abhinavp's picture
Training in progress, epoch 1, checkpoint
0efbfeb verified
raw
history blame
No virus
37.5 kB
{
"best_metric": 4.522295951843262,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/lstm/2/checkpoints/checkpoint-152638",
"epoch": 1.0250002784396635,
"eval_steps": 10,
"global_step": 152638,
"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": 10.8189,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5766,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0513,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9791,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9499,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8293,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.6937,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.5841,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5062,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4294,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3809,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3188,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2573,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.1866,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1218,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.075,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0276,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 5.9778,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9435,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984066699730012e-05,
"loss": 5.9012,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8726,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8347,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.7997,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.7776,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7449,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7183,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.6939,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6724,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6387,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6235,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.5966,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.5782,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5656,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.5474,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5259,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5167,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5017,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.482,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4636,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4535,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4274,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.427,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.397,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.3968,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963110020355577e-05,
"loss": 5.3891,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962271425604525e-05,
"loss": 5.3783,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961432830853473e-05,
"loss": 5.3527,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960594236102421e-05,
"loss": 5.3507,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 5.347,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3236,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3095,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3072,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.3124,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2793,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.3005,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2593,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.271,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2487,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2442,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2368,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2306,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.2106,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948021866358134e-05,
"loss": 5.2175,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947183271607082e-05,
"loss": 5.1997,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.94634467685603e-05,
"loss": 5.207,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945506082104978e-05,
"loss": 5.1876,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.1789,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943830530483247e-05,
"loss": 5.163,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942991935732195e-05,
"loss": 5.1704,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942153340981143e-05,
"loss": 5.1645,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413147462300904e-05,
"loss": 5.1443,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404761514790384e-05,
"loss": 5.1472,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.939637556727987e-05,
"loss": 5.1392,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938798961976935e-05,
"loss": 5.1349,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1317,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371250482355776e-05,
"loss": 5.1258,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1141,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935447858733473e-05,
"loss": 5.0967,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934609263982421e-05,
"loss": 5.1035,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.0945,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329337123606905e-05,
"loss": 5.0964,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932095117609638e-05,
"loss": 5.0893,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931256522858586e-05,
"loss": 5.077,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930417928107534e-05,
"loss": 5.0572,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295793333564825e-05,
"loss": 5.0639,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.0656,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.0612,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.0507,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262265922326474e-05,
"loss": 5.0429,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.9253879974815954e-05,
"loss": 5.0312,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.9245494027305433e-05,
"loss": 5.026,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.9237108079794913e-05,
"loss": 5.0214,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922872213228439e-05,
"loss": 5.0314,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 5.0199,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.9966,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 4.9978,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 5.0043,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 5.0006,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.9896,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 4.9891,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916168368861143e-05,
"loss": 4.975,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915329774110091e-05,
"loss": 4.9736,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.9806,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.9754,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.9499,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9608,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9397,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.9444,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.9426,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.9309,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.9304,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9191,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9176,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.915,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.9269,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.9017,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.887,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.8958,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901080214863699e-05,
"loss": 4.9079,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.8892,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899403025361595e-05,
"loss": 4.8975,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.886,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.8858,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.8717,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.8754,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.8691,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.8736,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.8521,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8618,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8586,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.842,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.8528,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.845,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.8487,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.8461,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.8282,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.8239,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.8227,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884314871364151e-05,
"loss": 4.8276,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883476276613099e-05,
"loss": 4.8349,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882637681862047e-05,
"loss": 4.8233,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881799087110995e-05,
"loss": 4.8141,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880960492359943e-05,
"loss": 4.8091,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.807,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.8068,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.801,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.8136,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.7994,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.7912,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.7854,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.802785396575928,
"eval_runtime": 550.4578,
"eval_samples_per_second": 693.225,
"eval_steps_per_second": 21.664,
"step": 76319
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.8012,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.7914,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.777,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.7791,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.7677,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.7651,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.7614,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.7634,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.7597,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.7602,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.7597,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.7637,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.7515,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.7417,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.7411,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.7232,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.7367,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.7329,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.73,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.7404,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.7285,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.7269,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.7296,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.7236,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.7151,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.7136,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.7194,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.7053,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.707,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.6927,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.6949,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.7082,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.6972,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.6968,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.6934,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.6974,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.6919,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.6885,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.6887,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.6757,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840725960993552e-05,
"loss": 4.6813,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398873662425e-05,
"loss": 4.6665,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839048771491447e-05,
"loss": 4.6726,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838210176740395e-05,
"loss": 4.6812,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.6797,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.6638,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.668,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.6723,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.6518,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331818839948295e-05,
"loss": 4.6516,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323432892437775e-05,
"loss": 4.6527,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315046944927255e-05,
"loss": 4.665,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306660997416735e-05,
"loss": 4.642,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.6677,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.6356,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.6499,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273133586178384e-05,
"loss": 4.643,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826474763866787e-05,
"loss": 4.6451,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.637,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824797574364683e-05,
"loss": 4.64,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823958979613631e-05,
"loss": 4.6291,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823120384862579e-05,
"loss": 4.637,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822281790111527e-05,
"loss": 4.6292,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.6349,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.6269,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.6261,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.6066,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.633,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817251859485588e-05,
"loss": 4.6213,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.6099,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815574669983483e-05,
"loss": 4.6187,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.613,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138991183617535e-05,
"loss": 4.6147,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813060523610701e-05,
"loss": 4.6222,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.6186,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113866098693434e-05,
"loss": 4.6067,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.5984,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097094203672393e-05,
"loss": 4.6051,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.8088708256161873e-05,
"loss": 4.6053,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.6125,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.6048,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.5983,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805518084492352e-05,
"loss": 4.5809,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046794897413e-05,
"loss": 4.5895,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803840894990248e-05,
"loss": 4.596,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803002300239196e-05,
"loss": 4.5945,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802165343368518e-05,
"loss": 4.5962,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.5893,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800488153866413e-05,
"loss": 4.5819,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799649559115361e-05,
"loss": 4.5842,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798812602244683e-05,
"loss": 4.5763,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.79797400749363e-05,
"loss": 4.5844,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.5858,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7962984558718996e-05,
"loss": 4.5637,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954598611208476e-05,
"loss": 4.5665,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946212663697956e-05,
"loss": 4.5763,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937826716187436e-05,
"loss": 4.5837,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929440768676916e-05,
"loss": 4.568,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921054821166396e-05,
"loss": 4.5738,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912668873655876e-05,
"loss": 4.5667,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904282926145356e-05,
"loss": 4.5639,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895913357438565e-05,
"loss": 4.5752,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887543788731774e-05,
"loss": 4.5693,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879157841221254e-05,
"loss": 4.5528,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870771893710734e-05,
"loss": 4.5681,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862385946200214e-05,
"loss": 4.5467,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853999998689694e-05,
"loss": 4.5518,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784561405117918e-05,
"loss": 4.5601,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783724448247239e-05,
"loss": 4.5475,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782885853496187e-05,
"loss": 4.5484,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782047258745135e-05,
"loss": 4.5441,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781208663994083e-05,
"loss": 4.5431,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780370069243031e-05,
"loss": 4.5425,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779531474491979e-05,
"loss": 4.5577,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778692879740927e-05,
"loss": 4.5377,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777854284989875e-05,
"loss": 4.5303,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777015690238823e-05,
"loss": 4.5368,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776177095487771e-05,
"loss": 4.5445,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775338500736719e-05,
"loss": 4.5379,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450154386604e-05,
"loss": 4.5427,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773662949114988e-05,
"loss": 4.5391,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772824354363936e-05,
"loss": 4.5395,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719857596128845e-05,
"loss": 4.5314,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711488027422054e-05,
"loss": 4.527,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703102079911534e-05,
"loss": 4.5312,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694716132401014e-05,
"loss": 4.5352,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686330184890494e-05,
"loss": 4.5209,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76779606161837e-05,
"loss": 4.5246,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766957466867318e-05,
"loss": 4.5385,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766118872116266e-05,
"loss": 4.5115,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.7652802773652136e-05,
"loss": 4.5258,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.7644416826141616e-05,
"loss": 4.5212,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.7636030878631096e-05,
"loss": 4.5318,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762764493112058e-05,
"loss": 4.5242,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761925898361006e-05,
"loss": 4.5118,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761088941490327e-05,
"loss": 4.5102,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760251984619649e-05,
"loss": 4.5115,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759413389868596e-05,
"loss": 4.5185,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758574795117544e-05,
"loss": 4.5266,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757736200366492e-05,
"loss": 4.5214,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.75689760561544e-05,
"loss": 4.5069,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756059010864388e-05,
"loss": 4.5098,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755220416113336e-05,
"loss": 4.5113,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754381821362284e-05,
"loss": 4.5089,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753544864491605e-05,
"loss": 4.5068,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527062697405536e-05,
"loss": 4.5223,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518676749895016e-05,
"loss": 4.5033,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510290802384496e-05,
"loss": 4.5023,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501921233677705e-05,
"loss": 4.4977,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.522295951843262,
"eval_runtime": 547.7152,
"eval_samples_per_second": 696.696,
"eval_steps_per_second": 21.772,
"step": 152638
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 5.873792269349571e+16,
"trial_name": null,
"trial_params": null
}