abhinavp's picture
Training in progress, epoch 1, checkpoint
d5188dc verified
raw
history blame
No virus
37.5 kB
{
"best_metric": 4.4971795082092285,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/re-irr-sv-agr/lstm/3/checkpoints/checkpoint-152640",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 152640,
"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": 10.8201,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5492,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0526,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9871,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9407,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8843,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7378,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6415,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5324,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4537,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3806,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3206,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.252,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.1814,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1257,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0627,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0237,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 5.9827,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9414,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9069,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.879,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8403,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8174,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.7748,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7628,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7318,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.712,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6865,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6532,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6376,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 5.6133,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 5.6036,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 5.5765,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5648,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5546,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5318,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5215,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.9689785457325684e-05,
"loss": 5.4777,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4722,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4533,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.439,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 5.434,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 5.4257,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.3975,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.3965,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 5.3909,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 5.379,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.3733,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 5.3563,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3349,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3376,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 5.3174,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.3197,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2887,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.3009,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2731,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.2915,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2634,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2499,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2446,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2396,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.2252,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948021866358134e-05,
"loss": 5.2266,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947183271607082e-05,
"loss": 5.198,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.94634467685603e-05,
"loss": 5.195,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.2061,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.1981,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1816,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1626,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1623,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1629,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940477789359412e-05,
"loss": 5.1562,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.93963919460836e-05,
"loss": 5.1519,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938800599857309e-05,
"loss": 5.1479,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.937962005106256e-05,
"loss": 5.1494,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.937123410355204e-05,
"loss": 5.1399,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 5.1137,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 5.1105,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346109018627945e-05,
"loss": 5.107,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.095,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329337123606905e-05,
"loss": 5.1048,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932095117609638e-05,
"loss": 5.0855,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931256522858586e-05,
"loss": 5.1028,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930417928107534e-05,
"loss": 5.0783,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295793333564825e-05,
"loss": 5.0619,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.0673,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.0676,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.0641,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262265922326474e-05,
"loss": 5.0502,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925389635361968e-05,
"loss": 5.0465,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924551040610916e-05,
"loss": 5.0385,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.0372,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.025,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 5.0226,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921198299487081e-05,
"loss": 5.021,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920359704736029e-05,
"loss": 5.0256,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 5.0058,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918682515233926e-05,
"loss": 4.9998,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917843920482874e-05,
"loss": 4.9933,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 4.9894,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916168368861143e-05,
"loss": 4.9939,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915329774110091e-05,
"loss": 4.9811,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914491179359039e-05,
"loss": 4.9736,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913652584607987e-05,
"loss": 4.9654,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912813989856935e-05,
"loss": 4.9688,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.9409,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.956,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9429,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.9493,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908624291862421e-05,
"loss": 4.9367,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907785697111369e-05,
"loss": 4.9451,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906947102360317e-05,
"loss": 4.9312,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906108507609265e-05,
"loss": 4.9244,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.9322,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.9104,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.9269,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.90275576648543e-05,
"loss": 4.9158,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901917171734378e-05,
"loss": 4.9131,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901078576983326e-05,
"loss": 4.9006,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900239982232274e-05,
"loss": 4.9007,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899403025361595e-05,
"loss": 4.9025,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.898564430610543e-05,
"loss": 4.8934,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897725835859491e-05,
"loss": 4.8928,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968872411084396e-05,
"loss": 4.8821,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.896048646357387e-05,
"loss": 4.8854,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895210051606335e-05,
"loss": 4.8653,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.894371456855283e-05,
"loss": 4.8692,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893532862104231e-05,
"loss": 4.8529,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892695905233552e-05,
"loss": 4.8585,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918573104825e-05,
"loss": 4.8461,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891018715731448e-05,
"loss": 4.8661,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890180120980396e-05,
"loss": 4.8716,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889341526229344e-05,
"loss": 4.8553,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888504569358665e-05,
"loss": 4.8336,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.8876659746076134e-05,
"loss": 4.8458,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.8868273798565614e-05,
"loss": 4.8442,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.8859887851055094e-05,
"loss": 4.838,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.8851501903544574e-05,
"loss": 4.8328,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.8336,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883474638732726e-05,
"loss": 4.8306,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882636043981674e-05,
"loss": 4.8187,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881797449230622e-05,
"loss": 4.8199,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88095885447957e-05,
"loss": 4.819,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880121897608891e-05,
"loss": 4.8069,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879283302857839e-05,
"loss": 4.8075,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.8154,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.8038,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876769156485057e-05,
"loss": 4.8018,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875930561734005e-05,
"loss": 4.8134,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875091966982953e-05,
"loss": 4.7907,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.779759407043457,
"eval_runtime": 295.6929,
"eval_samples_per_second": 1290.498,
"eval_steps_per_second": 40.329,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874253372231901e-05,
"loss": 4.7784,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873414777480849e-05,
"loss": 4.784,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.87257782061017e-05,
"loss": 4.7984,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871739225859118e-05,
"loss": 4.7851,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709006311080657e-05,
"loss": 4.7911,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700620363570137e-05,
"loss": 4.765,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692234416059616e-05,
"loss": 4.7833,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683848468549096e-05,
"loss": 4.7554,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675462521038576e-05,
"loss": 4.7691,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667076573528056e-05,
"loss": 4.7587,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658690626017536e-05,
"loss": 4.7718,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.8650304678507016e-05,
"loss": 4.7685,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864195148860396e-05,
"loss": 4.7562,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863356554109344e-05,
"loss": 4.7493,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862517959358292e-05,
"loss": 4.736,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.7379,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.748,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.7439,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.7368,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858326623483405e-05,
"loss": 4.7517,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857488028732352e-05,
"loss": 4.7459,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856649433981301e-05,
"loss": 4.7374,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855810839230249e-05,
"loss": 4.7243,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854972244479197e-05,
"loss": 4.7455,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854133649728145e-05,
"loss": 4.7214,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853295054977093e-05,
"loss": 4.731,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852458098106414e-05,
"loss": 4.7272,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851619503355362e-05,
"loss": 4.7206,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.85078090860431e-05,
"loss": 4.7096,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849942313853258e-05,
"loss": 4.7089,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849103719102206e-05,
"loss": 4.7119,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848265124351154e-05,
"loss": 4.7087,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847426529600102e-05,
"loss": 4.7094,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.84658793484905e-05,
"loss": 4.7141,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845750977978371e-05,
"loss": 4.7046,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.8449123832273194e-05,
"loss": 4.7035,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.8440737884762674e-05,
"loss": 4.6828,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.8432351937252154e-05,
"loss": 4.6883,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.8423965989741634e-05,
"loss": 4.6799,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.8415580042231114e-05,
"loss": 4.677,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840719409472059e-05,
"loss": 4.6866,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.83988245260138e-05,
"loss": 4.6895,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839043857850328e-05,
"loss": 4.6722,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838205263099276e-05,
"loss": 4.679,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373666683482236e-05,
"loss": 4.6768,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836529711477545e-05,
"loss": 4.6786,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835691116726493e-05,
"loss": 4.6803,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834852521975441e-05,
"loss": 4.6717,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834013927224389e-05,
"loss": 4.6604,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833175332473337e-05,
"loss": 4.6692,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832338375602659e-05,
"loss": 4.6563,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831499780851606e-05,
"loss": 4.6655,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830661186100554e-05,
"loss": 4.6524,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829822591349502e-05,
"loss": 4.663,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828985634478824e-05,
"loss": 4.6406,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828147039727771e-05,
"loss": 4.6642,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827308444976719e-05,
"loss": 4.6484,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826469850225667e-05,
"loss": 4.6416,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256328933549886e-05,
"loss": 4.6506,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247942986039366e-05,
"loss": 4.6417,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239557038528846e-05,
"loss": 4.6337,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231171091018326e-05,
"loss": 4.6483,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222785143507806e-05,
"loss": 4.6179,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214399195997286e-05,
"loss": 4.6246,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206013248486766e-05,
"loss": 4.6365,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197643679779975e-05,
"loss": 4.6366,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189257732269455e-05,
"loss": 4.6268,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180871784758935e-05,
"loss": 4.6177,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172485837248415e-05,
"loss": 4.6172,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164116268541624e-05,
"loss": 4.6221,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155730321031104e-05,
"loss": 4.6273,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147344373520584e-05,
"loss": 4.6222,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138958426010064e-05,
"loss": 4.623,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813057247849955e-05,
"loss": 4.628,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812218653098903e-05,
"loss": 4.6244,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811381696228224e-05,
"loss": 4.6059,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810543101477172e-05,
"loss": 4.6068,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.80970450672612e-05,
"loss": 4.6139,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808865911975068e-05,
"loss": 4.5986,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808027317224016e-05,
"loss": 4.6103,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807188722472964e-05,
"loss": 4.5963,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806350127721912e-05,
"loss": 4.6213,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.80551153297086e-05,
"loss": 4.6016,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804674576100181e-05,
"loss": 4.5852,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803835981349129e-05,
"loss": 4.5957,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.802997386598077e-05,
"loss": 4.5981,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802158791847025e-05,
"loss": 4.6022,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801320197095973e-05,
"loss": 4.5909,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004832402252944e-05,
"loss": 4.5929,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996446454742424e-05,
"loss": 4.5963,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.79880605072319e-05,
"loss": 4.5843,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797967455972138e-05,
"loss": 4.5836,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797128861221086e-05,
"loss": 4.582,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796291904350407e-05,
"loss": 4.59,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954533095993546e-05,
"loss": 4.5858,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946147148483026e-05,
"loss": 4.5826,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937761200972506e-05,
"loss": 4.5722,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929375253461986e-05,
"loss": 4.5716,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792098930595147e-05,
"loss": 4.5769,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791260335844095e-05,
"loss": 4.5757,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790421741093043e-05,
"loss": 4.5711,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789584784222364e-05,
"loss": 4.5677,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788747827351685e-05,
"loss": 4.5597,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787909232600633e-05,
"loss": 4.5716,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.787070637849581e-05,
"loss": 4.5405,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786232043098529e-05,
"loss": 4.5647,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785393448347477e-05,
"loss": 4.5553,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784554853596425e-05,
"loss": 4.5642,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783716258845373e-05,
"loss": 4.551,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782879301974694e-05,
"loss": 4.5646,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782040707223642e-05,
"loss": 4.5518,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812021124725906e-05,
"loss": 4.5493,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803635177215386e-05,
"loss": 4.5595,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795249229704866e-05,
"loss": 4.5427,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786863282194346e-05,
"loss": 4.5573,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778477334683826e-05,
"loss": 4.5556,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770107765977035e-05,
"loss": 4.5497,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761721818466515e-05,
"loss": 4.5415,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.7753335870955995e-05,
"loss": 4.5465,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7744966302249204e-05,
"loss": 4.5487,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736580354738684e-05,
"loss": 4.5352,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728194407228164e-05,
"loss": 4.551,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719808459717644e-05,
"loss": 4.5335,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771143889101086e-05,
"loss": 4.5419,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770305294350034e-05,
"loss": 4.5344,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769466699598982e-05,
"loss": 4.532,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.76862810484793e-05,
"loss": 4.5148,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767791147977251e-05,
"loss": 4.5305,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766952553226199e-05,
"loss": 4.5166,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766113958475147e-05,
"loss": 4.5387,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765275363724095e-05,
"loss": 4.5492,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764436768973043e-05,
"loss": 4.5322,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.76359817422199e-05,
"loss": 4.515,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762759579470938e-05,
"loss": 4.5288,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761920984719886e-05,
"loss": 4.5234,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761082389968834e-05,
"loss": 4.5265,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760243795217783e-05,
"loss": 4.5231,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759405200466731e-05,
"loss": 4.5219,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758566605715679e-05,
"loss": 4.5186,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757731286725373e-05,
"loss": 4.5164,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7568926919743206e-05,
"loss": 4.5163,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560540972232686e-05,
"loss": 4.521,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552155024722166e-05,
"loss": 4.5128,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543785456015375e-05,
"loss": 4.5066,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535399508504855e-05,
"loss": 4.5203,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527013560994335e-05,
"loss": 4.5137,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518627613483815e-05,
"loss": 4.5045,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510241665973295e-05,
"loss": 4.5231,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750185571846278e-05,
"loss": 4.5038,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.4971795082092285,
"eval_runtime": 294.126,
"eval_samples_per_second": 1297.373,
"eval_steps_per_second": 40.544,
"step": 152640
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 6.111909859839682e+16,
"trial_name": null,
"trial_params": null
}