abhinavp's picture
Training in progress, epoch 0, checkpoint
cbd8b67 verified
raw
history blame
No virus
56 kB
{
"best_metric": 4.3308024406433105,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/lstm/4/checkpoints/checkpoint-228960",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 228960,
"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
},
{
"epoch": 1.0,
"learning_rate": 4.874253372231901e-05,
"loss": 4.7633,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873414777480849e-05,
"loss": 4.7743,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.87257782061017e-05,
"loss": 4.7893,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871739225859118e-05,
"loss": 4.7638,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709006311080657e-05,
"loss": 4.7758,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700620363570137e-05,
"loss": 4.7509,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692234416059616e-05,
"loss": 4.7671,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683848468549096e-05,
"loss": 4.7444,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675478899842306e-05,
"loss": 4.7539,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.753,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7565,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.7516,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.7338,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.7319,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.7266,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.7308,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.7448,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.7239,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.731,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858326623483405e-05,
"loss": 4.7447,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857488028732352e-05,
"loss": 4.7182,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856651071861674e-05,
"loss": 4.7155,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558124771106226e-05,
"loss": 4.7139,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.85497388235957e-05,
"loss": 4.7264,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854135287608518e-05,
"loss": 4.7059,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853296692857466e-05,
"loss": 4.7084,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852458098106414e-05,
"loss": 4.7059,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851619503355362e-05,
"loss": 4.7042,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.85078090860431e-05,
"loss": 4.6855,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849943951733631e-05,
"loss": 4.6928,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849105356982579e-05,
"loss": 4.6896,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.6967,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.7018,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.6879,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.6844,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.6952,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844077064237013e-05,
"loss": 4.6671,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.6737,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842399874734909e-05,
"loss": 4.6623,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841561279983857e-05,
"loss": 4.6704,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840722685232805e-05,
"loss": 4.6619,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839884090481753e-05,
"loss": 4.6768,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839045495730701e-05,
"loss": 4.6591,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838206900979649e-05,
"loss": 4.6647,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.6595,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836531349357918e-05,
"loss": 4.664,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835692754606866e-05,
"loss": 4.6595,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834854159855814e-05,
"loss": 4.6499,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.6375,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.6612,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.6494,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.6402,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.636,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.6425,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.631,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281486776081446e-05,
"loss": 4.6508,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273100828570926e-05,
"loss": 4.6309,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.629,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.6372,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.6182,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.6128,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.6236,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222801522311535e-05,
"loss": 4.6041,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821443195360475e-05,
"loss": 4.6133,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.6219,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819766005858371e-05,
"loss": 4.6252,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189274111073184e-05,
"loss": 4.6121,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.604,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817251859485588e-05,
"loss": 4.5955,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.6163,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815574669983483e-05,
"loss": 4.61,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814736075232432e-05,
"loss": 4.6091,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.81389748048138e-05,
"loss": 4.6092,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813060523610701e-05,
"loss": 4.616,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.6106,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811383334108597e-05,
"loss": 4.5898,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810544739357545e-05,
"loss": 4.6,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809706144606493e-05,
"loss": 4.5987,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808867549855441e-05,
"loss": 4.5829,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808028955104389e-05,
"loss": 4.6086,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.5967,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806353403482658e-05,
"loss": 4.6015,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805514808731606e-05,
"loss": 4.5982,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804676213980554e-05,
"loss": 4.5713,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803837619229502e-05,
"loss": 4.5893,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8029990244784504e-05,
"loss": 4.5854,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.8021604297273984e-05,
"loss": 4.588,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013218349763464e-05,
"loss": 4.5846,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800484878105667e-05,
"loss": 4.581,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799646283354615e-05,
"loss": 4.5817,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798807688603563e-05,
"loss": 4.5775,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797969093852511e-05,
"loss": 4.5636,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797130499101459e-05,
"loss": 4.57,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796291904350407e-05,
"loss": 4.5731,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954533095993546e-05,
"loss": 4.5764,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794616352728676e-05,
"loss": 4.5649,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793777757977624e-05,
"loss": 4.5581,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792939163226572e-05,
"loss": 4.5569,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.79210056847552e-05,
"loss": 4.5698,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791261973724468e-05,
"loss": 4.5662,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790423378973416e-05,
"loss": 4.5596,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789584784222364e-05,
"loss": 4.5517,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788746189471312e-05,
"loss": 4.5452,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787909232600633e-05,
"loss": 4.5543,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870722757299546e-05,
"loss": 4.5409,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786233680978902e-05,
"loss": 4.5465,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.78539508622785e-05,
"loss": 4.5463,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784556491476798e-05,
"loss": 4.5473,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783717896725746e-05,
"loss": 4.5458,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782879301974694e-05,
"loss": 4.5489,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782040707223642e-05,
"loss": 4.5362,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812021124725906e-05,
"loss": 4.5403,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803635177215386e-05,
"loss": 4.5364,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795249229704866e-05,
"loss": 4.5304,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786863282194346e-05,
"loss": 4.547,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778493713487555e-05,
"loss": 4.5402,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770107765977035e-05,
"loss": 4.5387,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761721818466515e-05,
"loss": 4.5321,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.7753335870955995e-05,
"loss": 4.5394,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7744949923445475e-05,
"loss": 4.5374,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736563975934955e-05,
"loss": 4.5228,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728178028424435e-05,
"loss": 4.5429,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719808459717644e-05,
"loss": 4.5296,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771145526981459e-05,
"loss": 4.5318,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770306932230407e-05,
"loss": 4.5159,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769468337479355e-05,
"loss": 4.5175,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768629742728303e-05,
"loss": 4.5102,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767791147977251e-05,
"loss": 4.5133,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766952553226199e-05,
"loss": 4.5098,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766113958475147e-05,
"loss": 4.5257,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765275363724095e-05,
"loss": 4.5285,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764436768973043e-05,
"loss": 4.5161,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.76359817422199e-05,
"loss": 4.5097,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762759579470938e-05,
"loss": 4.5157,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.76192262260026e-05,
"loss": 4.5162,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761084027849208e-05,
"loss": 4.5232,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760245433098156e-05,
"loss": 4.5176,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759406838347104e-05,
"loss": 4.5086,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758568243596052e-05,
"loss": 4.5034,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757729648845e-05,
"loss": 4.5099,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756891054093948e-05,
"loss": 4.5024,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560540972232686e-05,
"loss": 4.5089,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552155024722166e-05,
"loss": 4.5029,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543769077211646e-05,
"loss": 4.4977,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535383129701126e-05,
"loss": 4.5095,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7526997182190606e-05,
"loss": 4.4972,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518611234680086e-05,
"loss": 4.4916,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510241665973295e-05,
"loss": 4.4947,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750185571846278e-05,
"loss": 4.4932,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.463821887969971,
"eval_runtime": 297.3209,
"eval_samples_per_second": 1283.432,
"eval_steps_per_second": 40.108,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749346977095226e-05,
"loss": 4.4796,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748508382344174e-05,
"loss": 4.4932,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747669787593122e-05,
"loss": 4.5077,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.74683119284207e-05,
"loss": 4.4857,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745992598091018e-05,
"loss": 4.4978,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745154003339966e-05,
"loss": 4.4788,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744315408588914e-05,
"loss": 4.4947,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743476813837862e-05,
"loss": 4.4709,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426382190868095e-05,
"loss": 4.4891,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7417996243357575e-05,
"loss": 4.4862,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409610295847055e-05,
"loss": 4.4866,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401224348336535e-05,
"loss": 4.4944,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739285477962975e-05,
"loss": 4.4703,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384485210922966e-05,
"loss": 4.4701,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376099263412446e-05,
"loss": 4.4662,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736771331590192e-05,
"loss": 4.4756,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.73593273683914e-05,
"loss": 4.4823,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735094142088088e-05,
"loss": 4.4721,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734255547337036e-05,
"loss": 4.4756,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733416952585984e-05,
"loss": 4.4913,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732578357834932e-05,
"loss": 4.4693,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.73173976308388e-05,
"loss": 4.4643,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730901168332828e-05,
"loss": 4.4678,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730062573581776e-05,
"loss": 4.4798,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729225616711097e-05,
"loss": 4.4621,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728387021960045e-05,
"loss": 4.4639,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727548427208993e-05,
"loss": 4.464,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267098324579415e-05,
"loss": 4.4625,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258712377068895e-05,
"loss": 4.4474,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250326429558375e-05,
"loss": 4.457,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7241956860851584e-05,
"loss": 4.4574,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233570913341064e-05,
"loss": 4.4574,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225184965830544e-05,
"loss": 4.471,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216799018320024e-05,
"loss": 4.4498,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720842944961323e-05,
"loss": 4.4538,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720004350210271e-05,
"loss": 4.4611,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719165755459219e-05,
"loss": 4.4444,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718327160708167e-05,
"loss": 4.4425,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717488565957115e-05,
"loss": 4.4384,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716651609086437e-05,
"loss": 4.4468,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715813014335385e-05,
"loss": 4.436,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714974419584333e-05,
"loss": 4.4556,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714137462713654e-05,
"loss": 4.4354,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713300505842975e-05,
"loss": 4.4505,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712461911091923e-05,
"loss": 4.442,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711623316340871e-05,
"loss": 4.4396,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710784721589819e-05,
"loss": 4.4468,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099461268387667e-05,
"loss": 4.4305,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091075320877147e-05,
"loss": 4.4226,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082689373366627e-05,
"loss": 4.4459,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074303425856106e-05,
"loss": 4.4377,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7065917478345586e-05,
"loss": 4.4275,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057531530835066e-05,
"loss": 4.432,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.7049145583324546e-05,
"loss": 4.4344,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040759635814026e-05,
"loss": 4.4166,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032390067107235e-05,
"loss": 4.44,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024004119596715e-05,
"loss": 4.4243,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015618172086195e-05,
"loss": 4.4221,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007232224575675e-05,
"loss": 4.4348,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998846277065155e-05,
"loss": 4.4134,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990476708358364e-05,
"loss": 4.4112,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982090760847844e-05,
"loss": 4.4255,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973704813337324e-05,
"loss": 4.4059,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965318865826804e-05,
"loss": 4.4124,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695693291831629e-05,
"loss": 4.424,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.69485633496095e-05,
"loss": 4.4275,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.6940210159706445e-05,
"loss": 4.4119,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931824212195925e-05,
"loss": 4.412,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.69234382646854e-05,
"loss": 4.4002,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691505231717488e-05,
"loss": 4.4231,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690666636966436e-05,
"loss": 4.4152,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689828042215384e-05,
"loss": 4.4197,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688989447464332e-05,
"loss": 4.4151,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.68815085271328e-05,
"loss": 4.4245,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687312257962228e-05,
"loss": 4.426,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686473663211176e-05,
"loss": 4.3994,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856350684601245e-05,
"loss": 4.4112,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6847964737090725e-05,
"loss": 4.4154,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839578789580204e-05,
"loss": 4.3955,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831192842069684e-05,
"loss": 4.4206,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822823273362894e-05,
"loss": 4.4127,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814437325852373e-05,
"loss": 4.4159,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806051378341853e-05,
"loss": 4.415,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797665430831333e-05,
"loss": 4.3901,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678929586212454e-05,
"loss": 4.4088,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678090991461402e-05,
"loss": 4.404,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.67725239671035e-05,
"loss": 4.4104,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676413801959298e-05,
"loss": 4.402,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675576845088619e-05,
"loss": 4.4069,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674738250337568e-05,
"loss": 4.403,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673899655586516e-05,
"loss": 4.4,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673061060835464e-05,
"loss": 4.3887,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672222466084412e-05,
"loss": 4.3947,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671385509213733e-05,
"loss": 4.4004,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670546914462681e-05,
"loss": 4.4028,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669708319711629e-05,
"loss": 4.3963,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688713628409496e-05,
"loss": 4.3841,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680327680898976e-05,
"loss": 4.3866,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6671941733388456e-05,
"loss": 4.3988,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663555785877936e-05,
"loss": 4.3945,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655169838367416e-05,
"loss": 4.391,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.6646783890856896e-05,
"loss": 4.385,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663841432215011e-05,
"loss": 4.375,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663002837463959e-05,
"loss": 4.3924,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621642427129065e-05,
"loss": 4.37,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613256479618545e-05,
"loss": 4.3842,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6604870532108025e-05,
"loss": 4.3749,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596484584597505e-05,
"loss": 4.3918,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588098637086985e-05,
"loss": 4.377,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579712689576465e-05,
"loss": 4.3877,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571343120869674e-05,
"loss": 4.3751,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6562957173359154e-05,
"loss": 4.3731,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554571225848634e-05,
"loss": 4.379,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546185278338114e-05,
"loss": 4.3674,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.65377993308276e-05,
"loss": 4.3883,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652941338331708e-05,
"loss": 4.3827,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652104381461029e-05,
"loss": 4.3806,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651265786709977e-05,
"loss": 4.3722,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650427191958925e-05,
"loss": 4.3794,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649588597207873e-05,
"loss": 4.383,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648750002456821e-05,
"loss": 4.3623,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647911407705769e-05,
"loss": 4.3864,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647072812954717e-05,
"loss": 4.3759,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646235856084038e-05,
"loss": 4.3762,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645398899213359e-05,
"loss": 4.3674,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.64456194234268e-05,
"loss": 4.3664,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643723347591628e-05,
"loss": 4.353,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642884752840576e-05,
"loss": 4.3638,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642046158089524e-05,
"loss": 4.3599,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641207563338472e-05,
"loss": 4.3718,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.64036896858742e-05,
"loss": 4.3774,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639530373836368e-05,
"loss": 4.3661,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638691779085316e-05,
"loss": 4.3607,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637853184334264e-05,
"loss": 4.365,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637014589583212e-05,
"loss": 4.3692,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6361759948321596e-05,
"loss": 4.3731,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353374000811076e-05,
"loss": 4.3699,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6344988053300556e-05,
"loss": 4.3589,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336602105790036e-05,
"loss": 4.3648,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632821615827952e-05,
"loss": 4.3683,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6319830210769e-05,
"loss": 4.3538,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631146064206221e-05,
"loss": 4.3636,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630309107335542e-05,
"loss": 4.3573,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.62947051258449e-05,
"loss": 4.3553,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628631917833438e-05,
"loss": 4.3669,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627793323082386e-05,
"loss": 4.3555,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626956366211707e-05,
"loss": 4.3479,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626117771460655e-05,
"loss": 4.3552,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625279176709603e-05,
"loss": 4.3479,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.3308024406433105,
"eval_runtime": 296.402,
"eval_samples_per_second": 1287.411,
"eval_steps_per_second": 40.233,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 9.420222446476171e+16,
"trial_name": null,
"trial_params": null
}