abhinavp's picture
Training in progress, epoch 0, checkpoint
cfbf84e verified
{
"best_metric": 3.950981855392456,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full/transformer/4/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": 11.0625,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8438,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.19,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9707,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8179,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.6964,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5965,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5336,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4804,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4012,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3622,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3225,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2804,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2196,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1926,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1604,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1211,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0868,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0669,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.039,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0085,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9812,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9682,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9393,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.929,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.9023,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8901,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8712,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8371,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8388,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8094,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7989,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7874,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7796,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971497605746471e-05,
"loss": 4.7549,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970659010995419e-05,
"loss": 4.7462,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969820416244367e-05,
"loss": 4.7438,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7264,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7184,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967306269871584e-05,
"loss": 4.6998,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966467675120532e-05,
"loss": 4.6839,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.96562908036948e-05,
"loss": 4.6761,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964790485618428e-05,
"loss": 4.6541,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 4.6712,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6455,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6454,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6347,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.9605991497435414e-05,
"loss": 4.6319,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 4.622,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5979,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.5904,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957248046500079e-05,
"loss": 4.583,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956409451749027e-05,
"loss": 4.5902,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955570856997975e-05,
"loss": 4.5683,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 4.579,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 4.5542,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.5466,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5431,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5379,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5345,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949702331620985e-05,
"loss": 4.5171,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 4.5127,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5203,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.5014,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946349590497149e-05,
"loss": 4.4957,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.4955,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4943,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4729,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.9429968493733145e-05,
"loss": 4.4844,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4737,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4645,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4718,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396441082494794e-05,
"loss": 4.4555,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938807151378801e-05,
"loss": 4.4685,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.937968556627749e-05,
"loss": 4.469,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.937129961876696e-05,
"loss": 4.4589,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4418,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4312,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934615815503914e-05,
"loss": 4.4218,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933777220752861e-05,
"loss": 4.4346,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.93293862600181e-05,
"loss": 4.4345,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932100031250758e-05,
"loss": 4.4327,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931261436499706e-05,
"loss": 4.405,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930422841748654e-05,
"loss": 4.405,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.4099,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928747290126923e-05,
"loss": 4.3979,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927908695375871e-05,
"loss": 4.4033,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927070100624819e-05,
"loss": 4.3995,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.4,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.3893,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3855,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3747,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.3895,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922041807879253e-05,
"loss": 4.3722,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921203213128201e-05,
"loss": 4.3577,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3631,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3764,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3688,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917850472004366e-05,
"loss": 4.3671,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917011877253314e-05,
"loss": 4.3471,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916173282502262e-05,
"loss": 4.3629,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.91533468775121e-05,
"loss": 4.3361,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914496093000158e-05,
"loss": 4.3532,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913657498249106e-05,
"loss": 4.3554,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912820541378427e-05,
"loss": 4.3411,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911981946627375e-05,
"loss": 4.3353,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3109,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3252,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3236,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3224,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.9077906107524886e-05,
"loss": 4.3276,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.9069520160014366e-05,
"loss": 4.3088,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.9061134212503846e-05,
"loss": 4.3118,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3183,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3196,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3069,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027606801265495e-05,
"loss": 4.3064,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.3005,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.3018,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.305,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899407939002715e-05,
"loss": 4.2918,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985693442516624e-05,
"loss": 4.2879,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2838,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.2811,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2874,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2843,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2902,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2668,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.2798,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2814,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2691,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2865,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889348077750837e-05,
"loss": 4.268,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888509482999785e-05,
"loss": 4.2792,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.2694,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.2477,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885995336627002e-05,
"loss": 4.2505,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.2539,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.8843197850052706e-05,
"loss": 4.2607,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.8834811902542186e-05,
"loss": 4.2614,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.8826425955031666e-05,
"loss": 4.2615,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.8818040007521146e-05,
"loss": 4.2509,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809654060010626e-05,
"loss": 4.2453,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801268112500106e-05,
"loss": 4.2399,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2349,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2444,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877612664877228e-05,
"loss": 4.2537,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876775708006549e-05,
"loss": 4.2458,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875937113255497e-05,
"loss": 4.2263,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875098518504445e-05,
"loss": 4.2293,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.1957807540893555,
"eval_runtime": 622.6197,
"eval_samples_per_second": 612.88,
"eval_steps_per_second": 19.153,
"step": 76319
},
{
"epoch": 0.0,
"learning_rate": 4.874259923753393e-05,
"loss": 4.232,
"step": 76800
},
{
"epoch": 0.0,
"learning_rate": 4.873421329002341e-05,
"loss": 4.2268,
"step": 77312
},
{
"epoch": 0.0,
"learning_rate": 4.872582734251289e-05,
"loss": 4.2213,
"step": 77824
},
{
"epoch": 0.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.2219,
"step": 78336
},
{
"epoch": 0.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.2131,
"step": 78848
},
{
"epoch": 0.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.1968,
"step": 79360
},
{
"epoch": 0.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.2042,
"step": 79872
},
{
"epoch": 0.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.2168,
"step": 80384
},
{
"epoch": 0.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2047,
"step": 80896
},
{
"epoch": 0.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.2081,
"step": 81408
},
{
"epoch": 0.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2105,
"step": 81920
},
{
"epoch": 0.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2093,
"step": 82432
},
{
"epoch": 0.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.1997,
"step": 82944
},
{
"epoch": 0.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.2022,
"step": 83456
},
{
"epoch": 0.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.1959,
"step": 83968
},
{
"epoch": 0.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.1815,
"step": 84480
},
{
"epoch": 0.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.1899,
"step": 84992
},
{
"epoch": 0.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.194,
"step": 85504
},
{
"epoch": 0.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.1926,
"step": 86016
},
{
"epoch": 0.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.1942,
"step": 86528
},
{
"epoch": 0.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.1794,
"step": 87040
},
{
"epoch": 0.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.191,
"step": 87552
},
{
"epoch": 0.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.1757,
"step": 88064
},
{
"epoch": 0.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.1871,
"step": 88576
},
{
"epoch": 0.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.1779,
"step": 89088
},
{
"epoch": 0.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.1756,
"step": 89600
},
{
"epoch": 0.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.1801,
"step": 90112
},
{
"epoch": 0.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.1611,
"step": 90624
},
{
"epoch": 0.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.1765,
"step": 91136
},
{
"epoch": 0.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.1609,
"step": 91648
},
{
"epoch": 0.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.1653,
"step": 92160
},
{
"epoch": 0.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.1668,
"step": 92672
},
{
"epoch": 0.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1709,
"step": 93184
},
{
"epoch": 0.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.1598,
"step": 93696
},
{
"epoch": 0.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.1543,
"step": 94208
},
{
"epoch": 0.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.1683,
"step": 94720
},
{
"epoch": 0.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.1573,
"step": 95232
},
{
"epoch": 0.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.1646,
"step": 95744
},
{
"epoch": 0.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.149,
"step": 96256
},
{
"epoch": 0.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.1394,
"step": 96768
},
{
"epoch": 0.01,
"learning_rate": 4.840725960993552e-05,
"loss": 4.1427,
"step": 97280
},
{
"epoch": 0.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.1387,
"step": 97792
},
{
"epoch": 0.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.1534,
"step": 98304
},
{
"epoch": 0.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.1413,
"step": 98816
},
{
"epoch": 0.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.1469,
"step": 99328
},
{
"epoch": 0.01,
"learning_rate": 4.8365346251186646e-05,
"loss": 4.1412,
"step": 99840
},
{
"epoch": 0.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1466,
"step": 100352
},
{
"epoch": 0.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.1437,
"step": 100864
},
{
"epoch": 0.01,
"learning_rate": 4.834020478745882e-05,
"loss": 4.1199,
"step": 101376
},
{
"epoch": 0.01,
"learning_rate": 4.8331818839948295e-05,
"loss": 4.1272,
"step": 101888
},
{
"epoch": 0.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.1237,
"step": 102400
},
{
"epoch": 0.01,
"learning_rate": 4.831506332373099e-05,
"loss": 4.1395,
"step": 102912
},
{
"epoch": 0.01,
"learning_rate": 4.830667737622047e-05,
"loss": 4.1172,
"step": 103424
},
{
"epoch": 0.01,
"learning_rate": 4.8298291428709944e-05,
"loss": 4.1395,
"step": 103936
},
{
"epoch": 0.01,
"learning_rate": 4.828992186000316e-05,
"loss": 4.1154,
"step": 104448
},
{
"epoch": 0.01,
"learning_rate": 4.828153591249264e-05,
"loss": 4.1135,
"step": 104960
},
{
"epoch": 0.01,
"learning_rate": 4.827314996498212e-05,
"loss": 4.1231,
"step": 105472
},
{
"epoch": 0.01,
"learning_rate": 4.82647640174716e-05,
"loss": 4.1178,
"step": 105984
},
{
"epoch": 0.01,
"learning_rate": 4.825637806996108e-05,
"loss": 4.1172,
"step": 106496
},
{
"epoch": 0.01,
"learning_rate": 4.8248008501254296e-05,
"loss": 4.1104,
"step": 107008
},
{
"epoch": 0.01,
"learning_rate": 4.823962255374377e-05,
"loss": 4.1057,
"step": 107520
},
{
"epoch": 0.01,
"learning_rate": 4.823123660623325e-05,
"loss": 4.1201,
"step": 108032
},
{
"epoch": 0.01,
"learning_rate": 4.822285065872273e-05,
"loss": 4.1074,
"step": 108544
},
{
"epoch": 0.01,
"learning_rate": 4.8214481090015945e-05,
"loss": 4.1061,
"step": 109056
},
{
"epoch": 0.01,
"learning_rate": 4.820609514250542e-05,
"loss": 4.105,
"step": 109568
},
{
"epoch": 0.01,
"learning_rate": 4.81977091949949e-05,
"loss": 4.1106,
"step": 110080
},
{
"epoch": 0.01,
"learning_rate": 4.818932324748438e-05,
"loss": 4.0907,
"step": 110592
},
{
"epoch": 0.01,
"learning_rate": 4.8180953678777594e-05,
"loss": 4.1112,
"step": 111104
},
{
"epoch": 0.01,
"learning_rate": 4.8172567731267074e-05,
"loss": 4.0985,
"step": 111616
},
{
"epoch": 0.01,
"learning_rate": 4.8164181783756554e-05,
"loss": 4.0997,
"step": 112128
},
{
"epoch": 0.01,
"learning_rate": 4.8155795836246034e-05,
"loss": 4.1061,
"step": 112640
},
{
"epoch": 0.01,
"learning_rate": 4.814742626753924e-05,
"loss": 4.0959,
"step": 113152
},
{
"epoch": 0.01,
"learning_rate": 4.813904032002872e-05,
"loss": 4.1145,
"step": 113664
},
{
"epoch": 0.01,
"learning_rate": 4.81306543725182e-05,
"loss": 4.1171,
"step": 114176
},
{
"epoch": 0.01,
"learning_rate": 4.812226842500768e-05,
"loss": 4.1107,
"step": 114688
},
{
"epoch": 0.01,
"learning_rate": 4.811389885630089e-05,
"loss": 4.0947,
"step": 115200
},
{
"epoch": 0.01,
"learning_rate": 4.810551290879037e-05,
"loss": 4.0886,
"step": 115712
},
{
"epoch": 0.01,
"learning_rate": 4.809714334008359e-05,
"loss": 4.0839,
"step": 116224
},
{
"epoch": 0.01,
"learning_rate": 4.808875739257306e-05,
"loss": 4.0951,
"step": 116736
},
{
"epoch": 0.01,
"learning_rate": 4.808037144506255e-05,
"loss": 4.109,
"step": 117248
},
{
"epoch": 0.01,
"learning_rate": 4.807198549755203e-05,
"loss": 4.0976,
"step": 117760
},
{
"epoch": 0.01,
"learning_rate": 4.806359955004151e-05,
"loss": 4.0828,
"step": 118272
},
{
"epoch": 0.01,
"learning_rate": 4.805521360253099e-05,
"loss": 4.0772,
"step": 118784
},
{
"epoch": 0.01,
"learning_rate": 4.804682765502047e-05,
"loss": 4.0903,
"step": 119296
},
{
"epoch": 0.01,
"learning_rate": 4.803844170750995e-05,
"loss": 4.0786,
"step": 119808
},
{
"epoch": 0.01,
"learning_rate": 4.8030072138803156e-05,
"loss": 4.0844,
"step": 120320
},
{
"epoch": 0.01,
"learning_rate": 4.8021686191292636e-05,
"loss": 4.0859,
"step": 120832
},
{
"epoch": 0.01,
"learning_rate": 4.8013300243782116e-05,
"loss": 4.0904,
"step": 121344
},
{
"epoch": 0.01,
"learning_rate": 4.8004914296271596e-05,
"loss": 4.081,
"step": 121856
},
{
"epoch": 0.02,
"learning_rate": 4.7996561106368535e-05,
"loss": 4.0798,
"step": 122368
},
{
"epoch": 0.02,
"learning_rate": 4.7988175158858015e-05,
"loss": 4.0729,
"step": 122880
},
{
"epoch": 0.02,
"learning_rate": 4.7979789211347494e-05,
"loss": 4.0835,
"step": 123392
},
{
"epoch": 0.02,
"learning_rate": 4.797140326383698e-05,
"loss": 4.0806,
"step": 123904
},
{
"epoch": 0.02,
"learning_rate": 4.796301731632646e-05,
"loss": 4.0614,
"step": 124416
},
{
"epoch": 0.02,
"learning_rate": 4.795463136881594e-05,
"loss": 4.0723,
"step": 124928
},
{
"epoch": 0.02,
"learning_rate": 4.794624542130542e-05,
"loss": 4.0813,
"step": 125440
},
{
"epoch": 0.02,
"learning_rate": 4.79378594737949e-05,
"loss": 4.0875,
"step": 125952
},
{
"epoch": 0.02,
"learning_rate": 4.792948990508811e-05,
"loss": 4.076,
"step": 126464
},
{
"epoch": 0.02,
"learning_rate": 4.792110395757759e-05,
"loss": 4.0674,
"step": 126976
},
{
"epoch": 0.02,
"learning_rate": 4.791271801006707e-05,
"loss": 4.0799,
"step": 127488
},
{
"epoch": 0.02,
"learning_rate": 4.790433206255655e-05,
"loss": 4.0567,
"step": 128000
},
{
"epoch": 0.02,
"learning_rate": 4.789596249384976e-05,
"loss": 4.0724,
"step": 128512
},
{
"epoch": 0.02,
"learning_rate": 4.788757654633924e-05,
"loss": 4.0801,
"step": 129024
},
{
"epoch": 0.02,
"learning_rate": 4.787920697763245e-05,
"loss": 4.0702,
"step": 129536
},
{
"epoch": 0.02,
"learning_rate": 4.7870821030121935e-05,
"loss": 4.0703,
"step": 130048
},
{
"epoch": 0.02,
"learning_rate": 4.7862435082611415e-05,
"loss": 4.0482,
"step": 130560
},
{
"epoch": 0.02,
"learning_rate": 4.7854049135100895e-05,
"loss": 4.0531,
"step": 131072
},
{
"epoch": 0.02,
"learning_rate": 4.7845663187590375e-05,
"loss": 4.0572,
"step": 131584
},
{
"epoch": 0.02,
"learning_rate": 4.7837277240079855e-05,
"loss": 4.0579,
"step": 132096
},
{
"epoch": 0.02,
"learning_rate": 4.7828891292569335e-05,
"loss": 4.0657,
"step": 132608
},
{
"epoch": 0.02,
"learning_rate": 4.7820505345058815e-05,
"loss": 4.0537,
"step": 133120
},
{
"epoch": 0.02,
"learning_rate": 4.7812135776352024e-05,
"loss": 4.0492,
"step": 133632
},
{
"epoch": 0.02,
"learning_rate": 4.7803749828841504e-05,
"loss": 4.0607,
"step": 134144
},
{
"epoch": 0.02,
"learning_rate": 4.7795363881330984e-05,
"loss": 4.0674,
"step": 134656
},
{
"epoch": 0.02,
"learning_rate": 4.7786977933820464e-05,
"loss": 4.0529,
"step": 135168
},
{
"epoch": 0.02,
"learning_rate": 4.777860836511367e-05,
"loss": 4.0605,
"step": 135680
},
{
"epoch": 0.02,
"learning_rate": 4.777022241760315e-05,
"loss": 4.0505,
"step": 136192
},
{
"epoch": 0.02,
"learning_rate": 4.776183647009263e-05,
"loss": 4.0533,
"step": 136704
},
{
"epoch": 0.02,
"learning_rate": 4.775345052258212e-05,
"loss": 4.0583,
"step": 137216
},
{
"epoch": 0.02,
"learning_rate": 4.774509733267906e-05,
"loss": 4.046,
"step": 137728
},
{
"epoch": 0.02,
"learning_rate": 4.773671138516854e-05,
"loss": 4.0456,
"step": 138240
},
{
"epoch": 0.02,
"learning_rate": 4.772832543765802e-05,
"loss": 4.0442,
"step": 138752
},
{
"epoch": 0.02,
"learning_rate": 4.77199394901475e-05,
"loss": 4.0423,
"step": 139264
},
{
"epoch": 0.02,
"learning_rate": 4.771155354263698e-05,
"loss": 4.0476,
"step": 139776
},
{
"epoch": 0.02,
"learning_rate": 4.770316759512646e-05,
"loss": 4.05,
"step": 140288
},
{
"epoch": 0.02,
"learning_rate": 4.769478164761594e-05,
"loss": 4.0542,
"step": 140800
},
{
"epoch": 0.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.0354,
"step": 141312
},
{
"epoch": 0.02,
"learning_rate": 4.7678026131398626e-05,
"loss": 4.0421,
"step": 141824
},
{
"epoch": 0.02,
"learning_rate": 4.7669640183888106e-05,
"loss": 4.0555,
"step": 142336
},
{
"epoch": 0.02,
"learning_rate": 4.7661254236377586e-05,
"loss": 4.0397,
"step": 142848
},
{
"epoch": 0.02,
"learning_rate": 4.765286828886707e-05,
"loss": 4.0539,
"step": 143360
},
{
"epoch": 0.02,
"learning_rate": 4.764449872016028e-05,
"loss": 4.0402,
"step": 143872
},
{
"epoch": 0.02,
"learning_rate": 4.763611277264976e-05,
"loss": 4.0558,
"step": 144384
},
{
"epoch": 0.02,
"learning_rate": 4.762772682513924e-05,
"loss": 4.0446,
"step": 144896
},
{
"epoch": 0.02,
"learning_rate": 4.761934087762872e-05,
"loss": 4.0286,
"step": 145408
},
{
"epoch": 0.02,
"learning_rate": 4.761097130892193e-05,
"loss": 4.0282,
"step": 145920
},
{
"epoch": 0.02,
"learning_rate": 4.760258536141141e-05,
"loss": 4.032,
"step": 146432
},
{
"epoch": 0.02,
"learning_rate": 4.759419941390089e-05,
"loss": 4.0449,
"step": 146944
},
{
"epoch": 0.02,
"learning_rate": 4.758581346639037e-05,
"loss": 4.0412,
"step": 147456
},
{
"epoch": 0.02,
"learning_rate": 4.757744389768358e-05,
"loss": 4.0451,
"step": 147968
},
{
"epoch": 0.02,
"learning_rate": 4.7569074328976796e-05,
"loss": 4.0366,
"step": 148480
},
{
"epoch": 0.02,
"learning_rate": 4.7560688381466276e-05,
"loss": 4.0289,
"step": 148992
},
{
"epoch": 0.02,
"learning_rate": 4.7552302433955756e-05,
"loss": 4.0287,
"step": 149504
},
{
"epoch": 0.02,
"learning_rate": 4.7543916486445236e-05,
"loss": 4.0237,
"step": 150016
},
{
"epoch": 0.02,
"learning_rate": 4.7535530538934716e-05,
"loss": 4.0329,
"step": 150528
},
{
"epoch": 0.02,
"learning_rate": 4.7527144591424196e-05,
"loss": 4.0465,
"step": 151040
},
{
"epoch": 0.02,
"learning_rate": 4.751875864391367e-05,
"loss": 4.0318,
"step": 151552
},
{
"epoch": 0.02,
"learning_rate": 4.751037269640315e-05,
"loss": 4.0258,
"step": 152064
},
{
"epoch": 0.02,
"learning_rate": 4.7502003127696365e-05,
"loss": 4.0241,
"step": 152576
},
{
"epoch": 0.03,
"eval_loss": 4.025460720062256,
"eval_runtime": 588.8804,
"eval_samples_per_second": 647.994,
"eval_steps_per_second": 20.25,
"step": 152638
},
{
"epoch": 0.0,
"learning_rate": 4.7493633558989574e-05,
"loss": 4.0321,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485247611479054e-05,
"loss": 4.0269,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476861663968534e-05,
"loss": 4.0179,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468475716458014e-05,
"loss": 4.0223,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460089768947494e-05,
"loss": 4.0194,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451703821436974e-05,
"loss": 3.9993,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443317873926453e-05,
"loss": 4.0086,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434931926415933e-05,
"loss": 4.0242,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426545978905413e-05,
"loss": 4.0067,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741817641019862e-05,
"loss": 4.0143,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.74097904626881e-05,
"loss": 4.0201,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740140451517758e-05,
"loss": 4.0178,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739303494647079e-05,
"loss": 4.0068,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738464899896027e-05,
"loss": 4.0138,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737626305144975e-05,
"loss": 4.0061,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736787710393923e-05,
"loss": 3.9991,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735949115642871e-05,
"loss": 4.0034,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.73511052089182e-05,
"loss": 4.0082,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734271926140768e-05,
"loss": 4.0109,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733433331389716e-05,
"loss": 4.0134,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732594736638664e-05,
"loss": 3.9979,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731756141887612e-05,
"loss": 4.0119,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73091754713656e-05,
"loss": 3.9996,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730080590265881e-05,
"loss": 4.0055,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729241995514829e-05,
"loss": 4.0014,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728403400763777e-05,
"loss": 3.9995,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727564806012725e-05,
"loss": 4.0071,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726726211261673e-05,
"loss": 3.9887,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725887616510621e-05,
"loss": 4.0015,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725049021759568e-05,
"loss": 3.9891,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724210427008517e-05,
"loss": 3.9933,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723373470137838e-05,
"loss": 3.996,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722536513267159e-05,
"loss": 3.9996,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721697918516107e-05,
"loss": 3.9942,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720859323765055e-05,
"loss": 3.9859,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720020729014003e-05,
"loss": 4.0009,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191821342629505e-05,
"loss": 3.9919,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183435395118985e-05,
"loss": 4.0014,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175049447608465e-05,
"loss": 3.9866,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166663500097945e-05,
"loss": 3.9749,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158293931391154e-05,
"loss": 3.9776,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714992436268437e-05,
"loss": 3.9817,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714153841517385e-05,
"loss": 3.9964,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713315246766333e-05,
"loss": 3.9758,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712476652015281e-05,
"loss": 3.9894,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711638057264229e-05,
"loss": 3.9841,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7108011003935505e-05,
"loss": 3.9848,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709962505642498e-05,
"loss": 3.9902,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709123910891446e-05,
"loss": 3.9649,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708285316140394e-05,
"loss": 3.9707,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074483592697154e-05,
"loss": 3.966,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706609764518663e-05,
"loss": 3.9875,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705771169767611e-05,
"loss": 3.9669,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704932575016559e-05,
"loss": 3.9867,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.70409561814588e-05,
"loss": 3.9631,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703257023394828e-05,
"loss": 3.9636,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702418428643776e-05,
"loss": 3.9698,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701579833892724e-05,
"loss": 3.964,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700742877022045e-05,
"loss": 3.9708,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699904282270993e-05,
"loss": 3.9663,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699065687519941e-05,
"loss": 3.9542,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698227092768889e-05,
"loss": 3.971,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697388498017837e-05,
"loss": 3.9607,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696549903266785e-05,
"loss": 3.9651,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695711308515733e-05,
"loss": 3.9583,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694872713764681e-05,
"loss": 3.9677,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694035756894003e-05,
"loss": 3.9448,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693198800023324e-05,
"loss": 3.9681,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692360205272272e-05,
"loss": 3.9535,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.69152161052122e-05,
"loss": 3.962,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906830157701677e-05,
"loss": 3.9618,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898444210191157e-05,
"loss": 3.9554,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890074641484366e-05,
"loss": 3.9716,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881688693973846e-05,
"loss": 3.9778,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873302746463326e-05,
"loss": 3.9727,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864916798952806e-05,
"loss": 3.9615,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856547230246015e-05,
"loss": 3.9505,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848161282735495e-05,
"loss": 3.9429,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683977533522498e-05,
"loss": 3.9613,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683138938771446e-05,
"loss": 3.9694,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682301981900767e-05,
"loss": 3.9632,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681463387149715e-05,
"loss": 3.9478,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680624792398663e-05,
"loss": 3.9426,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679786197647611e-05,
"loss": 3.9527,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678947602896559e-05,
"loss": 3.9415,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.67811064602588e-05,
"loss": 3.9484,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677272051274828e-05,
"loss": 3.9545,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676433456523776e-05,
"loss": 3.9556,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675594861772724e-05,
"loss": 3.951,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674757904902045e-05,
"loss": 3.9533,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739193101509935e-05,
"loss": 3.9419,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730807153999415e-05,
"loss": 3.9539,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722421206488895e-05,
"loss": 3.9478,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6714035258978375e-05,
"loss": 3.9376,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705665690271584e-05,
"loss": 3.9417,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697279742761064e-05,
"loss": 3.952,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688893795250544e-05,
"loss": 3.9605,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680507847740024e-05,
"loss": 3.9463,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6672121900229504e-05,
"loss": 3.9441,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666375233152271e-05,
"loss": 3.9504,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665536638401219e-05,
"loss": 3.9319,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664698043650167e-05,
"loss": 3.9498,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663859448899115e-05,
"loss": 3.9527,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663022492028437e-05,
"loss": 3.9429,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662183897277385e-05,
"loss": 3.9509,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661345302526333e-05,
"loss": 3.9271,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660506707775281e-05,
"loss": 3.9255,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659669750904602e-05,
"loss": 3.9342,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.65883115615355e-05,
"loss": 3.9357,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657992561402498e-05,
"loss": 3.9467,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657153966651446e-05,
"loss": 3.9312,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6563170097807667e-05,
"loss": 3.9274,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554784150297146e-05,
"loss": 3.9351,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546398202786626e-05,
"loss": 3.947,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6538012255276106e-05,
"loss": 3.9371,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.6529626307765586e-05,
"loss": 3.9456,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.65212567390588e-05,
"loss": 3.9301,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651287079154828e-05,
"loss": 3.9306,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650448484403776e-05,
"loss": 3.9443,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6496098896527235e-05,
"loss": 3.9284,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648772932782045e-05,
"loss": 3.928,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647934338030993e-05,
"loss": 3.928,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470957432799404e-05,
"loss": 3.9244,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462571485288884e-05,
"loss": 3.9327,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.64542019165821e-05,
"loss": 3.9315,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644581596907158e-05,
"loss": 3.9404,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643743002156106e-05,
"loss": 3.9211,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642904407405054e-05,
"loss": 3.9244,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642065812654002e-05,
"loss": 3.9456,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412288557833236e-05,
"loss": 3.9236,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640390261032271e-05,
"loss": 3.9404,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639551666281219e-05,
"loss": 3.928,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638713071530167e-05,
"loss": 3.9409,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637876114659488e-05,
"loss": 3.9318,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637037519908436e-05,
"loss": 3.9184,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636198925157384e-05,
"loss": 3.9172,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635360330406332e-05,
"loss": 3.9191,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634523373535653e-05,
"loss": 3.9308,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336847787846014e-05,
"loss": 3.9364,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328461840335494e-05,
"loss": 3.932,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320075892824974e-05,
"loss": 3.9266,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631170632411818e-05,
"loss": 3.9182,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630332037660766e-05,
"loss": 3.9199,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629493442909714e-05,
"loss": 3.9134,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628654848158662e-05,
"loss": 3.9251,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.62781625340761e-05,
"loss": 3.933,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626979296536931e-05,
"loss": 3.9224,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626140701785879e-05,
"loss": 3.9198,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625302107034827e-05,
"loss": 3.9167,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.950981855392456,
"eval_runtime": 570.4475,
"eval_samples_per_second": 668.933,
"eval_steps_per_second": 20.905,
"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
}