abhinavp's picture
Training in progress, epoch 0, checkpoint
e9145a9 verified
raw
history blame
No virus
19.1 kB
{
"best_metric": 4.742868900299072,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/lstm/4/checkpoints/checkpoint-76320",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 76320,
"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": 10.8204,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5494,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0584,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9988,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9454,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.9362,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7913,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.652,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5405,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4673,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.412,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3604,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2976,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.2349,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1714,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.1143,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0627,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 6.0242,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.98490857024181e-05,
"loss": 5.9703,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984069975490758e-05,
"loss": 5.9346,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983231380739706e-05,
"loss": 5.8984,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 5.8487,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 5.8187,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.7859,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7672,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7317,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 5.7045,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 5.6864,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6597,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6319,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6092,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 5.5993,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 5.5765,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5654,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.544,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 5.5242,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.52,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4793,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4699,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4495,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966467675120532e-05,
"loss": 5.4442,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.96562908036948e-05,
"loss": 5.4196,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964790485618428e-05,
"loss": 5.425,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 5.39,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 5.3908,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.9622763392456454e-05,
"loss": 5.3843,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.9614377444945934e-05,
"loss": 5.3754,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.9605991497435414e-05,
"loss": 5.3667,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 5.343,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 5.323,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 5.337,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 5.3164,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.3028,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2851,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 5.2916,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 5.2689,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 5.2843,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 5.2531,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 5.2449,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2457,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 5.231,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 5.2091,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2119,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.1898,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.1911,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2003,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.1918,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1734,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1541,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1481,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1591,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1484,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.1429,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 5.1403,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 5.1401,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 5.1309,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 5.1024,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 5.1067,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346109018627945e-05,
"loss": 5.1005,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.0868,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329337123606905e-05,
"loss": 5.1046,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 5.0833,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.0891,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 5.0743,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295809712368554e-05,
"loss": 5.0501,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.0553,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.058,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 5.052,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 5.0455,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 5.0331,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.92455267849129e-05,
"loss": 5.0322,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.0194,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.0118,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 5.0095,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921198299487081e-05,
"loss": 5.0025,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920359704736029e-05,
"loss": 5.0095,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 4.9913,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918682515233926e-05,
"loss": 4.985,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.9778,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.9816,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.9792,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.9666,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.9598,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.944,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.9524,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9392,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111384382352036e-05,
"loss": 4.9353,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9363,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.933,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908624291862421e-05,
"loss": 4.9271,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907785697111369e-05,
"loss": 4.9238,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9135,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9142,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.9049,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.9001,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.9069,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.8977,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.8959,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901080214863699e-05,
"loss": 4.8862,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.8955,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899403025361595e-05,
"loss": 4.8897,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.898564430610543e-05,
"loss": 4.8706,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897725835859491e-05,
"loss": 4.8848,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968872411084396e-05,
"loss": 4.873,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.896048646357387e-05,
"loss": 4.8742,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895210051606335e-05,
"loss": 4.8529,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.894371456855283e-05,
"loss": 4.8468,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.8418,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8455,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8332,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.8521,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890181758860769e-05,
"loss": 4.8479,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889343164109717e-05,
"loss": 4.8304,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888504569358665e-05,
"loss": 4.834,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.83,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.8296,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885990422985882e-05,
"loss": 4.8306,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515182823483e-05,
"loss": 4.8304,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.8123,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883474638732726e-05,
"loss": 4.8136,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882636043981674e-05,
"loss": 4.8077,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881797449230622e-05,
"loss": 4.7993,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88095885447957e-05,
"loss": 4.8124,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880120259728518e-05,
"loss": 4.7981,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879281664977466e-05,
"loss": 4.7879,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878443070226414e-05,
"loss": 4.8033,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877606113355735e-05,
"loss": 4.7858,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876769156485057e-05,
"loss": 4.783,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875930561734005e-05,
"loss": 4.7862,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875091966982953e-05,
"loss": 4.7774,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.742868900299072,
"eval_runtime": 297.3608,
"eval_samples_per_second": 1283.259,
"eval_steps_per_second": 40.103,
"step": 76320
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.1400741488253904e+16,
"trial_name": null,
"trial_params": null
}