abhinavp's picture
Training in progress, epoch 0, checkpoint
de9f059 verified
raw
history blame contribute delete
No virus
93.1 kB
{
"best_metric": 3.884277105331421,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-only/transformer/1/checkpoints/checkpoint-381600",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 381600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.9232,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8136,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1808,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.976,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8215,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.713,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.61,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5443,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4534,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4147,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3633,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3228,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2592,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2219,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1884,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1394,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1226,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.089,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0496,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0283,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0114,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.981,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9633,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9298,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9221,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.9022,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8784,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.857,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8314,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.824,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8069,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.8009,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7843,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7694,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7615,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7503,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.739,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.7088,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 4.707,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 4.6818,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 4.6879,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6677,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6699,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.649,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6457,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6376,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6291,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6187,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5937,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.6004,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.601,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.5946,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5739,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5624,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 4.5642,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 4.55,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.5649,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5261,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5434,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5326,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5126,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5224,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5079,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4979,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4943,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5034,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4827,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4789,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.471,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4655,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4722,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940482703000532e-05,
"loss": 4.477,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396441082494794e-05,
"loss": 4.4526,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388055134984274e-05,
"loss": 4.4636,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4666,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4495,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4365,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4387,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4364,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4224,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4195,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4287,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4282,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.4123,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.3904,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.4031,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.4074,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.3974,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.3991,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.3821,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3804,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3754,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.3731,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3787,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3669,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3841,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3662,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3504,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.352,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3593,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.351,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.3494,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3473,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913657498249106e-05,
"loss": 4.337,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3398,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3189,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3246,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3298,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3238,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3181,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3261,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3007,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3122,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3079,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3116,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3183,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.3073,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019237232558704e-05,
"loss": 4.2984,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010851285048184e-05,
"loss": 4.2929,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900246533753767e-05,
"loss": 4.3001,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899407939002715e-05,
"loss": 4.2944,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985693442516624e-05,
"loss": 4.2926,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2851,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.2819,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2825,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2709,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2795,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2758,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.2697,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2613,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2795,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2796,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2674,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2552,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.2636,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.2639,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.2627,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2588,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2586,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2527,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2502,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2447,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2488,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.2398,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2344,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2476,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.2317,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2424,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2295,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875096880624072e-05,
"loss": 4.224,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.19596529006958,
"eval_runtime": 307.6211,
"eval_samples_per_second": 1240.458,
"eval_steps_per_second": 38.765,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.2161,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.2145,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2271,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2185,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2223,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.2098,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.2089,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.1976,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2139,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.2054,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2174,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.199,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642000625015155e-05,
"loss": 4.1959,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.1895,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.1857,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.1848,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.1926,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.181,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.1791,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.1997,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.1842,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.1846,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.1733,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.186,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.1715,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853301606498585e-05,
"loss": 4.1731,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.1706,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.1629,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850787460125802e-05,
"loss": 4.159,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.84994886537475e-05,
"loss": 4.158,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.1673,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.1656,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847434719001968e-05,
"loss": 4.1599,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846596124250916e-05,
"loss": 4.1656,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845757529499864e-05,
"loss": 4.1609,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.1605,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844081977878133e-05,
"loss": 4.1478,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843243383127081e-05,
"loss": 4.1481,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842404788376029e-05,
"loss": 4.1373,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.15,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.1347,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398906420032456e-05,
"loss": 4.1489,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.8390520472521936e-05,
"loss": 4.1351,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382134525011416e-05,
"loss": 4.1394,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83737485775009e-05,
"loss": 4.1396,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836537900879411e-05,
"loss": 4.1371,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835699306128359e-05,
"loss": 4.1348,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834860711377307e-05,
"loss": 4.1203,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834022116626255e-05,
"loss": 4.1246,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833185159755576e-05,
"loss": 4.1364,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832346565004524e-05,
"loss": 4.1332,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831507970253472e-05,
"loss": 4.1238,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.83066937550242e-05,
"loss": 4.1138,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829832418631741e-05,
"loss": 4.1229,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828993823880689e-05,
"loss": 4.11,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828155229129637e-05,
"loss": 4.1329,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273166343785856e-05,
"loss": 4.1041,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264796775079065e-05,
"loss": 4.1261,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256410827568545e-05,
"loss": 4.1179,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248024880058025e-05,
"loss": 4.1028,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239638932547505e-05,
"loss": 4.1151,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231269363840714e-05,
"loss": 4.1112,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222883416330194e-05,
"loss": 4.0991,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214497468819674e-05,
"loss": 4.1038,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206111521309154e-05,
"loss": 4.1144,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819774195260236e-05,
"loss": 4.1019,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818935600509184e-05,
"loss": 4.1004,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818097005758132e-05,
"loss": 4.0964,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817258411007081e-05,
"loss": 4.0942,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816421454136402e-05,
"loss": 4.1035,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.81558285938535e-05,
"loss": 4.1158,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814744264634298e-05,
"loss": 4.0961,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813905669883246e-05,
"loss": 4.1094,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813068713012567e-05,
"loss": 4.1096,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812230118261515e-05,
"loss": 4.0974,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811391523510463e-05,
"loss": 4.089,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810552928759411e-05,
"loss": 4.0998,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809715971888732e-05,
"loss": 4.0974,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887737713768e-05,
"loss": 4.088,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808038782386628e-05,
"loss": 4.0883,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807200187635576e-05,
"loss": 4.0946,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806363230764897e-05,
"loss": 4.1017,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805524636013845e-05,
"loss": 4.0884,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804686041262793e-05,
"loss": 4.0768,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803847446511741e-05,
"loss": 4.082,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803010489641062e-05,
"loss": 4.0887,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.80217189489001e-05,
"loss": 4.0863,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801333300138958e-05,
"loss": 4.0892,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800496343268279e-05,
"loss": 4.0766,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799657748517227e-05,
"loss": 4.0722,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798819153766175e-05,
"loss": 4.0715,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797980559015123e-05,
"loss": 4.0741,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797141964264071e-05,
"loss": 4.0767,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796303369513019e-05,
"loss": 4.0739,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795464774761967e-05,
"loss": 4.094,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794626180010915e-05,
"loss": 4.0777,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793789223140236e-05,
"loss": 4.061,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792950628389184e-05,
"loss": 4.0699,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792112033638132e-05,
"loss": 4.0729,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.79127343888708e-05,
"loss": 4.0726,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790436482016401e-05,
"loss": 4.0715,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789597887265349e-05,
"loss": 4.068,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788759292514297e-05,
"loss": 4.0614,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787920697763245e-05,
"loss": 4.0714,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870837408925664e-05,
"loss": 4.0442,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862451461415144e-05,
"loss": 4.0587,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785408189270836e-05,
"loss": 4.0595,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784569594519783e-05,
"loss": 4.0604,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783730999768731e-05,
"loss": 4.051,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782892405017679e-05,
"loss": 4.0618,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782053810266627e-05,
"loss": 4.0482,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781215215515575e-05,
"loss": 4.052,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780376620764523e-05,
"loss": 4.0537,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779539663893844e-05,
"loss": 4.054,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778701069142792e-05,
"loss": 4.0698,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.77786247439174e-05,
"loss": 4.0596,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777025517521062e-05,
"loss": 4.0532,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.77618692277001e-05,
"loss": 4.048,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775348328018958e-05,
"loss": 4.0512,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774509733267906e-05,
"loss": 4.0502,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773671138516854e-05,
"loss": 4.0467,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772832543765802e-05,
"loss": 4.046,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.77199394901475e-05,
"loss": 4.0423,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771155354263698e-05,
"loss": 4.0469,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703183973930186e-05,
"loss": 4.035,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694798026419666e-05,
"loss": 4.0426,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686412078909146e-05,
"loss": 4.0393,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.7678042510202355e-05,
"loss": 4.0414,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766965656269184e-05,
"loss": 4.0281,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766127061518132e-05,
"loss": 4.0519,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.76528846676708e-05,
"loss": 4.0558,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764451509896401e-05,
"loss": 4.0378,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763612915145349e-05,
"loss": 4.0316,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762774320394297e-05,
"loss": 4.0392,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761935725643245e-05,
"loss": 4.0414,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761098768772566e-05,
"loss": 4.042,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760260174021514e-05,
"loss": 4.038,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759421579270462e-05,
"loss": 4.0379,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758584622399783e-05,
"loss": 4.0331,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757746027648731e-05,
"loss": 4.0389,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569074328976796e-05,
"loss": 4.0273,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560688381466276e-05,
"loss": 4.0357,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552302433955756e-05,
"loss": 4.0321,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543932865248965e-05,
"loss": 4.0209,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535546917738445e-05,
"loss": 4.0379,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527160970227925e-05,
"loss": 4.0249,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518775022717405e-05,
"loss": 4.0343,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510389075206885e-05,
"loss": 4.0203,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7502003127696365e-05,
"loss": 4.021,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.025944232940674,
"eval_runtime": 312.8015,
"eval_samples_per_second": 1219.914,
"eval_steps_per_second": 38.123,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493617180185845e-05,
"loss": 4.0152,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748523123267532e-05,
"loss": 4.0082,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.74768452851648e-05,
"loss": 4.0288,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746845933765428e-05,
"loss": 4.0195,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460073390143764e-05,
"loss": 4.0285,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451687442633244e-05,
"loss": 4.0096,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443301495122724e-05,
"loss": 4.0167,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434915547612204e-05,
"loss": 4.0008,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426529600101684e-05,
"loss": 4.0183,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418143652591164e-05,
"loss": 4.0191,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409757705080644e-05,
"loss": 4.0196,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740138813637385e-05,
"loss": 4.0122,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739301856766706e-05,
"loss": 4.004,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738463262015654e-05,
"loss": 4.0029,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737624667264602e-05,
"loss": 3.9995,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.73678607251355e-05,
"loss": 4.0008,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735947477762498e-05,
"loss": 4.0031,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735108883011446e-05,
"loss": 3.9981,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734270288260394e-05,
"loss": 3.9991,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733433331389716e-05,
"loss": 4.0189,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732594736638664e-05,
"loss": 4.0015,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731756141887612e-05,
"loss": 4.0076,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730919185016933e-05,
"loss": 3.9948,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730080590265881e-05,
"loss": 4.0107,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729241995514829e-05,
"loss": 3.9874,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728403400763777e-05,
"loss": 3.9989,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727564806012725e-05,
"loss": 3.9967,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726726211261673e-05,
"loss": 3.9934,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258892543909936e-05,
"loss": 3.9809,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250506596399416e-05,
"loss": 3.9872,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7242120648888896e-05,
"loss": 3.9963,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723373470137838e-05,
"loss": 3.9972,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225348753867856e-05,
"loss": 3.9931,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216962806357336e-05,
"loss": 3.9947,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208576858846816e-05,
"loss": 3.9912,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200190911336296e-05,
"loss": 3.9972,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191821342629505e-05,
"loss": 3.9815,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183435395118985e-05,
"loss": 3.9819,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175049447608465e-05,
"loss": 3.9722,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716667987890168e-05,
"loss": 3.9896,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158293931391154e-05,
"loss": 3.9758,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149907983880634e-05,
"loss": 3.9858,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714152203637012e-05,
"loss": 3.9783,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71331360888596e-05,
"loss": 3.9749,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712476652015281e-05,
"loss": 3.9874,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711638057264229e-05,
"loss": 3.9756,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710799462513177e-05,
"loss": 3.9774,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709960867762125e-05,
"loss": 3.9596,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709122273011073e-05,
"loss": 3.9712,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708283678260021e-05,
"loss": 3.9803,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707445083508969e-05,
"loss": 3.9751,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.70660812663829e-05,
"loss": 3.9738,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705769531887238e-05,
"loss": 3.9593,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704930937136186e-05,
"loss": 3.9722,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704092342385134e-05,
"loss": 3.9577,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703253747634082e-05,
"loss": 3.9814,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024151528830305e-05,
"loss": 3.955,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015781960123514e-05,
"loss": 3.9744,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007396012612994e-05,
"loss": 3.972,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6999010065102474e-05,
"loss": 3.953,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990624117591954e-05,
"loss": 3.963,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982238170081434e-05,
"loss": 3.9669,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973852222570914e-05,
"loss": 3.953,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696548265386412e-05,
"loss": 3.9589,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69570967063536e-05,
"loss": 3.9676,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694871075884308e-05,
"loss": 3.964,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694032481133256e-05,
"loss": 3.9518,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693193886382204e-05,
"loss": 3.9563,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692355291631152e-05,
"loss": 3.9486,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915166968801e-05,
"loss": 3.9609,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690678102129048e-05,
"loss": 3.9739,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689842783138743e-05,
"loss": 3.9575,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689004188387691e-05,
"loss": 3.9697,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688165593636639e-05,
"loss": 3.968,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687326998885587e-05,
"loss": 3.9614,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686488404134534e-05,
"loss": 3.9488,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856514472638556e-05,
"loss": 3.9646,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848128525128036e-05,
"loss": 3.9557,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683974257761751e-05,
"loss": 3.9564,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831356630106996e-05,
"loss": 3.9518,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822970682596476e-05,
"loss": 3.9574,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681460111388969e-05,
"loss": 3.9695,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806215166379165e-05,
"loss": 3.9526,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797829218868645e-05,
"loss": 3.9405,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789443271358125e-05,
"loss": 3.9459,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.6781057323847605e-05,
"loss": 3.9561,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772671376337085e-05,
"loss": 3.9559,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764285428826565e-05,
"loss": 3.9581,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755915860119774e-05,
"loss": 3.9426,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747529912609254e-05,
"loss": 3.9461,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739143965098734e-05,
"loss": 3.9371,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730758017588214e-05,
"loss": 3.943,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672238844888143e-05,
"loss": 3.9485,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671400250137091e-05,
"loss": 3.9487,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670561655386039e-05,
"loss": 3.9659,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669723060634987e-05,
"loss": 3.9461,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668884465883935e-05,
"loss": 3.9381,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668045871132883e-05,
"loss": 3.9426,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667207276381831e-05,
"loss": 3.9435,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666370319511152e-05,
"loss": 3.9499,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655317247601e-05,
"loss": 3.9459,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664693130009048e-05,
"loss": 3.9419,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663854535257996e-05,
"loss": 3.9377,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663015940506944e-05,
"loss": 3.9463,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662177345755892e-05,
"loss": 3.9211,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661340388885213e-05,
"loss": 3.9387,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6605017941341614e-05,
"loss": 3.9345,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596631993831094e-05,
"loss": 3.9378,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588246046320574e-05,
"loss": 3.9303,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657987647761378e-05,
"loss": 3.9396,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657149053010326e-05,
"loss": 3.925,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656310458259274e-05,
"loss": 3.931,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655471863508222e-05,
"loss": 3.9383,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.65463326875717e-05,
"loss": 3.9313,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653796311886491e-05,
"loss": 3.9512,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652957717135439e-05,
"loss": 3.9432,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652119122384387e-05,
"loss": 3.9377,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651280527633335e-05,
"loss": 3.9264,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650443570762657e-05,
"loss": 3.9306,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649604976011605e-05,
"loss": 3.9343,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648766381260553e-05,
"loss": 3.931,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479277865095e-05,
"loss": 3.9295,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647090829638822e-05,
"loss": 3.9216,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.64625223488777e-05,
"loss": 3.9317,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645413640136718e-05,
"loss": 3.9188,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644575045385665e-05,
"loss": 3.9276,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643736450634613e-05,
"loss": 3.9241,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428994937639346e-05,
"loss": 3.9254,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642060899012882e-05,
"loss": 3.9145,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412223042618306e-05,
"loss": 3.9399,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403837095107786e-05,
"loss": 3.9408,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395467526401e-05,
"loss": 3.9287,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387081578890475e-05,
"loss": 3.9144,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378695631379955e-05,
"loss": 3.9268,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370309683869435e-05,
"loss": 3.9281,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6361923736358915e-05,
"loss": 3.9319,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353554167652124e-05,
"loss": 3.9251,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345168220141604e-05,
"loss": 3.9242,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336782272631084e-05,
"loss": 3.9244,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328396325120564e-05,
"loss": 3.9314,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320010377610043e-05,
"loss": 3.9206,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631164080890326e-05,
"loss": 3.9259,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630325486139274e-05,
"loss": 3.9222,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629486891388222e-05,
"loss": 3.914,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.62864829663717e-05,
"loss": 3.9269,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627811339766491e-05,
"loss": 3.9242,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626972745015439e-05,
"loss": 3.9223,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626134150264387e-05,
"loss": 3.9137,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625295555513335e-05,
"loss": 3.9128,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.951106309890747,
"eval_runtime": 307.338,
"eval_samples_per_second": 1241.6,
"eval_steps_per_second": 38.801,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624456960762283e-05,
"loss": 3.9148,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623620003891604e-05,
"loss": 3.9056,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622781409140552e-05,
"loss": 3.9222,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219428143895e-05,
"loss": 3.9141,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621104219638448e-05,
"loss": 3.9257,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620267262767769e-05,
"loss": 3.9068,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619428668016717e-05,
"loss": 3.9103,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618590073265665e-05,
"loss": 3.8988,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617751478514613e-05,
"loss": 3.9153,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616912883763561e-05,
"loss": 3.9135,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616075926892882e-05,
"loss": 3.9169,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.61523733214183e-05,
"loss": 3.9094,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614398737390778e-05,
"loss": 3.9027,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613560142639726e-05,
"loss": 3.9024,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612721547888674e-05,
"loss": 3.8978,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611884591017995e-05,
"loss": 3.9008,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611045996266943e-05,
"loss": 3.9021,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610207401515891e-05,
"loss": 3.8975,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609368806764839e-05,
"loss": 3.8975,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608530212013788e-05,
"loss": 3.9214,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076932551431087e-05,
"loss": 3.9018,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068546603920566e-05,
"loss": 3.9045,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6060160656410046e-05,
"loss": 3.8985,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051774708899526e-05,
"loss": 3.9081,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.6043405140192735e-05,
"loss": 3.8913,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.6035019192682215e-05,
"loss": 3.906,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.6026633245171695e-05,
"loss": 3.897,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018247297661175e-05,
"loss": 3.8936,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009877728954384e-05,
"loss": 3.8808,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001491781443864e-05,
"loss": 3.8913,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.5993105833933344e-05,
"loss": 3.8972,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598471988642283e-05,
"loss": 3.9008,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597635031771604e-05,
"loss": 3.9015,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596796437020552e-05,
"loss": 3.8986,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.5959578422695e-05,
"loss": 3.8896,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595119247518448e-05,
"loss": 3.9044,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594282290647769e-05,
"loss": 3.8846,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593443695896717e-05,
"loss": 3.8915,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592605101145665e-05,
"loss": 3.8767,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591766506394613e-05,
"loss": 3.8927,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590929549523934e-05,
"loss": 3.8842,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590090954772882e-05,
"loss": 3.8934,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.58925236002183e-05,
"loss": 3.8895,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5884137652707785e-05,
"loss": 3.8803,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587575170519726e-05,
"loss": 3.8951,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867382136490474e-05,
"loss": 3.8847,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858996188979954e-05,
"loss": 3.8823,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585061024146943e-05,
"loss": 3.8693,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584222429395891e-05,
"loss": 3.8783,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583383834644839e-05,
"loss": 3.8902,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.58254687777416e-05,
"loss": 3.8851,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.5817082830231076e-05,
"loss": 3.8829,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808696882720556e-05,
"loss": 3.871,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800310935210036e-05,
"loss": 3.8829,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579194136650325e-05,
"loss": 3.8675,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578355541899273e-05,
"loss": 3.8869,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577516947148221e-05,
"loss": 3.872,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576678352397169e-05,
"loss": 3.8795,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.57584139552649e-05,
"loss": 3.8841,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.575002800775438e-05,
"loss": 3.8673,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574164206024386e-05,
"loss": 3.8718,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573325611273334e-05,
"loss": 3.8785,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572487016522282e-05,
"loss": 3.865,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571650059651603e-05,
"loss": 3.8738,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570811464900551e-05,
"loss": 3.8762,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569972870149499e-05,
"loss": 3.8798,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.5691342753984476e-05,
"loss": 3.8647,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5682973185277685e-05,
"loss": 3.8704,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.5674587237767165e-05,
"loss": 3.861,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.5666201290256645e-05,
"loss": 3.8716,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.5657815342746125e-05,
"loss": 3.8828,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.5649445774039334e-05,
"loss": 3.8733,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.5641059826528814e-05,
"loss": 3.8848,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.5632673879018294e-05,
"loss": 3.8836,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624287931507774e-05,
"loss": 3.8812,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561591836280098e-05,
"loss": 3.8599,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560753241529046e-05,
"loss": 3.8781,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559914646777994e-05,
"loss": 3.8771,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559076052026943e-05,
"loss": 3.867,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558239095156264e-05,
"loss": 3.872,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557400500405212e-05,
"loss": 3.8748,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.55656190565416e-05,
"loss": 3.8861,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555723310903108e-05,
"loss": 3.8684,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554886354032429e-05,
"loss": 3.8562,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554047759281377e-05,
"loss": 3.8665,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553209164530325e-05,
"loss": 3.8689,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552370569779273e-05,
"loss": 3.8735,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551533612908594e-05,
"loss": 3.8738,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550695018157542e-05,
"loss": 3.8629,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.54985642340649e-05,
"loss": 3.8656,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.5490178286554384e-05,
"loss": 3.8555,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548180871784759e-05,
"loss": 3.8606,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547342277033707e-05,
"loss": 3.8611,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546503682282655e-05,
"loss": 3.8743,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545665087531603e-05,
"loss": 3.8857,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544828130660924e-05,
"loss": 3.862,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543989535909872e-05,
"loss": 3.8545,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.54315094115882e-05,
"loss": 3.8642,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542312346407768e-05,
"loss": 3.8616,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541475389537089e-05,
"loss": 3.8731,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540636794786037e-05,
"loss": 3.8625,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539798200034985e-05,
"loss": 3.8651,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538959605283933e-05,
"loss": 3.8589,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5381226484132546e-05,
"loss": 3.8696,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372840536622026e-05,
"loss": 3.8422,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364454589111506e-05,
"loss": 3.8566,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5356068641600986e-05,
"loss": 3.8522,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347699072894195e-05,
"loss": 3.8643,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339313125383675e-05,
"loss": 3.8503,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330927177873155e-05,
"loss": 3.8594,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322541230362635e-05,
"loss": 3.8493,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314171661655844e-05,
"loss": 3.8534,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.5305785714145324e-05,
"loss": 3.8572,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297399766634804e-05,
"loss": 3.8583,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.5289013819124284e-05,
"loss": 3.8695,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.52806442504175e-05,
"loss": 3.8698,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527227468171071e-05,
"loss": 3.8594,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526388873420019e-05,
"loss": 3.8515,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525550278668967e-05,
"loss": 3.8528,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524711683917915e-05,
"loss": 3.8587,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523873089166863e-05,
"loss": 3.8499,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523034494415811e-05,
"loss": 3.8544,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522195899664759e-05,
"loss": 3.8528,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521357304913707e-05,
"loss": 3.8521,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520520348043028e-05,
"loss": 3.8478,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519681753291976e-05,
"loss": 3.8487,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518843158540924e-05,
"loss": 3.8479,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5180045637898725e-05,
"loss": 3.8523,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171676069191934e-05,
"loss": 3.8383,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163290121681414e-05,
"loss": 3.8654,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.5154904174170894e-05,
"loss": 3.8632,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146518226660373e-05,
"loss": 3.8585,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513814865795358e-05,
"loss": 3.8364,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512976271044306e-05,
"loss": 3.8536,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512137676293254e-05,
"loss": 3.8575,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511299081542202e-05,
"loss": 3.8537,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510462124671523e-05,
"loss": 3.8519,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509623529920471e-05,
"loss": 3.8519,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508784935169419e-05,
"loss": 3.8501,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507946340418368e-05,
"loss": 3.8574,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507109383547689e-05,
"loss": 3.8471,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506270788796637e-05,
"loss": 3.8504,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505432194045585e-05,
"loss": 3.8501,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504593599294533e-05,
"loss": 3.8388,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.5037566424238536e-05,
"loss": 3.8563,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5029180476728016e-05,
"loss": 3.8523,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020794529217496e-05,
"loss": 3.85,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012408581706976e-05,
"loss": 3.8396,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500402263419645e-05,
"loss": 3.8414,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.909769058227539,
"eval_runtime": 307.4618,
"eval_samples_per_second": 1241.101,
"eval_steps_per_second": 38.785,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499563668668593e-05,
"loss": 3.8395,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987250739175416e-05,
"loss": 3.8349,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978864791664896e-05,
"loss": 3.8475,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970478844154376e-05,
"loss": 3.8428,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4962092896643856e-05,
"loss": 3.859,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953706949133336e-05,
"loss": 3.8336,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945321001622816e-05,
"loss": 3.8396,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936935054112296e-05,
"loss": 3.8267,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928565485405505e-05,
"loss": 3.8468,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4920179537894985e-05,
"loss": 3.8432,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911793590384465e-05,
"loss": 3.8415,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903407642873945e-05,
"loss": 3.8414,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.4895038074167154e-05,
"loss": 3.8298,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.4886652126656634e-05,
"loss": 3.8381,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4878266179146114e-05,
"loss": 3.8258,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.48698802316356e-05,
"loss": 3.8339,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486151066292881e-05,
"loss": 3.83,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485312471541829e-05,
"loss": 3.8305,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484473876790777e-05,
"loss": 3.8343,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483635282039725e-05,
"loss": 3.851,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482798325169046e-05,
"loss": 3.8323,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481959730417994e-05,
"loss": 3.838,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481121135666942e-05,
"loss": 3.8305,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.48028254091589e-05,
"loss": 3.8404,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479445584045211e-05,
"loss": 3.8263,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478606989294159e-05,
"loss": 3.8371,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477768394543107e-05,
"loss": 3.8295,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476931437672428e-05,
"loss": 3.8248,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476092842921376e-05,
"loss": 3.8184,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475254248170324e-05,
"loss": 3.8242,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474415653419272e-05,
"loss": 3.8305,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473578696548593e-05,
"loss": 3.8347,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472740101797541e-05,
"loss": 3.8355,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471901507046489e-05,
"loss": 3.8294,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471062912295437e-05,
"loss": 3.8239,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470225955424758e-05,
"loss": 3.8382,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469387360673706e-05,
"loss": 3.825,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468548765922654e-05,
"loss": 3.8249,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467710171171602e-05,
"loss": 3.8101,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466873214300924e-05,
"loss": 3.8257,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466034619549872e-05,
"loss": 3.8205,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.46519602479882e-05,
"loss": 3.831,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464357430047768e-05,
"loss": 3.8252,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4635204731770886e-05,
"loss": 3.8145,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626818784260366e-05,
"loss": 3.8298,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618432836749846e-05,
"loss": 3.8195,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4610046889239326e-05,
"loss": 3.8168,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601677320532535e-05,
"loss": 3.8102,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4593291373022015e-05,
"loss": 3.81,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584905425511495e-05,
"loss": 3.825,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576519478000975e-05,
"loss": 3.8188,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456814990929419e-05,
"loss": 3.818,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455976396178367e-05,
"loss": 3.8096,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455137801427315e-05,
"loss": 3.8194,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454299206676263e-05,
"loss": 3.8044,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453462249805584e-05,
"loss": 3.822,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452623655054532e-05,
"loss": 3.8055,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.45178506030348e-05,
"loss": 3.8193,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450946465552428e-05,
"loss": 3.8177,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450109508681749e-05,
"loss": 3.8108,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449270913930697e-05,
"loss": 3.8061,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448432319179645e-05,
"loss": 3.817,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447593724428593e-05,
"loss": 3.8024,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.4467567675579144e-05,
"loss": 3.8109,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.4459181728068624e-05,
"loss": 3.8181,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.4450795780558104e-05,
"loss": 3.8145,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.4442409833047584e-05,
"loss": 3.8041,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443404026434079e-05,
"loss": 3.8068,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442565431683027e-05,
"loss": 3.8032,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441726836931975e-05,
"loss": 3.8069,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440888242180923e-05,
"loss": 3.8191,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440051285310244e-05,
"loss": 3.8137,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439212690559192e-05,
"loss": 3.8248,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.43837409580814e-05,
"loss": 3.8228,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437535501057088e-05,
"loss": 3.821,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.43669854418641e-05,
"loss": 3.8013,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435859949435358e-05,
"loss": 3.8114,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435021354684306e-05,
"loss": 3.8204,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434184397813627e-05,
"loss": 3.8072,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433345803062575e-05,
"loss": 3.8088,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432507208311523e-05,
"loss": 3.8115,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431668613560471e-05,
"loss": 3.8268,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430830018809418e-05,
"loss": 3.809,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429991424058366e-05,
"loss": 3.7949,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429152829307314e-05,
"loss": 3.8046,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428314234556262e-05,
"loss": 3.8092,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274772776855836e-05,
"loss": 3.8144,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266386829345316e-05,
"loss": 3.8139,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4258000881834796e-05,
"loss": 3.8014,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249614934324276e-05,
"loss": 3.8053,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4241245365617485e-05,
"loss": 3.8018,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232859418106965e-05,
"loss": 3.7986,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224473470596445e-05,
"loss": 3.805,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4216087523085925e-05,
"loss": 3.8118,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207717954379134e-05,
"loss": 3.8278,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.4199332006868614e-05,
"loss": 3.8089,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190946059358094e-05,
"loss": 3.7936,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182560111847573e-05,
"loss": 3.8048,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417419054314079e-05,
"loss": 3.8005,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416580459563027e-05,
"loss": 3.8146,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415741864811975e-05,
"loss": 3.807,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414903270060923e-05,
"loss": 3.8059,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414066313190244e-05,
"loss": 3.7972,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413227718439192e-05,
"loss": 3.8102,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.41238912368814e-05,
"loss": 3.7856,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411550528937088e-05,
"loss": 3.8016,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410713572066409e-05,
"loss": 3.79,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409874977315357e-05,
"loss": 3.81,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409036382564305e-05,
"loss": 3.7944,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408197787813253e-05,
"loss": 3.7985,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407360830942574e-05,
"loss": 3.7936,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406522236191522e-05,
"loss": 3.8004,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.40568364144047e-05,
"loss": 3.8017,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404845046689418e-05,
"loss": 3.7993,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.404008089818739e-05,
"loss": 3.8116,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.40317113294806e-05,
"loss": 3.8123,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402332538197008e-05,
"loss": 3.8021,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401493943445956e-05,
"loss": 3.7955,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400655348694904e-05,
"loss": 3.7963,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399818391824225e-05,
"loss": 3.8061,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398979797073173e-05,
"loss": 3.7874,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398141202322122e-05,
"loss": 3.8025,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.39730260757107e-05,
"loss": 3.7911,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396464012820018e-05,
"loss": 3.7969,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3956254180689657e-05,
"loss": 3.7942,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.3947868233179137e-05,
"loss": 3.7944,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939498664472346e-05,
"loss": 3.7882,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3931112716961826e-05,
"loss": 3.8007,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.3922726769451306e-05,
"loss": 3.786,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3914340821940786e-05,
"loss": 3.8077,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905971253233995e-05,
"loss": 3.8018,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897585305723475e-05,
"loss": 3.8092,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.3889199358212955e-05,
"loss": 3.779,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.3880813410702434e-05,
"loss": 3.8012,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387244384199565e-05,
"loss": 3.8003,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386405789448513e-05,
"loss": 3.7979,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385567194697461e-05,
"loss": 3.7961,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384728599946409e-05,
"loss": 3.7993,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.38389164307573e-05,
"loss": 3.7937,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383053048324678e-05,
"loss": 3.8051,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382214453573626e-05,
"loss": 3.7871,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381377496702947e-05,
"loss": 3.7971,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380538901951895e-05,
"loss": 3.7951,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379700307200843e-05,
"loss": 3.786,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378861712449791e-05,
"loss": 3.7979,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378023117698739e-05,
"loss": 3.8018,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771861608280604e-05,
"loss": 3.7938,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763475660770084e-05,
"loss": 3.7841,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3755089713259564e-05,
"loss": 3.7915,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.884277105331421,
"eval_runtime": 308.3892,
"eval_samples_per_second": 1237.368,
"eval_steps_per_second": 38.669,
"step": 381600
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 2.661013841810688e+17,
"trial_name": null,
"trial_params": null
}