abhinavp's picture
Training in progress, epoch 0, checkpoint
a2705e3 verified
raw
history blame
No virus
56.1 kB
{
"best_metric": 3.9549131393432617,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/transformer/1/checkpoints/checkpoint-228960",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 228960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 11.0349,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8119,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.188,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9793,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8074,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.6987,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5939,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5293,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4394,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3947,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3436,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3029,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2501,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2025,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1605,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1281,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.0983,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0846,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0412,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.021,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0107,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9653,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9416,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9255,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9185,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8828,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8641,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8569,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8349,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8096,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7946,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740117521192533e-05,
"loss": 4.7898,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731731573682013e-05,
"loss": 4.7776,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7744,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7505,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7358,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.74,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7022,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.6978,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6838,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6831,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6613,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6745,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6423,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6471,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6362,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6279,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6255,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6015,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 4.5886,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.6025,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.5884,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5707,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 4.5589,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 4.5672,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 4.5503,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.5625,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5352,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5332,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5366,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5176,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5018,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5068,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4904,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4913,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5002,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.4929,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4799,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4668,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4594,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4726,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.467,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396441082494794e-05,
"loss": 4.4599,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388055134984274e-05,
"loss": 4.4575,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4619,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4541,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4283,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4385,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4344,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.42,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4327,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4224,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.429,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.418,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.392,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928747290126923e-05,
"loss": 4.4016,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927908695375871e-05,
"loss": 4.4018,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927070100624819e-05,
"loss": 4.4014,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.394,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.3858,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3892,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3773,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.9228804026303046e-05,
"loss": 4.3709,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922041807879253e-05,
"loss": 4.3721,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921203213128201e-05,
"loss": 4.368,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.379,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3552,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3514,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.3505,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3605,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916173282502262e-05,
"loss": 4.3566,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.91533468775121e-05,
"loss": 4.3432,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914496093000158e-05,
"loss": 4.3415,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913657498249106e-05,
"loss": 4.3243,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3379,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3236,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3204,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3271,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3251,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3197,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3161,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3088,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3154,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3027,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.303,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3086,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.3059,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019237232558704e-05,
"loss": 4.3034,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010851285048184e-05,
"loss": 4.2953,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900246533753767e-05,
"loss": 4.2997,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899407939002715e-05,
"loss": 4.2948,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985693442516624e-05,
"loss": 4.2816,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2985,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.2837,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2912,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2744,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2699,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2664,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.27,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2611,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2774,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2738,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2583,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888509482999785e-05,
"loss": 4.2609,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.2657,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.2613,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.2666,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.2625,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2489,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2541,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.25,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2412,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2518,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.2394,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2287,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2524,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.2314,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2292,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2312,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875096880624072e-05,
"loss": 4.2241,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.197596073150635,
"eval_runtime": 303.2397,
"eval_samples_per_second": 1258.381,
"eval_steps_per_second": 39.325,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.2094,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.2203,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2365,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2139,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2286,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2034,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2152,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.1994,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.2105,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.206,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2093,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.207,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642000625015155e-05,
"loss": 4.1923,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.1855,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.1848,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.1894,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.1964,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.1837,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.1906,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.206,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.1814,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.1752,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.1791,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.1889,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.1685,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.1742,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.1736,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.1675,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.1541,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.161,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.1567,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.1667,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.1729,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.1561,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.1534,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.1656,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.1412,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.1478,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.1387,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.145,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840725960993552e-05,
"loss": 4.1377,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398873662425e-05,
"loss": 4.1552,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.1406,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.1414,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.1376,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365346251186646e-05,
"loss": 4.1422,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1352,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.1264,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834020478745882e-05,
"loss": 4.1185,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331818839948295e-05,
"loss": 4.1403,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323432892437775e-05,
"loss": 4.1304,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315046944927255e-05,
"loss": 4.1191,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830667737622047e-05,
"loss": 4.1173,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298291428709944e-05,
"loss": 4.1257,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289905481199424e-05,
"loss": 4.1144,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281519533688904e-05,
"loss": 4.1291,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827314996498212e-05,
"loss": 4.1141,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.82647640174716e-05,
"loss": 4.1153,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825637806996108e-05,
"loss": 4.1266,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824799212245056e-05,
"loss": 4.1049,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823962255374377e-05,
"loss": 4.102,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823123660623325e-05,
"loss": 4.1116,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822285065872273e-05,
"loss": 4.0943,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821446471121221e-05,
"loss": 4.1002,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820609514250542e-05,
"loss": 4.1124,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.81977091949949e-05,
"loss": 4.1143,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818932324748438e-05,
"loss": 4.1028,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818093729997386e-05,
"loss": 4.0966,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172567731267074e-05,
"loss": 4.0864,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164181783756554e-05,
"loss": 4.1062,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155795836246034e-05,
"loss": 4.104,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147409888735514e-05,
"loss": 4.1037,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813904032002872e-05,
"loss": 4.1042,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.81306543725182e-05,
"loss": 4.1066,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812226842500768e-05,
"loss": 4.1062,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811388247749716e-05,
"loss": 4.0819,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810551290879037e-05,
"loss": 4.0976,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809712696127985e-05,
"loss": 4.0966,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808874101376933e-05,
"loss": 4.0811,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808035506625881e-05,
"loss": 4.1023,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807198549755203e-05,
"loss": 4.0945,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806359955004151e-05,
"loss": 4.1003,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805521360253099e-05,
"loss": 4.0971,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804682765502047e-05,
"loss": 4.0739,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.8038458086313677e-05,
"loss": 4.0847,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8030072138803156e-05,
"loss": 4.0838,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.8021686191292636e-05,
"loss": 4.0881,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013300243782116e-05,
"loss": 4.0832,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004914296271596e-05,
"loss": 4.0752,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996544727564805e-05,
"loss": 4.0851,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988158780054285e-05,
"loss": 4.0794,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979789211347494e-05,
"loss": 4.0653,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797140326383698e-05,
"loss": 4.0728,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796301731632646e-05,
"loss": 4.0785,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795463136881594e-05,
"loss": 4.0875,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794624542130542e-05,
"loss": 4.0694,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.79378594737949e-05,
"loss": 4.0568,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792947352628438e-05,
"loss": 4.0675,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792108757877386e-05,
"loss": 4.0752,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.79127343888708e-05,
"loss": 4.0757,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790434844136028e-05,
"loss": 4.0686,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789596249384976e-05,
"loss": 4.0625,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788757654633924e-05,
"loss": 4.0524,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787919059882872e-05,
"loss": 4.0657,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.78708046513182e-05,
"loss": 4.0519,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786241870380768e-05,
"loss": 4.0563,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854049135100895e-05,
"loss": 4.0615,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845663187590375e-05,
"loss": 4.0592,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837277240079855e-05,
"loss": 4.055,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828891292569335e-05,
"loss": 4.0609,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820505345058815e-05,
"loss": 4.0503,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812119397548295e-05,
"loss": 4.0559,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803733450037775e-05,
"loss": 4.0504,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779534750252725e-05,
"loss": 4.0482,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786977933820464e-05,
"loss": 4.0606,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778591986309944e-05,
"loss": 4.0592,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777022241760315e-05,
"loss": 4.0548,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776183647009263e-05,
"loss": 4.0476,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775345052258212e-05,
"loss": 4.0524,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450645750716e-05,
"loss": 4.0508,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773667862756108e-05,
"loss": 4.0398,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772829268005055e-05,
"loss": 4.0598,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771990673254003e-05,
"loss": 4.0436,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771152078502951e-05,
"loss": 4.0526,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770315121632272e-05,
"loss": 4.0374,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.76947652688122e-05,
"loss": 4.0377,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768637932130168e-05,
"loss": 4.0333,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767799337379116e-05,
"loss": 4.035,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766962380508437e-05,
"loss": 4.0335,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766123785757386e-05,
"loss": 4.0478,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765285191006334e-05,
"loss": 4.0488,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764446596255282e-05,
"loss": 4.0361,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.7636096393846026e-05,
"loss": 4.0292,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.7627710446335506e-05,
"loss": 4.0414,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.7619324498824986e-05,
"loss": 4.0397,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610938551314466e-05,
"loss": 4.0463,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602568982607675e-05,
"loss": 4.04,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594183035097155e-05,
"loss": 4.0343,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.7585797087586635e-05,
"loss": 4.029,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577411140076115e-05,
"loss": 4.0395,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569041571369324e-05,
"loss": 4.0283,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756065562385881e-05,
"loss": 4.0324,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755226967634829e-05,
"loss": 4.0301,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754388372883777e-05,
"loss": 4.0212,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753551416013098e-05,
"loss": 4.0435,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752712821262046e-05,
"loss": 4.0235,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751874226510994e-05,
"loss": 4.0202,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751035631759942e-05,
"loss": 4.0227,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750198674889263e-05,
"loss": 4.0185,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.028837203979492,
"eval_runtime": 303.893,
"eval_samples_per_second": 1255.675,
"eval_steps_per_second": 39.241,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749360080138211e-05,
"loss": 4.0037,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748521485387159e-05,
"loss": 4.0188,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747682890636107e-05,
"loss": 4.0332,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746844295885055e-05,
"loss": 4.0175,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.746005701134003e-05,
"loss": 4.0303,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745167106382951e-05,
"loss": 4.0088,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744328511631899e-05,
"loss": 4.0208,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434899168808475e-05,
"loss": 4.0015,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426529600101684e-05,
"loss": 4.0181,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418143652591164e-05,
"loss": 4.0142,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409757705080644e-05,
"loss": 4.0141,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401371757570124e-05,
"loss": 4.0229,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739300218886333e-05,
"loss": 4.0026,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738461624135281e-05,
"loss": 3.9977,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737623029384229e-05,
"loss": 3.9976,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736784434633177e-05,
"loss": 4.0064,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735945839882125e-05,
"loss": 4.0094,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735107245131073e-05,
"loss": 4.0025,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734268650380021e-05,
"loss": 4.0066,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733430055628969e-05,
"loss": 4.0246,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732591460877917e-05,
"loss": 3.9993,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731752866126865e-05,
"loss": 3.9954,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730914271375813e-05,
"loss": 4.0023,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730077314505134e-05,
"loss": 4.0084,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729238719754082e-05,
"loss": 3.9934,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728401762883403e-05,
"loss": 3.9974,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727563168132351e-05,
"loss": 3.9979,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726724573381299e-05,
"loss": 3.9935,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725885978630247e-05,
"loss": 3.9826,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725049021759568e-05,
"loss": 3.9901,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724210427008517e-05,
"loss": 3.989,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233718322574647e-05,
"loss": 3.9929,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225332375064127e-05,
"loss": 4.0066,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216946427553606e-05,
"loss": 3.9853,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208560480043086e-05,
"loss": 3.9856,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200174532532566e-05,
"loss": 3.9973,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191788585022046e-05,
"loss": 3.9807,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183419016315255e-05,
"loss": 3.9787,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175033068804735e-05,
"loss": 3.9743,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166647121294215e-05,
"loss": 3.9843,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158261173783695e-05,
"loss": 3.9732,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149891605076904e-05,
"loss": 3.9965,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141505657566384e-05,
"loss": 3.9753,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133119710055864e-05,
"loss": 3.9859,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712475014134908e-05,
"loss": 3.9805,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711636419383856e-05,
"loss": 3.9802,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710797824632804e-05,
"loss": 3.9787,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709959229881752e-05,
"loss": 3.9669,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709122273011073e-05,
"loss": 3.9646,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708283678260021e-05,
"loss": 3.9848,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707445083508969e-05,
"loss": 3.9775,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706606488757917e-05,
"loss": 3.9651,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705769531887238e-05,
"loss": 3.9684,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704932575016559e-05,
"loss": 3.9764,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040939802655074e-05,
"loss": 3.9563,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032553855144554e-05,
"loss": 3.9761,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024167907634034e-05,
"loss": 3.9664,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015781960123514e-05,
"loss": 3.9647,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007396012612994e-05,
"loss": 3.9826,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6999010065102474e-05,
"loss": 3.9578,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990624117591954e-05,
"loss": 3.9547,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698225454888516e-05,
"loss": 3.9657,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697386860137464e-05,
"loss": 3.9502,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696548265386412e-05,
"loss": 3.955,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69570967063536e-05,
"loss": 3.9678,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694872713764681e-05,
"loss": 3.9698,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694034119013629e-05,
"loss": 3.9539,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693195524262577e-05,
"loss": 3.9561,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692358567391899e-05,
"loss": 3.9435,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691519972640847e-05,
"loss": 3.9648,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690681377889795e-05,
"loss": 3.96,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689842783138743e-05,
"loss": 3.9665,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689004188387691e-05,
"loss": 3.9611,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688165593636639e-05,
"loss": 3.9647,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873286367659596e-05,
"loss": 3.9722,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864900420149076e-05,
"loss": 3.9437,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856514472638556e-05,
"loss": 3.9585,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848128525128036e-05,
"loss": 3.9628,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683974257761751e-05,
"loss": 3.9447,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831356630106996e-05,
"loss": 3.965,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822970682596476e-05,
"loss": 3.9592,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814584735085956e-05,
"loss": 3.9648,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.68062315451829e-05,
"loss": 3.9625,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679784559767238e-05,
"loss": 3.9401,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678945965016186e-05,
"loss": 3.9525,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678107370265134e-05,
"loss": 3.9503,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772687755140814e-05,
"loss": 3.9584,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764301807630294e-05,
"loss": 3.9487,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9471,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674754629141298e-05,
"loss": 3.9532,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673916034390246e-05,
"loss": 3.95,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673077439639194e-05,
"loss": 3.936,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672238844888143e-05,
"loss": 3.9429,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671400250137091e-05,
"loss": 3.9526,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670563293266412e-05,
"loss": 3.9567,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.66972469851536e-05,
"loss": 3.9462,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668886103764308e-05,
"loss": 3.9278,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668047509013256e-05,
"loss": 3.9411,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667210552142577e-05,
"loss": 3.948,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666371957391525e-05,
"loss": 3.9476,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665533362640473e-05,
"loss": 3.9441,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664694767889421e-05,
"loss": 3.9383,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663856173138369e-05,
"loss": 3.9274,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663017578387317e-05,
"loss": 3.9463,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662178983636265e-05,
"loss": 3.9233,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661340388885213e-05,
"loss": 3.9363,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660503432014534e-05,
"loss": 3.9313,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659664837263482e-05,
"loss": 3.9434,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.65882624251243e-05,
"loss": 3.928,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657987647761378e-05,
"loss": 3.9404,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657149053010326e-05,
"loss": 3.9312,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656310458259274e-05,
"loss": 3.9305,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655473501388595e-05,
"loss": 3.9359,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654634906637543e-05,
"loss": 3.9262,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653796311886491e-05,
"loss": 3.941,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652957717135439e-05,
"loss": 3.9399,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.65212076026476e-05,
"loss": 3.9373,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651282165513708e-05,
"loss": 3.9297,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650443570762657e-05,
"loss": 3.9329,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649604976011605e-05,
"loss": 3.9367,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648768019140926e-05,
"loss": 3.9187,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647929424389874e-05,
"loss": 3.9408,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647090829638822e-05,
"loss": 3.9298,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.64625223488777e-05,
"loss": 3.9347,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645413640136718e-05,
"loss": 3.9242,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644575045385665e-05,
"loss": 3.9268,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643736450634613e-05,
"loss": 3.9145,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428994937639346e-05,
"loss": 3.9213,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642060899012882e-05,
"loss": 3.9201,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412223042618306e-05,
"loss": 3.9341,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403837095107786e-05,
"loss": 3.9352,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395467526401e-05,
"loss": 3.9255,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387081578890475e-05,
"loss": 3.9173,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378695631379955e-05,
"loss": 3.9272,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370309683869435e-05,
"loss": 3.9288,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636194011516265e-05,
"loss": 3.9334,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353554167652124e-05,
"loss": 3.9279,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345168220141604e-05,
"loss": 3.9191,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336782272631084e-05,
"loss": 3.9253,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328396325120564e-05,
"loss": 3.9297,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320010377610043e-05,
"loss": 3.9167,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311624430099523e-05,
"loss": 3.9222,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630325486139274e-05,
"loss": 3.9206,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629486891388222e-05,
"loss": 3.9121,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.62864829663717e-05,
"loss": 3.9349,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627809701886118e-05,
"loss": 3.9176,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626971107135066e-05,
"loss": 3.912,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626134150264387e-05,
"loss": 3.9133,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625295555513335e-05,
"loss": 3.9098,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9549131393432617,
"eval_runtime": 303.0366,
"eval_samples_per_second": 1259.224,
"eval_steps_per_second": 39.352,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.5869192680625357e+17,
"trial_name": null,
"trial_params": null
}