full-transformer-1 / checkpoint-1602720 /trainer_state.json
abhinavp's picture
Training in progress, epoch 1, checkpoint
85189f7 verified
{
"best_metric": 3.8405232429504395,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full2/transformer/1/checkpoints/checkpoint-992160",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 1602720,
"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": 10.9454,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8259,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1849,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9803,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8167,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7055,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6038,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5334,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4448,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3954,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3443,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3189,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2639,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.1992,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1743,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.137,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1066,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0804,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0551,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0135,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0066,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9713,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9507,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9237,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9215,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8944,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8692,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8503,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8324,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8222,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7998,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7909,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7796,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.7645,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7622,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7476,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969820416244367e-05,
"loss": 4.733,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7055,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7012,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6844,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6838,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6677,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6617,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6456,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6513,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6349,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6356,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6256,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5973,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5911,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.6054,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.5893,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5748,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5602,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5638,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5468,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5615,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.525,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5379,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5354,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5131,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5289,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5001,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.5001,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4881,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.5029,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4753,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.481,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4663,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4627,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4745,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940482703000532e-05,
"loss": 4.4668,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396441082494794e-05,
"loss": 4.4581,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388055134984274e-05,
"loss": 4.4597,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4643,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4363,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4522,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4266,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4257,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.424,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4271,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4194,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4262,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.4109,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.3903,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.3918,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.4035,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.3888,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92623314375414e-05,
"loss": 4.3881,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.3925,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.375,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3815,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.3739,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3801,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921203213128201e-05,
"loss": 4.3768,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3721,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3504,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3571,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.3499,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3525,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.3597,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.3371,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914496093000158e-05,
"loss": 4.3421,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913657498249106e-05,
"loss": 4.3442,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3366,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3252,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3289,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3174,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3167,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.9086292055035406e-05,
"loss": 4.3155,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.9077906107524886e-05,
"loss": 4.3148,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.9069520160014366e-05,
"loss": 4.3079,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.9061134212503846e-05,
"loss": 4.3144,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3044,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3066,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3138,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027606801265495e-05,
"loss": 4.31,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.3043,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.295,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.2948,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2928,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.2805,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2849,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.2801,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.284,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2741,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2821,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2762,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2694,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2626,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2799,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2705,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2632,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888509482999785e-05,
"loss": 4.2629,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887672526129106e-05,
"loss": 4.2671,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886833931378054e-05,
"loss": 4.2628,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885995336627002e-05,
"loss": 4.265,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.2548,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2543,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2528,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2439,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2412,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809654060010626e-05,
"loss": 4.2412,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801268112500106e-05,
"loss": 4.2439,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2334,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2446,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877614302757601e-05,
"loss": 4.2349,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876775708006549e-05,
"loss": 4.2371,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875937113255497e-05,
"loss": 4.2406,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875098518504445e-05,
"loss": 4.2215,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.193474292755127,
"eval_runtime": 317.2956,
"eval_samples_per_second": 1202.636,
"eval_steps_per_second": 37.583,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874259923753393e-05,
"loss": 4.2116,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873421329002341e-05,
"loss": 4.21,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872584372131662e-05,
"loss": 4.2335,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.87174577738061e-05,
"loss": 4.2158,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870907182629558e-05,
"loss": 4.2208,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870068587878506e-05,
"loss": 4.2133,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869229993127454e-05,
"loss": 4.2059,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683913983764027e-05,
"loss": 4.1979,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675544415057236e-05,
"loss": 4.2071,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667158467546716e-05,
"loss": 4.1993,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658772520036196e-05,
"loss": 4.2226,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.8650386572525676e-05,
"loss": 4.2066,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642017003818885e-05,
"loss": 4.1887,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633631056308365e-05,
"loss": 4.188,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625245108797845e-05,
"loss": 4.1931,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616859161287324e-05,
"loss": 4.1794,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608473213776804e-05,
"loss": 4.1918,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860008726626628e-05,
"loss": 4.189,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591701318755764e-05,
"loss": 4.1751,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583315371245244e-05,
"loss": 4.2017,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.1808,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.1821,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855817390751741e-05,
"loss": 4.173,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854978796000689e-05,
"loss": 4.1918,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.1693,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853301606498585e-05,
"loss": 4.1707,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.166,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851626054876854e-05,
"loss": 4.1657,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850787460125802e-05,
"loss": 4.1628,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.84994886537475e-05,
"loss": 4.1599,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.1631,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.1636,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1601,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.1662,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845757529499864e-05,
"loss": 4.1608,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.1597,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.145,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.1474,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.1394,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.1485,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.1392,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.1485,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.1294,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.1491,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.1411,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836536262999038e-05,
"loss": 4.1424,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1374,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.1224,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834022116626255e-05,
"loss": 4.1235,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833183521875203e-05,
"loss": 4.1393,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.1297,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831506332373099e-05,
"loss": 4.1247,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830667737622047e-05,
"loss": 4.1158,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298291428709944e-05,
"loss": 4.1274,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289905481199424e-05,
"loss": 4.1072,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281519533688904e-05,
"loss": 4.1334,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273133586178384e-05,
"loss": 4.103,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.82647640174716e-05,
"loss": 4.1229,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825637806996108e-05,
"loss": 4.1192,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824799212245056e-05,
"loss": 4.1066,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823960617494004e-05,
"loss": 4.1188,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823123660623325e-05,
"loss": 4.1073,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822285065872273e-05,
"loss": 4.1064,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821446471121221e-05,
"loss": 4.0946,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820607876370169e-05,
"loss": 4.1185,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.81977091949949e-05,
"loss": 4.0927,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818932324748438e-05,
"loss": 4.1058,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818093729997386e-05,
"loss": 4.0837,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817255135246334e-05,
"loss": 4.097,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164181783756554e-05,
"loss": 4.1068,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155795836246034e-05,
"loss": 4.1047,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147409888735514e-05,
"loss": 4.0996,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139023941224994e-05,
"loss": 4.1027,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.81306543725182e-05,
"loss": 4.1087,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812226842500768e-05,
"loss": 4.0931,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811388247749716e-05,
"loss": 4.1021,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810549652998664e-05,
"loss": 4.0893,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809712696127985e-05,
"loss": 4.0892,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808874101376933e-05,
"loss": 4.0848,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808035506625881e-05,
"loss": 4.0956,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807196911874829e-05,
"loss": 4.0944,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806358317123777e-05,
"loss": 4.0999,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805519722372726e-05,
"loss": 4.0898,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804682765502047e-05,
"loss": 4.0693,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803844170750995e-05,
"loss": 4.0746,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803005575999943e-05,
"loss": 4.085,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802166981248891e-05,
"loss": 4.0808,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013300243782116e-05,
"loss": 4.0758,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004914296271596e-05,
"loss": 4.0856,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996528348761076e-05,
"loss": 4.0698,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988142401250556e-05,
"loss": 4.0733,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979772832543765e-05,
"loss": 4.0757,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971386885033245e-05,
"loss": 4.0839,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7963000937522725e-05,
"loss": 4.0795,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795461499001221e-05,
"loss": 4.0863,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794624542130542e-05,
"loss": 4.0585,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.79378594737949e-05,
"loss": 4.0702,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792947352628438e-05,
"loss": 4.0669,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792108757877386e-05,
"loss": 4.0652,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791271801006707e-05,
"loss": 4.0818,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790433206255655e-05,
"loss": 4.0596,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789594611504603e-05,
"loss": 4.0654,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788756016753551e-05,
"loss": 4.071,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787919059882872e-05,
"loss": 4.0669,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.78708046513182e-05,
"loss": 4.0507,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786241870380768e-05,
"loss": 4.0646,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854032756297166e-05,
"loss": 4.0553,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845663187590375e-05,
"loss": 4.0517,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837293618883584e-05,
"loss": 4.0508,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828907671373064e-05,
"loss": 4.0524,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820521723862544e-05,
"loss": 4.0497,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812135776352024e-05,
"loss": 4.0614,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803749828841504e-05,
"loss": 4.0462,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795363881330984e-05,
"loss": 4.0537,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786977933820464e-05,
"loss": 4.0654,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778591986309944e-05,
"loss": 4.0583,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777022241760315e-05,
"loss": 4.0558,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776183647009263e-05,
"loss": 4.0505,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775345052258212e-05,
"loss": 4.0455,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450645750716e-05,
"loss": 4.0485,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773669500636481e-05,
"loss": 4.0427,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772832543765802e-05,
"loss": 4.0414,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.77199394901475e-05,
"loss": 4.0433,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771155354263698e-05,
"loss": 4.0485,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770316759512646e-05,
"loss": 4.0439,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769478164761594e-05,
"loss": 4.0444,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.045,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76780097525949e-05,
"loss": 4.0345,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766962380508437e-05,
"loss": 4.0331,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766123785757386e-05,
"loss": 4.0517,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765286828886707e-05,
"loss": 4.0464,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764448234135655e-05,
"loss": 4.0413,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.7636096393846026e-05,
"loss": 4.0357,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.7627710446335506e-05,
"loss": 4.0427,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.7619324498824986e-05,
"loss": 4.0382,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610954930118195e-05,
"loss": 4.0468,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602568982607675e-05,
"loss": 4.0383,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594183035097155e-05,
"loss": 4.0336,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.7585797087586635e-05,
"loss": 4.0348,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577427518879844e-05,
"loss": 4.0317,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569041571369324e-05,
"loss": 4.0245,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756065562385881e-05,
"loss": 4.0304,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755226967634829e-05,
"loss": 4.0347,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754388372883777e-05,
"loss": 4.0212,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753551416013098e-05,
"loss": 4.0394,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752712821262046e-05,
"loss": 4.0288,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751874226510994e-05,
"loss": 4.0277,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751035631759942e-05,
"loss": 4.0313,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750198674889263e-05,
"loss": 4.0184,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.025022029876709,
"eval_runtime": 317.0746,
"eval_samples_per_second": 1203.474,
"eval_steps_per_second": 37.609,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749360080138211e-05,
"loss": 4.0074,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748521485387159e-05,
"loss": 4.0086,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747682890636107e-05,
"loss": 4.0333,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746844295885055e-05,
"loss": 4.0181,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.746005701134003e-05,
"loss": 4.0278,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745167106382951e-05,
"loss": 4.0109,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744328511631899e-05,
"loss": 4.0141,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434899168808475e-05,
"loss": 4.0027,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426529600101684e-05,
"loss": 4.0138,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418143652591164e-05,
"loss": 4.0093,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409757705080644e-05,
"loss": 4.0274,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401371757570124e-05,
"loss": 4.0181,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739300218886333e-05,
"loss": 3.998,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738461624135281e-05,
"loss": 4.0035,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737623029384229e-05,
"loss": 4.0092,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736784434633177e-05,
"loss": 3.992,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735945839882125e-05,
"loss": 4.0043,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735107245131073e-05,
"loss": 4.0069,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734268650380021e-05,
"loss": 3.9951,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733430055628969e-05,
"loss": 4.0229,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732591460877917e-05,
"loss": 3.9992,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731752866126865e-05,
"loss": 4.0041,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730914271375813e-05,
"loss": 3.9967,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730075676624761e-05,
"loss": 4.0149,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729238719754082e-05,
"loss": 3.989,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.72840012500303e-05,
"loss": 3.9962,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727561530251978e-05,
"loss": 3.9893,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726722935500926e-05,
"loss": 3.9946,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725885978630247e-05,
"loss": 3.9888,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725047383879195e-05,
"loss": 3.9873,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724210427008517e-05,
"loss": 3.9952,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233718322574647e-05,
"loss": 3.996,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225332375064127e-05,
"loss": 3.988,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216946427553606e-05,
"loss": 4.0014,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208560480043086e-05,
"loss": 3.9881,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200174532532566e-05,
"loss": 3.9944,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191788585022046e-05,
"loss": 3.9806,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183402637511526e-05,
"loss": 3.9846,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175033068804735e-05,
"loss": 3.9719,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166647121294215e-05,
"loss": 3.9875,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158261173783695e-05,
"loss": 3.9756,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149875226273175e-05,
"loss": 3.9883,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141505657566384e-05,
"loss": 3.9731,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133119710055864e-05,
"loss": 3.9851,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712473376254535e-05,
"loss": 3.9894,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711634781503483e-05,
"loss": 3.9813,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710797824632804e-05,
"loss": 3.984,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709959229881752e-05,
"loss": 3.9663,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709122273011073e-05,
"loss": 3.9671,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708283678260021e-05,
"loss": 3.9843,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707445083508969e-05,
"loss": 3.9758,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706606488757917e-05,
"loss": 3.974,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705767894006865e-05,
"loss": 3.9616,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704929299255813e-05,
"loss": 3.9752,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704090704504761e-05,
"loss": 3.9527,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703252109753709e-05,
"loss": 3.986,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024151528830305e-05,
"loss": 3.9538,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015765581319785e-05,
"loss": 3.9739,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007379633809265e-05,
"loss": 3.9729,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998993686298745e-05,
"loss": 3.9587,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990624117591954e-05,
"loss": 3.9746,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982238170081434e-05,
"loss": 3.9588,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973852222570914e-05,
"loss": 3.9598,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965466275060394e-05,
"loss": 3.9478,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69570967063536e-05,
"loss": 3.9715,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694871075884308e-05,
"loss": 3.9525,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694032481133256e-05,
"loss": 3.9603,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693193886382204e-05,
"loss": 3.9448,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692356929511526e-05,
"loss": 3.9528,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691518334760474e-05,
"loss": 3.9644,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690679740009422e-05,
"loss": 3.9676,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689841145258369e-05,
"loss": 3.9551,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689004188387691e-05,
"loss": 3.9669,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688165593636639e-05,
"loss": 3.9676,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687326998885587e-05,
"loss": 3.9573,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686488404134534e-05,
"loss": 3.958,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856514472638556e-05,
"loss": 3.9583,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848128525128036e-05,
"loss": 3.9522,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683974257761751e-05,
"loss": 3.9499,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831356630106996e-05,
"loss": 3.959,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822987061400205e-05,
"loss": 3.9605,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681460111388969e-05,
"loss": 3.9668,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806215166379165e-05,
"loss": 3.952,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797829218868645e-05,
"loss": 3.9326,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678945965016186e-05,
"loss": 3.9416,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678107370265134e-05,
"loss": 3.9539,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772687755140814e-05,
"loss": 3.948,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764301807630294e-05,
"loss": 3.9429,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9503,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674754629141298e-05,
"loss": 3.9454,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673916034390246e-05,
"loss": 3.9373,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673077439639194e-05,
"loss": 3.945,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672240482768516e-05,
"loss": 3.9548,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671401888017464e-05,
"loss": 3.9505,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670563293266412e-05,
"loss": 3.9554,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.66972469851536e-05,
"loss": 3.9388,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688877416446815e-05,
"loss": 3.9423,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668049146893629e-05,
"loss": 3.9405,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667210552142577e-05,
"loss": 3.9429,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666371957391525e-05,
"loss": 3.9524,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665535000520846e-05,
"loss": 3.937,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664696405769794e-05,
"loss": 3.9386,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663857811018742e-05,
"loss": 3.9455,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66301921626769e-05,
"loss": 3.9468,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662182259397011e-05,
"loss": 3.9272,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661343664645959e-05,
"loss": 3.9357,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660505069894907e-05,
"loss": 3.9376,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659668113024229e-05,
"loss": 3.9292,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.65883115615355e-05,
"loss": 3.9297,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657992561402498e-05,
"loss": 3.9309,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657153966651446e-05,
"loss": 3.933,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656315371900393e-05,
"loss": 3.9375,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655476777149341e-05,
"loss": 3.9263,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654638182398289e-05,
"loss": 3.9327,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653799587647237e-05,
"loss": 3.9452,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652960992896185e-05,
"loss": 3.9463,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521240360255066e-05,
"loss": 3.9346,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512854412744546e-05,
"loss": 3.9348,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.6504468465234026e-05,
"loss": 3.9303,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6496082517723506e-05,
"loss": 3.9311,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487712949016715e-05,
"loss": 3.9221,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647934338030993e-05,
"loss": 3.9235,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470957432799404e-05,
"loss": 3.9275,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462571485288884e-05,
"loss": 3.9355,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454185537778364e-05,
"loss": 3.9269,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445799590267844e-05,
"loss": 3.9308,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437413642757324e-05,
"loss": 3.9288,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429027695246804e-05,
"loss": 3.9202,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642064174773629e-05,
"loss": 3.9177,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.64122721790295e-05,
"loss": 3.9377,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640388623151898e-05,
"loss": 3.9347,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639550028400846e-05,
"loss": 3.9259,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638713071530167e-05,
"loss": 3.9231,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637874476779115e-05,
"loss": 3.9261,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637035882028063e-05,
"loss": 3.9294,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636197287277011e-05,
"loss": 3.9395,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635360330406332e-05,
"loss": 3.9267,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.63452173565528e-05,
"loss": 3.9211,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633683140904228e-05,
"loss": 3.9246,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632844546153176e-05,
"loss": 3.9214,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320059514021244e-05,
"loss": 3.9185,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311673566510724e-05,
"loss": 3.9207,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303287619000204e-05,
"loss": 3.925,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294901671489684e-05,
"loss": 3.9151,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628654848158662e-05,
"loss": 3.928,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.62781625340761e-05,
"loss": 3.9243,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626977658656558e-05,
"loss": 3.9191,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626139063905506e-05,
"loss": 3.9233,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625300469154454e-05,
"loss": 3.9089,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9513087272644043,
"eval_runtime": 301.973,
"eval_samples_per_second": 1263.659,
"eval_steps_per_second": 39.49,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624461874403402e-05,
"loss": 3.9125,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.62362327965235e-05,
"loss": 3.9009,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622786322781671e-05,
"loss": 3.9276,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.62194772803062e-05,
"loss": 3.9126,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621109133279568e-05,
"loss": 3.9262,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620270538528516e-05,
"loss": 3.9052,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619431943777464e-05,
"loss": 3.9158,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618593349026412e-05,
"loss": 3.8953,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617756392155733e-05,
"loss": 3.9142,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616917797404681e-05,
"loss": 3.9035,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616079202653629e-05,
"loss": 3.9261,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615240607902577e-05,
"loss": 3.9134,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6144036510318976e-05,
"loss": 3.8943,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135650562808456e-05,
"loss": 3.901,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.6127264615297936e-05,
"loss": 3.909,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.6118878667787416e-05,
"loss": 3.8948,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.6110492720276896e-05,
"loss": 3.9025,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.6102106772766376e-05,
"loss": 3.9059,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.6093720825255856e-05,
"loss": 3.8965,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.6085334877745336e-05,
"loss": 3.9278,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076948930234816e-05,
"loss": 3.8983,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068562982724296e-05,
"loss": 3.9022,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6060177035213776e-05,
"loss": 3.9017,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051807466506985e-05,
"loss": 3.9094,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.6043421518996465e-05,
"loss": 3.8932,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.6035035571485945e-05,
"loss": 3.8994,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.6026649623975425e-05,
"loss": 3.8938,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018280055268634e-05,
"loss": 3.8967,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009894107758114e-05,
"loss": 3.8913,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.60015081602476e-05,
"loss": 3.8909,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599312221273708e-05,
"loss": 3.895,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598473626522656e-05,
"loss": 3.9013,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597635031771604e-05,
"loss": 3.8996,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596796437020552e-05,
"loss": 3.9016,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595959480149873e-05,
"loss": 3.8928,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595120885398821e-05,
"loss": 3.8981,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594282290647769e-05,
"loss": 3.8839,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593443695896717e-05,
"loss": 3.8972,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592605101145665e-05,
"loss": 3.8781,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591768144274986e-05,
"loss": 3.8905,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590929549523934e-05,
"loss": 3.8828,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590090954772882e-05,
"loss": 3.898,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.58925236002183e-05,
"loss": 3.8818,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5884137652707785e-05,
"loss": 3.8869,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587575170519726e-05,
"loss": 3.8972,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586736575768674e-05,
"loss": 3.8911,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585897981017622e-05,
"loss": 3.8929,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585061024146943e-05,
"loss": 3.877,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584224067276264e-05,
"loss": 3.8754,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583385472525212e-05,
"loss": 3.8892,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.58254687777416e-05,
"loss": 3.8863,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.5817082830231076e-05,
"loss": 3.8807,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808696882720556e-05,
"loss": 3.8751,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580032731401377e-05,
"loss": 3.8864,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579194136650325e-05,
"loss": 3.8654,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578355541899273e-05,
"loss": 3.8862,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577516947148221e-05,
"loss": 3.8675,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576678352397169e-05,
"loss": 3.8814,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.57584139552649e-05,
"loss": 3.8863,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.575002800775438e-05,
"loss": 3.8715,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574164206024386e-05,
"loss": 3.8817,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573325611273334e-05,
"loss": 3.8735,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572487016522282e-05,
"loss": 3.8714,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571650059651603e-05,
"loss": 3.8657,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570811464900551e-05,
"loss": 3.8805,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569972870149499e-05,
"loss": 3.8672,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.5691342753984476e-05,
"loss": 3.8752,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5682956806473956e-05,
"loss": 3.8592,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.5674587237767165e-05,
"loss": 3.8654,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.5666201290256645e-05,
"loss": 3.8766,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.5657815342746125e-05,
"loss": 3.8832,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.5649429395235605e-05,
"loss": 3.869,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.5641043447725085e-05,
"loss": 3.883,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.5632657500214565e-05,
"loss": 3.8808,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624271552704045e-05,
"loss": 3.8709,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615885605193525e-05,
"loss": 3.8756,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.5607516036486734e-05,
"loss": 3.8727,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.5599130088976214e-05,
"loss": 3.8685,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.5590744141465694e-05,
"loss": 3.8669,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582358193955174e-05,
"loss": 3.8741,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557398862524839e-05,
"loss": 3.8781,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556560267773787e-05,
"loss": 3.8743,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555721673022735e-05,
"loss": 3.8724,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554883078271683e-05,
"loss": 3.853,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554044483520631e-05,
"loss": 3.8575,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553207526649952e-05,
"loss": 3.8682,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523689318989e-05,
"loss": 3.8678,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551530337147848e-05,
"loss": 3.8623,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550691742396796e-05,
"loss": 3.8668,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549854785526117e-05,
"loss": 3.8631,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549016190775065e-05,
"loss": 3.8563,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548177596024013e-05,
"loss": 3.8641,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547339001272961e-05,
"loss": 3.8712,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546500406521909e-05,
"loss": 3.8682,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545661811770857e-05,
"loss": 3.8783,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544823217019805e-05,
"loss": 3.8612,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543984622268753e-05,
"loss": 3.859,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543149303278447e-05,
"loss": 3.8615,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542310708527395e-05,
"loss": 3.8634,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541472113776343e-05,
"loss": 3.8735,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540633519025291e-05,
"loss": 3.8565,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539796562154612e-05,
"loss": 3.86,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.53895796740356e-05,
"loss": 3.864,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538119372652508e-05,
"loss": 3.8692,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537280777901456e-05,
"loss": 3.8491,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536442183150404e-05,
"loss": 3.8591,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535605226279726e-05,
"loss": 3.8593,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534766631528674e-05,
"loss": 3.8511,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533928036777621e-05,
"loss": 3.8475,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533089442026569e-05,
"loss": 3.8569,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532250847275517e-05,
"loss": 3.8564,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531412252524465e-05,
"loss": 3.8581,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530575295653786e-05,
"loss": 3.8508,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529736700902734e-05,
"loss": 3.851,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528898106151682e-05,
"loss": 3.8702,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.52805951140063e-05,
"loss": 3.8668,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.5272209166495786e-05,
"loss": 3.8609,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.5263839597788995e-05,
"loss": 3.8579,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.5255453650278475e-05,
"loss": 3.855,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.5247067702767955e-05,
"loss": 3.8528,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.5238681755257435e-05,
"loss": 3.8471,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.5230312186550644e-05,
"loss": 3.847,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.5221926239040124e-05,
"loss": 3.8507,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.5213540291529604e-05,
"loss": 3.8596,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.5205154344019084e-05,
"loss": 3.8497,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519678477531229e-05,
"loss": 3.8584,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518839882780177e-05,
"loss": 3.8505,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.518001288029125e-05,
"loss": 3.8466,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517162693278074e-05,
"loss": 3.843,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516325736407395e-05,
"loss": 3.8639,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515487141656343e-05,
"loss": 3.8618,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514648546905291e-05,
"loss": 3.8516,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513809952154239e-05,
"loss": 3.8481,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512971357403187e-05,
"loss": 3.8549,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512134400532508e-05,
"loss": 3.8514,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511295805781456e-05,
"loss": 3.8633,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510457211030404e-05,
"loss": 3.8484,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509618616279352e-05,
"loss": 3.8522,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087816594086726e-05,
"loss": 3.8489,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079430646576206e-05,
"loss": 3.8544,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507104469906569e-05,
"loss": 3.8425,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506265875155517e-05,
"loss": 3.8469,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505428918284838e-05,
"loss": 3.8517,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504590323533786e-05,
"loss": 3.844,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503751728782734e-05,
"loss": 3.8518,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502913134031682e-05,
"loss": 3.8557,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502076177161003e-05,
"loss": 3.8473,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501237582409951e-05,
"loss": 3.8488,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500398987658899e-05,
"loss": 3.8437,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.9104487895965576,
"eval_runtime": 302.9202,
"eval_samples_per_second": 1259.708,
"eval_steps_per_second": 39.367,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499560392907847e-05,
"loss": 3.8326,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498721798156795e-05,
"loss": 3.8302,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497883203405743e-05,
"loss": 3.8531,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497044608654691e-05,
"loss": 3.8444,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496206013903639e-05,
"loss": 3.8557,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495367419152587e-05,
"loss": 3.8337,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494528824401535e-05,
"loss": 3.8457,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493690229650483e-05,
"loss": 3.8244,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928532727798047e-05,
"loss": 3.8468,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.492014678028752e-05,
"loss": 3.8338,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911760832777e-05,
"loss": 3.8514,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490337488526648e-05,
"loss": 3.8463,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489500531655969e-05,
"loss": 3.8216,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488661936904917e-05,
"loss": 3.8368,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487823342153865e-05,
"loss": 3.8387,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486984747402813e-05,
"loss": 3.826,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486146152651761e-05,
"loss": 3.8334,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.4853075579007095e-05,
"loss": 3.8362,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.4844689631496575e-05,
"loss": 3.8322,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.4836303683986055e-05,
"loss": 3.8521,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.4827917736475535e-05,
"loss": 3.8287,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.4819548167768744e-05,
"loss": 3.8341,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.4811162220258224e-05,
"loss": 3.8359,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.4802776272747704e-05,
"loss": 3.8415,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.4794390325237184e-05,
"loss": 3.826,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478602075653039e-05,
"loss": 3.8372,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477763480901987e-05,
"loss": 3.8217,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476924886150935e-05,
"loss": 3.8282,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476086291399883e-05,
"loss": 3.8237,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475249334529205e-05,
"loss": 3.8253,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474410739778153e-05,
"loss": 3.8293,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473572145027101e-05,
"loss": 3.8338,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472733550276049e-05,
"loss": 3.8334,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471894955524997e-05,
"loss": 3.8353,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471057998654318e-05,
"loss": 3.8236,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470219403903266e-05,
"loss": 3.8344,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469380809152214e-05,
"loss": 3.8238,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468542214401162e-05,
"loss": 3.8244,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467705257530483e-05,
"loss": 3.8124,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466866662779431e-05,
"loss": 3.8236,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466028068028379e-05,
"loss": 3.8196,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465189473277327e-05,
"loss": 3.8326,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464350878526275e-05,
"loss": 3.8179,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463513921655596e-05,
"loss": 3.8209,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462675326904544e-05,
"loss": 3.8344,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461836732153492e-05,
"loss": 3.8255,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.46099813740244e-05,
"loss": 3.8256,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460161180531761e-05,
"loss": 3.8168,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459322585780709e-05,
"loss": 3.8048,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.458483991029657e-05,
"loss": 3.8274,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457645396278605e-05,
"loss": 3.8211,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4568068015275525e-05,
"loss": 3.8153,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455969844656874e-05,
"loss": 3.8152,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455131249905822e-05,
"loss": 3.8246,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.45429265515477e-05,
"loss": 3.8019,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453454060403718e-05,
"loss": 3.8263,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4526171035330396e-05,
"loss": 3.8046,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.4517785087819876e-05,
"loss": 3.8188,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.4509399140309356e-05,
"loss": 3.8206,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450101319279883e-05,
"loss": 3.8113,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.4492643624092045e-05,
"loss": 3.8145,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.4484257676581525e-05,
"loss": 3.8137,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.4475871729071e-05,
"loss": 3.8072,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446748578156048e-05,
"loss": 3.8098,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.4459116212853694e-05,
"loss": 3.8134,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.4450730265343174e-05,
"loss": 3.8094,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.4442344317832654e-05,
"loss": 3.8108,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.4433958370322134e-05,
"loss": 3.799,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442558880161535e-05,
"loss": 3.8004,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441720285410482e-05,
"loss": 3.8135,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.44088169065943e-05,
"loss": 3.8243,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440043095908378e-05,
"loss": 3.8074,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439204501157326e-05,
"loss": 3.824,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438367544286647e-05,
"loss": 3.82,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437528949535595e-05,
"loss": 3.8086,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436690354784543e-05,
"loss": 3.8113,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435851760033491e-05,
"loss": 3.817,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435014803162813e-05,
"loss": 3.8074,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434176208411761e-05,
"loss": 3.8072,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433337613660709e-05,
"loss": 3.8149,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432499018909657e-05,
"loss": 3.815,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431662062038978e-05,
"loss": 3.8161,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4308234672879257e-05,
"loss": 3.8103,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299848725368737e-05,
"loss": 3.795,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291462777858217e-05,
"loss": 3.7946,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4283093209151426e-05,
"loss": 3.8101,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274707261640906e-05,
"loss": 3.8107,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266321314130386e-05,
"loss": 3.8036,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257935366619865e-05,
"loss": 3.8064,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424956579791308e-05,
"loss": 3.8023,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424117985040256e-05,
"loss": 3.8009,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423279390289204e-05,
"loss": 3.8053,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422440795538152e-05,
"loss": 3.8069,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421603838667473e-05,
"loss": 3.8117,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420765243916421e-05,
"loss": 3.8146,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419926649165369e-05,
"loss": 3.8086,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419088054414317e-05,
"loss": 3.7985,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418251097543638e-05,
"loss": 3.8088,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417412502792586e-05,
"loss": 3.8027,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416573908041534e-05,
"loss": 3.8149,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157369511708555e-05,
"loss": 3.8012,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.4148983564198035e-05,
"loss": 3.7959,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.4140597616687515e-05,
"loss": 3.8125,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4132211669176995e-05,
"loss": 3.8078,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123825721666475e-05,
"loss": 3.7977,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115456152959684e-05,
"loss": 3.8004,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4107070205449164e-05,
"loss": 3.8027,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098684257938644e-05,
"loss": 3.7872,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409031468923185e-05,
"loss": 3.791,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408192874172133e-05,
"loss": 3.8037,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407354279421081e-05,
"loss": 3.7968,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406515684670029e-05,
"loss": 3.799,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405677089918977e-05,
"loss": 3.7937,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404838495167925e-05,
"loss": 3.795,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.403999900416873e-05,
"loss": 3.8141,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403161305665822e-05,
"loss": 3.8132,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.40232271091477e-05,
"loss": 3.8046,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401485754044091e-05,
"loss": 3.8024,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400647159293039e-05,
"loss": 3.7955,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399808564541987e-05,
"loss": 3.7941,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398971607671308e-05,
"loss": 3.792,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398133012920256e-05,
"loss": 3.7953,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397294418169204e-05,
"loss": 3.7937,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396455823418152e-05,
"loss": 3.8018,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3956188665474726e-05,
"loss": 3.7946,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.3947802717964206e-05,
"loss": 3.7994,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939416770453686e-05,
"loss": 3.7934,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393103082294317e-05,
"loss": 3.7907,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392266125423638e-05,
"loss": 3.7905,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391427530672586e-05,
"loss": 3.8036,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390588935921534e-05,
"loss": 3.8077,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389750341170482e-05,
"loss": 3.7997,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388913384299803e-05,
"loss": 3.7913,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388074789548751e-05,
"loss": 3.8013,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387236194797699e-05,
"loss": 3.7952,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386397600046647e-05,
"loss": 3.8062,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385559005295595e-05,
"loss": 3.7953,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384722048424916e-05,
"loss": 3.7957,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383883453673864e-05,
"loss": 3.7949,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383044858922813e-05,
"loss": 3.8032,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3822079020521336e-05,
"loss": 3.7868,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813693073010816e-05,
"loss": 3.7917,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3805307125500296e-05,
"loss": 3.7962,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796921177989776e-05,
"loss": 3.7922,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788551609282985e-05,
"loss": 3.7994,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3780165661772465e-05,
"loss": 3.7994,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771779714261945e-05,
"loss": 3.7953,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763393766751425e-05,
"loss": 3.7909,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.37550078192409e-05,
"loss": 3.7912,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.8856112957000732,
"eval_runtime": 304.7445,
"eval_samples_per_second": 1252.167,
"eval_steps_per_second": 39.131,
"step": 381600
},
{
"epoch": 0.0,
"learning_rate": 4.3746638250534114e-05,
"loss": 3.7817,
"step": 381952
},
{
"epoch": 0.0,
"learning_rate": 4.3738252303023594e-05,
"loss": 3.7742,
"step": 382464
},
{
"epoch": 0.0,
"learning_rate": 4.372986635551308e-05,
"loss": 3.801,
"step": 382976
},
{
"epoch": 0.0,
"learning_rate": 4.3721480408002554e-05,
"loss": 3.7922,
"step": 383488
},
{
"epoch": 0.0,
"learning_rate": 4.3713094460492034e-05,
"loss": 3.7994,
"step": 384000
},
{
"epoch": 0.0,
"learning_rate": 4.3704708512981514e-05,
"loss": 3.7849,
"step": 384512
},
{
"epoch": 0.0,
"learning_rate": 4.3696322565470993e-05,
"loss": 3.788,
"step": 385024
},
{
"epoch": 0.0,
"learning_rate": 4.3687936617960473e-05,
"loss": 3.7763,
"step": 385536
},
{
"epoch": 0.0,
"learning_rate": 4.367956704925368e-05,
"loss": 3.7882,
"step": 386048
},
{
"epoch": 0.0,
"learning_rate": 4.367118110174316e-05,
"loss": 3.7857,
"step": 386560
},
{
"epoch": 0.0,
"learning_rate": 4.366279515423264e-05,
"loss": 3.7963,
"step": 387072
},
{
"epoch": 0.0,
"learning_rate": 4.365440920672212e-05,
"loss": 3.794,
"step": 387584
},
{
"epoch": 0.0,
"learning_rate": 4.364605601681907e-05,
"loss": 3.7688,
"step": 388096
},
{
"epoch": 0.0,
"learning_rate": 4.363767006930855e-05,
"loss": 3.7848,
"step": 388608
},
{
"epoch": 0.0,
"learning_rate": 4.362928412179803e-05,
"loss": 3.7876,
"step": 389120
},
{
"epoch": 0.0,
"learning_rate": 4.362089817428751e-05,
"loss": 3.775,
"step": 389632
},
{
"epoch": 0.0,
"learning_rate": 4.361251222677699e-05,
"loss": 3.78,
"step": 390144
},
{
"epoch": 0.0,
"learning_rate": 4.360412627926647e-05,
"loss": 3.7831,
"step": 390656
},
{
"epoch": 0.0,
"learning_rate": 4.359574033175595e-05,
"loss": 3.7803,
"step": 391168
},
{
"epoch": 0.0,
"learning_rate": 4.358735438424543e-05,
"loss": 3.7982,
"step": 391680
},
{
"epoch": 0.0,
"learning_rate": 4.3578984815538636e-05,
"loss": 3.7806,
"step": 392192
},
{
"epoch": 0.0,
"learning_rate": 4.3570598868028116e-05,
"loss": 3.7849,
"step": 392704
},
{
"epoch": 0.0,
"learning_rate": 4.3562212920517596e-05,
"loss": 3.7824,
"step": 393216
},
{
"epoch": 0.0,
"learning_rate": 4.3553826973007076e-05,
"loss": 3.7878,
"step": 393728
},
{
"epoch": 0.0,
"learning_rate": 4.3545457404300285e-05,
"loss": 3.7744,
"step": 394240
},
{
"epoch": 0.0,
"learning_rate": 4.353707145678977e-05,
"loss": 3.7837,
"step": 394752
},
{
"epoch": 0.0,
"learning_rate": 4.352868550927925e-05,
"loss": 3.7766,
"step": 395264
},
{
"epoch": 0.0,
"learning_rate": 4.352031594057246e-05,
"loss": 3.7742,
"step": 395776
},
{
"epoch": 0.0,
"learning_rate": 4.351192999306194e-05,
"loss": 3.7737,
"step": 396288
},
{
"epoch": 0.0,
"learning_rate": 4.350354404555142e-05,
"loss": 3.7761,
"step": 396800
},
{
"epoch": 0.01,
"learning_rate": 4.34951580980409e-05,
"loss": 3.777,
"step": 397312
},
{
"epoch": 0.01,
"learning_rate": 4.348677215053038e-05,
"loss": 3.7816,
"step": 397824
},
{
"epoch": 0.01,
"learning_rate": 4.347840258182359e-05,
"loss": 3.7854,
"step": 398336
},
{
"epoch": 0.01,
"learning_rate": 4.347001663431307e-05,
"loss": 3.7859,
"step": 398848
},
{
"epoch": 0.01,
"learning_rate": 4.346163068680255e-05,
"loss": 3.7728,
"step": 399360
},
{
"epoch": 0.01,
"learning_rate": 4.345324473929203e-05,
"loss": 3.7821,
"step": 399872
},
{
"epoch": 0.01,
"learning_rate": 4.344487517058524e-05,
"loss": 3.7768,
"step": 400384
},
{
"epoch": 0.01,
"learning_rate": 4.3436489223074726e-05,
"loss": 3.7763,
"step": 400896
},
{
"epoch": 0.01,
"learning_rate": 4.3428103275564206e-05,
"loss": 3.7634,
"step": 401408
},
{
"epoch": 0.01,
"learning_rate": 4.3419717328053685e-05,
"loss": 3.7709,
"step": 401920
},
{
"epoch": 0.01,
"learning_rate": 4.3411347759346895e-05,
"loss": 3.7722,
"step": 402432
},
{
"epoch": 0.01,
"learning_rate": 4.3402961811836375e-05,
"loss": 3.7797,
"step": 402944
},
{
"epoch": 0.01,
"learning_rate": 4.3394575864325854e-05,
"loss": 3.7691,
"step": 403456
},
{
"epoch": 0.01,
"learning_rate": 4.3386189916815334e-05,
"loss": 3.771,
"step": 403968
},
{
"epoch": 0.01,
"learning_rate": 4.3377820348108544e-05,
"loss": 3.7868,
"step": 404480
},
{
"epoch": 0.01,
"learning_rate": 4.3369434400598024e-05,
"loss": 3.7749,
"step": 404992
},
{
"epoch": 0.01,
"learning_rate": 4.3361048453087503e-05,
"loss": 3.7769,
"step": 405504
},
{
"epoch": 0.01,
"learning_rate": 4.3352662505576983e-05,
"loss": 3.7696,
"step": 406016
},
{
"epoch": 0.01,
"learning_rate": 4.334429293687019e-05,
"loss": 3.7554,
"step": 406528
},
{
"epoch": 0.01,
"learning_rate": 4.333590698935968e-05,
"loss": 3.7761,
"step": 407040
},
{
"epoch": 0.01,
"learning_rate": 4.332752104184916e-05,
"loss": 3.775,
"step": 407552
},
{
"epoch": 0.01,
"learning_rate": 4.331915147314237e-05,
"loss": 3.7645,
"step": 408064
},
{
"epoch": 0.01,
"learning_rate": 4.331076552563185e-05,
"loss": 3.7679,
"step": 408576
},
{
"epoch": 0.01,
"learning_rate": 4.330239595692506e-05,
"loss": 3.7773,
"step": 409088
},
{
"epoch": 0.01,
"learning_rate": 4.329401000941454e-05,
"loss": 3.7475,
"step": 409600
},
{
"epoch": 0.01,
"learning_rate": 4.328562406190402e-05,
"loss": 3.7771,
"step": 410112
},
{
"epoch": 0.01,
"learning_rate": 4.32772381143935e-05,
"loss": 3.7592,
"step": 410624
},
{
"epoch": 0.01,
"learning_rate": 4.326885216688298e-05,
"loss": 3.7669,
"step": 411136
},
{
"epoch": 0.01,
"learning_rate": 4.326046621937246e-05,
"loss": 3.775,
"step": 411648
},
{
"epoch": 0.01,
"learning_rate": 4.325208027186194e-05,
"loss": 3.7645,
"step": 412160
},
{
"epoch": 0.01,
"learning_rate": 4.324369432435142e-05,
"loss": 3.7627,
"step": 412672
},
{
"epoch": 0.01,
"learning_rate": 4.3235324755644626e-05,
"loss": 3.7691,
"step": 413184
},
{
"epoch": 0.01,
"learning_rate": 4.322693880813411e-05,
"loss": 3.7588,
"step": 413696
},
{
"epoch": 0.01,
"learning_rate": 4.321855286062359e-05,
"loss": 3.7566,
"step": 414208
},
{
"epoch": 0.01,
"learning_rate": 4.321016691311307e-05,
"loss": 3.7669,
"step": 414720
},
{
"epoch": 0.01,
"learning_rate": 4.320179734440628e-05,
"loss": 3.7648,
"step": 415232
},
{
"epoch": 0.01,
"learning_rate": 4.319341139689576e-05,
"loss": 3.7607,
"step": 415744
},
{
"epoch": 0.01,
"learning_rate": 4.318502544938524e-05,
"loss": 3.753,
"step": 416256
},
{
"epoch": 0.01,
"learning_rate": 4.317663950187472e-05,
"loss": 3.754,
"step": 416768
},
{
"epoch": 0.01,
"learning_rate": 4.316826993316793e-05,
"loss": 3.7629,
"step": 417280
},
{
"epoch": 0.01,
"learning_rate": 4.315988398565741e-05,
"loss": 3.7742,
"step": 417792
},
{
"epoch": 0.01,
"learning_rate": 4.315149803814689e-05,
"loss": 3.7601,
"step": 418304
},
{
"epoch": 0.01,
"learning_rate": 4.314311209063637e-05,
"loss": 3.7771,
"step": 418816
},
{
"epoch": 0.01,
"learning_rate": 4.313474252192958e-05,
"loss": 3.7746,
"step": 419328
},
{
"epoch": 0.01,
"learning_rate": 4.3126356574419067e-05,
"loss": 3.7643,
"step": 419840
},
{
"epoch": 0.01,
"learning_rate": 4.3117970626908546e-05,
"loss": 3.7583,
"step": 420352
},
{
"epoch": 0.01,
"learning_rate": 4.3109584679398026e-05,
"loss": 3.7723,
"step": 420864
},
{
"epoch": 0.01,
"learning_rate": 4.3101215110691236e-05,
"loss": 3.7624,
"step": 421376
},
{
"epoch": 0.01,
"learning_rate": 4.3092845541984445e-05,
"loss": 3.7586,
"step": 421888
},
{
"epoch": 0.01,
"learning_rate": 4.3084459594473925e-05,
"loss": 3.771,
"step": 422400
},
{
"epoch": 0.01,
"learning_rate": 4.3076073646963405e-05,
"loss": 3.7655,
"step": 422912
},
{
"epoch": 0.01,
"learning_rate": 4.3067687699452885e-05,
"loss": 3.7698,
"step": 423424
},
{
"epoch": 0.01,
"learning_rate": 4.3059301751942364e-05,
"loss": 3.7641,
"step": 423936
},
{
"epoch": 0.01,
"learning_rate": 4.3050915804431844e-05,
"loss": 3.7507,
"step": 424448
},
{
"epoch": 0.01,
"learning_rate": 4.3042529856921324e-05,
"loss": 3.7447,
"step": 424960
},
{
"epoch": 0.01,
"learning_rate": 4.3034143909410804e-05,
"loss": 3.7611,
"step": 425472
},
{
"epoch": 0.01,
"learning_rate": 4.302577434070402e-05,
"loss": 3.7659,
"step": 425984
},
{
"epoch": 0.01,
"learning_rate": 4.30173883931935e-05,
"loss": 3.757,
"step": 426496
},
{
"epoch": 0.01,
"learning_rate": 4.300900244568298e-05,
"loss": 3.7577,
"step": 427008
},
{
"epoch": 0.02,
"learning_rate": 4.300061649817245e-05,
"loss": 3.7589,
"step": 427520
},
{
"epoch": 0.02,
"learning_rate": 4.299224692946567e-05,
"loss": 3.751,
"step": 428032
},
{
"epoch": 0.02,
"learning_rate": 4.298386098195515e-05,
"loss": 3.763,
"step": 428544
},
{
"epoch": 0.02,
"learning_rate": 4.297547503444463e-05,
"loss": 3.7563,
"step": 429056
},
{
"epoch": 0.02,
"learning_rate": 4.29670890869341e-05,
"loss": 3.7683,
"step": 429568
},
{
"epoch": 0.02,
"learning_rate": 4.295871951822732e-05,
"loss": 3.7725,
"step": 430080
},
{
"epoch": 0.02,
"learning_rate": 4.29503335707168e-05,
"loss": 3.7631,
"step": 430592
},
{
"epoch": 0.02,
"learning_rate": 4.294194762320628e-05,
"loss": 3.755,
"step": 431104
},
{
"epoch": 0.02,
"learning_rate": 4.293356167569576e-05,
"loss": 3.759,
"step": 431616
},
{
"epoch": 0.02,
"learning_rate": 4.2925192106988974e-05,
"loss": 3.7565,
"step": 432128
},
{
"epoch": 0.02,
"learning_rate": 4.2916806159478454e-05,
"loss": 3.77,
"step": 432640
},
{
"epoch": 0.02,
"learning_rate": 4.290842021196793e-05,
"loss": 3.7534,
"step": 433152
},
{
"epoch": 0.02,
"learning_rate": 4.290003426445741e-05,
"loss": 3.7522,
"step": 433664
},
{
"epoch": 0.02,
"learning_rate": 4.289166469575062e-05,
"loss": 3.7654,
"step": 434176
},
{
"epoch": 0.02,
"learning_rate": 4.28832787482401e-05,
"loss": 3.7595,
"step": 434688
},
{
"epoch": 0.02,
"learning_rate": 4.2874892800729576e-05,
"loss": 3.755,
"step": 435200
},
{
"epoch": 0.02,
"learning_rate": 4.2866506853219056e-05,
"loss": 3.7558,
"step": 435712
},
{
"epoch": 0.02,
"learning_rate": 4.285813728451227e-05,
"loss": 3.7534,
"step": 436224
},
{
"epoch": 0.02,
"learning_rate": 4.284975133700175e-05,
"loss": 3.7503,
"step": 436736
},
{
"epoch": 0.02,
"learning_rate": 4.284138176829496e-05,
"loss": 3.7413,
"step": 437248
},
{
"epoch": 0.02,
"learning_rate": 4.283299582078444e-05,
"loss": 3.7595,
"step": 437760
},
{
"epoch": 0.02,
"learning_rate": 4.282460987327393e-05,
"loss": 3.757,
"step": 438272
},
{
"epoch": 0.02,
"learning_rate": 4.28162239257634e-05,
"loss": 3.7538,
"step": 438784
},
{
"epoch": 0.02,
"learning_rate": 4.280783797825288e-05,
"loss": 3.7517,
"step": 439296
},
{
"epoch": 0.02,
"learning_rate": 4.279945203074236e-05,
"loss": 3.7466,
"step": 439808
},
{
"epoch": 0.02,
"learning_rate": 4.279106608323184e-05,
"loss": 3.7695,
"step": 440320
},
{
"epoch": 0.02,
"learning_rate": 4.278268013572132e-05,
"loss": 3.7682,
"step": 440832
},
{
"epoch": 0.02,
"learning_rate": 4.277431056701453e-05,
"loss": 3.7613,
"step": 441344
},
{
"epoch": 0.02,
"learning_rate": 4.276592461950401e-05,
"loss": 3.7601,
"step": 441856
},
{
"epoch": 0.02,
"learning_rate": 4.275753867199349e-05,
"loss": 3.7498,
"step": 442368
},
{
"epoch": 0.02,
"learning_rate": 4.274915272448297e-05,
"loss": 3.7516,
"step": 442880
},
{
"epoch": 0.02,
"learning_rate": 4.274078315577618e-05,
"loss": 3.7457,
"step": 443392
},
{
"epoch": 0.02,
"learning_rate": 4.2732413587069394e-05,
"loss": 3.7498,
"step": 443904
},
{
"epoch": 0.02,
"learning_rate": 4.2724027639558874e-05,
"loss": 3.7545,
"step": 444416
},
{
"epoch": 0.02,
"learning_rate": 4.2715641692048354e-05,
"loss": 3.7532,
"step": 444928
},
{
"epoch": 0.02,
"learning_rate": 4.2707255744537834e-05,
"loss": 3.7543,
"step": 445440
},
{
"epoch": 0.02,
"learning_rate": 4.2698869797027314e-05,
"loss": 3.7517,
"step": 445952
},
{
"epoch": 0.02,
"learning_rate": 4.2690483849516794e-05,
"loss": 3.7522,
"step": 446464
},
{
"epoch": 0.02,
"learning_rate": 4.2682097902006274e-05,
"loss": 3.7487,
"step": 446976
},
{
"epoch": 0.02,
"learning_rate": 4.2673711954495754e-05,
"loss": 3.749,
"step": 447488
},
{
"epoch": 0.02,
"learning_rate": 4.266534238578896e-05,
"loss": 3.7541,
"step": 448000
},
{
"epoch": 0.02,
"learning_rate": 4.265695643827844e-05,
"loss": 3.7625,
"step": 448512
},
{
"epoch": 0.02,
"learning_rate": 4.264857049076792e-05,
"loss": 3.761,
"step": 449024
},
{
"epoch": 0.02,
"learning_rate": 4.26401845432574e-05,
"loss": 3.7473,
"step": 449536
},
{
"epoch": 0.02,
"learning_rate": 4.263181497455062e-05,
"loss": 3.7585,
"step": 450048
},
{
"epoch": 0.02,
"learning_rate": 4.26234290270401e-05,
"loss": 3.7532,
"step": 450560
},
{
"epoch": 0.02,
"learning_rate": 4.261504307952958e-05,
"loss": 3.759,
"step": 451072
},
{
"epoch": 0.02,
"learning_rate": 4.260665713201906e-05,
"loss": 3.753,
"step": 451584
},
{
"epoch": 0.02,
"learning_rate": 4.259828756331227e-05,
"loss": 3.7562,
"step": 452096
},
{
"epoch": 0.02,
"learning_rate": 4.258990161580175e-05,
"loss": 3.7523,
"step": 452608
},
{
"epoch": 0.02,
"learning_rate": 4.258151566829123e-05,
"loss": 3.7575,
"step": 453120
},
{
"epoch": 0.02,
"learning_rate": 4.257312972078071e-05,
"loss": 3.7436,
"step": 453632
},
{
"epoch": 0.02,
"learning_rate": 4.2564776530877646e-05,
"loss": 3.7517,
"step": 454144
},
{
"epoch": 0.02,
"learning_rate": 4.2556390583367126e-05,
"loss": 3.7498,
"step": 454656
},
{
"epoch": 0.02,
"learning_rate": 4.2548004635856606e-05,
"loss": 3.7529,
"step": 455168
},
{
"epoch": 0.02,
"learning_rate": 4.2539618688346086e-05,
"loss": 3.7544,
"step": 455680
},
{
"epoch": 0.02,
"learning_rate": 4.253123274083557e-05,
"loss": 3.7519,
"step": 456192
},
{
"epoch": 0.02,
"learning_rate": 4.252284679332505e-05,
"loss": 3.7603,
"step": 456704
},
{
"epoch": 0.02,
"learning_rate": 4.251446084581453e-05,
"loss": 3.7425,
"step": 457216
},
{
"epoch": 0.02,
"learning_rate": 4.250609127710774e-05,
"loss": 3.7513,
"step": 457728
},
{
"epoch": 0.03,
"eval_loss": 3.8687496185302734,
"eval_runtime": 310.0094,
"eval_samples_per_second": 1230.902,
"eval_steps_per_second": 38.467,
"step": 457920
},
{
"epoch": 1.0,
"learning_rate": 4.249770532959722e-05,
"loss": 3.7488,
"step": 458240
},
{
"epoch": 1.0,
"learning_rate": 4.248933576089043e-05,
"loss": 3.7293,
"step": 458752
},
{
"epoch": 1.0,
"learning_rate": 4.248094981337991e-05,
"loss": 3.7597,
"step": 459264
},
{
"epoch": 1.0,
"learning_rate": 4.247256386586939e-05,
"loss": 3.75,
"step": 459776
},
{
"epoch": 1.0,
"learning_rate": 4.246417791835887e-05,
"loss": 3.7586,
"step": 460288
},
{
"epoch": 1.0,
"learning_rate": 4.245580834965208e-05,
"loss": 3.7413,
"step": 460800
},
{
"epoch": 1.0,
"learning_rate": 4.244742240214156e-05,
"loss": 3.7407,
"step": 461312
},
{
"epoch": 1.0,
"learning_rate": 4.243903645463104e-05,
"loss": 3.7393,
"step": 461824
},
{
"epoch": 1.0,
"learning_rate": 4.243065050712052e-05,
"loss": 3.7441,
"step": 462336
},
{
"epoch": 1.0,
"learning_rate": 4.2422264559610006e-05,
"loss": 3.7429,
"step": 462848
},
{
"epoch": 1.0,
"learning_rate": 4.2413878612099486e-05,
"loss": 3.7523,
"step": 463360
},
{
"epoch": 1.0,
"learning_rate": 4.2405492664588966e-05,
"loss": 3.754,
"step": 463872
},
{
"epoch": 1.0,
"learning_rate": 4.2397123095882175e-05,
"loss": 3.7306,
"step": 464384
},
{
"epoch": 1.0,
"learning_rate": 4.2388737148371655e-05,
"loss": 3.7397,
"step": 464896
},
{
"epoch": 1.0,
"learning_rate": 4.2380351200861135e-05,
"loss": 3.7471,
"step": 465408
},
{
"epoch": 1.0,
"learning_rate": 4.2371965253350615e-05,
"loss": 3.7319,
"step": 465920
},
{
"epoch": 1.0,
"learning_rate": 4.2363579305840095e-05,
"loss": 3.7379,
"step": 466432
},
{
"epoch": 1.0,
"learning_rate": 4.2355193358329575e-05,
"loss": 3.7385,
"step": 466944
},
{
"epoch": 1.0,
"learning_rate": 4.2346807410819055e-05,
"loss": 3.7389,
"step": 467456
},
{
"epoch": 1.0,
"learning_rate": 4.233842146330853e-05,
"loss": 3.7558,
"step": 467968
},
{
"epoch": 1.0,
"learning_rate": 4.2330051894601744e-05,
"loss": 3.7423,
"step": 468480
},
{
"epoch": 1.0,
"learning_rate": 4.2321665947091224e-05,
"loss": 3.7427,
"step": 468992
},
{
"epoch": 1.0,
"learning_rate": 4.2313279999580704e-05,
"loss": 3.7403,
"step": 469504
},
{
"epoch": 1.0,
"learning_rate": 4.2304894052070184e-05,
"loss": 3.746,
"step": 470016
},
{
"epoch": 1.0,
"learning_rate": 4.22965244833634e-05,
"loss": 3.7356,
"step": 470528
},
{
"epoch": 1.0,
"learning_rate": 4.228813853585288e-05,
"loss": 3.7425,
"step": 471040
},
{
"epoch": 1.0,
"learning_rate": 4.227975258834236e-05,
"loss": 3.7341,
"step": 471552
},
{
"epoch": 1.0,
"learning_rate": 4.227136664083183e-05,
"loss": 3.7326,
"step": 472064
},
{
"epoch": 1.0,
"learning_rate": 4.226299707212505e-05,
"loss": 3.735,
"step": 472576
},
{
"epoch": 1.0,
"learning_rate": 4.225461112461453e-05,
"loss": 3.7342,
"step": 473088
},
{
"epoch": 1.01,
"learning_rate": 4.2246225177104e-05,
"loss": 3.7386,
"step": 473600
},
{
"epoch": 1.01,
"learning_rate": 4.223783922959348e-05,
"loss": 3.7394,
"step": 474112
},
{
"epoch": 1.01,
"learning_rate": 4.22294696608867e-05,
"loss": 3.747,
"step": 474624
},
{
"epoch": 1.01,
"learning_rate": 4.222108371337618e-05,
"loss": 3.7465,
"step": 475136
},
{
"epoch": 1.01,
"learning_rate": 4.221269776586566e-05,
"loss": 3.7313,
"step": 475648
},
{
"epoch": 1.01,
"learning_rate": 4.2204328197158874e-05,
"loss": 3.741,
"step": 476160
},
{
"epoch": 1.01,
"learning_rate": 4.2195942249648353e-05,
"loss": 3.7395,
"step": 476672
},
{
"epoch": 1.01,
"learning_rate": 4.2187556302137833e-05,
"loss": 3.7331,
"step": 477184
},
{
"epoch": 1.01,
"learning_rate": 4.217917035462731e-05,
"loss": 3.7223,
"step": 477696
},
{
"epoch": 1.01,
"learning_rate": 4.217081716472425e-05,
"loss": 3.7306,
"step": 478208
},
{
"epoch": 1.01,
"learning_rate": 4.216243121721373e-05,
"loss": 3.7342,
"step": 478720
},
{
"epoch": 1.01,
"learning_rate": 4.215404526970321e-05,
"loss": 3.7394,
"step": 479232
},
{
"epoch": 1.01,
"learning_rate": 4.214565932219269e-05,
"loss": 3.7304,
"step": 479744
},
{
"epoch": 1.01,
"learning_rate": 4.213727337468217e-05,
"loss": 3.731,
"step": 480256
},
{
"epoch": 1.01,
"learning_rate": 4.212888742717165e-05,
"loss": 3.7497,
"step": 480768
},
{
"epoch": 1.01,
"learning_rate": 4.212050147966113e-05,
"loss": 3.7344,
"step": 481280
},
{
"epoch": 1.01,
"learning_rate": 4.211211553215061e-05,
"loss": 3.7391,
"step": 481792
},
{
"epoch": 1.01,
"learning_rate": 4.210374596344383e-05,
"loss": 3.7257,
"step": 482304
},
{
"epoch": 1.01,
"learning_rate": 4.209536001593331e-05,
"loss": 3.7174,
"step": 482816
},
{
"epoch": 1.01,
"learning_rate": 4.2086990447226516e-05,
"loss": 3.741,
"step": 483328
},
{
"epoch": 1.01,
"learning_rate": 4.2078604499715996e-05,
"loss": 3.7315,
"step": 483840
},
{
"epoch": 1.01,
"learning_rate": 4.2070218552205476e-05,
"loss": 3.7273,
"step": 484352
},
{
"epoch": 1.01,
"learning_rate": 4.206183260469495e-05,
"loss": 3.7291,
"step": 484864
},
{
"epoch": 1.01,
"learning_rate": 4.205344665718443e-05,
"loss": 3.7353,
"step": 485376
},
{
"epoch": 1.01,
"learning_rate": 4.204506070967391e-05,
"loss": 3.7106,
"step": 485888
},
{
"epoch": 1.01,
"learning_rate": 4.2036691140967125e-05,
"loss": 3.7321,
"step": 486400
},
{
"epoch": 1.01,
"learning_rate": 4.2028305193456605e-05,
"loss": 3.7229,
"step": 486912
},
{
"epoch": 1.01,
"learning_rate": 4.2019919245946085e-05,
"loss": 3.7209,
"step": 487424
},
{
"epoch": 1.01,
"learning_rate": 4.2011533298435565e-05,
"loss": 3.7409,
"step": 487936
},
{
"epoch": 1.01,
"learning_rate": 4.2003147350925045e-05,
"loss": 3.725,
"step": 488448
},
{
"epoch": 1.01,
"learning_rate": 4.1994761403414525e-05,
"loss": 3.7227,
"step": 488960
},
{
"epoch": 1.01,
"learning_rate": 4.1986375455904005e-05,
"loss": 3.7304,
"step": 489472
},
{
"epoch": 1.01,
"learning_rate": 4.1977989508393485e-05,
"loss": 3.7212,
"step": 489984
},
{
"epoch": 1.01,
"learning_rate": 4.1969619939686694e-05,
"loss": 3.7196,
"step": 490496
},
{
"epoch": 1.01,
"learning_rate": 4.1961233992176174e-05,
"loss": 3.7259,
"step": 491008
},
{
"epoch": 1.01,
"learning_rate": 4.195286442346938e-05,
"loss": 3.7244,
"step": 491520
},
{
"epoch": 1.01,
"learning_rate": 4.194447847595886e-05,
"loss": 3.7262,
"step": 492032
},
{
"epoch": 1.01,
"learning_rate": 4.193609252844834e-05,
"loss": 3.7171,
"step": 492544
},
{
"epoch": 1.01,
"learning_rate": 4.192770658093782e-05,
"loss": 3.709,
"step": 493056
},
{
"epoch": 1.01,
"learning_rate": 4.19193206334273e-05,
"loss": 3.7228,
"step": 493568
},
{
"epoch": 1.01,
"learning_rate": 4.191093468591679e-05,
"loss": 3.7368,
"step": 494080
},
{
"epoch": 1.01,
"learning_rate": 4.190254873840627e-05,
"loss": 3.7203,
"step": 494592
},
{
"epoch": 1.01,
"learning_rate": 4.189416279089575e-05,
"loss": 3.741,
"step": 495104
},
{
"epoch": 1.01,
"learning_rate": 4.188579322218896e-05,
"loss": 3.7347,
"step": 495616
},
{
"epoch": 1.01,
"learning_rate": 4.187740727467844e-05,
"loss": 3.7305,
"step": 496128
},
{
"epoch": 1.01,
"learning_rate": 4.186902132716792e-05,
"loss": 3.7153,
"step": 496640
},
{
"epoch": 1.01,
"learning_rate": 4.186065175846113e-05,
"loss": 3.7351,
"step": 497152
},
{
"epoch": 1.01,
"learning_rate": 4.185226581095061e-05,
"loss": 3.7245,
"step": 497664
},
{
"epoch": 1.01,
"learning_rate": 4.184387986344009e-05,
"loss": 3.7205,
"step": 498176
},
{
"epoch": 1.01,
"learning_rate": 4.183549391592957e-05,
"loss": 3.7352,
"step": 498688
},
{
"epoch": 1.01,
"learning_rate": 4.182710796841905e-05,
"loss": 3.7274,
"step": 499200
},
{
"epoch": 1.01,
"learning_rate": 4.181872202090853e-05,
"loss": 3.7326,
"step": 499712
},
{
"epoch": 1.01,
"learning_rate": 4.181033607339801e-05,
"loss": 3.7275,
"step": 500224
},
{
"epoch": 1.01,
"learning_rate": 4.180195012588749e-05,
"loss": 3.7111,
"step": 500736
},
{
"epoch": 1.01,
"learning_rate": 4.17935805571807e-05,
"loss": 3.7093,
"step": 501248
},
{
"epoch": 1.01,
"learning_rate": 4.178519460967018e-05,
"loss": 3.7198,
"step": 501760
},
{
"epoch": 1.01,
"learning_rate": 4.177682504096339e-05,
"loss": 3.7286,
"step": 502272
},
{
"epoch": 1.01,
"learning_rate": 4.176843909345287e-05,
"loss": 3.7216,
"step": 502784
},
{
"epoch": 1.01,
"learning_rate": 4.176005314594235e-05,
"loss": 3.7163,
"step": 503296
},
{
"epoch": 1.02,
"learning_rate": 4.175166719843183e-05,
"loss": 3.7241,
"step": 503808
},
{
"epoch": 1.02,
"learning_rate": 4.174329762972504e-05,
"loss": 3.7137,
"step": 504320
},
{
"epoch": 1.02,
"learning_rate": 4.173491168221452e-05,
"loss": 3.7213,
"step": 504832
},
{
"epoch": 1.02,
"learning_rate": 4.1726525734704e-05,
"loss": 3.7171,
"step": 505344
},
{
"epoch": 1.02,
"learning_rate": 4.171813978719348e-05,
"loss": 3.735,
"step": 505856
},
{
"epoch": 1.02,
"learning_rate": 4.170975383968296e-05,
"loss": 3.7356,
"step": 506368
},
{
"epoch": 1.02,
"learning_rate": 4.170136789217244e-05,
"loss": 3.7243,
"step": 506880
},
{
"epoch": 1.02,
"learning_rate": 4.169298194466192e-05,
"loss": 3.7168,
"step": 507392
},
{
"epoch": 1.02,
"learning_rate": 4.16845959971514e-05,
"loss": 3.7246,
"step": 507904
},
{
"epoch": 1.02,
"learning_rate": 4.167622642844461e-05,
"loss": 3.7159,
"step": 508416
},
{
"epoch": 1.02,
"learning_rate": 4.166784048093409e-05,
"loss": 3.7347,
"step": 508928
},
{
"epoch": 1.02,
"learning_rate": 4.165945453342357e-05,
"loss": 3.7155,
"step": 509440
},
{
"epoch": 1.02,
"learning_rate": 4.165106858591305e-05,
"loss": 3.719,
"step": 509952
},
{
"epoch": 1.02,
"learning_rate": 4.164269901720626e-05,
"loss": 3.7243,
"step": 510464
},
{
"epoch": 1.02,
"learning_rate": 4.163431306969574e-05,
"loss": 3.7264,
"step": 510976
},
{
"epoch": 1.02,
"learning_rate": 4.162592712218522e-05,
"loss": 3.7135,
"step": 511488
},
{
"epoch": 1.02,
"learning_rate": 4.16175411746747e-05,
"loss": 3.7207,
"step": 512000
},
{
"epoch": 1.02,
"learning_rate": 4.1609171605967915e-05,
"loss": 3.7156,
"step": 512512
},
{
"epoch": 1.02,
"learning_rate": 4.1600785658457395e-05,
"loss": 3.7113,
"step": 513024
},
{
"epoch": 1.02,
"learning_rate": 4.159241608975061e-05,
"loss": 3.7059,
"step": 513536
},
{
"epoch": 1.02,
"learning_rate": 4.1584030142240084e-05,
"loss": 3.7203,
"step": 514048
},
{
"epoch": 1.02,
"learning_rate": 4.1575644194729564e-05,
"loss": 3.7212,
"step": 514560
},
{
"epoch": 1.02,
"learning_rate": 4.1567258247219044e-05,
"loss": 3.7138,
"step": 515072
},
{
"epoch": 1.02,
"learning_rate": 4.1558872299708523e-05,
"loss": 3.718,
"step": 515584
},
{
"epoch": 1.02,
"learning_rate": 4.1550486352198003e-05,
"loss": 3.7121,
"step": 516096
},
{
"epoch": 1.02,
"learning_rate": 4.154211678349121e-05,
"loss": 3.7287,
"step": 516608
},
{
"epoch": 1.02,
"learning_rate": 4.153373083598069e-05,
"loss": 3.734,
"step": 517120
},
{
"epoch": 1.02,
"learning_rate": 4.152534488847017e-05,
"loss": 3.7258,
"step": 517632
},
{
"epoch": 1.02,
"learning_rate": 4.151695894095965e-05,
"loss": 3.722,
"step": 518144
},
{
"epoch": 1.02,
"learning_rate": 4.150857299344913e-05,
"loss": 3.7118,
"step": 518656
},
{
"epoch": 1.02,
"learning_rate": 4.150020342474235e-05,
"loss": 3.7185,
"step": 519168
},
{
"epoch": 1.02,
"learning_rate": 4.149181747723183e-05,
"loss": 3.705,
"step": 519680
},
{
"epoch": 1.02,
"learning_rate": 4.148343152972131e-05,
"loss": 3.7156,
"step": 520192
},
{
"epoch": 1.02,
"learning_rate": 4.147504558221079e-05,
"loss": 3.7165,
"step": 520704
},
{
"epoch": 1.02,
"learning_rate": 4.146665963470027e-05,
"loss": 3.7155,
"step": 521216
},
{
"epoch": 1.02,
"learning_rate": 4.145827368718975e-05,
"loss": 3.7194,
"step": 521728
},
{
"epoch": 1.02,
"learning_rate": 4.144990411848296e-05,
"loss": 3.7155,
"step": 522240
},
{
"epoch": 1.02,
"learning_rate": 4.144151817097244e-05,
"loss": 3.7199,
"step": 522752
},
{
"epoch": 1.02,
"learning_rate": 4.143313222346192e-05,
"loss": 3.7124,
"step": 523264
},
{
"epoch": 1.02,
"learning_rate": 4.14247462759514e-05,
"loss": 3.7149,
"step": 523776
},
{
"epoch": 1.02,
"learning_rate": 4.141636032844088e-05,
"loss": 3.7176,
"step": 524288
},
{
"epoch": 1.02,
"learning_rate": 4.140797438093036e-05,
"loss": 3.722,
"step": 524800
},
{
"epoch": 1.02,
"learning_rate": 4.139958843341984e-05,
"loss": 3.7285,
"step": 525312
},
{
"epoch": 1.02,
"learning_rate": 4.139120248590932e-05,
"loss": 3.7107,
"step": 525824
},
{
"epoch": 1.02,
"learning_rate": 4.138283291720253e-05,
"loss": 3.7237,
"step": 526336
},
{
"epoch": 1.02,
"learning_rate": 4.137444696969201e-05,
"loss": 3.7183,
"step": 526848
},
{
"epoch": 1.02,
"learning_rate": 4.136606102218149e-05,
"loss": 3.7228,
"step": 527360
},
{
"epoch": 1.02,
"learning_rate": 4.13576914534747e-05,
"loss": 3.7165,
"step": 527872
},
{
"epoch": 1.02,
"learning_rate": 4.134930550596418e-05,
"loss": 3.722,
"step": 528384
},
{
"epoch": 1.02,
"learning_rate": 4.134091955845366e-05,
"loss": 3.7117,
"step": 528896
},
{
"epoch": 1.02,
"learning_rate": 4.133253361094314e-05,
"loss": 3.725,
"step": 529408
},
{
"epoch": 1.02,
"learning_rate": 4.132416404223635e-05,
"loss": 3.7055,
"step": 529920
},
{
"epoch": 1.02,
"learning_rate": 4.131579447352956e-05,
"loss": 3.7154,
"step": 530432
},
{
"epoch": 1.02,
"learning_rate": 4.130740852601904e-05,
"loss": 3.7141,
"step": 530944
},
{
"epoch": 1.02,
"learning_rate": 4.129902257850852e-05,
"loss": 3.7176,
"step": 531456
},
{
"epoch": 1.02,
"learning_rate": 4.1290636630998006e-05,
"loss": 3.7147,
"step": 531968
},
{
"epoch": 1.02,
"learning_rate": 4.1282250683487486e-05,
"loss": 3.7192,
"step": 532480
},
{
"epoch": 1.02,
"learning_rate": 4.1273881114780695e-05,
"loss": 3.7222,
"step": 532992
},
{
"epoch": 1.02,
"learning_rate": 4.1265495167270175e-05,
"loss": 3.7067,
"step": 533504
},
{
"epoch": 1.02,
"learning_rate": 4.1257109219759655e-05,
"loss": 3.722,
"step": 534016
},
{
"epoch": 1.03,
"eval_loss": 3.8589980602264404,
"eval_runtime": 310.3836,
"eval_samples_per_second": 1229.417,
"eval_steps_per_second": 38.42,
"step": 534240
},
{
"epoch": 0.0,
"learning_rate": 4.1248723272249135e-05,
"loss": 3.7093,
"step": 534528
},
{
"epoch": 0.0,
"learning_rate": 4.1240337324738615e-05,
"loss": 3.6977,
"step": 535040
},
{
"epoch": 0.0,
"learning_rate": 4.1231951377228095e-05,
"loss": 3.7189,
"step": 535552
},
{
"epoch": 0.0,
"learning_rate": 4.122356542971757e-05,
"loss": 3.7173,
"step": 536064
},
{
"epoch": 0.0,
"learning_rate": 4.121517948220705e-05,
"loss": 3.7199,
"step": 536576
},
{
"epoch": 0.0,
"learning_rate": 4.1206809913500264e-05,
"loss": 3.7075,
"step": 537088
},
{
"epoch": 0.0,
"learning_rate": 4.1198423965989744e-05,
"loss": 3.7079,
"step": 537600
},
{
"epoch": 0.0,
"learning_rate": 4.1190038018479224e-05,
"loss": 3.7052,
"step": 538112
},
{
"epoch": 0.0,
"learning_rate": 4.1181652070968704e-05,
"loss": 3.7096,
"step": 538624
},
{
"epoch": 0.0,
"learning_rate": 4.1173266123458184e-05,
"loss": 3.7045,
"step": 539136
},
{
"epoch": 0.0,
"learning_rate": 4.116489655475139e-05,
"loss": 3.7181,
"step": 539648
},
{
"epoch": 0.0,
"learning_rate": 4.115651060724087e-05,
"loss": 3.7156,
"step": 540160
},
{
"epoch": 0.0,
"learning_rate": 4.114814103853409e-05,
"loss": 3.7042,
"step": 540672
},
{
"epoch": 0.0,
"learning_rate": 4.113975509102357e-05,
"loss": 3.7003,
"step": 541184
},
{
"epoch": 0.0,
"learning_rate": 4.113136914351304e-05,
"loss": 3.7129,
"step": 541696
},
{
"epoch": 0.0,
"learning_rate": 4.112298319600252e-05,
"loss": 3.6944,
"step": 542208
},
{
"epoch": 0.0,
"learning_rate": 4.1114597248492e-05,
"loss": 3.7065,
"step": 542720
},
{
"epoch": 0.0,
"learning_rate": 4.110621130098148e-05,
"loss": 3.7052,
"step": 543232
},
{
"epoch": 0.0,
"learning_rate": 4.109782535347096e-05,
"loss": 3.7061,
"step": 543744
},
{
"epoch": 0.0,
"learning_rate": 4.108943940596044e-05,
"loss": 3.7164,
"step": 544256
},
{
"epoch": 0.0,
"learning_rate": 4.108105345844992e-05,
"loss": 3.7115,
"step": 544768
},
{
"epoch": 0.0,
"learning_rate": 4.107266751093941e-05,
"loss": 3.7064,
"step": 545280
},
{
"epoch": 0.0,
"learning_rate": 4.106428156342889e-05,
"loss": 3.7051,
"step": 545792
},
{
"epoch": 0.0,
"learning_rate": 4.105589561591837e-05,
"loss": 3.7087,
"step": 546304
},
{
"epoch": 0.0,
"learning_rate": 4.104752604721158e-05,
"loss": 3.6999,
"step": 546816
},
{
"epoch": 0.0,
"learning_rate": 4.103914009970106e-05,
"loss": 3.7105,
"step": 547328
},
{
"epoch": 0.0,
"learning_rate": 4.103075415219054e-05,
"loss": 3.7027,
"step": 547840
},
{
"epoch": 0.0,
"learning_rate": 4.102236820468002e-05,
"loss": 3.6972,
"step": 548352
},
{
"epoch": 0.0,
"learning_rate": 4.1013998635973227e-05,
"loss": 3.6997,
"step": 548864
},
{
"epoch": 0.0,
"learning_rate": 4.1005612688462706e-05,
"loss": 3.7046,
"step": 549376
},
{
"epoch": 0.01,
"learning_rate": 4.0997243119755916e-05,
"loss": 3.6985,
"step": 549888
},
{
"epoch": 0.01,
"learning_rate": 4.0988857172245396e-05,
"loss": 3.709,
"step": 550400
},
{
"epoch": 0.01,
"learning_rate": 4.0980471224734875e-05,
"loss": 3.7144,
"step": 550912
},
{
"epoch": 0.01,
"learning_rate": 4.097208527722436e-05,
"loss": 3.7094,
"step": 551424
},
{
"epoch": 0.01,
"learning_rate": 4.096369932971384e-05,
"loss": 3.6953,
"step": 551936
},
{
"epoch": 0.01,
"learning_rate": 4.095532976100705e-05,
"loss": 3.7074,
"step": 552448
},
{
"epoch": 0.01,
"learning_rate": 4.094694381349653e-05,
"loss": 3.7081,
"step": 552960
},
{
"epoch": 0.01,
"learning_rate": 4.093855786598601e-05,
"loss": 3.6987,
"step": 553472
},
{
"epoch": 0.01,
"learning_rate": 4.093017191847549e-05,
"loss": 3.6898,
"step": 553984
},
{
"epoch": 0.01,
"learning_rate": 4.092178597096497e-05,
"loss": 3.6932,
"step": 554496
},
{
"epoch": 0.01,
"learning_rate": 4.091341640225818e-05,
"loss": 3.7018,
"step": 555008
},
{
"epoch": 0.01,
"learning_rate": 4.090503045474766e-05,
"loss": 3.7052,
"step": 555520
},
{
"epoch": 0.01,
"learning_rate": 4.089664450723714e-05,
"loss": 3.6934,
"step": 556032
},
{
"epoch": 0.01,
"learning_rate": 4.088825855972662e-05,
"loss": 3.6963,
"step": 556544
},
{
"epoch": 0.01,
"learning_rate": 4.08798726122161e-05,
"loss": 3.7152,
"step": 557056
},
{
"epoch": 0.01,
"learning_rate": 4.087148666470558e-05,
"loss": 3.7011,
"step": 557568
},
{
"epoch": 0.01,
"learning_rate": 4.086310071719506e-05,
"loss": 3.7066,
"step": 558080
},
{
"epoch": 0.01,
"learning_rate": 4.0854731148488276e-05,
"loss": 3.6943,
"step": 558592
},
{
"epoch": 0.01,
"learning_rate": 4.0846361579781485e-05,
"loss": 3.6812,
"step": 559104
},
{
"epoch": 0.01,
"learning_rate": 4.0837975632270965e-05,
"loss": 3.711,
"step": 559616
},
{
"epoch": 0.01,
"learning_rate": 4.0829589684760445e-05,
"loss": 3.6972,
"step": 560128
},
{
"epoch": 0.01,
"learning_rate": 4.0821203737249925e-05,
"loss": 3.6938,
"step": 560640
},
{
"epoch": 0.01,
"learning_rate": 4.0812817789739405e-05,
"loss": 3.7018,
"step": 561152
},
{
"epoch": 0.01,
"learning_rate": 4.0804448221032614e-05,
"loss": 3.6962,
"step": 561664
},
{
"epoch": 0.01,
"learning_rate": 4.0796062273522094e-05,
"loss": 3.6867,
"step": 562176
},
{
"epoch": 0.01,
"learning_rate": 4.0787676326011574e-05,
"loss": 3.6922,
"step": 562688
},
{
"epoch": 0.01,
"learning_rate": 4.0779290378501054e-05,
"loss": 3.6898,
"step": 563200
},
{
"epoch": 0.01,
"learning_rate": 4.0770904430990534e-05,
"loss": 3.694,
"step": 563712
},
{
"epoch": 0.01,
"learning_rate": 4.076253486228375e-05,
"loss": 3.7043,
"step": 564224
},
{
"epoch": 0.01,
"learning_rate": 4.075414891477323e-05,
"loss": 3.6926,
"step": 564736
},
{
"epoch": 0.01,
"learning_rate": 4.07457629672627e-05,
"loss": 3.6908,
"step": 565248
},
{
"epoch": 0.01,
"learning_rate": 4.073737701975218e-05,
"loss": 3.6997,
"step": 565760
},
{
"epoch": 0.01,
"learning_rate": 4.072899107224166e-05,
"loss": 3.6852,
"step": 566272
},
{
"epoch": 0.01,
"learning_rate": 4.072062150353488e-05,
"loss": 3.689,
"step": 566784
},
{
"epoch": 0.01,
"learning_rate": 4.071223555602435e-05,
"loss": 3.69,
"step": 567296
},
{
"epoch": 0.01,
"learning_rate": 4.070384960851383e-05,
"loss": 3.6948,
"step": 567808
},
{
"epoch": 0.01,
"learning_rate": 4.069546366100331e-05,
"loss": 3.6899,
"step": 568320
},
{
"epoch": 0.01,
"learning_rate": 4.068707771349279e-05,
"loss": 3.6892,
"step": 568832
},
{
"epoch": 0.01,
"learning_rate": 4.067869176598227e-05,
"loss": 3.6728,
"step": 569344
},
{
"epoch": 0.01,
"learning_rate": 4.067032219727549e-05,
"loss": 3.6908,
"step": 569856
},
{
"epoch": 0.01,
"learning_rate": 4.066193624976497e-05,
"loss": 3.7039,
"step": 570368
},
{
"epoch": 0.01,
"learning_rate": 4.065355030225445e-05,
"loss": 3.6861,
"step": 570880
},
{
"epoch": 0.01,
"learning_rate": 4.064516435474393e-05,
"loss": 3.7075,
"step": 571392
},
{
"epoch": 0.01,
"learning_rate": 4.063677840723341e-05,
"loss": 3.6981,
"step": 571904
},
{
"epoch": 0.01,
"learning_rate": 4.062839245972289e-05,
"loss": 3.7013,
"step": 572416
},
{
"epoch": 0.01,
"learning_rate": 4.062000651221237e-05,
"loss": 3.6855,
"step": 572928
},
{
"epoch": 0.01,
"learning_rate": 4.0611636943505576e-05,
"loss": 3.7009,
"step": 573440
},
{
"epoch": 0.01,
"learning_rate": 4.0603250995995056e-05,
"loss": 3.6927,
"step": 573952
},
{
"epoch": 0.01,
"learning_rate": 4.0594865048484536e-05,
"loss": 3.6875,
"step": 574464
},
{
"epoch": 0.01,
"learning_rate": 4.0586479100974016e-05,
"loss": 3.7031,
"step": 574976
},
{
"epoch": 0.01,
"learning_rate": 4.0578093153463496e-05,
"loss": 3.6932,
"step": 575488
},
{
"epoch": 0.01,
"learning_rate": 4.0569723584756705e-05,
"loss": 3.6998,
"step": 576000
},
{
"epoch": 0.01,
"learning_rate": 4.056133763724619e-05,
"loss": 3.6967,
"step": 576512
},
{
"epoch": 0.01,
"learning_rate": 4.055295168973567e-05,
"loss": 3.6733,
"step": 577024
},
{
"epoch": 0.01,
"learning_rate": 4.054456574222515e-05,
"loss": 3.6833,
"step": 577536
},
{
"epoch": 0.01,
"learning_rate": 4.053619617351836e-05,
"loss": 3.6838,
"step": 578048
},
{
"epoch": 0.01,
"learning_rate": 4.052781022600784e-05,
"loss": 3.6975,
"step": 578560
},
{
"epoch": 0.01,
"learning_rate": 4.051942427849732e-05,
"loss": 3.6912,
"step": 579072
},
{
"epoch": 0.01,
"learning_rate": 4.05110383309868e-05,
"loss": 3.6845,
"step": 579584
},
{
"epoch": 0.02,
"learning_rate": 4.050265238347628e-05,
"loss": 3.6886,
"step": 580096
},
{
"epoch": 0.02,
"learning_rate": 4.049428281476949e-05,
"loss": 3.6845,
"step": 580608
},
{
"epoch": 0.02,
"learning_rate": 4.048589686725897e-05,
"loss": 3.6873,
"step": 581120
},
{
"epoch": 0.02,
"learning_rate": 4.047751091974845e-05,
"loss": 3.6861,
"step": 581632
},
{
"epoch": 0.02,
"learning_rate": 4.046912497223793e-05,
"loss": 3.7027,
"step": 582144
},
{
"epoch": 0.02,
"learning_rate": 4.046073902472741e-05,
"loss": 3.7086,
"step": 582656
},
{
"epoch": 0.02,
"learning_rate": 4.0452369456020625e-05,
"loss": 3.6883,
"step": 583168
},
{
"epoch": 0.02,
"learning_rate": 4.0443983508510105e-05,
"loss": 3.6854,
"step": 583680
},
{
"epoch": 0.02,
"learning_rate": 4.0435597560999585e-05,
"loss": 3.6937,
"step": 584192
},
{
"epoch": 0.02,
"learning_rate": 4.0427211613489065e-05,
"loss": 3.6849,
"step": 584704
},
{
"epoch": 0.02,
"learning_rate": 4.0418842044782274e-05,
"loss": 3.7009,
"step": 585216
},
{
"epoch": 0.02,
"learning_rate": 4.0410456097271754e-05,
"loss": 3.6869,
"step": 585728
},
{
"epoch": 0.02,
"learning_rate": 4.0402070149761234e-05,
"loss": 3.6884,
"step": 586240
},
{
"epoch": 0.02,
"learning_rate": 4.039368420225071e-05,
"loss": 3.6935,
"step": 586752
},
{
"epoch": 0.02,
"learning_rate": 4.038529825474019e-05,
"loss": 3.6951,
"step": 587264
},
{
"epoch": 0.02,
"learning_rate": 4.037691230722967e-05,
"loss": 3.6812,
"step": 587776
},
{
"epoch": 0.02,
"learning_rate": 4.036852635971915e-05,
"loss": 3.6883,
"step": 588288
},
{
"epoch": 0.02,
"learning_rate": 4.036015679101236e-05,
"loss": 3.6865,
"step": 588800
},
{
"epoch": 0.02,
"learning_rate": 4.035177084350184e-05,
"loss": 3.6797,
"step": 589312
},
{
"epoch": 0.02,
"learning_rate": 4.034338489599132e-05,
"loss": 3.6773,
"step": 589824
},
{
"epoch": 0.02,
"learning_rate": 4.033501532728454e-05,
"loss": 3.6881,
"step": 590336
},
{
"epoch": 0.02,
"learning_rate": 4.032662937977401e-05,
"loss": 3.6891,
"step": 590848
},
{
"epoch": 0.02,
"learning_rate": 4.031824343226349e-05,
"loss": 3.6839,
"step": 591360
},
{
"epoch": 0.02,
"learning_rate": 4.030985748475297e-05,
"loss": 3.6885,
"step": 591872
},
{
"epoch": 0.02,
"learning_rate": 4.030147153724245e-05,
"loss": 3.6811,
"step": 592384
},
{
"epoch": 0.02,
"learning_rate": 4.029310196853566e-05,
"loss": 3.6993,
"step": 592896
},
{
"epoch": 0.02,
"learning_rate": 4.028471602102514e-05,
"loss": 3.702,
"step": 593408
},
{
"epoch": 0.02,
"learning_rate": 4.027633007351462e-05,
"loss": 3.6972,
"step": 593920
},
{
"epoch": 0.02,
"learning_rate": 4.02679441260041e-05,
"loss": 3.69,
"step": 594432
},
{
"epoch": 0.02,
"learning_rate": 4.025955817849358e-05,
"loss": 3.6775,
"step": 594944
},
{
"epoch": 0.02,
"learning_rate": 4.02511886097868e-05,
"loss": 3.69,
"step": 595456
},
{
"epoch": 0.02,
"learning_rate": 4.024280266227628e-05,
"loss": 3.6765,
"step": 595968
},
{
"epoch": 0.02,
"learning_rate": 4.023441671476576e-05,
"loss": 3.6856,
"step": 596480
},
{
"epoch": 0.02,
"learning_rate": 4.022603076725524e-05,
"loss": 3.682,
"step": 596992
},
{
"epoch": 0.02,
"learning_rate": 4.021764481974472e-05,
"loss": 3.6873,
"step": 597504
},
{
"epoch": 0.02,
"learning_rate": 4.0209258872234197e-05,
"loss": 3.6859,
"step": 598016
},
{
"epoch": 0.02,
"learning_rate": 4.0200889303527406e-05,
"loss": 3.6871,
"step": 598528
},
{
"epoch": 0.02,
"learning_rate": 4.0192503356016886e-05,
"loss": 3.6914,
"step": 599040
},
{
"epoch": 0.02,
"learning_rate": 4.0184117408506366e-05,
"loss": 3.6825,
"step": 599552
},
{
"epoch": 0.02,
"learning_rate": 4.0175731460995846e-05,
"loss": 3.6828,
"step": 600064
},
{
"epoch": 0.02,
"learning_rate": 4.0167361892289055e-05,
"loss": 3.6902,
"step": 600576
},
{
"epoch": 0.02,
"learning_rate": 4.0158975944778535e-05,
"loss": 3.6878,
"step": 601088
},
{
"epoch": 0.02,
"learning_rate": 4.0150589997268015e-05,
"loss": 3.697,
"step": 601600
},
{
"epoch": 0.02,
"learning_rate": 4.01422040497575e-05,
"loss": 3.6815,
"step": 602112
},
{
"epoch": 0.02,
"learning_rate": 4.013381810224698e-05,
"loss": 3.6951,
"step": 602624
},
{
"epoch": 0.02,
"learning_rate": 4.012544853354019e-05,
"loss": 3.6878,
"step": 603136
},
{
"epoch": 0.02,
"learning_rate": 4.011706258602967e-05,
"loss": 3.6913,
"step": 603648
},
{
"epoch": 0.02,
"learning_rate": 4.010867663851915e-05,
"loss": 3.6853,
"step": 604160
},
{
"epoch": 0.02,
"learning_rate": 4.010029069100863e-05,
"loss": 3.69,
"step": 604672
},
{
"epoch": 0.02,
"learning_rate": 4.009192112230184e-05,
"loss": 3.6819,
"step": 605184
},
{
"epoch": 0.02,
"learning_rate": 4.008353517479132e-05,
"loss": 3.695,
"step": 605696
},
{
"epoch": 0.02,
"learning_rate": 4.00751492272808e-05,
"loss": 3.6739,
"step": 606208
},
{
"epoch": 0.02,
"learning_rate": 4.006676327977028e-05,
"loss": 3.6856,
"step": 606720
},
{
"epoch": 0.02,
"learning_rate": 4.005837733225976e-05,
"loss": 3.6897,
"step": 607232
},
{
"epoch": 0.02,
"learning_rate": 4.005000776355297e-05,
"loss": 3.6875,
"step": 607744
},
{
"epoch": 0.02,
"learning_rate": 4.0041621816042455e-05,
"loss": 3.6824,
"step": 608256
},
{
"epoch": 0.02,
"learning_rate": 4.0033235868531935e-05,
"loss": 3.6852,
"step": 608768
},
{
"epoch": 0.02,
"learning_rate": 4.0024849921021415e-05,
"loss": 3.6961,
"step": 609280
},
{
"epoch": 0.02,
"learning_rate": 4.0016463973510895e-05,
"loss": 3.676,
"step": 609792
},
{
"epoch": 0.02,
"learning_rate": 4.0008094404804104e-05,
"loss": 3.6915,
"step": 610304
},
{
"epoch": 0.03,
"eval_loss": 3.851436138153076,
"eval_runtime": 305.4421,
"eval_samples_per_second": 1249.307,
"eval_steps_per_second": 39.042,
"step": 610560
},
{
"epoch": 1.0,
"learning_rate": 3.9999708457293584e-05,
"loss": 3.6763,
"step": 610816
},
{
"epoch": 1.0,
"learning_rate": 3.9991322509783064e-05,
"loss": 3.6727,
"step": 611328
},
{
"epoch": 1.0,
"learning_rate": 3.9982936562272544e-05,
"loss": 3.6866,
"step": 611840
},
{
"epoch": 1.0,
"learning_rate": 3.997455061476202e-05,
"loss": 3.6862,
"step": 612352
},
{
"epoch": 1.0,
"learning_rate": 3.996618104605523e-05,
"loss": 3.6942,
"step": 612864
},
{
"epoch": 1.0,
"learning_rate": 3.995779509854471e-05,
"loss": 3.6763,
"step": 613376
},
{
"epoch": 1.0,
"learning_rate": 3.994940915103419e-05,
"loss": 3.6824,
"step": 613888
},
{
"epoch": 1.0,
"learning_rate": 3.994102320352367e-05,
"loss": 3.6779,
"step": 614400
},
{
"epoch": 1.0,
"learning_rate": 3.993265363481689e-05,
"loss": 3.677,
"step": 614912
},
{
"epoch": 1.0,
"learning_rate": 3.992426768730637e-05,
"loss": 3.6774,
"step": 615424
},
{
"epoch": 1.0,
"learning_rate": 3.991588173979584e-05,
"loss": 3.6879,
"step": 615936
},
{
"epoch": 1.0,
"learning_rate": 3.990749579228532e-05,
"loss": 3.6862,
"step": 616448
},
{
"epoch": 1.0,
"learning_rate": 3.989912622357854e-05,
"loss": 3.672,
"step": 616960
},
{
"epoch": 1.0,
"learning_rate": 3.989074027606802e-05,
"loss": 3.6708,
"step": 617472
},
{
"epoch": 1.0,
"learning_rate": 3.988235432855749e-05,
"loss": 3.6849,
"step": 617984
},
{
"epoch": 1.0,
"learning_rate": 3.987396838104697e-05,
"loss": 3.6646,
"step": 618496
},
{
"epoch": 1.0,
"learning_rate": 3.986558243353645e-05,
"loss": 3.677,
"step": 619008
},
{
"epoch": 1.0,
"learning_rate": 3.985719648602593e-05,
"loss": 3.675,
"step": 619520
},
{
"epoch": 1.0,
"learning_rate": 3.984881053851541e-05,
"loss": 3.6789,
"step": 620032
},
{
"epoch": 1.0,
"learning_rate": 3.984042459100489e-05,
"loss": 3.6822,
"step": 620544
},
{
"epoch": 1.0,
"learning_rate": 3.983203864349437e-05,
"loss": 3.6853,
"step": 621056
},
{
"epoch": 1.0,
"learning_rate": 3.982365269598386e-05,
"loss": 3.6797,
"step": 621568
},
{
"epoch": 1.0,
"learning_rate": 3.981526674847334e-05,
"loss": 3.675,
"step": 622080
},
{
"epoch": 1.0,
"learning_rate": 3.980688080096282e-05,
"loss": 3.6764,
"step": 622592
},
{
"epoch": 1.0,
"learning_rate": 3.9798511232256026e-05,
"loss": 3.6739,
"step": 623104
},
{
"epoch": 1.0,
"learning_rate": 3.9790141663549235e-05,
"loss": 3.6816,
"step": 623616
},
{
"epoch": 1.0,
"learning_rate": 3.9781755716038715e-05,
"loss": 3.6727,
"step": 624128
},
{
"epoch": 1.0,
"learning_rate": 3.9773369768528195e-05,
"loss": 3.6689,
"step": 624640
},
{
"epoch": 1.0,
"learning_rate": 3.9764983821017675e-05,
"loss": 3.6754,
"step": 625152
},
{
"epoch": 1.0,
"learning_rate": 3.9756614252310884e-05,
"loss": 3.6712,
"step": 625664
},
{
"epoch": 1.01,
"learning_rate": 3.9748228304800364e-05,
"loss": 3.6685,
"step": 626176
},
{
"epoch": 1.01,
"learning_rate": 3.9739842357289844e-05,
"loss": 3.6838,
"step": 626688
},
{
"epoch": 1.01,
"learning_rate": 3.9731456409779324e-05,
"loss": 3.6823,
"step": 627200
},
{
"epoch": 1.01,
"learning_rate": 3.972307046226881e-05,
"loss": 3.6783,
"step": 627712
},
{
"epoch": 1.01,
"learning_rate": 3.971468451475829e-05,
"loss": 3.6688,
"step": 628224
},
{
"epoch": 1.01,
"learning_rate": 3.97063149460515e-05,
"loss": 3.6812,
"step": 628736
},
{
"epoch": 1.01,
"learning_rate": 3.969792899854098e-05,
"loss": 3.6779,
"step": 629248
},
{
"epoch": 1.01,
"learning_rate": 3.968954305103046e-05,
"loss": 3.6732,
"step": 629760
},
{
"epoch": 1.01,
"learning_rate": 3.968115710351994e-05,
"loss": 3.6604,
"step": 630272
},
{
"epoch": 1.01,
"learning_rate": 3.967277115600942e-05,
"loss": 3.6645,
"step": 630784
},
{
"epoch": 1.01,
"learning_rate": 3.966440158730263e-05,
"loss": 3.6683,
"step": 631296
},
{
"epoch": 1.01,
"learning_rate": 3.965601563979211e-05,
"loss": 3.6783,
"step": 631808
},
{
"epoch": 1.01,
"learning_rate": 3.964762969228159e-05,
"loss": 3.6682,
"step": 632320
},
{
"epoch": 1.01,
"learning_rate": 3.963924374477107e-05,
"loss": 3.6685,
"step": 632832
},
{
"epoch": 1.01,
"learning_rate": 3.963085779726055e-05,
"loss": 3.6839,
"step": 633344
},
{
"epoch": 1.01,
"learning_rate": 3.962247184975003e-05,
"loss": 3.6721,
"step": 633856
},
{
"epoch": 1.01,
"learning_rate": 3.961408590223951e-05,
"loss": 3.68,
"step": 634368
},
{
"epoch": 1.01,
"learning_rate": 3.9605716333532724e-05,
"loss": 3.666,
"step": 634880
},
{
"epoch": 1.01,
"learning_rate": 3.9597346764825933e-05,
"loss": 3.6496,
"step": 635392
},
{
"epoch": 1.01,
"learning_rate": 3.9588960817315413e-05,
"loss": 3.6838,
"step": 635904
},
{
"epoch": 1.01,
"learning_rate": 3.9580574869804893e-05,
"loss": 3.6709,
"step": 636416
},
{
"epoch": 1.01,
"learning_rate": 3.957218892229437e-05,
"loss": 3.668,
"step": 636928
},
{
"epoch": 1.01,
"learning_rate": 3.956380297478385e-05,
"loss": 3.6689,
"step": 637440
},
{
"epoch": 1.01,
"learning_rate": 3.955543340607706e-05,
"loss": 3.6714,
"step": 637952
},
{
"epoch": 1.01,
"learning_rate": 3.954704745856654e-05,
"loss": 3.6549,
"step": 638464
},
{
"epoch": 1.01,
"learning_rate": 3.953866151105602e-05,
"loss": 3.6624,
"step": 638976
},
{
"epoch": 1.01,
"learning_rate": 3.95302755635455e-05,
"loss": 3.6627,
"step": 639488
},
{
"epoch": 1.01,
"learning_rate": 3.952190599483872e-05,
"loss": 3.6638,
"step": 640000
},
{
"epoch": 1.01,
"learning_rate": 3.95135200473282e-05,
"loss": 3.6768,
"step": 640512
},
{
"epoch": 1.01,
"learning_rate": 3.950513409981768e-05,
"loss": 3.6635,
"step": 641024
},
{
"epoch": 1.01,
"learning_rate": 3.949674815230715e-05,
"loss": 3.6618,
"step": 641536
},
{
"epoch": 1.01,
"learning_rate": 3.948836220479663e-05,
"loss": 3.6769,
"step": 642048
},
{
"epoch": 1.01,
"learning_rate": 3.947999263608985e-05,
"loss": 3.6529,
"step": 642560
},
{
"epoch": 1.01,
"learning_rate": 3.947160668857933e-05,
"loss": 3.6587,
"step": 643072
},
{
"epoch": 1.01,
"learning_rate": 3.94632207410688e-05,
"loss": 3.6625,
"step": 643584
},
{
"epoch": 1.01,
"learning_rate": 3.945483479355828e-05,
"loss": 3.6663,
"step": 644096
},
{
"epoch": 1.01,
"learning_rate": 3.9446465224851496e-05,
"loss": 3.6608,
"step": 644608
},
{
"epoch": 1.01,
"learning_rate": 3.943807927734097e-05,
"loss": 3.6621,
"step": 645120
},
{
"epoch": 1.01,
"learning_rate": 3.9429693329830456e-05,
"loss": 3.6473,
"step": 645632
},
{
"epoch": 1.01,
"learning_rate": 3.9421307382319936e-05,
"loss": 3.6608,
"step": 646144
},
{
"epoch": 1.01,
"learning_rate": 3.9412921434809416e-05,
"loss": 3.6749,
"step": 646656
},
{
"epoch": 1.01,
"learning_rate": 3.9404551866102625e-05,
"loss": 3.6599,
"step": 647168
},
{
"epoch": 1.01,
"learning_rate": 3.9396165918592105e-05,
"loss": 3.6799,
"step": 647680
},
{
"epoch": 1.01,
"learning_rate": 3.9387779971081585e-05,
"loss": 3.6713,
"step": 648192
},
{
"epoch": 1.01,
"learning_rate": 3.9379394023571065e-05,
"loss": 3.6766,
"step": 648704
},
{
"epoch": 1.01,
"learning_rate": 3.9371008076060545e-05,
"loss": 3.6539,
"step": 649216
},
{
"epoch": 1.01,
"learning_rate": 3.9362638507353754e-05,
"loss": 3.6729,
"step": 649728
},
{
"epoch": 1.01,
"learning_rate": 3.9354252559843234e-05,
"loss": 3.6673,
"step": 650240
},
{
"epoch": 1.01,
"learning_rate": 3.9345866612332714e-05,
"loss": 3.6565,
"step": 650752
},
{
"epoch": 1.01,
"learning_rate": 3.9337480664822194e-05,
"loss": 3.6752,
"step": 651264
},
{
"epoch": 1.01,
"learning_rate": 3.9329094717311674e-05,
"loss": 3.6663,
"step": 651776
},
{
"epoch": 1.01,
"learning_rate": 3.932072514860489e-05,
"loss": 3.6686,
"step": 652288
},
{
"epoch": 1.01,
"learning_rate": 3.931233920109437e-05,
"loss": 3.6689,
"step": 652800
},
{
"epoch": 1.01,
"learning_rate": 3.930395325358385e-05,
"loss": 3.6497,
"step": 653312
},
{
"epoch": 1.01,
"learning_rate": 3.929556730607333e-05,
"loss": 3.6538,
"step": 653824
},
{
"epoch": 1.01,
"learning_rate": 3.928719773736654e-05,
"loss": 3.6574,
"step": 654336
},
{
"epoch": 1.01,
"learning_rate": 3.927881178985602e-05,
"loss": 3.6665,
"step": 654848
},
{
"epoch": 1.01,
"learning_rate": 3.92704258423455e-05,
"loss": 3.6616,
"step": 655360
},
{
"epoch": 1.01,
"learning_rate": 3.926203989483498e-05,
"loss": 3.6569,
"step": 655872
},
{
"epoch": 1.02,
"learning_rate": 3.925367032612819e-05,
"loss": 3.6599,
"step": 656384
},
{
"epoch": 1.02,
"learning_rate": 3.924528437861767e-05,
"loss": 3.6618,
"step": 656896
},
{
"epoch": 1.02,
"learning_rate": 3.923689843110715e-05,
"loss": 3.6591,
"step": 657408
},
{
"epoch": 1.02,
"learning_rate": 3.922851248359663e-05,
"loss": 3.6564,
"step": 657920
},
{
"epoch": 1.02,
"learning_rate": 3.922014291488984e-05,
"loss": 3.6783,
"step": 658432
},
{
"epoch": 1.02,
"learning_rate": 3.921175696737932e-05,
"loss": 3.6759,
"step": 658944
},
{
"epoch": 1.02,
"learning_rate": 3.92033710198688e-05,
"loss": 3.6661,
"step": 659456
},
{
"epoch": 1.02,
"learning_rate": 3.919498507235828e-05,
"loss": 3.6552,
"step": 659968
},
{
"epoch": 1.02,
"learning_rate": 3.918659912484776e-05,
"loss": 3.6649,
"step": 660480
},
{
"epoch": 1.02,
"learning_rate": 3.917822955614097e-05,
"loss": 3.657,
"step": 660992
},
{
"epoch": 1.02,
"learning_rate": 3.916984360863045e-05,
"loss": 3.6733,
"step": 661504
},
{
"epoch": 1.02,
"learning_rate": 3.916145766111993e-05,
"loss": 3.6623,
"step": 662016
},
{
"epoch": 1.02,
"learning_rate": 3.915307171360941e-05,
"loss": 3.659,
"step": 662528
},
{
"epoch": 1.02,
"learning_rate": 3.914468576609889e-05,
"loss": 3.6665,
"step": 663040
},
{
"epoch": 1.02,
"learning_rate": 3.913629981858837e-05,
"loss": 3.6695,
"step": 663552
},
{
"epoch": 1.02,
"learning_rate": 3.912793024988158e-05,
"loss": 3.6542,
"step": 664064
},
{
"epoch": 1.02,
"learning_rate": 3.911954430237106e-05,
"loss": 3.661,
"step": 664576
},
{
"epoch": 1.02,
"learning_rate": 3.911115835486054e-05,
"loss": 3.6553,
"step": 665088
},
{
"epoch": 1.02,
"learning_rate": 3.910277240735003e-05,
"loss": 3.6564,
"step": 665600
},
{
"epoch": 1.02,
"learning_rate": 3.909440283864324e-05,
"loss": 3.6498,
"step": 666112
},
{
"epoch": 1.02,
"learning_rate": 3.908601689113272e-05,
"loss": 3.66,
"step": 666624
},
{
"epoch": 1.02,
"learning_rate": 3.90776309436222e-05,
"loss": 3.6593,
"step": 667136
},
{
"epoch": 1.02,
"learning_rate": 3.906924499611168e-05,
"loss": 3.6614,
"step": 667648
},
{
"epoch": 1.02,
"learning_rate": 3.9060875427404886e-05,
"loss": 3.661,
"step": 668160
},
{
"epoch": 1.02,
"learning_rate": 3.9052489479894366e-05,
"loss": 3.6508,
"step": 668672
},
{
"epoch": 1.02,
"learning_rate": 3.9044103532383846e-05,
"loss": 3.6685,
"step": 669184
},
{
"epoch": 1.02,
"learning_rate": 3.9035717584873326e-05,
"loss": 3.6783,
"step": 669696
},
{
"epoch": 1.02,
"learning_rate": 3.9027331637362806e-05,
"loss": 3.6639,
"step": 670208
},
{
"epoch": 1.02,
"learning_rate": 3.901894568985228e-05,
"loss": 3.6705,
"step": 670720
},
{
"epoch": 1.02,
"learning_rate": 3.9010576121145495e-05,
"loss": 3.6473,
"step": 671232
},
{
"epoch": 1.02,
"learning_rate": 3.900219017363498e-05,
"loss": 3.6643,
"step": 671744
},
{
"epoch": 1.02,
"learning_rate": 3.899380422612446e-05,
"loss": 3.6532,
"step": 672256
},
{
"epoch": 1.02,
"learning_rate": 3.8985418278613934e-05,
"loss": 3.6558,
"step": 672768
},
{
"epoch": 1.02,
"learning_rate": 3.8977032331103414e-05,
"loss": 3.6539,
"step": 673280
},
{
"epoch": 1.02,
"learning_rate": 3.8968646383592894e-05,
"loss": 3.6591,
"step": 673792
},
{
"epoch": 1.02,
"learning_rate": 3.8960260436082374e-05,
"loss": 3.6602,
"step": 674304
},
{
"epoch": 1.02,
"learning_rate": 3.8951890867375583e-05,
"loss": 3.6587,
"step": 674816
},
{
"epoch": 1.02,
"learning_rate": 3.8943504919865063e-05,
"loss": 3.6634,
"step": 675328
},
{
"epoch": 1.02,
"learning_rate": 3.893511897235454e-05,
"loss": 3.6579,
"step": 675840
},
{
"epoch": 1.02,
"learning_rate": 3.892673302484402e-05,
"loss": 3.6507,
"step": 676352
},
{
"epoch": 1.02,
"learning_rate": 3.891836345613723e-05,
"loss": 3.6635,
"step": 676864
},
{
"epoch": 1.02,
"learning_rate": 3.890997750862672e-05,
"loss": 3.6628,
"step": 677376
},
{
"epoch": 1.02,
"learning_rate": 3.89015915611162e-05,
"loss": 3.6708,
"step": 677888
},
{
"epoch": 1.02,
"learning_rate": 3.889320561360568e-05,
"loss": 3.653,
"step": 678400
},
{
"epoch": 1.02,
"learning_rate": 3.888481966609516e-05,
"loss": 3.6688,
"step": 678912
},
{
"epoch": 1.02,
"learning_rate": 3.887645009738837e-05,
"loss": 3.662,
"step": 679424
},
{
"epoch": 1.02,
"learning_rate": 3.886806414987785e-05,
"loss": 3.6615,
"step": 679936
},
{
"epoch": 1.02,
"learning_rate": 3.885967820236733e-05,
"loss": 3.6606,
"step": 680448
},
{
"epoch": 1.02,
"learning_rate": 3.885130863366054e-05,
"loss": 3.6617,
"step": 680960
},
{
"epoch": 1.02,
"learning_rate": 3.884292268615002e-05,
"loss": 3.6567,
"step": 681472
},
{
"epoch": 1.02,
"learning_rate": 3.88345367386395e-05,
"loss": 3.6688,
"step": 681984
},
{
"epoch": 1.02,
"learning_rate": 3.882615079112898e-05,
"loss": 3.6498,
"step": 682496
},
{
"epoch": 1.02,
"learning_rate": 3.881776484361846e-05,
"loss": 3.6574,
"step": 683008
},
{
"epoch": 1.02,
"learning_rate": 3.880939527491167e-05,
"loss": 3.6621,
"step": 683520
},
{
"epoch": 1.02,
"learning_rate": 3.880100932740115e-05,
"loss": 3.6657,
"step": 684032
},
{
"epoch": 1.02,
"learning_rate": 3.879262337989063e-05,
"loss": 3.6512,
"step": 684544
},
{
"epoch": 1.02,
"learning_rate": 3.878423743238011e-05,
"loss": 3.6604,
"step": 685056
},
{
"epoch": 1.02,
"learning_rate": 3.877586786367332e-05,
"loss": 3.6659,
"step": 685568
},
{
"epoch": 1.02,
"learning_rate": 3.87674819161628e-05,
"loss": 3.6551,
"step": 686080
},
{
"epoch": 1.02,
"learning_rate": 3.875909596865228e-05,
"loss": 3.6647,
"step": 686592
},
{
"epoch": 1.03,
"eval_loss": 3.8468892574310303,
"eval_runtime": 304.9955,
"eval_samples_per_second": 1251.136,
"eval_steps_per_second": 39.099,
"step": 686880
},
{
"epoch": 0.0,
"learning_rate": 3.875071002114176e-05,
"loss": 3.6385,
"step": 687104
},
{
"epoch": 0.0,
"learning_rate": 3.874232407363124e-05,
"loss": 3.6486,
"step": 687616
},
{
"epoch": 0.0,
"learning_rate": 3.873393812612072e-05,
"loss": 3.6597,
"step": 688128
},
{
"epoch": 0.0,
"learning_rate": 3.87255521786102e-05,
"loss": 3.6606,
"step": 688640
},
{
"epoch": 0.0,
"learning_rate": 3.871718260990341e-05,
"loss": 3.6656,
"step": 689152
},
{
"epoch": 0.0,
"learning_rate": 3.870879666239289e-05,
"loss": 3.6488,
"step": 689664
},
{
"epoch": 0.0,
"learning_rate": 3.870041071488237e-05,
"loss": 3.6554,
"step": 690176
},
{
"epoch": 0.0,
"learning_rate": 3.869202476737186e-05,
"loss": 3.6541,
"step": 690688
},
{
"epoch": 0.0,
"learning_rate": 3.8683655198665066e-05,
"loss": 3.6481,
"step": 691200
},
{
"epoch": 0.0,
"learning_rate": 3.8675269251154546e-05,
"loss": 3.6526,
"step": 691712
},
{
"epoch": 0.0,
"learning_rate": 3.8666883303644026e-05,
"loss": 3.6589,
"step": 692224
},
{
"epoch": 0.0,
"learning_rate": 3.8658497356133506e-05,
"loss": 3.6562,
"step": 692736
},
{
"epoch": 0.0,
"learning_rate": 3.8650127787426715e-05,
"loss": 3.657,
"step": 693248
},
{
"epoch": 0.0,
"learning_rate": 3.8641741839916195e-05,
"loss": 3.6382,
"step": 693760
},
{
"epoch": 0.0,
"learning_rate": 3.8633355892405675e-05,
"loss": 3.6583,
"step": 694272
},
{
"epoch": 0.0,
"learning_rate": 3.8624969944895155e-05,
"loss": 3.6401,
"step": 694784
},
{
"epoch": 0.0,
"learning_rate": 3.8616583997384635e-05,
"loss": 3.6496,
"step": 695296
},
{
"epoch": 0.0,
"learning_rate": 3.8608198049874115e-05,
"loss": 3.6526,
"step": 695808
},
{
"epoch": 0.0,
"learning_rate": 3.8599812102363595e-05,
"loss": 3.6497,
"step": 696320
},
{
"epoch": 0.0,
"learning_rate": 3.8591426154853075e-05,
"loss": 3.6573,
"step": 696832
},
{
"epoch": 0.0,
"learning_rate": 3.8583040207342555e-05,
"loss": 3.6586,
"step": 697344
},
{
"epoch": 0.0,
"learning_rate": 3.8574654259832035e-05,
"loss": 3.6568,
"step": 697856
},
{
"epoch": 0.0,
"learning_rate": 3.8566284691125244e-05,
"loss": 3.6532,
"step": 698368
},
{
"epoch": 0.0,
"learning_rate": 3.8557898743614724e-05,
"loss": 3.6463,
"step": 698880
},
{
"epoch": 0.0,
"learning_rate": 3.8549512796104204e-05,
"loss": 3.6514,
"step": 699392
},
{
"epoch": 0.0,
"learning_rate": 3.8541126848593684e-05,
"loss": 3.6539,
"step": 699904
},
{
"epoch": 0.0,
"learning_rate": 3.853275727988689e-05,
"loss": 3.6507,
"step": 700416
},
{
"epoch": 0.0,
"learning_rate": 3.852437133237637e-05,
"loss": 3.6459,
"step": 700928
},
{
"epoch": 0.0,
"learning_rate": 3.851598538486585e-05,
"loss": 3.6453,
"step": 701440
},
{
"epoch": 0.0,
"learning_rate": 3.850759943735533e-05,
"loss": 3.6487,
"step": 701952
},
{
"epoch": 0.01,
"learning_rate": 3.849922986864854e-05,
"loss": 3.639,
"step": 702464
},
{
"epoch": 0.01,
"learning_rate": 3.849084392113803e-05,
"loss": 3.6574,
"step": 702976
},
{
"epoch": 0.01,
"learning_rate": 3.848245797362751e-05,
"loss": 3.6553,
"step": 703488
},
{
"epoch": 0.01,
"learning_rate": 3.847407202611699e-05,
"loss": 3.6541,
"step": 704000
},
{
"epoch": 0.01,
"learning_rate": 3.84657024574102e-05,
"loss": 3.6443,
"step": 704512
},
{
"epoch": 0.01,
"learning_rate": 3.845731650989968e-05,
"loss": 3.6519,
"step": 705024
},
{
"epoch": 0.01,
"learning_rate": 3.844893056238916e-05,
"loss": 3.6539,
"step": 705536
},
{
"epoch": 0.01,
"learning_rate": 3.844054461487864e-05,
"loss": 3.6469,
"step": 706048
},
{
"epoch": 0.01,
"learning_rate": 3.843217504617185e-05,
"loss": 3.6377,
"step": 706560
},
{
"epoch": 0.01,
"learning_rate": 3.8423789098661327e-05,
"loss": 3.6391,
"step": 707072
},
{
"epoch": 0.01,
"learning_rate": 3.8415403151150807e-05,
"loss": 3.6421,
"step": 707584
},
{
"epoch": 0.01,
"learning_rate": 3.8407017203640286e-05,
"loss": 3.6528,
"step": 708096
},
{
"epoch": 0.01,
"learning_rate": 3.8398631256129766e-05,
"loss": 3.6415,
"step": 708608
},
{
"epoch": 0.01,
"learning_rate": 3.839026168742298e-05,
"loss": 3.6421,
"step": 709120
},
{
"epoch": 0.01,
"learning_rate": 3.838187573991246e-05,
"loss": 3.6562,
"step": 709632
},
{
"epoch": 0.01,
"learning_rate": 3.837348979240194e-05,
"loss": 3.6475,
"step": 710144
},
{
"epoch": 0.01,
"learning_rate": 3.836510384489142e-05,
"loss": 3.6534,
"step": 710656
},
{
"epoch": 0.01,
"learning_rate": 3.83567178973809e-05,
"loss": 3.6421,
"step": 711168
},
{
"epoch": 0.01,
"learning_rate": 3.834834832867411e-05,
"loss": 3.6272,
"step": 711680
},
{
"epoch": 0.01,
"learning_rate": 3.833996238116359e-05,
"loss": 3.656,
"step": 712192
},
{
"epoch": 0.01,
"learning_rate": 3.833157643365307e-05,
"loss": 3.6424,
"step": 712704
},
{
"epoch": 0.01,
"learning_rate": 3.832319048614255e-05,
"loss": 3.6464,
"step": 713216
},
{
"epoch": 0.01,
"learning_rate": 3.831480453863203e-05,
"loss": 3.6445,
"step": 713728
},
{
"epoch": 0.01,
"learning_rate": 3.830643496992524e-05,
"loss": 3.6444,
"step": 714240
},
{
"epoch": 0.01,
"learning_rate": 3.829804902241472e-05,
"loss": 3.6283,
"step": 714752
},
{
"epoch": 0.01,
"learning_rate": 3.82896630749042e-05,
"loss": 3.6414,
"step": 715264
},
{
"epoch": 0.01,
"learning_rate": 3.828127712739368e-05,
"loss": 3.6368,
"step": 715776
},
{
"epoch": 0.01,
"learning_rate": 3.827289117988317e-05,
"loss": 3.6395,
"step": 716288
},
{
"epoch": 0.01,
"learning_rate": 3.8264521611176376e-05,
"loss": 3.655,
"step": 716800
},
{
"epoch": 0.01,
"learning_rate": 3.8256135663665856e-05,
"loss": 3.638,
"step": 717312
},
{
"epoch": 0.01,
"learning_rate": 3.8247749716155336e-05,
"loss": 3.636,
"step": 717824
},
{
"epoch": 0.01,
"learning_rate": 3.8239363768644816e-05,
"loss": 3.6545,
"step": 718336
},
{
"epoch": 0.01,
"learning_rate": 3.8230994199938025e-05,
"loss": 3.6276,
"step": 718848
},
{
"epoch": 0.01,
"learning_rate": 3.8222608252427505e-05,
"loss": 3.6296,
"step": 719360
},
{
"epoch": 0.01,
"learning_rate": 3.8214222304916985e-05,
"loss": 3.6433,
"step": 719872
},
{
"epoch": 0.01,
"learning_rate": 3.8205836357406465e-05,
"loss": 3.6418,
"step": 720384
},
{
"epoch": 0.01,
"learning_rate": 3.8197466788699674e-05,
"loss": 3.6339,
"step": 720896
},
{
"epoch": 0.01,
"learning_rate": 3.8189080841189154e-05,
"loss": 3.6405,
"step": 721408
},
{
"epoch": 0.01,
"learning_rate": 3.8180694893678634e-05,
"loss": 3.6221,
"step": 721920
},
{
"epoch": 0.01,
"learning_rate": 3.817230894616812e-05,
"loss": 3.6354,
"step": 722432
},
{
"epoch": 0.01,
"learning_rate": 3.81639229986576e-05,
"loss": 3.6518,
"step": 722944
},
{
"epoch": 0.01,
"learning_rate": 3.815555342995081e-05,
"loss": 3.638,
"step": 723456
},
{
"epoch": 0.01,
"learning_rate": 3.814716748244029e-05,
"loss": 3.6505,
"step": 723968
},
{
"epoch": 0.01,
"learning_rate": 3.813878153492977e-05,
"loss": 3.6478,
"step": 724480
},
{
"epoch": 0.01,
"learning_rate": 3.813039558741925e-05,
"loss": 3.6576,
"step": 724992
},
{
"epoch": 0.01,
"learning_rate": 3.812200963990872e-05,
"loss": 3.6303,
"step": 725504
},
{
"epoch": 0.01,
"learning_rate": 3.811364007120194e-05,
"loss": 3.6465,
"step": 726016
},
{
"epoch": 0.01,
"learning_rate": 3.810525412369142e-05,
"loss": 3.6444,
"step": 726528
},
{
"epoch": 0.01,
"learning_rate": 3.80968681761809e-05,
"loss": 3.6282,
"step": 727040
},
{
"epoch": 0.01,
"learning_rate": 3.808848222867037e-05,
"loss": 3.6539,
"step": 727552
},
{
"epoch": 0.01,
"learning_rate": 3.808011265996359e-05,
"loss": 3.6411,
"step": 728064
},
{
"epoch": 0.01,
"learning_rate": 3.8071726712453074e-05,
"loss": 3.6445,
"step": 728576
},
{
"epoch": 0.01,
"learning_rate": 3.806334076494255e-05,
"loss": 3.6468,
"step": 729088
},
{
"epoch": 0.01,
"learning_rate": 3.805495481743203e-05,
"loss": 3.6269,
"step": 729600
},
{
"epoch": 0.01,
"learning_rate": 3.804656886992151e-05,
"loss": 3.6256,
"step": 730112
},
{
"epoch": 0.01,
"learning_rate": 3.803819930121472e-05,
"loss": 3.6346,
"step": 730624
},
{
"epoch": 0.01,
"learning_rate": 3.8029813353704196e-05,
"loss": 3.6431,
"step": 731136
},
{
"epoch": 0.01,
"learning_rate": 3.8021427406193676e-05,
"loss": 3.6368,
"step": 731648
},
{
"epoch": 0.01,
"learning_rate": 3.8013041458683156e-05,
"loss": 3.6323,
"step": 732160
},
{
"epoch": 0.02,
"learning_rate": 3.800467188997637e-05,
"loss": 3.6331,
"step": 732672
},
{
"epoch": 0.02,
"learning_rate": 3.7996285942465845e-05,
"loss": 3.6409,
"step": 733184
},
{
"epoch": 0.02,
"learning_rate": 3.7987899994955325e-05,
"loss": 3.6338,
"step": 733696
},
{
"epoch": 0.02,
"learning_rate": 3.797951404744481e-05,
"loss": 3.6295,
"step": 734208
},
{
"epoch": 0.02,
"learning_rate": 3.797114447873802e-05,
"loss": 3.6548,
"step": 734720
},
{
"epoch": 0.02,
"learning_rate": 3.79627585312275e-05,
"loss": 3.6525,
"step": 735232
},
{
"epoch": 0.02,
"learning_rate": 3.795437258371698e-05,
"loss": 3.6448,
"step": 735744
},
{
"epoch": 0.02,
"learning_rate": 3.794598663620646e-05,
"loss": 3.6292,
"step": 736256
},
{
"epoch": 0.02,
"learning_rate": 3.793761706749967e-05,
"loss": 3.6416,
"step": 736768
},
{
"epoch": 0.02,
"learning_rate": 3.792923111998915e-05,
"loss": 3.6357,
"step": 737280
},
{
"epoch": 0.02,
"learning_rate": 3.792084517247863e-05,
"loss": 3.6461,
"step": 737792
},
{
"epoch": 0.02,
"learning_rate": 3.791245922496811e-05,
"loss": 3.6376,
"step": 738304
},
{
"epoch": 0.02,
"learning_rate": 3.790408965626132e-05,
"loss": 3.6312,
"step": 738816
},
{
"epoch": 0.02,
"learning_rate": 3.78957037087508e-05,
"loss": 3.641,
"step": 739328
},
{
"epoch": 0.02,
"learning_rate": 3.788731776124028e-05,
"loss": 3.6487,
"step": 739840
},
{
"epoch": 0.02,
"learning_rate": 3.7878931813729766e-05,
"loss": 3.6305,
"step": 740352
},
{
"epoch": 0.02,
"learning_rate": 3.7870545866219246e-05,
"loss": 3.6409,
"step": 740864
},
{
"epoch": 0.02,
"learning_rate": 3.7862176297512455e-05,
"loss": 3.6276,
"step": 741376
},
{
"epoch": 0.02,
"learning_rate": 3.7853790350001935e-05,
"loss": 3.6352,
"step": 741888
},
{
"epoch": 0.02,
"learning_rate": 3.7845404402491415e-05,
"loss": 3.6297,
"step": 742400
},
{
"epoch": 0.02,
"learning_rate": 3.7837018454980894e-05,
"loss": 3.6294,
"step": 742912
},
{
"epoch": 0.02,
"learning_rate": 3.7828648886274104e-05,
"loss": 3.6375,
"step": 743424
},
{
"epoch": 0.02,
"learning_rate": 3.7820262938763584e-05,
"loss": 3.638,
"step": 743936
},
{
"epoch": 0.02,
"learning_rate": 3.7811876991253063e-05,
"loss": 3.6379,
"step": 744448
},
{
"epoch": 0.02,
"learning_rate": 3.7803491043742543e-05,
"loss": 3.6278,
"step": 744960
},
{
"epoch": 0.02,
"learning_rate": 3.779512147503575e-05,
"loss": 3.6467,
"step": 745472
},
{
"epoch": 0.02,
"learning_rate": 3.778673552752523e-05,
"loss": 3.6513,
"step": 745984
},
{
"epoch": 0.02,
"learning_rate": 3.777834958001471e-05,
"loss": 3.6412,
"step": 746496
},
{
"epoch": 0.02,
"learning_rate": 3.77699636325042e-05,
"loss": 3.6483,
"step": 747008
},
{
"epoch": 0.02,
"learning_rate": 3.776159406379741e-05,
"loss": 3.6262,
"step": 747520
},
{
"epoch": 0.02,
"learning_rate": 3.775320811628689e-05,
"loss": 3.6375,
"step": 748032
},
{
"epoch": 0.02,
"learning_rate": 3.774482216877637e-05,
"loss": 3.6329,
"step": 748544
},
{
"epoch": 0.02,
"learning_rate": 3.773643622126585e-05,
"loss": 3.6293,
"step": 749056
},
{
"epoch": 0.02,
"learning_rate": 3.772806665255906e-05,
"loss": 3.6311,
"step": 749568
},
{
"epoch": 0.02,
"learning_rate": 3.771968070504854e-05,
"loss": 3.6343,
"step": 750080
},
{
"epoch": 0.02,
"learning_rate": 3.771129475753802e-05,
"loss": 3.6366,
"step": 750592
},
{
"epoch": 0.02,
"learning_rate": 3.77029088100275e-05,
"loss": 3.634,
"step": 751104
},
{
"epoch": 0.02,
"learning_rate": 3.769452286251698e-05,
"loss": 3.6393,
"step": 751616
},
{
"epoch": 0.02,
"learning_rate": 3.7686153293810186e-05,
"loss": 3.638,
"step": 752128
},
{
"epoch": 0.02,
"learning_rate": 3.7677767346299666e-05,
"loss": 3.6257,
"step": 752640
},
{
"epoch": 0.02,
"learning_rate": 3.766938139878915e-05,
"loss": 3.64,
"step": 753152
},
{
"epoch": 0.02,
"learning_rate": 3.766099545127863e-05,
"loss": 3.6416,
"step": 753664
},
{
"epoch": 0.02,
"learning_rate": 3.765262588257184e-05,
"loss": 3.645,
"step": 754176
},
{
"epoch": 0.02,
"learning_rate": 3.764423993506132e-05,
"loss": 3.6312,
"step": 754688
},
{
"epoch": 0.02,
"learning_rate": 3.76358539875508e-05,
"loss": 3.6468,
"step": 755200
},
{
"epoch": 0.02,
"learning_rate": 3.762746804004028e-05,
"loss": 3.638,
"step": 755712
},
{
"epoch": 0.02,
"learning_rate": 3.761908209252976e-05,
"loss": 3.6379,
"step": 756224
},
{
"epoch": 0.02,
"learning_rate": 3.761071252382297e-05,
"loss": 3.6379,
"step": 756736
},
{
"epoch": 0.02,
"learning_rate": 3.760232657631245e-05,
"loss": 3.6342,
"step": 757248
},
{
"epoch": 0.02,
"learning_rate": 3.759394062880193e-05,
"loss": 3.6332,
"step": 757760
},
{
"epoch": 0.02,
"learning_rate": 3.758555468129141e-05,
"loss": 3.6496,
"step": 758272
},
{
"epoch": 0.02,
"learning_rate": 3.757718511258462e-05,
"loss": 3.621,
"step": 758784
},
{
"epoch": 0.02,
"learning_rate": 3.7568799165074107e-05,
"loss": 3.6364,
"step": 759296
},
{
"epoch": 0.02,
"learning_rate": 3.7560413217563586e-05,
"loss": 3.6402,
"step": 759808
},
{
"epoch": 0.02,
"learning_rate": 3.7552027270053066e-05,
"loss": 3.6362,
"step": 760320
},
{
"epoch": 0.02,
"learning_rate": 3.7543657701346276e-05,
"loss": 3.6313,
"step": 760832
},
{
"epoch": 0.02,
"learning_rate": 3.7535271753835755e-05,
"loss": 3.6369,
"step": 761344
},
{
"epoch": 0.02,
"learning_rate": 3.7526885806325235e-05,
"loss": 3.6397,
"step": 761856
},
{
"epoch": 0.02,
"learning_rate": 3.7518499858814715e-05,
"loss": 3.636,
"step": 762368
},
{
"epoch": 0.02,
"learning_rate": 3.7510130290107924e-05,
"loss": 3.6384,
"step": 762880
},
{
"epoch": 0.03,
"eval_loss": 3.843653917312622,
"eval_runtime": 301.8904,
"eval_samples_per_second": 1264.005,
"eval_steps_per_second": 39.501,
"step": 763200
},
{
"epoch": 0.0,
"learning_rate": 3.7501744342597404e-05,
"loss": 3.6183,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.7493358395086884e-05,
"loss": 3.6242,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.7484972447576364e-05,
"loss": 3.6354,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.7476586500065844e-05,
"loss": 3.6363,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.746821693135906e-05,
"loss": 3.6449,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.745983098384854e-05,
"loss": 3.6271,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.745144503633802e-05,
"loss": 3.634,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.74430590888275e-05,
"loss": 3.6303,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.743468952012071e-05,
"loss": 3.6264,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.742630357261019e-05,
"loss": 3.628,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.741791762509967e-05,
"loss": 3.6368,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.740953167758915e-05,
"loss": 3.638,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.740116210888236e-05,
"loss": 3.6372,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.739277616137184e-05,
"loss": 3.613,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.738439021386132e-05,
"loss": 3.6361,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.73760042663508e-05,
"loss": 3.6156,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.736761831884028e-05,
"loss": 3.6262,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.735923237132976e-05,
"loss": 3.6272,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.735084642381924e-05,
"loss": 3.6257,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.734246047630872e-05,
"loss": 3.6332,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.73340745287982e-05,
"loss": 3.6395,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.732570496009141e-05,
"loss": 3.6321,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.731731901258089e-05,
"loss": 3.6283,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.730893306507037e-05,
"loss": 3.6219,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.730054711755985e-05,
"loss": 3.632,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.7292177548853056e-05,
"loss": 3.6298,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.7283791601342536e-05,
"loss": 3.6263,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.7275405653832016e-05,
"loss": 3.6249,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.7267019706321496e-05,
"loss": 3.6205,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.725865013761471e-05,
"loss": 3.6269,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.725026419010419e-05,
"loss": 3.6144,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.724187824259367e-05,
"loss": 3.6353,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.723349229508315e-05,
"loss": 3.6379,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.722512272637636e-05,
"loss": 3.6279,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.721673677886584e-05,
"loss": 3.6237,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.720835083135532e-05,
"loss": 3.6235,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.71999648838448e-05,
"loss": 3.6339,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.719159531513801e-05,
"loss": 3.6259,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.718320936762749e-05,
"loss": 3.61,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.717482342011697e-05,
"loss": 3.6201,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.716643747260645e-05,
"loss": 3.6203,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.715805152509593e-05,
"loss": 3.6272,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.7149681956389145e-05,
"loss": 3.6229,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.7141296008878625e-05,
"loss": 3.6223,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.7132910061368105e-05,
"loss": 3.6321,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.7124524113857585e-05,
"loss": 3.6281,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.7116154545150794e-05,
"loss": 3.6298,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.7107768597640274e-05,
"loss": 3.6223,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.7099382650129754e-05,
"loss": 3.6016,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.7090996702619234e-05,
"loss": 3.6338,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.708262713391244e-05,
"loss": 3.621,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.707424118640192e-05,
"loss": 3.6218,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.70658552388914e-05,
"loss": 3.6248,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.705746929138088e-05,
"loss": 3.6229,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.70490997226741e-05,
"loss": 3.6073,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.704071377516358e-05,
"loss": 3.6147,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.703232782765306e-05,
"loss": 3.6159,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.702394188014254e-05,
"loss": 3.6141,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.701557231143575e-05,
"loss": 3.6312,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.700718636392523e-05,
"loss": 3.6176,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.699880041641471e-05,
"loss": 3.6148,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.699041446890419e-05,
"loss": 3.6286,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.698202852139367e-05,
"loss": 3.611,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.697365895268688e-05,
"loss": 3.6059,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.696527300517636e-05,
"loss": 3.6227,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.695688705766584e-05,
"loss": 3.6156,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.694850111015532e-05,
"loss": 3.6094,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.694013154144853e-05,
"loss": 3.6168,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.693174559393801e-05,
"loss": 3.6034,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.692335964642749e-05,
"loss": 3.6132,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.691497369891697e-05,
"loss": 3.6297,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.690660413021018e-05,
"loss": 3.6186,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.689821818269966e-05,
"loss": 3.6285,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.688983223518914e-05,
"loss": 3.6196,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.688144628767862e-05,
"loss": 3.6357,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.687307671897183e-05,
"loss": 3.6077,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.686469077146131e-05,
"loss": 3.6244,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.685630482395079e-05,
"loss": 3.6218,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.684791887644028e-05,
"loss": 3.6072,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.683953292892976e-05,
"loss": 3.6301,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.6831163360222966e-05,
"loss": 3.6188,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.6822777412712446e-05,
"loss": 3.6224,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.6814391465201926e-05,
"loss": 3.6267,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.6806005517691406e-05,
"loss": 3.6064,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.6797635948984615e-05,
"loss": 3.6035,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.6789250001474095e-05,
"loss": 3.6103,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.6780864053963575e-05,
"loss": 3.6215,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.6772478106453055e-05,
"loss": 3.6142,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.6764108537746264e-05,
"loss": 3.612,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.6755722590235744e-05,
"loss": 3.6126,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.674733664272523e-05,
"loss": 3.621,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.6738950695214704e-05,
"loss": 3.611,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.673058112650792e-05,
"loss": 3.6124,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.67221951789974e-05,
"loss": 3.6283,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.671380923148688e-05,
"loss": 3.6317,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.670542328397635e-05,
"loss": 3.6221,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.669705371526957e-05,
"loss": 3.6109,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.668866776775905e-05,
"loss": 3.616,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.668028182024853e-05,
"loss": 3.611,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.6671895872738e-05,
"loss": 3.6234,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.666352630403122e-05,
"loss": 3.616,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.66551403565207e-05,
"loss": 3.6158,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.664675440901018e-05,
"loss": 3.616,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.663836846149966e-05,
"loss": 3.6191,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.662998251398914e-05,
"loss": 3.6163,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.662161294528235e-05,
"loss": 3.6156,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.6613226997771827e-05,
"loss": 3.6079,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.6604841050261307e-05,
"loss": 3.613,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.659647148155452e-05,
"loss": 3.609,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.6588085534044e-05,
"loss": 3.6075,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.6579699586533476e-05,
"loss": 3.6141,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.6571313639022955e-05,
"loss": 3.6131,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.656294407031617e-05,
"loss": 3.6187,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.655455812280565e-05,
"loss": 3.6071,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.654617217529513e-05,
"loss": 3.625,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.653778622778461e-05,
"loss": 3.6325,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.652940028027409e-05,
"loss": 3.6162,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.65210307115673e-05,
"loss": 3.6246,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.651264476405678e-05,
"loss": 3.6121,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.650425881654626e-05,
"loss": 3.614,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.649587286903574e-05,
"loss": 3.6112,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.648750330032895e-05,
"loss": 3.6064,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.647911735281843e-05,
"loss": 3.6117,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.647073140530791e-05,
"loss": 3.6157,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.646234545779739e-05,
"loss": 3.618,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.6453975889090605e-05,
"loss": 3.6113,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.6445589941580085e-05,
"loss": 3.6177,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.6437203994069565e-05,
"loss": 3.6131,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.6428818046559045e-05,
"loss": 3.6083,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.6420448477852254e-05,
"loss": 3.6157,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.6412062530341734e-05,
"loss": 3.6217,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.6403676582831214e-05,
"loss": 3.624,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.6395290635320694e-05,
"loss": 3.6076,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.63869210666139e-05,
"loss": 3.626,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.637853511910338e-05,
"loss": 3.6142,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.637014917159286e-05,
"loss": 3.6194,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.636176322408234e-05,
"loss": 3.6162,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.635339365537556e-05,
"loss": 3.6096,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.634500770786504e-05,
"loss": 3.6074,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.633662176035452e-05,
"loss": 3.63,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.6328235812844e-05,
"loss": 3.6019,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.631986624413721e-05,
"loss": 3.6142,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.631148029662669e-05,
"loss": 3.6178,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.630309434911617e-05,
"loss": 3.6188,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.629470840160565e-05,
"loss": 3.6111,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.6286338832898857e-05,
"loss": 3.6141,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.6277952885388337e-05,
"loss": 3.6169,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.6269566937877816e-05,
"loss": 3.6216,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.6261180990367296e-05,
"loss": 3.6155,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 3.841677665710449,
"eval_runtime": 305.0924,
"eval_samples_per_second": 1250.739,
"eval_steps_per_second": 39.087,
"step": 839520
},
{
"epoch": 1.0,
"learning_rate": 3.625281142166051e-05,
"loss": 3.602,
"step": 839680
},
{
"epoch": 1.0,
"learning_rate": 3.624442547414999e-05,
"loss": 3.6052,
"step": 840192
},
{
"epoch": 1.0,
"learning_rate": 3.623603952663947e-05,
"loss": 3.6144,
"step": 840704
},
{
"epoch": 1.0,
"learning_rate": 3.622765357912895e-05,
"loss": 3.6164,
"step": 841216
},
{
"epoch": 1.0,
"learning_rate": 3.621928401042216e-05,
"loss": 3.6213,
"step": 841728
},
{
"epoch": 1.0,
"learning_rate": 3.621089806291164e-05,
"loss": 3.6078,
"step": 842240
},
{
"epoch": 1.0,
"learning_rate": 3.620251211540112e-05,
"loss": 3.6112,
"step": 842752
},
{
"epoch": 1.0,
"learning_rate": 3.61941261678906e-05,
"loss": 3.6111,
"step": 843264
},
{
"epoch": 1.0,
"learning_rate": 3.618575659918381e-05,
"loss": 3.6033,
"step": 843776
},
{
"epoch": 1.0,
"learning_rate": 3.617737065167329e-05,
"loss": 3.6019,
"step": 844288
},
{
"epoch": 1.0,
"learning_rate": 3.616898470416277e-05,
"loss": 3.6157,
"step": 844800
},
{
"epoch": 1.0,
"learning_rate": 3.616059875665225e-05,
"loss": 3.6224,
"step": 845312
},
{
"epoch": 1.0,
"learning_rate": 3.6152229187945466e-05,
"loss": 3.61,
"step": 845824
},
{
"epoch": 1.0,
"learning_rate": 3.6143843240434946e-05,
"loss": 3.5937,
"step": 846336
},
{
"epoch": 1.0,
"learning_rate": 3.6135457292924426e-05,
"loss": 3.6125,
"step": 846848
},
{
"epoch": 1.0,
"learning_rate": 3.6127071345413906e-05,
"loss": 3.5957,
"step": 847360
},
{
"epoch": 1.0,
"learning_rate": 3.6118685397903386e-05,
"loss": 3.6069,
"step": 847872
},
{
"epoch": 1.0,
"learning_rate": 3.6110299450392866e-05,
"loss": 3.6089,
"step": 848384
},
{
"epoch": 1.0,
"learning_rate": 3.6101913502882346e-05,
"loss": 3.6052,
"step": 848896
},
{
"epoch": 1.0,
"learning_rate": 3.6093527555371826e-05,
"loss": 3.6101,
"step": 849408
},
{
"epoch": 1.0,
"learning_rate": 3.6085157986665035e-05,
"loss": 3.6158,
"step": 849920
},
{
"epoch": 1.0,
"learning_rate": 3.6076772039154515e-05,
"loss": 3.6095,
"step": 850432
},
{
"epoch": 1.0,
"learning_rate": 3.6068386091643995e-05,
"loss": 3.6088,
"step": 850944
},
{
"epoch": 1.0,
"learning_rate": 3.6060000144133475e-05,
"loss": 3.6029,
"step": 851456
},
{
"epoch": 1.0,
"learning_rate": 3.6051630575426684e-05,
"loss": 3.61,
"step": 851968
},
{
"epoch": 1.0,
"learning_rate": 3.604324462791617e-05,
"loss": 3.6094,
"step": 852480
},
{
"epoch": 1.0,
"learning_rate": 3.603485868040565e-05,
"loss": 3.6025,
"step": 852992
},
{
"epoch": 1.0,
"learning_rate": 3.602647273289513e-05,
"loss": 3.6091,
"step": 853504
},
{
"epoch": 1.0,
"learning_rate": 3.601810316418834e-05,
"loss": 3.6007,
"step": 854016
},
{
"epoch": 1.0,
"learning_rate": 3.600971721667782e-05,
"loss": 3.6043,
"step": 854528
},
{
"epoch": 1.01,
"learning_rate": 3.60013312691673e-05,
"loss": 3.5986,
"step": 855040
},
{
"epoch": 1.01,
"learning_rate": 3.599294532165678e-05,
"loss": 3.611,
"step": 855552
},
{
"epoch": 1.01,
"learning_rate": 3.598457575294999e-05,
"loss": 3.6108,
"step": 856064
},
{
"epoch": 1.01,
"learning_rate": 3.597618980543947e-05,
"loss": 3.6115,
"step": 856576
},
{
"epoch": 1.01,
"learning_rate": 3.596780385792895e-05,
"loss": 3.6031,
"step": 857088
},
{
"epoch": 1.01,
"learning_rate": 3.595941791041843e-05,
"loss": 3.6045,
"step": 857600
},
{
"epoch": 1.01,
"learning_rate": 3.595103196290791e-05,
"loss": 3.6141,
"step": 858112
},
{
"epoch": 1.01,
"learning_rate": 3.5942662394201124e-05,
"loss": 3.6025,
"step": 858624
},
{
"epoch": 1.01,
"learning_rate": 3.5934276446690604e-05,
"loss": 3.5938,
"step": 859136
},
{
"epoch": 1.01,
"learning_rate": 3.5925890499180084e-05,
"loss": 3.6001,
"step": 859648
},
{
"epoch": 1.01,
"learning_rate": 3.591750455166956e-05,
"loss": 3.599,
"step": 860160
},
{
"epoch": 1.01,
"learning_rate": 3.590913498296277e-05,
"loss": 3.6028,
"step": 860672
},
{
"epoch": 1.01,
"learning_rate": 3.590074903545225e-05,
"loss": 3.6017,
"step": 861184
},
{
"epoch": 1.01,
"learning_rate": 3.5892363087941726e-05,
"loss": 3.6058,
"step": 861696
},
{
"epoch": 1.01,
"learning_rate": 3.5883977140431206e-05,
"loss": 3.6081,
"step": 862208
},
{
"epoch": 1.01,
"learning_rate": 3.587560757172442e-05,
"loss": 3.6094,
"step": 862720
},
{
"epoch": 1.01,
"learning_rate": 3.58672216242139e-05,
"loss": 3.6097,
"step": 863232
},
{
"epoch": 1.01,
"learning_rate": 3.5858835676703375e-05,
"loss": 3.6036,
"step": 863744
},
{
"epoch": 1.01,
"learning_rate": 3.585044972919286e-05,
"loss": 3.5832,
"step": 864256
},
{
"epoch": 1.01,
"learning_rate": 3.584208016048608e-05,
"loss": 3.6117,
"step": 864768
},
{
"epoch": 1.01,
"learning_rate": 3.583369421297556e-05,
"loss": 3.6013,
"step": 865280
},
{
"epoch": 1.01,
"learning_rate": 3.582530826546503e-05,
"loss": 3.6005,
"step": 865792
},
{
"epoch": 1.01,
"learning_rate": 3.581692231795451e-05,
"loss": 3.6051,
"step": 866304
},
{
"epoch": 1.01,
"learning_rate": 3.580855274924773e-05,
"loss": 3.6024,
"step": 866816
},
{
"epoch": 1.01,
"learning_rate": 3.58001668017372e-05,
"loss": 3.5864,
"step": 867328
},
{
"epoch": 1.01,
"learning_rate": 3.579178085422668e-05,
"loss": 3.5955,
"step": 867840
},
{
"epoch": 1.01,
"learning_rate": 3.578339490671616e-05,
"loss": 3.5972,
"step": 868352
},
{
"epoch": 1.01,
"learning_rate": 3.5775025338009376e-05,
"loss": 3.5928,
"step": 868864
},
{
"epoch": 1.01,
"learning_rate": 3.576663939049885e-05,
"loss": 3.6128,
"step": 869376
},
{
"epoch": 1.01,
"learning_rate": 3.575825344298833e-05,
"loss": 3.6006,
"step": 869888
},
{
"epoch": 1.01,
"learning_rate": 3.5749867495477816e-05,
"loss": 3.5871,
"step": 870400
},
{
"epoch": 1.01,
"learning_rate": 3.574149792677103e-05,
"loss": 3.6103,
"step": 870912
},
{
"epoch": 1.01,
"learning_rate": 3.5733111979260505e-05,
"loss": 3.5934,
"step": 871424
},
{
"epoch": 1.01,
"learning_rate": 3.5724726031749985e-05,
"loss": 3.5862,
"step": 871936
},
{
"epoch": 1.01,
"learning_rate": 3.5716340084239465e-05,
"loss": 3.6033,
"step": 872448
},
{
"epoch": 1.01,
"learning_rate": 3.5707970515532674e-05,
"loss": 3.5972,
"step": 872960
},
{
"epoch": 1.01,
"learning_rate": 3.5699584568022154e-05,
"loss": 3.5897,
"step": 873472
},
{
"epoch": 1.01,
"learning_rate": 3.5691198620511634e-05,
"loss": 3.5962,
"step": 873984
},
{
"epoch": 1.01,
"learning_rate": 3.5682812673001114e-05,
"loss": 3.5827,
"step": 874496
},
{
"epoch": 1.01,
"learning_rate": 3.567444310429432e-05,
"loss": 3.5953,
"step": 875008
},
{
"epoch": 1.01,
"learning_rate": 3.56660571567838e-05,
"loss": 3.6047,
"step": 875520
},
{
"epoch": 1.01,
"learning_rate": 3.565767120927328e-05,
"loss": 3.5998,
"step": 876032
},
{
"epoch": 1.01,
"learning_rate": 3.564928526176277e-05,
"loss": 3.6095,
"step": 876544
},
{
"epoch": 1.01,
"learning_rate": 3.564091569305598e-05,
"loss": 3.5952,
"step": 877056
},
{
"epoch": 1.01,
"learning_rate": 3.563252974554546e-05,
"loss": 3.6146,
"step": 877568
},
{
"epoch": 1.01,
"learning_rate": 3.562414379803494e-05,
"loss": 3.5874,
"step": 878080
},
{
"epoch": 1.01,
"learning_rate": 3.561575785052442e-05,
"loss": 3.6066,
"step": 878592
},
{
"epoch": 1.01,
"learning_rate": 3.560738828181763e-05,
"loss": 3.5994,
"step": 879104
},
{
"epoch": 1.01,
"learning_rate": 3.559900233430711e-05,
"loss": 3.5897,
"step": 879616
},
{
"epoch": 1.01,
"learning_rate": 3.559061638679659e-05,
"loss": 3.6068,
"step": 880128
},
{
"epoch": 1.01,
"learning_rate": 3.5582246818089796e-05,
"loss": 3.6046,
"step": 880640
},
{
"epoch": 1.01,
"learning_rate": 3.5573860870579276e-05,
"loss": 3.5998,
"step": 881152
},
{
"epoch": 1.01,
"learning_rate": 3.5565474923068756e-05,
"loss": 3.6083,
"step": 881664
},
{
"epoch": 1.01,
"learning_rate": 3.5557088975558236e-05,
"loss": 3.5871,
"step": 882176
},
{
"epoch": 1.01,
"learning_rate": 3.554870302804772e-05,
"loss": 3.5831,
"step": 882688
},
{
"epoch": 1.01,
"learning_rate": 3.554033345934093e-05,
"loss": 3.5907,
"step": 883200
},
{
"epoch": 1.01,
"learning_rate": 3.553194751183041e-05,
"loss": 3.6022,
"step": 883712
},
{
"epoch": 1.01,
"learning_rate": 3.552356156431989e-05,
"loss": 3.5954,
"step": 884224
},
{
"epoch": 1.01,
"learning_rate": 3.551517561680937e-05,
"loss": 3.5934,
"step": 884736
},
{
"epoch": 1.01,
"learning_rate": 3.550680604810258e-05,
"loss": 3.5926,
"step": 885248
},
{
"epoch": 1.02,
"learning_rate": 3.549842010059206e-05,
"loss": 3.5968,
"step": 885760
},
{
"epoch": 1.02,
"learning_rate": 3.549003415308154e-05,
"loss": 3.5924,
"step": 886272
},
{
"epoch": 1.02,
"learning_rate": 3.548164820557102e-05,
"loss": 3.595,
"step": 886784
},
{
"epoch": 1.02,
"learning_rate": 3.547327863686423e-05,
"loss": 3.6048,
"step": 887296
},
{
"epoch": 1.02,
"learning_rate": 3.546489268935371e-05,
"loss": 3.611,
"step": 887808
},
{
"epoch": 1.02,
"learning_rate": 3.545650674184319e-05,
"loss": 3.6056,
"step": 888320
},
{
"epoch": 1.02,
"learning_rate": 3.5448120794332677e-05,
"loss": 3.5922,
"step": 888832
},
{
"epoch": 1.02,
"learning_rate": 3.5439751225625886e-05,
"loss": 3.5937,
"step": 889344
},
{
"epoch": 1.02,
"learning_rate": 3.5431365278115366e-05,
"loss": 3.5933,
"step": 889856
},
{
"epoch": 1.02,
"learning_rate": 3.5422979330604846e-05,
"loss": 3.6041,
"step": 890368
},
{
"epoch": 1.02,
"learning_rate": 3.5414593383094326e-05,
"loss": 3.5995,
"step": 890880
},
{
"epoch": 1.02,
"learning_rate": 3.5406223814387535e-05,
"loss": 3.5947,
"step": 891392
},
{
"epoch": 1.02,
"learning_rate": 3.5397837866877015e-05,
"loss": 3.5983,
"step": 891904
},
{
"epoch": 1.02,
"learning_rate": 3.5389451919366495e-05,
"loss": 3.5975,
"step": 892416
},
{
"epoch": 1.02,
"learning_rate": 3.5381065971855975e-05,
"loss": 3.602,
"step": 892928
},
{
"epoch": 1.02,
"learning_rate": 3.5372696403149184e-05,
"loss": 3.5928,
"step": 893440
},
{
"epoch": 1.02,
"learning_rate": 3.5364310455638664e-05,
"loss": 3.5872,
"step": 893952
},
{
"epoch": 1.02,
"learning_rate": 3.5355924508128144e-05,
"loss": 3.591,
"step": 894464
},
{
"epoch": 1.02,
"learning_rate": 3.5347538560617623e-05,
"loss": 3.5936,
"step": 894976
},
{
"epoch": 1.02,
"learning_rate": 3.533916899191084e-05,
"loss": 3.5889,
"step": 895488
},
{
"epoch": 1.02,
"learning_rate": 3.533078304440032e-05,
"loss": 3.5937,
"step": 896000
},
{
"epoch": 1.02,
"learning_rate": 3.53223970968898e-05,
"loss": 3.5922,
"step": 896512
},
{
"epoch": 1.02,
"learning_rate": 3.531401114937928e-05,
"loss": 3.5983,
"step": 897024
},
{
"epoch": 1.02,
"learning_rate": 3.530564158067249e-05,
"loss": 3.5882,
"step": 897536
},
{
"epoch": 1.02,
"learning_rate": 3.529725563316197e-05,
"loss": 3.6073,
"step": 898048
},
{
"epoch": 1.02,
"learning_rate": 3.528886968565145e-05,
"loss": 3.6103,
"step": 898560
},
{
"epoch": 1.02,
"learning_rate": 3.528048373814093e-05,
"loss": 3.5954,
"step": 899072
},
{
"epoch": 1.02,
"learning_rate": 3.527211416943414e-05,
"loss": 3.6037,
"step": 899584
},
{
"epoch": 1.02,
"learning_rate": 3.526372822192362e-05,
"loss": 3.5935,
"step": 900096
},
{
"epoch": 1.02,
"learning_rate": 3.52553422744131e-05,
"loss": 3.5935,
"step": 900608
},
{
"epoch": 1.02,
"learning_rate": 3.524695632690258e-05,
"loss": 3.594,
"step": 901120
},
{
"epoch": 1.02,
"learning_rate": 3.523858675819579e-05,
"loss": 3.5822,
"step": 901632
},
{
"epoch": 1.02,
"learning_rate": 3.523020081068527e-05,
"loss": 3.5946,
"step": 902144
},
{
"epoch": 1.02,
"learning_rate": 3.522181486317475e-05,
"loss": 3.5955,
"step": 902656
},
{
"epoch": 1.02,
"learning_rate": 3.521342891566423e-05,
"loss": 3.6018,
"step": 903168
},
{
"epoch": 1.02,
"learning_rate": 3.520505934695744e-05,
"loss": 3.5893,
"step": 903680
},
{
"epoch": 1.02,
"learning_rate": 3.519667339944692e-05,
"loss": 3.6014,
"step": 904192
},
{
"epoch": 1.02,
"learning_rate": 3.51882874519364e-05,
"loss": 3.5945,
"step": 904704
},
{
"epoch": 1.02,
"learning_rate": 3.517990150442588e-05,
"loss": 3.5879,
"step": 905216
},
{
"epoch": 1.02,
"learning_rate": 3.517153193571909e-05,
"loss": 3.5981,
"step": 905728
},
{
"epoch": 1.02,
"learning_rate": 3.516314598820857e-05,
"loss": 3.5984,
"step": 906240
},
{
"epoch": 1.02,
"learning_rate": 3.515476004069805e-05,
"loss": 3.6045,
"step": 906752
},
{
"epoch": 1.02,
"learning_rate": 3.514637409318753e-05,
"loss": 3.5865,
"step": 907264
},
{
"epoch": 1.02,
"learning_rate": 3.513800452448075e-05,
"loss": 3.6095,
"step": 907776
},
{
"epoch": 1.02,
"learning_rate": 3.512961857697023e-05,
"loss": 3.5924,
"step": 908288
},
{
"epoch": 1.02,
"learning_rate": 3.5121232629459707e-05,
"loss": 3.6009,
"step": 908800
},
{
"epoch": 1.02,
"learning_rate": 3.5112846681949187e-05,
"loss": 3.598,
"step": 909312
},
{
"epoch": 1.02,
"learning_rate": 3.5104477113242396e-05,
"loss": 3.59,
"step": 909824
},
{
"epoch": 1.02,
"learning_rate": 3.5096091165731876e-05,
"loss": 3.5921,
"step": 910336
},
{
"epoch": 1.02,
"learning_rate": 3.5087705218221356e-05,
"loss": 3.6109,
"step": 910848
},
{
"epoch": 1.02,
"learning_rate": 3.5079319270710836e-05,
"loss": 3.5826,
"step": 911360
},
{
"epoch": 1.02,
"learning_rate": 3.5070949702004045e-05,
"loss": 3.5941,
"step": 911872
},
{
"epoch": 1.02,
"learning_rate": 3.5062563754493525e-05,
"loss": 3.5958,
"step": 912384
},
{
"epoch": 1.02,
"learning_rate": 3.5054177806983005e-05,
"loss": 3.595,
"step": 912896
},
{
"epoch": 1.02,
"learning_rate": 3.5045791859472484e-05,
"loss": 3.5942,
"step": 913408
},
{
"epoch": 1.02,
"learning_rate": 3.50374222907657e-05,
"loss": 3.5929,
"step": 913920
},
{
"epoch": 1.02,
"learning_rate": 3.502903634325518e-05,
"loss": 3.5973,
"step": 914432
},
{
"epoch": 1.02,
"learning_rate": 3.502065039574466e-05,
"loss": 3.6013,
"step": 914944
},
{
"epoch": 1.02,
"learning_rate": 3.501226444823414e-05,
"loss": 3.5932,
"step": 915456
},
{
"epoch": 1.03,
"eval_loss": 3.8412368297576904,
"eval_runtime": 304.4129,
"eval_samples_per_second": 1253.531,
"eval_steps_per_second": 39.174,
"step": 915840
},
{
"epoch": 0.0,
"learning_rate": 3.500389487952735e-05,
"loss": 3.5863,
"step": 915968
},
{
"epoch": 0.0,
"learning_rate": 3.499550893201683e-05,
"loss": 3.5803,
"step": 916480
},
{
"epoch": 0.0,
"learning_rate": 3.498712298450631e-05,
"loss": 3.5939,
"step": 916992
},
{
"epoch": 0.0,
"learning_rate": 3.497873703699579e-05,
"loss": 3.6008,
"step": 917504
},
{
"epoch": 0.0,
"learning_rate": 3.4970367468289e-05,
"loss": 3.598,
"step": 918016
},
{
"epoch": 0.0,
"learning_rate": 3.496198152077848e-05,
"loss": 3.5899,
"step": 918528
},
{
"epoch": 0.0,
"learning_rate": 3.495359557326796e-05,
"loss": 3.5955,
"step": 919040
},
{
"epoch": 0.0,
"learning_rate": 3.494520962575744e-05,
"loss": 3.5909,
"step": 919552
},
{
"epoch": 0.0,
"learning_rate": 3.4936840057050654e-05,
"loss": 3.5847,
"step": 920064
},
{
"epoch": 0.0,
"learning_rate": 3.4928454109540134e-05,
"loss": 3.5829,
"step": 920576
},
{
"epoch": 0.0,
"learning_rate": 3.4920068162029614e-05,
"loss": 3.5989,
"step": 921088
},
{
"epoch": 0.0,
"learning_rate": 3.4911682214519094e-05,
"loss": 3.6013,
"step": 921600
},
{
"epoch": 0.0,
"learning_rate": 3.49033126458123e-05,
"loss": 3.5956,
"step": 922112
},
{
"epoch": 0.0,
"learning_rate": 3.489492669830178e-05,
"loss": 3.5739,
"step": 922624
},
{
"epoch": 0.0,
"learning_rate": 3.488654075079126e-05,
"loss": 3.5925,
"step": 923136
},
{
"epoch": 0.0,
"learning_rate": 3.487815480328074e-05,
"loss": 3.5749,
"step": 923648
},
{
"epoch": 0.0,
"learning_rate": 3.486978523457395e-05,
"loss": 3.5913,
"step": 924160
},
{
"epoch": 0.0,
"learning_rate": 3.486139928706343e-05,
"loss": 3.5876,
"step": 924672
},
{
"epoch": 0.0,
"learning_rate": 3.485301333955291e-05,
"loss": 3.5851,
"step": 925184
},
{
"epoch": 0.0,
"learning_rate": 3.484462739204239e-05,
"loss": 3.5914,
"step": 925696
},
{
"epoch": 0.0,
"learning_rate": 3.483625782333561e-05,
"loss": 3.6013,
"step": 926208
},
{
"epoch": 0.0,
"learning_rate": 3.482787187582509e-05,
"loss": 3.5884,
"step": 926720
},
{
"epoch": 0.0,
"learning_rate": 3.481948592831457e-05,
"loss": 3.5891,
"step": 927232
},
{
"epoch": 0.0,
"learning_rate": 3.481109998080405e-05,
"loss": 3.5859,
"step": 927744
},
{
"epoch": 0.0,
"learning_rate": 3.480271403329352e-05,
"loss": 3.592,
"step": 928256
},
{
"epoch": 0.0,
"learning_rate": 3.4794344464586737e-05,
"loss": 3.5908,
"step": 928768
},
{
"epoch": 0.0,
"learning_rate": 3.4785958517076217e-05,
"loss": 3.5824,
"step": 929280
},
{
"epoch": 0.0,
"learning_rate": 3.4777572569565697e-05,
"loss": 3.5879,
"step": 929792
},
{
"epoch": 0.0,
"learning_rate": 3.476918662205517e-05,
"loss": 3.5813,
"step": 930304
},
{
"epoch": 0.0,
"learning_rate": 3.4760817053348386e-05,
"loss": 3.5843,
"step": 930816
},
{
"epoch": 0.01,
"learning_rate": 3.4752431105837866e-05,
"loss": 3.5836,
"step": 931328
},
{
"epoch": 0.01,
"learning_rate": 3.4744045158327345e-05,
"loss": 3.5905,
"step": 931840
},
{
"epoch": 0.01,
"learning_rate": 3.4735659210816825e-05,
"loss": 3.589,
"step": 932352
},
{
"epoch": 0.01,
"learning_rate": 3.472728964211004e-05,
"loss": 3.5975,
"step": 932864
},
{
"epoch": 0.01,
"learning_rate": 3.471890369459952e-05,
"loss": 3.5865,
"step": 933376
},
{
"epoch": 0.01,
"learning_rate": 3.4710517747088994e-05,
"loss": 3.5832,
"step": 933888
},
{
"epoch": 0.01,
"learning_rate": 3.4702131799578474e-05,
"loss": 3.5985,
"step": 934400
},
{
"epoch": 0.01,
"learning_rate": 3.469376223087169e-05,
"loss": 3.5807,
"step": 934912
},
{
"epoch": 0.01,
"learning_rate": 3.468537628336117e-05,
"loss": 3.5764,
"step": 935424
},
{
"epoch": 0.01,
"learning_rate": 3.4676990335850643e-05,
"loss": 3.5814,
"step": 935936
},
{
"epoch": 0.01,
"learning_rate": 3.466860438834012e-05,
"loss": 3.5809,
"step": 936448
},
{
"epoch": 0.01,
"learning_rate": 3.466023481963334e-05,
"loss": 3.5828,
"step": 936960
},
{
"epoch": 0.01,
"learning_rate": 3.465184887212282e-05,
"loss": 3.5831,
"step": 937472
},
{
"epoch": 0.01,
"learning_rate": 3.46434629246123e-05,
"loss": 3.5848,
"step": 937984
},
{
"epoch": 0.01,
"learning_rate": 3.463507697710178e-05,
"loss": 3.5884,
"step": 938496
},
{
"epoch": 0.01,
"learning_rate": 3.4626707408394995e-05,
"loss": 3.5901,
"step": 939008
},
{
"epoch": 0.01,
"learning_rate": 3.461832146088447e-05,
"loss": 3.59,
"step": 939520
},
{
"epoch": 0.01,
"learning_rate": 3.460993551337395e-05,
"loss": 3.586,
"step": 940032
},
{
"epoch": 0.01,
"learning_rate": 3.460154956586343e-05,
"loss": 3.5669,
"step": 940544
},
{
"epoch": 0.01,
"learning_rate": 3.4593179997156644e-05,
"loss": 3.5924,
"step": 941056
},
{
"epoch": 0.01,
"learning_rate": 3.458479404964612e-05,
"loss": 3.5819,
"step": 941568
},
{
"epoch": 0.01,
"learning_rate": 3.45764081021356e-05,
"loss": 3.5847,
"step": 942080
},
{
"epoch": 0.01,
"learning_rate": 3.456802215462508e-05,
"loss": 3.581,
"step": 942592
},
{
"epoch": 0.01,
"learning_rate": 3.455965258591829e-05,
"loss": 3.5813,
"step": 943104
},
{
"epoch": 0.01,
"learning_rate": 3.455126663840777e-05,
"loss": 3.5719,
"step": 943616
},
{
"epoch": 0.01,
"learning_rate": 3.454288069089725e-05,
"loss": 3.578,
"step": 944128
},
{
"epoch": 0.01,
"learning_rate": 3.453449474338673e-05,
"loss": 3.5828,
"step": 944640
},
{
"epoch": 0.01,
"learning_rate": 3.452612517467994e-05,
"loss": 3.5713,
"step": 945152
},
{
"epoch": 0.01,
"learning_rate": 3.451773922716942e-05,
"loss": 3.5947,
"step": 945664
},
{
"epoch": 0.01,
"learning_rate": 3.45093532796589e-05,
"loss": 3.585,
"step": 946176
},
{
"epoch": 0.01,
"learning_rate": 3.450096733214838e-05,
"loss": 3.5651,
"step": 946688
},
{
"epoch": 0.01,
"learning_rate": 3.449259776344159e-05,
"loss": 3.5941,
"step": 947200
},
{
"epoch": 0.01,
"learning_rate": 3.448421181593107e-05,
"loss": 3.5721,
"step": 947712
},
{
"epoch": 0.01,
"learning_rate": 3.447582586842055e-05,
"loss": 3.5677,
"step": 948224
},
{
"epoch": 0.01,
"learning_rate": 3.446743992091003e-05,
"loss": 3.5814,
"step": 948736
},
{
"epoch": 0.01,
"learning_rate": 3.4459070352203247e-05,
"loss": 3.5794,
"step": 949248
},
{
"epoch": 0.01,
"learning_rate": 3.4450684404692727e-05,
"loss": 3.5677,
"step": 949760
},
{
"epoch": 0.01,
"learning_rate": 3.4442298457182206e-05,
"loss": 3.581,
"step": 950272
},
{
"epoch": 0.01,
"learning_rate": 3.4433912509671686e-05,
"loss": 3.5669,
"step": 950784
},
{
"epoch": 0.01,
"learning_rate": 3.4425542940964896e-05,
"loss": 3.5724,
"step": 951296
},
{
"epoch": 0.01,
"learning_rate": 3.4417156993454375e-05,
"loss": 3.5887,
"step": 951808
},
{
"epoch": 0.01,
"learning_rate": 3.4408771045943855e-05,
"loss": 3.5824,
"step": 952320
},
{
"epoch": 0.01,
"learning_rate": 3.4400385098433335e-05,
"loss": 3.5881,
"step": 952832
},
{
"epoch": 0.01,
"learning_rate": 3.4392015529726544e-05,
"loss": 3.5794,
"step": 953344
},
{
"epoch": 0.01,
"learning_rate": 3.4383629582216024e-05,
"loss": 3.5966,
"step": 953856
},
{
"epoch": 0.01,
"learning_rate": 3.4375243634705504e-05,
"loss": 3.571,
"step": 954368
},
{
"epoch": 0.01,
"learning_rate": 3.4366857687194984e-05,
"loss": 3.59,
"step": 954880
},
{
"epoch": 0.01,
"learning_rate": 3.4358488118488193e-05,
"loss": 3.5775,
"step": 955392
},
{
"epoch": 0.01,
"learning_rate": 3.435010217097768e-05,
"loss": 3.5747,
"step": 955904
},
{
"epoch": 0.01,
"learning_rate": 3.434171622346716e-05,
"loss": 3.5837,
"step": 956416
},
{
"epoch": 0.01,
"learning_rate": 3.433333027595664e-05,
"loss": 3.5932,
"step": 956928
},
{
"epoch": 0.01,
"learning_rate": 3.432496070724985e-05,
"loss": 3.5799,
"step": 957440
},
{
"epoch": 0.01,
"learning_rate": 3.431657475973933e-05,
"loss": 3.5912,
"step": 957952
},
{
"epoch": 0.01,
"learning_rate": 3.430818881222881e-05,
"loss": 3.5668,
"step": 958464
},
{
"epoch": 0.01,
"learning_rate": 3.429980286471829e-05,
"loss": 3.5633,
"step": 958976
},
{
"epoch": 0.01,
"learning_rate": 3.42914332960115e-05,
"loss": 3.5728,
"step": 959488
},
{
"epoch": 0.01,
"learning_rate": 3.428304734850098e-05,
"loss": 3.5816,
"step": 960000
},
{
"epoch": 0.01,
"learning_rate": 3.427466140099046e-05,
"loss": 3.5797,
"step": 960512
},
{
"epoch": 0.01,
"learning_rate": 3.426627545347994e-05,
"loss": 3.577,
"step": 961024
},
{
"epoch": 0.01,
"learning_rate": 3.425790588477315e-05,
"loss": 3.572,
"step": 961536
},
{
"epoch": 0.02,
"learning_rate": 3.4249519937262634e-05,
"loss": 3.5779,
"step": 962048
},
{
"epoch": 0.02,
"learning_rate": 3.4241133989752114e-05,
"loss": 3.5763,
"step": 962560
},
{
"epoch": 0.02,
"learning_rate": 3.4232748042241594e-05,
"loss": 3.5733,
"step": 963072
},
{
"epoch": 0.02,
"learning_rate": 3.42243784735348e-05,
"loss": 3.5883,
"step": 963584
},
{
"epoch": 0.02,
"learning_rate": 3.421599252602428e-05,
"loss": 3.5916,
"step": 964096
},
{
"epoch": 0.02,
"learning_rate": 3.420760657851376e-05,
"loss": 3.59,
"step": 964608
},
{
"epoch": 0.02,
"learning_rate": 3.419922063100324e-05,
"loss": 3.5704,
"step": 965120
},
{
"epoch": 0.02,
"learning_rate": 3.419085106229645e-05,
"loss": 3.5787,
"step": 965632
},
{
"epoch": 0.02,
"learning_rate": 3.418246511478593e-05,
"loss": 3.5755,
"step": 966144
},
{
"epoch": 0.02,
"learning_rate": 3.417407916727541e-05,
"loss": 3.5825,
"step": 966656
},
{
"epoch": 0.02,
"learning_rate": 3.416569321976489e-05,
"loss": 3.583,
"step": 967168
},
{
"epoch": 0.02,
"learning_rate": 3.41573236510581e-05,
"loss": 3.5754,
"step": 967680
},
{
"epoch": 0.02,
"learning_rate": 3.414893770354759e-05,
"loss": 3.5782,
"step": 968192
},
{
"epoch": 0.02,
"learning_rate": 3.414055175603707e-05,
"loss": 3.5816,
"step": 968704
},
{
"epoch": 0.02,
"learning_rate": 3.413216580852655e-05,
"loss": 3.583,
"step": 969216
},
{
"epoch": 0.02,
"learning_rate": 3.4123796239819757e-05,
"loss": 3.5773,
"step": 969728
},
{
"epoch": 0.02,
"learning_rate": 3.4115410292309236e-05,
"loss": 3.5735,
"step": 970240
},
{
"epoch": 0.02,
"learning_rate": 3.4107024344798716e-05,
"loss": 3.571,
"step": 970752
},
{
"epoch": 0.02,
"learning_rate": 3.4098638397288196e-05,
"loss": 3.5732,
"step": 971264
},
{
"epoch": 0.02,
"learning_rate": 3.4090268828581405e-05,
"loss": 3.5736,
"step": 971776
},
{
"epoch": 0.02,
"learning_rate": 3.4081882881070885e-05,
"loss": 3.5717,
"step": 972288
},
{
"epoch": 0.02,
"learning_rate": 3.4073496933560365e-05,
"loss": 3.572,
"step": 972800
},
{
"epoch": 0.02,
"learning_rate": 3.4065110986049845e-05,
"loss": 3.5829,
"step": 973312
},
{
"epoch": 0.02,
"learning_rate": 3.4056741417343054e-05,
"loss": 3.5668,
"step": 973824
},
{
"epoch": 0.02,
"learning_rate": 3.404835546983254e-05,
"loss": 3.5875,
"step": 974336
},
{
"epoch": 0.02,
"learning_rate": 3.403996952232202e-05,
"loss": 3.5951,
"step": 974848
},
{
"epoch": 0.02,
"learning_rate": 3.40315835748115e-05,
"loss": 3.5812,
"step": 975360
},
{
"epoch": 0.02,
"learning_rate": 3.402321400610471e-05,
"loss": 3.5826,
"step": 975872
},
{
"epoch": 0.02,
"learning_rate": 3.401482805859419e-05,
"loss": 3.5799,
"step": 976384
},
{
"epoch": 0.02,
"learning_rate": 3.400644211108367e-05,
"loss": 3.5707,
"step": 976896
},
{
"epoch": 0.02,
"learning_rate": 3.399805616357315e-05,
"loss": 3.5826,
"step": 977408
},
{
"epoch": 0.02,
"learning_rate": 3.398968659486636e-05,
"loss": 3.5603,
"step": 977920
},
{
"epoch": 0.02,
"learning_rate": 3.398130064735584e-05,
"loss": 3.578,
"step": 978432
},
{
"epoch": 0.02,
"learning_rate": 3.397291469984532e-05,
"loss": 3.5762,
"step": 978944
},
{
"epoch": 0.02,
"learning_rate": 3.39645287523348e-05,
"loss": 3.5807,
"step": 979456
},
{
"epoch": 0.02,
"learning_rate": 3.395615918362801e-05,
"loss": 3.5747,
"step": 979968
},
{
"epoch": 0.02,
"learning_rate": 3.3947773236117495e-05,
"loss": 3.5816,
"step": 980480
},
{
"epoch": 0.02,
"learning_rate": 3.3939387288606975e-05,
"loss": 3.5736,
"step": 980992
},
{
"epoch": 0.02,
"learning_rate": 3.3931001341096455e-05,
"loss": 3.5687,
"step": 981504
},
{
"epoch": 0.02,
"learning_rate": 3.3922631772389664e-05,
"loss": 3.585,
"step": 982016
},
{
"epoch": 0.02,
"learning_rate": 3.3914245824879144e-05,
"loss": 3.5769,
"step": 982528
},
{
"epoch": 0.02,
"learning_rate": 3.3905859877368624e-05,
"loss": 3.5883,
"step": 983040
},
{
"epoch": 0.02,
"learning_rate": 3.3897473929858104e-05,
"loss": 3.5723,
"step": 983552
},
{
"epoch": 0.02,
"learning_rate": 3.388910436115131e-05,
"loss": 3.5889,
"step": 984064
},
{
"epoch": 0.02,
"learning_rate": 3.388071841364079e-05,
"loss": 3.5765,
"step": 984576
},
{
"epoch": 0.02,
"learning_rate": 3.387233246613027e-05,
"loss": 3.5784,
"step": 985088
},
{
"epoch": 0.02,
"learning_rate": 3.386394651861975e-05,
"loss": 3.5818,
"step": 985600
},
{
"epoch": 0.02,
"learning_rate": 3.385557694991296e-05,
"loss": 3.5738,
"step": 986112
},
{
"epoch": 0.02,
"learning_rate": 3.384719100240245e-05,
"loss": 3.5731,
"step": 986624
},
{
"epoch": 0.02,
"learning_rate": 3.383880505489193e-05,
"loss": 3.5908,
"step": 987136
},
{
"epoch": 0.02,
"learning_rate": 3.383041910738141e-05,
"loss": 3.5682,
"step": 987648
},
{
"epoch": 0.02,
"learning_rate": 3.382204953867462e-05,
"loss": 3.5725,
"step": 988160
},
{
"epoch": 0.02,
"learning_rate": 3.38136635911641e-05,
"loss": 3.5801,
"step": 988672
},
{
"epoch": 0.02,
"learning_rate": 3.380527764365358e-05,
"loss": 3.5777,
"step": 989184
},
{
"epoch": 0.02,
"learning_rate": 3.379689169614306e-05,
"loss": 3.5768,
"step": 989696
},
{
"epoch": 0.02,
"learning_rate": 3.3788522127436266e-05,
"loss": 3.5781,
"step": 990208
},
{
"epoch": 0.02,
"learning_rate": 3.3780136179925746e-05,
"loss": 3.5772,
"step": 990720
},
{
"epoch": 0.02,
"learning_rate": 3.3771750232415226e-05,
"loss": 3.5822,
"step": 991232
},
{
"epoch": 0.02,
"learning_rate": 3.3763364284904706e-05,
"loss": 3.5776,
"step": 991744
},
{
"epoch": 0.03,
"eval_loss": 3.8405232429504395,
"eval_runtime": 303.6118,
"eval_samples_per_second": 1256.839,
"eval_steps_per_second": 39.277,
"step": 992160
},
{
"epoch": 1.0,
"learning_rate": 3.3754994716197915e-05,
"loss": 3.5716,
"step": 992256
},
{
"epoch": 1.0,
"learning_rate": 3.37466087686874e-05,
"loss": 3.563,
"step": 992768
},
{
"epoch": 1.0,
"learning_rate": 3.373822282117688e-05,
"loss": 3.5746,
"step": 993280
},
{
"epoch": 1.0,
"learning_rate": 3.372983687366636e-05,
"loss": 3.59,
"step": 993792
},
{
"epoch": 1.0,
"learning_rate": 3.372146730495957e-05,
"loss": 3.578,
"step": 994304
},
{
"epoch": 1.0,
"learning_rate": 3.371308135744905e-05,
"loss": 3.5752,
"step": 994816
},
{
"epoch": 1.0,
"learning_rate": 3.370469540993853e-05,
"loss": 3.5775,
"step": 995328
},
{
"epoch": 1.0,
"learning_rate": 3.369630946242801e-05,
"loss": 3.5751,
"step": 995840
},
{
"epoch": 1.0,
"learning_rate": 3.368793989372122e-05,
"loss": 3.5633,
"step": 996352
},
{
"epoch": 1.0,
"learning_rate": 3.36795539462107e-05,
"loss": 3.5691,
"step": 996864
},
{
"epoch": 1.0,
"learning_rate": 3.367116799870018e-05,
"loss": 3.5779,
"step": 997376
},
{
"epoch": 1.0,
"learning_rate": 3.366278205118966e-05,
"loss": 3.584,
"step": 997888
},
{
"epoch": 1.0,
"learning_rate": 3.3654428861286605e-05,
"loss": 3.5833,
"step": 998400
},
{
"epoch": 1.0,
"learning_rate": 3.3646042913776085e-05,
"loss": 3.553,
"step": 998912
},
{
"epoch": 1.0,
"learning_rate": 3.3637656966265565e-05,
"loss": 3.5694,
"step": 999424
},
{
"epoch": 1.0,
"learning_rate": 3.3629271018755045e-05,
"loss": 3.5599,
"step": 999936
},
{
"epoch": 1.0,
"learning_rate": 3.3620885071244525e-05,
"loss": 3.5724,
"step": 1000448
},
{
"epoch": 1.0,
"learning_rate": 3.3612499123734005e-05,
"loss": 3.5712,
"step": 1000960
},
{
"epoch": 1.0,
"learning_rate": 3.3604113176223485e-05,
"loss": 3.5689,
"step": 1001472
},
{
"epoch": 1.0,
"learning_rate": 3.3595727228712965e-05,
"loss": 3.5675,
"step": 1001984
},
{
"epoch": 1.0,
"learning_rate": 3.3587357660006174e-05,
"loss": 3.5886,
"step": 1002496
},
{
"epoch": 1.0,
"learning_rate": 3.3578971712495654e-05,
"loss": 3.5696,
"step": 1003008
},
{
"epoch": 1.0,
"learning_rate": 3.3570585764985134e-05,
"loss": 3.5721,
"step": 1003520
},
{
"epoch": 1.0,
"learning_rate": 3.3562199817474614e-05,
"loss": 3.5694,
"step": 1004032
},
{
"epoch": 1.0,
"learning_rate": 3.355383024876782e-05,
"loss": 3.5784,
"step": 1004544
},
{
"epoch": 1.0,
"learning_rate": 3.35454443012573e-05,
"loss": 3.5707,
"step": 1005056
},
{
"epoch": 1.0,
"learning_rate": 3.353705835374679e-05,
"loss": 3.565,
"step": 1005568
},
{
"epoch": 1.0,
"learning_rate": 3.352867240623626e-05,
"loss": 3.5717,
"step": 1006080
},
{
"epoch": 1.0,
"learning_rate": 3.352030283752948e-05,
"loss": 3.5634,
"step": 1006592
},
{
"epoch": 1.0,
"learning_rate": 3.351191689001896e-05,
"loss": 3.5639,
"step": 1007104
},
{
"epoch": 1.01,
"learning_rate": 3.350353094250844e-05,
"loss": 3.5685,
"step": 1007616
},
{
"epoch": 1.01,
"learning_rate": 3.349514499499791e-05,
"loss": 3.5705,
"step": 1008128
},
{
"epoch": 1.01,
"learning_rate": 3.348677542629113e-05,
"loss": 3.5745,
"step": 1008640
},
{
"epoch": 1.01,
"learning_rate": 3.347838947878061e-05,
"loss": 3.5742,
"step": 1009152
},
{
"epoch": 1.01,
"learning_rate": 3.347000353127009e-05,
"loss": 3.5708,
"step": 1009664
},
{
"epoch": 1.01,
"learning_rate": 3.346161758375956e-05,
"loss": 3.5682,
"step": 1010176
},
{
"epoch": 1.01,
"learning_rate": 3.3453248015052776e-05,
"loss": 3.5826,
"step": 1010688
},
{
"epoch": 1.01,
"learning_rate": 3.3444862067542256e-05,
"loss": 3.5578,
"step": 1011200
},
{
"epoch": 1.01,
"learning_rate": 3.3436476120031736e-05,
"loss": 3.5619,
"step": 1011712
},
{
"epoch": 1.01,
"learning_rate": 3.3428090172521216e-05,
"loss": 3.5683,
"step": 1012224
},
{
"epoch": 1.01,
"learning_rate": 3.341972060381443e-05,
"loss": 3.56,
"step": 1012736
},
{
"epoch": 1.01,
"learning_rate": 3.341133465630391e-05,
"loss": 3.5687,
"step": 1013248
},
{
"epoch": 1.01,
"learning_rate": 3.3402948708793385e-05,
"loss": 3.5689,
"step": 1013760
},
{
"epoch": 1.01,
"learning_rate": 3.3394562761282865e-05,
"loss": 3.5672,
"step": 1014272
},
{
"epoch": 1.01,
"learning_rate": 3.338619319257608e-05,
"loss": 3.5712,
"step": 1014784
},
{
"epoch": 1.01,
"learning_rate": 3.337780724506556e-05,
"loss": 3.5713,
"step": 1015296
},
{
"epoch": 1.01,
"learning_rate": 3.3369421297555034e-05,
"loss": 3.5753,
"step": 1015808
},
{
"epoch": 1.01,
"learning_rate": 3.3361035350044514e-05,
"loss": 3.5662,
"step": 1016320
},
{
"epoch": 1.01,
"learning_rate": 3.335266578133773e-05,
"loss": 3.5533,
"step": 1016832
},
{
"epoch": 1.01,
"learning_rate": 3.334427983382721e-05,
"loss": 3.5719,
"step": 1017344
},
{
"epoch": 1.01,
"learning_rate": 3.333589388631669e-05,
"loss": 3.566,
"step": 1017856
},
{
"epoch": 1.01,
"learning_rate": 3.332750793880617e-05,
"loss": 3.5706,
"step": 1018368
},
{
"epoch": 1.01,
"learning_rate": 3.3319138370099386e-05,
"loss": 3.5637,
"step": 1018880
},
{
"epoch": 1.01,
"learning_rate": 3.331075242258886e-05,
"loss": 3.5612,
"step": 1019392
},
{
"epoch": 1.01,
"learning_rate": 3.330236647507834e-05,
"loss": 3.5553,
"step": 1019904
},
{
"epoch": 1.01,
"learning_rate": 3.329398052756782e-05,
"loss": 3.5608,
"step": 1020416
},
{
"epoch": 1.01,
"learning_rate": 3.3285610958861035e-05,
"loss": 3.567,
"step": 1020928
},
{
"epoch": 1.01,
"learning_rate": 3.327722501135051e-05,
"loss": 3.5534,
"step": 1021440
},
{
"epoch": 1.01,
"learning_rate": 3.326883906383999e-05,
"loss": 3.5783,
"step": 1021952
},
{
"epoch": 1.01,
"learning_rate": 3.326045311632947e-05,
"loss": 3.5689,
"step": 1022464
},
{
"epoch": 1.01,
"learning_rate": 3.3252083547622684e-05,
"loss": 3.547,
"step": 1022976
},
{
"epoch": 1.01,
"learning_rate": 3.3243697600112164e-05,
"loss": 3.5746,
"step": 1023488
},
{
"epoch": 1.01,
"learning_rate": 3.3235311652601644e-05,
"loss": 3.555,
"step": 1024000
},
{
"epoch": 1.01,
"learning_rate": 3.3226925705091124e-05,
"loss": 3.5566,
"step": 1024512
},
{
"epoch": 1.01,
"learning_rate": 3.321855613638433e-05,
"loss": 3.56,
"step": 1025024
},
{
"epoch": 1.01,
"learning_rate": 3.321017018887381e-05,
"loss": 3.5685,
"step": 1025536
},
{
"epoch": 1.01,
"learning_rate": 3.320178424136329e-05,
"loss": 3.55,
"step": 1026048
},
{
"epoch": 1.01,
"learning_rate": 3.319339829385277e-05,
"loss": 3.5674,
"step": 1026560
},
{
"epoch": 1.01,
"learning_rate": 3.318502872514598e-05,
"loss": 3.5455,
"step": 1027072
},
{
"epoch": 1.01,
"learning_rate": 3.317664277763546e-05,
"loss": 3.5568,
"step": 1027584
},
{
"epoch": 1.01,
"learning_rate": 3.316825683012494e-05,
"loss": 3.5726,
"step": 1028096
},
{
"epoch": 1.01,
"learning_rate": 3.315987088261442e-05,
"loss": 3.5621,
"step": 1028608
},
{
"epoch": 1.01,
"learning_rate": 3.315150131390764e-05,
"loss": 3.5702,
"step": 1029120
},
{
"epoch": 1.01,
"learning_rate": 3.314311536639712e-05,
"loss": 3.5622,
"step": 1029632
},
{
"epoch": 1.01,
"learning_rate": 3.31347294188866e-05,
"loss": 3.5781,
"step": 1030144
},
{
"epoch": 1.01,
"learning_rate": 3.312634347137608e-05,
"loss": 3.5531,
"step": 1030656
},
{
"epoch": 1.01,
"learning_rate": 3.3117973902669286e-05,
"loss": 3.5751,
"step": 1031168
},
{
"epoch": 1.01,
"learning_rate": 3.3109587955158766e-05,
"loss": 3.5596,
"step": 1031680
},
{
"epoch": 1.01,
"learning_rate": 3.3101202007648246e-05,
"loss": 3.5597,
"step": 1032192
},
{
"epoch": 1.01,
"learning_rate": 3.3092816060137726e-05,
"loss": 3.5649,
"step": 1032704
},
{
"epoch": 1.01,
"learning_rate": 3.3084446491430935e-05,
"loss": 3.5741,
"step": 1033216
},
{
"epoch": 1.01,
"learning_rate": 3.3076060543920415e-05,
"loss": 3.5628,
"step": 1033728
},
{
"epoch": 1.01,
"learning_rate": 3.3067674596409895e-05,
"loss": 3.5729,
"step": 1034240
},
{
"epoch": 1.01,
"learning_rate": 3.3059288648899375e-05,
"loss": 3.5502,
"step": 1034752
},
{
"epoch": 1.01,
"learning_rate": 3.305091908019259e-05,
"loss": 3.5461,
"step": 1035264
},
{
"epoch": 1.01,
"learning_rate": 3.304253313268207e-05,
"loss": 3.5572,
"step": 1035776
},
{
"epoch": 1.01,
"learning_rate": 3.303414718517155e-05,
"loss": 3.561,
"step": 1036288
},
{
"epoch": 1.01,
"learning_rate": 3.302576123766103e-05,
"loss": 3.5601,
"step": 1036800
},
{
"epoch": 1.01,
"learning_rate": 3.301739166895424e-05,
"loss": 3.5598,
"step": 1037312
},
{
"epoch": 1.01,
"learning_rate": 3.300900572144372e-05,
"loss": 3.5611,
"step": 1037824
},
{
"epoch": 1.02,
"learning_rate": 3.30006197739332e-05,
"loss": 3.5586,
"step": 1038336
},
{
"epoch": 1.02,
"learning_rate": 3.299223382642268e-05,
"loss": 3.5603,
"step": 1038848
},
{
"epoch": 1.02,
"learning_rate": 3.298386425771589e-05,
"loss": 3.5582,
"step": 1039360
},
{
"epoch": 1.02,
"learning_rate": 3.297547831020537e-05,
"loss": 3.57,
"step": 1039872
},
{
"epoch": 1.02,
"learning_rate": 3.296709236269485e-05,
"loss": 3.5734,
"step": 1040384
},
{
"epoch": 1.02,
"learning_rate": 3.295870641518433e-05,
"loss": 3.5722,
"step": 1040896
},
{
"epoch": 1.02,
"learning_rate": 3.2950336846477545e-05,
"loss": 3.5542,
"step": 1041408
},
{
"epoch": 1.02,
"learning_rate": 3.2941950898967025e-05,
"loss": 3.5617,
"step": 1041920
},
{
"epoch": 1.02,
"learning_rate": 3.2933564951456505e-05,
"loss": 3.5588,
"step": 1042432
},
{
"epoch": 1.02,
"learning_rate": 3.2925179003945985e-05,
"loss": 3.5665,
"step": 1042944
},
{
"epoch": 1.02,
"learning_rate": 3.2916809435239194e-05,
"loss": 3.5647,
"step": 1043456
},
{
"epoch": 1.02,
"learning_rate": 3.2908423487728674e-05,
"loss": 3.5586,
"step": 1043968
},
{
"epoch": 1.02,
"learning_rate": 3.2900037540218154e-05,
"loss": 3.5608,
"step": 1044480
},
{
"epoch": 1.02,
"learning_rate": 3.2891651592707634e-05,
"loss": 3.5693,
"step": 1044992
},
{
"epoch": 1.02,
"learning_rate": 3.288328202400084e-05,
"loss": 3.5645,
"step": 1045504
},
{
"epoch": 1.02,
"learning_rate": 3.287489607649032e-05,
"loss": 3.5616,
"step": 1046016
},
{
"epoch": 1.02,
"learning_rate": 3.28665101289798e-05,
"loss": 3.5551,
"step": 1046528
},
{
"epoch": 1.02,
"learning_rate": 3.285812418146928e-05,
"loss": 3.5531,
"step": 1047040
},
{
"epoch": 1.02,
"learning_rate": 3.28497546127625e-05,
"loss": 3.5617,
"step": 1047552
},
{
"epoch": 1.02,
"learning_rate": 3.284136866525198e-05,
"loss": 3.5543,
"step": 1048064
},
{
"epoch": 1.02,
"learning_rate": 3.283298271774146e-05,
"loss": 3.5577,
"step": 1048576
},
{
"epoch": 1.02,
"learning_rate": 3.282459677023094e-05,
"loss": 3.5563,
"step": 1049088
},
{
"epoch": 1.02,
"learning_rate": 3.281622720152415e-05,
"loss": 3.5621,
"step": 1049600
},
{
"epoch": 1.02,
"learning_rate": 3.280784125401363e-05,
"loss": 3.5572,
"step": 1050112
},
{
"epoch": 1.02,
"learning_rate": 3.279945530650311e-05,
"loss": 3.5656,
"step": 1050624
},
{
"epoch": 1.02,
"learning_rate": 3.279106935899259e-05,
"loss": 3.5746,
"step": 1051136
},
{
"epoch": 1.02,
"learning_rate": 3.2782699790285796e-05,
"loss": 3.569,
"step": 1051648
},
{
"epoch": 1.02,
"learning_rate": 3.2774313842775276e-05,
"loss": 3.5679,
"step": 1052160
},
{
"epoch": 1.02,
"learning_rate": 3.2765927895264756e-05,
"loss": 3.5587,
"step": 1052672
},
{
"epoch": 1.02,
"learning_rate": 3.2757541947754236e-05,
"loss": 3.5612,
"step": 1053184
},
{
"epoch": 1.02,
"learning_rate": 3.274917237904745e-05,
"loss": 3.5606,
"step": 1053696
},
{
"epoch": 1.02,
"learning_rate": 3.274078643153693e-05,
"loss": 3.5444,
"step": 1054208
},
{
"epoch": 1.02,
"learning_rate": 3.273240048402641e-05,
"loss": 3.5612,
"step": 1054720
},
{
"epoch": 1.02,
"learning_rate": 3.272401453651589e-05,
"loss": 3.5546,
"step": 1055232
},
{
"epoch": 1.02,
"learning_rate": 3.27156449678091e-05,
"loss": 3.5668,
"step": 1055744
},
{
"epoch": 1.02,
"learning_rate": 3.270725902029858e-05,
"loss": 3.5636,
"step": 1056256
},
{
"epoch": 1.02,
"learning_rate": 3.269887307278806e-05,
"loss": 3.562,
"step": 1056768
},
{
"epoch": 1.02,
"learning_rate": 3.269048712527754e-05,
"loss": 3.554,
"step": 1057280
},
{
"epoch": 1.02,
"learning_rate": 3.268211755657075e-05,
"loss": 3.5534,
"step": 1057792
},
{
"epoch": 1.02,
"learning_rate": 3.267373160906023e-05,
"loss": 3.5684,
"step": 1058304
},
{
"epoch": 1.02,
"learning_rate": 3.266534566154971e-05,
"loss": 3.562,
"step": 1058816
},
{
"epoch": 1.02,
"learning_rate": 3.265695971403919e-05,
"loss": 3.5721,
"step": 1059328
},
{
"epoch": 1.02,
"learning_rate": 3.2648590145332406e-05,
"loss": 3.5572,
"step": 1059840
},
{
"epoch": 1.02,
"learning_rate": 3.2640204197821886e-05,
"loss": 3.568,
"step": 1060352
},
{
"epoch": 1.02,
"learning_rate": 3.2631818250311366e-05,
"loss": 3.5618,
"step": 1060864
},
{
"epoch": 1.02,
"learning_rate": 3.2623432302800846e-05,
"loss": 3.5596,
"step": 1061376
},
{
"epoch": 1.02,
"learning_rate": 3.2615062734094055e-05,
"loss": 3.5655,
"step": 1061888
},
{
"epoch": 1.02,
"learning_rate": 3.2606676786583535e-05,
"loss": 3.5585,
"step": 1062400
},
{
"epoch": 1.02,
"learning_rate": 3.2598290839073015e-05,
"loss": 3.5581,
"step": 1062912
},
{
"epoch": 1.02,
"learning_rate": 3.2589904891562495e-05,
"loss": 3.5712,
"step": 1063424
},
{
"epoch": 1.02,
"learning_rate": 3.2581535322855704e-05,
"loss": 3.5561,
"step": 1063936
},
{
"epoch": 1.02,
"learning_rate": 3.2573149375345184e-05,
"loss": 3.5538,
"step": 1064448
},
{
"epoch": 1.02,
"learning_rate": 3.2564763427834664e-05,
"loss": 3.566,
"step": 1064960
},
{
"epoch": 1.02,
"learning_rate": 3.2556377480324144e-05,
"loss": 3.564,
"step": 1065472
},
{
"epoch": 1.02,
"learning_rate": 3.254800791161736e-05,
"loss": 3.557,
"step": 1065984
},
{
"epoch": 1.02,
"learning_rate": 3.253962196410684e-05,
"loss": 3.5641,
"step": 1066496
},
{
"epoch": 1.02,
"learning_rate": 3.253123601659632e-05,
"loss": 3.5568,
"step": 1067008
},
{
"epoch": 1.02,
"learning_rate": 3.25228500690858e-05,
"loss": 3.5687,
"step": 1067520
},
{
"epoch": 1.02,
"learning_rate": 3.251448050037901e-05,
"loss": 3.56,
"step": 1068032
},
{
"epoch": 1.03,
"eval_loss": 3.8411619663238525,
"eval_runtime": 303.6312,
"eval_samples_per_second": 1256.758,
"eval_steps_per_second": 39.275,
"step": 1068480
},
{
"epoch": 0.0,
"learning_rate": 3.250609455286849e-05,
"loss": 3.5501,
"step": 1068544
},
{
"epoch": 0.0,
"learning_rate": 3.249770860535797e-05,
"loss": 3.5466,
"step": 1069056
},
{
"epoch": 0.0,
"learning_rate": 3.248932265784745e-05,
"loss": 3.5565,
"step": 1069568
},
{
"epoch": 0.0,
"learning_rate": 3.248093671033693e-05,
"loss": 3.5735,
"step": 1070080
},
{
"epoch": 0.0,
"learning_rate": 3.247256714163014e-05,
"loss": 3.5623,
"step": 1070592
},
{
"epoch": 0.0,
"learning_rate": 3.246418119411962e-05,
"loss": 3.5572,
"step": 1071104
},
{
"epoch": 0.0,
"learning_rate": 3.24557952466091e-05,
"loss": 3.5569,
"step": 1071616
},
{
"epoch": 0.0,
"learning_rate": 3.244740929909858e-05,
"loss": 3.559,
"step": 1072128
},
{
"epoch": 0.0,
"learning_rate": 3.243903973039179e-05,
"loss": 3.5466,
"step": 1072640
},
{
"epoch": 0.0,
"learning_rate": 3.243065378288127e-05,
"loss": 3.5586,
"step": 1073152
},
{
"epoch": 0.0,
"learning_rate": 3.242226783537075e-05,
"loss": 3.5572,
"step": 1073664
},
{
"epoch": 0.0,
"learning_rate": 3.241388188786023e-05,
"loss": 3.5712,
"step": 1074176
},
{
"epoch": 0.0,
"learning_rate": 3.240551231915344e-05,
"loss": 3.5661,
"step": 1074688
},
{
"epoch": 0.0,
"learning_rate": 3.239712637164292e-05,
"loss": 3.5358,
"step": 1075200
},
{
"epoch": 0.0,
"learning_rate": 3.23887404241324e-05,
"loss": 3.5564,
"step": 1075712
},
{
"epoch": 0.0,
"learning_rate": 3.238035447662188e-05,
"loss": 3.5446,
"step": 1076224
},
{
"epoch": 0.0,
"learning_rate": 3.237198490791509e-05,
"loss": 3.5543,
"step": 1076736
},
{
"epoch": 0.0,
"learning_rate": 3.236359896040457e-05,
"loss": 3.5525,
"step": 1077248
},
{
"epoch": 0.0,
"learning_rate": 3.235521301289405e-05,
"loss": 3.5567,
"step": 1077760
},
{
"epoch": 0.0,
"learning_rate": 3.234682706538353e-05,
"loss": 3.5483,
"step": 1078272
},
{
"epoch": 0.0,
"learning_rate": 3.233845749667675e-05,
"loss": 3.5715,
"step": 1078784
},
{
"epoch": 0.0,
"learning_rate": 3.233007154916623e-05,
"loss": 3.5535,
"step": 1079296
},
{
"epoch": 0.0,
"learning_rate": 3.232168560165571e-05,
"loss": 3.556,
"step": 1079808
},
{
"epoch": 0.0,
"learning_rate": 3.231329965414518e-05,
"loss": 3.5498,
"step": 1080320
},
{
"epoch": 0.0,
"learning_rate": 3.2304930085438396e-05,
"loss": 3.5685,
"step": 1080832
},
{
"epoch": 0.0,
"learning_rate": 3.2296544137927876e-05,
"loss": 3.5508,
"step": 1081344
},
{
"epoch": 0.0,
"learning_rate": 3.2288158190417356e-05,
"loss": 3.5499,
"step": 1081856
},
{
"epoch": 0.0,
"learning_rate": 3.227977224290683e-05,
"loss": 3.5552,
"step": 1082368
},
{
"epoch": 0.0,
"learning_rate": 3.2271402674200045e-05,
"loss": 3.5506,
"step": 1082880
},
{
"epoch": 0.0,
"learning_rate": 3.2263016726689525e-05,
"loss": 3.5478,
"step": 1083392
},
{
"epoch": 0.01,
"learning_rate": 3.2254630779179005e-05,
"loss": 3.5519,
"step": 1083904
},
{
"epoch": 0.01,
"learning_rate": 3.2246244831668485e-05,
"loss": 3.5523,
"step": 1084416
},
{
"epoch": 0.01,
"learning_rate": 3.22378752629617e-05,
"loss": 3.5578,
"step": 1084928
},
{
"epoch": 0.01,
"learning_rate": 3.222948931545118e-05,
"loss": 3.5578,
"step": 1085440
},
{
"epoch": 0.01,
"learning_rate": 3.2221103367940654e-05,
"loss": 3.5557,
"step": 1085952
},
{
"epoch": 0.01,
"learning_rate": 3.2212717420430134e-05,
"loss": 3.5544,
"step": 1086464
},
{
"epoch": 0.01,
"learning_rate": 3.220434785172335e-05,
"loss": 3.5614,
"step": 1086976
},
{
"epoch": 0.01,
"learning_rate": 3.219596190421283e-05,
"loss": 3.5442,
"step": 1087488
},
{
"epoch": 0.01,
"learning_rate": 3.21875759567023e-05,
"loss": 3.5474,
"step": 1088000
},
{
"epoch": 0.01,
"learning_rate": 3.217919000919178e-05,
"loss": 3.5492,
"step": 1088512
},
{
"epoch": 0.01,
"learning_rate": 3.2170820440485e-05,
"loss": 3.542,
"step": 1089024
},
{
"epoch": 0.01,
"learning_rate": 3.216243449297447e-05,
"loss": 3.5539,
"step": 1089536
},
{
"epoch": 0.01,
"learning_rate": 3.215404854546396e-05,
"loss": 3.5573,
"step": 1090048
},
{
"epoch": 0.01,
"learning_rate": 3.214566259795344e-05,
"loss": 3.5449,
"step": 1090560
},
{
"epoch": 0.01,
"learning_rate": 3.2137293029246654e-05,
"loss": 3.5565,
"step": 1091072
},
{
"epoch": 0.01,
"learning_rate": 3.212890708173613e-05,
"loss": 3.5545,
"step": 1091584
},
{
"epoch": 0.01,
"learning_rate": 3.212052113422561e-05,
"loss": 3.558,
"step": 1092096
},
{
"epoch": 0.01,
"learning_rate": 3.211213518671509e-05,
"loss": 3.5513,
"step": 1092608
},
{
"epoch": 0.01,
"learning_rate": 3.21037656180083e-05,
"loss": 3.5368,
"step": 1093120
},
{
"epoch": 0.01,
"learning_rate": 3.2095379670497776e-05,
"loss": 3.5541,
"step": 1093632
},
{
"epoch": 0.01,
"learning_rate": 3.2086993722987256e-05,
"loss": 3.5545,
"step": 1094144
},
{
"epoch": 0.01,
"learning_rate": 3.2078607775476736e-05,
"loss": 3.5547,
"step": 1094656
},
{
"epoch": 0.01,
"learning_rate": 3.2070238206769945e-05,
"loss": 3.5455,
"step": 1095168
},
{
"epoch": 0.01,
"learning_rate": 3.2061852259259425e-05,
"loss": 3.547,
"step": 1095680
},
{
"epoch": 0.01,
"learning_rate": 3.205348269055264e-05,
"loss": 3.5392,
"step": 1096192
},
{
"epoch": 0.01,
"learning_rate": 3.204509674304213e-05,
"loss": 3.5426,
"step": 1096704
},
{
"epoch": 0.01,
"learning_rate": 3.20367107955316e-05,
"loss": 3.5522,
"step": 1097216
},
{
"epoch": 0.01,
"learning_rate": 3.202832484802108e-05,
"loss": 3.5325,
"step": 1097728
},
{
"epoch": 0.01,
"learning_rate": 3.201993890051056e-05,
"loss": 3.5618,
"step": 1098240
},
{
"epoch": 0.01,
"learning_rate": 3.201155295300004e-05,
"loss": 3.5519,
"step": 1098752
},
{
"epoch": 0.01,
"learning_rate": 3.200316700548952e-05,
"loss": 3.532,
"step": 1099264
},
{
"epoch": 0.01,
"learning_rate": 3.199479743678273e-05,
"loss": 3.5586,
"step": 1099776
},
{
"epoch": 0.01,
"learning_rate": 3.198641148927221e-05,
"loss": 3.5378,
"step": 1100288
},
{
"epoch": 0.01,
"learning_rate": 3.197802554176169e-05,
"loss": 3.5421,
"step": 1100800
},
{
"epoch": 0.01,
"learning_rate": 3.196963959425117e-05,
"loss": 3.5404,
"step": 1101312
},
{
"epoch": 0.01,
"learning_rate": 3.196127002554438e-05,
"loss": 3.5507,
"step": 1101824
},
{
"epoch": 0.01,
"learning_rate": 3.1952884078033866e-05,
"loss": 3.5363,
"step": 1102336
},
{
"epoch": 0.01,
"learning_rate": 3.1944498130523346e-05,
"loss": 3.5529,
"step": 1102848
},
{
"epoch": 0.01,
"learning_rate": 3.1936112183012825e-05,
"loss": 3.5269,
"step": 1103360
},
{
"epoch": 0.01,
"learning_rate": 3.1927742614306035e-05,
"loss": 3.5438,
"step": 1103872
},
{
"epoch": 0.01,
"learning_rate": 3.1919356666795515e-05,
"loss": 3.5554,
"step": 1104384
},
{
"epoch": 0.01,
"learning_rate": 3.1910970719284995e-05,
"loss": 3.5455,
"step": 1104896
},
{
"epoch": 0.01,
"learning_rate": 3.1902584771774474e-05,
"loss": 3.5546,
"step": 1105408
},
{
"epoch": 0.01,
"learning_rate": 3.1894215203067684e-05,
"loss": 3.5482,
"step": 1105920
},
{
"epoch": 0.01,
"learning_rate": 3.1885829255557164e-05,
"loss": 3.5627,
"step": 1106432
},
{
"epoch": 0.01,
"learning_rate": 3.1877443308046643e-05,
"loss": 3.5408,
"step": 1106944
},
{
"epoch": 0.01,
"learning_rate": 3.1869057360536123e-05,
"loss": 3.5601,
"step": 1107456
},
{
"epoch": 0.01,
"learning_rate": 3.186068779182933e-05,
"loss": 3.5403,
"step": 1107968
},
{
"epoch": 0.01,
"learning_rate": 3.185230184431882e-05,
"loss": 3.5451,
"step": 1108480
},
{
"epoch": 0.01,
"learning_rate": 3.184393227561203e-05,
"loss": 3.552,
"step": 1108992
},
{
"epoch": 0.01,
"learning_rate": 3.183554632810151e-05,
"loss": 3.557,
"step": 1109504
},
{
"epoch": 0.01,
"learning_rate": 3.182716038059099e-05,
"loss": 3.549,
"step": 1110016
},
{
"epoch": 0.01,
"learning_rate": 3.181877443308047e-05,
"loss": 3.5567,
"step": 1110528
},
{
"epoch": 0.01,
"learning_rate": 3.181038848556995e-05,
"loss": 3.5364,
"step": 1111040
},
{
"epoch": 0.01,
"learning_rate": 3.180200253805943e-05,
"loss": 3.5273,
"step": 1111552
},
{
"epoch": 0.01,
"learning_rate": 3.179361659054891e-05,
"loss": 3.5438,
"step": 1112064
},
{
"epoch": 0.01,
"learning_rate": 3.178523064303839e-05,
"loss": 3.5454,
"step": 1112576
},
{
"epoch": 0.01,
"learning_rate": 3.17768610743316e-05,
"loss": 3.5463,
"step": 1113088
},
{
"epoch": 0.01,
"learning_rate": 3.176847512682108e-05,
"loss": 3.5413,
"step": 1113600
},
{
"epoch": 0.01,
"learning_rate": 3.176008917931056e-05,
"loss": 3.5477,
"step": 1114112
},
{
"epoch": 0.02,
"learning_rate": 3.175170323180004e-05,
"loss": 3.542,
"step": 1114624
},
{
"epoch": 0.02,
"learning_rate": 3.174333366309325e-05,
"loss": 3.5448,
"step": 1115136
},
{
"epoch": 0.02,
"learning_rate": 3.173494771558273e-05,
"loss": 3.5408,
"step": 1115648
},
{
"epoch": 0.02,
"learning_rate": 3.172656176807221e-05,
"loss": 3.5533,
"step": 1116160
},
{
"epoch": 0.02,
"learning_rate": 3.171817582056169e-05,
"loss": 3.558,
"step": 1116672
},
{
"epoch": 0.02,
"learning_rate": 3.17098062518549e-05,
"loss": 3.5576,
"step": 1117184
},
{
"epoch": 0.02,
"learning_rate": 3.170142030434438e-05,
"loss": 3.5357,
"step": 1117696
},
{
"epoch": 0.02,
"learning_rate": 3.169303435683386e-05,
"loss": 3.5457,
"step": 1118208
},
{
"epoch": 0.02,
"learning_rate": 3.168464840932334e-05,
"loss": 3.546,
"step": 1118720
},
{
"epoch": 0.02,
"learning_rate": 3.167627884061655e-05,
"loss": 3.5505,
"step": 1119232
},
{
"epoch": 0.02,
"learning_rate": 3.166789289310603e-05,
"loss": 3.551,
"step": 1119744
},
{
"epoch": 0.02,
"learning_rate": 3.165950694559551e-05,
"loss": 3.5424,
"step": 1120256
},
{
"epoch": 0.02,
"learning_rate": 3.165112099808499e-05,
"loss": 3.5463,
"step": 1120768
},
{
"epoch": 0.02,
"learning_rate": 3.1642751429378207e-05,
"loss": 3.5488,
"step": 1121280
},
{
"epoch": 0.02,
"learning_rate": 3.1634365481867686e-05,
"loss": 3.5526,
"step": 1121792
},
{
"epoch": 0.02,
"learning_rate": 3.1625979534357166e-05,
"loss": 3.5421,
"step": 1122304
},
{
"epoch": 0.02,
"learning_rate": 3.1617593586846646e-05,
"loss": 3.5464,
"step": 1122816
},
{
"epoch": 0.02,
"learning_rate": 3.1609224018139856e-05,
"loss": 3.5366,
"step": 1123328
},
{
"epoch": 0.02,
"learning_rate": 3.1600838070629335e-05,
"loss": 3.5463,
"step": 1123840
},
{
"epoch": 0.02,
"learning_rate": 3.1592452123118815e-05,
"loss": 3.5379,
"step": 1124352
},
{
"epoch": 0.02,
"learning_rate": 3.1584066175608295e-05,
"loss": 3.5409,
"step": 1124864
},
{
"epoch": 0.02,
"learning_rate": 3.1575696606901504e-05,
"loss": 3.5399,
"step": 1125376
},
{
"epoch": 0.02,
"learning_rate": 3.1567310659390984e-05,
"loss": 3.5497,
"step": 1125888
},
{
"epoch": 0.02,
"learning_rate": 3.1558924711880464e-05,
"loss": 3.5417,
"step": 1126400
},
{
"epoch": 0.02,
"learning_rate": 3.1550538764369944e-05,
"loss": 3.5482,
"step": 1126912
},
{
"epoch": 0.02,
"learning_rate": 3.154216919566316e-05,
"loss": 3.5563,
"step": 1127424
},
{
"epoch": 0.02,
"learning_rate": 3.153378324815264e-05,
"loss": 3.5579,
"step": 1127936
},
{
"epoch": 0.02,
"learning_rate": 3.152539730064212e-05,
"loss": 3.5526,
"step": 1128448
},
{
"epoch": 0.02,
"learning_rate": 3.15170113531316e-05,
"loss": 3.5431,
"step": 1128960
},
{
"epoch": 0.02,
"learning_rate": 3.150864178442481e-05,
"loss": 3.545,
"step": 1129472
},
{
"epoch": 0.02,
"learning_rate": 3.150025583691429e-05,
"loss": 3.5433,
"step": 1129984
},
{
"epoch": 0.02,
"learning_rate": 3.149186988940377e-05,
"loss": 3.532,
"step": 1130496
},
{
"epoch": 0.02,
"learning_rate": 3.148350032069698e-05,
"loss": 3.5472,
"step": 1131008
},
{
"epoch": 0.02,
"learning_rate": 3.147511437318646e-05,
"loss": 3.5404,
"step": 1131520
},
{
"epoch": 0.02,
"learning_rate": 3.146672842567594e-05,
"loss": 3.5529,
"step": 1132032
},
{
"epoch": 0.02,
"learning_rate": 3.145834247816542e-05,
"loss": 3.5433,
"step": 1132544
},
{
"epoch": 0.02,
"learning_rate": 3.144997290945863e-05,
"loss": 3.5473,
"step": 1133056
},
{
"epoch": 0.02,
"learning_rate": 3.1441586961948114e-05,
"loss": 3.5396,
"step": 1133568
},
{
"epoch": 0.02,
"learning_rate": 3.1433201014437594e-05,
"loss": 3.5394,
"step": 1134080
},
{
"epoch": 0.02,
"learning_rate": 3.1424815066927074e-05,
"loss": 3.5513,
"step": 1134592
},
{
"epoch": 0.02,
"learning_rate": 3.141644549822028e-05,
"loss": 3.5453,
"step": 1135104
},
{
"epoch": 0.02,
"learning_rate": 3.140805955070976e-05,
"loss": 3.5596,
"step": 1135616
},
{
"epoch": 0.02,
"learning_rate": 3.139967360319924e-05,
"loss": 3.5416,
"step": 1136128
},
{
"epoch": 0.02,
"learning_rate": 3.139128765568872e-05,
"loss": 3.5512,
"step": 1136640
},
{
"epoch": 0.02,
"learning_rate": 3.138291808698193e-05,
"loss": 3.5482,
"step": 1137152
},
{
"epoch": 0.02,
"learning_rate": 3.137453213947141e-05,
"loss": 3.5453,
"step": 1137664
},
{
"epoch": 0.02,
"learning_rate": 3.136614619196089e-05,
"loss": 3.5468,
"step": 1138176
},
{
"epoch": 0.02,
"learning_rate": 3.135776024445037e-05,
"loss": 3.5421,
"step": 1138688
},
{
"epoch": 0.02,
"learning_rate": 3.134939067574358e-05,
"loss": 3.5493,
"step": 1139200
},
{
"epoch": 0.02,
"learning_rate": 3.134100472823307e-05,
"loss": 3.5533,
"step": 1139712
},
{
"epoch": 0.02,
"learning_rate": 3.133261878072255e-05,
"loss": 3.5427,
"step": 1140224
},
{
"epoch": 0.02,
"learning_rate": 3.132423283321203e-05,
"loss": 3.5384,
"step": 1140736
},
{
"epoch": 0.02,
"learning_rate": 3.1315863264505237e-05,
"loss": 3.5463,
"step": 1141248
},
{
"epoch": 0.02,
"learning_rate": 3.1307477316994717e-05,
"loss": 3.5463,
"step": 1141760
},
{
"epoch": 0.02,
"learning_rate": 3.1299091369484196e-05,
"loss": 3.5408,
"step": 1142272
},
{
"epoch": 0.02,
"learning_rate": 3.1290705421973676e-05,
"loss": 3.5487,
"step": 1142784
},
{
"epoch": 0.02,
"learning_rate": 3.1282335853266886e-05,
"loss": 3.5417,
"step": 1143296
},
{
"epoch": 0.02,
"learning_rate": 3.1273949905756365e-05,
"loss": 3.5572,
"step": 1143808
},
{
"epoch": 0.02,
"learning_rate": 3.1265563958245845e-05,
"loss": 3.5407,
"step": 1144320
},
{
"epoch": 0.03,
"eval_loss": 3.841902732849121,
"eval_runtime": 302.5858,
"eval_samples_per_second": 1261.1,
"eval_steps_per_second": 39.41,
"step": 1144800
},
{
"epoch": 1.0,
"learning_rate": 3.1257178010735325e-05,
"loss": 3.5386,
"step": 1144832
},
{
"epoch": 1.0,
"learning_rate": 3.1248792063224805e-05,
"loss": 3.534,
"step": 1145344
},
{
"epoch": 1.0,
"learning_rate": 3.124042249451802e-05,
"loss": 3.5385,
"step": 1145856
},
{
"epoch": 1.0,
"learning_rate": 3.12320365470075e-05,
"loss": 3.5565,
"step": 1146368
},
{
"epoch": 1.0,
"learning_rate": 3.1223650599496974e-05,
"loss": 3.5459,
"step": 1146880
},
{
"epoch": 1.0,
"learning_rate": 3.1215264651986454e-05,
"loss": 3.5446,
"step": 1147392
},
{
"epoch": 1.0,
"learning_rate": 3.120689508327967e-05,
"loss": 3.5403,
"step": 1147904
},
{
"epoch": 1.0,
"learning_rate": 3.119850913576915e-05,
"loss": 3.5427,
"step": 1148416
},
{
"epoch": 1.0,
"learning_rate": 3.119012318825862e-05,
"loss": 3.5339,
"step": 1148928
},
{
"epoch": 1.0,
"learning_rate": 3.11817372407481e-05,
"loss": 3.5412,
"step": 1149440
},
{
"epoch": 1.0,
"learning_rate": 3.117335129323758e-05,
"loss": 3.5402,
"step": 1149952
},
{
"epoch": 1.0,
"learning_rate": 3.116496534572706e-05,
"loss": 3.5561,
"step": 1150464
},
{
"epoch": 1.0,
"learning_rate": 3.115659577702027e-05,
"loss": 3.5498,
"step": 1150976
},
{
"epoch": 1.0,
"learning_rate": 3.114820982950976e-05,
"loss": 3.5221,
"step": 1151488
},
{
"epoch": 1.0,
"learning_rate": 3.113982388199924e-05,
"loss": 3.5395,
"step": 1152000
},
{
"epoch": 1.0,
"learning_rate": 3.113143793448872e-05,
"loss": 3.5294,
"step": 1152512
},
{
"epoch": 1.0,
"learning_rate": 3.11230519869782e-05,
"loss": 3.5394,
"step": 1153024
},
{
"epoch": 1.0,
"learning_rate": 3.111466603946768e-05,
"loss": 3.5371,
"step": 1153536
},
{
"epoch": 1.0,
"learning_rate": 3.110628009195716e-05,
"loss": 3.5423,
"step": 1154048
},
{
"epoch": 1.0,
"learning_rate": 3.109789414444664e-05,
"loss": 3.5342,
"step": 1154560
},
{
"epoch": 1.0,
"learning_rate": 3.108952457573985e-05,
"loss": 3.5571,
"step": 1155072
},
{
"epoch": 1.0,
"learning_rate": 3.108113862822933e-05,
"loss": 3.541,
"step": 1155584
},
{
"epoch": 1.0,
"learning_rate": 3.107275268071881e-05,
"loss": 3.5367,
"step": 1156096
},
{
"epoch": 1.0,
"learning_rate": 3.106436673320829e-05,
"loss": 3.5338,
"step": 1156608
},
{
"epoch": 1.0,
"learning_rate": 3.10559971645015e-05,
"loss": 3.5535,
"step": 1157120
},
{
"epoch": 1.0,
"learning_rate": 3.104761121699098e-05,
"loss": 3.5338,
"step": 1157632
},
{
"epoch": 1.0,
"learning_rate": 3.103922526948046e-05,
"loss": 3.5315,
"step": 1158144
},
{
"epoch": 1.0,
"learning_rate": 3.103083932196994e-05,
"loss": 3.5436,
"step": 1158656
},
{
"epoch": 1.0,
"learning_rate": 3.102246975326315e-05,
"loss": 3.532,
"step": 1159168
},
{
"epoch": 1.0,
"learning_rate": 3.101408380575263e-05,
"loss": 3.5326,
"step": 1159680
},
{
"epoch": 1.01,
"learning_rate": 3.100569785824211e-05,
"loss": 3.5379,
"step": 1160192
},
{
"epoch": 1.01,
"learning_rate": 3.099731191073159e-05,
"loss": 3.5374,
"step": 1160704
},
{
"epoch": 1.01,
"learning_rate": 3.09889423420248e-05,
"loss": 3.5415,
"step": 1161216
},
{
"epoch": 1.01,
"learning_rate": 3.098055639451428e-05,
"loss": 3.5405,
"step": 1161728
},
{
"epoch": 1.01,
"learning_rate": 3.097217044700376e-05,
"loss": 3.5452,
"step": 1162240
},
{
"epoch": 1.01,
"learning_rate": 3.096378449949324e-05,
"loss": 3.5371,
"step": 1162752
},
{
"epoch": 1.01,
"learning_rate": 3.095541493078645e-05,
"loss": 3.5443,
"step": 1163264
},
{
"epoch": 1.01,
"learning_rate": 3.094702898327593e-05,
"loss": 3.531,
"step": 1163776
},
{
"epoch": 1.01,
"learning_rate": 3.093864303576541e-05,
"loss": 3.5349,
"step": 1164288
},
{
"epoch": 1.01,
"learning_rate": 3.093025708825489e-05,
"loss": 3.5316,
"step": 1164800
},
{
"epoch": 1.01,
"learning_rate": 3.0921887519548106e-05,
"loss": 3.531,
"step": 1165312
},
{
"epoch": 1.01,
"learning_rate": 3.0913501572037586e-05,
"loss": 3.5332,
"step": 1165824
},
{
"epoch": 1.01,
"learning_rate": 3.0905115624527066e-05,
"loss": 3.5424,
"step": 1166336
},
{
"epoch": 1.01,
"learning_rate": 3.0896729677016546e-05,
"loss": 3.5314,
"step": 1166848
},
{
"epoch": 1.01,
"learning_rate": 3.0888360108309755e-05,
"loss": 3.5406,
"step": 1167360
},
{
"epoch": 1.01,
"learning_rate": 3.0879974160799235e-05,
"loss": 3.5429,
"step": 1167872
},
{
"epoch": 1.01,
"learning_rate": 3.0871588213288715e-05,
"loss": 3.5426,
"step": 1168384
},
{
"epoch": 1.01,
"learning_rate": 3.0863202265778195e-05,
"loss": 3.5356,
"step": 1168896
},
{
"epoch": 1.01,
"learning_rate": 3.0854832697071404e-05,
"loss": 3.5205,
"step": 1169408
},
{
"epoch": 1.01,
"learning_rate": 3.0846446749560884e-05,
"loss": 3.5392,
"step": 1169920
},
{
"epoch": 1.01,
"learning_rate": 3.0838060802050364e-05,
"loss": 3.542,
"step": 1170432
},
{
"epoch": 1.01,
"learning_rate": 3.0829674854539844e-05,
"loss": 3.5395,
"step": 1170944
},
{
"epoch": 1.01,
"learning_rate": 3.082130528583306e-05,
"loss": 3.5291,
"step": 1171456
},
{
"epoch": 1.01,
"learning_rate": 3.081291933832254e-05,
"loss": 3.5323,
"step": 1171968
},
{
"epoch": 1.01,
"learning_rate": 3.080454976961575e-05,
"loss": 3.5231,
"step": 1172480
},
{
"epoch": 1.01,
"learning_rate": 3.079616382210523e-05,
"loss": 3.5235,
"step": 1172992
},
{
"epoch": 1.01,
"learning_rate": 3.078777787459471e-05,
"loss": 3.5392,
"step": 1173504
},
{
"epoch": 1.01,
"learning_rate": 3.077939192708419e-05,
"loss": 3.5224,
"step": 1174016
},
{
"epoch": 1.01,
"learning_rate": 3.077100597957367e-05,
"loss": 3.5435,
"step": 1174528
},
{
"epoch": 1.01,
"learning_rate": 3.076262003206315e-05,
"loss": 3.5332,
"step": 1175040
},
{
"epoch": 1.01,
"learning_rate": 3.075423408455263e-05,
"loss": 3.5247,
"step": 1175552
},
{
"epoch": 1.01,
"learning_rate": 3.074586451584584e-05,
"loss": 3.542,
"step": 1176064
},
{
"epoch": 1.01,
"learning_rate": 3.073747856833532e-05,
"loss": 3.5221,
"step": 1176576
},
{
"epoch": 1.01,
"learning_rate": 3.07290926208248e-05,
"loss": 3.5274,
"step": 1177088
},
{
"epoch": 1.01,
"learning_rate": 3.0720706673314284e-05,
"loss": 3.5249,
"step": 1177600
},
{
"epoch": 1.01,
"learning_rate": 3.071232072580376e-05,
"loss": 3.5387,
"step": 1178112
},
{
"epoch": 1.01,
"learning_rate": 3.0703951157096973e-05,
"loss": 3.5208,
"step": 1178624
},
{
"epoch": 1.01,
"learning_rate": 3.0695565209586453e-05,
"loss": 3.5339,
"step": 1179136
},
{
"epoch": 1.01,
"learning_rate": 3.068717926207593e-05,
"loss": 3.5119,
"step": 1179648
},
{
"epoch": 1.01,
"learning_rate": 3.067880969336914e-05,
"loss": 3.5278,
"step": 1180160
},
{
"epoch": 1.01,
"learning_rate": 3.067042374585862e-05,
"loss": 3.5418,
"step": 1180672
},
{
"epoch": 1.01,
"learning_rate": 3.06620377983481e-05,
"loss": 3.5332,
"step": 1181184
},
{
"epoch": 1.01,
"learning_rate": 3.0653651850837576e-05,
"loss": 3.5369,
"step": 1181696
},
{
"epoch": 1.01,
"learning_rate": 3.064528228213079e-05,
"loss": 3.5362,
"step": 1182208
},
{
"epoch": 1.01,
"learning_rate": 3.063689633462027e-05,
"loss": 3.5435,
"step": 1182720
},
{
"epoch": 1.01,
"learning_rate": 3.062851038710975e-05,
"loss": 3.5277,
"step": 1183232
},
{
"epoch": 1.01,
"learning_rate": 3.062012443959923e-05,
"loss": 3.5436,
"step": 1183744
},
{
"epoch": 1.01,
"learning_rate": 3.061175487089245e-05,
"loss": 3.5229,
"step": 1184256
},
{
"epoch": 1.01,
"learning_rate": 3.060336892338193e-05,
"loss": 3.5298,
"step": 1184768
},
{
"epoch": 1.01,
"learning_rate": 3.0594999354675136e-05,
"loss": 3.5323,
"step": 1185280
},
{
"epoch": 1.01,
"learning_rate": 3.0586613407164616e-05,
"loss": 3.5422,
"step": 1185792
},
{
"epoch": 1.01,
"learning_rate": 3.0578227459654096e-05,
"loss": 3.5317,
"step": 1186304
},
{
"epoch": 1.01,
"learning_rate": 3.0569841512143576e-05,
"loss": 3.5457,
"step": 1186816
},
{
"epoch": 1.01,
"learning_rate": 3.056145556463305e-05,
"loss": 3.5256,
"step": 1187328
},
{
"epoch": 1.01,
"learning_rate": 3.055306961712253e-05,
"loss": 3.5151,
"step": 1187840
},
{
"epoch": 1.01,
"learning_rate": 3.054468366961201e-05,
"loss": 3.5268,
"step": 1188352
},
{
"epoch": 1.01,
"learning_rate": 3.053629772210149e-05,
"loss": 3.5328,
"step": 1188864
},
{
"epoch": 1.01,
"learning_rate": 3.0527928153394705e-05,
"loss": 3.5286,
"step": 1189376
},
{
"epoch": 1.01,
"learning_rate": 3.0519542205884185e-05,
"loss": 3.5273,
"step": 1189888
},
{
"epoch": 1.01,
"learning_rate": 3.051115625837366e-05,
"loss": 3.5337,
"step": 1190400
},
{
"epoch": 1.02,
"learning_rate": 3.0502770310863145e-05,
"loss": 3.5261,
"step": 1190912
},
{
"epoch": 1.02,
"learning_rate": 3.0494400742156354e-05,
"loss": 3.5282,
"step": 1191424
},
{
"epoch": 1.02,
"learning_rate": 3.0486014794645834e-05,
"loss": 3.5271,
"step": 1191936
},
{
"epoch": 1.02,
"learning_rate": 3.0477628847135314e-05,
"loss": 3.5395,
"step": 1192448
},
{
"epoch": 1.02,
"learning_rate": 3.0469242899624794e-05,
"loss": 3.542,
"step": 1192960
},
{
"epoch": 1.02,
"learning_rate": 3.0460873330918006e-05,
"loss": 3.5406,
"step": 1193472
},
{
"epoch": 1.02,
"learning_rate": 3.0452487383407486e-05,
"loss": 3.524,
"step": 1193984
},
{
"epoch": 1.02,
"learning_rate": 3.0444101435896966e-05,
"loss": 3.534,
"step": 1194496
},
{
"epoch": 1.02,
"learning_rate": 3.0435715488386446e-05,
"loss": 3.5285,
"step": 1195008
},
{
"epoch": 1.02,
"learning_rate": 3.0427345919679655e-05,
"loss": 3.5355,
"step": 1195520
},
{
"epoch": 1.02,
"learning_rate": 3.0418959972169135e-05,
"loss": 3.5362,
"step": 1196032
},
{
"epoch": 1.02,
"learning_rate": 3.0410574024658615e-05,
"loss": 3.5272,
"step": 1196544
},
{
"epoch": 1.02,
"learning_rate": 3.04021880771481e-05,
"loss": 3.5308,
"step": 1197056
},
{
"epoch": 1.02,
"learning_rate": 3.0393818508441308e-05,
"loss": 3.5368,
"step": 1197568
},
{
"epoch": 1.02,
"learning_rate": 3.0385432560930788e-05,
"loss": 3.5358,
"step": 1198080
},
{
"epoch": 1.02,
"learning_rate": 3.0377046613420268e-05,
"loss": 3.5285,
"step": 1198592
},
{
"epoch": 1.02,
"learning_rate": 3.0368660665909747e-05,
"loss": 3.5311,
"step": 1199104
},
{
"epoch": 1.02,
"learning_rate": 3.036029109720296e-05,
"loss": 3.5209,
"step": 1199616
},
{
"epoch": 1.02,
"learning_rate": 3.035190514969244e-05,
"loss": 3.5293,
"step": 1200128
},
{
"epoch": 1.02,
"learning_rate": 3.034351920218192e-05,
"loss": 3.5223,
"step": 1200640
},
{
"epoch": 1.02,
"learning_rate": 3.03351332546714e-05,
"loss": 3.5259,
"step": 1201152
},
{
"epoch": 1.02,
"learning_rate": 3.032676368596461e-05,
"loss": 3.523,
"step": 1201664
},
{
"epoch": 1.02,
"learning_rate": 3.031837773845409e-05,
"loss": 3.5356,
"step": 1202176
},
{
"epoch": 1.02,
"learning_rate": 3.030999179094357e-05,
"loss": 3.5291,
"step": 1202688
},
{
"epoch": 1.02,
"learning_rate": 3.0301605843433052e-05,
"loss": 3.5287,
"step": 1203200
},
{
"epoch": 1.02,
"learning_rate": 3.029323627472626e-05,
"loss": 3.5441,
"step": 1203712
},
{
"epoch": 1.02,
"learning_rate": 3.028485032721574e-05,
"loss": 3.5427,
"step": 1204224
},
{
"epoch": 1.02,
"learning_rate": 3.027646437970522e-05,
"loss": 3.5402,
"step": 1204736
},
{
"epoch": 1.02,
"learning_rate": 3.02680784321947e-05,
"loss": 3.5276,
"step": 1205248
},
{
"epoch": 1.02,
"learning_rate": 3.0259708863487914e-05,
"loss": 3.5312,
"step": 1205760
},
{
"epoch": 1.02,
"learning_rate": 3.0251322915977394e-05,
"loss": 3.5257,
"step": 1206272
},
{
"epoch": 1.02,
"learning_rate": 3.0242936968466874e-05,
"loss": 3.5194,
"step": 1206784
},
{
"epoch": 1.02,
"learning_rate": 3.0234551020956354e-05,
"loss": 3.5308,
"step": 1207296
},
{
"epoch": 1.02,
"learning_rate": 3.0226181452249563e-05,
"loss": 3.5273,
"step": 1207808
},
{
"epoch": 1.02,
"learning_rate": 3.0217795504739043e-05,
"loss": 3.5331,
"step": 1208320
},
{
"epoch": 1.02,
"learning_rate": 3.0209409557228523e-05,
"loss": 3.5281,
"step": 1208832
},
{
"epoch": 1.02,
"learning_rate": 3.0201039988521735e-05,
"loss": 3.5344,
"step": 1209344
},
{
"epoch": 1.02,
"learning_rate": 3.0192654041011215e-05,
"loss": 3.5285,
"step": 1209856
},
{
"epoch": 1.02,
"learning_rate": 3.0184268093500695e-05,
"loss": 3.5235,
"step": 1210368
},
{
"epoch": 1.02,
"learning_rate": 3.0175882145990175e-05,
"loss": 3.53,
"step": 1210880
},
{
"epoch": 1.02,
"learning_rate": 3.0167496198479655e-05,
"loss": 3.5356,
"step": 1211392
},
{
"epoch": 1.02,
"learning_rate": 3.0159126629772867e-05,
"loss": 3.5419,
"step": 1211904
},
{
"epoch": 1.02,
"learning_rate": 3.0150740682262347e-05,
"loss": 3.529,
"step": 1212416
},
{
"epoch": 1.02,
"learning_rate": 3.0142354734751827e-05,
"loss": 3.5364,
"step": 1212928
},
{
"epoch": 1.02,
"learning_rate": 3.0133968787241307e-05,
"loss": 3.5336,
"step": 1213440
},
{
"epoch": 1.02,
"learning_rate": 3.0125599218534516e-05,
"loss": 3.5308,
"step": 1213952
},
{
"epoch": 1.02,
"learning_rate": 3.0117213271023996e-05,
"loss": 3.5325,
"step": 1214464
},
{
"epoch": 1.02,
"learning_rate": 3.0108827323513476e-05,
"loss": 3.5281,
"step": 1214976
},
{
"epoch": 1.02,
"learning_rate": 3.010045775480669e-05,
"loss": 3.5354,
"step": 1215488
},
{
"epoch": 1.02,
"learning_rate": 3.009207180729617e-05,
"loss": 3.5405,
"step": 1216000
},
{
"epoch": 1.02,
"learning_rate": 3.008368585978565e-05,
"loss": 3.5279,
"step": 1216512
},
{
"epoch": 1.02,
"learning_rate": 3.007529991227513e-05,
"loss": 3.5249,
"step": 1217024
},
{
"epoch": 1.02,
"learning_rate": 3.0066930343568338e-05,
"loss": 3.5309,
"step": 1217536
},
{
"epoch": 1.02,
"learning_rate": 3.005854439605782e-05,
"loss": 3.5326,
"step": 1218048
},
{
"epoch": 1.02,
"learning_rate": 3.00501584485473e-05,
"loss": 3.5239,
"step": 1218560
},
{
"epoch": 1.02,
"learning_rate": 3.004177250103678e-05,
"loss": 3.5365,
"step": 1219072
},
{
"epoch": 1.02,
"learning_rate": 3.003340293232999e-05,
"loss": 3.5266,
"step": 1219584
},
{
"epoch": 1.02,
"learning_rate": 3.002501698481947e-05,
"loss": 3.5399,
"step": 1220096
},
{
"epoch": 1.02,
"learning_rate": 3.001663103730895e-05,
"loss": 3.5284,
"step": 1220608
},
{
"epoch": 1.03,
"learning_rate": 3.000824508979843e-05,
"loss": 3.5278,
"step": 1221120
},
{
"epoch": 1.03,
"eval_loss": 3.8411803245544434,
"eval_runtime": 303.1028,
"eval_samples_per_second": 1258.949,
"eval_steps_per_second": 39.343,
"step": 1221120
},
{
"epoch": 0.0,
"learning_rate": 2.9999859142287913e-05,
"loss": 3.5191,
"step": 1221632
},
{
"epoch": 0.0,
"learning_rate": 2.9991473194777393e-05,
"loss": 3.524,
"step": 1222144
},
{
"epoch": 0.0,
"learning_rate": 2.9983087247266873e-05,
"loss": 3.5414,
"step": 1222656
},
{
"epoch": 0.0,
"learning_rate": 2.9974717678560082e-05,
"loss": 3.534,
"step": 1223168
},
{
"epoch": 0.0,
"learning_rate": 2.9966331731049562e-05,
"loss": 3.5299,
"step": 1223680
},
{
"epoch": 0.0,
"learning_rate": 2.9957945783539042e-05,
"loss": 3.526,
"step": 1224192
},
{
"epoch": 0.0,
"learning_rate": 2.9949559836028522e-05,
"loss": 3.5279,
"step": 1224704
},
{
"epoch": 0.0,
"learning_rate": 2.9941190267321735e-05,
"loss": 3.5122,
"step": 1225216
},
{
"epoch": 0.0,
"learning_rate": 2.9932804319811215e-05,
"loss": 3.5323,
"step": 1225728
},
{
"epoch": 0.0,
"learning_rate": 2.9924418372300694e-05,
"loss": 3.5209,
"step": 1226240
},
{
"epoch": 0.0,
"learning_rate": 2.9916032424790174e-05,
"loss": 3.5456,
"step": 1226752
},
{
"epoch": 0.0,
"learning_rate": 2.9907679234887116e-05,
"loss": 3.5336,
"step": 1227264
},
{
"epoch": 0.0,
"learning_rate": 2.9899293287376596e-05,
"loss": 3.509,
"step": 1227776
},
{
"epoch": 0.0,
"learning_rate": 2.9890907339866076e-05,
"loss": 3.5209,
"step": 1228288
},
{
"epoch": 0.0,
"learning_rate": 2.9882521392355556e-05,
"loss": 3.5204,
"step": 1228800
},
{
"epoch": 0.0,
"learning_rate": 2.9874135444845036e-05,
"loss": 3.5196,
"step": 1229312
},
{
"epoch": 0.0,
"learning_rate": 2.9865749497334516e-05,
"loss": 3.5271,
"step": 1229824
},
{
"epoch": 0.0,
"learning_rate": 2.9857363549823996e-05,
"loss": 3.5296,
"step": 1230336
},
{
"epoch": 0.0,
"learning_rate": 2.9848977602313476e-05,
"loss": 3.5172,
"step": 1230848
},
{
"epoch": 0.0,
"learning_rate": 2.9840608033606688e-05,
"loss": 3.5436,
"step": 1231360
},
{
"epoch": 0.0,
"learning_rate": 2.9832222086096168e-05,
"loss": 3.524,
"step": 1231872
},
{
"epoch": 0.0,
"learning_rate": 2.9823836138585648e-05,
"loss": 3.5246,
"step": 1232384
},
{
"epoch": 0.0,
"learning_rate": 2.9815450191075128e-05,
"loss": 3.5231,
"step": 1232896
},
{
"epoch": 0.0,
"learning_rate": 2.9807080622368337e-05,
"loss": 3.5384,
"step": 1233408
},
{
"epoch": 0.0,
"learning_rate": 2.979869467485782e-05,
"loss": 3.5197,
"step": 1233920
},
{
"epoch": 0.0,
"learning_rate": 2.97903087273473e-05,
"loss": 3.5209,
"step": 1234432
},
{
"epoch": 0.0,
"learning_rate": 2.978192277983678e-05,
"loss": 3.5279,
"step": 1234944
},
{
"epoch": 0.0,
"learning_rate": 2.977355321112999e-05,
"loss": 3.5201,
"step": 1235456
},
{
"epoch": 0.0,
"learning_rate": 2.976516726361947e-05,
"loss": 3.5191,
"step": 1235968
},
{
"epoch": 0.01,
"learning_rate": 2.975678131610895e-05,
"loss": 3.5208,
"step": 1236480
},
{
"epoch": 0.01,
"learning_rate": 2.9748395368598426e-05,
"loss": 3.5244,
"step": 1236992
},
{
"epoch": 0.01,
"learning_rate": 2.9740025799891642e-05,
"loss": 3.5268,
"step": 1237504
},
{
"epoch": 0.01,
"learning_rate": 2.9731639852381122e-05,
"loss": 3.5266,
"step": 1238016
},
{
"epoch": 0.01,
"learning_rate": 2.9723253904870602e-05,
"loss": 3.5283,
"step": 1238528
},
{
"epoch": 0.01,
"learning_rate": 2.9714867957360075e-05,
"loss": 3.5257,
"step": 1239040
},
{
"epoch": 0.01,
"learning_rate": 2.970649838865329e-05,
"loss": 3.5314,
"step": 1239552
},
{
"epoch": 0.01,
"learning_rate": 2.969811244114277e-05,
"loss": 3.5209,
"step": 1240064
},
{
"epoch": 0.01,
"learning_rate": 2.9689726493632254e-05,
"loss": 3.5201,
"step": 1240576
},
{
"epoch": 0.01,
"learning_rate": 2.9681340546121727e-05,
"loss": 3.5152,
"step": 1241088
},
{
"epoch": 0.01,
"learning_rate": 2.9672970977414943e-05,
"loss": 3.5207,
"step": 1241600
},
{
"epoch": 0.01,
"learning_rate": 2.9664585029904423e-05,
"loss": 3.517,
"step": 1242112
},
{
"epoch": 0.01,
"learning_rate": 2.96561990823939e-05,
"loss": 3.5274,
"step": 1242624
},
{
"epoch": 0.01,
"learning_rate": 2.964781313488338e-05,
"loss": 3.5185,
"step": 1243136
},
{
"epoch": 0.01,
"learning_rate": 2.9639443566176596e-05,
"loss": 3.5264,
"step": 1243648
},
{
"epoch": 0.01,
"learning_rate": 2.9631057618666076e-05,
"loss": 3.5248,
"step": 1244160
},
{
"epoch": 0.01,
"learning_rate": 2.962267167115555e-05,
"loss": 3.5321,
"step": 1244672
},
{
"epoch": 0.01,
"learning_rate": 2.961428572364503e-05,
"loss": 3.5194,
"step": 1245184
},
{
"epoch": 0.01,
"learning_rate": 2.9605916154938245e-05,
"loss": 3.5096,
"step": 1245696
},
{
"epoch": 0.01,
"learning_rate": 2.9597530207427724e-05,
"loss": 3.515,
"step": 1246208
},
{
"epoch": 0.01,
"learning_rate": 2.95891442599172e-05,
"loss": 3.533,
"step": 1246720
},
{
"epoch": 0.01,
"learning_rate": 2.958075831240668e-05,
"loss": 3.5226,
"step": 1247232
},
{
"epoch": 0.01,
"learning_rate": 2.9572388743699897e-05,
"loss": 3.5139,
"step": 1247744
},
{
"epoch": 0.01,
"learning_rate": 2.956400279618937e-05,
"loss": 3.5147,
"step": 1248256
},
{
"epoch": 0.01,
"learning_rate": 2.9555633227482586e-05,
"loss": 3.5181,
"step": 1248768
},
{
"epoch": 0.01,
"learning_rate": 2.954724727997207e-05,
"loss": 3.5064,
"step": 1249280
},
{
"epoch": 0.01,
"learning_rate": 2.953886133246155e-05,
"loss": 3.5292,
"step": 1249792
},
{
"epoch": 0.01,
"learning_rate": 2.9530475384951022e-05,
"loss": 3.5093,
"step": 1250304
},
{
"epoch": 0.01,
"learning_rate": 2.9522089437440502e-05,
"loss": 3.524,
"step": 1250816
},
{
"epoch": 0.01,
"learning_rate": 2.9513703489929982e-05,
"loss": 3.5217,
"step": 1251328
},
{
"epoch": 0.01,
"learning_rate": 2.9505317542419462e-05,
"loss": 3.5067,
"step": 1251840
},
{
"epoch": 0.01,
"learning_rate": 2.9496947973712675e-05,
"loss": 3.5272,
"step": 1252352
},
{
"epoch": 0.01,
"learning_rate": 2.9488562026202155e-05,
"loss": 3.5097,
"step": 1252864
},
{
"epoch": 0.01,
"learning_rate": 2.9480176078691635e-05,
"loss": 3.5181,
"step": 1253376
},
{
"epoch": 0.01,
"learning_rate": 2.9471790131181115e-05,
"loss": 3.5063,
"step": 1253888
},
{
"epoch": 0.01,
"learning_rate": 2.9463404183670595e-05,
"loss": 3.5285,
"step": 1254400
},
{
"epoch": 0.01,
"learning_rate": 2.9455034614963807e-05,
"loss": 3.5102,
"step": 1254912
},
{
"epoch": 0.01,
"learning_rate": 2.9446665046257023e-05,
"loss": 3.5142,
"step": 1255424
},
{
"epoch": 0.01,
"learning_rate": 2.9438279098746496e-05,
"loss": 3.5039,
"step": 1255936
},
{
"epoch": 0.01,
"learning_rate": 2.9429893151235976e-05,
"loss": 3.511,
"step": 1256448
},
{
"epoch": 0.01,
"learning_rate": 2.9421507203725456e-05,
"loss": 3.5243,
"step": 1256960
},
{
"epoch": 0.01,
"learning_rate": 2.9413121256214936e-05,
"loss": 3.5254,
"step": 1257472
},
{
"epoch": 0.01,
"learning_rate": 2.9404735308704416e-05,
"loss": 3.5228,
"step": 1257984
},
{
"epoch": 0.01,
"learning_rate": 2.93963493611939e-05,
"loss": 3.5205,
"step": 1258496
},
{
"epoch": 0.01,
"learning_rate": 2.938797979248711e-05,
"loss": 3.5274,
"step": 1259008
},
{
"epoch": 0.01,
"learning_rate": 2.937959384497659e-05,
"loss": 3.5143,
"step": 1259520
},
{
"epoch": 0.01,
"learning_rate": 2.9371207897466068e-05,
"loss": 3.5335,
"step": 1260032
},
{
"epoch": 0.01,
"learning_rate": 2.9362821949955548e-05,
"loss": 3.5112,
"step": 1260544
},
{
"epoch": 0.01,
"learning_rate": 2.935445238124876e-05,
"loss": 3.5124,
"step": 1261056
},
{
"epoch": 0.01,
"learning_rate": 2.934606643373824e-05,
"loss": 3.519,
"step": 1261568
},
{
"epoch": 0.01,
"learning_rate": 2.933768048622772e-05,
"loss": 3.5259,
"step": 1262080
},
{
"epoch": 0.01,
"learning_rate": 2.93292945387172e-05,
"loss": 3.5188,
"step": 1262592
},
{
"epoch": 0.01,
"learning_rate": 2.932092497001041e-05,
"loss": 3.53,
"step": 1263104
},
{
"epoch": 0.01,
"learning_rate": 2.931253902249989e-05,
"loss": 3.5152,
"step": 1263616
},
{
"epoch": 0.01,
"learning_rate": 2.930415307498937e-05,
"loss": 3.4962,
"step": 1264128
},
{
"epoch": 0.01,
"learning_rate": 2.9295767127478853e-05,
"loss": 3.5114,
"step": 1264640
},
{
"epoch": 0.01,
"learning_rate": 2.9287397558772062e-05,
"loss": 3.5174,
"step": 1265152
},
{
"epoch": 0.01,
"learning_rate": 2.9279011611261542e-05,
"loss": 3.5159,
"step": 1265664
},
{
"epoch": 0.01,
"learning_rate": 2.9270625663751022e-05,
"loss": 3.5131,
"step": 1266176
},
{
"epoch": 0.01,
"learning_rate": 2.9262239716240502e-05,
"loss": 3.5204,
"step": 1266688
},
{
"epoch": 0.02,
"learning_rate": 2.9253870147533714e-05,
"loss": 3.5108,
"step": 1267200
},
{
"epoch": 0.02,
"learning_rate": 2.9245484200023194e-05,
"loss": 3.5178,
"step": 1267712
},
{
"epoch": 0.02,
"learning_rate": 2.9237098252512674e-05,
"loss": 3.5158,
"step": 1268224
},
{
"epoch": 0.02,
"learning_rate": 2.9228712305002154e-05,
"loss": 3.5245,
"step": 1268736
},
{
"epoch": 0.02,
"learning_rate": 2.9220342736295363e-05,
"loss": 3.5297,
"step": 1269248
},
{
"epoch": 0.02,
"learning_rate": 2.9211956788784843e-05,
"loss": 3.5316,
"step": 1269760
},
{
"epoch": 0.02,
"learning_rate": 2.9203570841274323e-05,
"loss": 3.5045,
"step": 1270272
},
{
"epoch": 0.02,
"learning_rate": 2.9195184893763807e-05,
"loss": 3.5201,
"step": 1270784
},
{
"epoch": 0.02,
"learning_rate": 2.9186815325057016e-05,
"loss": 3.5177,
"step": 1271296
},
{
"epoch": 0.02,
"learning_rate": 2.9178429377546496e-05,
"loss": 3.5185,
"step": 1271808
},
{
"epoch": 0.02,
"learning_rate": 2.9170043430035976e-05,
"loss": 3.5239,
"step": 1272320
},
{
"epoch": 0.02,
"learning_rate": 2.9161657482525456e-05,
"loss": 3.5118,
"step": 1272832
},
{
"epoch": 0.02,
"learning_rate": 2.9153287913818668e-05,
"loss": 3.5124,
"step": 1273344
},
{
"epoch": 0.02,
"learning_rate": 2.9144901966308148e-05,
"loss": 3.5251,
"step": 1273856
},
{
"epoch": 0.02,
"learning_rate": 2.9136516018797628e-05,
"loss": 3.5209,
"step": 1274368
},
{
"epoch": 0.02,
"learning_rate": 2.9128130071287108e-05,
"loss": 3.5131,
"step": 1274880
},
{
"epoch": 0.02,
"learning_rate": 2.9119760502580317e-05,
"loss": 3.5191,
"step": 1275392
},
{
"epoch": 0.02,
"learning_rate": 2.9111374555069797e-05,
"loss": 3.5122,
"step": 1275904
},
{
"epoch": 0.02,
"learning_rate": 2.9102988607559277e-05,
"loss": 3.512,
"step": 1276416
},
{
"epoch": 0.02,
"learning_rate": 2.909460266004876e-05,
"loss": 3.5096,
"step": 1276928
},
{
"epoch": 0.02,
"learning_rate": 2.908623309134197e-05,
"loss": 3.5129,
"step": 1277440
},
{
"epoch": 0.02,
"learning_rate": 2.907784714383145e-05,
"loss": 3.5088,
"step": 1277952
},
{
"epoch": 0.02,
"learning_rate": 2.906946119632093e-05,
"loss": 3.5217,
"step": 1278464
},
{
"epoch": 0.02,
"learning_rate": 2.906107524881041e-05,
"loss": 3.5135,
"step": 1278976
},
{
"epoch": 0.02,
"learning_rate": 2.9052705680103622e-05,
"loss": 3.5164,
"step": 1279488
},
{
"epoch": 0.02,
"learning_rate": 2.90443197325931e-05,
"loss": 3.5293,
"step": 1280000
},
{
"epoch": 0.02,
"learning_rate": 2.903593378508258e-05,
"loss": 3.53,
"step": 1280512
},
{
"epoch": 0.02,
"learning_rate": 2.902754783757206e-05,
"loss": 3.5187,
"step": 1281024
},
{
"epoch": 0.02,
"learning_rate": 2.901917826886527e-05,
"loss": 3.5193,
"step": 1281536
},
{
"epoch": 0.02,
"learning_rate": 2.901079232135475e-05,
"loss": 3.516,
"step": 1282048
},
{
"epoch": 0.02,
"learning_rate": 2.900240637384423e-05,
"loss": 3.5124,
"step": 1282560
},
{
"epoch": 0.02,
"learning_rate": 2.8994020426333714e-05,
"loss": 3.5068,
"step": 1283072
},
{
"epoch": 0.02,
"learning_rate": 2.8985650857626923e-05,
"loss": 3.5129,
"step": 1283584
},
{
"epoch": 0.02,
"learning_rate": 2.8977264910116403e-05,
"loss": 3.5138,
"step": 1284096
},
{
"epoch": 0.02,
"learning_rate": 2.8968878962605883e-05,
"loss": 3.5209,
"step": 1284608
},
{
"epoch": 0.02,
"learning_rate": 2.8960493015095363e-05,
"loss": 3.5137,
"step": 1285120
},
{
"epoch": 0.02,
"learning_rate": 2.8952123446388575e-05,
"loss": 3.5195,
"step": 1285632
},
{
"epoch": 0.02,
"learning_rate": 2.8943737498878055e-05,
"loss": 3.5167,
"step": 1286144
},
{
"epoch": 0.02,
"learning_rate": 2.8935351551367535e-05,
"loss": 3.5133,
"step": 1286656
},
{
"epoch": 0.02,
"learning_rate": 2.8926965603857015e-05,
"loss": 3.5121,
"step": 1287168
},
{
"epoch": 0.02,
"learning_rate": 2.8918596035150224e-05,
"loss": 3.5253,
"step": 1287680
},
{
"epoch": 0.02,
"learning_rate": 2.8910210087639704e-05,
"loss": 3.5264,
"step": 1288192
},
{
"epoch": 0.02,
"learning_rate": 2.8901824140129184e-05,
"loss": 3.5142,
"step": 1288704
},
{
"epoch": 0.02,
"learning_rate": 2.8893438192618664e-05,
"loss": 3.5185,
"step": 1289216
},
{
"epoch": 0.02,
"learning_rate": 2.8885068623911877e-05,
"loss": 3.5241,
"step": 1289728
},
{
"epoch": 0.02,
"learning_rate": 2.8876682676401357e-05,
"loss": 3.5177,
"step": 1290240
},
{
"epoch": 0.02,
"learning_rate": 2.8868296728890837e-05,
"loss": 3.5202,
"step": 1290752
},
{
"epoch": 0.02,
"learning_rate": 2.8859910781380317e-05,
"loss": 3.514,
"step": 1291264
},
{
"epoch": 0.02,
"learning_rate": 2.885154121267353e-05,
"loss": 3.5207,
"step": 1291776
},
{
"epoch": 0.02,
"learning_rate": 2.884315526516301e-05,
"loss": 3.5195,
"step": 1292288
},
{
"epoch": 0.02,
"learning_rate": 2.883476931765249e-05,
"loss": 3.5171,
"step": 1292800
},
{
"epoch": 0.02,
"learning_rate": 2.882638337014197e-05,
"loss": 3.5137,
"step": 1293312
},
{
"epoch": 0.02,
"learning_rate": 2.8818013801435178e-05,
"loss": 3.5149,
"step": 1293824
},
{
"epoch": 0.02,
"learning_rate": 2.8809627853924658e-05,
"loss": 3.5192,
"step": 1294336
},
{
"epoch": 0.02,
"learning_rate": 2.8801241906414138e-05,
"loss": 3.5096,
"step": 1294848
},
{
"epoch": 0.02,
"learning_rate": 2.8792855958903618e-05,
"loss": 3.5262,
"step": 1295360
},
{
"epoch": 0.02,
"learning_rate": 2.878448639019683e-05,
"loss": 3.5155,
"step": 1295872
},
{
"epoch": 0.02,
"learning_rate": 2.877610044268631e-05,
"loss": 3.5212,
"step": 1296384
},
{
"epoch": 0.02,
"learning_rate": 2.876771449517579e-05,
"loss": 3.5187,
"step": 1296896
},
{
"epoch": 0.02,
"learning_rate": 2.875932854766527e-05,
"loss": 3.509,
"step": 1297408
},
{
"epoch": 0.03,
"eval_loss": 3.843200922012329,
"eval_runtime": 304.3684,
"eval_samples_per_second": 1253.714,
"eval_steps_per_second": 39.179,
"step": 1297440
},
{
"epoch": 1.0,
"learning_rate": 2.875095897895848e-05,
"loss": 3.5086,
"step": 1297920
},
{
"epoch": 1.0,
"learning_rate": 2.8742573031447963e-05,
"loss": 3.5087,
"step": 1298432
},
{
"epoch": 1.0,
"learning_rate": 2.8734187083937443e-05,
"loss": 3.5307,
"step": 1298944
},
{
"epoch": 1.0,
"learning_rate": 2.8725801136426923e-05,
"loss": 3.5128,
"step": 1299456
},
{
"epoch": 1.0,
"learning_rate": 2.8717431567720132e-05,
"loss": 3.5203,
"step": 1299968
},
{
"epoch": 1.0,
"learning_rate": 2.870906199901334e-05,
"loss": 3.5131,
"step": 1300480
},
{
"epoch": 1.0,
"learning_rate": 2.8700676051502824e-05,
"loss": 3.5117,
"step": 1300992
},
{
"epoch": 1.0,
"learning_rate": 2.8692290103992304e-05,
"loss": 3.5033,
"step": 1301504
},
{
"epoch": 1.0,
"learning_rate": 2.8683904156481784e-05,
"loss": 3.5171,
"step": 1302016
},
{
"epoch": 1.0,
"learning_rate": 2.8675518208971264e-05,
"loss": 3.5075,
"step": 1302528
},
{
"epoch": 1.0,
"learning_rate": 2.8667132261460744e-05,
"loss": 3.5316,
"step": 1303040
},
{
"epoch": 1.0,
"learning_rate": 2.8658746313950224e-05,
"loss": 3.5164,
"step": 1303552
},
{
"epoch": 1.0,
"learning_rate": 2.8650376745243433e-05,
"loss": 3.5048,
"step": 1304064
},
{
"epoch": 1.0,
"learning_rate": 2.8641990797732916e-05,
"loss": 3.5054,
"step": 1304576
},
{
"epoch": 1.0,
"learning_rate": 2.8633604850222396e-05,
"loss": 3.5116,
"step": 1305088
},
{
"epoch": 1.0,
"learning_rate": 2.862521890271187e-05,
"loss": 3.5009,
"step": 1305600
},
{
"epoch": 1.0,
"learning_rate": 2.861683295520135e-05,
"loss": 3.5163,
"step": 1306112
},
{
"epoch": 1.0,
"learning_rate": 2.860844700769083e-05,
"loss": 3.5147,
"step": 1306624
},
{
"epoch": 1.0,
"learning_rate": 2.860006106018031e-05,
"loss": 3.5019,
"step": 1307136
},
{
"epoch": 1.0,
"learning_rate": 2.8591691491473522e-05,
"loss": 3.5321,
"step": 1307648
},
{
"epoch": 1.0,
"learning_rate": 2.8583305543963002e-05,
"loss": 3.5106,
"step": 1308160
},
{
"epoch": 1.0,
"learning_rate": 2.8574919596452482e-05,
"loss": 3.5131,
"step": 1308672
},
{
"epoch": 1.0,
"learning_rate": 2.8566533648941962e-05,
"loss": 3.5085,
"step": 1309184
},
{
"epoch": 1.0,
"learning_rate": 2.855816408023517e-05,
"loss": 3.5271,
"step": 1309696
},
{
"epoch": 1.0,
"learning_rate": 2.8549778132724654e-05,
"loss": 3.501,
"step": 1310208
},
{
"epoch": 1.0,
"learning_rate": 2.8541392185214134e-05,
"loss": 3.5096,
"step": 1310720
},
{
"epoch": 1.0,
"learning_rate": 2.8533006237703614e-05,
"loss": 3.5086,
"step": 1311232
},
{
"epoch": 1.0,
"learning_rate": 2.8524636668996823e-05,
"loss": 3.5078,
"step": 1311744
},
{
"epoch": 1.0,
"learning_rate": 2.8516250721486303e-05,
"loss": 3.504,
"step": 1312256
},
{
"epoch": 1.01,
"learning_rate": 2.8507864773975783e-05,
"loss": 3.5096,
"step": 1312768
},
{
"epoch": 1.01,
"learning_rate": 2.8499478826465263e-05,
"loss": 3.5132,
"step": 1313280
},
{
"epoch": 1.01,
"learning_rate": 2.8491109257758476e-05,
"loss": 3.5124,
"step": 1313792
},
{
"epoch": 1.01,
"learning_rate": 2.8482723310247955e-05,
"loss": 3.5122,
"step": 1314304
},
{
"epoch": 1.01,
"learning_rate": 2.8474337362737435e-05,
"loss": 3.5182,
"step": 1314816
},
{
"epoch": 1.01,
"learning_rate": 2.8465951415226915e-05,
"loss": 3.509,
"step": 1315328
},
{
"epoch": 1.01,
"learning_rate": 2.8457581846520124e-05,
"loss": 3.5151,
"step": 1315840
},
{
"epoch": 1.01,
"learning_rate": 2.8449195899009608e-05,
"loss": 3.5066,
"step": 1316352
},
{
"epoch": 1.01,
"learning_rate": 2.8440809951499088e-05,
"loss": 3.5085,
"step": 1316864
},
{
"epoch": 1.01,
"learning_rate": 2.8432424003988568e-05,
"loss": 3.4998,
"step": 1317376
},
{
"epoch": 1.01,
"learning_rate": 2.8424054435281777e-05,
"loss": 3.5089,
"step": 1317888
},
{
"epoch": 1.01,
"learning_rate": 2.8415668487771257e-05,
"loss": 3.5049,
"step": 1318400
},
{
"epoch": 1.01,
"learning_rate": 2.8407282540260737e-05,
"loss": 3.5171,
"step": 1318912
},
{
"epoch": 1.01,
"learning_rate": 2.8398896592750217e-05,
"loss": 3.5015,
"step": 1319424
},
{
"epoch": 1.01,
"learning_rate": 2.839052702404343e-05,
"loss": 3.5158,
"step": 1319936
},
{
"epoch": 1.01,
"learning_rate": 2.838214107653291e-05,
"loss": 3.5117,
"step": 1320448
},
{
"epoch": 1.01,
"learning_rate": 2.837375512902239e-05,
"loss": 3.515,
"step": 1320960
},
{
"epoch": 1.01,
"learning_rate": 2.836536918151187e-05,
"loss": 3.5062,
"step": 1321472
},
{
"epoch": 1.01,
"learning_rate": 2.8356999612805078e-05,
"loss": 3.4996,
"step": 1321984
},
{
"epoch": 1.01,
"learning_rate": 2.834861366529456e-05,
"loss": 3.5067,
"step": 1322496
},
{
"epoch": 1.01,
"learning_rate": 2.834022771778404e-05,
"loss": 3.5176,
"step": 1323008
},
{
"epoch": 1.01,
"learning_rate": 2.833184177027352e-05,
"loss": 3.509,
"step": 1323520
},
{
"epoch": 1.01,
"learning_rate": 2.832347220156673e-05,
"loss": 3.5,
"step": 1324032
},
{
"epoch": 1.01,
"learning_rate": 2.831508625405621e-05,
"loss": 3.499,
"step": 1324544
},
{
"epoch": 1.01,
"learning_rate": 2.8306716685349423e-05,
"loss": 3.5079,
"step": 1325056
},
{
"epoch": 1.01,
"learning_rate": 2.8298330737838903e-05,
"loss": 3.4896,
"step": 1325568
},
{
"epoch": 1.01,
"learning_rate": 2.8289944790328383e-05,
"loss": 3.5181,
"step": 1326080
},
{
"epoch": 1.01,
"learning_rate": 2.8281558842817863e-05,
"loss": 3.4945,
"step": 1326592
},
{
"epoch": 1.01,
"learning_rate": 2.8273172895307343e-05,
"loss": 3.5117,
"step": 1327104
},
{
"epoch": 1.01,
"learning_rate": 2.8264786947796823e-05,
"loss": 3.5068,
"step": 1327616
},
{
"epoch": 1.01,
"learning_rate": 2.8256401000286303e-05,
"loss": 3.4968,
"step": 1328128
},
{
"epoch": 1.01,
"learning_rate": 2.8248015052775783e-05,
"loss": 3.5114,
"step": 1328640
},
{
"epoch": 1.01,
"learning_rate": 2.8239645484068995e-05,
"loss": 3.5006,
"step": 1329152
},
{
"epoch": 1.01,
"learning_rate": 2.8231259536558475e-05,
"loss": 3.5028,
"step": 1329664
},
{
"epoch": 1.01,
"learning_rate": 2.8222873589047955e-05,
"loss": 3.492,
"step": 1330176
},
{
"epoch": 1.01,
"learning_rate": 2.8214487641537435e-05,
"loss": 3.5162,
"step": 1330688
},
{
"epoch": 1.01,
"learning_rate": 2.8206118072830644e-05,
"loss": 3.4944,
"step": 1331200
},
{
"epoch": 1.01,
"learning_rate": 2.8197732125320124e-05,
"loss": 3.5016,
"step": 1331712
},
{
"epoch": 1.01,
"learning_rate": 2.8189346177809607e-05,
"loss": 3.4857,
"step": 1332224
},
{
"epoch": 1.01,
"learning_rate": 2.8180976609102816e-05,
"loss": 3.4994,
"step": 1332736
},
{
"epoch": 1.01,
"learning_rate": 2.8172590661592296e-05,
"loss": 3.5109,
"step": 1333248
},
{
"epoch": 1.01,
"learning_rate": 2.8164204714081776e-05,
"loss": 3.5119,
"step": 1333760
},
{
"epoch": 1.01,
"learning_rate": 2.8155818766571256e-05,
"loss": 3.508,
"step": 1334272
},
{
"epoch": 1.01,
"learning_rate": 2.814744919786447e-05,
"loss": 3.5089,
"step": 1334784
},
{
"epoch": 1.01,
"learning_rate": 2.813906325035395e-05,
"loss": 3.5135,
"step": 1335296
},
{
"epoch": 1.01,
"learning_rate": 2.813067730284343e-05,
"loss": 3.504,
"step": 1335808
},
{
"epoch": 1.01,
"learning_rate": 2.812229135533291e-05,
"loss": 3.5146,
"step": 1336320
},
{
"epoch": 1.01,
"learning_rate": 2.8113921786626118e-05,
"loss": 3.5018,
"step": 1336832
},
{
"epoch": 1.01,
"learning_rate": 2.8105535839115598e-05,
"loss": 3.5026,
"step": 1337344
},
{
"epoch": 1.01,
"learning_rate": 2.8097149891605078e-05,
"loss": 3.5031,
"step": 1337856
},
{
"epoch": 1.01,
"learning_rate": 2.808878032289829e-05,
"loss": 3.5131,
"step": 1338368
},
{
"epoch": 1.01,
"learning_rate": 2.808039437538777e-05,
"loss": 3.5072,
"step": 1338880
},
{
"epoch": 1.01,
"learning_rate": 2.807200842787725e-05,
"loss": 3.5142,
"step": 1339392
},
{
"epoch": 1.01,
"learning_rate": 2.806362248036673e-05,
"loss": 3.5061,
"step": 1339904
},
{
"epoch": 1.01,
"learning_rate": 2.805523653285621e-05,
"loss": 3.4843,
"step": 1340416
},
{
"epoch": 1.01,
"learning_rate": 2.804685058534569e-05,
"loss": 3.4974,
"step": 1340928
},
{
"epoch": 1.01,
"learning_rate": 2.803846463783517e-05,
"loss": 3.5026,
"step": 1341440
},
{
"epoch": 1.01,
"learning_rate": 2.803007869032465e-05,
"loss": 3.5029,
"step": 1341952
},
{
"epoch": 1.01,
"learning_rate": 2.8021709121617862e-05,
"loss": 3.4986,
"step": 1342464
},
{
"epoch": 1.01,
"learning_rate": 2.8013323174107342e-05,
"loss": 3.5097,
"step": 1342976
},
{
"epoch": 1.02,
"learning_rate": 2.8004937226596822e-05,
"loss": 3.4972,
"step": 1343488
},
{
"epoch": 1.02,
"learning_rate": 2.7996551279086302e-05,
"loss": 3.4999,
"step": 1344000
},
{
"epoch": 1.02,
"learning_rate": 2.798818171037951e-05,
"loss": 3.5016,
"step": 1344512
},
{
"epoch": 1.02,
"learning_rate": 2.7979795762868995e-05,
"loss": 3.5111,
"step": 1345024
},
{
"epoch": 1.02,
"learning_rate": 2.7971409815358475e-05,
"loss": 3.5124,
"step": 1345536
},
{
"epoch": 1.02,
"learning_rate": 2.7963023867847948e-05,
"loss": 3.5205,
"step": 1346048
},
{
"epoch": 1.02,
"learning_rate": 2.7954654299141164e-05,
"loss": 3.4909,
"step": 1346560
},
{
"epoch": 1.02,
"learning_rate": 2.7946268351630644e-05,
"loss": 3.5063,
"step": 1347072
},
{
"epoch": 1.02,
"learning_rate": 2.7937882404120124e-05,
"loss": 3.5058,
"step": 1347584
},
{
"epoch": 1.02,
"learning_rate": 2.79294964566096e-05,
"loss": 3.5025,
"step": 1348096
},
{
"epoch": 1.02,
"learning_rate": 2.7921126887902816e-05,
"loss": 3.5123,
"step": 1348608
},
{
"epoch": 1.02,
"learning_rate": 2.7912740940392296e-05,
"loss": 3.4998,
"step": 1349120
},
{
"epoch": 1.02,
"learning_rate": 2.790435499288177e-05,
"loss": 3.5006,
"step": 1349632
},
{
"epoch": 1.02,
"learning_rate": 2.789596904537125e-05,
"loss": 3.5144,
"step": 1350144
},
{
"epoch": 1.02,
"learning_rate": 2.7887599476664465e-05,
"loss": 3.5097,
"step": 1350656
},
{
"epoch": 1.02,
"learning_rate": 2.787921352915395e-05,
"loss": 3.4945,
"step": 1351168
},
{
"epoch": 1.02,
"learning_rate": 2.787082758164342e-05,
"loss": 3.5066,
"step": 1351680
},
{
"epoch": 1.02,
"learning_rate": 2.78624416341329e-05,
"loss": 3.4998,
"step": 1352192
},
{
"epoch": 1.02,
"learning_rate": 2.7854072065426117e-05,
"loss": 3.498,
"step": 1352704
},
{
"epoch": 1.02,
"learning_rate": 2.7845686117915597e-05,
"loss": 3.4949,
"step": 1353216
},
{
"epoch": 1.02,
"learning_rate": 2.7837300170405074e-05,
"loss": 3.5001,
"step": 1353728
},
{
"epoch": 1.02,
"learning_rate": 2.7828914222894554e-05,
"loss": 3.4969,
"step": 1354240
},
{
"epoch": 1.02,
"learning_rate": 2.782054465418777e-05,
"loss": 3.5083,
"step": 1354752
},
{
"epoch": 1.02,
"learning_rate": 2.7812158706677243e-05,
"loss": 3.4983,
"step": 1355264
},
{
"epoch": 1.02,
"learning_rate": 2.7803772759166723e-05,
"loss": 3.5048,
"step": 1355776
},
{
"epoch": 1.02,
"learning_rate": 2.7795386811656203e-05,
"loss": 3.5176,
"step": 1356288
},
{
"epoch": 1.02,
"learning_rate": 2.778701724294942e-05,
"loss": 3.5141,
"step": 1356800
},
{
"epoch": 1.02,
"learning_rate": 2.7778631295438895e-05,
"loss": 3.5057,
"step": 1357312
},
{
"epoch": 1.02,
"learning_rate": 2.7770245347928375e-05,
"loss": 3.5076,
"step": 1357824
},
{
"epoch": 1.02,
"learning_rate": 2.7761859400417855e-05,
"loss": 3.5019,
"step": 1358336
},
{
"epoch": 1.02,
"learning_rate": 2.775348983171107e-05,
"loss": 3.4983,
"step": 1358848
},
{
"epoch": 1.02,
"learning_rate": 2.7745103884200548e-05,
"loss": 3.4976,
"step": 1359360
},
{
"epoch": 1.02,
"learning_rate": 2.7736717936690028e-05,
"loss": 3.4955,
"step": 1359872
},
{
"epoch": 1.02,
"learning_rate": 2.7728348367983243e-05,
"loss": 3.5026,
"step": 1360384
},
{
"epoch": 1.02,
"learning_rate": 2.7719962420472717e-05,
"loss": 3.5079,
"step": 1360896
},
{
"epoch": 1.02,
"learning_rate": 2.7711576472962197e-05,
"loss": 3.5044,
"step": 1361408
},
{
"epoch": 1.02,
"learning_rate": 2.7703190525451676e-05,
"loss": 3.5038,
"step": 1361920
},
{
"epoch": 1.02,
"learning_rate": 2.7694820956744892e-05,
"loss": 3.5045,
"step": 1362432
},
{
"epoch": 1.02,
"learning_rate": 2.768643500923437e-05,
"loss": 3.496,
"step": 1362944
},
{
"epoch": 1.02,
"learning_rate": 2.767804906172385e-05,
"loss": 3.4992,
"step": 1363456
},
{
"epoch": 1.02,
"learning_rate": 2.766966311421333e-05,
"loss": 3.516,
"step": 1363968
},
{
"epoch": 1.02,
"learning_rate": 2.7661293545506545e-05,
"loss": 3.513,
"step": 1364480
},
{
"epoch": 1.02,
"learning_rate": 2.7652907597996018e-05,
"loss": 3.5079,
"step": 1364992
},
{
"epoch": 1.02,
"learning_rate": 2.76445216504855e-05,
"loss": 3.5013,
"step": 1365504
},
{
"epoch": 1.02,
"learning_rate": 2.763613570297498e-05,
"loss": 3.5071,
"step": 1366016
},
{
"epoch": 1.02,
"learning_rate": 2.762776613426819e-05,
"loss": 3.5018,
"step": 1366528
},
{
"epoch": 1.02,
"learning_rate": 2.761938018675767e-05,
"loss": 3.5097,
"step": 1367040
},
{
"epoch": 1.02,
"learning_rate": 2.761099423924715e-05,
"loss": 3.5022,
"step": 1367552
},
{
"epoch": 1.02,
"learning_rate": 2.760260829173663e-05,
"loss": 3.5049,
"step": 1368064
},
{
"epoch": 1.02,
"learning_rate": 2.7594238723029843e-05,
"loss": 3.5064,
"step": 1368576
},
{
"epoch": 1.02,
"learning_rate": 2.7585852775519323e-05,
"loss": 3.5038,
"step": 1369088
},
{
"epoch": 1.02,
"learning_rate": 2.7577466828008803e-05,
"loss": 3.4982,
"step": 1369600
},
{
"epoch": 1.02,
"learning_rate": 2.7569080880498283e-05,
"loss": 3.5031,
"step": 1370112
},
{
"epoch": 1.02,
"learning_rate": 2.756071131179149e-05,
"loss": 3.5084,
"step": 1370624
},
{
"epoch": 1.02,
"learning_rate": 2.755232536428097e-05,
"loss": 3.4944,
"step": 1371136
},
{
"epoch": 1.02,
"learning_rate": 2.7543955795574187e-05,
"loss": 3.513,
"step": 1371648
},
{
"epoch": 1.02,
"learning_rate": 2.7535569848063664e-05,
"loss": 3.5041,
"step": 1372160
},
{
"epoch": 1.02,
"learning_rate": 2.7527183900553144e-05,
"loss": 3.5042,
"step": 1372672
},
{
"epoch": 1.02,
"learning_rate": 2.7518797953042624e-05,
"loss": 3.5043,
"step": 1373184
},
{
"epoch": 1.02,
"learning_rate": 2.7510412005532104e-05,
"loss": 3.4952,
"step": 1373696
},
{
"epoch": 1.03,
"eval_loss": 3.844034194946289,
"eval_runtime": 303.2319,
"eval_samples_per_second": 1258.413,
"eval_steps_per_second": 39.326,
"step": 1373760
},
{
"epoch": 0.0,
"learning_rate": 2.7502026058021584e-05,
"loss": 3.4949,
"step": 1374208
},
{
"epoch": 0.0,
"learning_rate": 2.7493640110511064e-05,
"loss": 3.4961,
"step": 1374720
},
{
"epoch": 0.0,
"learning_rate": 2.7485254163000547e-05,
"loss": 3.5173,
"step": 1375232
},
{
"epoch": 0.0,
"learning_rate": 2.7476868215490027e-05,
"loss": 3.5006,
"step": 1375744
},
{
"epoch": 0.0,
"learning_rate": 2.7468498646783236e-05,
"loss": 3.5117,
"step": 1376256
},
{
"epoch": 0.0,
"learning_rate": 2.7460112699272716e-05,
"loss": 3.4968,
"step": 1376768
},
{
"epoch": 0.0,
"learning_rate": 2.7451726751762196e-05,
"loss": 3.5007,
"step": 1377280
},
{
"epoch": 0.0,
"learning_rate": 2.744335718305541e-05,
"loss": 3.4888,
"step": 1377792
},
{
"epoch": 0.0,
"learning_rate": 2.743497123554489e-05,
"loss": 3.5041,
"step": 1378304
},
{
"epoch": 0.0,
"learning_rate": 2.742658528803437e-05,
"loss": 3.4979,
"step": 1378816
},
{
"epoch": 0.0,
"learning_rate": 2.741819934052385e-05,
"loss": 3.5151,
"step": 1379328
},
{
"epoch": 0.0,
"learning_rate": 2.740981339301333e-05,
"loss": 3.5037,
"step": 1379840
},
{
"epoch": 0.0,
"learning_rate": 2.7401443824306537e-05,
"loss": 3.4908,
"step": 1380352
},
{
"epoch": 0.0,
"learning_rate": 2.7393057876796017e-05,
"loss": 3.4915,
"step": 1380864
},
{
"epoch": 0.0,
"learning_rate": 2.73846719292855e-05,
"loss": 3.5003,
"step": 1381376
},
{
"epoch": 0.0,
"learning_rate": 2.737628598177498e-05,
"loss": 3.4888,
"step": 1381888
},
{
"epoch": 0.0,
"learning_rate": 2.736791641306819e-05,
"loss": 3.4993,
"step": 1382400
},
{
"epoch": 0.0,
"learning_rate": 2.735953046555767e-05,
"loss": 3.5026,
"step": 1382912
},
{
"epoch": 0.0,
"learning_rate": 2.735114451804715e-05,
"loss": 3.4921,
"step": 1383424
},
{
"epoch": 0.0,
"learning_rate": 2.7342774949340362e-05,
"loss": 3.52,
"step": 1383936
},
{
"epoch": 0.0,
"learning_rate": 2.7334389001829842e-05,
"loss": 3.4961,
"step": 1384448
},
{
"epoch": 0.0,
"learning_rate": 2.7326003054319322e-05,
"loss": 3.5019,
"step": 1384960
},
{
"epoch": 0.0,
"learning_rate": 2.7317617106808802e-05,
"loss": 3.494,
"step": 1385472
},
{
"epoch": 0.0,
"learning_rate": 2.7309231159298282e-05,
"loss": 3.5128,
"step": 1385984
},
{
"epoch": 0.0,
"learning_rate": 2.730086159059149e-05,
"loss": 3.487,
"step": 1386496
},
{
"epoch": 0.0,
"learning_rate": 2.729247564308097e-05,
"loss": 3.4985,
"step": 1387008
},
{
"epoch": 0.0,
"learning_rate": 2.7284089695570454e-05,
"loss": 3.4937,
"step": 1387520
},
{
"epoch": 0.0,
"learning_rate": 2.7275720126863664e-05,
"loss": 3.4966,
"step": 1388032
},
{
"epoch": 0.0,
"learning_rate": 2.7267334179353144e-05,
"loss": 3.4921,
"step": 1388544
},
{
"epoch": 0.01,
"learning_rate": 2.7258948231842623e-05,
"loss": 3.4933,
"step": 1389056
},
{
"epoch": 0.01,
"learning_rate": 2.7250562284332103e-05,
"loss": 3.5012,
"step": 1389568
},
{
"epoch": 0.01,
"learning_rate": 2.7242192715625316e-05,
"loss": 3.5003,
"step": 1390080
},
{
"epoch": 0.01,
"learning_rate": 2.7233806768114796e-05,
"loss": 3.4958,
"step": 1390592
},
{
"epoch": 0.01,
"learning_rate": 2.7225420820604276e-05,
"loss": 3.5093,
"step": 1391104
},
{
"epoch": 0.01,
"learning_rate": 2.7217034873093756e-05,
"loss": 3.4925,
"step": 1391616
},
{
"epoch": 0.01,
"learning_rate": 2.7208665304386965e-05,
"loss": 3.5028,
"step": 1392128
},
{
"epoch": 0.01,
"learning_rate": 2.7200279356876445e-05,
"loss": 3.4934,
"step": 1392640
},
{
"epoch": 0.01,
"learning_rate": 2.7191893409365925e-05,
"loss": 3.4941,
"step": 1393152
},
{
"epoch": 0.01,
"learning_rate": 2.7183507461855405e-05,
"loss": 3.4855,
"step": 1393664
},
{
"epoch": 0.01,
"learning_rate": 2.7175137893148617e-05,
"loss": 3.4982,
"step": 1394176
},
{
"epoch": 0.01,
"learning_rate": 2.7166751945638097e-05,
"loss": 3.4901,
"step": 1394688
},
{
"epoch": 0.01,
"learning_rate": 2.7158365998127577e-05,
"loss": 3.5043,
"step": 1395200
},
{
"epoch": 0.01,
"learning_rate": 2.7149980050617057e-05,
"loss": 3.4917,
"step": 1395712
},
{
"epoch": 0.01,
"learning_rate": 2.714161048191027e-05,
"loss": 3.5014,
"step": 1396224
},
{
"epoch": 0.01,
"learning_rate": 2.713322453439975e-05,
"loss": 3.5047,
"step": 1396736
},
{
"epoch": 0.01,
"learning_rate": 2.712483858688923e-05,
"loss": 3.499,
"step": 1397248
},
{
"epoch": 0.01,
"learning_rate": 2.711645263937871e-05,
"loss": 3.4967,
"step": 1397760
},
{
"epoch": 0.01,
"learning_rate": 2.710808307067192e-05,
"loss": 3.4848,
"step": 1398272
},
{
"epoch": 0.01,
"learning_rate": 2.70996971231614e-05,
"loss": 3.4907,
"step": 1398784
},
{
"epoch": 0.01,
"learning_rate": 2.709131117565088e-05,
"loss": 3.5045,
"step": 1399296
},
{
"epoch": 0.01,
"learning_rate": 2.708292522814036e-05,
"loss": 3.4958,
"step": 1399808
},
{
"epoch": 0.01,
"learning_rate": 2.707455565943357e-05,
"loss": 3.4906,
"step": 1400320
},
{
"epoch": 0.01,
"learning_rate": 2.706616971192305e-05,
"loss": 3.4839,
"step": 1400832
},
{
"epoch": 0.01,
"learning_rate": 2.705780014321626e-05,
"loss": 3.4962,
"step": 1401344
},
{
"epoch": 0.01,
"learning_rate": 2.704941419570574e-05,
"loss": 3.4753,
"step": 1401856
},
{
"epoch": 0.01,
"learning_rate": 2.704102824819522e-05,
"loss": 3.5078,
"step": 1402368
},
{
"epoch": 0.01,
"learning_rate": 2.7032642300684703e-05,
"loss": 3.4791,
"step": 1402880
},
{
"epoch": 0.01,
"learning_rate": 2.7024256353174183e-05,
"loss": 3.4995,
"step": 1403392
},
{
"epoch": 0.01,
"learning_rate": 2.7015870405663663e-05,
"loss": 3.4941,
"step": 1403904
},
{
"epoch": 0.01,
"learning_rate": 2.7007484458153143e-05,
"loss": 3.4828,
"step": 1404416
},
{
"epoch": 0.01,
"learning_rate": 2.6999098510642623e-05,
"loss": 3.5011,
"step": 1404928
},
{
"epoch": 0.01,
"learning_rate": 2.6990728941935832e-05,
"loss": 3.4845,
"step": 1405440
},
{
"epoch": 0.01,
"learning_rate": 2.6982342994425312e-05,
"loss": 3.4886,
"step": 1405952
},
{
"epoch": 0.01,
"learning_rate": 2.6973957046914795e-05,
"loss": 3.4774,
"step": 1406464
},
{
"epoch": 0.01,
"learning_rate": 2.696557109940427e-05,
"loss": 3.5023,
"step": 1406976
},
{
"epoch": 0.01,
"learning_rate": 2.6957201530697484e-05,
"loss": 3.4855,
"step": 1407488
},
{
"epoch": 0.01,
"learning_rate": 2.6948815583186964e-05,
"loss": 3.489,
"step": 1408000
},
{
"epoch": 0.01,
"learning_rate": 2.6940429635676444e-05,
"loss": 3.4767,
"step": 1408512
},
{
"epoch": 0.01,
"learning_rate": 2.6932060066969657e-05,
"loss": 3.484,
"step": 1409024
},
{
"epoch": 0.01,
"learning_rate": 2.6923674119459137e-05,
"loss": 3.4954,
"step": 1409536
},
{
"epoch": 0.01,
"learning_rate": 2.6915288171948617e-05,
"loss": 3.5006,
"step": 1410048
},
{
"epoch": 0.01,
"learning_rate": 2.6906902224438097e-05,
"loss": 3.4929,
"step": 1410560
},
{
"epoch": 0.01,
"learning_rate": 2.6898532655731306e-05,
"loss": 3.4982,
"step": 1411072
},
{
"epoch": 0.01,
"learning_rate": 2.6890146708220786e-05,
"loss": 3.4976,
"step": 1411584
},
{
"epoch": 0.01,
"learning_rate": 2.6881760760710266e-05,
"loss": 3.493,
"step": 1412096
},
{
"epoch": 0.01,
"learning_rate": 2.6873374813199742e-05,
"loss": 3.4959,
"step": 1412608
},
{
"epoch": 0.01,
"learning_rate": 2.6865005244492958e-05,
"loss": 3.4952,
"step": 1413120
},
{
"epoch": 0.01,
"learning_rate": 2.6856619296982438e-05,
"loss": 3.4878,
"step": 1413632
},
{
"epoch": 0.01,
"learning_rate": 2.6848249728275647e-05,
"loss": 3.4889,
"step": 1414144
},
{
"epoch": 0.01,
"learning_rate": 2.6839863780765127e-05,
"loss": 3.4987,
"step": 1414656
},
{
"epoch": 0.01,
"learning_rate": 2.683147783325461e-05,
"loss": 3.4981,
"step": 1415168
},
{
"epoch": 0.01,
"learning_rate": 2.682309188574409e-05,
"loss": 3.5061,
"step": 1415680
},
{
"epoch": 0.01,
"learning_rate": 2.681470593823357e-05,
"loss": 3.4902,
"step": 1416192
},
{
"epoch": 0.01,
"learning_rate": 2.6806319990723044e-05,
"loss": 3.4692,
"step": 1416704
},
{
"epoch": 0.01,
"learning_rate": 2.6797934043212524e-05,
"loss": 3.4843,
"step": 1417216
},
{
"epoch": 0.01,
"learning_rate": 2.6789548095702004e-05,
"loss": 3.4914,
"step": 1417728
},
{
"epoch": 0.01,
"learning_rate": 2.6781178526995216e-05,
"loss": 3.4922,
"step": 1418240
},
{
"epoch": 0.01,
"learning_rate": 2.6772792579484696e-05,
"loss": 3.4865,
"step": 1418752
},
{
"epoch": 0.01,
"learning_rate": 2.6764406631974176e-05,
"loss": 3.4959,
"step": 1419264
},
{
"epoch": 0.02,
"learning_rate": 2.6756020684463656e-05,
"loss": 3.4884,
"step": 1419776
},
{
"epoch": 0.02,
"learning_rate": 2.6747651115756865e-05,
"loss": 3.4809,
"step": 1420288
},
{
"epoch": 0.02,
"learning_rate": 2.673926516824635e-05,
"loss": 3.4937,
"step": 1420800
},
{
"epoch": 0.02,
"learning_rate": 2.6730879220735828e-05,
"loss": 3.5005,
"step": 1421312
},
{
"epoch": 0.02,
"learning_rate": 2.6722493273225308e-05,
"loss": 3.497,
"step": 1421824
},
{
"epoch": 0.02,
"learning_rate": 2.6714123704518517e-05,
"loss": 3.5036,
"step": 1422336
},
{
"epoch": 0.02,
"learning_rate": 2.6705737757007997e-05,
"loss": 3.4863,
"step": 1422848
},
{
"epoch": 0.02,
"learning_rate": 2.6697351809497477e-05,
"loss": 3.4923,
"step": 1423360
},
{
"epoch": 0.02,
"learning_rate": 2.6688965861986957e-05,
"loss": 3.4931,
"step": 1423872
},
{
"epoch": 0.02,
"learning_rate": 2.668059629328017e-05,
"loss": 3.4922,
"step": 1424384
},
{
"epoch": 0.02,
"learning_rate": 2.667221034576965e-05,
"loss": 3.4982,
"step": 1424896
},
{
"epoch": 0.02,
"learning_rate": 2.666382439825913e-05,
"loss": 3.4885,
"step": 1425408
},
{
"epoch": 0.02,
"learning_rate": 2.665543845074861e-05,
"loss": 3.4872,
"step": 1425920
},
{
"epoch": 0.02,
"learning_rate": 2.664706888204182e-05,
"loss": 3.4967,
"step": 1426432
},
{
"epoch": 0.02,
"learning_rate": 2.6638682934531302e-05,
"loss": 3.5013,
"step": 1426944
},
{
"epoch": 0.02,
"learning_rate": 2.6630296987020782e-05,
"loss": 3.4808,
"step": 1427456
},
{
"epoch": 0.02,
"learning_rate": 2.6621911039510262e-05,
"loss": 3.492,
"step": 1427968
},
{
"epoch": 0.02,
"learning_rate": 2.661354147080347e-05,
"loss": 3.4923,
"step": 1428480
},
{
"epoch": 0.02,
"learning_rate": 2.660515552329295e-05,
"loss": 3.4871,
"step": 1428992
},
{
"epoch": 0.02,
"learning_rate": 2.659676957578243e-05,
"loss": 3.4819,
"step": 1429504
},
{
"epoch": 0.02,
"learning_rate": 2.658838362827191e-05,
"loss": 3.4861,
"step": 1430016
},
{
"epoch": 0.02,
"learning_rate": 2.6580014059565123e-05,
"loss": 3.4869,
"step": 1430528
},
{
"epoch": 0.02,
"learning_rate": 2.6571628112054603e-05,
"loss": 3.4919,
"step": 1431040
},
{
"epoch": 0.02,
"learning_rate": 2.6563242164544083e-05,
"loss": 3.4856,
"step": 1431552
},
{
"epoch": 0.02,
"learning_rate": 2.6554856217033563e-05,
"loss": 3.4905,
"step": 1432064
},
{
"epoch": 0.02,
"learning_rate": 2.6546486648326772e-05,
"loss": 3.5033,
"step": 1432576
},
{
"epoch": 0.02,
"learning_rate": 2.6538100700816256e-05,
"loss": 3.5073,
"step": 1433088
},
{
"epoch": 0.02,
"learning_rate": 2.6529714753305736e-05,
"loss": 3.4921,
"step": 1433600
},
{
"epoch": 0.02,
"learning_rate": 2.6521328805795216e-05,
"loss": 3.495,
"step": 1434112
},
{
"epoch": 0.02,
"learning_rate": 2.6512959237088425e-05,
"loss": 3.4881,
"step": 1434624
},
{
"epoch": 0.02,
"learning_rate": 2.6504573289577905e-05,
"loss": 3.4877,
"step": 1435136
},
{
"epoch": 0.02,
"learning_rate": 2.6496187342067385e-05,
"loss": 3.4827,
"step": 1435648
},
{
"epoch": 0.02,
"learning_rate": 2.6487801394556865e-05,
"loss": 3.4839,
"step": 1436160
},
{
"epoch": 0.02,
"learning_rate": 2.6479431825850077e-05,
"loss": 3.4872,
"step": 1436672
},
{
"epoch": 0.02,
"learning_rate": 2.6471045878339557e-05,
"loss": 3.4982,
"step": 1437184
},
{
"epoch": 0.02,
"learning_rate": 2.6462659930829037e-05,
"loss": 3.4894,
"step": 1437696
},
{
"epoch": 0.02,
"learning_rate": 2.6454273983318517e-05,
"loss": 3.4927,
"step": 1438208
},
{
"epoch": 0.02,
"learning_rate": 2.6445904414611726e-05,
"loss": 3.4907,
"step": 1438720
},
{
"epoch": 0.02,
"learning_rate": 2.643751846710121e-05,
"loss": 3.4827,
"step": 1439232
},
{
"epoch": 0.02,
"learning_rate": 2.642913251959069e-05,
"loss": 3.4866,
"step": 1439744
},
{
"epoch": 0.02,
"learning_rate": 2.642074657208017e-05,
"loss": 3.5032,
"step": 1440256
},
{
"epoch": 0.02,
"learning_rate": 2.641237700337338e-05,
"loss": 3.504,
"step": 1440768
},
{
"epoch": 0.02,
"learning_rate": 2.6403991055862858e-05,
"loss": 3.4926,
"step": 1441280
},
{
"epoch": 0.02,
"learning_rate": 2.6395605108352338e-05,
"loss": 3.4884,
"step": 1441792
},
{
"epoch": 0.02,
"learning_rate": 2.6387219160841818e-05,
"loss": 3.4925,
"step": 1442304
},
{
"epoch": 0.02,
"learning_rate": 2.637884959213503e-05,
"loss": 3.4909,
"step": 1442816
},
{
"epoch": 0.02,
"learning_rate": 2.637046364462451e-05,
"loss": 3.501,
"step": 1443328
},
{
"epoch": 0.02,
"learning_rate": 2.636207769711399e-05,
"loss": 3.4906,
"step": 1443840
},
{
"epoch": 0.02,
"learning_rate": 2.635369174960347e-05,
"loss": 3.4903,
"step": 1444352
},
{
"epoch": 0.02,
"learning_rate": 2.634532218089668e-05,
"loss": 3.4922,
"step": 1444864
},
{
"epoch": 0.02,
"learning_rate": 2.6336936233386163e-05,
"loss": 3.493,
"step": 1445376
},
{
"epoch": 0.02,
"learning_rate": 2.6328550285875643e-05,
"loss": 3.4905,
"step": 1445888
},
{
"epoch": 0.02,
"learning_rate": 2.6320164338365123e-05,
"loss": 3.4903,
"step": 1446400
},
{
"epoch": 0.02,
"learning_rate": 2.6311794769658332e-05,
"loss": 3.4964,
"step": 1446912
},
{
"epoch": 0.02,
"learning_rate": 2.6303408822147812e-05,
"loss": 3.4849,
"step": 1447424
},
{
"epoch": 0.02,
"learning_rate": 2.6295022874637292e-05,
"loss": 3.4962,
"step": 1447936
},
{
"epoch": 0.02,
"learning_rate": 2.6286636927126772e-05,
"loss": 3.4975,
"step": 1448448
},
{
"epoch": 0.02,
"learning_rate": 2.6278267358419984e-05,
"loss": 3.491,
"step": 1448960
},
{
"epoch": 0.02,
"learning_rate": 2.6269881410909464e-05,
"loss": 3.4923,
"step": 1449472
},
{
"epoch": 0.02,
"learning_rate": 2.6261495463398944e-05,
"loss": 3.4796,
"step": 1449984
},
{
"epoch": 0.03,
"eval_loss": 3.8456063270568848,
"eval_runtime": 359.9777,
"eval_samples_per_second": 1060.041,
"eval_steps_per_second": 33.127,
"step": 1450080
},
{
"epoch": 0.0,
"learning_rate": 2.6253109515888424e-05,
"loss": 3.4831,
"step": 1450496
},
{
"epoch": 0.0,
"learning_rate": 2.6244723568377904e-05,
"loss": 3.4806,
"step": 1451008
},
{
"epoch": 0.0,
"learning_rate": 2.6236337620867384e-05,
"loss": 3.5033,
"step": 1451520
},
{
"epoch": 0.0,
"learning_rate": 2.6227951673356864e-05,
"loss": 3.4883,
"step": 1452032
},
{
"epoch": 0.0,
"learning_rate": 2.6219582104650077e-05,
"loss": 3.5006,
"step": 1452544
},
{
"epoch": 0.0,
"learning_rate": 2.6211196157139557e-05,
"loss": 3.4844,
"step": 1453056
},
{
"epoch": 0.0,
"learning_rate": 2.6202810209629036e-05,
"loss": 3.4912,
"step": 1453568
},
{
"epoch": 0.0,
"learning_rate": 2.6194424262118516e-05,
"loss": 3.4735,
"step": 1454080
},
{
"epoch": 0.0,
"learning_rate": 2.6186054693411726e-05,
"loss": 3.495,
"step": 1454592
},
{
"epoch": 0.0,
"learning_rate": 2.6177668745901205e-05,
"loss": 3.4835,
"step": 1455104
},
{
"epoch": 0.0,
"learning_rate": 2.616928279839069e-05,
"loss": 3.5034,
"step": 1455616
},
{
"epoch": 0.0,
"learning_rate": 2.616089685088017e-05,
"loss": 3.4913,
"step": 1456128
},
{
"epoch": 0.0,
"learning_rate": 2.6152543660977107e-05,
"loss": 3.4764,
"step": 1456640
},
{
"epoch": 0.0,
"learning_rate": 2.6144157713466587e-05,
"loss": 3.4803,
"step": 1457152
},
{
"epoch": 0.0,
"learning_rate": 2.6135771765956067e-05,
"loss": 3.4891,
"step": 1457664
},
{
"epoch": 0.0,
"learning_rate": 2.612738581844555e-05,
"loss": 3.4753,
"step": 1458176
},
{
"epoch": 0.0,
"learning_rate": 2.611899987093503e-05,
"loss": 3.4842,
"step": 1458688
},
{
"epoch": 0.0,
"learning_rate": 2.611061392342451e-05,
"loss": 3.4874,
"step": 1459200
},
{
"epoch": 0.0,
"learning_rate": 2.610222797591399e-05,
"loss": 3.4781,
"step": 1459712
},
{
"epoch": 0.0,
"learning_rate": 2.609384202840347e-05,
"loss": 3.5109,
"step": 1460224
},
{
"epoch": 0.0,
"learning_rate": 2.608547245969668e-05,
"loss": 3.4844,
"step": 1460736
},
{
"epoch": 0.0,
"learning_rate": 2.607708651218616e-05,
"loss": 3.4849,
"step": 1461248
},
{
"epoch": 0.0,
"learning_rate": 2.6068700564675642e-05,
"loss": 3.4852,
"step": 1461760
},
{
"epoch": 0.0,
"learning_rate": 2.6060314617165122e-05,
"loss": 3.4939,
"step": 1462272
},
{
"epoch": 0.0,
"learning_rate": 2.605194504845833e-05,
"loss": 3.4775,
"step": 1462784
},
{
"epoch": 0.0,
"learning_rate": 2.604355910094781e-05,
"loss": 3.4862,
"step": 1463296
},
{
"epoch": 0.0,
"learning_rate": 2.603517315343729e-05,
"loss": 3.4825,
"step": 1463808
},
{
"epoch": 0.0,
"learning_rate": 2.6026787205926768e-05,
"loss": 3.4848,
"step": 1464320
},
{
"epoch": 0.0,
"learning_rate": 2.6018417637219984e-05,
"loss": 3.4794,
"step": 1464832
},
{
"epoch": 0.01,
"learning_rate": 2.6010031689709464e-05,
"loss": 3.4802,
"step": 1465344
},
{
"epoch": 0.01,
"learning_rate": 2.6001645742198944e-05,
"loss": 3.4859,
"step": 1465856
},
{
"epoch": 0.01,
"learning_rate": 2.5993276173492153e-05,
"loss": 3.4888,
"step": 1466368
},
{
"epoch": 0.01,
"learning_rate": 2.5984890225981633e-05,
"loss": 3.4878,
"step": 1466880
},
{
"epoch": 0.01,
"learning_rate": 2.5976504278471113e-05,
"loss": 3.4917,
"step": 1467392
},
{
"epoch": 0.01,
"learning_rate": 2.596811833096059e-05,
"loss": 3.4807,
"step": 1467904
},
{
"epoch": 0.01,
"learning_rate": 2.5959748762253805e-05,
"loss": 3.49,
"step": 1468416
},
{
"epoch": 0.01,
"learning_rate": 2.5951362814743285e-05,
"loss": 3.478,
"step": 1468928
},
{
"epoch": 0.01,
"learning_rate": 2.5942976867232765e-05,
"loss": 3.4898,
"step": 1469440
},
{
"epoch": 0.01,
"learning_rate": 2.5934590919722242e-05,
"loss": 3.4713,
"step": 1469952
},
{
"epoch": 0.01,
"learning_rate": 2.5926221351015458e-05,
"loss": 3.4831,
"step": 1470464
},
{
"epoch": 0.01,
"learning_rate": 2.5917835403504938e-05,
"loss": 3.4763,
"step": 1470976
},
{
"epoch": 0.01,
"learning_rate": 2.5909449455994418e-05,
"loss": 3.4949,
"step": 1471488
},
{
"epoch": 0.01,
"learning_rate": 2.590106350848389e-05,
"loss": 3.4765,
"step": 1472000
},
{
"epoch": 0.01,
"learning_rate": 2.5892693939777107e-05,
"loss": 3.4828,
"step": 1472512
},
{
"epoch": 0.01,
"learning_rate": 2.5884307992266587e-05,
"loss": 3.4925,
"step": 1473024
},
{
"epoch": 0.01,
"learning_rate": 2.5875922044756063e-05,
"loss": 3.49,
"step": 1473536
},
{
"epoch": 0.01,
"learning_rate": 2.5867536097245543e-05,
"loss": 3.487,
"step": 1474048
},
{
"epoch": 0.01,
"learning_rate": 2.585916652853876e-05,
"loss": 3.4726,
"step": 1474560
},
{
"epoch": 0.01,
"learning_rate": 2.585078058102824e-05,
"loss": 3.4772,
"step": 1475072
},
{
"epoch": 0.01,
"learning_rate": 2.5842394633517712e-05,
"loss": 3.4881,
"step": 1475584
},
{
"epoch": 0.01,
"learning_rate": 2.5834008686007195e-05,
"loss": 3.4859,
"step": 1476096
},
{
"epoch": 0.01,
"learning_rate": 2.582563911730041e-05,
"loss": 3.4777,
"step": 1476608
},
{
"epoch": 0.01,
"learning_rate": 2.581725316978989e-05,
"loss": 3.4756,
"step": 1477120
},
{
"epoch": 0.01,
"learning_rate": 2.58088836010831e-05,
"loss": 3.486,
"step": 1477632
},
{
"epoch": 0.01,
"learning_rate": 2.580049765357258e-05,
"loss": 3.4663,
"step": 1478144
},
{
"epoch": 0.01,
"learning_rate": 2.579211170606206e-05,
"loss": 3.4872,
"step": 1478656
},
{
"epoch": 0.01,
"learning_rate": 2.5783725758551537e-05,
"loss": 3.4704,
"step": 1479168
},
{
"epoch": 0.01,
"learning_rate": 2.5775339811041017e-05,
"loss": 3.4837,
"step": 1479680
},
{
"epoch": 0.01,
"learning_rate": 2.5766953863530497e-05,
"loss": 3.4873,
"step": 1480192
},
{
"epoch": 0.01,
"learning_rate": 2.5758567916019977e-05,
"loss": 3.4719,
"step": 1480704
},
{
"epoch": 0.01,
"learning_rate": 2.5750181968509457e-05,
"loss": 3.4848,
"step": 1481216
},
{
"epoch": 0.01,
"learning_rate": 2.5741812399802666e-05,
"loss": 3.4743,
"step": 1481728
},
{
"epoch": 0.01,
"learning_rate": 2.573342645229215e-05,
"loss": 3.4767,
"step": 1482240
},
{
"epoch": 0.01,
"learning_rate": 2.572504050478163e-05,
"loss": 3.4706,
"step": 1482752
},
{
"epoch": 0.01,
"learning_rate": 2.571665455727111e-05,
"loss": 3.4864,
"step": 1483264
},
{
"epoch": 0.01,
"learning_rate": 2.5708284988564318e-05,
"loss": 3.4738,
"step": 1483776
},
{
"epoch": 0.01,
"learning_rate": 2.5699899041053798e-05,
"loss": 3.477,
"step": 1484288
},
{
"epoch": 0.01,
"learning_rate": 2.5691513093543278e-05,
"loss": 3.4653,
"step": 1484800
},
{
"epoch": 0.01,
"learning_rate": 2.5683127146032758e-05,
"loss": 3.4714,
"step": 1485312
},
{
"epoch": 0.01,
"learning_rate": 2.567475757732597e-05,
"loss": 3.4815,
"step": 1485824
},
{
"epoch": 0.01,
"learning_rate": 2.566637162981545e-05,
"loss": 3.4904,
"step": 1486336
},
{
"epoch": 0.01,
"learning_rate": 2.565798568230493e-05,
"loss": 3.4776,
"step": 1486848
},
{
"epoch": 0.01,
"learning_rate": 2.564959973479441e-05,
"loss": 3.4879,
"step": 1487360
},
{
"epoch": 0.01,
"learning_rate": 2.564123016608762e-05,
"loss": 3.4864,
"step": 1487872
},
{
"epoch": 0.01,
"learning_rate": 2.5632844218577103e-05,
"loss": 3.4794,
"step": 1488384
},
{
"epoch": 0.01,
"learning_rate": 2.5624458271066583e-05,
"loss": 3.486,
"step": 1488896
},
{
"epoch": 0.01,
"learning_rate": 2.5616072323556063e-05,
"loss": 3.4806,
"step": 1489408
},
{
"epoch": 0.01,
"learning_rate": 2.5607702754849272e-05,
"loss": 3.4801,
"step": 1489920
},
{
"epoch": 0.01,
"learning_rate": 2.559933318614248e-05,
"loss": 3.4772,
"step": 1490432
},
{
"epoch": 0.01,
"learning_rate": 2.5590947238631964e-05,
"loss": 3.4867,
"step": 1490944
},
{
"epoch": 0.01,
"learning_rate": 2.5582561291121444e-05,
"loss": 3.4857,
"step": 1491456
},
{
"epoch": 0.01,
"learning_rate": 2.5574175343610924e-05,
"loss": 3.4848,
"step": 1491968
},
{
"epoch": 0.01,
"learning_rate": 2.5565789396100404e-05,
"loss": 3.4822,
"step": 1492480
},
{
"epoch": 0.01,
"learning_rate": 2.5557403448589884e-05,
"loss": 3.4605,
"step": 1492992
},
{
"epoch": 0.01,
"learning_rate": 2.5549017501079364e-05,
"loss": 3.4694,
"step": 1493504
},
{
"epoch": 0.01,
"learning_rate": 2.5540631553568844e-05,
"loss": 3.4775,
"step": 1494016
},
{
"epoch": 0.01,
"learning_rate": 2.5532261984862056e-05,
"loss": 3.4823,
"step": 1494528
},
{
"epoch": 0.01,
"learning_rate": 2.5523876037351536e-05,
"loss": 3.475,
"step": 1495040
},
{
"epoch": 0.01,
"learning_rate": 2.5515490089841016e-05,
"loss": 3.4813,
"step": 1495552
},
{
"epoch": 0.02,
"learning_rate": 2.5507104142330496e-05,
"loss": 3.4766,
"step": 1496064
},
{
"epoch": 0.02,
"learning_rate": 2.5498734573623705e-05,
"loss": 3.4695,
"step": 1496576
},
{
"epoch": 0.02,
"learning_rate": 2.5490348626113185e-05,
"loss": 3.4778,
"step": 1497088
},
{
"epoch": 0.02,
"learning_rate": 2.5481962678602665e-05,
"loss": 3.4851,
"step": 1497600
},
{
"epoch": 0.02,
"learning_rate": 2.5473576731092145e-05,
"loss": 3.4853,
"step": 1498112
},
{
"epoch": 0.02,
"learning_rate": 2.5465207162385358e-05,
"loss": 3.4946,
"step": 1498624
},
{
"epoch": 0.02,
"learning_rate": 2.5456821214874838e-05,
"loss": 3.4739,
"step": 1499136
},
{
"epoch": 0.02,
"learning_rate": 2.5448435267364318e-05,
"loss": 3.4781,
"step": 1499648
},
{
"epoch": 0.02,
"learning_rate": 2.5440049319853798e-05,
"loss": 3.4815,
"step": 1500160
},
{
"epoch": 0.02,
"learning_rate": 2.543167975114701e-05,
"loss": 3.4782,
"step": 1500672
},
{
"epoch": 0.02,
"learning_rate": 2.542329380363649e-05,
"loss": 3.4871,
"step": 1501184
},
{
"epoch": 0.02,
"learning_rate": 2.541490785612597e-05,
"loss": 3.4764,
"step": 1501696
},
{
"epoch": 0.02,
"learning_rate": 2.540652190861545e-05,
"loss": 3.476,
"step": 1502208
},
{
"epoch": 0.02,
"learning_rate": 2.539815233990866e-05,
"loss": 3.483,
"step": 1502720
},
{
"epoch": 0.02,
"learning_rate": 2.538976639239814e-05,
"loss": 3.4887,
"step": 1503232
},
{
"epoch": 0.02,
"learning_rate": 2.538138044488762e-05,
"loss": 3.47,
"step": 1503744
},
{
"epoch": 0.02,
"learning_rate": 2.53729944973771e-05,
"loss": 3.4808,
"step": 1504256
},
{
"epoch": 0.02,
"learning_rate": 2.536462492867031e-05,
"loss": 3.4786,
"step": 1504768
},
{
"epoch": 0.02,
"learning_rate": 2.535623898115979e-05,
"loss": 3.4752,
"step": 1505280
},
{
"epoch": 0.02,
"learning_rate": 2.534785303364927e-05,
"loss": 3.4657,
"step": 1505792
},
{
"epoch": 0.02,
"learning_rate": 2.533946708613875e-05,
"loss": 3.4781,
"step": 1506304
},
{
"epoch": 0.02,
"learning_rate": 2.533109751743196e-05,
"loss": 3.4783,
"step": 1506816
},
{
"epoch": 0.02,
"learning_rate": 2.5322711569921444e-05,
"loss": 3.477,
"step": 1507328
},
{
"epoch": 0.02,
"learning_rate": 2.5314325622410924e-05,
"loss": 3.4759,
"step": 1507840
},
{
"epoch": 0.02,
"learning_rate": 2.5305939674900404e-05,
"loss": 3.4751,
"step": 1508352
},
{
"epoch": 0.02,
"learning_rate": 2.5297570106193613e-05,
"loss": 3.4936,
"step": 1508864
},
{
"epoch": 0.02,
"learning_rate": 2.5289184158683093e-05,
"loss": 3.4938,
"step": 1509376
},
{
"epoch": 0.02,
"learning_rate": 2.5280798211172573e-05,
"loss": 3.4841,
"step": 1509888
},
{
"epoch": 0.02,
"learning_rate": 2.5272412263662053e-05,
"loss": 3.4821,
"step": 1510400
},
{
"epoch": 0.02,
"learning_rate": 2.5264042694955265e-05,
"loss": 3.4781,
"step": 1510912
},
{
"epoch": 0.02,
"learning_rate": 2.5255656747444745e-05,
"loss": 3.4729,
"step": 1511424
},
{
"epoch": 0.02,
"learning_rate": 2.5247270799934225e-05,
"loss": 3.4721,
"step": 1511936
},
{
"epoch": 0.02,
"learning_rate": 2.5238884852423705e-05,
"loss": 3.4702,
"step": 1512448
},
{
"epoch": 0.02,
"learning_rate": 2.5230515283716914e-05,
"loss": 3.4773,
"step": 1512960
},
{
"epoch": 0.02,
"learning_rate": 2.5222129336206397e-05,
"loss": 3.4848,
"step": 1513472
},
{
"epoch": 0.02,
"learning_rate": 2.5213743388695877e-05,
"loss": 3.4747,
"step": 1513984
},
{
"epoch": 0.02,
"learning_rate": 2.5205357441185357e-05,
"loss": 3.484,
"step": 1514496
},
{
"epoch": 0.02,
"learning_rate": 2.5196987872478566e-05,
"loss": 3.4763,
"step": 1515008
},
{
"epoch": 0.02,
"learning_rate": 2.5188601924968046e-05,
"loss": 3.4724,
"step": 1515520
},
{
"epoch": 0.02,
"learning_rate": 2.5180215977457526e-05,
"loss": 3.4739,
"step": 1516032
},
{
"epoch": 0.02,
"learning_rate": 2.5171830029947006e-05,
"loss": 3.49,
"step": 1516544
},
{
"epoch": 0.02,
"learning_rate": 2.516346046124022e-05,
"loss": 3.4937,
"step": 1517056
},
{
"epoch": 0.02,
"learning_rate": 2.51550745137297e-05,
"loss": 3.4809,
"step": 1517568
},
{
"epoch": 0.02,
"learning_rate": 2.514668856621918e-05,
"loss": 3.4778,
"step": 1518080
},
{
"epoch": 0.02,
"learning_rate": 2.513830261870866e-05,
"loss": 3.4826,
"step": 1518592
},
{
"epoch": 0.02,
"learning_rate": 2.5129933050001868e-05,
"loss": 3.4757,
"step": 1519104
},
{
"epoch": 0.02,
"learning_rate": 2.512154710249135e-05,
"loss": 3.4879,
"step": 1519616
},
{
"epoch": 0.02,
"learning_rate": 2.511316115498083e-05,
"loss": 3.4755,
"step": 1520128
},
{
"epoch": 0.02,
"learning_rate": 2.510477520747031e-05,
"loss": 3.4814,
"step": 1520640
},
{
"epoch": 0.02,
"learning_rate": 2.509640563876352e-05,
"loss": 3.4769,
"step": 1521152
},
{
"epoch": 0.02,
"learning_rate": 2.5088019691253e-05,
"loss": 3.4846,
"step": 1521664
},
{
"epoch": 0.02,
"learning_rate": 2.507963374374248e-05,
"loss": 3.4744,
"step": 1522176
},
{
"epoch": 0.02,
"learning_rate": 2.507124779623196e-05,
"loss": 3.4757,
"step": 1522688
},
{
"epoch": 0.02,
"learning_rate": 2.5062878227525172e-05,
"loss": 3.4837,
"step": 1523200
},
{
"epoch": 0.02,
"learning_rate": 2.5054492280014652e-05,
"loss": 3.4757,
"step": 1523712
},
{
"epoch": 0.02,
"learning_rate": 2.5046106332504132e-05,
"loss": 3.4823,
"step": 1524224
},
{
"epoch": 0.02,
"learning_rate": 2.5037720384993612e-05,
"loss": 3.4894,
"step": 1524736
},
{
"epoch": 0.02,
"learning_rate": 2.502935081628682e-05,
"loss": 3.4776,
"step": 1525248
},
{
"epoch": 0.02,
"learning_rate": 2.5020964868776305e-05,
"loss": 3.4784,
"step": 1525760
},
{
"epoch": 0.02,
"learning_rate": 2.5012578921265785e-05,
"loss": 3.4729,
"step": 1526272
},
{
"epoch": 0.03,
"eval_loss": 3.846611738204956,
"eval_runtime": 303.9017,
"eval_samples_per_second": 1255.639,
"eval_steps_per_second": 39.24,
"step": 1526400
},
{
"epoch": 1.0,
"learning_rate": 2.5004209352558994e-05,
"loss": 3.4742,
"step": 1526784
},
{
"epoch": 1.0,
"learning_rate": 2.499582340504847e-05,
"loss": 3.4683,
"step": 1527296
},
{
"epoch": 1.0,
"learning_rate": 2.498743745753795e-05,
"loss": 3.4869,
"step": 1527808
},
{
"epoch": 1.0,
"learning_rate": 2.4979051510027434e-05,
"loss": 3.4801,
"step": 1528320
},
{
"epoch": 1.0,
"learning_rate": 2.4970681941320646e-05,
"loss": 3.4896,
"step": 1528832
},
{
"epoch": 1.0,
"learning_rate": 2.4962295993810123e-05,
"loss": 3.471,
"step": 1529344
},
{
"epoch": 1.0,
"learning_rate": 2.4953910046299603e-05,
"loss": 3.4805,
"step": 1529856
},
{
"epoch": 1.0,
"learning_rate": 2.4945524098789083e-05,
"loss": 3.459,
"step": 1530368
},
{
"epoch": 1.0,
"learning_rate": 2.4937154530082295e-05,
"loss": 3.483,
"step": 1530880
},
{
"epoch": 1.0,
"learning_rate": 2.4928768582571775e-05,
"loss": 3.4705,
"step": 1531392
},
{
"epoch": 1.0,
"learning_rate": 2.4920382635061255e-05,
"loss": 3.4865,
"step": 1531904
},
{
"epoch": 1.0,
"learning_rate": 2.4911996687550735e-05,
"loss": 3.4827,
"step": 1532416
},
{
"epoch": 1.0,
"learning_rate": 2.4903627118843944e-05,
"loss": 3.4616,
"step": 1532928
},
{
"epoch": 1.0,
"learning_rate": 2.4895241171333424e-05,
"loss": 3.4724,
"step": 1533440
},
{
"epoch": 1.0,
"learning_rate": 2.4886855223822904e-05,
"loss": 3.4765,
"step": 1533952
},
{
"epoch": 1.0,
"learning_rate": 2.4878469276312384e-05,
"loss": 3.465,
"step": 1534464
},
{
"epoch": 1.0,
"learning_rate": 2.4870083328801867e-05,
"loss": 3.4731,
"step": 1534976
},
{
"epoch": 1.0,
"learning_rate": 2.4861697381291347e-05,
"loss": 3.4747,
"step": 1535488
},
{
"epoch": 1.0,
"learning_rate": 2.4853311433780827e-05,
"loss": 3.4713,
"step": 1536000
},
{
"epoch": 1.0,
"learning_rate": 2.4844925486270304e-05,
"loss": 3.492,
"step": 1536512
},
{
"epoch": 1.0,
"learning_rate": 2.4836555917563516e-05,
"loss": 3.4712,
"step": 1537024
},
{
"epoch": 1.0,
"learning_rate": 2.4828169970052996e-05,
"loss": 3.4722,
"step": 1537536
},
{
"epoch": 1.0,
"learning_rate": 2.4819784022542476e-05,
"loss": 3.4769,
"step": 1538048
},
{
"epoch": 1.0,
"learning_rate": 2.4811398075031956e-05,
"loss": 3.4816,
"step": 1538560
},
{
"epoch": 1.0,
"learning_rate": 2.480302850632517e-05,
"loss": 3.4687,
"step": 1539072
},
{
"epoch": 1.0,
"learning_rate": 2.479464255881465e-05,
"loss": 3.4792,
"step": 1539584
},
{
"epoch": 1.0,
"learning_rate": 2.4786256611304125e-05,
"loss": 3.4664,
"step": 1540096
},
{
"epoch": 1.0,
"learning_rate": 2.4777870663793605e-05,
"loss": 3.4697,
"step": 1540608
},
{
"epoch": 1.0,
"learning_rate": 2.476950109508682e-05,
"loss": 3.4658,
"step": 1541120
},
{
"epoch": 1.0,
"learning_rate": 2.47611151475763e-05,
"loss": 3.4689,
"step": 1541632
},
{
"epoch": 1.01,
"learning_rate": 2.4752729200065777e-05,
"loss": 3.4755,
"step": 1542144
},
{
"epoch": 1.01,
"learning_rate": 2.4744343252555257e-05,
"loss": 3.4771,
"step": 1542656
},
{
"epoch": 1.01,
"learning_rate": 2.473597368384847e-05,
"loss": 3.4783,
"step": 1543168
},
{
"epoch": 1.01,
"learning_rate": 2.472758773633795e-05,
"loss": 3.4824,
"step": 1543680
},
{
"epoch": 1.01,
"learning_rate": 2.471920178882743e-05,
"loss": 3.466,
"step": 1544192
},
{
"epoch": 1.01,
"learning_rate": 2.471081584131691e-05,
"loss": 3.4824,
"step": 1544704
},
{
"epoch": 1.01,
"learning_rate": 2.4702446272610122e-05,
"loss": 3.4707,
"step": 1545216
},
{
"epoch": 1.01,
"learning_rate": 2.46940603250996e-05,
"loss": 3.4721,
"step": 1545728
},
{
"epoch": 1.01,
"learning_rate": 2.468567437758908e-05,
"loss": 3.4617,
"step": 1546240
},
{
"epoch": 1.01,
"learning_rate": 2.467728843007856e-05,
"loss": 3.47,
"step": 1546752
},
{
"epoch": 1.01,
"learning_rate": 2.4668918861371775e-05,
"loss": 3.4665,
"step": 1547264
},
{
"epoch": 1.01,
"learning_rate": 2.466053291386125e-05,
"loss": 3.4822,
"step": 1547776
},
{
"epoch": 1.01,
"learning_rate": 2.465214696635073e-05,
"loss": 3.4673,
"step": 1548288
},
{
"epoch": 1.01,
"learning_rate": 2.464376101884021e-05,
"loss": 3.4712,
"step": 1548800
},
{
"epoch": 1.01,
"learning_rate": 2.463539145013342e-05,
"loss": 3.484,
"step": 1549312
},
{
"epoch": 1.01,
"learning_rate": 2.4627005502622903e-05,
"loss": 3.4779,
"step": 1549824
},
{
"epoch": 1.01,
"learning_rate": 2.4618619555112383e-05,
"loss": 3.4739,
"step": 1550336
},
{
"epoch": 1.01,
"learning_rate": 2.4610249986405596e-05,
"loss": 3.4683,
"step": 1550848
},
{
"epoch": 1.01,
"learning_rate": 2.4601864038895073e-05,
"loss": 3.4587,
"step": 1551360
},
{
"epoch": 1.01,
"learning_rate": 2.4593478091384552e-05,
"loss": 3.4792,
"step": 1551872
},
{
"epoch": 1.01,
"learning_rate": 2.4585092143874032e-05,
"loss": 3.4734,
"step": 1552384
},
{
"epoch": 1.01,
"learning_rate": 2.4576706196363512e-05,
"loss": 3.4623,
"step": 1552896
},
{
"epoch": 1.01,
"learning_rate": 2.4568336627656725e-05,
"loss": 3.4637,
"step": 1553408
},
{
"epoch": 1.01,
"learning_rate": 2.4559967058949937e-05,
"loss": 3.475,
"step": 1553920
},
{
"epoch": 1.01,
"learning_rate": 2.4551581111439417e-05,
"loss": 3.4533,
"step": 1554432
},
{
"epoch": 1.01,
"learning_rate": 2.4543195163928894e-05,
"loss": 3.4764,
"step": 1554944
},
{
"epoch": 1.01,
"learning_rate": 2.4534809216418374e-05,
"loss": 3.4564,
"step": 1555456
},
{
"epoch": 1.01,
"learning_rate": 2.4526423268907857e-05,
"loss": 3.4717,
"step": 1555968
},
{
"epoch": 1.01,
"learning_rate": 2.4518037321397337e-05,
"loss": 3.4713,
"step": 1556480
},
{
"epoch": 1.01,
"learning_rate": 2.4509651373886817e-05,
"loss": 3.4644,
"step": 1556992
},
{
"epoch": 1.01,
"learning_rate": 2.4501265426376297e-05,
"loss": 3.4693,
"step": 1557504
},
{
"epoch": 1.01,
"learning_rate": 2.4492895857669506e-05,
"loss": 3.4642,
"step": 1558016
},
{
"epoch": 1.01,
"learning_rate": 2.4484509910158986e-05,
"loss": 3.4618,
"step": 1558528
},
{
"epoch": 1.01,
"learning_rate": 2.4476123962648466e-05,
"loss": 3.4658,
"step": 1559040
},
{
"epoch": 1.01,
"learning_rate": 2.4467738015137946e-05,
"loss": 3.4682,
"step": 1559552
},
{
"epoch": 1.01,
"learning_rate": 2.445936844643116e-05,
"loss": 3.4666,
"step": 1560064
},
{
"epoch": 1.01,
"learning_rate": 2.445098249892064e-05,
"loss": 3.4657,
"step": 1560576
},
{
"epoch": 1.01,
"learning_rate": 2.444259655141012e-05,
"loss": 3.4544,
"step": 1561088
},
{
"epoch": 1.01,
"learning_rate": 2.44342106038996e-05,
"loss": 3.4581,
"step": 1561600
},
{
"epoch": 1.01,
"learning_rate": 2.4425841035192807e-05,
"loss": 3.4686,
"step": 1562112
},
{
"epoch": 1.01,
"learning_rate": 2.441745508768229e-05,
"loss": 3.4774,
"step": 1562624
},
{
"epoch": 1.01,
"learning_rate": 2.440906914017177e-05,
"loss": 3.4651,
"step": 1563136
},
{
"epoch": 1.01,
"learning_rate": 2.440068319266125e-05,
"loss": 3.4795,
"step": 1563648
},
{
"epoch": 1.01,
"learning_rate": 2.439231362395446e-05,
"loss": 3.4745,
"step": 1564160
},
{
"epoch": 1.01,
"learning_rate": 2.438392767644394e-05,
"loss": 3.4656,
"step": 1564672
},
{
"epoch": 1.01,
"learning_rate": 2.437554172893342e-05,
"loss": 3.4678,
"step": 1565184
},
{
"epoch": 1.01,
"learning_rate": 2.43671557814229e-05,
"loss": 3.4759,
"step": 1565696
},
{
"epoch": 1.01,
"learning_rate": 2.4358786212716112e-05,
"loss": 3.4675,
"step": 1566208
},
{
"epoch": 1.01,
"learning_rate": 2.435041664400932e-05,
"loss": 3.4651,
"step": 1566720
},
{
"epoch": 1.01,
"learning_rate": 2.43420306964988e-05,
"loss": 3.4754,
"step": 1567232
},
{
"epoch": 1.01,
"learning_rate": 2.433364474898828e-05,
"loss": 3.4696,
"step": 1567744
},
{
"epoch": 1.01,
"learning_rate": 2.432525880147776e-05,
"loss": 3.4733,
"step": 1568256
},
{
"epoch": 1.01,
"learning_rate": 2.4316872853967244e-05,
"loss": 3.4704,
"step": 1568768
},
{
"epoch": 1.01,
"learning_rate": 2.4308486906456724e-05,
"loss": 3.454,
"step": 1569280
},
{
"epoch": 1.01,
"learning_rate": 2.43001009589462e-05,
"loss": 3.455,
"step": 1569792
},
{
"epoch": 1.01,
"learning_rate": 2.429171501143568e-05,
"loss": 3.4679,
"step": 1570304
},
{
"epoch": 1.01,
"learning_rate": 2.4283345442728893e-05,
"loss": 3.473,
"step": 1570816
},
{
"epoch": 1.01,
"learning_rate": 2.4274959495218373e-05,
"loss": 3.4653,
"step": 1571328
},
{
"epoch": 1.01,
"learning_rate": 2.4266573547707853e-05,
"loss": 3.4666,
"step": 1571840
},
{
"epoch": 1.02,
"learning_rate": 2.4258187600197333e-05,
"loss": 3.4632,
"step": 1572352
},
{
"epoch": 1.02,
"learning_rate": 2.4249818031490546e-05,
"loss": 3.4613,
"step": 1572864
},
{
"epoch": 1.02,
"learning_rate": 2.4241432083980022e-05,
"loss": 3.4668,
"step": 1573376
},
{
"epoch": 1.02,
"learning_rate": 2.4233046136469502e-05,
"loss": 3.4686,
"step": 1573888
},
{
"epoch": 1.02,
"learning_rate": 2.4224660188958982e-05,
"loss": 3.4762,
"step": 1574400
},
{
"epoch": 1.02,
"learning_rate": 2.4216290620252198e-05,
"loss": 3.476,
"step": 1574912
},
{
"epoch": 1.02,
"learning_rate": 2.4207904672741675e-05,
"loss": 3.4712,
"step": 1575424
},
{
"epoch": 1.02,
"learning_rate": 2.4199518725231155e-05,
"loss": 3.4608,
"step": 1575936
},
{
"epoch": 1.02,
"learning_rate": 2.4191132777720635e-05,
"loss": 3.4745,
"step": 1576448
},
{
"epoch": 1.02,
"learning_rate": 2.4182763209013847e-05,
"loss": 3.4646,
"step": 1576960
},
{
"epoch": 1.02,
"learning_rate": 2.4174377261503327e-05,
"loss": 3.4742,
"step": 1577472
},
{
"epoch": 1.02,
"learning_rate": 2.4165991313992807e-05,
"loss": 3.4668,
"step": 1577984
},
{
"epoch": 1.02,
"learning_rate": 2.4157605366482287e-05,
"loss": 3.4607,
"step": 1578496
},
{
"epoch": 1.02,
"learning_rate": 2.4149235797775496e-05,
"loss": 3.4774,
"step": 1579008
},
{
"epoch": 1.02,
"learning_rate": 2.4140849850264976e-05,
"loss": 3.4726,
"step": 1579520
},
{
"epoch": 1.02,
"learning_rate": 2.4132463902754456e-05,
"loss": 3.4632,
"step": 1580032
},
{
"epoch": 1.02,
"learning_rate": 2.4124077955243936e-05,
"loss": 3.4668,
"step": 1580544
},
{
"epoch": 1.02,
"learning_rate": 2.411570838653715e-05,
"loss": 3.4674,
"step": 1581056
},
{
"epoch": 1.02,
"learning_rate": 2.410732243902663e-05,
"loss": 3.4553,
"step": 1581568
},
{
"epoch": 1.02,
"learning_rate": 2.4098936491516108e-05,
"loss": 3.4574,
"step": 1582080
},
{
"epoch": 1.02,
"learning_rate": 2.4090550544005588e-05,
"loss": 3.4674,
"step": 1582592
},
{
"epoch": 1.02,
"learning_rate": 2.4082180975298797e-05,
"loss": 3.4655,
"step": 1583104
},
{
"epoch": 1.02,
"learning_rate": 2.4073795027788277e-05,
"loss": 3.4646,
"step": 1583616
},
{
"epoch": 1.02,
"learning_rate": 2.406540908027776e-05,
"loss": 3.4629,
"step": 1584128
},
{
"epoch": 1.02,
"learning_rate": 2.405702313276724e-05,
"loss": 3.4629,
"step": 1584640
},
{
"epoch": 1.02,
"learning_rate": 2.404865356406045e-05,
"loss": 3.4836,
"step": 1585152
},
{
"epoch": 1.02,
"learning_rate": 2.404026761654993e-05,
"loss": 3.4821,
"step": 1585664
},
{
"epoch": 1.02,
"learning_rate": 2.403188166903941e-05,
"loss": 3.4704,
"step": 1586176
},
{
"epoch": 1.02,
"learning_rate": 2.402349572152889e-05,
"loss": 3.4692,
"step": 1586688
},
{
"epoch": 1.02,
"learning_rate": 2.4015126152822102e-05,
"loss": 3.4652,
"step": 1587200
},
{
"epoch": 1.02,
"learning_rate": 2.4006740205311582e-05,
"loss": 3.4616,
"step": 1587712
},
{
"epoch": 1.02,
"learning_rate": 2.3998354257801062e-05,
"loss": 3.4599,
"step": 1588224
},
{
"epoch": 1.02,
"learning_rate": 2.3989968310290542e-05,
"loss": 3.4633,
"step": 1588736
},
{
"epoch": 1.02,
"learning_rate": 2.398159874158375e-05,
"loss": 3.464,
"step": 1589248
},
{
"epoch": 1.02,
"learning_rate": 2.397321279407323e-05,
"loss": 3.4702,
"step": 1589760
},
{
"epoch": 1.02,
"learning_rate": 2.3964826846562714e-05,
"loss": 3.4659,
"step": 1590272
},
{
"epoch": 1.02,
"learning_rate": 2.3956440899052194e-05,
"loss": 3.4695,
"step": 1590784
},
{
"epoch": 1.02,
"learning_rate": 2.3948071330345403e-05,
"loss": 3.4655,
"step": 1591296
},
{
"epoch": 1.02,
"learning_rate": 2.3939685382834883e-05,
"loss": 3.4608,
"step": 1591808
},
{
"epoch": 1.02,
"learning_rate": 2.3931299435324363e-05,
"loss": 3.465,
"step": 1592320
},
{
"epoch": 1.02,
"learning_rate": 2.3922913487813843e-05,
"loss": 3.4737,
"step": 1592832
},
{
"epoch": 1.02,
"learning_rate": 2.3914543919107056e-05,
"loss": 3.4822,
"step": 1593344
},
{
"epoch": 1.02,
"learning_rate": 2.3906157971596536e-05,
"loss": 3.4713,
"step": 1593856
},
{
"epoch": 1.02,
"learning_rate": 2.3897772024086016e-05,
"loss": 3.464,
"step": 1594368
},
{
"epoch": 1.02,
"learning_rate": 2.3889386076575496e-05,
"loss": 3.472,
"step": 1594880
},
{
"epoch": 1.02,
"learning_rate": 2.3881016507868705e-05,
"loss": 3.4634,
"step": 1595392
},
{
"epoch": 1.02,
"learning_rate": 2.3872630560358185e-05,
"loss": 3.4755,
"step": 1595904
},
{
"epoch": 1.02,
"learning_rate": 2.3864244612847668e-05,
"loss": 3.4652,
"step": 1596416
},
{
"epoch": 1.02,
"learning_rate": 2.3855858665337148e-05,
"loss": 3.4677,
"step": 1596928
},
{
"epoch": 1.02,
"learning_rate": 2.3847489096630357e-05,
"loss": 3.4677,
"step": 1597440
},
{
"epoch": 1.02,
"learning_rate": 2.3839103149119837e-05,
"loss": 3.4756,
"step": 1597952
},
{
"epoch": 1.02,
"learning_rate": 2.3830717201609317e-05,
"loss": 3.4606,
"step": 1598464
},
{
"epoch": 1.02,
"learning_rate": 2.3822331254098797e-05,
"loss": 3.4645,
"step": 1598976
},
{
"epoch": 1.02,
"learning_rate": 2.381396168539201e-05,
"loss": 3.4702,
"step": 1599488
},
{
"epoch": 1.02,
"learning_rate": 2.380557573788149e-05,
"loss": 3.4641,
"step": 1600000
},
{
"epoch": 1.02,
"learning_rate": 2.379718979037097e-05,
"loss": 3.469,
"step": 1600512
},
{
"epoch": 1.02,
"learning_rate": 2.3788803842860446e-05,
"loss": 3.4766,
"step": 1601024
},
{
"epoch": 1.02,
"learning_rate": 2.378043427415366e-05,
"loss": 3.4698,
"step": 1601536
},
{
"epoch": 1.02,
"learning_rate": 2.377204832664314e-05,
"loss": 3.462,
"step": 1602048
},
{
"epoch": 1.02,
"learning_rate": 2.376366237913262e-05,
"loss": 3.4662,
"step": 1602560
},
{
"epoch": 1.03,
"eval_loss": 3.846222162246704,
"eval_runtime": 303.7824,
"eval_samples_per_second": 1256.133,
"eval_steps_per_second": 39.255,
"step": 1602720
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.1154526482988063e+18,
"trial_name": null,
"trial_params": null
}