abhinavp's picture
Training in progress, epoch 0, checkpoint
bce9e29 verified
{
"best_metric": 3.9479596614837646,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full/transformer/1/checkpoints/checkpoint-228957",
"epoch": 0.025000278439663435,
"eval_steps": 10,
"global_step": 228957,
"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": 11.0634,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8389,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1855,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9639,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8109,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.6897,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5891,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5257,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4716,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3921,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3531,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3124,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.269,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2094,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1808,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1489,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1096,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.076,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0555,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0279,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 4.9988,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9703,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9581,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9289,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.919,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8917,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8799,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8626,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.828,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.831,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8005,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7908,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7795,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7732,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7481,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.739,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7382,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7204,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7121,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6943,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6778,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.96562908036948e-05,
"loss": 4.6707,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964790485618428e-05,
"loss": 4.6477,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 4.6663,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6397,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.9622763392456454e-05,
"loss": 4.6409,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.9614377444945934e-05,
"loss": 4.63,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.9605991497435414e-05,
"loss": 4.6254,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 4.6178,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 4.5949,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958086641251131e-05,
"loss": 4.5868,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957248046500079e-05,
"loss": 4.5768,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956409451749027e-05,
"loss": 4.5836,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955570856997975e-05,
"loss": 4.5639,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 4.5733,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 4.5479,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.5422,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5388,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951379521123089e-05,
"loss": 4.5331,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950540926372037e-05,
"loss": 4.5303,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949702331620985e-05,
"loss": 4.5119,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 4.5097,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.9480267799992536e-05,
"loss": 4.5168,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.9471881852482016e-05,
"loss": 4.4974,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946349590497149e-05,
"loss": 4.492,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.4907,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.9446740388754185e-05,
"loss": 4.4901,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.9438354441243665e-05,
"loss": 4.4692,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.9429968493733145e-05,
"loss": 4.4815,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4701,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941321297751584e-05,
"loss": 4.4594,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940482703000532e-05,
"loss": 4.4649,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396441082494794e-05,
"loss": 4.4523,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938807151378801e-05,
"loss": 4.4667,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.937968556627749e-05,
"loss": 4.4639,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.937129961876696e-05,
"loss": 4.455,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4379,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4281,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934615815503914e-05,
"loss": 4.4183,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933777220752861e-05,
"loss": 4.4319,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.93293862600181e-05,
"loss": 4.4329,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932100031250758e-05,
"loss": 4.4279,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931261436499706e-05,
"loss": 4.4009,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930422841748654e-05,
"loss": 4.3998,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.4061,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928747290126923e-05,
"loss": 4.3943,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927908695375871e-05,
"loss": 4.399,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927070100624819e-05,
"loss": 4.3958,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.3963,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3862,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3824,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3703,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3851,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922041807879253e-05,
"loss": 4.3679,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921203213128201e-05,
"loss": 4.3549,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3598,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3723,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3661,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.3613,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3434,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.3586,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.91533468775121e-05,
"loss": 4.3326,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914497730880531e-05,
"loss": 4.35,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913659136129479e-05,
"loss": 4.3526,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912820541378427e-05,
"loss": 4.3381,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911981946627375e-05,
"loss": 4.3293,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3071,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3225,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.9094678002545926e-05,
"loss": 4.32,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.9086292055035406e-05,
"loss": 4.3181,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.9077906107524886e-05,
"loss": 4.3234,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.9069520160014366e-05,
"loss": 4.3047,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.9061150591307575e-05,
"loss": 4.3082,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052764643797055e-05,
"loss": 4.3144,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.9044378696286535e-05,
"loss": 4.3171,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.9035992748776015e-05,
"loss": 4.3033,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027606801265495e-05,
"loss": 4.302,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.2961,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010851285048184e-05,
"loss": 4.2971,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900246533753767e-05,
"loss": 4.3029,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899409576883088e-05,
"loss": 4.2871,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.898570982132036e-05,
"loss": 4.2837,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897732387380984e-05,
"loss": 4.2812,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.896893792629932e-05,
"loss": 4.2788,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.89605519787888e-05,
"loss": 4.2816,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895216603127827e-05,
"loss": 4.2814,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.894378008376775e-05,
"loss": 4.2859,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893539413625723e-05,
"loss": 4.2625,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892702456755045e-05,
"loss": 4.2753,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891863862003992e-05,
"loss": 4.277,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891025267252941e-05,
"loss": 4.2661,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890186672501889e-05,
"loss": 4.2817,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889348077750837e-05,
"loss": 4.2644,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888511120880158e-05,
"loss": 4.2757,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887672526129106e-05,
"loss": 4.2663,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886833931378054e-05,
"loss": 4.2452,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885995336627002e-05,
"loss": 4.2462,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.8851583797563226e-05,
"loss": 4.2491,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.8843197850052706e-05,
"loss": 4.2565,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.8834811902542186e-05,
"loss": 4.2572,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.8826425955031666e-05,
"loss": 4.2582,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.8818056386324875e-05,
"loss": 4.2472,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880967043881436e-05,
"loss": 4.2416,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880128449130384e-05,
"loss": 4.2359,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879289854379332e-05,
"loss": 4.2309,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878452897508653e-05,
"loss": 4.2393,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877614302757601e-05,
"loss": 4.2494,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876775708006549e-05,
"loss": 4.2434,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875937113255497e-05,
"loss": 4.2233,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875098518504445e-05,
"loss": 4.2263,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.191549301147461,
"eval_runtime": 619.6834,
"eval_samples_per_second": 615.784,
"eval_steps_per_second": 19.244,
"step": 76319
},
{
"epoch": 0.0,
"learning_rate": 4.874261561633766e-05,
"loss": 4.2271,
"step": 76800
},
{
"epoch": 0.0,
"learning_rate": 4.873422966882714e-05,
"loss": 4.2236,
"step": 77312
},
{
"epoch": 0.0,
"learning_rate": 4.872584372131662e-05,
"loss": 4.2196,
"step": 77824
},
{
"epoch": 0.0,
"learning_rate": 4.87174577738061e-05,
"loss": 4.2196,
"step": 78336
},
{
"epoch": 0.0,
"learning_rate": 4.870907182629558e-05,
"loss": 4.2101,
"step": 78848
},
{
"epoch": 0.0,
"learning_rate": 4.870068587878506e-05,
"loss": 4.1946,
"step": 79360
},
{
"epoch": 0.0,
"learning_rate": 4.869229993127454e-05,
"loss": 4.2003,
"step": 79872
},
{
"epoch": 0.0,
"learning_rate": 4.8683913983764027e-05,
"loss": 4.2123,
"step": 80384
},
{
"epoch": 0.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.2026,
"step": 80896
},
{
"epoch": 0.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.2049,
"step": 81408
},
{
"epoch": 0.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2058,
"step": 81920
},
{
"epoch": 0.0,
"learning_rate": 4.8650386572525676e-05,
"loss": 4.2061,
"step": 82432
},
{
"epoch": 0.0,
"learning_rate": 4.8642017003818885e-05,
"loss": 4.1969,
"step": 82944
},
{
"epoch": 0.0,
"learning_rate": 4.8633631056308365e-05,
"loss": 4.1974,
"step": 83456
},
{
"epoch": 0.0,
"learning_rate": 4.8625245108797845e-05,
"loss": 4.1931,
"step": 83968
},
{
"epoch": 0.0,
"learning_rate": 4.8616859161287324e-05,
"loss": 4.1777,
"step": 84480
},
{
"epoch": 0.0,
"learning_rate": 4.8608473213776804e-05,
"loss": 4.186,
"step": 84992
},
{
"epoch": 0.0,
"learning_rate": 4.860008726626628e-05,
"loss": 4.1901,
"step": 85504
},
{
"epoch": 0.0,
"learning_rate": 4.8591701318755764e-05,
"loss": 4.1885,
"step": 86016
},
{
"epoch": 0.0,
"learning_rate": 4.858333175004898e-05,
"loss": 4.1891,
"step": 86528
},
{
"epoch": 0.0,
"learning_rate": 4.857494580253846e-05,
"loss": 4.1768,
"step": 87040
},
{
"epoch": 0.0,
"learning_rate": 4.856655985502793e-05,
"loss": 4.1852,
"step": 87552
},
{
"epoch": 0.0,
"learning_rate": 4.855817390751741e-05,
"loss": 4.1732,
"step": 88064
},
{
"epoch": 0.0,
"learning_rate": 4.854980433881063e-05,
"loss": 4.1842,
"step": 88576
},
{
"epoch": 0.0,
"learning_rate": 4.854141839130011e-05,
"loss": 4.1749,
"step": 89088
},
{
"epoch": 0.0,
"learning_rate": 4.853303244378958e-05,
"loss": 4.1714,
"step": 89600
},
{
"epoch": 0.0,
"learning_rate": 4.852464649627906e-05,
"loss": 4.1768,
"step": 90112
},
{
"epoch": 0.0,
"learning_rate": 4.851627692757228e-05,
"loss": 4.1561,
"step": 90624
},
{
"epoch": 0.0,
"learning_rate": 4.850789098006175e-05,
"loss": 4.1743,
"step": 91136
},
{
"epoch": 0.01,
"learning_rate": 4.849950503255123e-05,
"loss": 4.1566,
"step": 91648
},
{
"epoch": 0.01,
"learning_rate": 4.849111908504072e-05,
"loss": 4.1625,
"step": 92160
},
{
"epoch": 0.01,
"learning_rate": 4.8482749516333934e-05,
"loss": 4.1607,
"step": 92672
},
{
"epoch": 0.01,
"learning_rate": 4.847436356882341e-05,
"loss": 4.1687,
"step": 93184
},
{
"epoch": 0.01,
"learning_rate": 4.846597762131289e-05,
"loss": 4.1562,
"step": 93696
},
{
"epoch": 0.01,
"learning_rate": 4.845759167380237e-05,
"loss": 4.1538,
"step": 94208
},
{
"epoch": 0.01,
"learning_rate": 4.844920572629185e-05,
"loss": 4.1638,
"step": 94720
},
{
"epoch": 0.01,
"learning_rate": 4.8440836157585056e-05,
"loss": 4.1531,
"step": 95232
},
{
"epoch": 0.01,
"learning_rate": 4.8432450210074536e-05,
"loss": 4.1605,
"step": 95744
},
{
"epoch": 0.01,
"learning_rate": 4.8424064262564016e-05,
"loss": 4.1453,
"step": 96256
},
{
"epoch": 0.01,
"learning_rate": 4.8415678315053496e-05,
"loss": 4.1368,
"step": 96768
},
{
"epoch": 0.01,
"learning_rate": 4.8407308746346705e-05,
"loss": 4.1395,
"step": 97280
},
{
"epoch": 0.01,
"learning_rate": 4.8398922798836185e-05,
"loss": 4.133,
"step": 97792
},
{
"epoch": 0.01,
"learning_rate": 4.839053685132567e-05,
"loss": 4.1497,
"step": 98304
},
{
"epoch": 0.01,
"learning_rate": 4.838215090381515e-05,
"loss": 4.137,
"step": 98816
},
{
"epoch": 0.01,
"learning_rate": 4.837378133510836e-05,
"loss": 4.1442,
"step": 99328
},
{
"epoch": 0.01,
"learning_rate": 4.836539538759784e-05,
"loss": 4.1377,
"step": 99840
},
{
"epoch": 0.01,
"learning_rate": 4.8357025818891057e-05,
"loss": 4.1415,
"step": 100352
},
{
"epoch": 0.01,
"learning_rate": 4.834863987138053e-05,
"loss": 4.1418,
"step": 100864
},
{
"epoch": 0.01,
"learning_rate": 4.834025392387001e-05,
"loss": 4.1192,
"step": 101376
},
{
"epoch": 0.01,
"learning_rate": 4.833186797635949e-05,
"loss": 4.1246,
"step": 101888
},
{
"epoch": 0.01,
"learning_rate": 4.83234984076527e-05,
"loss": 4.1197,
"step": 102400
},
{
"epoch": 0.01,
"learning_rate": 4.831511246014218e-05,
"loss": 4.1356,
"step": 102912
},
{
"epoch": 0.01,
"learning_rate": 4.830672651263166e-05,
"loss": 4.1125,
"step": 103424
},
{
"epoch": 0.01,
"learning_rate": 4.829834056512114e-05,
"loss": 4.1358,
"step": 103936
},
{
"epoch": 0.01,
"learning_rate": 4.8289954617610625e-05,
"loss": 4.1111,
"step": 104448
},
{
"epoch": 0.01,
"learning_rate": 4.8281568670100105e-05,
"loss": 4.1101,
"step": 104960
},
{
"epoch": 0.01,
"learning_rate": 4.8273182722589585e-05,
"loss": 4.1193,
"step": 105472
},
{
"epoch": 0.01,
"learning_rate": 4.8264796775079065e-05,
"loss": 4.1143,
"step": 105984
},
{
"epoch": 0.01,
"learning_rate": 4.8256427206372274e-05,
"loss": 4.1136,
"step": 106496
},
{
"epoch": 0.01,
"learning_rate": 4.8248041258861754e-05,
"loss": 4.1071,
"step": 107008
},
{
"epoch": 0.01,
"learning_rate": 4.8239655311351234e-05,
"loss": 4.1029,
"step": 107520
},
{
"epoch": 0.01,
"learning_rate": 4.8231269363840714e-05,
"loss": 4.1159,
"step": 108032
},
{
"epoch": 0.01,
"learning_rate": 4.822289979513392e-05,
"loss": 4.104,
"step": 108544
},
{
"epoch": 0.01,
"learning_rate": 4.82145138476234e-05,
"loss": 4.1047,
"step": 109056
},
{
"epoch": 0.01,
"learning_rate": 4.820612790011288e-05,
"loss": 4.1037,
"step": 109568
},
{
"epoch": 0.01,
"learning_rate": 4.819774195260236e-05,
"loss": 4.1075,
"step": 110080
},
{
"epoch": 0.01,
"learning_rate": 4.818937238389558e-05,
"loss": 4.0874,
"step": 110592
},
{
"epoch": 0.01,
"learning_rate": 4.818098643638506e-05,
"loss": 4.1088,
"step": 111104
},
{
"epoch": 0.01,
"learning_rate": 4.817260048887454e-05,
"loss": 4.0949,
"step": 111616
},
{
"epoch": 0.01,
"learning_rate": 4.816421454136402e-05,
"loss": 4.097,
"step": 112128
},
{
"epoch": 0.01,
"learning_rate": 4.815584497265723e-05,
"loss": 4.103,
"step": 112640
},
{
"epoch": 0.01,
"learning_rate": 4.814745902514671e-05,
"loss": 4.094,
"step": 113152
},
{
"epoch": 0.01,
"learning_rate": 4.813907307763619e-05,
"loss": 4.1096,
"step": 113664
},
{
"epoch": 0.01,
"learning_rate": 4.813068713012567e-05,
"loss": 4.1144,
"step": 114176
},
{
"epoch": 0.01,
"learning_rate": 4.812231756141888e-05,
"loss": 4.1067,
"step": 114688
},
{
"epoch": 0.01,
"learning_rate": 4.811393161390836e-05,
"loss": 4.092,
"step": 115200
},
{
"epoch": 0.01,
"learning_rate": 4.810554566639784e-05,
"loss": 4.0846,
"step": 115712
},
{
"epoch": 0.01,
"learning_rate": 4.8097176097691046e-05,
"loss": 4.0798,
"step": 116224
},
{
"epoch": 0.01,
"learning_rate": 4.808879015018053e-05,
"loss": 4.0936,
"step": 116736
},
{
"epoch": 0.01,
"learning_rate": 4.808040420267001e-05,
"loss": 4.1053,
"step": 117248
},
{
"epoch": 0.01,
"learning_rate": 4.807201825515949e-05,
"loss": 4.0948,
"step": 117760
},
{
"epoch": 0.01,
"learning_rate": 4.806363230764897e-05,
"loss": 4.0796,
"step": 118272
},
{
"epoch": 0.01,
"learning_rate": 4.805524636013845e-05,
"loss": 4.074,
"step": 118784
},
{
"epoch": 0.01,
"learning_rate": 4.804686041262793e-05,
"loss": 4.0859,
"step": 119296
},
{
"epoch": 0.01,
"learning_rate": 4.803849084392114e-05,
"loss": 4.0728,
"step": 119808
},
{
"epoch": 0.01,
"learning_rate": 4.803010489641062e-05,
"loss": 4.0812,
"step": 120320
},
{
"epoch": 0.01,
"learning_rate": 4.80217189489001e-05,
"loss": 4.0833,
"step": 120832
},
{
"epoch": 0.01,
"learning_rate": 4.801333300138958e-05,
"loss": 4.0882,
"step": 121344
},
{
"epoch": 0.01,
"learning_rate": 4.800494705387906e-05,
"loss": 4.0773,
"step": 121856
},
{
"epoch": 0.02,
"learning_rate": 4.7996561106368535e-05,
"loss": 4.0783,
"step": 122368
},
{
"epoch": 0.02,
"learning_rate": 4.7988175158858015e-05,
"loss": 4.0692,
"step": 122880
},
{
"epoch": 0.02,
"learning_rate": 4.797980559015123e-05,
"loss": 4.0806,
"step": 123392
},
{
"epoch": 0.02,
"learning_rate": 4.797141964264071e-05,
"loss": 4.0779,
"step": 123904
},
{
"epoch": 0.02,
"learning_rate": 4.796303369513019e-05,
"loss": 4.058,
"step": 124416
},
{
"epoch": 0.02,
"learning_rate": 4.795464774761967e-05,
"loss": 4.0683,
"step": 124928
},
{
"epoch": 0.02,
"learning_rate": 4.794626180010915e-05,
"loss": 4.0802,
"step": 125440
},
{
"epoch": 0.02,
"learning_rate": 4.793787585259863e-05,
"loss": 4.0854,
"step": 125952
},
{
"epoch": 0.02,
"learning_rate": 4.792948990508811e-05,
"loss": 4.07,
"step": 126464
},
{
"epoch": 0.02,
"learning_rate": 4.792110395757759e-05,
"loss": 4.0636,
"step": 126976
},
{
"epoch": 0.02,
"learning_rate": 4.79127343888708e-05,
"loss": 4.0766,
"step": 127488
},
{
"epoch": 0.02,
"learning_rate": 4.790434844136028e-05,
"loss": 4.0551,
"step": 128000
},
{
"epoch": 0.02,
"learning_rate": 4.789596249384976e-05,
"loss": 4.0702,
"step": 128512
},
{
"epoch": 0.02,
"learning_rate": 4.788757654633924e-05,
"loss": 4.0768,
"step": 129024
},
{
"epoch": 0.02,
"learning_rate": 4.787920697763245e-05,
"loss": 4.0672,
"step": 129536
},
{
"epoch": 0.02,
"learning_rate": 4.7870821030121935e-05,
"loss": 4.0648,
"step": 130048
},
{
"epoch": 0.02,
"learning_rate": 4.7862435082611415e-05,
"loss": 4.045,
"step": 130560
},
{
"epoch": 0.02,
"learning_rate": 4.7854049135100895e-05,
"loss": 4.0495,
"step": 131072
},
{
"epoch": 0.02,
"learning_rate": 4.7845679566394104e-05,
"loss": 4.0538,
"step": 131584
},
{
"epoch": 0.02,
"learning_rate": 4.7837293618883584e-05,
"loss": 4.055,
"step": 132096
},
{
"epoch": 0.02,
"learning_rate": 4.782892405017679e-05,
"loss": 4.0618,
"step": 132608
},
{
"epoch": 0.02,
"learning_rate": 4.782053810266627e-05,
"loss": 4.05,
"step": 133120
},
{
"epoch": 0.02,
"learning_rate": 4.781215215515575e-05,
"loss": 4.046,
"step": 133632
},
{
"epoch": 0.02,
"learning_rate": 4.780376620764523e-05,
"loss": 4.0582,
"step": 134144
},
{
"epoch": 0.02,
"learning_rate": 4.779538026013471e-05,
"loss": 4.0647,
"step": 134656
},
{
"epoch": 0.02,
"learning_rate": 4.778699431262419e-05,
"loss": 4.0511,
"step": 135168
},
{
"epoch": 0.02,
"learning_rate": 4.777860836511367e-05,
"loss": 4.0573,
"step": 135680
},
{
"epoch": 0.02,
"learning_rate": 4.777023879640689e-05,
"loss": 4.0472,
"step": 136192
},
{
"epoch": 0.02,
"learning_rate": 4.776185284889637e-05,
"loss": 4.0509,
"step": 136704
},
{
"epoch": 0.02,
"learning_rate": 4.775346690138585e-05,
"loss": 4.0575,
"step": 137216
},
{
"epoch": 0.02,
"learning_rate": 4.774509733267906e-05,
"loss": 4.0408,
"step": 137728
},
{
"epoch": 0.02,
"learning_rate": 4.773671138516854e-05,
"loss": 4.042,
"step": 138240
},
{
"epoch": 0.02,
"learning_rate": 4.772832543765802e-05,
"loss": 4.0411,
"step": 138752
},
{
"epoch": 0.02,
"learning_rate": 4.77199394901475e-05,
"loss": 4.0401,
"step": 139264
},
{
"epoch": 0.02,
"learning_rate": 4.771155354263698e-05,
"loss": 4.0433,
"step": 139776
},
{
"epoch": 0.02,
"learning_rate": 4.770316759512646e-05,
"loss": 4.0475,
"step": 140288
},
{
"epoch": 0.02,
"learning_rate": 4.769478164761594e-05,
"loss": 4.0522,
"step": 140800
},
{
"epoch": 0.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.0327,
"step": 141312
},
{
"epoch": 0.02,
"learning_rate": 4.7678042510202355e-05,
"loss": 4.0393,
"step": 141824
},
{
"epoch": 0.02,
"learning_rate": 4.766965656269184e-05,
"loss": 4.0527,
"step": 142336
},
{
"epoch": 0.02,
"learning_rate": 4.766127061518132e-05,
"loss": 4.0378,
"step": 142848
},
{
"epoch": 0.02,
"learning_rate": 4.76528846676708e-05,
"loss": 4.0508,
"step": 143360
},
{
"epoch": 0.02,
"learning_rate": 4.764449872016028e-05,
"loss": 4.0371,
"step": 143872
},
{
"epoch": 0.02,
"learning_rate": 4.763612915145349e-05,
"loss": 4.0521,
"step": 144384
},
{
"epoch": 0.02,
"learning_rate": 4.762774320394297e-05,
"loss": 4.0418,
"step": 144896
},
{
"epoch": 0.02,
"learning_rate": 4.761935725643245e-05,
"loss": 4.0255,
"step": 145408
},
{
"epoch": 0.02,
"learning_rate": 4.761097130892193e-05,
"loss": 4.026,
"step": 145920
},
{
"epoch": 0.02,
"learning_rate": 4.760258536141141e-05,
"loss": 4.0288,
"step": 146432
},
{
"epoch": 0.02,
"learning_rate": 4.759419941390089e-05,
"loss": 4.0412,
"step": 146944
},
{
"epoch": 0.02,
"learning_rate": 4.75858298451941e-05,
"loss": 4.0375,
"step": 147456
},
{
"epoch": 0.02,
"learning_rate": 4.757744389768358e-05,
"loss": 4.0413,
"step": 147968
},
{
"epoch": 0.02,
"learning_rate": 4.756905795017306e-05,
"loss": 4.0337,
"step": 148480
},
{
"epoch": 0.02,
"learning_rate": 4.756067200266254e-05,
"loss": 4.028,
"step": 148992
},
{
"epoch": 0.02,
"learning_rate": 4.755228605515202e-05,
"loss": 4.0258,
"step": 149504
},
{
"epoch": 0.02,
"learning_rate": 4.75439001076415e-05,
"loss": 4.0199,
"step": 150016
},
{
"epoch": 0.02,
"learning_rate": 4.753551416013098e-05,
"loss": 4.0291,
"step": 150528
},
{
"epoch": 0.02,
"learning_rate": 4.752712821262046e-05,
"loss": 4.0427,
"step": 151040
},
{
"epoch": 0.02,
"learning_rate": 4.751875864391367e-05,
"loss": 4.0292,
"step": 151552
},
{
"epoch": 0.02,
"learning_rate": 4.751037269640315e-05,
"loss": 4.0234,
"step": 152064
},
{
"epoch": 0.02,
"learning_rate": 4.750198674889263e-05,
"loss": 4.0206,
"step": 152576
},
{
"epoch": 0.03,
"eval_loss": 4.022192001342773,
"eval_runtime": 552.4226,
"eval_samples_per_second": 690.759,
"eval_steps_per_second": 21.587,
"step": 152638
},
{
"epoch": 0.0,
"learning_rate": 4.7493617180185845e-05,
"loss": 4.0278,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748523123267532e-05,
"loss": 4.0254,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.74768452851648e-05,
"loss": 4.0151,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746845933765428e-05,
"loss": 4.0183,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460073390143764e-05,
"loss": 4.0168,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451687442633244e-05,
"loss": 3.998,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443301495122724e-05,
"loss": 4.0059,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434915547612204e-05,
"loss": 4.0226,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426529600101684e-05,
"loss": 4.0044,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741816003139489e-05,
"loss": 4.0108,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740977408388437e-05,
"loss": 4.018,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740138813637385e-05,
"loss": 4.0152,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739300218886333e-05,
"loss": 4.0054,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738461624135281e-05,
"loss": 4.0104,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737624667264602e-05,
"loss": 4.0036,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.73678607251355e-05,
"loss": 3.9934,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735947477762498e-05,
"loss": 4.0003,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735108883011446e-05,
"loss": 4.005,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734270288260394e-05,
"loss": 4.0065,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733431693509343e-05,
"loss": 4.0082,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732593098758291e-05,
"loss": 3.9975,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731754504007238e-05,
"loss": 4.0078,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730919185016933e-05,
"loss": 3.9952,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730080590265881e-05,
"loss": 4.0054,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729241995514829e-05,
"loss": 3.9987,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728403400763777e-05,
"loss": 3.9974,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727564806012725e-05,
"loss": 4.0045,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726726211261673e-05,
"loss": 3.9832,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258892543909936e-05,
"loss": 4.0004,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250506596399416e-05,
"loss": 3.9868,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7242120648888896e-05,
"loss": 3.9908,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723373470137838e-05,
"loss": 3.9928,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225348753867856e-05,
"loss": 3.9964,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216962806357336e-05,
"loss": 3.9919,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208576858846816e-05,
"loss": 3.9846,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720020729014003e-05,
"loss": 3.9965,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191821342629505e-05,
"loss": 3.9881,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183435395118985e-05,
"loss": 3.9991,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175049447608465e-05,
"loss": 3.9835,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166663500097945e-05,
"loss": 3.9723,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158277552587424e-05,
"loss": 3.9753,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149907983880634e-05,
"loss": 3.9753,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714152203637012e-05,
"loss": 3.9939,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71331360888596e-05,
"loss": 3.9725,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712475014134908e-05,
"loss": 3.9874,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711638057264229e-05,
"loss": 3.9817,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710799462513177e-05,
"loss": 3.9793,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709960867762125e-05,
"loss": 3.9862,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709122273011073e-05,
"loss": 3.9636,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708283678260021e-05,
"loss": 3.9688,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707445083508969e-05,
"loss": 3.964,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.70660812663829e-05,
"loss": 3.9841,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705769531887238e-05,
"loss": 3.9628,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704930937136186e-05,
"loss": 3.9816,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704092342385134e-05,
"loss": 3.9613,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032553855144554e-05,
"loss": 3.9605,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024167907634034e-05,
"loss": 3.9654,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015781960123514e-05,
"loss": 3.9631,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007396012612994e-05,
"loss": 3.9687,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.69990264439062e-05,
"loss": 3.9636,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699064049639568e-05,
"loss": 3.9515,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698225454888516e-05,
"loss": 3.968,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697386860137464e-05,
"loss": 3.9578,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696548265386412e-05,
"loss": 3.9631,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69570967063536e-05,
"loss": 3.9569,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694871075884308e-05,
"loss": 3.9655,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694032481133256e-05,
"loss": 3.9433,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693195524262577e-05,
"loss": 3.9665,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692356929511526e-05,
"loss": 3.9502,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691518334760474e-05,
"loss": 3.9581,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690679740009422e-05,
"loss": 3.9589,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689842783138743e-05,
"loss": 3.9552,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689004188387691e-05,
"loss": 3.9687,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688165593636639e-05,
"loss": 3.9752,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873286367659596e-05,
"loss": 3.9698,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864900420149076e-05,
"loss": 3.9583,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856514472638556e-05,
"loss": 3.948,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848128525128036e-05,
"loss": 3.9396,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839758956421245e-05,
"loss": 3.9599,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831373008910725e-05,
"loss": 3.9666,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822987061400205e-05,
"loss": 3.9627,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681460111388969e-05,
"loss": 3.9438,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.68062315451829e-05,
"loss": 3.9415,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679784559767238e-05,
"loss": 3.9496,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678945965016186e-05,
"loss": 3.9371,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678107370265134e-05,
"loss": 3.9458,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772687755140814e-05,
"loss": 3.9544,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764301807630294e-05,
"loss": 3.9516,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755915860119774e-05,
"loss": 3.9472,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674754629141298e-05,
"loss": 3.9509,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673916034390246e-05,
"loss": 3.938,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673077439639194e-05,
"loss": 3.9527,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672238844888143e-05,
"loss": 3.9451,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671400250137091e-05,
"loss": 3.9347,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670563293266412e-05,
"loss": 3.9395,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.66972469851536e-05,
"loss": 3.9502,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668886103764308e-05,
"loss": 3.9572,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668047509013256e-05,
"loss": 3.9419,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667210552142577e-05,
"loss": 3.9412,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666371957391525e-05,
"loss": 3.9483,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665533362640473e-05,
"loss": 3.9304,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664694767889421e-05,
"loss": 3.9471,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663856173138369e-05,
"loss": 3.952,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66301921626769e-05,
"loss": 3.9406,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621806215166383e-05,
"loss": 3.9465,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613420267655863e-05,
"loss": 3.9239,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660503432014534e-05,
"loss": 3.9229,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659666475143855e-05,
"loss": 3.9323,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658827880392803e-05,
"loss": 3.9338,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657989285641751e-05,
"loss": 3.9424,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657150690890699e-05,
"loss": 3.9292,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656312096139647e-05,
"loss": 3.9248,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655475139268968e-05,
"loss": 3.9334,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654636544517916e-05,
"loss": 3.9438,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653797949766864e-05,
"loss": 3.936,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652959355015812e-05,
"loss": 3.9417,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.65212076026476e-05,
"loss": 3.9267,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651283803394082e-05,
"loss": 3.9295,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.65044520864303e-05,
"loss": 3.9427,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649606613891978e-05,
"loss": 3.9235,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648768019140926e-05,
"loss": 3.9264,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479310622702466e-05,
"loss": 3.9256,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470924675191946e-05,
"loss": 3.9232,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462538727681426e-05,
"loss": 3.9271,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454152780170906e-05,
"loss": 3.9285,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445766832660386e-05,
"loss": 3.9394,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437397263953595e-05,
"loss": 3.9188,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429011316443075e-05,
"loss": 3.9221,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420625368932555e-05,
"loss": 3.9423,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412239421422035e-05,
"loss": 3.9231,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640385347391152e-05,
"loss": 3.9371,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639548390520473e-05,
"loss": 3.9246,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638709795769421e-05,
"loss": 3.9394,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637871201018369e-05,
"loss": 3.9295,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637032606267317e-05,
"loss": 3.9158,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636195649396638e-05,
"loss": 3.9168,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635357054645586e-05,
"loss": 3.9169,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634518459894534e-05,
"loss": 3.9277,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633679865143482e-05,
"loss": 3.932,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632842908272803e-05,
"loss": 3.9291,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632004313521751e-05,
"loss": 3.925,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631165718770699e-05,
"loss": 3.918,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303271240196475e-05,
"loss": 3.9183,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294901671489684e-05,
"loss": 3.9094,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286515723979164e-05,
"loss": 3.9212,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6278129776468644e-05,
"loss": 3.9325,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626974382895812e-05,
"loss": 3.9197,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.62613578814476e-05,
"loss": 3.9161,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625297193393708e-05,
"loss": 3.9134,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9479596614837646,
"eval_runtime": 568.4433,
"eval_samples_per_second": 671.291,
"eval_steps_per_second": 20.978,
"step": 228957
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.5918121563486106e+17,
"trial_name": null,
"trial_params": null
}