.032,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577411140076115e-05,
"loss": 4.0418,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569041571369324e-05,
"loss": 4.019,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756065562385881e-05,
"loss": 4.0345,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755226967634829e-05,
"loss": 4.0294,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754388372883777e-05,
"loss": 4.0217,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753551416013098e-05,
"loss": 4.043,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752712821262046e-05,
"loss": 4.0223,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751874226510994e-05,
"loss": 4.0278,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751035631759942e-05,
"loss": 4.0277,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.75019703700889e-05,
"loss": 4.0273,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.07391881942749,
"eval_runtime": 304.0061,
"eval_samples_per_second": 1255.208,
"eval_steps_per_second": 39.226,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749358442257838e-05,
"loss": 4.0097,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748519847506786e-05,
"loss": 4.0189,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747681252755734e-05,
"loss": 4.0279,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746842658004682e-05,
"loss": 4.0208,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.74600406325363e-05,
"loss": 4.0267,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745165468502578e-05,
"loss": 4.0046,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744326873751526e-05,
"loss": 4.0124,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743488279000474e-05,
"loss": 4.0077,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742649684249422e-05,
"loss": 4.0179,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.74181108949837e-05,
"loss": 4.0077,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740972494747318e-05,
"loss": 4.0154,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740135537876639e-05,
"loss": 4.0173,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392985810059604e-05,
"loss": 4.0032,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384599862549084e-05,
"loss": 4.0071,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737621391503856e-05,
"loss": 3.99,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736782796752804e-05,
"loss": 4.0005,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735944202001752e-05,
"loss": 4.001,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7351056072507e-05,
"loss": 3.9969,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734267012499648e-05,
"loss": 3.9968,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733430055628969e-05,
"loss": 4.0228,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732591460877917e-05,
"loss": 3.9991,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731752866126865e-05,
"loss": 3.9984,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730914271375813e-05,
"loss": 4.006,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730077314505134e-05,
"loss": 4.0005,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729238719754082e-05,
"loss": 3.9922,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.72840012500303e-05,
"loss": 3.9873,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727561530251978e-05,
"loss": 3.998,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726724573381299e-05,
"loss": 3.9886,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725885978630247e-05,
"loss": 3.9825,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725047383879195e-05,
"loss": 3.9941,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724208789128143e-05,
"loss": 3.9847,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233718322574647e-05,
"loss": 3.9957,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225332375064127e-05,
"loss": 3.9915,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216946427553606e-05,
"loss": 3.9816,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208560480043086e-05,
"loss": 3.9927,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200190911336296e-05,
"loss": 4.0046,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191804963825775e-05,
"loss": 3.9735,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183419016315255e-05,
"loss": 3.9889,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175033068804735e-05,
"loss": 3.9769,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166663500097945e-05,
"loss": 3.9778,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158277552587424e-05,
"loss": 3.9775,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149891605076904e-05,
"loss": 3.9916,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141505657566384e-05,
"loss": 3.9864,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71331360888596e-05,
"loss": 3.9781,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712475014134908e-05,
"loss": 3.983,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711636419383856e-05,
"loss": 3.9739,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710797824632804e-05,
"loss": 3.9849,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709960867762125e-05,
"loss": 3.9655,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709122273011073e-05,
"loss": 3.9684,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708283678260021e-05,
"loss": 3.9813,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707445083508969e-05,
"loss": 3.9787,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.70660812663829e-05,
"loss": 3.9724,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705769531887238e-05,
"loss": 3.9673,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704930937136186e-05,
"loss": 3.9761,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040939802655074e-05,
"loss": 3.9564,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032553855144554e-05,
"loss": 3.9811,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024167907634034e-05,
"loss": 3.9711,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015781960123514e-05,
"loss": 3.9807,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007396012612994e-05,
"loss": 3.9744,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6999010065102474e-05,
"loss": 3.9612,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990624117591954e-05,
"loss": 3.9638,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982238170081434e-05,
"loss": 3.9702,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697386860137464e-05,
"loss": 3.9561,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696548265386412e-05,
"loss": 3.9582,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69570967063536e-05,
"loss": 3.9692,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694872713764681e-05,
"loss": 3.9609,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694034119013629e-05,
"loss": 3.9485,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693195524262577e-05,
"loss": 3.951,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692356929511526e-05,
"loss": 3.9519,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691519972640847e-05,
"loss": 3.9721,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906830157701677e-05,
"loss": 3.9661,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898444210191157e-05,
"loss": 3.9553,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890058262680636e-05,
"loss": 3.9627,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881672315170116e-05,
"loss": 3.9588,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873286367659596e-05,
"loss": 3.9628,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864900420149076e-05,
"loss": 3.9518,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856530851442285e-05,
"loss": 3.9628,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848144903931765e-05,
"loss": 3.9563,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839758956421245e-05,
"loss": 3.9564,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831373008910725e-05,
"loss": 3.9508,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822987061400205e-05,
"loss": 3.9573,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681460111388969e-05,
"loss": 3.9572,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806215166379165e-05,
"loss": 3.9569,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679784559767238e-05,
"loss": 3.944,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678945965016186e-05,
"loss": 3.9499,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678107370265134e-05,
"loss": 3.9473,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772687755140814e-05,
"loss": 3.9506,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676431818643403e-05,
"loss": 3.9539,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9366,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674754629141298e-05,
"loss": 3.9499,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673916034390246e-05,
"loss": 3.9456,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673079077519568e-05,
"loss": 3.9541,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672240482768516e-05,
"loss": 3.9344,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671401888017464e-05,
"loss": 3.9444,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670563293266412e-05,
"loss": 3.9554,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697263363957335e-05,
"loss": 3.9412,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688877416446815e-05,
"loss": 3.9242,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668049146893629e-05,
"loss": 3.9413,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667210552142577e-05,
"loss": 3.9457,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666371957391525e-05,
"loss": 3.9465,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665533362640473e-05,
"loss": 3.944,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664694767889421e-05,
"loss": 3.9316,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663856173138369e-05,
"loss": 3.9337,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66301921626769e-05,
"loss": 3.9435,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621806215166383e-05,
"loss": 3.9256,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613420267655863e-05,
"loss": 3.9317,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660505069894907e-05,
"loss": 3.9393,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659666475143855e-05,
"loss": 3.9399,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658827880392803e-05,
"loss": 3.9166,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657989285641751e-05,
"loss": 3.9318,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657152328771072e-05,
"loss": 3.9236,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.65631373402002e-05,
"loss": 3.9377,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655475139268968e-05,
"loss": 3.9326,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654636544517916e-05,
"loss": 3.9241,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653797949766864e-05,
"loss": 3.9405,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652959355015812e-05,
"loss": 3.9364,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652122398145134e-05,
"loss": 3.9257,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651283803394082e-05,
"loss": 3.933,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.65044520864303e-05,
"loss": 3.9326,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649606613891978e-05,
"loss": 3.9296,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648768019140926e-05,
"loss": 3.9167,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479310622702466e-05,
"loss": 3.9313,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470924675191946e-05,
"loss": 3.9247,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462538727681426e-05,
"loss": 3.9307,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454152780170906e-05,
"loss": 3.9273,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445766832660386e-05,
"loss": 3.9306,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437380885149866e-05,
"loss": 3.9167,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428994937639346e-05,
"loss": 3.9213,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420625368932555e-05,
"loss": 3.9104,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412239421422035e-05,
"loss": 3.9375,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640385347391152e-05,
"loss": 3.9278,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395467526401e-05,
"loss": 3.926,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387081578890475e-05,
"loss": 3.9138,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378695631379955e-05,
"loss": 3.9308,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370309683869435e-05,
"loss": 3.9293,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636194011516265e-05,
"loss": 3.918,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353554167652124e-05,
"loss": 3.9178,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345168220141604e-05,
"loss": 3.9265,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336782272631084e-05,
"loss": 3.9198,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632841270392429e-05,
"loss": 3.9307,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632002675641377e-05,
"loss": 3.9118,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631164080890326e-05,
"loss": 3.9234,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630325486139274e-05,
"loss": 3.9179,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629486891388222e-05,
"loss": 3.9117,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628649934517543e-05,
"loss": 3.9342,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627811339766491e-05,
"loss": 3.911,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626972745015439e-05,
"loss": 3.9201,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626134150264387e-05,
"loss": 3.9199,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625295555513335e-05,
"loss": 3.9168,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9984824657440186,
"eval_runtime": 301.9446,
"eval_samples_per_second": 1263.778,
"eval_steps_per_second": 39.494,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624458598642656e-05,
"loss": 3.9098,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623620003891604e-05,
"loss": 3.911,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622781409140552e-05,
"loss": 3.9206,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219428143895e-05,
"loss": 3.9151,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621104219638448e-05,
"loss": 3.9213,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620265624887396e-05,
"loss": 3.9002,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619428668016717e-05,
"loss": 3.9089,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618590073265665e-05,
"loss": 3.8984,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617751478514613e-05,
"loss": 3.9194,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616912883763561e-05,
"loss": 3.902,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616074289012509e-05,
"loss": 3.9126,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.61523733214183e-05,
"loss": 3.9138,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614400375271151e-05,
"loss": 3.9052,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613561780520099e-05,
"loss": 3.8957,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612723185769047e-05,
"loss": 3.8955,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611884591017995e-05,
"loss": 3.8926,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611045996266943e-05,
"loss": 3.9027,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610207401515891e-05,
"loss": 3.8956,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609368806764839e-05,
"loss": 3.8958,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608530212013788e-05,
"loss": 3.9183,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076932551431087e-05,
"loss": 3.901,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068546603920566e-05,
"loss": 3.8972,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6060160656410046e-05,
"loss": 3.9061,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051774708899526e-05,
"loss": 3.9018,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.6043388761389006e-05,
"loss": 3.895,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603500281387848e-05,
"loss": 3.8876,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602661686636796e-05,
"loss": 3.903,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018247297661175e-05,
"loss": 3.8838,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009861350150655e-05,
"loss": 3.8878,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600147540264013e-05,
"loss": 3.8917,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.5993089455129615e-05,
"loss": 3.8875,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598471988642283e-05,
"loss": 3.9014,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597633393891231e-05,
"loss": 3.8932,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5967947991401784e-05,
"loss": 3.8841,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.5959562043891264e-05,
"loss": 3.8968,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595119247518448e-05,
"loss": 3.906,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594280652767395e-05,
"loss": 3.8821,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593442058016343e-05,
"loss": 3.8938,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592603463265291e-05,
"loss": 3.8759,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591764868514239e-05,
"loss": 3.8923,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590926273763187e-05,
"loss": 3.8776,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590087679012135e-05,
"loss": 3.9006,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589250722141457e-05,
"loss": 3.8902,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588412127390405e-05,
"loss": 3.8842,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587573532639353e-05,
"loss": 3.8921,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586734937888301e-05,
"loss": 3.8818,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585896343137249e-05,
"loss": 3.8913,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.58505938626657e-05,
"loss": 3.876,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584220791515518e-05,
"loss": 3.8732,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583382196764466e-05,
"loss": 3.8909,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582543602013414e-05,
"loss": 3.885,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581705007262362e-05,
"loss": 3.8855,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580868050391683e-05,
"loss": 3.8731,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580029455640631e-05,
"loss": 3.8824,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579190860889579e-05,
"loss": 3.8666,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783522661385267e-05,
"loss": 3.8883,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577513671387475e-05,
"loss": 3.8794,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576675076636423e-05,
"loss": 3.8931,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575836481885371e-05,
"loss": 3.8846,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.574999525014692e-05,
"loss": 3.8747,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.57416093026364e-05,
"loss": 3.8706,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573322335512588e-05,
"loss": 3.8805,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572483740761536e-05,
"loss": 3.8686,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571646783890857e-05,
"loss": 3.8693,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570808189139805e-05,
"loss": 3.8785,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569969594388753e-05,
"loss": 3.8764,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569130999637701e-05,
"loss": 3.8599,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568294042767022e-05,
"loss": 3.8627,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567455448015971e-05,
"loss": 3.8617,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566616853264919e-05,
"loss": 3.8875,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565778258513867e-05,
"loss": 3.8774,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.5649413016431876e-05,
"loss": 3.8702,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.5641027068921356e-05,
"loss": 3.8749,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.5632641121410836e-05,
"loss": 3.8698,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624255173900316e-05,
"loss": 3.8818,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615885605193525e-05,
"loss": 3.8614,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.5607499657683005e-05,
"loss": 3.882,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.5599113710172485e-05,
"loss": 3.8668,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.5590727762661965e-05,
"loss": 3.8714,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582341815151445e-05,
"loss": 3.8709,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.5573972246444654e-05,
"loss": 3.8682,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556558629893414e-05,
"loss": 3.8775,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.5557200351423614e-05,
"loss": 3.8687,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.5548814403913094e-05,
"loss": 3.859,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554044483520631e-05,
"loss": 3.8678,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553205888769579e-05,
"loss": 3.8602,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552367294018526e-05,
"loss": 3.8738,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551528699267474e-05,
"loss": 3.8687,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550690104516422e-05,
"loss": 3.8534,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549853147645744e-05,
"loss": 3.869,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549014552894691e-05,
"loss": 3.8612,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548175958143639e-05,
"loss": 3.8694,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547337363392588e-05,
"loss": 3.855,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546498768641536e-05,
"loss": 3.8629,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545661811770857e-05,
"loss": 3.873,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544823217019805e-05,
"loss": 3.8582,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543984622268753e-05,
"loss": 3.8465,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543146027517701e-05,
"loss": 3.8608,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.5423090706470216e-05,
"loss": 3.859,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.5414704758959696e-05,
"loss": 3.8708,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406318811449176e-05,
"loss": 3.8614,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5397932863938656e-05,
"loss": 3.8536,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389546916428136e-05,
"loss": 3.8537,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5381177347721345e-05,
"loss": 3.8649,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537279140021083e-05,
"loss": 3.8442,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536440545270031e-05,
"loss": 3.8552,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535601950518979e-05,
"loss": 3.8584,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347649936483e-05,
"loss": 3.8616,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533926398897248e-05,
"loss": 3.8342,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533087804146196e-05,
"loss": 3.8534,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532249209395144e-05,
"loss": 3.8518,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531410614644092e-05,
"loss": 3.8505,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530573657773413e-05,
"loss": 3.856,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529735063022361e-05,
"loss": 3.8442,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528896468271309e-05,
"loss": 3.8653,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528057873520257e-05,
"loss": 3.8551,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.5272209166495786e-05,
"loss": 3.8496,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.5263823218985266e-05,
"loss": 3.8554,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.5255437271474746e-05,
"loss": 3.8544,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.5247051323964226e-05,
"loss": 3.8542,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.5238681755257435e-05,
"loss": 3.8346,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.5230295807746915e-05,
"loss": 3.8585,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.5221909860236395e-05,
"loss": 3.8459,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.5213523912725875e-05,
"loss": 3.8533,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.5205154344019084e-05,
"loss": 3.8504,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.5196768396508564e-05,
"loss": 3.8575,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.5188382448998044e-05,
"loss": 3.8456,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5179996501487524e-05,
"loss": 3.8406,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171610553977003e-05,
"loss": 3.8373,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163224606466483e-05,
"loss": 3.8584,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.51548550377597e-05,
"loss": 3.8526,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514646909024918e-05,
"loss": 3.8519,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513808314273866e-05,
"loss": 3.8405,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512969719522814e-05,
"loss": 3.8548,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512132762652135e-05,
"loss": 3.8525,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511294167901083e-05,
"loss": 3.8423,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510455573150031e-05,
"loss": 3.8436,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509616978398979e-05,
"loss": 3.8515,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087800215283e-05,
"loss": 3.85,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507941426777248e-05,
"loss": 3.8545,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507102832026196e-05,
"loss": 3.8374,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506264237275144e-05,
"loss": 3.8507,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505427280404465e-05,
"loss": 3.8419,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504588685653413e-05,
"loss": 3.8413,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503751728782734e-05,
"loss": 3.8561,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502913134031682e-05,
"loss": 3.8427,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.50207453928063e-05,
"loss": 3.8475,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501235944529578e-05,
"loss": 3.8416,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500397349778526e-05,
"loss": 3.8483,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.95876407623291,
"eval_runtime": 301.8238,
"eval_samples_per_second": 1264.284,
"eval_steps_per_second": 39.51,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499558755027474e-05,
"loss": 3.8307,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987201602764215e-05,
"loss": 3.8409,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978815655253695e-05,
"loss": 3.8487,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970429707743175e-05,
"loss": 3.8414,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496204376023266e-05,
"loss": 3.8517,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495365781272214e-05,
"loss": 3.8271,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494527186521162e-05,
"loss": 3.8389,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.49368859177011e-05,
"loss": 3.8284,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492851634899431e-05,
"loss": 3.8454,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.492013040148379e-05,
"loss": 3.8379,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491174445397327e-05,
"loss": 3.8384,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490335850646275e-05,
"loss": 3.8372,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489498893775596e-05,
"loss": 3.8335,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488660299024544e-05,
"loss": 3.826,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487821704273492e-05,
"loss": 3.8286,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.48698310952244e-05,
"loss": 3.8191,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486144514771388e-05,
"loss": 3.8342,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485305920020336e-05,
"loss": 3.8253,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484467325269284e-05,
"loss": 3.8245,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.4836287305182326e-05,
"loss": 3.8538,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.4827917736475535e-05,
"loss": 3.8285,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.4819531788965015e-05,
"loss": 3.833,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.4811145841454495e-05,
"loss": 3.8358,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.4802759893943975e-05,
"loss": 3.8305,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.4794390325237184e-05,
"loss": 3.8262,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.4786004377726664e-05,
"loss": 3.8206,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.4777618430216144e-05,
"loss": 3.8346,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.4769232482705624e-05,
"loss": 3.8132,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476086291399883e-05,
"loss": 3.8223,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475247696648831e-05,
"loss": 3.8218,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474409101897779e-05,
"loss": 3.8234,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473570507146728e-05,
"loss": 3.8342,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472733550276049e-05,
"loss": 3.826,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471894955524997e-05,
"loss": 3.8221,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471056360773945e-05,
"loss": 3.8291,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470217766022893e-05,
"loss": 3.8356,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469380809152214e-05,
"loss": 3.8175,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468542214401162e-05,
"loss": 3.8287,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.46770361965011e-05,
"loss": 3.8109,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466865024899058e-05,
"loss": 3.8244,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466028068028379e-05,
"loss": 3.8088,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465189473277327e-05,
"loss": 3.8361,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464350878526275e-05,
"loss": 3.824,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463512283775223e-05,
"loss": 3.819,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462675326904544e-05,
"loss": 3.8252,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461836732153492e-05,
"loss": 3.8175,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.46099813740244e-05,
"loss": 3.8246,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460159542651388e-05,
"loss": 3.812,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459322585780709e-05,
"loss": 3.8076,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.458483991029657e-05,
"loss": 3.8279,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457645396278605e-05,
"loss": 3.819,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4568068015275525e-05,
"loss": 3.8205,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455969844656874e-05,
"loss": 3.8109,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455131249905822e-05,
"loss": 3.8171,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.45429265515477e-05,
"loss": 3.8062,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453454060403718e-05,
"loss": 3.822,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4526171035330396e-05,
"loss": 3.8159,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.4517785087819876e-05,
"loss": 3.8301,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.4509399140309356e-05,
"loss": 3.8207,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450101319279883e-05,
"loss": 3.8088,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.4492643624092045e-05,
"loss": 3.8105,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.4484257676581525e-05,
"loss": 3.8158,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.4475871729071e-05,
"loss": 3.8042,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446748578156048e-05,
"loss": 3.8108,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445909983404996e-05,
"loss": 3.8128,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.4450730265343174e-05,
"loss": 3.8153,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.4442344317832654e-05,
"loss": 3.797,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.4433958370322134e-05,
"loss": 3.802,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.4425572422811614e-05,
"loss": 3.8003,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441720285410482e-05,
"loss": 3.8203,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.44088169065943e-05,
"loss": 3.8119,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440043095908378e-05,
"loss": 3.8095,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439204501157326e-05,
"loss": 3.812,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438367544286647e-05,
"loss": 3.8083,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437528949535595e-05,
"loss": 3.8248,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436690354784543e-05,
"loss": 3.7985,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435851760033491e-05,
"loss": 3.8172,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435014803162813e-05,
"loss": 3.8087,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434176208411761e-05,
"loss": 3.8091,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433337613660709e-05,
"loss": 3.8111,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432499018909657e-05,
"loss": 3.8088,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431660424158605e-05,
"loss": 3.8137,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4308234672879257e-05,
"loss": 3.8094,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299848725368737e-05,
"loss": 3.7946,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291462777858217e-05,
"loss": 3.8082,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4283076830347696e-05,
"loss": 3.8007,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274707261640906e-05,
"loss": 3.8106,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266321314130386e-05,
"loss": 3.8063,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257935366619865e-05,
"loss": 3.7942,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249549419109345e-05,
"loss": 3.8091,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424117985040256e-05,
"loss": 3.8022,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423279390289204e-05,
"loss": 3.8116,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422440795538152e-05,
"loss": 3.7914,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4216022007871e-05,
"loss": 3.8079,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420763606036048e-05,
"loss": 3.8198,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419926649165369e-05,
"loss": 3.7969,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419088054414317e-05,
"loss": 3.7833,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418249459663265e-05,
"loss": 3.7998,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417410864912213e-05,
"loss": 3.8047,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416573908041534e-05,
"loss": 3.8078,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415735313290482e-05,
"loss": 3.8064,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.41489671853943e-05,
"loss": 3.7962,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414058123788378e-05,
"loss": 3.7964,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4132211669176995e-05,
"loss": 3.8048,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123825721666475e-05,
"loss": 3.7864,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115439774155955e-05,
"loss": 3.7954,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4107053826645435e-05,
"loss": 3.7995,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098684257938644e-05,
"loss": 3.8039,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.4090298310428124e-05,
"loss": 3.7766,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081912362917604e-05,
"loss": 3.7958,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.4073526415407084e-05,
"loss": 3.7919,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.4065140467896564e-05,
"loss": 3.7968,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405677089918977e-05,
"loss": 3.794,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404838495167925e-05,
"loss": 3.7898,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.403999900416873e-05,
"loss": 3.8031,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403161305665822e-05,
"loss": 3.8022,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402325986675516e-05,
"loss": 3.7912,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401487391924464e-05,
"loss": 3.8006,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400648797173412e-05,
"loss": 3.795,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.39981020242236e-05,
"loss": 3.7997,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398971607671308e-05,
"loss": 3.7813,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398133012920256e-05,
"loss": 3.8033,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397294418169204e-05,
"loss": 3.7836,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396455823418152e-05,
"loss": 3.7969,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3956188665474726e-05,
"loss": 3.7886,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.3947802717964206e-05,
"loss": 3.8045,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939416770453686e-05,
"loss": 3.7922,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393103082294317e-05,
"loss": 3.7867,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392266125423638e-05,
"loss": 3.7787,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391427530672586e-05,
"loss": 3.8065,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390588935921534e-05,
"loss": 3.7906,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389750341170482e-05,
"loss": 3.7981,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388913384299803e-05,
"loss": 3.7835,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388074789548751e-05,
"loss": 3.7991,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387236194797699e-05,
"loss": 3.7994,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386397600046647e-05,
"loss": 3.7871,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385560643175968e-05,
"loss": 3.786,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384722048424916e-05,
"loss": 3.7957,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383883453673864e-05,
"loss": 3.7954,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383044858922813e-05,
"loss": 3.8006,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3822079020521336e-05,
"loss": 3.7801,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813693073010816e-05,
"loss": 3.7946,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3805307125500296e-05,
"loss": 3.7883,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796921177989776e-05,
"loss": 3.7911,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788551609282985e-05,
"loss": 3.7994,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3780165661772465e-05,
"loss": 3.7842,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771779714261945e-05,
"loss": 3.7989,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763393766751425e-05,
"loss": 3.7841,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.37550078192409e-05,
"loss": 3.799,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.9349238872528076,
"eval_runtime": 302.9482,
"eval_samples_per_second": 1259.592,
"eval_steps_per_second": 39.363,
"step": 381600
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 2.475910139818752e+17,
"trial_name": null,
"trial_params": null
}