abhinavp's picture
Training in progress, epoch 0, checkpoint
6da7469 verified
{
"best_metric": 3.86488938331604,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl/transformer/3/checkpoints/checkpoint-534233",
"epoch": 0.025000278439663435,
"eval_steps": 10,
"global_step": 534233,
"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": 10.9675,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8442,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.2012,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9806,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8323,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7129,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6086,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5465,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4913,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4143,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3845,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3436,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2855,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 5.2356,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 5.2099,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 5.179,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 5.1463,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.1011,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0832,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.053,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0275,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.0107,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 4.9884,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9628,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9434,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.9274,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 4.9014,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 4.8911,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 4.8564,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.86,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 4.8264,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 4.8159,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 4.8184,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.8007,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 4.7742,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 4.7608,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 4.7629,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.7439,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.733,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.718,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6988,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6883,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6767,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6765,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6665,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6614,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.646,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6418,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6451,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 4.6211,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.615,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.6033,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.6149,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 4.5787,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5958,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5704,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5678,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5701,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 4.5601,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5459,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5362,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5251,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 4.5374,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.5237,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.5137,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5123,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.5038,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 4.4844,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.506,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4831,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4796,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4907,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4678,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4832,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4781,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4666,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4697,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4446,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4413,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4438,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.446,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4378,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4216,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.4131,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.4157,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.418,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.4178,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.4195,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.4155,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 4.4014,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3891,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3868,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3937,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 4.3902,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.3725,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 4.3762,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3777,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3801,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3747,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3714,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3722,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3612,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.361,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.3674,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3497,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3561,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3367,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3325,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.333,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.34,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3349,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3127,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3165,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3257,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3343,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3187,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.3251,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.3164,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.318,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.3093,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.304,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.2982,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.3054,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2896,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.3007,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2915,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.3014,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2771,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.2887,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2973,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2753,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2934,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2797,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2806,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.2737,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.2675,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.2702,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2759,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2784,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2678,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2718,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2645,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.252,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.26,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2477,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2511,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.2488,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2454,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2428,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2434,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.205959320068359,
"eval_runtime": 565.7702,
"eval_samples_per_second": 674.463,
"eval_steps_per_second": 21.077,
"step": 76319
},
{
"epoch": 0.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.2475,
"step": 76800
},
{
"epoch": 0.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.2426,
"step": 77312
},
{
"epoch": 0.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2332,
"step": 77824
},
{
"epoch": 0.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2346,
"step": 78336
},
{
"epoch": 0.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2327,
"step": 78848
},
{
"epoch": 0.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2101,
"step": 79360
},
{
"epoch": 0.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2252,
"step": 79872
},
{
"epoch": 0.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.223,
"step": 80384
},
{
"epoch": 0.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.2142,
"step": 80896
},
{
"epoch": 0.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.2241,
"step": 81408
},
{
"epoch": 0.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.2248,
"step": 81920
},
{
"epoch": 0.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.2106,
"step": 82432
},
{
"epoch": 0.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.2068,
"step": 82944
},
{
"epoch": 0.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.2103,
"step": 83456
},
{
"epoch": 0.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.2078,
"step": 83968
},
{
"epoch": 0.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.1978,
"step": 84480
},
{
"epoch": 0.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.2011,
"step": 84992
},
{
"epoch": 0.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.2003,
"step": 85504
},
{
"epoch": 0.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.1976,
"step": 86016
},
{
"epoch": 0.0,
"learning_rate": 4.858326623483405e-05,
"loss": 4.2016,
"step": 86528
},
{
"epoch": 0.0,
"learning_rate": 4.857488028732352e-05,
"loss": 4.1995,
"step": 87040
},
{
"epoch": 0.0,
"learning_rate": 4.856651071861674e-05,
"loss": 4.1999,
"step": 87552
},
{
"epoch": 0.0,
"learning_rate": 4.8558124771106226e-05,
"loss": 4.1955,
"step": 88064
},
{
"epoch": 0.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.1936,
"step": 88576
},
{
"epoch": 0.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.1926,
"step": 89088
},
{
"epoch": 0.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.1859,
"step": 89600
},
{
"epoch": 0.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.1931,
"step": 90112
},
{
"epoch": 0.0,
"learning_rate": 4.851621141235735e-05,
"loss": 4.1735,
"step": 90624
},
{
"epoch": 0.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.1868,
"step": 91136
},
{
"epoch": 0.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.1705,
"step": 91648
},
{
"epoch": 0.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.1747,
"step": 92160
},
{
"epoch": 0.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.1838,
"step": 92672
},
{
"epoch": 0.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.1834,
"step": 93184
},
{
"epoch": 0.01,
"learning_rate": 4.8465912106097964e-05,
"loss": 4.1698,
"step": 93696
},
{
"epoch": 0.01,
"learning_rate": 4.8457526158587444e-05,
"loss": 4.1657,
"step": 94208
},
{
"epoch": 0.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.178,
"step": 94720
},
{
"epoch": 0.01,
"learning_rate": 4.844077064237013e-05,
"loss": 4.1706,
"step": 95232
},
{
"epoch": 0.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.1692,
"step": 95744
},
{
"epoch": 0.01,
"learning_rate": 4.842399874734909e-05,
"loss": 4.1629,
"step": 96256
},
{
"epoch": 0.01,
"learning_rate": 4.841561279983857e-05,
"loss": 4.1518,
"step": 96768
},
{
"epoch": 0.01,
"learning_rate": 4.840722685232805e-05,
"loss": 4.1496,
"step": 97280
},
{
"epoch": 0.01,
"learning_rate": 4.839884090481753e-05,
"loss": 4.1509,
"step": 97792
},
{
"epoch": 0.01,
"learning_rate": 4.839045495730701e-05,
"loss": 4.1601,
"step": 98304
},
{
"epoch": 0.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.1478,
"step": 98816
},
{
"epoch": 0.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.1522,
"step": 99328
},
{
"epoch": 0.01,
"learning_rate": 4.836531349357918e-05,
"loss": 4.1496,
"step": 99840
},
{
"epoch": 0.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.1507,
"step": 100352
},
{
"epoch": 0.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.1597,
"step": 100864
},
{
"epoch": 0.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.1399,
"step": 101376
},
{
"epoch": 0.01,
"learning_rate": 4.833178608234084e-05,
"loss": 4.1442,
"step": 101888
},
{
"epoch": 0.01,
"learning_rate": 4.832340013483032e-05,
"loss": 4.1353,
"step": 102400
},
{
"epoch": 0.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.1579,
"step": 102912
},
{
"epoch": 0.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.1281,
"step": 103424
},
{
"epoch": 0.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.1438,
"step": 103936
},
{
"epoch": 0.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.1271,
"step": 104448
},
{
"epoch": 0.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.1349,
"step": 104960
},
{
"epoch": 0.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.1364,
"step": 105472
},
{
"epoch": 0.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.1352,
"step": 105984
},
{
"epoch": 0.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.1261,
"step": 106496
},
{
"epoch": 0.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.1261,
"step": 107008
},
{
"epoch": 0.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.1123,
"step": 107520
},
{
"epoch": 0.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.1303,
"step": 108032
},
{
"epoch": 0.01,
"learning_rate": 4.822281790111527e-05,
"loss": 4.1252,
"step": 108544
},
{
"epoch": 0.01,
"learning_rate": 4.821443195360475e-05,
"loss": 4.1197,
"step": 109056
},
{
"epoch": 0.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.1174,
"step": 109568
},
{
"epoch": 0.01,
"learning_rate": 4.819766005858371e-05,
"loss": 4.1198,
"step": 110080
},
{
"epoch": 0.01,
"learning_rate": 4.8189274111073184e-05,
"loss": 4.1012,
"step": 110592
},
{
"epoch": 0.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.1235,
"step": 111104
},
{
"epoch": 0.01,
"learning_rate": 4.817251859485588e-05,
"loss": 4.107,
"step": 111616
},
{
"epoch": 0.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.111,
"step": 112128
},
{
"epoch": 0.01,
"learning_rate": 4.815574669983483e-05,
"loss": 4.1198,
"step": 112640
},
{
"epoch": 0.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.1071,
"step": 113152
},
{
"epoch": 0.01,
"learning_rate": 4.8138991183617535e-05,
"loss": 4.1186,
"step": 113664
},
{
"epoch": 0.01,
"learning_rate": 4.813060523610701e-05,
"loss": 4.1231,
"step": 114176
},
{
"epoch": 0.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.1154,
"step": 114688
},
{
"epoch": 0.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.1182,
"step": 115200
},
{
"epoch": 0.01,
"learning_rate": 4.8105463772379184e-05,
"loss": 4.1007,
"step": 115712
},
{
"epoch": 0.01,
"learning_rate": 4.809707782486866e-05,
"loss": 4.0952,
"step": 116224
},
{
"epoch": 0.01,
"learning_rate": 4.808869187735814e-05,
"loss": 4.1051,
"step": 116736
},
{
"epoch": 0.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.1128,
"step": 117248
},
{
"epoch": 0.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.102,
"step": 117760
},
{
"epoch": 0.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.0963,
"step": 118272
},
{
"epoch": 0.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.0846,
"step": 118784
},
{
"epoch": 0.01,
"learning_rate": 4.8046794897413e-05,
"loss": 4.0897,
"step": 119296
},
{
"epoch": 0.01,
"learning_rate": 4.803840894990248e-05,
"loss": 4.0916,
"step": 119808
},
{
"epoch": 0.01,
"learning_rate": 4.80300393811957e-05,
"loss": 4.0947,
"step": 120320
},
{
"epoch": 0.01,
"learning_rate": 4.802165343368518e-05,
"loss": 4.1023,
"step": 120832
},
{
"epoch": 0.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.1006,
"step": 121344
},
{
"epoch": 0.01,
"learning_rate": 4.800488153866413e-05,
"loss": 4.0898,
"step": 121856
},
{
"epoch": 0.02,
"learning_rate": 4.799651196995735e-05,
"loss": 4.0828,
"step": 122368
},
{
"epoch": 0.02,
"learning_rate": 4.798812602244683e-05,
"loss": 4.0794,
"step": 122880
},
{
"epoch": 0.02,
"learning_rate": 4.79797400749363e-05,
"loss": 4.0875,
"step": 123392
},
{
"epoch": 0.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.0872,
"step": 123904
},
{
"epoch": 0.02,
"learning_rate": 4.796296817991526e-05,
"loss": 4.0796,
"step": 124416
},
{
"epoch": 0.02,
"learning_rate": 4.795458223240474e-05,
"loss": 4.0793,
"step": 124928
},
{
"epoch": 0.02,
"learning_rate": 4.794619628489423e-05,
"loss": 4.0848,
"step": 125440
},
{
"epoch": 0.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.0899,
"step": 125952
},
{
"epoch": 0.02,
"learning_rate": 4.7929440768676916e-05,
"loss": 4.0816,
"step": 126464
},
{
"epoch": 0.02,
"learning_rate": 4.7921054821166396e-05,
"loss": 4.0838,
"step": 126976
},
{
"epoch": 0.02,
"learning_rate": 4.7912668873655876e-05,
"loss": 4.0908,
"step": 127488
},
{
"epoch": 0.02,
"learning_rate": 4.7904282926145356e-05,
"loss": 4.0791,
"step": 128000
},
{
"epoch": 0.02,
"learning_rate": 4.7895913357438565e-05,
"loss": 4.0765,
"step": 128512
},
{
"epoch": 0.02,
"learning_rate": 4.7887527409928045e-05,
"loss": 4.0892,
"step": 129024
},
{
"epoch": 0.02,
"learning_rate": 4.7879157841221254e-05,
"loss": 4.0735,
"step": 129536
},
{
"epoch": 0.02,
"learning_rate": 4.7870771893710734e-05,
"loss": 4.0849,
"step": 130048
},
{
"epoch": 0.02,
"learning_rate": 4.7862385946200214e-05,
"loss": 4.0702,
"step": 130560
},
{
"epoch": 0.02,
"learning_rate": 4.7853999998689694e-05,
"loss": 4.0594,
"step": 131072
},
{
"epoch": 0.02,
"learning_rate": 4.784561405117918e-05,
"loss": 4.0671,
"step": 131584
},
{
"epoch": 0.02,
"learning_rate": 4.783722810366866e-05,
"loss": 4.0748,
"step": 132096
},
{
"epoch": 0.02,
"learning_rate": 4.782885853496187e-05,
"loss": 4.0666,
"step": 132608
},
{
"epoch": 0.02,
"learning_rate": 4.782047258745135e-05,
"loss": 4.0558,
"step": 133120
},
{
"epoch": 0.02,
"learning_rate": 4.781208663994083e-05,
"loss": 4.0547,
"step": 133632
},
{
"epoch": 0.02,
"learning_rate": 4.780370069243031e-05,
"loss": 4.0654,
"step": 134144
},
{
"epoch": 0.02,
"learning_rate": 4.779531474491979e-05,
"loss": 4.0758,
"step": 134656
},
{
"epoch": 0.02,
"learning_rate": 4.778692879740927e-05,
"loss": 4.0633,
"step": 135168
},
{
"epoch": 0.02,
"learning_rate": 4.777855922870248e-05,
"loss": 4.0765,
"step": 135680
},
{
"epoch": 0.02,
"learning_rate": 4.777017328119196e-05,
"loss": 4.0637,
"step": 136192
},
{
"epoch": 0.02,
"learning_rate": 4.776178733368144e-05,
"loss": 4.0648,
"step": 136704
},
{
"epoch": 0.02,
"learning_rate": 4.775340138617092e-05,
"loss": 4.0633,
"step": 137216
},
{
"epoch": 0.02,
"learning_rate": 4.77450154386604e-05,
"loss": 4.0539,
"step": 137728
},
{
"epoch": 0.02,
"learning_rate": 4.773662949114988e-05,
"loss": 4.0509,
"step": 138240
},
{
"epoch": 0.02,
"learning_rate": 4.772824354363936e-05,
"loss": 4.0635,
"step": 138752
},
{
"epoch": 0.02,
"learning_rate": 4.7719857596128845e-05,
"loss": 4.0527,
"step": 139264
},
{
"epoch": 0.02,
"learning_rate": 4.7711488027422054e-05,
"loss": 4.0529,
"step": 139776
},
{
"epoch": 0.02,
"learning_rate": 4.7703102079911534e-05,
"loss": 4.0554,
"step": 140288
},
{
"epoch": 0.02,
"learning_rate": 4.7694716132401014e-05,
"loss": 4.0637,
"step": 140800
},
{
"epoch": 0.02,
"learning_rate": 4.7686330184890494e-05,
"loss": 4.0428,
"step": 141312
},
{
"epoch": 0.02,
"learning_rate": 4.76779606161837e-05,
"loss": 4.0467,
"step": 141824
},
{
"epoch": 0.02,
"learning_rate": 4.766957466867318e-05,
"loss": 4.0652,
"step": 142336
},
{
"epoch": 0.02,
"learning_rate": 4.766118872116266e-05,
"loss": 4.0449,
"step": 142848
},
{
"epoch": 0.02,
"learning_rate": 4.7652802773652136e-05,
"loss": 4.0646,
"step": 143360
},
{
"epoch": 0.02,
"learning_rate": 4.764443320494535e-05,
"loss": 4.0475,
"step": 143872
},
{
"epoch": 0.02,
"learning_rate": 4.763604725743483e-05,
"loss": 4.0569,
"step": 144384
},
{
"epoch": 0.02,
"learning_rate": 4.762766130992431e-05,
"loss": 4.0462,
"step": 144896
},
{
"epoch": 0.02,
"learning_rate": 4.761927536241379e-05,
"loss": 4.0408,
"step": 145408
},
{
"epoch": 0.02,
"learning_rate": 4.761090579370701e-05,
"loss": 4.0461,
"step": 145920
},
{
"epoch": 0.02,
"learning_rate": 4.760251984619649e-05,
"loss": 4.0514,
"step": 146432
},
{
"epoch": 0.02,
"learning_rate": 4.759413389868596e-05,
"loss": 4.0614,
"step": 146944
},
{
"epoch": 0.02,
"learning_rate": 4.758574795117544e-05,
"loss": 4.0508,
"step": 147456
},
{
"epoch": 0.02,
"learning_rate": 4.757737838246866e-05,
"loss": 4.0521,
"step": 147968
},
{
"epoch": 0.02,
"learning_rate": 4.7568992434958137e-05,
"loss": 4.0439,
"step": 148480
},
{
"epoch": 0.02,
"learning_rate": 4.756060648744761e-05,
"loss": 4.0352,
"step": 148992
},
{
"epoch": 0.02,
"learning_rate": 4.755222053993709e-05,
"loss": 4.0481,
"step": 149504
},
{
"epoch": 0.02,
"learning_rate": 4.7543850971230306e-05,
"loss": 4.0345,
"step": 150016
},
{
"epoch": 0.02,
"learning_rate": 4.7535465023719786e-05,
"loss": 4.0368,
"step": 150528
},
{
"epoch": 0.02,
"learning_rate": 4.7527079076209266e-05,
"loss": 4.0407,
"step": 151040
},
{
"epoch": 0.02,
"learning_rate": 4.7518693128698745e-05,
"loss": 4.0282,
"step": 151552
},
{
"epoch": 0.02,
"learning_rate": 4.751032355999196e-05,
"loss": 4.0357,
"step": 152064
},
{
"epoch": 0.02,
"learning_rate": 4.7501937612481435e-05,
"loss": 4.0345,
"step": 152576
},
{
"epoch": 0.03,
"eval_loss": 4.034010410308838,
"eval_runtime": 582.8384,
"eval_samples_per_second": 654.712,
"eval_steps_per_second": 20.46,
"step": 152638
},
{
"epoch": 0.0,
"learning_rate": 4.749356804377465e-05,
"loss": 4.0415,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748518209626413e-05,
"loss": 4.0382,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747679614875361e-05,
"loss": 4.0307,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468410201243084e-05,
"loss": 4.0307,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460024253732563e-05,
"loss": 4.0331,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451638306222043e-05,
"loss": 4.0119,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744325235871152e-05,
"loss": 4.0289,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434866411201e-05,
"loss": 4.024,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742648046369049e-05,
"loss": 4.0164,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.74181108949837e-05,
"loss": 4.0303,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740972494747318e-05,
"loss": 4.033,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740133899996266e-05,
"loss": 4.0179,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739295305245214e-05,
"loss": 4.0138,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738456710494162e-05,
"loss": 4.0195,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.73761811574311e-05,
"loss": 4.0197,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736779520992058e-05,
"loss": 4.0116,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735940926241006e-05,
"loss": 4.0119,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735103969370327e-05,
"loss": 4.0117,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734265374619275e-05,
"loss": 4.0149,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733426779868223e-05,
"loss": 4.0168,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732588185117171e-05,
"loss": 4.0169,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317512282464924e-05,
"loss": 4.0215,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7309126334954404e-05,
"loss": 4.0178,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300740387443884e-05,
"loss": 4.0095,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292354439933364e-05,
"loss": 4.0147,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728398487122657e-05,
"loss": 4.0099,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727559892371605e-05,
"loss": 4.0132,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726721297620553e-05,
"loss": 3.9993,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725882702869501e-05,
"loss": 4.01,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725045745998822e-05,
"loss": 3.9968,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.72420715124777e-05,
"loss": 4.0032,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723368556496718e-05,
"loss": 4.0119,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722529961745666e-05,
"loss": 4.011,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721693004874988e-05,
"loss": 4.0004,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720854410123936e-05,
"loss": 3.997,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720015815372884e-05,
"loss": 4.0134,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719177220621832e-05,
"loss": 3.9958,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183402637511526e-05,
"loss": 4.0028,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175016690001006e-05,
"loss": 3.9984,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166630742490486e-05,
"loss": 3.9849,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158244794979966e-05,
"loss": 3.9859,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149875226273175e-05,
"loss": 3.9844,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141489278762655e-05,
"loss": 4.0028,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133103331252135e-05,
"loss": 3.989,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124717383741615e-05,
"loss": 3.9883,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711634781503483e-05,
"loss": 3.9893,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710796186752431e-05,
"loss": 3.9892,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709957592001379e-05,
"loss": 4.0043,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709118997250327e-05,
"loss": 3.9816,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708282040379648e-05,
"loss": 3.9816,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707443445628596e-05,
"loss": 3.9801,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706604850877544e-05,
"loss": 4.001,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705766256126492e-05,
"loss": 3.9733,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704929299255813e-05,
"loss": 3.9897,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704090704504761e-05,
"loss": 3.9701,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703252109753709e-05,
"loss": 3.9839,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702413515002657e-05,
"loss": 3.9877,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015765581319785e-05,
"loss": 3.9776,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007379633809265e-05,
"loss": 3.9812,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998993686298745e-05,
"loss": 3.9764,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699060773878822e-05,
"loss": 3.9587,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982238170081434e-05,
"loss": 3.9791,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973852222570914e-05,
"loss": 3.9811,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965466275060394e-05,
"loss": 3.9718,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69570967063536e-05,
"loss": 3.9683,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694871075884308e-05,
"loss": 3.9738,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694032481133256e-05,
"loss": 3.956,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693193886382204e-05,
"loss": 3.9797,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692355291631152e-05,
"loss": 3.9584,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915166968801e-05,
"loss": 3.9671,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690678102129048e-05,
"loss": 3.9763,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689841145258369e-05,
"loss": 3.966,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689002550507317e-05,
"loss": 3.9731,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688163955756265e-05,
"loss": 3.9859,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687325361005213e-05,
"loss": 3.9709,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686486766254161e-05,
"loss": 3.9794,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685648171503109e-05,
"loss": 3.9633,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684809576752057e-05,
"loss": 3.9544,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683970982001005e-05,
"loss": 3.9646,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683134025130326e-05,
"loss": 3.9767,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682295430379274e-05,
"loss": 3.966,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681456835628222e-05,
"loss": 3.9569,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680618240877171e-05,
"loss": 3.951,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797812840064916e-05,
"loss": 3.954,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789426892554396e-05,
"loss": 3.9508,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.6781057323847605e-05,
"loss": 3.9597,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772671376337085e-05,
"loss": 3.9665,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764285428826565e-05,
"loss": 3.9647,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755899481316045e-05,
"loss": 3.957,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747529912609254e-05,
"loss": 3.9528,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739143965098734e-05,
"loss": 3.9483,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730758017588214e-05,
"loss": 3.9551,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722372070077694e-05,
"loss": 3.9528,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713986122567174e-05,
"loss": 3.9534,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670560017505666e-05,
"loss": 3.9478,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669721422754614e-05,
"loss": 3.9552,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668882828003562e-05,
"loss": 3.9563,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668045871132883e-05,
"loss": 3.9566,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667207276381831e-05,
"loss": 3.9574,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666368681630779e-05,
"loss": 3.961,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665530086879727e-05,
"loss": 3.9551,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664693130009048e-05,
"loss": 3.9484,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663854535257996e-05,
"loss": 3.965,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663017578387317e-05,
"loss": 3.9441,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662178983636265e-05,
"loss": 3.9648,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661340388885213e-05,
"loss": 3.9415,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6605017941341614e-05,
"loss": 3.9359,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659664837263482e-05,
"loss": 3.9419,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.65882624251243e-05,
"loss": 3.9554,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657987647761378e-05,
"loss": 3.9464,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657149053010326e-05,
"loss": 3.9343,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656310458259274e-05,
"loss": 3.9333,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655471863508222e-05,
"loss": 3.9414,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.65463326875717e-05,
"loss": 3.9547,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6537946740061176e-05,
"loss": 3.9415,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652957717135439e-05,
"loss": 3.9556,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652119122384387e-05,
"loss": 3.9433,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651280527633335e-05,
"loss": 3.9435,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650441932882283e-05,
"loss": 3.9487,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649603338131231e-05,
"loss": 3.933,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648764743380179e-05,
"loss": 3.9353,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647926148629127e-05,
"loss": 3.9428,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647087553878075e-05,
"loss": 3.9333,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646250597007396e-05,
"loss": 3.9382,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645412002256344e-05,
"loss": 3.9394,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644573407505292e-05,
"loss": 3.9457,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.64373481275424e-05,
"loss": 3.9276,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642897855883561e-05,
"loss": 3.9287,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642059261132509e-05,
"loss": 3.9529,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641220666381457e-05,
"loss": 3.9312,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640382071630405e-05,
"loss": 3.9459,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395451147597266e-05,
"loss": 3.9374,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387065200086746e-05,
"loss": 3.9409,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378679252576226e-05,
"loss": 3.9342,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370309683869435e-05,
"loss": 3.9312,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636194011516265e-05,
"loss": 3.9355,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353554167652124e-05,
"loss": 3.9358,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345168220141604e-05,
"loss": 3.9485,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336782272631084e-05,
"loss": 3.942,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328396325120564e-05,
"loss": 3.9393,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320010377610043e-05,
"loss": 3.933,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311624430099523e-05,
"loss": 3.9262,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303238482589003e-05,
"loss": 3.9367,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629486891388222e-05,
"loss": 3.9237,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.62864829663717e-05,
"loss": 3.9287,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627809701886118e-05,
"loss": 3.9283,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626971107135066e-05,
"loss": 3.9202,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626134150264387e-05,
"loss": 3.9272,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625295555513335e-05,
"loss": 3.9248,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.958523750305176,
"eval_runtime": 586.2687,
"eval_samples_per_second": 650.881,
"eval_steps_per_second": 20.341,
"step": 228957
},
{
"epoch": 0.0,
"learning_rate": 4.624458598642656e-05,
"loss": 3.9293,
"step": 229376
},
{
"epoch": 0.0,
"learning_rate": 4.623620003891604e-05,
"loss": 3.9353,
"step": 229888
},
{
"epoch": 0.0,
"learning_rate": 4.622781409140552e-05,
"loss": 3.9229,
"step": 230400
},
{
"epoch": 0.0,
"learning_rate": 4.6219428143895e-05,
"loss": 3.9239,
"step": 230912
},
{
"epoch": 0.0,
"learning_rate": 4.621104219638448e-05,
"loss": 3.9286,
"step": 231424
},
{
"epoch": 0.0,
"learning_rate": 4.620265624887396e-05,
"loss": 3.9071,
"step": 231936
},
{
"epoch": 0.0,
"learning_rate": 4.619427030136344e-05,
"loss": 3.9221,
"step": 232448
},
{
"epoch": 0.0,
"learning_rate": 4.6185884353852924e-05,
"loss": 3.9209,
"step": 232960
},
{
"epoch": 0.0,
"learning_rate": 4.6177498406342404e-05,
"loss": 3.9153,
"step": 233472
},
{
"epoch": 0.0,
"learning_rate": 4.616912883763561e-05,
"loss": 3.9258,
"step": 233984
},
{
"epoch": 0.0,
"learning_rate": 4.616074289012509e-05,
"loss": 3.9279,
"step": 234496
},
{
"epoch": 0.0,
"learning_rate": 4.615235694261457e-05,
"loss": 3.9105,
"step": 235008
},
{
"epoch": 0.0,
"learning_rate": 4.614397099510405e-05,
"loss": 3.9116,
"step": 235520
},
{
"epoch": 0.0,
"learning_rate": 4.613558504759353e-05,
"loss": 3.9167,
"step": 236032
},
{
"epoch": 0.0,
"learning_rate": 4.6127199100083006e-05,
"loss": 3.9178,
"step": 236544
},
{
"epoch": 0.0,
"learning_rate": 4.6118813152572486e-05,
"loss": 3.9056,
"step": 237056
},
{
"epoch": 0.0,
"learning_rate": 4.61104435838657e-05,
"loss": 3.9071,
"step": 237568
},
{
"epoch": 0.0,
"learning_rate": 4.610205763635518e-05,
"loss": 3.9114,
"step": 238080
},
{
"epoch": 0.0,
"learning_rate": 4.609367168884466e-05,
"loss": 3.9119,
"step": 238592
},
{
"epoch": 0.0,
"learning_rate": 4.608528574133414e-05,
"loss": 3.9188,
"step": 239104
},
{
"epoch": 0.0,
"learning_rate": 4.607689979382362e-05,
"loss": 3.9117,
"step": 239616
},
{
"epoch": 0.0,
"learning_rate": 4.60685138463131e-05,
"loss": 3.922,
"step": 240128
},
{
"epoch": 0.0,
"learning_rate": 4.606012789880258e-05,
"loss": 3.9161,
"step": 240640
},
{
"epoch": 0.0,
"learning_rate": 4.605174195129206e-05,
"loss": 3.9124,
"step": 241152
},
{
"epoch": 0.0,
"learning_rate": 4.604337238258527e-05,
"loss": 3.9114,
"step": 241664
},
{
"epoch": 0.0,
"learning_rate": 4.603498643507475e-05,
"loss": 3.9089,
"step": 242176
},
{
"epoch": 0.0,
"learning_rate": 4.602660048756423e-05,
"loss": 3.919,
"step": 242688
},
{
"epoch": 0.0,
"learning_rate": 4.601821454005371e-05,
"loss": 3.9051,
"step": 243200
},
{
"epoch": 0.0,
"learning_rate": 4.600984497134692e-05,
"loss": 3.912,
"step": 243712
},
{
"epoch": 0.01,
"learning_rate": 4.60014590238364e-05,
"loss": 3.9005,
"step": 244224
},
{
"epoch": 0.01,
"learning_rate": 4.599307307632588e-05,
"loss": 3.9014,
"step": 244736
},
{
"epoch": 0.01,
"learning_rate": 4.598468712881536e-05,
"loss": 3.9158,
"step": 245248
},
{
"epoch": 0.01,
"learning_rate": 4.5976301181304846e-05,
"loss": 3.9115,
"step": 245760
},
{
"epoch": 0.01,
"learning_rate": 4.5967915233794326e-05,
"loss": 3.9052,
"step": 246272
},
{
"epoch": 0.01,
"learning_rate": 4.5959529286283806e-05,
"loss": 3.9023,
"step": 246784
},
{
"epoch": 0.01,
"learning_rate": 4.5951143338773286e-05,
"loss": 3.9122,
"step": 247296
},
{
"epoch": 0.01,
"learning_rate": 4.5942773770066495e-05,
"loss": 3.9011,
"step": 247808
},
{
"epoch": 0.01,
"learning_rate": 4.5934404201359704e-05,
"loss": 3.9093,
"step": 248320
},
{
"epoch": 0.01,
"learning_rate": 4.5926018253849184e-05,
"loss": 3.9017,
"step": 248832
},
{
"epoch": 0.01,
"learning_rate": 4.5917632306338664e-05,
"loss": 3.8894,
"step": 249344
},
{
"epoch": 0.01,
"learning_rate": 4.5909246358828144e-05,
"loss": 3.8944,
"step": 249856
},
{
"epoch": 0.01,
"learning_rate": 4.5900860411317624e-05,
"loss": 3.893,
"step": 250368
},
{
"epoch": 0.01,
"learning_rate": 4.5892474463807104e-05,
"loss": 3.9069,
"step": 250880
},
{
"epoch": 0.01,
"learning_rate": 4.588410489510031e-05,
"loss": 3.8948,
"step": 251392
},
{
"epoch": 0.01,
"learning_rate": 4.58757189475898e-05,
"loss": 3.8936,
"step": 251904
},
{
"epoch": 0.01,
"learning_rate": 4.586733300007928e-05,
"loss": 3.8969,
"step": 252416
},
{
"epoch": 0.01,
"learning_rate": 4.585894705256876e-05,
"loss": 3.8996,
"step": 252928
},
{
"epoch": 0.01,
"learning_rate": 4.585056110505824e-05,
"loss": 3.9092,
"step": 253440
},
{
"epoch": 0.01,
"learning_rate": 4.584217515754772e-05,
"loss": 3.888,
"step": 253952
},
{
"epoch": 0.01,
"learning_rate": 4.58337892100372e-05,
"loss": 3.889,
"step": 254464
},
{
"epoch": 0.01,
"learning_rate": 4.582540326252667e-05,
"loss": 3.8937,
"step": 254976
},
{
"epoch": 0.01,
"learning_rate": 4.581703369381989e-05,
"loss": 3.9019,
"step": 255488
},
{
"epoch": 0.01,
"learning_rate": 4.580864774630937e-05,
"loss": 3.8839,
"step": 256000
},
{
"epoch": 0.01,
"learning_rate": 4.580026179879884e-05,
"loss": 3.8949,
"step": 256512
},
{
"epoch": 0.01,
"learning_rate": 4.579187585128832e-05,
"loss": 3.8812,
"step": 257024
},
{
"epoch": 0.01,
"learning_rate": 4.57834899037778e-05,
"loss": 3.8892,
"step": 257536
},
{
"epoch": 0.01,
"learning_rate": 4.577510395626728e-05,
"loss": 3.8985,
"step": 258048
},
{
"epoch": 0.01,
"learning_rate": 4.576671800875677e-05,
"loss": 3.8833,
"step": 258560
},
{
"epoch": 0.01,
"learning_rate": 4.575834844004998e-05,
"loss": 3.8984,
"step": 259072
},
{
"epoch": 0.01,
"learning_rate": 4.574996249253946e-05,
"loss": 3.8906,
"step": 259584
},
{
"epoch": 0.01,
"learning_rate": 4.574157654502894e-05,
"loss": 3.8679,
"step": 260096
},
{
"epoch": 0.01,
"learning_rate": 4.573319059751842e-05,
"loss": 3.887,
"step": 260608
},
{
"epoch": 0.01,
"learning_rate": 4.57248046500079e-05,
"loss": 3.8904,
"step": 261120
},
{
"epoch": 0.01,
"learning_rate": 4.571641870249738e-05,
"loss": 3.8887,
"step": 261632
},
{
"epoch": 0.01,
"learning_rate": 4.5708049133790586e-05,
"loss": 3.88,
"step": 262144
},
{
"epoch": 0.01,
"learning_rate": 4.5699663186280066e-05,
"loss": 3.8849,
"step": 262656
},
{
"epoch": 0.01,
"learning_rate": 4.5691277238769546e-05,
"loss": 3.8693,
"step": 263168
},
{
"epoch": 0.01,
"learning_rate": 4.5682891291259026e-05,
"loss": 3.8912,
"step": 263680
},
{
"epoch": 0.01,
"learning_rate": 4.5674505343748506e-05,
"loss": 3.8701,
"step": 264192
},
{
"epoch": 0.01,
"learning_rate": 4.5666119396237986e-05,
"loss": 3.8824,
"step": 264704
},
{
"epoch": 0.01,
"learning_rate": 4.5657733448727466e-05,
"loss": 3.8905,
"step": 265216
},
{
"epoch": 0.01,
"learning_rate": 4.564936388002068e-05,
"loss": 3.8783,
"step": 265728
},
{
"epoch": 0.01,
"learning_rate": 4.564097793251016e-05,
"loss": 3.8855,
"step": 266240
},
{
"epoch": 0.01,
"learning_rate": 4.563259198499964e-05,
"loss": 3.8967,
"step": 266752
},
{
"epoch": 0.01,
"learning_rate": 4.562420603748912e-05,
"loss": 3.8878,
"step": 267264
},
{
"epoch": 0.01,
"learning_rate": 4.561583646878233e-05,
"loss": 3.8947,
"step": 267776
},
{
"epoch": 0.01,
"learning_rate": 4.560745052127181e-05,
"loss": 3.8766,
"step": 268288
},
{
"epoch": 0.01,
"learning_rate": 4.559906457376129e-05,
"loss": 3.872,
"step": 268800
},
{
"epoch": 0.01,
"learning_rate": 4.559067862625077e-05,
"loss": 3.8754,
"step": 269312
},
{
"epoch": 0.01,
"learning_rate": 4.558229267874025e-05,
"loss": 3.8951,
"step": 269824
},
{
"epoch": 0.01,
"learning_rate": 4.557392311003346e-05,
"loss": 3.879,
"step": 270336
},
{
"epoch": 0.01,
"learning_rate": 4.556553716252294e-05,
"loss": 3.8708,
"step": 270848
},
{
"epoch": 0.01,
"learning_rate": 4.555715121501242e-05,
"loss": 3.8642,
"step": 271360
},
{
"epoch": 0.01,
"learning_rate": 4.55487652675019e-05,
"loss": 3.8742,
"step": 271872
},
{
"epoch": 0.01,
"learning_rate": 4.5540379319991386e-05,
"loss": 3.8686,
"step": 272384
},
{
"epoch": 0.01,
"learning_rate": 4.5532009751284595e-05,
"loss": 3.8727,
"step": 272896
},
{
"epoch": 0.01,
"learning_rate": 4.5523623803774075e-05,
"loss": 3.8803,
"step": 273408
},
{
"epoch": 0.01,
"learning_rate": 4.5515237856263555e-05,
"loss": 3.8844,
"step": 273920
},
{
"epoch": 0.01,
"learning_rate": 4.550685190875303e-05,
"loss": 3.8753,
"step": 274432
},
{
"epoch": 0.02,
"learning_rate": 4.5498482340046244e-05,
"loss": 3.8736,
"step": 274944
},
{
"epoch": 0.02,
"learning_rate": 4.5490096392535724e-05,
"loss": 3.8622,
"step": 275456
},
{
"epoch": 0.02,
"learning_rate": 4.5481710445025204e-05,
"loss": 3.8719,
"step": 275968
},
{
"epoch": 0.02,
"learning_rate": 4.547332449751468e-05,
"loss": 3.8736,
"step": 276480
},
{
"epoch": 0.02,
"learning_rate": 4.546493855000416e-05,
"loss": 3.8701,
"step": 276992
},
{
"epoch": 0.02,
"learning_rate": 4.545655260249364e-05,
"loss": 3.865,
"step": 277504
},
{
"epoch": 0.02,
"learning_rate": 4.544818303378685e-05,
"loss": 3.8746,
"step": 278016
},
{
"epoch": 0.02,
"learning_rate": 4.543979708627633e-05,
"loss": 3.8702,
"step": 278528
},
{
"epoch": 0.02,
"learning_rate": 4.543141113876581e-05,
"loss": 3.8826,
"step": 279040
},
{
"epoch": 0.02,
"learning_rate": 4.542302519125529e-05,
"loss": 3.8722,
"step": 279552
},
{
"epoch": 0.02,
"learning_rate": 4.541463924374477e-05,
"loss": 3.8794,
"step": 280064
},
{
"epoch": 0.02,
"learning_rate": 4.540626967503798e-05,
"loss": 3.8722,
"step": 280576
},
{
"epoch": 0.02,
"learning_rate": 4.539788372752746e-05,
"loss": 3.8675,
"step": 281088
},
{
"epoch": 0.02,
"learning_rate": 4.538949778001694e-05,
"loss": 3.885,
"step": 281600
},
{
"epoch": 0.02,
"learning_rate": 4.538111183250642e-05,
"loss": 3.8651,
"step": 282112
},
{
"epoch": 0.02,
"learning_rate": 4.537274226379963e-05,
"loss": 3.8861,
"step": 282624
},
{
"epoch": 0.02,
"learning_rate": 4.536435631628911e-05,
"loss": 3.86,
"step": 283136
},
{
"epoch": 0.02,
"learning_rate": 4.535597036877859e-05,
"loss": 3.8601,
"step": 283648
},
{
"epoch": 0.02,
"learning_rate": 4.534758442126808e-05,
"loss": 3.8625,
"step": 284160
},
{
"epoch": 0.02,
"learning_rate": 4.533921485256129e-05,
"loss": 3.8786,
"step": 284672
},
{
"epoch": 0.02,
"learning_rate": 4.53308452838545e-05,
"loss": 3.8673,
"step": 285184
},
{
"epoch": 0.02,
"learning_rate": 4.5322459336343976e-05,
"loss": 3.8538,
"step": 285696
},
{
"epoch": 0.02,
"learning_rate": 4.5314073388833456e-05,
"loss": 3.8516,
"step": 286208
},
{
"epoch": 0.02,
"learning_rate": 4.5305687441322936e-05,
"loss": 3.8614,
"step": 286720
},
{
"epoch": 0.02,
"learning_rate": 4.5297301493812416e-05,
"loss": 3.8792,
"step": 287232
},
{
"epoch": 0.02,
"learning_rate": 4.5288915546301896e-05,
"loss": 3.8627,
"step": 287744
},
{
"epoch": 0.02,
"learning_rate": 4.5280529598791376e-05,
"loss": 3.8788,
"step": 288256
},
{
"epoch": 0.02,
"learning_rate": 4.5272143651280856e-05,
"loss": 3.8648,
"step": 288768
},
{
"epoch": 0.02,
"learning_rate": 4.5263774082574065e-05,
"loss": 3.8687,
"step": 289280
},
{
"epoch": 0.02,
"learning_rate": 4.5255388135063545e-05,
"loss": 3.8704,
"step": 289792
},
{
"epoch": 0.02,
"learning_rate": 4.524700218755303e-05,
"loss": 3.8571,
"step": 290304
},
{
"epoch": 0.02,
"learning_rate": 4.523861624004251e-05,
"loss": 3.8576,
"step": 290816
},
{
"epoch": 0.02,
"learning_rate": 4.523024667133572e-05,
"loss": 3.8644,
"step": 291328
},
{
"epoch": 0.02,
"learning_rate": 4.52218607238252e-05,
"loss": 3.8585,
"step": 291840
},
{
"epoch": 0.02,
"learning_rate": 4.521347477631468e-05,
"loss": 3.8595,
"step": 292352
},
{
"epoch": 0.02,
"learning_rate": 4.520508882880416e-05,
"loss": 3.8644,
"step": 292864
},
{
"epoch": 0.02,
"learning_rate": 4.519670288129364e-05,
"loss": 3.8651,
"step": 293376
},
{
"epoch": 0.02,
"learning_rate": 4.518833331258685e-05,
"loss": 3.8526,
"step": 293888
},
{
"epoch": 0.02,
"learning_rate": 4.517994736507633e-05,
"loss": 3.8541,
"step": 294400
},
{
"epoch": 0.02,
"learning_rate": 4.517156141756581e-05,
"loss": 3.874,
"step": 294912
},
{
"epoch": 0.02,
"learning_rate": 4.516317547005529e-05,
"loss": 3.8548,
"step": 295424
},
{
"epoch": 0.02,
"learning_rate": 4.51548059013485e-05,
"loss": 3.87,
"step": 295936
},
{
"epoch": 0.02,
"learning_rate": 4.5146419953837985e-05,
"loss": 3.8629,
"step": 296448
},
{
"epoch": 0.02,
"learning_rate": 4.5138034006327465e-05,
"loss": 3.8646,
"step": 296960
},
{
"epoch": 0.02,
"learning_rate": 4.5129648058816945e-05,
"loss": 3.8566,
"step": 297472
},
{
"epoch": 0.02,
"learning_rate": 4.5121278490110154e-05,
"loss": 3.8614,
"step": 297984
},
{
"epoch": 0.02,
"learning_rate": 4.5112892542599634e-05,
"loss": 3.8582,
"step": 298496
},
{
"epoch": 0.02,
"learning_rate": 4.5104506595089114e-05,
"loss": 3.861,
"step": 299008
},
{
"epoch": 0.02,
"learning_rate": 4.5096120647578594e-05,
"loss": 3.8746,
"step": 299520
},
{
"epoch": 0.02,
"learning_rate": 4.50877510788718e-05,
"loss": 3.8621,
"step": 300032
},
{
"epoch": 0.02,
"learning_rate": 4.507936513136128e-05,
"loss": 3.8673,
"step": 300544
},
{
"epoch": 0.02,
"learning_rate": 4.507097918385076e-05,
"loss": 3.8653,
"step": 301056
},
{
"epoch": 0.02,
"learning_rate": 4.506259323634024e-05,
"loss": 3.8516,
"step": 301568
},
{
"epoch": 0.02,
"learning_rate": 4.505422366763345e-05,
"loss": 3.8617,
"step": 302080
},
{
"epoch": 0.02,
"learning_rate": 4.504583772012293e-05,
"loss": 3.8505,
"step": 302592
},
{
"epoch": 0.02,
"learning_rate": 4.503745177261242e-05,
"loss": 3.8553,
"step": 303104
},
{
"epoch": 0.02,
"learning_rate": 4.50290658251019e-05,
"loss": 3.8548,
"step": 303616
},
{
"epoch": 0.02,
"learning_rate": 4.502069625639511e-05,
"loss": 3.8523,
"step": 304128
},
{
"epoch": 0.02,
"learning_rate": 4.501231030888459e-05,
"loss": 3.8488,
"step": 304640
},
{
"epoch": 0.02,
"learning_rate": 4.500392436137407e-05,
"loss": 3.8562,
"step": 305152
},
{
"epoch": 0.03,
"eval_loss": 3.9172492027282715,
"eval_runtime": 566.0397,
"eval_samples_per_second": 674.142,
"eval_steps_per_second": 21.067,
"step": 305276
},
{
"epoch": 0.0,
"learning_rate": 4.499553841386355e-05,
"loss": 3.8596,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498715246635303e-05,
"loss": 3.8605,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497876651884251e-05,
"loss": 3.8541,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497038057133199e-05,
"loss": 3.8513,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496199462382146e-05,
"loss": 3.8602,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495360867631094e-05,
"loss": 3.8344,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494522272880042e-05,
"loss": 3.8536,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.49368367812899e-05,
"loss": 3.8453,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928467212583116e-05,
"loss": 3.8451,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4920081265072596e-05,
"loss": 3.8546,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911695317562076e-05,
"loss": 3.8566,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903309370051556e-05,
"loss": 3.8398,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.4894939801344765e-05,
"loss": 3.8445,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.4886553853834245e-05,
"loss": 3.844,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4878167906323725e-05,
"loss": 3.849,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.4869781958813205e-05,
"loss": 3.8325,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.4861412390106414e-05,
"loss": 3.838,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.4853026442595894e-05,
"loss": 3.8396,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.4844640495085374e-05,
"loss": 3.8416,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.4836254547574854e-05,
"loss": 3.8516,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482788497886807e-05,
"loss": 3.8421,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481949903135755e-05,
"loss": 3.8532,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481111308384703e-05,
"loss": 3.8512,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480272713633651e-05,
"loss": 3.8454,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479434118882599e-05,
"loss": 3.8413,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.47859716201192e-05,
"loss": 3.8416,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477758567260868e-05,
"loss": 3.8506,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476919972509816e-05,
"loss": 3.8377,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476081377758764e-05,
"loss": 3.8418,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475244420888085e-05,
"loss": 3.8399,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474405826137033e-05,
"loss": 3.8289,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473567231385981e-05,
"loss": 3.8444,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.4727286366349295e-05,
"loss": 3.8495,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.4718916797642504e-05,
"loss": 3.8388,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710530850131984e-05,
"loss": 3.8358,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.4702144902621464e-05,
"loss": 3.8402,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693758955110944e-05,
"loss": 3.8388,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468538938640415e-05,
"loss": 3.8392,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467700343889363e-05,
"loss": 3.8358,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466861749138311e-05,
"loss": 3.8241,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466023154387259e-05,
"loss": 3.8289,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.46518619751658e-05,
"loss": 3.8241,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464347602765528e-05,
"loss": 3.841,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463509008014476e-05,
"loss": 3.8278,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462670413263425e-05,
"loss": 3.8292,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461833456392746e-05,
"loss": 3.8324,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460994861641694e-05,
"loss": 3.8319,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460156266890642e-05,
"loss": 3.8459,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.45931767213959e-05,
"loss": 3.8249,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584807152689106e-05,
"loss": 3.8217,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576421205178586e-05,
"loss": 3.8323,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4568035257668066e-05,
"loss": 3.8333,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559649310157546e-05,
"loss": 3.8224,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551279741450755e-05,
"loss": 3.8282,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542893793940235e-05,
"loss": 3.8214,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534507846429715e-05,
"loss": 3.8262,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.45261218989192e-05,
"loss": 3.8342,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451775233021241e-05,
"loss": 3.8174,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450936638270189e-05,
"loss": 3.8359,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450098043519137e-05,
"loss": 3.8243,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449259448768085e-05,
"loss": 3.8086,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448422491897406e-05,
"loss": 3.8213,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447583897146354e-05,
"loss": 3.8265,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446745302395302e-05,
"loss": 3.8303,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.44590670764425e-05,
"loss": 3.817,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445069750773571e-05,
"loss": 3.8229,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444231156022519e-05,
"loss": 3.8019,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443392561271467e-05,
"loss": 3.8298,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.4425539665204156e-05,
"loss": 3.8113,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.4417170096497365e-05,
"loss": 3.819,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.4408784148986845e-05,
"loss": 3.8265,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.4400398201476325e-05,
"loss": 3.8167,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.4392012253965805e-05,
"loss": 3.8205,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.4383642685259014e-05,
"loss": 3.8332,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.4375256737748494e-05,
"loss": 3.8269,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.4366870790237974e-05,
"loss": 3.8303,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.4358484842727454e-05,
"loss": 3.8172,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435011527402066e-05,
"loss": 3.8111,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434172932651014e-05,
"loss": 3.8166,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433334337899962e-05,
"loss": 3.8318,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.43249574314891e-05,
"loss": 3.8173,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431658786278232e-05,
"loss": 3.8133,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.43082019152718e-05,
"loss": 3.802,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429981596776128e-05,
"loss": 3.8138,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429143002025076e-05,
"loss": 3.8047,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428306045154397e-05,
"loss": 3.8168,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427467450403345e-05,
"loss": 3.815,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426628855652293e-05,
"loss": 3.8263,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425790260901241e-05,
"loss": 3.8155,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249533040305616e-05,
"loss": 3.8149,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4241147092795096e-05,
"loss": 3.8023,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232761145284576e-05,
"loss": 3.8122,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224375197774056e-05,
"loss": 3.8158,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421600562906727e-05,
"loss": 3.8086,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420761968155675e-05,
"loss": 3.8051,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419923373404623e-05,
"loss": 3.8176,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419084778653571e-05,
"loss": 3.8074,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418247821782892e-05,
"loss": 3.8309,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.41740922703184e-05,
"loss": 3.8106,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416570632280788e-05,
"loss": 3.8205,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415732037529736e-05,
"loss": 3.812,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414895080659057e-05,
"loss": 3.8089,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414056485908005e-05,
"loss": 3.8271,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413217891156953e-05,
"loss": 3.8068,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412379296405901e-05,
"loss": 3.8246,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115423395352226e-05,
"loss": 3.8045,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4107037447841706e-05,
"loss": 3.8038,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098651500331186e-05,
"loss": 3.8011,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409026555282066e-05,
"loss": 3.8162,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081895984113875e-05,
"loss": 3.8141,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.4073510036603355e-05,
"loss": 3.8021,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.4065124089092835e-05,
"loss": 3.7906,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405673814158231e-05,
"loss": 3.8034,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.4048368572875524e-05,
"loss": 3.8217,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.4039982625365004e-05,
"loss": 3.8024,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.4031596677854484e-05,
"loss": 3.8211,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.4023210730343963e-05,
"loss": 3.8087,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401484116163718e-05,
"loss": 3.81,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400645521412666e-05,
"loss": 3.8136,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399806926661613e-05,
"loss": 3.8011,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398968331910561e-05,
"loss": 3.7979,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398131375039883e-05,
"loss": 3.8048,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397292780288831e-05,
"loss": 3.8047,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396454185537778e-05,
"loss": 3.8036,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395615590786726e-05,
"loss": 3.8057,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394778633916048e-05,
"loss": 3.8084,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393940039164996e-05,
"loss": 3.7959,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393101444413944e-05,
"loss": 3.799,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392262849662892e-05,
"loss": 3.8152,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391425892792213e-05,
"loss": 3.7996,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905872980411606e-05,
"loss": 3.8145,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897487032901086e-05,
"loss": 3.8104,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.3889101085390566e-05,
"loss": 3.8055,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388073151668378e-05,
"loss": 3.8037,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872345569173255e-05,
"loss": 3.8057,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3863959621662735e-05,
"loss": 3.8021,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855573674152215e-05,
"loss": 3.8037,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3847204105445424e-05,
"loss": 3.8197,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383881815793491e-05,
"loss": 3.8105,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383043221042439e-05,
"loss": 3.8109,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382204626291387e-05,
"loss": 3.8089,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381367669420708e-05,
"loss": 3.7985,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380529074669656e-05,
"loss": 3.804,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379690479918604e-05,
"loss": 3.7947,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378851885167552e-05,
"loss": 3.8001,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378014928296873e-05,
"loss": 3.8032,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377176333545821e-05,
"loss": 3.7973,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376337738794769e-05,
"loss": 3.7917,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.37550078192409e-05,
"loss": 3.8037,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.890806198120117,
"eval_runtime": 570.4872,
"eval_samples_per_second": 668.886,
"eval_steps_per_second": 20.903,
"step": 381595
},
{
"epoch": 0.0,
"learning_rate": 4.374662187173038e-05,
"loss": 3.8088,
"step": 381952
},
{
"epoch": 0.0,
"learning_rate": 4.3738235924219865e-05,
"loss": 3.8028,
"step": 382464
},
{
"epoch": 0.0,
"learning_rate": 4.3729849976709345e-05,
"loss": 3.8016,
"step": 382976
},
{
"epoch": 0.0,
"learning_rate": 4.3721464029198824e-05,
"loss": 3.8007,
"step": 383488
},
{
"epoch": 0.0,
"learning_rate": 4.3713078081688304e-05,
"loss": 3.7992,
"step": 384000
},
{
"epoch": 0.0,
"learning_rate": 4.3704692134177784e-05,
"loss": 3.7863,
"step": 384512
},
{
"epoch": 0.0,
"learning_rate": 4.3696306186667264e-05,
"loss": 3.7969,
"step": 385024
},
{
"epoch": 0.0,
"learning_rate": 4.3687920239156744e-05,
"loss": 3.789,
"step": 385536
},
{
"epoch": 0.0,
"learning_rate": 4.3679550670449953e-05,
"loss": 3.7981,
"step": 386048
},
{
"epoch": 0.0,
"learning_rate": 4.367118110174316e-05,
"loss": 3.8001,
"step": 386560
},
{
"epoch": 0.0,
"learning_rate": 4.366279515423264e-05,
"loss": 3.801,
"step": 387072
},
{
"epoch": 0.0,
"learning_rate": 4.365440920672212e-05,
"loss": 3.7862,
"step": 387584
},
{
"epoch": 0.0,
"learning_rate": 4.36460232592116e-05,
"loss": 3.7922,
"step": 388096
},
{
"epoch": 0.0,
"learning_rate": 4.363763731170108e-05,
"loss": 3.7901,
"step": 388608
},
{
"epoch": 0.0,
"learning_rate": 4.362925136419056e-05,
"loss": 3.7955,
"step": 389120
},
{
"epoch": 0.0,
"learning_rate": 4.362086541668005e-05,
"loss": 3.7805,
"step": 389632
},
{
"epoch": 0.0,
"learning_rate": 4.361247946916953e-05,
"loss": 3.7823,
"step": 390144
},
{
"epoch": 0.0,
"learning_rate": 4.360410990046274e-05,
"loss": 3.7869,
"step": 390656
},
{
"epoch": 0.0,
"learning_rate": 4.359572395295222e-05,
"loss": 3.7897,
"step": 391168
},
{
"epoch": 0.0,
"learning_rate": 4.35873380054417e-05,
"loss": 3.7994,
"step": 391680
},
{
"epoch": 0.0,
"learning_rate": 4.357895205793118e-05,
"loss": 3.7864,
"step": 392192
},
{
"epoch": 0.0,
"learning_rate": 4.357058248922439e-05,
"loss": 3.8045,
"step": 392704
},
{
"epoch": 0.0,
"learning_rate": 4.356219654171387e-05,
"loss": 3.7947,
"step": 393216
},
{
"epoch": 0.0,
"learning_rate": 4.355381059420335e-05,
"loss": 3.7953,
"step": 393728
},
{
"epoch": 0.0,
"learning_rate": 4.354542464669283e-05,
"loss": 3.7882,
"step": 394240
},
{
"epoch": 0.0,
"learning_rate": 4.3537055077986036e-05,
"loss": 3.7888,
"step": 394752
},
{
"epoch": 0.0,
"learning_rate": 4.3528669130475516e-05,
"loss": 3.8017,
"step": 395264
},
{
"epoch": 0.0,
"learning_rate": 4.3520283182964996e-05,
"loss": 3.7864,
"step": 395776
},
{
"epoch": 0.0,
"learning_rate": 4.351189723545448e-05,
"loss": 3.7918,
"step": 396288
},
{
"epoch": 0.0,
"learning_rate": 4.350352766674769e-05,
"loss": 3.7885,
"step": 396800
},
{
"epoch": 0.01,
"learning_rate": 4.349514171923717e-05,
"loss": 3.775,
"step": 397312
},
{
"epoch": 0.01,
"learning_rate": 4.348675577172665e-05,
"loss": 3.7946,
"step": 397824
},
{
"epoch": 0.01,
"learning_rate": 4.347836982421613e-05,
"loss": 3.7954,
"step": 398336
},
{
"epoch": 0.01,
"learning_rate": 4.347000025550934e-05,
"loss": 3.7921,
"step": 398848
},
{
"epoch": 0.01,
"learning_rate": 4.346161430799882e-05,
"loss": 3.7817,
"step": 399360
},
{
"epoch": 0.01,
"learning_rate": 4.34532283604883e-05,
"loss": 3.7944,
"step": 399872
},
{
"epoch": 0.01,
"learning_rate": 4.344484241297778e-05,
"loss": 3.7821,
"step": 400384
},
{
"epoch": 0.01,
"learning_rate": 4.343647284427099e-05,
"loss": 3.7919,
"step": 400896
},
{
"epoch": 0.01,
"learning_rate": 4.342808689676047e-05,
"loss": 3.7858,
"step": 401408
},
{
"epoch": 0.01,
"learning_rate": 4.341970094924995e-05,
"loss": 3.7724,
"step": 401920
},
{
"epoch": 0.01,
"learning_rate": 4.3411315001739436e-05,
"loss": 3.7794,
"step": 402432
},
{
"epoch": 0.01,
"learning_rate": 4.3402945433032645e-05,
"loss": 3.7706,
"step": 402944
},
{
"epoch": 0.01,
"learning_rate": 4.3394559485522125e-05,
"loss": 3.7945,
"step": 403456
},
{
"epoch": 0.01,
"learning_rate": 4.3386173538011605e-05,
"loss": 3.7773,
"step": 403968
},
{
"epoch": 0.01,
"learning_rate": 4.3377787590501085e-05,
"loss": 3.7758,
"step": 404480
},
{
"epoch": 0.01,
"learning_rate": 4.3369418021794294e-05,
"loss": 3.7852,
"step": 404992
},
{
"epoch": 0.01,
"learning_rate": 4.3361032074283774e-05,
"loss": 3.7824,
"step": 405504
},
{
"epoch": 0.01,
"learning_rate": 4.3352646126773254e-05,
"loss": 3.7954,
"step": 406016
},
{
"epoch": 0.01,
"learning_rate": 4.3344260179262734e-05,
"loss": 3.7714,
"step": 406528
},
{
"epoch": 0.01,
"learning_rate": 4.333589061055594e-05,
"loss": 3.7746,
"step": 407040
},
{
"epoch": 0.01,
"learning_rate": 4.332750466304542e-05,
"loss": 3.7828,
"step": 407552
},
{
"epoch": 0.01,
"learning_rate": 4.33191187155349e-05,
"loss": 3.7818,
"step": 408064
},
{
"epoch": 0.01,
"learning_rate": 4.331073276802439e-05,
"loss": 3.7763,
"step": 408576
},
{
"epoch": 0.01,
"learning_rate": 4.33023631993176e-05,
"loss": 3.7749,
"step": 409088
},
{
"epoch": 0.01,
"learning_rate": 4.329397725180708e-05,
"loss": 3.7723,
"step": 409600
},
{
"epoch": 0.01,
"learning_rate": 4.328559130429656e-05,
"loss": 3.7777,
"step": 410112
},
{
"epoch": 0.01,
"learning_rate": 4.327720535678604e-05,
"loss": 3.7804,
"step": 410624
},
{
"epoch": 0.01,
"learning_rate": 4.326883578807925e-05,
"loss": 3.7743,
"step": 411136
},
{
"epoch": 0.01,
"learning_rate": 4.326044984056873e-05,
"loss": 3.787,
"step": 411648
},
{
"epoch": 0.01,
"learning_rate": 4.325206389305821e-05,
"loss": 3.7716,
"step": 412160
},
{
"epoch": 0.01,
"learning_rate": 4.324367794554768e-05,
"loss": 3.7645,
"step": 412672
},
{
"epoch": 0.01,
"learning_rate": 4.32353083768409e-05,
"loss": 3.7722,
"step": 413184
},
{
"epoch": 0.01,
"learning_rate": 4.322692242933038e-05,
"loss": 3.7716,
"step": 413696
},
{
"epoch": 0.01,
"learning_rate": 4.321853648181986e-05,
"loss": 3.7903,
"step": 414208
},
{
"epoch": 0.01,
"learning_rate": 4.321016691311307e-05,
"loss": 3.7673,
"step": 414720
},
{
"epoch": 0.01,
"learning_rate": 4.320178096560255e-05,
"loss": 3.7767,
"step": 415232
},
{
"epoch": 0.01,
"learning_rate": 4.319339501809203e-05,
"loss": 3.7578,
"step": 415744
},
{
"epoch": 0.01,
"learning_rate": 4.3185009070581506e-05,
"loss": 3.7763,
"step": 416256
},
{
"epoch": 0.01,
"learning_rate": 4.317663950187472e-05,
"loss": 3.7635,
"step": 416768
},
{
"epoch": 0.01,
"learning_rate": 4.31682535543642e-05,
"loss": 3.7689,
"step": 417280
},
{
"epoch": 0.01,
"learning_rate": 4.315986760685368e-05,
"loss": 3.7766,
"step": 417792
},
{
"epoch": 0.01,
"learning_rate": 4.3151481659343155e-05,
"loss": 3.7701,
"step": 418304
},
{
"epoch": 0.01,
"learning_rate": 4.314311209063637e-05,
"loss": 3.7724,
"step": 418816
},
{
"epoch": 0.01,
"learning_rate": 4.313472614312585e-05,
"loss": 3.7841,
"step": 419328
},
{
"epoch": 0.01,
"learning_rate": 4.312634019561533e-05,
"loss": 3.7755,
"step": 419840
},
{
"epoch": 0.01,
"learning_rate": 4.3117970626908546e-05,
"loss": 3.7847,
"step": 420352
},
{
"epoch": 0.01,
"learning_rate": 4.3109584679398026e-05,
"loss": 3.7702,
"step": 420864
},
{
"epoch": 0.01,
"learning_rate": 4.3101198731887506e-05,
"loss": 3.7626,
"step": 421376
},
{
"epoch": 0.01,
"learning_rate": 4.309281278437698e-05,
"loss": 3.7697,
"step": 421888
},
{
"epoch": 0.01,
"learning_rate": 4.308442683686646e-05,
"loss": 3.7848,
"step": 422400
},
{
"epoch": 0.01,
"learning_rate": 4.307604088935594e-05,
"loss": 3.7688,
"step": 422912
},
{
"epoch": 0.01,
"learning_rate": 4.306765494184542e-05,
"loss": 3.7665,
"step": 423424
},
{
"epoch": 0.01,
"learning_rate": 4.305928537313863e-05,
"loss": 3.7539,
"step": 423936
},
{
"epoch": 0.01,
"learning_rate": 4.305089942562811e-05,
"loss": 3.7691,
"step": 424448
},
{
"epoch": 0.01,
"learning_rate": 4.304251347811759e-05,
"loss": 3.7548,
"step": 424960
},
{
"epoch": 0.01,
"learning_rate": 4.303412753060707e-05,
"loss": 3.7696,
"step": 425472
},
{
"epoch": 0.01,
"learning_rate": 4.3025757961900284e-05,
"loss": 3.7712,
"step": 425984
},
{
"epoch": 0.01,
"learning_rate": 4.30173883931935e-05,
"loss": 3.7763,
"step": 426496
},
{
"epoch": 0.01,
"learning_rate": 4.300900244568298e-05,
"loss": 3.7692,
"step": 427008
},
{
"epoch": 0.02,
"learning_rate": 4.300061649817245e-05,
"loss": 3.7703,
"step": 427520
},
{
"epoch": 0.02,
"learning_rate": 4.299223055066193e-05,
"loss": 3.7542,
"step": 428032
},
{
"epoch": 0.02,
"learning_rate": 4.298384460315141e-05,
"loss": 3.7658,
"step": 428544
},
{
"epoch": 0.02,
"learning_rate": 4.297545865564089e-05,
"loss": 3.766,
"step": 429056
},
{
"epoch": 0.02,
"learning_rate": 4.296707270813037e-05,
"loss": 3.7644,
"step": 429568
},
{
"epoch": 0.02,
"learning_rate": 4.295868676061985e-05,
"loss": 3.7583,
"step": 430080
},
{
"epoch": 0.02,
"learning_rate": 4.295031719191306e-05,
"loss": 3.7728,
"step": 430592
},
{
"epoch": 0.02,
"learning_rate": 4.294193124440254e-05,
"loss": 3.7601,
"step": 431104
},
{
"epoch": 0.02,
"learning_rate": 4.293354529689202e-05,
"loss": 3.7872,
"step": 431616
},
{
"epoch": 0.02,
"learning_rate": 4.292517572818524e-05,
"loss": 3.7572,
"step": 432128
},
{
"epoch": 0.02,
"learning_rate": 4.291678978067472e-05,
"loss": 3.7763,
"step": 432640
},
{
"epoch": 0.02,
"learning_rate": 4.29084038331642e-05,
"loss": 3.7651,
"step": 433152
},
{
"epoch": 0.02,
"learning_rate": 4.290001788565368e-05,
"loss": 3.7629,
"step": 433664
},
{
"epoch": 0.02,
"learning_rate": 4.289163193814316e-05,
"loss": 3.7846,
"step": 434176
},
{
"epoch": 0.02,
"learning_rate": 4.288324599063264e-05,
"loss": 3.7578,
"step": 434688
},
{
"epoch": 0.02,
"learning_rate": 4.287486004312212e-05,
"loss": 3.779,
"step": 435200
},
{
"epoch": 0.02,
"learning_rate": 4.286649047441533e-05,
"loss": 3.7582,
"step": 435712
},
{
"epoch": 0.02,
"learning_rate": 4.285810452690481e-05,
"loss": 3.7596,
"step": 436224
},
{
"epoch": 0.02,
"learning_rate": 4.284971857939429e-05,
"loss": 3.7532,
"step": 436736
},
{
"epoch": 0.02,
"learning_rate": 4.284133263188377e-05,
"loss": 3.7699,
"step": 437248
},
{
"epoch": 0.02,
"learning_rate": 4.2832963063176976e-05,
"loss": 3.7682,
"step": 437760
},
{
"epoch": 0.02,
"learning_rate": 4.2824577115666456e-05,
"loss": 3.7587,
"step": 438272
},
{
"epoch": 0.02,
"learning_rate": 4.281619116815594e-05,
"loss": 3.7432,
"step": 438784
},
{
"epoch": 0.02,
"learning_rate": 4.280780522064542e-05,
"loss": 3.7596,
"step": 439296
},
{
"epoch": 0.02,
"learning_rate": 4.279943565193863e-05,
"loss": 3.7734,
"step": 439808
},
{
"epoch": 0.02,
"learning_rate": 4.279104970442811e-05,
"loss": 3.764,
"step": 440320
},
{
"epoch": 0.02,
"learning_rate": 4.278266375691759e-05,
"loss": 3.7729,
"step": 440832
},
{
"epoch": 0.02,
"learning_rate": 4.277427780940707e-05,
"loss": 3.7642,
"step": 441344
},
{
"epoch": 0.02,
"learning_rate": 4.276589186189655e-05,
"loss": 3.7642,
"step": 441856
},
{
"epoch": 0.02,
"learning_rate": 4.275750591438603e-05,
"loss": 3.7711,
"step": 442368
},
{
"epoch": 0.02,
"learning_rate": 4.274911996687551e-05,
"loss": 3.7591,
"step": 442880
},
{
"epoch": 0.02,
"learning_rate": 4.274075039816872e-05,
"loss": 3.7518,
"step": 443392
},
{
"epoch": 0.02,
"learning_rate": 4.27323644506582e-05,
"loss": 3.7584,
"step": 443904
},
{
"epoch": 0.02,
"learning_rate": 4.272397850314768e-05,
"loss": 3.7583,
"step": 444416
},
{
"epoch": 0.02,
"learning_rate": 4.271559255563716e-05,
"loss": 3.759,
"step": 444928
},
{
"epoch": 0.02,
"learning_rate": 4.2707222986930376e-05,
"loss": 3.7585,
"step": 445440
},
{
"epoch": 0.02,
"learning_rate": 4.2698853418223585e-05,
"loss": 3.7623,
"step": 445952
},
{
"epoch": 0.02,
"learning_rate": 4.2690467470713065e-05,
"loss": 3.7559,
"step": 446464
},
{
"epoch": 0.02,
"learning_rate": 4.2682081523202545e-05,
"loss": 3.7508,
"step": 446976
},
{
"epoch": 0.02,
"learning_rate": 4.2673695575692025e-05,
"loss": 3.7695,
"step": 447488
},
{
"epoch": 0.02,
"learning_rate": 4.2665309628181505e-05,
"loss": 3.7555,
"step": 448000
},
{
"epoch": 0.02,
"learning_rate": 4.2656923680670985e-05,
"loss": 3.7686,
"step": 448512
},
{
"epoch": 0.02,
"learning_rate": 4.2648537733160465e-05,
"loss": 3.7708,
"step": 449024
},
{
"epoch": 0.02,
"learning_rate": 4.264015178564994e-05,
"loss": 3.7606,
"step": 449536
},
{
"epoch": 0.02,
"learning_rate": 4.2631782216943154e-05,
"loss": 3.7618,
"step": 450048
},
{
"epoch": 0.02,
"learning_rate": 4.2623396269432634e-05,
"loss": 3.7614,
"step": 450560
},
{
"epoch": 0.02,
"learning_rate": 4.2615010321922114e-05,
"loss": 3.7576,
"step": 451072
},
{
"epoch": 0.02,
"learning_rate": 4.2606624374411594e-05,
"loss": 3.7561,
"step": 451584
},
{
"epoch": 0.02,
"learning_rate": 4.259825480570481e-05,
"loss": 3.7746,
"step": 452096
},
{
"epoch": 0.02,
"learning_rate": 4.258986885819429e-05,
"loss": 3.7706,
"step": 452608
},
{
"epoch": 0.02,
"learning_rate": 4.258148291068376e-05,
"loss": 3.7632,
"step": 453120
},
{
"epoch": 0.02,
"learning_rate": 4.257309696317324e-05,
"loss": 3.7649,
"step": 453632
},
{
"epoch": 0.02,
"learning_rate": 4.256472739446646e-05,
"loss": 3.757,
"step": 454144
},
{
"epoch": 0.02,
"learning_rate": 4.255634144695594e-05,
"loss": 3.7627,
"step": 454656
},
{
"epoch": 0.02,
"learning_rate": 4.254795549944541e-05,
"loss": 3.7535,
"step": 455168
},
{
"epoch": 0.02,
"learning_rate": 4.253958593073863e-05,
"loss": 3.7515,
"step": 455680
},
{
"epoch": 0.02,
"learning_rate": 4.253119998322811e-05,
"loss": 3.7623,
"step": 456192
},
{
"epoch": 0.02,
"learning_rate": 4.252281403571758e-05,
"loss": 3.7541,
"step": 456704
},
{
"epoch": 0.02,
"learning_rate": 4.251442808820707e-05,
"loss": 3.7488,
"step": 457216
},
{
"epoch": 0.02,
"learning_rate": 4.250604214069655e-05,
"loss": 3.7556,
"step": 457728
},
{
"epoch": 0.03,
"eval_loss": 3.874908685684204,
"eval_runtime": 556.2656,
"eval_samples_per_second": 685.987,
"eval_steps_per_second": 21.438,
"step": 457914
},
{
"epoch": 0.0,
"learning_rate": 4.249767257198976e-05,
"loss": 3.7647,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.2489286624479237e-05,
"loss": 3.7611,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.2480900676968716e-05,
"loss": 3.7564,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.2472514729458196e-05,
"loss": 3.7585,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.2464128781947676e-05,
"loss": 3.7582,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.2455742834437156e-05,
"loss": 3.7453,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.2447356886926636e-05,
"loss": 3.7554,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.2438970939416116e-05,
"loss": 3.7452,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.2430617749513054e-05,
"loss": 3.7538,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.2422231802002534e-05,
"loss": 3.7561,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.241384585449202e-05,
"loss": 3.7606,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.24054599069815e-05,
"loss": 3.7386,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239707395947098e-05,
"loss": 3.753,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238868801196046e-05,
"loss": 3.746,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.238030206444994e-05,
"loss": 3.7568,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237191611693942e-05,
"loss": 3.7371,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.236354654823263e-05,
"loss": 3.7398,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.235516060072211e-05,
"loss": 3.7485,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.234677465321159e-05,
"loss": 3.745,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.233838870570107e-05,
"loss": 3.7567,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.233003551579801e-05,
"loss": 3.7473,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.232164956828749e-05,
"loss": 3.76,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.2313263620776975e-05,
"loss": 3.7545,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.2304877673266455e-05,
"loss": 3.7502,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.2296491725755935e-05,
"loss": 3.7445,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.2288105778245415e-05,
"loss": 3.7498,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.2279719830734895e-05,
"loss": 3.7571,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.2271333883224375e-05,
"loss": 3.7484,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.2262964314517584e-05,
"loss": 3.7465,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.2254578367007064e-05,
"loss": 3.7499,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.2246192419496544e-05,
"loss": 3.7364,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.2237806471986024e-05,
"loss": 3.753,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.222943690327923e-05,
"loss": 3.7555,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.222105095576871e-05,
"loss": 3.7514,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.221266500825819e-05,
"loss": 3.7402,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.220427906074767e-05,
"loss": 3.7533,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.219589311323716e-05,
"loss": 3.74,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.218750716572664e-05,
"loss": 3.75,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.217912121821612e-05,
"loss": 3.7481,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.21707352707056e-05,
"loss": 3.7343,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.216236570199881e-05,
"loss": 3.7346,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.215397975448829e-05,
"loss": 3.7291,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.214559380697777e-05,
"loss": 3.7579,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.213720785946725e-05,
"loss": 3.7359,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.212883829076046e-05,
"loss": 3.7345,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.212045234324994e-05,
"loss": 3.7464,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.211206639573942e-05,
"loss": 3.742,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.2103696827032626e-05,
"loss": 3.7517,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.209531087952211e-05,
"loss": 3.7343,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.208692493201159e-05,
"loss": 3.7377,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.207853898450107e-05,
"loss": 3.7373,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.2070153036990546e-05,
"loss": 3.743,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.206178346828376e-05,
"loss": 3.7364,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.205339752077324e-05,
"loss": 3.7324,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.204501157326272e-05,
"loss": 3.736,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.2036625625752195e-05,
"loss": 3.7419,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.2028239678241675e-05,
"loss": 3.7375,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.2019853730731155e-05,
"loss": 3.733,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.2011467783220635e-05,
"loss": 3.7462,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.200309821451385e-05,
"loss": 3.7322,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.199471226700333e-05,
"loss": 3.7238,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.1986342698296547e-05,
"loss": 3.7332,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.197795675078602e-05,
"loss": 3.7314,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.19695708032755e-05,
"loss": 3.7515,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196118485576498e-05,
"loss": 3.7298,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195279890825446e-05,
"loss": 3.7344,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.194441296074394e-05,
"loss": 3.7191,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.193604339203715e-05,
"loss": 3.7349,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.192765744452663e-05,
"loss": 3.724,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.191927149701611e-05,
"loss": 3.73,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.191088554950559e-05,
"loss": 3.7371,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.1902515980798804e-05,
"loss": 3.7311,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.1894130033288284e-05,
"loss": 3.735,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.1885744085777764e-05,
"loss": 3.7419,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.1877358138267244e-05,
"loss": 3.7381,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.1868972190756724e-05,
"loss": 3.7442,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.1860586243246204e-05,
"loss": 3.7371,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.1852200295735684e-05,
"loss": 3.7203,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.1843814348225164e-05,
"loss": 3.7283,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.183544477951837e-05,
"loss": 3.7402,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.182705883200785e-05,
"loss": 3.7357,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.181867288449733e-05,
"loss": 3.7305,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.181028693698681e-05,
"loss": 3.7126,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.180190098947629e-05,
"loss": 3.7328,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.17935314207695e-05,
"loss": 3.7157,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.178514547325898e-05,
"loss": 3.7331,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.177675952574847e-05,
"loss": 3.7296,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.176837357823795e-05,
"loss": 3.7376,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.175998763072743e-05,
"loss": 3.7318,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.175160168321691e-05,
"loss": 3.7298,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.174323211451012e-05,
"loss": 3.7186,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.17348461669996e-05,
"loss": 3.7324,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.172646021948908e-05,
"loss": 3.7239,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.171807427197855e-05,
"loss": 3.7274,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.170968832446803e-05,
"loss": 3.7188,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.170130237695751e-05,
"loss": 3.7306,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.169293280825073e-05,
"loss": 3.7231,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.1684546860740207e-05,
"loss": 3.748,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.1676160913229687e-05,
"loss": 3.7207,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.1667774965719167e-05,
"loss": 3.7384,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.1659389018208646e-05,
"loss": 3.7292,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.1651003070698126e-05,
"loss": 3.725,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.1642617123187606e-05,
"loss": 3.7425,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.1634231175677086e-05,
"loss": 3.7253,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.1625861606970295e-05,
"loss": 3.7395,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.1617475659459775e-05,
"loss": 3.7253,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.1609089711949255e-05,
"loss": 3.7179,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.1600703764438735e-05,
"loss": 3.716,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.1592334195731944e-05,
"loss": 3.7317,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.1583948248221424e-05,
"loss": 3.7304,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.1575562300710904e-05,
"loss": 3.7264,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.156717635320039e-05,
"loss": 3.7007,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.155879040568987e-05,
"loss": 3.7226,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.155040445817935e-05,
"loss": 3.7369,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.154203488947256e-05,
"loss": 3.7269,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.153364894196204e-05,
"loss": 3.7341,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.152526299445152e-05,
"loss": 3.7286,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.1516877046941e-05,
"loss": 3.7272,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.150849109943048e-05,
"loss": 3.7317,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.150012153072369e-05,
"loss": 3.7235,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.149173558321317e-05,
"loss": 3.7133,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.148334963570265e-05,
"loss": 3.7223,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.147496368819213e-05,
"loss": 3.7224,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.1466594119485345e-05,
"loss": 3.7234,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.1458208171974825e-05,
"loss": 3.7229,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.1449822224464305e-05,
"loss": 3.7276,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.1441436276953785e-05,
"loss": 3.7187,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.1433050329443265e-05,
"loss": 3.7159,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.1424680760736474e-05,
"loss": 3.7326,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.1416294813225954e-05,
"loss": 3.7173,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.1407908865715434e-05,
"loss": 3.7322,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.1399522918204913e-05,
"loss": 3.7324,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.139113697069439e-05,
"loss": 3.7253,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.138275102318387e-05,
"loss": 3.7249,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.137438145447708e-05,
"loss": 3.7265,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.136599550696656e-05,
"loss": 3.7194,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.135760955945604e-05,
"loss": 3.7211,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.134922361194552e-05,
"loss": 3.7381,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.1340837664435e-05,
"loss": 3.7329,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.133246809572821e-05,
"loss": 3.7305,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.132408214821769e-05,
"loss": 3.7292,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.131569620070717e-05,
"loss": 3.7181,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.130731025319665e-05,
"loss": 3.7248,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.129892430568613e-05,
"loss": 3.7177,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.129055473697934e-05,
"loss": 3.7135,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.128216878946882e-05,
"loss": 3.7305,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.12737828419583e-05,
"loss": 3.717,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.126539689444778e-05,
"loss": 3.7126,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.125701094693726e-05,
"loss": 3.7229,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 3.86488938331604,
"eval_runtime": 582.4563,
"eval_samples_per_second": 655.141,
"eval_steps_per_second": 20.474,
"step": 534233
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.644393059920937e+17,
"trial_name": null,
"trial_params": null
}