abhinavp's picture
Training in progress, epoch 1, checkpoint
3d47f5d verified
{
"best_metric": 4.023052215576172,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sim-ques/transformer/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": 11.017,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8258,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.2024,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9812,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.812,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7064,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.595,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5237,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4424,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3939,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3316,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3101,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2571,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.1918,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1639,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1214,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1038,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.06,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0316,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0076,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 4.9891,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9663,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9455,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9271,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9063,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.884,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8572,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.842,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8209,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8138,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7963,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7798,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.772,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7526,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7482,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7436,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7239,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.6899,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 4.701,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 4.6717,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6672,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6654,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6575,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6407,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6428,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6341,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6237,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6151,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5926,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 4.5885,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.5936,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.578,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5651,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.552,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5559,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5399,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5554,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5274,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.534,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5266,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5026,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 4.5129,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.4983,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4888,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4864,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.5013,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4795,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4674,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4551,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4559,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4718,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4695,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4438,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388055134984274e-05,
"loss": 4.4624,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4554,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4414,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.428,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4326,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4215,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4163,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4164,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4129,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4138,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.4104,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.3922,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928747290126923e-05,
"loss": 4.3962,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927908695375871e-05,
"loss": 4.3973,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927070100624819e-05,
"loss": 4.3879,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.3838,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.381,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3813,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3689,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.3706,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3645,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3687,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3638,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3582,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3408,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.3462,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3497,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916173282502262e-05,
"loss": 4.3563,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.91533468775121e-05,
"loss": 4.3408,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914496093000158e-05,
"loss": 4.3309,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913657498249106e-05,
"loss": 4.3274,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3347,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3063,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3141,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.317,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3155,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3078,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3157,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.2964,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.323,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3014,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3048,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3082,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.317,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019237232558704e-05,
"loss": 4.294,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010851285048184e-05,
"loss": 4.2885,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900246533753767e-05,
"loss": 4.293,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899407939002715e-05,
"loss": 4.2822,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985693442516624e-05,
"loss": 4.2895,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2863,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.2743,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2925,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2733,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2692,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.268,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.2723,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2586,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2757,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2688,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2569,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2482,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.2593,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.254,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.259,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.2538,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2536,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2515,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2459,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.8818040007521146e-05,
"loss": 4.2378,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809654060010626e-05,
"loss": 4.2358,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801268112500106e-05,
"loss": 4.2426,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2214,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2425,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.2374,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876774070126176e-05,
"loss": 4.2293,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875935475375124e-05,
"loss": 4.2304,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875096880624072e-05,
"loss": 4.2287,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.191126823425293,
"eval_runtime": 302.1611,
"eval_samples_per_second": 1262.872,
"eval_steps_per_second": 39.466,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.2053,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873421329002341e-05,
"loss": 4.2138,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872582734251289e-05,
"loss": 4.2239,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.2113,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.2159,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.2058,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869229993127454e-05,
"loss": 4.2033,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683913983764027e-05,
"loss": 4.1972,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.2062,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.1942,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658772520036196e-05,
"loss": 4.2148,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.8650386572525676e-05,
"loss": 4.2074,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642017003818885e-05,
"loss": 4.1903,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633631056308365e-05,
"loss": 4.1855,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625245108797845e-05,
"loss": 4.1851,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616859161287324e-05,
"loss": 4.1839,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608473213776804e-05,
"loss": 4.1793,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860008726626628e-05,
"loss": 4.1798,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591701318755764e-05,
"loss": 4.1743,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583315371245244e-05,
"loss": 4.1893,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857494580253846e-05,
"loss": 4.1785,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856655985502793e-05,
"loss": 4.1823,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855817390751741e-05,
"loss": 4.1787,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854978796000689e-05,
"loss": 4.1866,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854141839130011e-05,
"loss": 4.1622,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853303244378958e-05,
"loss": 4.1643,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852464649627906e-05,
"loss": 4.1603,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851626054876854e-05,
"loss": 4.1606,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850789098006175e-05,
"loss": 4.1606,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849950503255123e-05,
"loss": 4.1585,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849111908504072e-05,
"loss": 4.161,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.84827331375302e-05,
"loss": 4.1628,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847436356882341e-05,
"loss": 4.1502,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846597762131289e-05,
"loss": 4.1583,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845759167380237e-05,
"loss": 4.1648,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844920572629185e-05,
"loss": 4.151,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.8440836157585056e-05,
"loss": 4.1369,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.8432450210074536e-05,
"loss": 4.1486,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.8424064262564016e-05,
"loss": 4.1298,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.8415678315053496e-05,
"loss": 4.1388,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.8407308746346705e-05,
"loss": 4.1377,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398922798836185e-05,
"loss": 4.1466,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839053685132567e-05,
"loss": 4.133,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838215090381515e-05,
"loss": 4.1399,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837378133510836e-05,
"loss": 4.1448,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836539538759784e-05,
"loss": 4.1364,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835700944008732e-05,
"loss": 4.1367,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.83486234925768e-05,
"loss": 4.1188,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834023754506628e-05,
"loss": 4.1264,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833185159755576e-05,
"loss": 4.1331,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832348202884897e-05,
"loss": 4.1251,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831509608133845e-05,
"loss": 4.1195,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830671013382793e-05,
"loss": 4.1058,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829832418631741e-05,
"loss": 4.1181,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289954617610625e-05,
"loss": 4.108,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281568670100105e-05,
"loss": 4.1229,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273182722589585e-05,
"loss": 4.1095,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264796775079065e-05,
"loss": 4.1197,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256427206372274e-05,
"loss": 4.1199,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248041258861754e-05,
"loss": 4.0944,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239655311351234e-05,
"loss": 4.1095,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231269363840714e-05,
"loss": 4.1064,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222883416330194e-05,
"loss": 4.096,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.82145138476234e-05,
"loss": 4.0985,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820612790011288e-05,
"loss": 4.1162,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819774195260236e-05,
"loss": 4.1032,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818935600509184e-05,
"loss": 4.0924,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818098643638506e-05,
"loss": 4.0838,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817260048887454e-05,
"loss": 4.0921,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816421454136402e-05,
"loss": 4.1058,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.81558285938535e-05,
"loss": 4.1083,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814745902514671e-05,
"loss": 4.0939,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813907307763619e-05,
"loss": 4.1062,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813068713012567e-05,
"loss": 4.1019,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812230118261515e-05,
"loss": 4.0956,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811393161390836e-05,
"loss": 4.0821,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810554566639784e-05,
"loss": 4.0975,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809715971888732e-05,
"loss": 4.0856,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887737713768e-05,
"loss": 4.0822,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808040420267001e-05,
"loss": 4.0867,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807201825515949e-05,
"loss": 4.0838,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806363230764897e-05,
"loss": 4.0966,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805524636013845e-05,
"loss": 4.0832,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804687679143166e-05,
"loss": 4.0765,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803849084392114e-05,
"loss": 4.0806,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803010489641062e-05,
"loss": 4.0834,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.80217189489001e-05,
"loss": 4.079,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801334938019331e-05,
"loss": 4.0768,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800497981148652e-05,
"loss": 4.0704,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996593863976e-05,
"loss": 4.0841,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988207916465486e-05,
"loss": 4.0681,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979821968954966e-05,
"loss": 4.0723,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971436021444446e-05,
"loss": 4.0669,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7963050073933926e-05,
"loss": 4.0789,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954664126423406e-05,
"loss": 4.0765,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946278178912886e-05,
"loss": 4.0682,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937908610206095e-05,
"loss": 4.0562,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929522662695575e-05,
"loss": 4.0648,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921136715185055e-05,
"loss": 4.0676,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912750767674535e-05,
"loss": 4.0761,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904381198967744e-05,
"loss": 4.0648,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895995251457224e-05,
"loss": 4.0586,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887609303946704e-05,
"loss": 4.0507,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879223356436184e-05,
"loss": 4.0658,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.78708537877294e-05,
"loss": 4.0351,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786248421902261e-05,
"loss": 4.0508,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785409827151209e-05,
"loss": 4.0549,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784571232400157e-05,
"loss": 4.0545,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783732637649105e-05,
"loss": 4.0432,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782894042898053e-05,
"loss": 4.0532,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782055448147001e-05,
"loss": 4.045,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781216853395948e-05,
"loss": 4.0632,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780378258644896e-05,
"loss": 4.0494,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779541301774218e-05,
"loss": 4.0479,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778702707023166e-05,
"loss": 4.0637,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777864112272114e-05,
"loss": 4.0664,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770271554014354e-05,
"loss": 4.0471,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761885606503834e-05,
"loss": 4.0423,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775349965899331e-05,
"loss": 4.0498,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774511371148279e-05,
"loss": 4.0402,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773672776397227e-05,
"loss": 4.0435,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728341816461747e-05,
"loss": 4.0502,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719955868951227e-05,
"loss": 4.0356,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711586300244436e-05,
"loss": 4.0565,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703200352733916e-05,
"loss": 4.0385,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694814405223396e-05,
"loss": 4.0396,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686428457712876e-05,
"loss": 4.0333,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767805888900609e-05,
"loss": 4.04,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766967294149557e-05,
"loss": 4.0312,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766128699398505e-05,
"loss": 4.047,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765290104647453e-05,
"loss": 4.0441,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764453147776774e-05,
"loss": 4.0349,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763614553025722e-05,
"loss": 4.0177,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.76277595827467e-05,
"loss": 4.0427,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761937363523618e-05,
"loss": 4.0325,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761100406652939e-05,
"loss": 4.039,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760261811901887e-05,
"loss": 4.0353,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759423217150835e-05,
"loss": 4.0345,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758584622399783e-05,
"loss": 4.0344,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577476655291045e-05,
"loss": 4.0362,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569090707780525e-05,
"loss": 4.0239,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560704760270005e-05,
"loss": 4.0217,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552318812759485e-05,
"loss": 4.0315,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543949244052694e-05,
"loss": 4.0128,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535563296542174e-05,
"loss": 4.0286,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527177349031654e-05,
"loss": 4.0349,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518791401521134e-05,
"loss": 4.022,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751042183281434e-05,
"loss": 4.0207,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750203588530382e-05,
"loss": 4.0243,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.023052215576172,
"eval_runtime": 302.5541,
"eval_samples_per_second": 1261.232,
"eval_steps_per_second": 39.414,
"step": 152640
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.0697475489568358e+17,
"trial_name": null,
"trial_params": null
}