full-transformer-3 / checkpoint-1755360 /trainer_state.json
abhinavp's picture
Training in progress, epoch 0, checkpoint
5b5546a verified
{
"best_metric": 3.8415114879608154,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full2/transformer/3/checkpoints/checkpoint-915840",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 1755360,
"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": 10.9241,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8212,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1757,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9703,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.808,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.6985,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5946,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5279,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4387,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3907,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3396,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3156,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2603,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.1973,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1716,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1336,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1049,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0781,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0526,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0119,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0047,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9693,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9494,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9211,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9195,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8928,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8653,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8486,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8312,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8205,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7977,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740117521192533e-05,
"loss": 4.7909,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731731573682013e-05,
"loss": 4.7772,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7644,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7614,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7466,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969820416244367e-05,
"loss": 4.7305,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7047,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7002,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6809,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6805,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6659,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6594,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6438,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6489,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6318,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6351,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6235,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5969,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 4.5892,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.6022,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.5871,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5717,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5584,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5618,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5453,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.558,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5245,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5362,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5343,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5112,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5263,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.4983,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4984,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4859,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.5022,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.474,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.479,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4624,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4604,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.473,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940482703000532e-05,
"loss": 4.4654,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396441082494794e-05,
"loss": 4.456,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388055134984274e-05,
"loss": 4.4562,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4617,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.437,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4508,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4244,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4234,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4223,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4254,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4175,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4251,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930422841748654e-05,
"loss": 4.4086,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.3894,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.391,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.4016,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927070100624819e-05,
"loss": 4.3874,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92623314375414e-05,
"loss": 4.3859,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.389,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3712,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3787,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.9228804026303046e-05,
"loss": 4.373,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922041807879253e-05,
"loss": 4.3774,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921203213128201e-05,
"loss": 4.3744,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3688,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3495,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3566,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.348,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3525,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.3569,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.3363,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.341,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3412,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3347,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3252,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3272,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3169,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3151,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3145,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3138,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3071,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3121,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3038,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3067,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3131,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027606801265495e-05,
"loss": 4.3093,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.3034,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.294,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.2936,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2923,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.2791,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2812,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.2796,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2837,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2739,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2818,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2747,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2663,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.261,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2785,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2694,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.261,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2628,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.2647,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.2615,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2638,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2533,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2528,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2518,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2424,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.2386,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.2404,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.2414,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.234,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2425,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.2337,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2361,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2409,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2206,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.191587448120117,
"eval_runtime": 303.7914,
"eval_samples_per_second": 1256.095,
"eval_steps_per_second": 39.254,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.2108,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.2076,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.2321,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.2169,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.2194,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.2116,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.2051,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.196,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.2055,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.1978,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2208,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2054,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642000625015155e-05,
"loss": 4.187,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.1882,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.1902,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.1772,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.1913,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.1867,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.174,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.2,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.179,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.1813,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.1719,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.1894,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.1664,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.1687,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.1636,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.1628,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.1611,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.1587,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.1626,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.1629,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.16,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.1648,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.1591,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.1589,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.1444,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.1477,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.1376,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.1462,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.1376,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.1471,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.1289,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382134525011416e-05,
"loss": 4.1472,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83737485775009e-05,
"loss": 4.1389,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836536262999038e-05,
"loss": 4.1402,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1379,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834860711377307e-05,
"loss": 4.1222,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834022116626255e-05,
"loss": 4.1244,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833183521875203e-05,
"loss": 4.1387,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.1291,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831506332373099e-05,
"loss": 4.1222,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.83066937550242e-05,
"loss": 4.1158,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829830780751368e-05,
"loss": 4.1245,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828992186000316e-05,
"loss": 4.1049,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828153591249264e-05,
"loss": 4.1315,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273166343785856e-05,
"loss": 4.1021,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264780396275336e-05,
"loss": 4.1221,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256394448764816e-05,
"loss": 4.1188,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248008501254296e-05,
"loss": 4.1058,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239638932547505e-05,
"loss": 4.1184,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231252985036985e-05,
"loss": 4.1064,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222867037526465e-05,
"loss": 4.104,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214481090015945e-05,
"loss": 4.0931,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206111521309154e-05,
"loss": 4.1177,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197725573798634e-05,
"loss": 4.092,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189339626288114e-05,
"loss": 4.1039,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180953678777594e-05,
"loss": 4.0828,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817258411007081e-05,
"loss": 4.095,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816419816256029e-05,
"loss": 4.1056,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815581221504977e-05,
"loss": 4.1028,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814742626753924e-05,
"loss": 4.0987,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813905669883246e-05,
"loss": 4.1031,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813067075132194e-05,
"loss": 4.1071,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812228480381141e-05,
"loss": 4.0928,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811389885630089e-05,
"loss": 4.1021,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810552928759411e-05,
"loss": 4.0867,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809714334008359e-05,
"loss": 4.0894,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808875739257306e-05,
"loss": 4.0845,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808037144506255e-05,
"loss": 4.0939,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807200187635576e-05,
"loss": 4.0931,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063615928845243e-05,
"loss": 4.0986,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055229981334717e-05,
"loss": 4.0888,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046844033824197e-05,
"loss": 4.0683,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803847446511741e-05,
"loss": 4.0729,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8030088517606886e-05,
"loss": 4.0847,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.8021702570096366e-05,
"loss": 4.0794,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013316622585846e-05,
"loss": 4.0761,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800494705387906e-05,
"loss": 4.0831,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799657748517227e-05,
"loss": 4.0694,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798819153766175e-05,
"loss": 4.0714,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797980559015123e-05,
"loss": 4.0745,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797141964264071e-05,
"loss": 4.0829,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796303369513019e-05,
"loss": 4.0808,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795464774761967e-05,
"loss": 4.0838,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794626180010915e-05,
"loss": 4.0589,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793787585259863e-05,
"loss": 4.0692,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792950628389184e-05,
"loss": 4.0653,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792112033638132e-05,
"loss": 4.0667,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.79127343888708e-05,
"loss": 4.0789,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790434844136028e-05,
"loss": 4.0574,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789597887265349e-05,
"loss": 4.062,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788759292514297e-05,
"loss": 4.0692,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787920697763245e-05,
"loss": 4.0666,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870821030121935e-05,
"loss": 4.0508,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786246784021888e-05,
"loss": 4.0626,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785408189270836e-05,
"loss": 4.0543,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784569594519783e-05,
"loss": 4.0507,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783730999768731e-05,
"loss": 4.0485,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782892405017679e-05,
"loss": 4.0504,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782053810266627e-05,
"loss": 4.0483,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781215215515575e-05,
"loss": 4.0593,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780376620764523e-05,
"loss": 4.0458,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779539663893844e-05,
"loss": 4.0548,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778701069142792e-05,
"loss": 4.0652,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.77786247439174e-05,
"loss": 4.0572,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777025517521062e-05,
"loss": 4.0558,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.77618692277001e-05,
"loss": 4.0504,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775348328018958e-05,
"loss": 4.0468,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774509733267906e-05,
"loss": 4.0483,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773671138516854e-05,
"loss": 4.0392,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728341816461747e-05,
"loss": 4.0396,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719955868951227e-05,
"loss": 4.0421,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711569921440707e-05,
"loss": 4.0472,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703183973930186e-05,
"loss": 4.0422,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694798026419666e-05,
"loss": 4.0442,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686412078909146e-05,
"loss": 4.0435,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.7678026131398626e-05,
"loss": 4.0316,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766965656269184e-05,
"loss": 4.031,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766127061518132e-05,
"loss": 4.0513,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.76528846676708e-05,
"loss": 4.0454,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764449872016028e-05,
"loss": 4.0391,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763612915145349e-05,
"loss": 4.0339,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762774320394297e-05,
"loss": 4.0406,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761935725643245e-05,
"loss": 4.037,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761097130892193e-05,
"loss": 4.0458,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760260174021514e-05,
"loss": 4.036,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759421579270462e-05,
"loss": 4.0347,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.75858298451941e-05,
"loss": 4.0337,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757744389768358e-05,
"loss": 4.0291,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569074328976796e-05,
"loss": 4.0231,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560688381466276e-05,
"loss": 4.0293,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552302433955756e-05,
"loss": 4.034,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543916486445236e-05,
"loss": 4.0184,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535546917738445e-05,
"loss": 4.0364,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527160970227925e-05,
"loss": 4.0276,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518775022717405e-05,
"loss": 4.0261,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510389075206885e-05,
"loss": 4.0301,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7502019506500094e-05,
"loss": 4.0169,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.023649215698242,
"eval_runtime": 303.8573,
"eval_samples_per_second": 1255.823,
"eval_steps_per_second": 39.245,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493633558989574e-05,
"loss": 4.0052,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485247611479054e-05,
"loss": 4.0069,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476861663968534e-05,
"loss": 4.0317,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468475716458014e-05,
"loss": 4.0181,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460089768947494e-05,
"loss": 4.0264,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451703821436974e-05,
"loss": 4.0103,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443317873926453e-05,
"loss": 4.0143,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434931926415933e-05,
"loss": 4.0003,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426545978905413e-05,
"loss": 4.0137,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741816003139489e-05,
"loss": 4.0083,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.74097904626881e-05,
"loss": 4.0262,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740140451517758e-05,
"loss": 4.0187,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739303494647079e-05,
"loss": 3.9954,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738464899896027e-05,
"loss": 4.0004,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737626305144975e-05,
"loss": 4.0056,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736787710393923e-05,
"loss": 3.99,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735949115642871e-05,
"loss": 4.0028,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.73511052089182e-05,
"loss": 4.0038,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734271926140768e-05,
"loss": 3.9945,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733433331389716e-05,
"loss": 4.0224,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732594736638664e-05,
"loss": 3.9979,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731756141887612e-05,
"loss": 4.0057,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730919185016933e-05,
"loss": 3.9946,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730080590265881e-05,
"loss": 4.0123,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729241995514829e-05,
"loss": 3.9882,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728403400763777e-05,
"loss": 3.9949,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727564806012725e-05,
"loss": 3.9899,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267278491420456e-05,
"loss": 3.9943,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258892543909936e-05,
"loss": 3.9874,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250506596399416e-05,
"loss": 3.9863,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7242120648888896e-05,
"loss": 3.9943,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723373470137838e-05,
"loss": 3.9957,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225348753867856e-05,
"loss": 3.9883,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216962806357336e-05,
"loss": 3.9999,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720859323765055e-05,
"loss": 3.9871,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720020729014003e-05,
"loss": 3.9926,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191821342629505e-05,
"loss": 3.9803,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183435395118985e-05,
"loss": 3.9849,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175049447608465e-05,
"loss": 3.9718,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716667987890168e-05,
"loss": 3.9859,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158293931391154e-05,
"loss": 3.9738,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149907983880634e-05,
"loss": 3.9883,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714152203637012e-05,
"loss": 3.9713,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71331360888596e-05,
"loss": 3.9832,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712475014134908e-05,
"loss": 3.9873,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711636419383856e-05,
"loss": 3.9821,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710797824632804e-05,
"loss": 3.9833,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709960867762125e-05,
"loss": 3.9654,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709122273011073e-05,
"loss": 3.9684,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708283678260021e-05,
"loss": 3.9838,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707445083508969e-05,
"loss": 3.9744,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.70660812663829e-05,
"loss": 3.9714,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705769531887238e-05,
"loss": 3.9612,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704930937136186e-05,
"loss": 3.9736,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704092342385134e-05,
"loss": 3.9515,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032553855144554e-05,
"loss": 3.9843,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024167907634034e-05,
"loss": 3.9517,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015781960123514e-05,
"loss": 3.9724,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007396012612994e-05,
"loss": 3.9738,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699904282270993e-05,
"loss": 3.9556,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699065687519941e-05,
"loss": 3.9752,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698227092768889e-05,
"loss": 3.9597,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697388498017837e-05,
"loss": 3.9588,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696549903266785e-05,
"loss": 3.9478,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695711308515733e-05,
"loss": 3.9722,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694874351645054e-05,
"loss": 3.9511,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694035756894003e-05,
"loss": 3.9581,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693197162142951e-05,
"loss": 3.9449,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692358567391899e-05,
"loss": 3.9509,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.69152161052122e-05,
"loss": 3.9637,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906830157701677e-05,
"loss": 3.9667,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898444210191157e-05,
"loss": 3.9525,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890058262680636e-05,
"loss": 3.9677,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881672315170116e-05,
"loss": 3.9663,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873286367659596e-05,
"loss": 3.957,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864900420149076e-05,
"loss": 3.9579,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856514472638556e-05,
"loss": 3.9571,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848144903931765e-05,
"loss": 3.9515,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683977533522498e-05,
"loss": 3.9489,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683138938771446e-05,
"loss": 3.9565,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682300344020394e-05,
"loss": 3.9604,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681461749269342e-05,
"loss": 3.9661,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.68062315451829e-05,
"loss": 3.9524,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679784559767238e-05,
"loss": 3.9316,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678945965016186e-05,
"loss": 3.9422,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678109008145507e-05,
"loss": 3.9524,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677270413394455e-05,
"loss": 3.9471,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676431818643403e-05,
"loss": 3.9438,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9512,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674756267021672e-05,
"loss": 3.945,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.67391767227062e-05,
"loss": 3.9376,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673079077519568e-05,
"loss": 3.9451,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672240482768516e-05,
"loss": 3.9541,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671401888017464e-05,
"loss": 3.9493,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705649311467855e-05,
"loss": 3.9553,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697263363957335e-05,
"loss": 3.936,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688877416446815e-05,
"loss": 3.9418,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668049146893629e-05,
"loss": 3.939,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667210552142577e-05,
"loss": 3.9439,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666371957391525e-05,
"loss": 3.9508,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665535000520846e-05,
"loss": 3.9352,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664696405769794e-05,
"loss": 3.9357,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663857811018742e-05,
"loss": 3.944,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66301921626769e-05,
"loss": 3.9467,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621806215166383e-05,
"loss": 3.9267,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661343664645959e-05,
"loss": 3.9351,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660505069894907e-05,
"loss": 3.9377,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659666475143855e-05,
"loss": 3.9278,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658827880392803e-05,
"loss": 3.9274,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657989285641751e-05,
"loss": 3.9298,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657152328771072e-05,
"loss": 3.9321,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.65631373402002e-05,
"loss": 3.9369,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655475139268968e-05,
"loss": 3.9253,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654636544517916e-05,
"loss": 3.9325,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653799587647237e-05,
"loss": 3.9431,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652960992896185e-05,
"loss": 3.9443,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521240360255066e-05,
"loss": 3.9347,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512854412744546e-05,
"loss": 3.9352,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.6504468465234026e-05,
"loss": 3.9296,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6496082517723506e-05,
"loss": 3.9319,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487696570212986e-05,
"loss": 3.9198,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479310622702466e-05,
"loss": 3.9219,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470924675191946e-05,
"loss": 3.9262,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462538727681426e-05,
"loss": 3.936,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454169158974635e-05,
"loss": 3.9274,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445783211464115e-05,
"loss": 3.9296,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437397263953595e-05,
"loss": 3.9293,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429011316443075e-05,
"loss": 3.9188,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642064174773629e-05,
"loss": 3.9162,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641225580022577e-05,
"loss": 3.9381,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640386985271525e-05,
"loss": 3.9355,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639548390520473e-05,
"loss": 3.9241,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638709795769421e-05,
"loss": 3.9217,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637872838898742e-05,
"loss": 3.925,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.63703424414769e-05,
"loss": 3.9272,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636195649396638e-05,
"loss": 3.9389,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635357054645586e-05,
"loss": 3.9228,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634520097774907e-05,
"loss": 3.9218,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633681503023855e-05,
"loss": 3.9223,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632842908272803e-05,
"loss": 3.9205,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632004313521751e-05,
"loss": 3.9166,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631165718770699e-05,
"loss": 3.9181,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303287619000204e-05,
"loss": 3.9232,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294901671489684e-05,
"loss": 3.9146,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286515723979164e-05,
"loss": 3.925,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6278129776468644e-05,
"loss": 3.9244,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626974382895812e-05,
"loss": 3.917,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626137426025133e-05,
"loss": 3.9226,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625298831274081e-05,
"loss": 3.9099,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9505887031555176,
"eval_runtime": 308.0876,
"eval_samples_per_second": 1238.579,
"eval_steps_per_second": 38.707,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624460236523029e-05,
"loss": 3.9115,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.6236216417719766e-05,
"loss": 3.901,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622784684901298e-05,
"loss": 3.926,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621946090150246e-05,
"loss": 3.9124,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621107495399194e-05,
"loss": 3.9263,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620268900648142e-05,
"loss": 3.9036,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.61943030589709e-05,
"loss": 3.9136,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618593349026412e-05,
"loss": 3.8941,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617754754275359e-05,
"loss": 3.9128,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616916159524307e-05,
"loss": 3.9038,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616077564773255e-05,
"loss": 3.9237,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615240607902577e-05,
"loss": 3.9145,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6144036510318976e-05,
"loss": 3.8942,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135650562808456e-05,
"loss": 3.8993,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.6127264615297936e-05,
"loss": 3.9062,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.6118878667787416e-05,
"loss": 3.8914,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.6110492720276896e-05,
"loss": 3.9,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.6102106772766376e-05,
"loss": 3.9042,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.6093720825255856e-05,
"loss": 3.895,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.6085334877745336e-05,
"loss": 3.9236,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076965309038545e-05,
"loss": 3.901,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068579361528025e-05,
"loss": 3.9025,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6060193414017505e-05,
"loss": 3.9009,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051807466506985e-05,
"loss": 3.9103,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.6043437897800194e-05,
"loss": 3.8919,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.6035051950289674e-05,
"loss": 3.8981,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.6026666002779154e-05,
"loss": 3.8927,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018280055268634e-05,
"loss": 3.896,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.600991048656185e-05,
"loss": 3.8897,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600152453905133e-05,
"loss": 3.8914,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599313859154081e-05,
"loss": 3.8948,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598475264403029e-05,
"loss": 3.9018,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597636669651977e-05,
"loss": 3.9008,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596799712781298e-05,
"loss": 3.9004,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595961118030246e-05,
"loss": 3.8923,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595122523279194e-05,
"loss": 3.8991,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594283928528142e-05,
"loss": 3.882,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593446971657463e-05,
"loss": 3.8963,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592608376906411e-05,
"loss": 3.879,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591769782155359e-05,
"loss": 3.8893,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590931187404307e-05,
"loss": 3.8814,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900925926532554e-05,
"loss": 3.8974,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589255635782576e-05,
"loss": 3.8796,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588417041031524e-05,
"loss": 3.8857,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587578446280472e-05,
"loss": 3.8973,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.58673985152942e-05,
"loss": 3.8931,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585902894658741e-05,
"loss": 3.8936,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585064299907689e-05,
"loss": 3.8739,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584225705156637e-05,
"loss": 3.8763,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583387110405585e-05,
"loss": 3.8893,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582550153534906e-05,
"loss": 3.8852,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581711558783854e-05,
"loss": 3.8803,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580872964032802e-05,
"loss": 3.8745,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580034369281751e-05,
"loss": 3.8861,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579197412411072e-05,
"loss": 3.8636,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.57835881766002e-05,
"loss": 3.8869,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577520222908968e-05,
"loss": 3.8683,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576681628157916e-05,
"loss": 3.8791,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758446712872366e-05,
"loss": 3.8877,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5750060765361846e-05,
"loss": 3.8679,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741674817851326e-05,
"loss": 3.882,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733288870340806e-05,
"loss": 3.8736,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724902922830286e-05,
"loss": 3.8706,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716533354123495e-05,
"loss": 3.8646,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5708147406612975e-05,
"loss": 3.8788,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569976145910246e-05,
"loss": 3.8657,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569137551159194e-05,
"loss": 3.873,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568300594288515e-05,
"loss": 3.8597,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567461999537463e-05,
"loss": 3.8632,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566623404786411e-05,
"loss": 3.8764,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565784810035359e-05,
"loss": 3.8798,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.56494785316468e-05,
"loss": 3.8675,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564109258413628e-05,
"loss": 3.8834,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563270663662576e-05,
"loss": 3.8784,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562432068911524e-05,
"loss": 3.8705,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561595112040845e-05,
"loss": 3.8757,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560756517289793e-05,
"loss": 3.8713,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.5599179225387415e-05,
"loss": 3.8683,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.5590793277876895e-05,
"loss": 3.8676,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582407330366375e-05,
"loss": 3.8742,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.5574037761659584e-05,
"loss": 3.8785,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.5565651814149064e-05,
"loss": 3.8726,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.5557265866638544e-05,
"loss": 3.8741,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.5548879919128024e-05,
"loss": 3.8518,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554051035042123e-05,
"loss": 3.858,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553212440291071e-05,
"loss": 3.8693,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552373845540019e-05,
"loss": 3.8658,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515352507889666e-05,
"loss": 3.8618,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550698293918288e-05,
"loss": 3.8693,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.54986133704761e-05,
"loss": 3.8636,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549022742296558e-05,
"loss": 3.8569,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548184147545506e-05,
"loss": 3.8619,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547345552794454e-05,
"loss": 3.8701,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546506958043402e-05,
"loss": 3.8676,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.54566836329235e-05,
"loss": 3.8768,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544829768541297e-05,
"loss": 3.8586,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543991173790245e-05,
"loss": 3.8576,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.5431542169195667e-05,
"loss": 3.8603,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542315622168514e-05,
"loss": 3.863,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541477027417462e-05,
"loss": 3.8706,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406384326664106e-05,
"loss": 3.8563,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539801475795732e-05,
"loss": 3.8569,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389628810446796e-05,
"loss": 3.8626,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5381242862936275e-05,
"loss": 3.868,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372856915425755e-05,
"loss": 3.8495,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536448734671897e-05,
"loss": 3.8575,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5356101399208444e-05,
"loss": 3.8602,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347715451697924e-05,
"loss": 3.8494,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339329504187404e-05,
"loss": 3.8452,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330959935480613e-05,
"loss": 3.855,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322573987970093e-05,
"loss": 3.8567,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314188040459573e-05,
"loss": 3.8559,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530580209294906e-05,
"loss": 3.8504,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529743252424227e-05,
"loss": 3.8525,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528904657673175e-05,
"loss": 3.8684,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528066062922123e-05,
"loss": 3.8665,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.5272291060514445e-05,
"loss": 3.8609,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526390511300392e-05,
"loss": 3.8575,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.52555191654934e-05,
"loss": 3.8534,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524713321798288e-05,
"loss": 3.8536,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523874727047236e-05,
"loss": 3.8433,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523036132296184e-05,
"loss": 3.8477,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522197537545132e-05,
"loss": 3.8489,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.52135894279408e-05,
"loss": 3.8592,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520521985923401e-05,
"loss": 3.8504,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.5196833911723494e-05,
"loss": 3.8593,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.5188447964212974e-05,
"loss": 3.8497,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.518007839550618e-05,
"loss": 3.8486,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517169244799566e-05,
"loss": 3.842,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516330650048514e-05,
"loss": 3.8635,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515492055297462e-05,
"loss": 3.8639,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.51465346054641e-05,
"loss": 3.8509,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513816503675731e-05,
"loss": 3.8459,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512977908924679e-05,
"loss": 3.8535,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512139314173627e-05,
"loss": 3.8479,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511300719422575e-05,
"loss": 3.8643,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510463762551896e-05,
"loss": 3.8459,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509625167800845e-05,
"loss": 3.8533,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508786573049793e-05,
"loss": 3.8476,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507947978298741e-05,
"loss": 3.8541,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5071110214280616e-05,
"loss": 3.8412,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062724266770096e-05,
"loss": 3.8449,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.5054338319259576e-05,
"loss": 3.8521,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.5045952371749056e-05,
"loss": 3.8436,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.5037582803042265e-05,
"loss": 3.8514,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5029196855531745e-05,
"loss": 3.8534,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020810908021225e-05,
"loss": 3.8458,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012424960510705e-05,
"loss": 3.8483,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.5004055391803914e-05,
"loss": 3.8437,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.9106061458587646,
"eval_runtime": 337.8387,
"eval_samples_per_second": 1129.507,
"eval_steps_per_second": 35.298,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.49956694442934e-05,
"loss": 3.8314,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498728349678288e-05,
"loss": 3.8301,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497889754927236e-05,
"loss": 3.8519,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497051160176184e-05,
"loss": 3.8438,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496212565425132e-05,
"loss": 3.8554,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.49537397067408e-05,
"loss": 3.8338,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945353759230274e-05,
"loss": 3.8451,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936967811719754e-05,
"loss": 3.8234,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492859824301297e-05,
"loss": 3.8446,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.492021229550245e-05,
"loss": 3.8338,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491182634799192e-05,
"loss": 3.849,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490345677928514e-05,
"loss": 3.8476,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.4895087210578355e-05,
"loss": 3.8215,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.4886701263067835e-05,
"loss": 3.8346,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4878315315557315e-05,
"loss": 3.8357,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.4869929368046795e-05,
"loss": 3.8237,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.4861543420536275e-05,
"loss": 3.8311,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485315747302575e-05,
"loss": 3.8346,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484477152551523e-05,
"loss": 3.832,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483638557800471e-05,
"loss": 3.8504,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.4828016009297924e-05,
"loss": 3.8304,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.48196300617874e-05,
"loss": 3.8356,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481124411427688e-05,
"loss": 3.8349,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480285816676636e-05,
"loss": 3.8404,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479448859805957e-05,
"loss": 3.8255,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478610265054905e-05,
"loss": 3.838,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477771670303853e-05,
"loss": 3.8231,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476933075552801e-05,
"loss": 3.827,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476096118682122e-05,
"loss": 3.8225,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.47525752393107e-05,
"loss": 3.8248,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474418929180018e-05,
"loss": 3.8268,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473580334428966e-05,
"loss": 3.8363,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472743377558287e-05,
"loss": 3.8336,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471904782807235e-05,
"loss": 3.8359,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471066188056183e-05,
"loss": 3.8252,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470227593305131e-05,
"loss": 3.8332,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693906364344526e-05,
"loss": 3.8212,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.4685520416834006e-05,
"loss": 3.8246,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4677134469323486e-05,
"loss": 3.8156,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668748521812966e-05,
"loss": 3.8221,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660378953106175e-05,
"loss": 3.8188,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651993005595655e-05,
"loss": 3.8314,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.4643607058085135e-05,
"loss": 3.8163,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4635221110574615e-05,
"loss": 3.8204,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626851541867824e-05,
"loss": 3.8345,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618465594357304e-05,
"loss": 3.8271,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4610079646846784e-05,
"loss": 3.8269,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601693699336264e-05,
"loss": 3.8158,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459332413062948e-05,
"loss": 3.8061,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.458493818311896e-05,
"loss": 3.8272,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457655223560844e-05,
"loss": 3.8225,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456816628809792e-05,
"loss": 3.8137,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455979671939113e-05,
"loss": 3.8142,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455141077188061e-05,
"loss": 3.8246,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454302482437009e-05,
"loss": 3.8001,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453463887685957e-05,
"loss": 3.8248,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452626930815278e-05,
"loss": 3.8035,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451788336064226e-05,
"loss": 3.8183,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450949741313174e-05,
"loss": 3.8218,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450111146562122e-05,
"loss": 3.8106,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.4492741896914433e-05,
"loss": 3.8159,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.4484355949403913e-05,
"loss": 3.8144,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.4475970001893393e-05,
"loss": 3.8062,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446758405438287e-05,
"loss": 3.8084,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445921448567608e-05,
"loss": 3.8122,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445082853816556e-05,
"loss": 3.8076,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444244259065504e-05,
"loss": 3.8099,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443405664314452e-05,
"loss": 3.7994,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442568707443773e-05,
"loss": 3.7981,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441730112692721e-05,
"loss": 3.8123,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440891517941669e-05,
"loss": 3.8216,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440052923190617e-05,
"loss": 3.8057,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439215966319939e-05,
"loss": 3.8243,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438377371568887e-05,
"loss": 3.8199,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437538776817835e-05,
"loss": 3.8076,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436700182066783e-05,
"loss": 3.8109,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.4358632251961036e-05,
"loss": 3.818,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.4350246304450516e-05,
"loss": 3.807,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.4341860356939996e-05,
"loss": 3.8081,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333474409429476e-05,
"loss": 3.8148,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4325104840722685e-05,
"loss": 3.8143,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316718893212165e-05,
"loss": 3.8136,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4308332945701645e-05,
"loss": 3.8109,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299946998191125e-05,
"loss": 3.7949,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429157742948434e-05,
"loss": 3.7961,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428319148197382e-05,
"loss": 3.8091,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.42748055344633e-05,
"loss": 3.8091,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426641958695278e-05,
"loss": 3.8027,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425805001824599e-05,
"loss": 3.8049,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.42496804495392e-05,
"loss": 3.8027,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424129450202868e-05,
"loss": 3.7986,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423290855451816e-05,
"loss": 3.804,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422452260700764e-05,
"loss": 3.806,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421613665949712e-05,
"loss": 3.812,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.42077507119866e-05,
"loss": 3.812,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419936476447608e-05,
"loss": 3.8072,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419097881696556e-05,
"loss": 3.7948,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182609248258774e-05,
"loss": 3.8069,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4174223300748254e-05,
"loss": 3.8016,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.4165837353237734e-05,
"loss": 3.8135,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157451405727214e-05,
"loss": 3.8002,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.4149081837020423e-05,
"loss": 3.7935,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.41406958895099e-05,
"loss": 3.8105,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413230994199938e-05,
"loss": 3.8059,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412392399448886e-05,
"loss": 3.7983,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411555442578207e-05,
"loss": 3.7995,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410716847827155e-05,
"loss": 3.8031,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409878253076103e-05,
"loss": 3.7857,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409039658325051e-05,
"loss": 3.79,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408202701454373e-05,
"loss": 3.8032,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407364106703321e-05,
"loss": 3.7956,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406525511952269e-05,
"loss": 3.8,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405686917201217e-05,
"loss": 3.7944,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404849960330538e-05,
"loss": 3.7934,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.404011365579486e-05,
"loss": 3.8137,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403172770828434e-05,
"loss": 3.8098,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402334176077382e-05,
"loss": 3.805,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.4014972192067026e-05,
"loss": 3.8016,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.4006586244556506e-05,
"loss": 3.7944,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.3998200297045986e-05,
"loss": 3.7962,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.3989814349535466e-05,
"loss": 3.7902,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398144478082868e-05,
"loss": 3.7964,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397305883331816e-05,
"loss": 3.7937,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396467288580764e-05,
"loss": 3.8019,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395628693829712e-05,
"loss": 3.7935,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394791736959033e-05,
"loss": 3.8001,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393953142207981e-05,
"loss": 3.7958,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393114547456929e-05,
"loss": 3.7912,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392275952705877e-05,
"loss": 3.7904,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391438995835198e-05,
"loss": 3.8044,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390600401084146e-05,
"loss": 3.8088,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389761806333094e-05,
"loss": 3.7996,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388923211582042e-05,
"loss": 3.789,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.3880878925917365e-05,
"loss": 3.7993,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872492978406845e-05,
"loss": 3.7922,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3864107030896325e-05,
"loss": 3.8057,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855721083385804e-05,
"loss": 3.7933,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3847335135875284e-05,
"loss": 3.7958,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.3838949188364764e-05,
"loss": 3.7936,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830563240854244e-05,
"loss": 3.8011,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382217729334372e-05,
"loss": 3.7856,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381380772463693e-05,
"loss": 3.7901,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380542177712641e-05,
"loss": 3.7974,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379703582961589e-05,
"loss": 3.7909,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378864988210537e-05,
"loss": 3.7969,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378028031339859e-05,
"loss": 3.7981,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377189436588807e-05,
"loss": 3.7941,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376350841837754e-05,
"loss": 3.791,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375512247086702e-05,
"loss": 3.7918,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.885725498199463,
"eval_runtime": 303.7787,
"eval_samples_per_second": 1256.148,
"eval_steps_per_second": 39.256,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.374675290216024e-05,
"loss": 3.7886,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.373836695464972e-05,
"loss": 3.7739,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.372998100713919e-05,
"loss": 3.7993,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.372159505962867e-05,
"loss": 3.7926,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.371322549092189e-05,
"loss": 3.7991,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.370483954341137e-05,
"loss": 3.7855,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.369645359590085e-05,
"loss": 3.7883,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368806764839033e-05,
"loss": 3.7759,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367969807968354e-05,
"loss": 3.7862,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.3671312132173016e-05,
"loss": 3.785,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366294256346623e-05,
"loss": 3.7933,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.365455661595571e-05,
"loss": 3.7951,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.364617066844519e-05,
"loss": 3.7706,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.3637784720934665e-05,
"loss": 3.7836,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.3629398773424145e-05,
"loss": 3.7861,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.3621012825913625e-05,
"loss": 3.7714,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.3612626878403105e-05,
"loss": 3.779,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.3604240930892585e-05,
"loss": 3.7804,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.35958713621858e-05,
"loss": 3.7783,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.358748541467528e-05,
"loss": 3.7967,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.357909946716476e-05,
"loss": 3.781,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.357071351965424e-05,
"loss": 3.7876,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.356234395094745e-05,
"loss": 3.7822,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.355395800343693e-05,
"loss": 3.7856,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.354557205592641e-05,
"loss": 3.7733,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.353718610841589e-05,
"loss": 3.7831,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.35288165397091e-05,
"loss": 3.7765,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.352043059219858e-05,
"loss": 3.7736,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.351204464468806e-05,
"loss": 3.7722,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.350365869717754e-05,
"loss": 3.7764,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.349528912847075e-05,
"loss": 3.7765,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.3486903180960234e-05,
"loss": 3.7835,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.3478517233449714e-05,
"loss": 3.7862,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.3470131285939194e-05,
"loss": 3.783,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.34617617172324e-05,
"loss": 3.7736,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345337576972188e-05,
"loss": 3.7798,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344498982221136e-05,
"loss": 3.7752,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.343660387470084e-05,
"loss": 3.7749,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.342823430599405e-05,
"loss": 3.764,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.341986473728726e-05,
"loss": 3.7699,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.341147878977674e-05,
"loss": 3.7726,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.340309284226622e-05,
"loss": 3.7786,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.33947068947557e-05,
"loss": 3.769,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338632094724519e-05,
"loss": 3.7696,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337793499973467e-05,
"loss": 3.7873,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.336954905222415e-05,
"loss": 3.7772,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.336116310471363e-05,
"loss": 3.7797,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.335279353600684e-05,
"loss": 3.7677,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334440758849632e-05,
"loss": 3.7546,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.33360216409858e-05,
"loss": 3.7785,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.332763569347528e-05,
"loss": 3.775,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.3319266124768486e-05,
"loss": 3.7672,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.3310880177257966e-05,
"loss": 3.767,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.3302494229747446e-05,
"loss": 3.7777,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.3294108282236926e-05,
"loss": 3.7452,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328573871353014e-05,
"loss": 3.7757,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.327735276601962e-05,
"loss": 3.7602,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.32689668185091e-05,
"loss": 3.7666,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326059724980231e-05,
"loss": 3.7769,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.325221130229179e-05,
"loss": 3.7641,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.324382535478127e-05,
"loss": 3.7637,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.323543940727075e-05,
"loss": 3.7706,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322706983856396e-05,
"loss": 3.7586,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.321868389105344e-05,
"loss": 3.7564,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.321029794354292e-05,
"loss": 3.7655,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.32019119960324e-05,
"loss": 3.764,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.319354242732561e-05,
"loss": 3.7574,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.3185156479815095e-05,
"loss": 3.7539,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.3176770532304575e-05,
"loss": 3.7508,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.3168384584794055e-05,
"loss": 3.7603,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.3160015016087264e-05,
"loss": 3.7728,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.3151629068576744e-05,
"loss": 3.7591,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.3143243121066224e-05,
"loss": 3.7768,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.3134857173555704e-05,
"loss": 3.7746,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.312648760484891e-05,
"loss": 3.7639,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311810165733839e-05,
"loss": 3.7588,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310971570982787e-05,
"loss": 3.7728,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310132976231735e-05,
"loss": 3.7615,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.309296019361056e-05,
"loss": 3.759,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308457424610005e-05,
"loss": 3.7705,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.307618829858953e-05,
"loss": 3.7661,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.306780235107901e-05,
"loss": 3.7685,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.305943278237222e-05,
"loss": 3.7653,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.30510468348617e-05,
"loss": 3.7489,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.304266088735118e-05,
"loss": 3.7463,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.303429131864439e-05,
"loss": 3.7604,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.302590537113387e-05,
"loss": 3.7635,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.301751942362335e-05,
"loss": 3.7581,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.300913347611283e-05,
"loss": 3.7561,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.3000763907406036e-05,
"loss": 3.7583,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.2992377959895516e-05,
"loss": 3.7502,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.2983992012385e-05,
"loss": 3.7611,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.297560606487448e-05,
"loss": 3.7571,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.296722011736396e-05,
"loss": 3.766,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.295883416985344e-05,
"loss": 3.7701,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.295044822234292e-05,
"loss": 3.7614,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.2942062274832396e-05,
"loss": 3.7528,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293369270612561e-05,
"loss": 3.7571,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.292530675861509e-05,
"loss": 3.756,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.2916920811104565e-05,
"loss": 3.7702,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.2908534863594045e-05,
"loss": 3.7541,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.290016529488726e-05,
"loss": 3.7506,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289177934737674e-05,
"loss": 3.7643,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288339339986622e-05,
"loss": 3.7588,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.28750074523557e-05,
"loss": 3.7536,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.2866637883648916e-05,
"loss": 3.7563,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.2858251936138396e-05,
"loss": 3.7567,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.284986598862787e-05,
"loss": 3.7484,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284148004111735e-05,
"loss": 3.7388,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.2833110472410565e-05,
"loss": 3.7587,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.282472452490004e-05,
"loss": 3.755,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281633857738952e-05,
"loss": 3.7524,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.2807952629879e-05,
"loss": 3.7515,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.2799583061172214e-05,
"loss": 3.7444,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.2791197113661694e-05,
"loss": 3.7674,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.2782811166151174e-05,
"loss": 3.7654,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.2774425218640654e-05,
"loss": 3.7617,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276605564993387e-05,
"loss": 3.7586,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.275766970242334e-05,
"loss": 3.7508,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.274928375491282e-05,
"loss": 3.7517,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.27408978074023e-05,
"loss": 3.7434,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273252823869551e-05,
"loss": 3.7488,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.272414229118499e-05,
"loss": 3.7537,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.271575634367447e-05,
"loss": 3.754,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.270737039616395e-05,
"loss": 3.7534,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.269900082745716e-05,
"loss": 3.7515,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.269061487994665e-05,
"loss": 3.7527,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.268222893243613e-05,
"loss": 3.7496,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.2673859363729344e-05,
"loss": 3.7504,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.266547341621882e-05,
"loss": 3.7539,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.26570874687083e-05,
"loss": 3.7619,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.264870152119778e-05,
"loss": 3.7608,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.2640331952490986e-05,
"loss": 3.7448,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.26319623837842e-05,
"loss": 3.7571,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.262357643627368e-05,
"loss": 3.7517,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.261519048876316e-05,
"loss": 3.7596,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.2606804541252635e-05,
"loss": 3.7521,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.2598418593742115e-05,
"loss": 3.7554,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.2590032646231595e-05,
"loss": 3.7503,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.258164669872108e-05,
"loss": 3.7558,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.257326075121056e-05,
"loss": 3.7417,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256489118250377e-05,
"loss": 3.7486,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255650523499325e-05,
"loss": 3.7507,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254811928748273e-05,
"loss": 3.7512,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253973333997221e-05,
"loss": 3.7551,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253136377126542e-05,
"loss": 3.7495,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.25229778237549e-05,
"loss": 3.759,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251459187624438e-05,
"loss": 3.743,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250620592873386e-05,
"loss": 3.7519,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 3.8688604831695557,
"eval_runtime": 304.8076,
"eval_samples_per_second": 1251.908,
"eval_steps_per_second": 39.123,
"step": 457920
},
{
"epoch": 0.0,
"learning_rate": 4.249783636002707e-05,
"loss": 3.741,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.248945041251655e-05,
"loss": 3.7303,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.2481064465006035e-05,
"loss": 3.7582,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.2472678517495515e-05,
"loss": 3.7501,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.2464292569984995e-05,
"loss": 3.7587,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.2455906622474475e-05,
"loss": 3.7419,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.2447520674963955e-05,
"loss": 3.7412,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.2439134727453435e-05,
"loss": 3.7391,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.2430765158746644e-05,
"loss": 3.7427,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.2422379211236124e-05,
"loss": 3.7432,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.241400964252933e-05,
"loss": 3.7521,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.240562369501881e-05,
"loss": 3.7551,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239723774750829e-05,
"loss": 3.7307,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238885179999777e-05,
"loss": 3.7343,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.238046585248725e-05,
"loss": 3.7449,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237207990497673e-05,
"loss": 3.7292,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.236369395746622e-05,
"loss": 3.7361,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.23553080099557e-05,
"loss": 3.7383,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.234693844124891e-05,
"loss": 3.7379,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.233855249373839e-05,
"loss": 3.7544,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.233016654622787e-05,
"loss": 3.7425,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.232178059871735e-05,
"loss": 3.7431,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.231341103001056e-05,
"loss": 3.7412,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.230502508250004e-05,
"loss": 3.7439,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.229663913498952e-05,
"loss": 3.7352,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.2288253187479e-05,
"loss": 3.7424,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.2279883618772206e-05,
"loss": 3.7343,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.2271497671261686e-05,
"loss": 3.7316,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.226311172375117e-05,
"loss": 3.7337,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.2254725776240646e-05,
"loss": 3.7343,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.224635620753386e-05,
"loss": 3.7368,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.223797026002334e-05,
"loss": 3.7406,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.222958431251282e-05,
"loss": 3.745,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.2221198365002295e-05,
"loss": 3.7448,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.221282879629551e-05,
"loss": 3.7326,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.220444284878499e-05,
"loss": 3.7408,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.219605690127447e-05,
"loss": 3.7371,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.2187670953763944e-05,
"loss": 3.7328,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.217930138505716e-05,
"loss": 3.7232,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.217091543754664e-05,
"loss": 3.73,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.216252949003612e-05,
"loss": 3.7324,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.21541435425256e-05,
"loss": 3.7384,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.2145773973818816e-05,
"loss": 3.73,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.2137388026308296e-05,
"loss": 3.7313,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.212900207879777e-05,
"loss": 3.7486,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.212061613128725e-05,
"loss": 3.7354,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.2112246562580465e-05,
"loss": 3.7397,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.2103860615069945e-05,
"loss": 3.7243,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.209547466755942e-05,
"loss": 3.7157,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.20870887200489e-05,
"loss": 3.7431,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.2078719151342114e-05,
"loss": 3.7317,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.2070333203831594e-05,
"loss": 3.7273,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.2061947256321074e-05,
"loss": 3.7264,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.2053561308810554e-05,
"loss": 3.7362,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.204519174010377e-05,
"loss": 3.709,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.203680579259324e-05,
"loss": 3.7308,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.202841984508272e-05,
"loss": 3.7243,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.20200338975722e-05,
"loss": 3.7204,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.201166432886542e-05,
"loss": 3.74,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.200327838135489e-05,
"loss": 3.7255,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.199489243384437e-05,
"loss": 3.7248,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.198650648633385e-05,
"loss": 3.7339,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.197813691762707e-05,
"loss": 3.72,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.196975097011655e-05,
"loss": 3.7201,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196136502260603e-05,
"loss": 3.7238,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195297907509551e-05,
"loss": 3.7225,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.1944609506388716e-05,
"loss": 3.7219,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.1936223558878196e-05,
"loss": 3.7166,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.1927837611367676e-05,
"loss": 3.7077,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.191946804266089e-05,
"loss": 3.7217,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.1911082095150365e-05,
"loss": 3.7333,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.1902696147639845e-05,
"loss": 3.7183,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.1894310200129325e-05,
"loss": 3.7405,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.188594063142254e-05,
"loss": 3.7329,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.187755468391202e-05,
"loss": 3.7315,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.18691687364015e-05,
"loss": 3.7154,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.186078278889098e-05,
"loss": 3.7352,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.185241322018419e-05,
"loss": 3.723,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.184402727267367e-05,
"loss": 3.7179,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.183564132516315e-05,
"loss": 3.7338,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.182725537765263e-05,
"loss": 3.7275,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.181888580894584e-05,
"loss": 3.7308,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.181049986143532e-05,
"loss": 3.7286,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.18021139139248e-05,
"loss": 3.7084,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.179372796641428e-05,
"loss": 3.7088,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.178535839770749e-05,
"loss": 3.7183,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.1776972450196975e-05,
"loss": 3.727,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.1768586502686455e-05,
"loss": 3.7215,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.1760200555175935e-05,
"loss": 3.7139,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.1751830986469144e-05,
"loss": 3.7239,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.1743445038958624e-05,
"loss": 3.7133,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.1735059091448104e-05,
"loss": 3.721,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.1726673143937584e-05,
"loss": 3.7166,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.1718287196427064e-05,
"loss": 3.7356,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.1709901248916544e-05,
"loss": 3.7337,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.1701515301406023e-05,
"loss": 3.7243,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.1693129353895503e-05,
"loss": 3.7157,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.168475978518871e-05,
"loss": 3.7228,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.167637383767819e-05,
"loss": 3.7143,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.166798789016767e-05,
"loss": 3.7344,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.165960194265716e-05,
"loss": 3.7153,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.165123237395037e-05,
"loss": 3.7174,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.164284642643985e-05,
"loss": 3.723,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.163446047892933e-05,
"loss": 3.726,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.162607453141881e-05,
"loss": 3.7117,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.161770496271202e-05,
"loss": 3.7215,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.16093190152015e-05,
"loss": 3.7155,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.1600949446494706e-05,
"loss": 3.7096,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.1592563498984186e-05,
"loss": 3.7026,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.1584177551473666e-05,
"loss": 3.7212,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.1575791603963146e-05,
"loss": 3.7189,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.1567405656452626e-05,
"loss": 3.7131,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.155901970894211e-05,
"loss": 3.7174,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.155063376143159e-05,
"loss": 3.7115,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.154224781392107e-05,
"loss": 3.7275,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.153387824521428e-05,
"loss": 3.7315,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.152549229770376e-05,
"loss": 3.7258,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.151710635019324e-05,
"loss": 3.7205,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.150872040268272e-05,
"loss": 3.7128,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.150035083397593e-05,
"loss": 3.7147,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.149196488646541e-05,
"loss": 3.7031,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.148357893895489e-05,
"loss": 3.7132,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.147519299144437e-05,
"loss": 3.7161,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.146682342273758e-05,
"loss": 3.7141,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.1458437475227067e-05,
"loss": 3.7182,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.1450051527716546e-05,
"loss": 3.7136,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.1441665580206026e-05,
"loss": 3.7199,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.1433296011499236e-05,
"loss": 3.7121,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.1424926442792445e-05,
"loss": 3.7159,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.1416540495281925e-05,
"loss": 3.7176,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.1408154547771405e-05,
"loss": 3.7196,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.1399768600260884e-05,
"loss": 3.7262,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.1391382652750364e-05,
"loss": 3.7091,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.1383013084043574e-05,
"loss": 3.7224,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.1374627136533054e-05,
"loss": 3.7149,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.1366241189022533e-05,
"loss": 3.7237,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.135785524151202e-05,
"loss": 3.7157,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.13494692940015e-05,
"loss": 3.7218,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.134108334649097e-05,
"loss": 3.7101,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.133269739898045e-05,
"loss": 3.7245,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.132431145146993e-05,
"loss": 3.7041,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.131594188276314e-05,
"loss": 3.7127,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.130755593525262e-05,
"loss": 3.7147,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.12991699877421e-05,
"loss": 3.7181,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.129078404023158e-05,
"loss": 3.7143,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.128241447152479e-05,
"loss": 3.7156,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.127402852401427e-05,
"loss": 3.7227,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.126564257650376e-05,
"loss": 3.7069,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.125725662899324e-05,
"loss": 3.7218,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 3.8580548763275146,
"eval_runtime": 303.4119,
"eval_samples_per_second": 1257.667,
"eval_steps_per_second": 39.303,
"step": 534240
},
{
"epoch": 1.0,
"learning_rate": 4.124888706028645e-05,
"loss": 3.7093,
"step": 534528
},
{
"epoch": 1.0,
"learning_rate": 4.124050111277593e-05,
"loss": 3.6978,
"step": 535040
},
{
"epoch": 1.0,
"learning_rate": 4.123211516526541e-05,
"loss": 3.7175,
"step": 535552
},
{
"epoch": 1.0,
"learning_rate": 4.122372921775489e-05,
"loss": 3.7156,
"step": 536064
},
{
"epoch": 1.0,
"learning_rate": 4.1215359649048096e-05,
"loss": 3.7202,
"step": 536576
},
{
"epoch": 1.0,
"learning_rate": 4.1206973701537576e-05,
"loss": 3.7088,
"step": 537088
},
{
"epoch": 1.0,
"learning_rate": 4.1198587754027056e-05,
"loss": 3.7078,
"step": 537600
},
{
"epoch": 1.0,
"learning_rate": 4.1190201806516536e-05,
"loss": 3.7059,
"step": 538112
},
{
"epoch": 1.0,
"learning_rate": 4.1181832237809745e-05,
"loss": 3.7089,
"step": 538624
},
{
"epoch": 1.0,
"learning_rate": 4.1173446290299225e-05,
"loss": 3.7067,
"step": 539136
},
{
"epoch": 1.0,
"learning_rate": 4.116507672159244e-05,
"loss": 3.7146,
"step": 539648
},
{
"epoch": 1.0,
"learning_rate": 4.115669077408192e-05,
"loss": 3.7174,
"step": 540160
},
{
"epoch": 1.0,
"learning_rate": 4.11483048265714e-05,
"loss": 3.7019,
"step": 540672
},
{
"epoch": 1.0,
"learning_rate": 4.113991887906088e-05,
"loss": 3.6976,
"step": 541184
},
{
"epoch": 1.0,
"learning_rate": 4.113153293155036e-05,
"loss": 3.709,
"step": 541696
},
{
"epoch": 1.0,
"learning_rate": 4.112314698403984e-05,
"loss": 3.6911,
"step": 542208
},
{
"epoch": 1.0,
"learning_rate": 4.111477741533305e-05,
"loss": 3.705,
"step": 542720
},
{
"epoch": 1.0,
"learning_rate": 4.110639146782253e-05,
"loss": 3.703,
"step": 543232
},
{
"epoch": 1.0,
"learning_rate": 4.109800552031201e-05,
"loss": 3.7061,
"step": 543744
},
{
"epoch": 1.0,
"learning_rate": 4.108961957280149e-05,
"loss": 3.715,
"step": 544256
},
{
"epoch": 1.0,
"learning_rate": 4.108123362529097e-05,
"loss": 3.7122,
"step": 544768
},
{
"epoch": 1.0,
"learning_rate": 4.107284767778045e-05,
"loss": 3.7077,
"step": 545280
},
{
"epoch": 1.0,
"learning_rate": 4.106446173026993e-05,
"loss": 3.7062,
"step": 545792
},
{
"epoch": 1.0,
"learning_rate": 4.105607578275941e-05,
"loss": 3.7056,
"step": 546304
},
{
"epoch": 1.0,
"learning_rate": 4.1047706214052625e-05,
"loss": 3.7007,
"step": 546816
},
{
"epoch": 1.0,
"learning_rate": 4.1039320266542105e-05,
"loss": 3.7106,
"step": 547328
},
{
"epoch": 1.0,
"learning_rate": 4.1030934319031585e-05,
"loss": 3.7027,
"step": 547840
},
{
"epoch": 1.0,
"learning_rate": 4.1022548371521065e-05,
"loss": 3.697,
"step": 548352
},
{
"epoch": 1.0,
"learning_rate": 4.1014178802814274e-05,
"loss": 3.6988,
"step": 548864
},
{
"epoch": 1.0,
"learning_rate": 4.1005792855303754e-05,
"loss": 3.7052,
"step": 549376
},
{
"epoch": 1.01,
"learning_rate": 4.0997406907793234e-05,
"loss": 3.7,
"step": 549888
},
{
"epoch": 1.01,
"learning_rate": 4.0989020960282714e-05,
"loss": 3.7092,
"step": 550400
},
{
"epoch": 1.01,
"learning_rate": 4.098065139157592e-05,
"loss": 3.7141,
"step": 550912
},
{
"epoch": 1.01,
"learning_rate": 4.09722654440654e-05,
"loss": 3.7073,
"step": 551424
},
{
"epoch": 1.01,
"learning_rate": 4.096387949655488e-05,
"loss": 3.6976,
"step": 551936
},
{
"epoch": 1.01,
"learning_rate": 4.09555099278481e-05,
"loss": 3.7049,
"step": 552448
},
{
"epoch": 1.01,
"learning_rate": 4.094712398033758e-05,
"loss": 3.7056,
"step": 552960
},
{
"epoch": 1.01,
"learning_rate": 4.093873803282706e-05,
"loss": 3.6976,
"step": 553472
},
{
"epoch": 1.01,
"learning_rate": 4.093035208531654e-05,
"loss": 3.6928,
"step": 553984
},
{
"epoch": 1.01,
"learning_rate": 4.092198251660975e-05,
"loss": 3.6932,
"step": 554496
},
{
"epoch": 1.01,
"learning_rate": 4.091359656909923e-05,
"loss": 3.7003,
"step": 555008
},
{
"epoch": 1.01,
"learning_rate": 4.090521062158871e-05,
"loss": 3.7043,
"step": 555520
},
{
"epoch": 1.01,
"learning_rate": 4.089682467407819e-05,
"loss": 3.695,
"step": 556032
},
{
"epoch": 1.01,
"learning_rate": 4.08884551053714e-05,
"loss": 3.6968,
"step": 556544
},
{
"epoch": 1.01,
"learning_rate": 4.088006915786088e-05,
"loss": 3.7143,
"step": 557056
},
{
"epoch": 1.01,
"learning_rate": 4.087168321035036e-05,
"loss": 3.7016,
"step": 557568
},
{
"epoch": 1.01,
"learning_rate": 4.086329726283984e-05,
"loss": 3.7077,
"step": 558080
},
{
"epoch": 1.01,
"learning_rate": 4.085492769413305e-05,
"loss": 3.6911,
"step": 558592
},
{
"epoch": 1.01,
"learning_rate": 4.084654174662253e-05,
"loss": 3.6801,
"step": 559104
},
{
"epoch": 1.01,
"learning_rate": 4.083815579911201e-05,
"loss": 3.7113,
"step": 559616
},
{
"epoch": 1.01,
"learning_rate": 4.082976985160149e-05,
"loss": 3.6973,
"step": 560128
},
{
"epoch": 1.01,
"learning_rate": 4.08214002828947e-05,
"loss": 3.6938,
"step": 560640
},
{
"epoch": 1.01,
"learning_rate": 4.081301433538418e-05,
"loss": 3.6999,
"step": 561152
},
{
"epoch": 1.01,
"learning_rate": 4.080462838787366e-05,
"loss": 3.6948,
"step": 561664
},
{
"epoch": 1.01,
"learning_rate": 4.079624244036314e-05,
"loss": 3.6847,
"step": 562176
},
{
"epoch": 1.01,
"learning_rate": 4.078787287165635e-05,
"loss": 3.6914,
"step": 562688
},
{
"epoch": 1.01,
"learning_rate": 4.077948692414583e-05,
"loss": 3.6918,
"step": 563200
},
{
"epoch": 1.01,
"learning_rate": 4.077110097663531e-05,
"loss": 3.6921,
"step": 563712
},
{
"epoch": 1.01,
"learning_rate": 4.076271502912479e-05,
"loss": 3.7028,
"step": 564224
},
{
"epoch": 1.01,
"learning_rate": 4.0754345460418006e-05,
"loss": 3.6941,
"step": 564736
},
{
"epoch": 1.01,
"learning_rate": 4.0745959512907486e-05,
"loss": 3.6914,
"step": 565248
},
{
"epoch": 1.01,
"learning_rate": 4.0737573565396966e-05,
"loss": 3.7019,
"step": 565760
},
{
"epoch": 1.01,
"learning_rate": 4.0729187617886446e-05,
"loss": 3.6845,
"step": 566272
},
{
"epoch": 1.01,
"learning_rate": 4.0720818049179655e-05,
"loss": 3.6885,
"step": 566784
},
{
"epoch": 1.01,
"learning_rate": 4.0712432101669135e-05,
"loss": 3.6894,
"step": 567296
},
{
"epoch": 1.01,
"learning_rate": 4.0704046154158615e-05,
"loss": 3.6927,
"step": 567808
},
{
"epoch": 1.01,
"learning_rate": 4.0695660206648095e-05,
"loss": 3.6865,
"step": 568320
},
{
"epoch": 1.01,
"learning_rate": 4.0687290637941304e-05,
"loss": 3.6892,
"step": 568832
},
{
"epoch": 1.01,
"learning_rate": 4.0678904690430784e-05,
"loss": 3.6731,
"step": 569344
},
{
"epoch": 1.01,
"learning_rate": 4.0670518742920264e-05,
"loss": 3.6881,
"step": 569856
},
{
"epoch": 1.01,
"learning_rate": 4.0662132795409744e-05,
"loss": 3.7023,
"step": 570368
},
{
"epoch": 1.01,
"learning_rate": 4.065376322670296e-05,
"loss": 3.6832,
"step": 570880
},
{
"epoch": 1.01,
"learning_rate": 4.064537727919244e-05,
"loss": 3.7074,
"step": 571392
},
{
"epoch": 1.01,
"learning_rate": 4.063699133168192e-05,
"loss": 3.699,
"step": 571904
},
{
"epoch": 1.01,
"learning_rate": 4.06286053841714e-05,
"loss": 3.7016,
"step": 572416
},
{
"epoch": 1.01,
"learning_rate": 4.062023581546461e-05,
"loss": 3.6848,
"step": 572928
},
{
"epoch": 1.01,
"learning_rate": 4.061184986795409e-05,
"loss": 3.7013,
"step": 573440
},
{
"epoch": 1.01,
"learning_rate": 4.060346392044357e-05,
"loss": 3.6923,
"step": 573952
},
{
"epoch": 1.01,
"learning_rate": 4.059507797293305e-05,
"loss": 3.6857,
"step": 574464
},
{
"epoch": 1.01,
"learning_rate": 4.058670840422626e-05,
"loss": 3.7029,
"step": 574976
},
{
"epoch": 1.01,
"learning_rate": 4.057832245671574e-05,
"loss": 3.6931,
"step": 575488
},
{
"epoch": 1.01,
"learning_rate": 4.056995288800895e-05,
"loss": 3.697,
"step": 576000
},
{
"epoch": 1.01,
"learning_rate": 4.056156694049843e-05,
"loss": 3.6976,
"step": 576512
},
{
"epoch": 1.01,
"learning_rate": 4.0553180992987914e-05,
"loss": 3.6723,
"step": 577024
},
{
"epoch": 1.01,
"learning_rate": 4.0544795045477394e-05,
"loss": 3.6831,
"step": 577536
},
{
"epoch": 1.01,
"learning_rate": 4.05364254767706e-05,
"loss": 3.6809,
"step": 578048
},
{
"epoch": 1.01,
"learning_rate": 4.052803952926008e-05,
"loss": 3.6965,
"step": 578560
},
{
"epoch": 1.01,
"learning_rate": 4.051965358174956e-05,
"loss": 3.6914,
"step": 579072
},
{
"epoch": 1.01,
"learning_rate": 4.051126763423904e-05,
"loss": 3.6821,
"step": 579584
},
{
"epoch": 1.02,
"learning_rate": 4.050289806553225e-05,
"loss": 3.6891,
"step": 580096
},
{
"epoch": 1.02,
"learning_rate": 4.049451211802173e-05,
"loss": 3.6843,
"step": 580608
},
{
"epoch": 1.02,
"learning_rate": 4.048612617051121e-05,
"loss": 3.6869,
"step": 581120
},
{
"epoch": 1.02,
"learning_rate": 4.047774022300069e-05,
"loss": 3.6846,
"step": 581632
},
{
"epoch": 1.02,
"learning_rate": 4.0469354275490165e-05,
"loss": 3.6995,
"step": 582144
},
{
"epoch": 1.02,
"learning_rate": 4.046096832797965e-05,
"loss": 3.7088,
"step": 582656
},
{
"epoch": 1.02,
"learning_rate": 4.045258238046913e-05,
"loss": 3.6871,
"step": 583168
},
{
"epoch": 1.02,
"learning_rate": 4.044419643295861e-05,
"loss": 3.6842,
"step": 583680
},
{
"epoch": 1.02,
"learning_rate": 4.043582686425182e-05,
"loss": 3.6907,
"step": 584192
},
{
"epoch": 1.02,
"learning_rate": 4.04274409167413e-05,
"loss": 3.683,
"step": 584704
},
{
"epoch": 1.02,
"learning_rate": 4.041905496923078e-05,
"loss": 3.6997,
"step": 585216
},
{
"epoch": 1.02,
"learning_rate": 4.041066902172026e-05,
"loss": 3.6857,
"step": 585728
},
{
"epoch": 1.02,
"learning_rate": 4.040229945301347e-05,
"loss": 3.6883,
"step": 586240
},
{
"epoch": 1.02,
"learning_rate": 4.039391350550295e-05,
"loss": 3.691,
"step": 586752
},
{
"epoch": 1.02,
"learning_rate": 4.038552755799243e-05,
"loss": 3.6934,
"step": 587264
},
{
"epoch": 1.02,
"learning_rate": 4.037714161048191e-05,
"loss": 3.6796,
"step": 587776
},
{
"epoch": 1.02,
"learning_rate": 4.036877204177512e-05,
"loss": 3.687,
"step": 588288
},
{
"epoch": 1.02,
"learning_rate": 4.0360386094264605e-05,
"loss": 3.6862,
"step": 588800
},
{
"epoch": 1.02,
"learning_rate": 4.0352016525557814e-05,
"loss": 3.6777,
"step": 589312
},
{
"epoch": 1.02,
"learning_rate": 4.0343630578047294e-05,
"loss": 3.6746,
"step": 589824
},
{
"epoch": 1.02,
"learning_rate": 4.0335244630536774e-05,
"loss": 3.689,
"step": 590336
},
{
"epoch": 1.02,
"learning_rate": 4.0326858683026254e-05,
"loss": 3.6872,
"step": 590848
},
{
"epoch": 1.02,
"learning_rate": 4.0318472735515734e-05,
"loss": 3.6817,
"step": 591360
},
{
"epoch": 1.02,
"learning_rate": 4.0310086788005214e-05,
"loss": 3.6883,
"step": 591872
},
{
"epoch": 1.02,
"learning_rate": 4.0301700840494694e-05,
"loss": 3.6802,
"step": 592384
},
{
"epoch": 1.02,
"learning_rate": 4.0293314892984174e-05,
"loss": 3.698,
"step": 592896
},
{
"epoch": 1.02,
"learning_rate": 4.028494532427738e-05,
"loss": 3.7002,
"step": 593408
},
{
"epoch": 1.02,
"learning_rate": 4.027655937676686e-05,
"loss": 3.6961,
"step": 593920
},
{
"epoch": 1.02,
"learning_rate": 4.026817342925634e-05,
"loss": 3.6891,
"step": 594432
},
{
"epoch": 1.02,
"learning_rate": 4.025978748174582e-05,
"loss": 3.6786,
"step": 594944
},
{
"epoch": 1.02,
"learning_rate": 4.025141791303904e-05,
"loss": 3.6895,
"step": 595456
},
{
"epoch": 1.02,
"learning_rate": 4.024303196552852e-05,
"loss": 3.6738,
"step": 595968
},
{
"epoch": 1.02,
"learning_rate": 4.023466239682173e-05,
"loss": 3.683,
"step": 596480
},
{
"epoch": 1.02,
"learning_rate": 4.022627644931121e-05,
"loss": 3.681,
"step": 596992
},
{
"epoch": 1.02,
"learning_rate": 4.021789050180069e-05,
"loss": 3.6842,
"step": 597504
},
{
"epoch": 1.02,
"learning_rate": 4.020950455429017e-05,
"loss": 3.685,
"step": 598016
},
{
"epoch": 1.02,
"learning_rate": 4.020111860677965e-05,
"loss": 3.6857,
"step": 598528
},
{
"epoch": 1.02,
"learning_rate": 4.019273265926913e-05,
"loss": 3.6912,
"step": 599040
},
{
"epoch": 1.02,
"learning_rate": 4.018436309056234e-05,
"loss": 3.6821,
"step": 599552
},
{
"epoch": 1.02,
"learning_rate": 4.0175977143051817e-05,
"loss": 3.6846,
"step": 600064
},
{
"epoch": 1.02,
"learning_rate": 4.0167591195541297e-05,
"loss": 3.6888,
"step": 600576
},
{
"epoch": 1.02,
"learning_rate": 4.0159205248030776e-05,
"loss": 3.6868,
"step": 601088
},
{
"epoch": 1.02,
"learning_rate": 4.0150819300520256e-05,
"loss": 3.6959,
"step": 601600
},
{
"epoch": 1.02,
"learning_rate": 4.0142433353009736e-05,
"loss": 3.6808,
"step": 602112
},
{
"epoch": 1.02,
"learning_rate": 4.013406378430295e-05,
"loss": 3.6938,
"step": 602624
},
{
"epoch": 1.02,
"learning_rate": 4.012567783679243e-05,
"loss": 3.6841,
"step": 603136
},
{
"epoch": 1.02,
"learning_rate": 4.011729188928191e-05,
"loss": 3.6911,
"step": 603648
},
{
"epoch": 1.02,
"learning_rate": 4.010890594177139e-05,
"loss": 3.6847,
"step": 604160
},
{
"epoch": 1.02,
"learning_rate": 4.010051999426087e-05,
"loss": 3.6897,
"step": 604672
},
{
"epoch": 1.02,
"learning_rate": 4.009213404675035e-05,
"loss": 3.6813,
"step": 605184
},
{
"epoch": 1.02,
"learning_rate": 4.0083748099239825e-05,
"loss": 3.696,
"step": 605696
},
{
"epoch": 1.02,
"learning_rate": 4.0075362151729305e-05,
"loss": 3.6727,
"step": 606208
},
{
"epoch": 1.02,
"learning_rate": 4.006699258302252e-05,
"loss": 3.6826,
"step": 606720
},
{
"epoch": 1.02,
"learning_rate": 4.0058606635512e-05,
"loss": 3.689,
"step": 607232
},
{
"epoch": 1.02,
"learning_rate": 4.0050220688001474e-05,
"loss": 3.6866,
"step": 607744
},
{
"epoch": 1.02,
"learning_rate": 4.004183474049096e-05,
"loss": 3.6808,
"step": 608256
},
{
"epoch": 1.02,
"learning_rate": 4.003346517178418e-05,
"loss": 3.682,
"step": 608768
},
{
"epoch": 1.02,
"learning_rate": 4.002507922427366e-05,
"loss": 3.695,
"step": 609280
},
{
"epoch": 1.02,
"learning_rate": 4.001669327676313e-05,
"loss": 3.6755,
"step": 609792
},
{
"epoch": 1.02,
"learning_rate": 4.000830732925261e-05,
"loss": 3.6904,
"step": 610304
},
{
"epoch": 1.03,
"eval_loss": 3.851750612258911,
"eval_runtime": 303.4347,
"eval_samples_per_second": 1257.572,
"eval_steps_per_second": 39.3,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.9999937760545826e-05,
"loss": 3.67,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.99915518130353e-05,
"loss": 3.6732,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.998316586552478e-05,
"loss": 3.6825,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.997477991801426e-05,
"loss": 3.6857,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.996639397050374e-05,
"loss": 3.6928,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.995800802299322e-05,
"loss": 3.6774,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.99496220754827e-05,
"loss": 3.6818,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.994123612797218e-05,
"loss": 3.6782,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.993288293806913e-05,
"loss": 3.6752,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.9924496990558604e-05,
"loss": 3.6761,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.9916111043048084e-05,
"loss": 3.6849,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.9907725095537564e-05,
"loss": 3.6876,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.989935552683077e-05,
"loss": 3.6714,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.989096957932025e-05,
"loss": 3.6672,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.988258363180973e-05,
"loss": 3.6806,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.987419768429921e-05,
"loss": 3.6619,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.986582811559242e-05,
"loss": 3.6756,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.98574421680819e-05,
"loss": 3.6722,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.984905622057138e-05,
"loss": 3.6784,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.984067027306087e-05,
"loss": 3.6814,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.983228432555035e-05,
"loss": 3.6838,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.982389837803983e-05,
"loss": 3.6806,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.981552880933304e-05,
"loss": 3.6753,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.980714286182252e-05,
"loss": 3.673,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.9798756914312e-05,
"loss": 3.6741,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.979037096680148e-05,
"loss": 3.6822,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.978198501929096e-05,
"loss": 3.6727,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.977359907178044e-05,
"loss": 3.6682,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.976521312426992e-05,
"loss": 3.673,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.9756843555563126e-05,
"loss": 3.6713,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.9748457608052606e-05,
"loss": 3.668,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.9740071660542086e-05,
"loss": 3.6833,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.9731685713031566e-05,
"loss": 3.6803,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.972331614432478e-05,
"loss": 3.6762,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971494657561799e-05,
"loss": 3.6697,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.970656062810747e-05,
"loss": 3.6799,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.969817468059695e-05,
"loss": 3.6759,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.968978873308643e-05,
"loss": 3.6736,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.968140278557591e-05,
"loss": 3.661,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.967303321686912e-05,
"loss": 3.6642,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.96646472693586e-05,
"loss": 3.6662,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.965626132184808e-05,
"loss": 3.6764,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.964787537433756e-05,
"loss": 3.6685,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.9639505805630776e-05,
"loss": 3.6676,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.9631119858120256e-05,
"loss": 3.6838,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.9622733910609735e-05,
"loss": 3.6734,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.9614347963099215e-05,
"loss": 3.6814,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.9605962015588695e-05,
"loss": 3.6645,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.9597576068078175e-05,
"loss": 3.6484,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.9589190120567655e-05,
"loss": 3.6828,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.9580804173057135e-05,
"loss": 3.6715,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.9572450983154074e-05,
"loss": 3.6681,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.9564065035643553e-05,
"loss": 3.6684,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.9555679088133033e-05,
"loss": 3.6689,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.954729314062251e-05,
"loss": 3.6532,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.953892357191572e-05,
"loss": 3.6598,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.953053762440521e-05,
"loss": 3.664,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.952215167689469e-05,
"loss": 3.6634,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.951376572938417e-05,
"loss": 3.678,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.950539616067738e-05,
"loss": 3.6639,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.949701021316686e-05,
"loss": 3.6613,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.948862426565634e-05,
"loss": 3.6791,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.948023831814582e-05,
"loss": 3.6527,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.94718523706353e-05,
"loss": 3.6566,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.946346642312478e-05,
"loss": 3.6616,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.945508047561426e-05,
"loss": 3.6655,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.944669452810373e-05,
"loss": 3.657,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.943832495939695e-05,
"loss": 3.663,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.942993901188643e-05,
"loss": 3.6465,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.942156944317964e-05,
"loss": 3.6586,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.941318349566912e-05,
"loss": 3.6727,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.94047975481586e-05,
"loss": 3.6569,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.939641160064808e-05,
"loss": 3.6786,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.9388025653137556e-05,
"loss": 3.6703,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.9379639705627036e-05,
"loss": 3.676,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.9371253758116516e-05,
"loss": 3.6554,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.9362867810605996e-05,
"loss": 3.6726,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.935451462070294e-05,
"loss": 3.6668,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.934612867319242e-05,
"loss": 3.6553,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.93377427256819e-05,
"loss": 3.6763,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.932935677817138e-05,
"loss": 3.6665,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.932097083066086e-05,
"loss": 3.6667,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.931258488315034e-05,
"loss": 3.6689,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.930419893563982e-05,
"loss": 3.6474,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.92958129881293e-05,
"loss": 3.6526,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.928744341942251e-05,
"loss": 3.6572,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.927905747191199e-05,
"loss": 3.6662,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.927067152440147e-05,
"loss": 3.6632,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.926228557689095e-05,
"loss": 3.6537,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.925391600818416e-05,
"loss": 3.661,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.924553006067364e-05,
"loss": 3.6593,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.923714411316312e-05,
"loss": 3.659,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.92287581656526e-05,
"loss": 3.6564,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.9220372218142085e-05,
"loss": 3.6759,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.9211986270631565e-05,
"loss": 3.6762,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.9203600323121045e-05,
"loss": 3.6655,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.9195214375610525e-05,
"loss": 3.6529,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.9186844806903734e-05,
"loss": 3.6645,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.9178458859393214e-05,
"loss": 3.6551,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.9170072911882694e-05,
"loss": 3.6725,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.9161686964372174e-05,
"loss": 3.6602,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.9153301016861654e-05,
"loss": 3.6584,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.9144915069351134e-05,
"loss": 3.6641,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.9136529121840614e-05,
"loss": 3.6692,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.912814317433009e-05,
"loss": 3.6519,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.91197736056233e-05,
"loss": 3.6624,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.911138765811278e-05,
"loss": 3.6558,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.9103018089406e-05,
"loss": 3.654,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.909463214189548e-05,
"loss": 3.6464,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.908624619438496e-05,
"loss": 3.6601,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.907786024687444e-05,
"loss": 3.6551,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.906947429936392e-05,
"loss": 3.6606,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.906108835185339e-05,
"loss": 3.6591,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.905270240434287e-05,
"loss": 3.6517,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.904431645683235e-05,
"loss": 3.6668,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.903594688812556e-05,
"loss": 3.6741,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.9027577319418777e-05,
"loss": 3.6633,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.9019191371908257e-05,
"loss": 3.6677,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.9010805424397736e-05,
"loss": 3.6465,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.9002419476887216e-05,
"loss": 3.6648,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.899404990818043e-05,
"loss": 3.6513,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.898566396066991e-05,
"loss": 3.6553,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.897727801315939e-05,
"loss": 3.6522,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.8968892065648865e-05,
"loss": 3.6552,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.8960506118138345e-05,
"loss": 3.6587,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.895213654943156e-05,
"loss": 3.6577,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.8943750601921034e-05,
"loss": 3.6648,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.8935364654410514e-05,
"loss": 3.6573,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.8926978706899994e-05,
"loss": 3.6525,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.8918592759389474e-05,
"loss": 3.6632,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.8910206811878954e-05,
"loss": 3.6621,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.890183724317217e-05,
"loss": 3.6703,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.889345129566165e-05,
"loss": 3.6505,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.888506534815113e-05,
"loss": 3.6677,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.887667940064061e-05,
"loss": 3.6571,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.886829345313009e-05,
"loss": 3.662,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.88599238844233e-05,
"loss": 3.6621,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.885153793691278e-05,
"loss": 3.6614,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884315198940226e-05,
"loss": 3.6535,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.883476604189174e-05,
"loss": 3.6692,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.882638009438122e-05,
"loss": 3.6481,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.881801052567443e-05,
"loss": 3.6555,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.880962457816391e-05,
"loss": 3.662,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.8801238630653395e-05,
"loss": 3.665,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.8792852683142875e-05,
"loss": 3.6527,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.8784466735632355e-05,
"loss": 3.6561,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.8776097166925564e-05,
"loss": 3.6651,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.8767711219415044e-05,
"loss": 3.656,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.8759325271904524e-05,
"loss": 3.6603,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 3.8467893600463867,
"eval_runtime": 312.7865,
"eval_samples_per_second": 1219.973,
"eval_steps_per_second": 38.125,
"step": 686880
},
{
"epoch": 1.0,
"learning_rate": 3.8750939324394004e-05,
"loss": 3.6457,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.8742553376883483e-05,
"loss": 3.649,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.873418380817669e-05,
"loss": 3.6568,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.872579786066617e-05,
"loss": 3.6611,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.871741191315565e-05,
"loss": 3.6668,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.870902596564513e-05,
"loss": 3.6494,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.870065639693835e-05,
"loss": 3.6549,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.869227044942783e-05,
"loss": 3.653,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.868388450191731e-05,
"loss": 3.6457,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.867549855440679e-05,
"loss": 3.6534,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.86671289857e-05,
"loss": 3.6569,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.865874303818948e-05,
"loss": 3.6594,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.865035709067896e-05,
"loss": 3.6558,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.864197114316844e-05,
"loss": 3.6348,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.863358519565792e-05,
"loss": 3.6549,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.86251992481474e-05,
"loss": 3.6366,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.8616829679440606e-05,
"loss": 3.6457,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.8608443731930086e-05,
"loss": 3.6494,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.8600057784419566e-05,
"loss": 3.6477,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.8591671836909046e-05,
"loss": 3.6552,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.8583285889398526e-05,
"loss": 3.6598,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.8574899941888006e-05,
"loss": 3.6558,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.856653037318122e-05,
"loss": 3.6528,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.8558144425670695e-05,
"loss": 3.6429,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.8549758478160175e-05,
"loss": 3.6496,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.8541372530649655e-05,
"loss": 3.6535,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.853300296194287e-05,
"loss": 3.6502,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.8524617014432344e-05,
"loss": 3.6448,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.8516231066921824e-05,
"loss": 3.6428,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.8507845119411304e-05,
"loss": 3.6479,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.8499459171900784e-05,
"loss": 3.6395,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.8491089603194e-05,
"loss": 3.6586,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.848270365568348e-05,
"loss": 3.6543,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.847431770817296e-05,
"loss": 3.6514,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.846593176066244e-05,
"loss": 3.6445,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.845756219195565e-05,
"loss": 3.6501,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.844917624444513e-05,
"loss": 3.6497,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.844079029693461e-05,
"loss": 3.645,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.843240434942409e-05,
"loss": 3.6382,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.842401840191357e-05,
"loss": 3.6383,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.841564883320678e-05,
"loss": 3.6405,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.840726288569626e-05,
"loss": 3.6524,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.839887693818574e-05,
"loss": 3.6417,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.8390490990675224e-05,
"loss": 3.6433,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.838212142196843e-05,
"loss": 3.6559,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.837373547445791e-05,
"loss": 3.6473,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.836534952694739e-05,
"loss": 3.6539,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.835696357943687e-05,
"loss": 3.6415,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.834859401073008e-05,
"loss": 3.6241,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.834020806321956e-05,
"loss": 3.6562,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.833182211570904e-05,
"loss": 3.6437,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.832343616819852e-05,
"loss": 3.6479,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.8315050220688e-05,
"loss": 3.643,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.830666427317748e-05,
"loss": 3.6423,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.829827832566696e-05,
"loss": 3.6273,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.828990875696017e-05,
"loss": 3.6387,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.828152280944966e-05,
"loss": 3.639,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.827313686193914e-05,
"loss": 3.6356,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.826475091442862e-05,
"loss": 3.6549,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.825638134572183e-05,
"loss": 3.6371,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.824799539821131e-05,
"loss": 3.6345,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.823960945070079e-05,
"loss": 3.6542,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.823122350319027e-05,
"loss": 3.6295,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.822283755567975e-05,
"loss": 3.6276,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.8214467986972956e-05,
"loss": 3.6399,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.8206082039462436e-05,
"loss": 3.6405,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.8197696091951916e-05,
"loss": 3.631,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.8189310144441396e-05,
"loss": 3.6405,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.8180924196930876e-05,
"loss": 3.6232,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.817255462822409e-05,
"loss": 3.632,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.816416868071357e-05,
"loss": 3.6462,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.815578273320305e-05,
"loss": 3.6341,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.814739678569253e-05,
"loss": 3.6503,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.8139010838182004e-05,
"loss": 3.6454,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.813064126947522e-05,
"loss": 3.6581,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.81222553219647e-05,
"loss": 3.6299,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.811386937445418e-05,
"loss": 3.6461,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.8105483426943653e-05,
"loss": 3.643,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.809711385823687e-05,
"loss": 3.6264,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.808872791072635e-05,
"loss": 3.6551,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.808034196321583e-05,
"loss": 3.6408,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.807195601570531e-05,
"loss": 3.6423,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.806357006819479e-05,
"loss": 3.6471,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.8055200499488005e-05,
"loss": 3.6281,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.804681455197748e-05,
"loss": 3.623,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.803842860446696e-05,
"loss": 3.6327,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.803004265695644e-05,
"loss": 3.6415,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.802165670944592e-05,
"loss": 3.6383,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.801328714073913e-05,
"loss": 3.6295,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.800490119322861e-05,
"loss": 3.6319,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.799651524571809e-05,
"loss": 3.6407,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.798812929820757e-05,
"loss": 3.6344,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.797974335069705e-05,
"loss": 3.6296,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.797137378199026e-05,
"loss": 3.6523,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.796298783447974e-05,
"loss": 3.6508,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.795460188696922e-05,
"loss": 3.6427,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.79462159394587e-05,
"loss": 3.6266,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.793782999194818e-05,
"loss": 3.6412,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.792944404443766e-05,
"loss": 3.6308,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.792105809692714e-05,
"loss": 3.6453,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.791268852822035e-05,
"loss": 3.636,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.790430258070983e-05,
"loss": 3.6329,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.789591663319931e-05,
"loss": 3.6387,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.788753068568879e-05,
"loss": 3.6447,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.7879161116982e-05,
"loss": 3.6262,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.787077516947149e-05,
"loss": 3.6404,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.786238922196097e-05,
"loss": 3.6281,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.785400327445045e-05,
"loss": 3.6332,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.7845633705743656e-05,
"loss": 3.6239,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.7837247758233136e-05,
"loss": 3.6289,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.7828861810722616e-05,
"loss": 3.6333,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.7820475863212096e-05,
"loss": 3.6377,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.7812089915701576e-05,
"loss": 3.6349,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.7803703968191056e-05,
"loss": 3.6288,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.7795318020680536e-05,
"loss": 3.6434,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.7786948451973745e-05,
"loss": 3.6491,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.7778562504463225e-05,
"loss": 3.6375,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.7770176556952705e-05,
"loss": 3.6453,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.7761790609442185e-05,
"loss": 3.6257,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.7753404661931665e-05,
"loss": 3.6361,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.774503509322488e-05,
"loss": 3.6298,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.773664914571436e-05,
"loss": 3.6256,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.772826319820384e-05,
"loss": 3.6296,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.7719877250693314e-05,
"loss": 3.6335,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.7711491303182794e-05,
"loss": 3.6337,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.770312173447601e-05,
"loss": 3.6338,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.769473578696549e-05,
"loss": 3.6393,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.768634983945496e-05,
"loss": 3.6377,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.767796389194444e-05,
"loss": 3.6279,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.766957794443392e-05,
"loss": 3.6398,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.766120837572714e-05,
"loss": 3.64,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.765282242821662e-05,
"loss": 3.6427,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.76444364807061e-05,
"loss": 3.6297,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.763605053319558e-05,
"loss": 3.6467,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.762768096448879e-05,
"loss": 3.6326,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.761929501697827e-05,
"loss": 3.6392,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.761090906946775e-05,
"loss": 3.6371,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.760252312195723e-05,
"loss": 3.6327,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.759413717444671e-05,
"loss": 3.63,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.758576760573992e-05,
"loss": 3.6493,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.7577381658229397e-05,
"loss": 3.619,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.7568995710718877e-05,
"loss": 3.6361,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.7560609763208356e-05,
"loss": 3.6399,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.755222381569784e-05,
"loss": 3.6342,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.754383786818732e-05,
"loss": 3.6311,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.75354519206768e-05,
"loss": 3.6323,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.752708235197001e-05,
"loss": 3.6381,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.751869640445949e-05,
"loss": 3.6369,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.751031045694897e-05,
"loss": 3.6377,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 3.844654083251953,
"eval_runtime": 303.5199,
"eval_samples_per_second": 1257.219,
"eval_steps_per_second": 39.289,
"step": 763200
},
{
"epoch": 0.0,
"learning_rate": 3.750192450943845e-05,
"loss": 3.6116,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.749353856192793e-05,
"loss": 3.6245,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.748515261441741e-05,
"loss": 3.6313,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.747676666690689e-05,
"loss": 3.636,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.74683970982001e-05,
"loss": 3.6441,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.746001115068958e-05,
"loss": 3.626,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.745162520317906e-05,
"loss": 3.6336,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.744323925566854e-05,
"loss": 3.6292,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.743486968696176e-05,
"loss": 3.6239,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.742648373945124e-05,
"loss": 3.6289,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.741809779194072e-05,
"loss": 3.6336,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.74097118444302e-05,
"loss": 3.6383,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.7401342275723406e-05,
"loss": 3.6351,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.7392956328212886e-05,
"loss": 3.6089,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.7384570380702366e-05,
"loss": 3.6332,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.7376184433191846e-05,
"loss": 3.6118,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.7367814864485055e-05,
"loss": 3.6241,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.7359428916974535e-05,
"loss": 3.6257,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.7351042969464015e-05,
"loss": 3.6237,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.7342657021953495e-05,
"loss": 3.6318,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.7334271074442975e-05,
"loss": 3.6387,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.7325885126932455e-05,
"loss": 3.632,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.731751555822567e-05,
"loss": 3.6285,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.730912961071515e-05,
"loss": 3.6186,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.7300743663204624e-05,
"loss": 3.632,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.7292357715694103e-05,
"loss": 3.6305,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.7283971768183583e-05,
"loss": 3.6267,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.727560219947679e-05,
"loss": 3.6238,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.726721625196627e-05,
"loss": 3.6193,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.725883030445575e-05,
"loss": 3.6243,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.725044435694523e-05,
"loss": 3.6116,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.724207478823845e-05,
"loss": 3.6349,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.723368884072793e-05,
"loss": 3.6351,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.722530289321741e-05,
"loss": 3.6275,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.721691694570689e-05,
"loss": 3.6229,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.72085473770001e-05,
"loss": 3.623,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.720016142948958e-05,
"loss": 3.6309,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.719177548197906e-05,
"loss": 3.6246,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.718338953446854e-05,
"loss": 3.6125,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.717500358695802e-05,
"loss": 3.6199,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.7166634018251226e-05,
"loss": 3.6185,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.7158248070740706e-05,
"loss": 3.6253,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.7149862123230186e-05,
"loss": 3.6223,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.714147617571967e-05,
"loss": 3.6227,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.713310660701288e-05,
"loss": 3.6296,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.712472065950236e-05,
"loss": 3.6268,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.711633471199184e-05,
"loss": 3.63,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.710794876448132e-05,
"loss": 3.6244,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.709957919577453e-05,
"loss": 3.5989,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.709119324826401e-05,
"loss": 3.6311,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.708280730075349e-05,
"loss": 3.62,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.707442135324297e-05,
"loss": 3.6234,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.706603540573245e-05,
"loss": 3.6244,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.705766583702566e-05,
"loss": 3.6213,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.704927988951514e-05,
"loss": 3.6045,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.704089394200462e-05,
"loss": 3.6127,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.7032507994494106e-05,
"loss": 3.618,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.7024122046983586e-05,
"loss": 3.614,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.7015752478276795e-05,
"loss": 3.6287,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.7007366530766275e-05,
"loss": 3.6183,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.6998980583255755e-05,
"loss": 3.6129,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.6990594635745235e-05,
"loss": 3.6306,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.6982225067038444e-05,
"loss": 3.6093,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.6973839119527924e-05,
"loss": 3.6051,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.6965453172017404e-05,
"loss": 3.6205,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.6957067224506884e-05,
"loss": 3.6154,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.6948697655800093e-05,
"loss": 3.6072,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.694031170828957e-05,
"loss": 3.6152,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.693192576077906e-05,
"loss": 3.6047,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.692353981326854e-05,
"loss": 3.61,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.691515386575802e-05,
"loss": 3.6251,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.690678429705123e-05,
"loss": 3.6141,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.689839834954071e-05,
"loss": 3.6272,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.689001240203019e-05,
"loss": 3.6192,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.688162645451967e-05,
"loss": 3.6349,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.687325688581288e-05,
"loss": 3.6084,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.686487093830236e-05,
"loss": 3.623,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.685648499079184e-05,
"loss": 3.622,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.684809904328132e-05,
"loss": 3.6046,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.683972947457453e-05,
"loss": 3.6297,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.6831343527064014e-05,
"loss": 3.6195,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.6822957579553494e-05,
"loss": 3.6198,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.6814571632042974e-05,
"loss": 3.6244,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.680620206333618e-05,
"loss": 3.6065,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.679781611582566e-05,
"loss": 3.6007,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.678943016831514e-05,
"loss": 3.6084,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.678104422080462e-05,
"loss": 3.6231,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.677267465209783e-05,
"loss": 3.6128,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.676428870458731e-05,
"loss": 3.6097,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.675590275707679e-05,
"loss": 3.6102,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.674751680956627e-05,
"loss": 3.6182,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.673913086205575e-05,
"loss": 3.6117,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.673074491454523e-05,
"loss": 3.6098,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.672237534583845e-05,
"loss": 3.6237,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.671398939832793e-05,
"loss": 3.6297,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.67056034508174e-05,
"loss": 3.6203,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.669721750330688e-05,
"loss": 3.6076,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.668883155579636e-05,
"loss": 3.6156,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.6680461987089576e-05,
"loss": 3.6087,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.667207603957905e-05,
"loss": 3.6226,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.666369009206853e-05,
"loss": 3.6146,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.665530414455801e-05,
"loss": 3.616,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.6646934575851225e-05,
"loss": 3.6127,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.6638548628340705e-05,
"loss": 3.6181,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.6630162680830185e-05,
"loss": 3.6143,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.6621776733319665e-05,
"loss": 3.6151,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.6613407164612874e-05,
"loss": 3.6077,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.6605021217102354e-05,
"loss": 3.611,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.6596635269591834e-05,
"loss": 3.6052,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.6588249322081314e-05,
"loss": 3.6073,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.6579863374570794e-05,
"loss": 3.6113,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.6571477427060274e-05,
"loss": 3.6128,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.656310785835348e-05,
"loss": 3.6148,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.655472191084296e-05,
"loss": 3.6046,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.654633596333244e-05,
"loss": 3.6229,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.653795001582192e-05,
"loss": 3.6273,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.652958044711514e-05,
"loss": 3.6142,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.652119449960462e-05,
"loss": 3.6223,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.65128085520941e-05,
"loss": 3.6112,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.650442260458358e-05,
"loss": 3.6123,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.649605303587679e-05,
"loss": 3.61,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.648766708836627e-05,
"loss": 3.6027,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.647928114085575e-05,
"loss": 3.6094,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.647089519334523e-05,
"loss": 3.6137,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.646250924583471e-05,
"loss": 3.6191,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.645413967712792e-05,
"loss": 3.6113,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.64457537296174e-05,
"loss": 3.6171,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.643736778210688e-05,
"loss": 3.6101,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.6428981834596357e-05,
"loss": 3.6102,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.642061226588957e-05,
"loss": 3.6136,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.641222631837905e-05,
"loss": 3.6203,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.640384037086853e-05,
"loss": 3.6205,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.639545442335801e-05,
"loss": 3.6059,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.638708485465122e-05,
"loss": 3.6279,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.63786989071407e-05,
"loss": 3.6101,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.637031295963018e-05,
"loss": 3.618,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.636192701211966e-05,
"loss": 3.6166,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.635355744341287e-05,
"loss": 3.6068,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.634517149590235e-05,
"loss": 3.6063,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.633678554839183e-05,
"loss": 3.6293,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.632839960088131e-05,
"loss": 3.6002,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.6320030032174526e-05,
"loss": 3.613,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.6311644084664006e-05,
"loss": 3.6162,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.6303258137153486e-05,
"loss": 3.6162,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.6294872189642966e-05,
"loss": 3.6075,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.6286486242132446e-05,
"loss": 3.6105,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.6278116673425655e-05,
"loss": 3.616,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.6269730725915135e-05,
"loss": 3.6207,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.6261344778404615e-05,
"loss": 3.6135,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 3.843158721923828,
"eval_runtime": 302.443,
"eval_samples_per_second": 1261.696,
"eval_steps_per_second": 39.429,
"step": 839520
},
{
"epoch": 1.0,
"learning_rate": 3.6252958830894095e-05,
"loss": 3.5989,
"step": 839680
},
{
"epoch": 1.0,
"learning_rate": 3.6244589262187304e-05,
"loss": 3.603,
"step": 840192
},
{
"epoch": 1.0,
"learning_rate": 3.6236203314676784e-05,
"loss": 3.6111,
"step": 840704
},
{
"epoch": 1.0,
"learning_rate": 3.6227817367166264e-05,
"loss": 3.6164,
"step": 841216
},
{
"epoch": 1.0,
"learning_rate": 3.6219431419655744e-05,
"loss": 3.6217,
"step": 841728
},
{
"epoch": 1.0,
"learning_rate": 3.621106185094896e-05,
"loss": 3.6063,
"step": 842240
},
{
"epoch": 1.0,
"learning_rate": 3.620267590343844e-05,
"loss": 3.6116,
"step": 842752
},
{
"epoch": 1.0,
"learning_rate": 3.619428995592792e-05,
"loss": 3.6095,
"step": 843264
},
{
"epoch": 1.0,
"learning_rate": 3.61859040084174e-05,
"loss": 3.6033,
"step": 843776
},
{
"epoch": 1.0,
"learning_rate": 3.617751806090688e-05,
"loss": 3.6012,
"step": 844288
},
{
"epoch": 1.0,
"learning_rate": 3.616913211339636e-05,
"loss": 3.6125,
"step": 844800
},
{
"epoch": 1.0,
"learning_rate": 3.616076254468957e-05,
"loss": 3.6214,
"step": 845312
},
{
"epoch": 1.0,
"learning_rate": 3.615237659717905e-05,
"loss": 3.6116,
"step": 845824
},
{
"epoch": 1.0,
"learning_rate": 3.614399064966853e-05,
"loss": 3.5889,
"step": 846336
},
{
"epoch": 1.0,
"learning_rate": 3.6135604702158e-05,
"loss": 3.6102,
"step": 846848
},
{
"epoch": 1.0,
"learning_rate": 3.612721875464748e-05,
"loss": 3.5922,
"step": 847360
},
{
"epoch": 1.0,
"learning_rate": 3.61188491859407e-05,
"loss": 3.6038,
"step": 847872
},
{
"epoch": 1.0,
"learning_rate": 3.6110463238430184e-05,
"loss": 3.6051,
"step": 848384
},
{
"epoch": 1.0,
"learning_rate": 3.610207729091966e-05,
"loss": 3.6038,
"step": 848896
},
{
"epoch": 1.0,
"learning_rate": 3.609369134340914e-05,
"loss": 3.6079,
"step": 849408
},
{
"epoch": 1.0,
"learning_rate": 3.608530539589862e-05,
"loss": 3.6151,
"step": 849920
},
{
"epoch": 1.0,
"learning_rate": 3.607693582719183e-05,
"loss": 3.6087,
"step": 850432
},
{
"epoch": 1.0,
"learning_rate": 3.6068549879681306e-05,
"loss": 3.6085,
"step": 850944
},
{
"epoch": 1.0,
"learning_rate": 3.6060163932170786e-05,
"loss": 3.6013,
"step": 851456
},
{
"epoch": 1.0,
"learning_rate": 3.6051777984660266e-05,
"loss": 3.6092,
"step": 851968
},
{
"epoch": 1.0,
"learning_rate": 3.6043408415953475e-05,
"loss": 3.6095,
"step": 852480
},
{
"epoch": 1.0,
"learning_rate": 3.6035022468442955e-05,
"loss": 3.6017,
"step": 852992
},
{
"epoch": 1.0,
"learning_rate": 3.6026636520932435e-05,
"loss": 3.6061,
"step": 853504
},
{
"epoch": 1.0,
"learning_rate": 3.601825057342192e-05,
"loss": 3.5988,
"step": 854016
},
{
"epoch": 1.0,
"learning_rate": 3.60098646259114e-05,
"loss": 3.602,
"step": 854528
},
{
"epoch": 1.01,
"learning_rate": 3.600149505720461e-05,
"loss": 3.5978,
"step": 855040
},
{
"epoch": 1.01,
"learning_rate": 3.599310910969409e-05,
"loss": 3.6114,
"step": 855552
},
{
"epoch": 1.01,
"learning_rate": 3.598472316218357e-05,
"loss": 3.6106,
"step": 856064
},
{
"epoch": 1.01,
"learning_rate": 3.597633721467305e-05,
"loss": 3.6112,
"step": 856576
},
{
"epoch": 1.01,
"learning_rate": 3.596796764596626e-05,
"loss": 3.602,
"step": 857088
},
{
"epoch": 1.01,
"learning_rate": 3.595958169845574e-05,
"loss": 3.604,
"step": 857600
},
{
"epoch": 1.01,
"learning_rate": 3.595119575094522e-05,
"loss": 3.6101,
"step": 858112
},
{
"epoch": 1.01,
"learning_rate": 3.59428098034347e-05,
"loss": 3.601,
"step": 858624
},
{
"epoch": 1.01,
"learning_rate": 3.593442385592418e-05,
"loss": 3.5948,
"step": 859136
},
{
"epoch": 1.01,
"learning_rate": 3.592605428721739e-05,
"loss": 3.5994,
"step": 859648
},
{
"epoch": 1.01,
"learning_rate": 3.5917668339706876e-05,
"loss": 3.5955,
"step": 860160
},
{
"epoch": 1.01,
"learning_rate": 3.5909282392196356e-05,
"loss": 3.6035,
"step": 860672
},
{
"epoch": 1.01,
"learning_rate": 3.5900896444685836e-05,
"loss": 3.5979,
"step": 861184
},
{
"epoch": 1.01,
"learning_rate": 3.5892526875979045e-05,
"loss": 3.6063,
"step": 861696
},
{
"epoch": 1.01,
"learning_rate": 3.5884140928468525e-05,
"loss": 3.6045,
"step": 862208
},
{
"epoch": 1.01,
"learning_rate": 3.5875754980958005e-05,
"loss": 3.607,
"step": 862720
},
{
"epoch": 1.01,
"learning_rate": 3.5867369033447485e-05,
"loss": 3.6096,
"step": 863232
},
{
"epoch": 1.01,
"learning_rate": 3.5858983085936965e-05,
"loss": 3.605,
"step": 863744
},
{
"epoch": 1.01,
"learning_rate": 3.5850613517230174e-05,
"loss": 3.5808,
"step": 864256
},
{
"epoch": 1.01,
"learning_rate": 3.5842227569719654e-05,
"loss": 3.6102,
"step": 864768
},
{
"epoch": 1.01,
"learning_rate": 3.5833841622209134e-05,
"loss": 3.6013,
"step": 865280
},
{
"epoch": 1.01,
"learning_rate": 3.5825455674698614e-05,
"loss": 3.6017,
"step": 865792
},
{
"epoch": 1.01,
"learning_rate": 3.581708610599183e-05,
"loss": 3.6036,
"step": 866304
},
{
"epoch": 1.01,
"learning_rate": 3.580870015848131e-05,
"loss": 3.6011,
"step": 866816
},
{
"epoch": 1.01,
"learning_rate": 3.580031421097079e-05,
"loss": 3.5839,
"step": 867328
},
{
"epoch": 1.01,
"learning_rate": 3.579192826346027e-05,
"loss": 3.5917,
"step": 867840
},
{
"epoch": 1.01,
"learning_rate": 3.578355869475348e-05,
"loss": 3.5979,
"step": 868352
},
{
"epoch": 1.01,
"learning_rate": 3.577517274724296e-05,
"loss": 3.5909,
"step": 868864
},
{
"epoch": 1.01,
"learning_rate": 3.576678679973244e-05,
"loss": 3.6105,
"step": 869376
},
{
"epoch": 1.01,
"learning_rate": 3.575840085222192e-05,
"loss": 3.6013,
"step": 869888
},
{
"epoch": 1.01,
"learning_rate": 3.575003128351513e-05,
"loss": 3.5848,
"step": 870400
},
{
"epoch": 1.01,
"learning_rate": 3.574164533600461e-05,
"loss": 3.6114,
"step": 870912
},
{
"epoch": 1.01,
"learning_rate": 3.573325938849409e-05,
"loss": 3.5922,
"step": 871424
},
{
"epoch": 1.01,
"learning_rate": 3.572487344098357e-05,
"loss": 3.5859,
"step": 871936
},
{
"epoch": 1.01,
"learning_rate": 3.571650387227678e-05,
"loss": 3.6006,
"step": 872448
},
{
"epoch": 1.01,
"learning_rate": 3.570811792476626e-05,
"loss": 3.5975,
"step": 872960
},
{
"epoch": 1.01,
"learning_rate": 3.569973197725574e-05,
"loss": 3.588,
"step": 873472
},
{
"epoch": 1.01,
"learning_rate": 3.569134602974522e-05,
"loss": 3.5954,
"step": 873984
},
{
"epoch": 1.01,
"learning_rate": 3.56829600822347e-05,
"loss": 3.5806,
"step": 874496
},
{
"epoch": 1.01,
"learning_rate": 3.567459051352791e-05,
"loss": 3.5921,
"step": 875008
},
{
"epoch": 1.01,
"learning_rate": 3.566620456601739e-05,
"loss": 3.6024,
"step": 875520
},
{
"epoch": 1.01,
"learning_rate": 3.565781861850687e-05,
"loss": 3.5955,
"step": 876032
},
{
"epoch": 1.01,
"learning_rate": 3.564943267099635e-05,
"loss": 3.6068,
"step": 876544
},
{
"epoch": 1.01,
"learning_rate": 3.564106310228956e-05,
"loss": 3.5963,
"step": 877056
},
{
"epoch": 1.01,
"learning_rate": 3.563267715477904e-05,
"loss": 3.6144,
"step": 877568
},
{
"epoch": 1.01,
"learning_rate": 3.562429120726852e-05,
"loss": 3.5887,
"step": 878080
},
{
"epoch": 1.01,
"learning_rate": 3.5615905259758e-05,
"loss": 3.6047,
"step": 878592
},
{
"epoch": 1.01,
"learning_rate": 3.560753569105122e-05,
"loss": 3.5984,
"step": 879104
},
{
"epoch": 1.01,
"learning_rate": 3.55991497435407e-05,
"loss": 3.5861,
"step": 879616
},
{
"epoch": 1.01,
"learning_rate": 3.5590763796030177e-05,
"loss": 3.6076,
"step": 880128
},
{
"epoch": 1.01,
"learning_rate": 3.5582377848519657e-05,
"loss": 3.6042,
"step": 880640
},
{
"epoch": 1.01,
"learning_rate": 3.5573991901009137e-05,
"loss": 3.5985,
"step": 881152
},
{
"epoch": 1.01,
"learning_rate": 3.5565622332302346e-05,
"loss": 3.6068,
"step": 881664
},
{
"epoch": 1.01,
"learning_rate": 3.5557236384791826e-05,
"loss": 3.5856,
"step": 882176
},
{
"epoch": 1.01,
"learning_rate": 3.5548850437281306e-05,
"loss": 3.5806,
"step": 882688
},
{
"epoch": 1.01,
"learning_rate": 3.5540464489770785e-05,
"loss": 3.5871,
"step": 883200
},
{
"epoch": 1.01,
"learning_rate": 3.5532094921063995e-05,
"loss": 3.603,
"step": 883712
},
{
"epoch": 1.01,
"learning_rate": 3.5523708973553475e-05,
"loss": 3.5948,
"step": 884224
},
{
"epoch": 1.01,
"learning_rate": 3.5515323026042954e-05,
"loss": 3.5908,
"step": 884736
},
{
"epoch": 1.01,
"learning_rate": 3.5506937078532434e-05,
"loss": 3.5903,
"step": 885248
},
{
"epoch": 1.02,
"learning_rate": 3.549856750982565e-05,
"loss": 3.5938,
"step": 885760
},
{
"epoch": 1.02,
"learning_rate": 3.549018156231513e-05,
"loss": 3.592,
"step": 886272
},
{
"epoch": 1.02,
"learning_rate": 3.548179561480461e-05,
"loss": 3.5928,
"step": 886784
},
{
"epoch": 1.02,
"learning_rate": 3.5473409667294083e-05,
"loss": 3.6011,
"step": 887296
},
{
"epoch": 1.02,
"learning_rate": 3.546502371978356e-05,
"loss": 3.6106,
"step": 887808
},
{
"epoch": 1.02,
"learning_rate": 3.545665415107678e-05,
"loss": 3.6026,
"step": 888320
},
{
"epoch": 1.02,
"learning_rate": 3.544826820356626e-05,
"loss": 3.5882,
"step": 888832
},
{
"epoch": 1.02,
"learning_rate": 3.543988225605573e-05,
"loss": 3.5913,
"step": 889344
},
{
"epoch": 1.02,
"learning_rate": 3.543149630854521e-05,
"loss": 3.5908,
"step": 889856
},
{
"epoch": 1.02,
"learning_rate": 3.542312673983843e-05,
"loss": 3.6014,
"step": 890368
},
{
"epoch": 1.02,
"learning_rate": 3.541474079232791e-05,
"loss": 3.5962,
"step": 890880
},
{
"epoch": 1.02,
"learning_rate": 3.540635484481739e-05,
"loss": 3.5959,
"step": 891392
},
{
"epoch": 1.02,
"learning_rate": 3.539796889730687e-05,
"loss": 3.5961,
"step": 891904
},
{
"epoch": 1.02,
"learning_rate": 3.5389599328600084e-05,
"loss": 3.5951,
"step": 892416
},
{
"epoch": 1.02,
"learning_rate": 3.538121338108956e-05,
"loss": 3.5969,
"step": 892928
},
{
"epoch": 1.02,
"learning_rate": 3.537282743357904e-05,
"loss": 3.5924,
"step": 893440
},
{
"epoch": 1.02,
"learning_rate": 3.536444148606852e-05,
"loss": 3.5869,
"step": 893952
},
{
"epoch": 1.02,
"learning_rate": 3.535607191736173e-05,
"loss": 3.5905,
"step": 894464
},
{
"epoch": 1.02,
"learning_rate": 3.5347685969851206e-05,
"loss": 3.5893,
"step": 894976
},
{
"epoch": 1.02,
"learning_rate": 3.5339300022340686e-05,
"loss": 3.5873,
"step": 895488
},
{
"epoch": 1.02,
"learning_rate": 3.5330914074830166e-05,
"loss": 3.5918,
"step": 896000
},
{
"epoch": 1.02,
"learning_rate": 3.532254450612338e-05,
"loss": 3.5931,
"step": 896512
},
{
"epoch": 1.02,
"learning_rate": 3.531415855861286e-05,
"loss": 3.5945,
"step": 897024
},
{
"epoch": 1.02,
"learning_rate": 3.530577261110234e-05,
"loss": 3.5856,
"step": 897536
},
{
"epoch": 1.02,
"learning_rate": 3.529738666359182e-05,
"loss": 3.6027,
"step": 898048
},
{
"epoch": 1.02,
"learning_rate": 3.528901709488503e-05,
"loss": 3.6081,
"step": 898560
},
{
"epoch": 1.02,
"learning_rate": 3.528063114737451e-05,
"loss": 3.5951,
"step": 899072
},
{
"epoch": 1.02,
"learning_rate": 3.527224519986399e-05,
"loss": 3.6007,
"step": 899584
},
{
"epoch": 1.02,
"learning_rate": 3.526385925235347e-05,
"loss": 3.5927,
"step": 900096
},
{
"epoch": 1.02,
"learning_rate": 3.525547330484295e-05,
"loss": 3.5928,
"step": 900608
},
{
"epoch": 1.02,
"learning_rate": 3.524710373613616e-05,
"loss": 3.5926,
"step": 901120
},
{
"epoch": 1.02,
"learning_rate": 3.523871778862564e-05,
"loss": 3.58,
"step": 901632
},
{
"epoch": 1.02,
"learning_rate": 3.523033184111512e-05,
"loss": 3.5911,
"step": 902144
},
{
"epoch": 1.02,
"learning_rate": 3.52219458936046e-05,
"loss": 3.5938,
"step": 902656
},
{
"epoch": 1.02,
"learning_rate": 3.5213576324897815e-05,
"loss": 3.5996,
"step": 903168
},
{
"epoch": 1.02,
"learning_rate": 3.5205190377387295e-05,
"loss": 3.5864,
"step": 903680
},
{
"epoch": 1.02,
"learning_rate": 3.5196804429876775e-05,
"loss": 3.5998,
"step": 904192
},
{
"epoch": 1.02,
"learning_rate": 3.5188418482366255e-05,
"loss": 3.5923,
"step": 904704
},
{
"epoch": 1.02,
"learning_rate": 3.5180048913659464e-05,
"loss": 3.5892,
"step": 905216
},
{
"epoch": 1.02,
"learning_rate": 3.5171662966148944e-05,
"loss": 3.5936,
"step": 905728
},
{
"epoch": 1.02,
"learning_rate": 3.5163277018638424e-05,
"loss": 3.5982,
"step": 906240
},
{
"epoch": 1.02,
"learning_rate": 3.5154891071127904e-05,
"loss": 3.6024,
"step": 906752
},
{
"epoch": 1.02,
"learning_rate": 3.5146521502421113e-05,
"loss": 3.5841,
"step": 907264
},
{
"epoch": 1.02,
"learning_rate": 3.513813555491059e-05,
"loss": 3.6093,
"step": 907776
},
{
"epoch": 1.02,
"learning_rate": 3.512974960740007e-05,
"loss": 3.5892,
"step": 908288
},
{
"epoch": 1.02,
"learning_rate": 3.512136365988955e-05,
"loss": 3.6005,
"step": 908800
},
{
"epoch": 1.02,
"learning_rate": 3.511297771237903e-05,
"loss": 3.5983,
"step": 909312
},
{
"epoch": 1.02,
"learning_rate": 3.510460814367225e-05,
"loss": 3.5903,
"step": 909824
},
{
"epoch": 1.02,
"learning_rate": 3.509622219616173e-05,
"loss": 3.5897,
"step": 910336
},
{
"epoch": 1.02,
"learning_rate": 3.508783624865121e-05,
"loss": 3.6093,
"step": 910848
},
{
"epoch": 1.02,
"learning_rate": 3.507945030114069e-05,
"loss": 3.5816,
"step": 911360
},
{
"epoch": 1.02,
"learning_rate": 3.50710807324339e-05,
"loss": 3.5929,
"step": 911872
},
{
"epoch": 1.02,
"learning_rate": 3.506269478492338e-05,
"loss": 3.5963,
"step": 912384
},
{
"epoch": 1.02,
"learning_rate": 3.505430883741286e-05,
"loss": 3.592,
"step": 912896
},
{
"epoch": 1.02,
"learning_rate": 3.504592288990234e-05,
"loss": 3.5944,
"step": 913408
},
{
"epoch": 1.02,
"learning_rate": 3.503755332119555e-05,
"loss": 3.5913,
"step": 913920
},
{
"epoch": 1.02,
"learning_rate": 3.502916737368503e-05,
"loss": 3.596,
"step": 914432
},
{
"epoch": 1.02,
"learning_rate": 3.502078142617451e-05,
"loss": 3.6028,
"step": 914944
},
{
"epoch": 1.02,
"learning_rate": 3.501239547866399e-05,
"loss": 3.5916,
"step": 915456
},
{
"epoch": 1.03,
"eval_loss": 3.8415114879608154,
"eval_runtime": 303.6265,
"eval_samples_per_second": 1256.778,
"eval_steps_per_second": 39.275,
"step": 915840
},
{
"epoch": 0.0,
"learning_rate": 3.500400953115347e-05,
"loss": 3.577,
"step": 915968
},
{
"epoch": 0.0,
"learning_rate": 3.4995623583642954e-05,
"loss": 3.5798,
"step": 916480
},
{
"epoch": 0.0,
"learning_rate": 3.4987237636132434e-05,
"loss": 3.5914,
"step": 916992
},
{
"epoch": 0.0,
"learning_rate": 3.4978851688621913e-05,
"loss": 3.5985,
"step": 917504
},
{
"epoch": 0.0,
"learning_rate": 3.497048211991512e-05,
"loss": 3.5973,
"step": 918016
},
{
"epoch": 0.0,
"learning_rate": 3.49620961724046e-05,
"loss": 3.5899,
"step": 918528
},
{
"epoch": 0.0,
"learning_rate": 3.495371022489408e-05,
"loss": 3.5956,
"step": 919040
},
{
"epoch": 0.0,
"learning_rate": 3.494532427738356e-05,
"loss": 3.5881,
"step": 919552
},
{
"epoch": 0.0,
"learning_rate": 3.493693832987304e-05,
"loss": 3.5839,
"step": 920064
},
{
"epoch": 0.0,
"learning_rate": 3.492856876116625e-05,
"loss": 3.5814,
"step": 920576
},
{
"epoch": 0.0,
"learning_rate": 3.492018281365573e-05,
"loss": 3.5972,
"step": 921088
},
{
"epoch": 0.0,
"learning_rate": 3.491179686614521e-05,
"loss": 3.6002,
"step": 921600
},
{
"epoch": 0.0,
"learning_rate": 3.490342729743842e-05,
"loss": 3.5934,
"step": 922112
},
{
"epoch": 0.0,
"learning_rate": 3.48950413499279e-05,
"loss": 3.5704,
"step": 922624
},
{
"epoch": 0.0,
"learning_rate": 3.488665540241739e-05,
"loss": 3.5909,
"step": 923136
},
{
"epoch": 0.0,
"learning_rate": 3.487826945490687e-05,
"loss": 3.572,
"step": 923648
},
{
"epoch": 0.0,
"learning_rate": 3.4869899886200076e-05,
"loss": 3.5878,
"step": 924160
},
{
"epoch": 0.0,
"learning_rate": 3.4861513938689556e-05,
"loss": 3.5845,
"step": 924672
},
{
"epoch": 0.0,
"learning_rate": 3.4853127991179036e-05,
"loss": 3.5838,
"step": 925184
},
{
"epoch": 0.0,
"learning_rate": 3.4844742043668516e-05,
"loss": 3.5904,
"step": 925696
},
{
"epoch": 0.0,
"learning_rate": 3.483635609615799e-05,
"loss": 3.597,
"step": 926208
},
{
"epoch": 0.0,
"learning_rate": 3.4827986527451205e-05,
"loss": 3.5889,
"step": 926720
},
{
"epoch": 0.0,
"learning_rate": 3.4819600579940685e-05,
"loss": 3.5891,
"step": 927232
},
{
"epoch": 0.0,
"learning_rate": 3.481121463243016e-05,
"loss": 3.5857,
"step": 927744
},
{
"epoch": 0.0,
"learning_rate": 3.4802828684919645e-05,
"loss": 3.5914,
"step": 928256
},
{
"epoch": 0.0,
"learning_rate": 3.4794459116212854e-05,
"loss": 3.591,
"step": 928768
},
{
"epoch": 0.0,
"learning_rate": 3.478607316870234e-05,
"loss": 3.583,
"step": 929280
},
{
"epoch": 0.0,
"learning_rate": 3.4777687221191814e-05,
"loss": 3.5863,
"step": 929792
},
{
"epoch": 0.0,
"learning_rate": 3.4769301273681294e-05,
"loss": 3.5807,
"step": 930304
},
{
"epoch": 0.0,
"learning_rate": 3.476093170497451e-05,
"loss": 3.5825,
"step": 930816
},
{
"epoch": 0.01,
"learning_rate": 3.475254575746399e-05,
"loss": 3.583,
"step": 931328
},
{
"epoch": 0.01,
"learning_rate": 3.474415980995346e-05,
"loss": 3.5888,
"step": 931840
},
{
"epoch": 0.01,
"learning_rate": 3.473577386244294e-05,
"loss": 3.5871,
"step": 932352
},
{
"epoch": 0.01,
"learning_rate": 3.472738791493242e-05,
"loss": 3.596,
"step": 932864
},
{
"epoch": 0.01,
"learning_rate": 3.471901834622563e-05,
"loss": 3.5852,
"step": 933376
},
{
"epoch": 0.01,
"learning_rate": 3.471063239871511e-05,
"loss": 3.582,
"step": 933888
},
{
"epoch": 0.01,
"learning_rate": 3.470224645120459e-05,
"loss": 3.5929,
"step": 934400
},
{
"epoch": 0.01,
"learning_rate": 3.469386050369408e-05,
"loss": 3.5797,
"step": 934912
},
{
"epoch": 0.01,
"learning_rate": 3.468549093498729e-05,
"loss": 3.5781,
"step": 935424
},
{
"epoch": 0.01,
"learning_rate": 3.467710498747677e-05,
"loss": 3.5812,
"step": 935936
},
{
"epoch": 0.01,
"learning_rate": 3.466871903996625e-05,
"loss": 3.5786,
"step": 936448
},
{
"epoch": 0.01,
"learning_rate": 3.466033309245573e-05,
"loss": 3.5814,
"step": 936960
},
{
"epoch": 0.01,
"learning_rate": 3.465194714494521e-05,
"loss": 3.5824,
"step": 937472
},
{
"epoch": 0.01,
"learning_rate": 3.464357757623842e-05,
"loss": 3.5844,
"step": 937984
},
{
"epoch": 0.01,
"learning_rate": 3.46351916287279e-05,
"loss": 3.5862,
"step": 938496
},
{
"epoch": 0.01,
"learning_rate": 3.4626805681217377e-05,
"loss": 3.5915,
"step": 939008
},
{
"epoch": 0.01,
"learning_rate": 3.4618419733706857e-05,
"loss": 3.5902,
"step": 939520
},
{
"epoch": 0.01,
"learning_rate": 3.4610033786196337e-05,
"loss": 3.587,
"step": 940032
},
{
"epoch": 0.01,
"learning_rate": 3.4601664217489546e-05,
"loss": 3.5635,
"step": 940544
},
{
"epoch": 0.01,
"learning_rate": 3.459327826997903e-05,
"loss": 3.5913,
"step": 941056
},
{
"epoch": 0.01,
"learning_rate": 3.458489232246851e-05,
"loss": 3.5801,
"step": 941568
},
{
"epoch": 0.01,
"learning_rate": 3.457650637495799e-05,
"loss": 3.5856,
"step": 942080
},
{
"epoch": 0.01,
"learning_rate": 3.45681368062512e-05,
"loss": 3.5792,
"step": 942592
},
{
"epoch": 0.01,
"learning_rate": 3.455975085874068e-05,
"loss": 3.5786,
"step": 943104
},
{
"epoch": 0.01,
"learning_rate": 3.455136491123016e-05,
"loss": 3.568,
"step": 943616
},
{
"epoch": 0.01,
"learning_rate": 3.454297896371964e-05,
"loss": 3.5743,
"step": 944128
},
{
"epoch": 0.01,
"learning_rate": 3.453460939501285e-05,
"loss": 3.5819,
"step": 944640
},
{
"epoch": 0.01,
"learning_rate": 3.452622344750233e-05,
"loss": 3.5704,
"step": 945152
},
{
"epoch": 0.01,
"learning_rate": 3.451783749999181e-05,
"loss": 3.5936,
"step": 945664
},
{
"epoch": 0.01,
"learning_rate": 3.450945155248129e-05,
"loss": 3.583,
"step": 946176
},
{
"epoch": 0.01,
"learning_rate": 3.45010819837745e-05,
"loss": 3.5633,
"step": 946688
},
{
"epoch": 0.01,
"learning_rate": 3.4492696036263986e-05,
"loss": 3.5945,
"step": 947200
},
{
"epoch": 0.01,
"learning_rate": 3.4484310088753466e-05,
"loss": 3.5732,
"step": 947712
},
{
"epoch": 0.01,
"learning_rate": 3.4475924141242946e-05,
"loss": 3.5668,
"step": 948224
},
{
"epoch": 0.01,
"learning_rate": 3.4467554572536155e-05,
"loss": 3.5805,
"step": 948736
},
{
"epoch": 0.01,
"learning_rate": 3.4459168625025635e-05,
"loss": 3.5795,
"step": 949248
},
{
"epoch": 0.01,
"learning_rate": 3.4450782677515115e-05,
"loss": 3.5671,
"step": 949760
},
{
"epoch": 0.01,
"learning_rate": 3.4442396730004595e-05,
"loss": 3.5778,
"step": 950272
},
{
"epoch": 0.01,
"learning_rate": 3.4434010782494075e-05,
"loss": 3.5658,
"step": 950784
},
{
"epoch": 0.01,
"learning_rate": 3.4425641213787284e-05,
"loss": 3.5694,
"step": 951296
},
{
"epoch": 0.01,
"learning_rate": 3.4417255266276764e-05,
"loss": 3.5851,
"step": 951808
},
{
"epoch": 0.01,
"learning_rate": 3.4408869318766244e-05,
"loss": 3.5768,
"step": 952320
},
{
"epoch": 0.01,
"learning_rate": 3.4400483371255724e-05,
"loss": 3.5868,
"step": 952832
},
{
"epoch": 0.01,
"learning_rate": 3.439211380254894e-05,
"loss": 3.5797,
"step": 953344
},
{
"epoch": 0.01,
"learning_rate": 3.438372785503842e-05,
"loss": 3.5958,
"step": 953856
},
{
"epoch": 0.01,
"learning_rate": 3.43753419075279e-05,
"loss": 3.5712,
"step": 954368
},
{
"epoch": 0.01,
"learning_rate": 3.436695596001738e-05,
"loss": 3.5893,
"step": 954880
},
{
"epoch": 0.01,
"learning_rate": 3.435858639131059e-05,
"loss": 3.5776,
"step": 955392
},
{
"epoch": 0.01,
"learning_rate": 3.435020044380007e-05,
"loss": 3.5705,
"step": 955904
},
{
"epoch": 0.01,
"learning_rate": 3.434181449628955e-05,
"loss": 3.5841,
"step": 956416
},
{
"epoch": 0.01,
"learning_rate": 3.433342854877903e-05,
"loss": 3.5911,
"step": 956928
},
{
"epoch": 0.01,
"learning_rate": 3.432505898007224e-05,
"loss": 3.577,
"step": 957440
},
{
"epoch": 0.01,
"learning_rate": 3.431667303256172e-05,
"loss": 3.5887,
"step": 957952
},
{
"epoch": 0.01,
"learning_rate": 3.43082870850512e-05,
"loss": 3.5664,
"step": 958464
},
{
"epoch": 0.01,
"learning_rate": 3.429990113754068e-05,
"loss": 3.5627,
"step": 958976
},
{
"epoch": 0.01,
"learning_rate": 3.429153156883389e-05,
"loss": 3.5688,
"step": 959488
},
{
"epoch": 0.01,
"learning_rate": 3.428314562132337e-05,
"loss": 3.5822,
"step": 960000
},
{
"epoch": 0.01,
"learning_rate": 3.427475967381285e-05,
"loss": 3.5777,
"step": 960512
},
{
"epoch": 0.01,
"learning_rate": 3.426637372630233e-05,
"loss": 3.5755,
"step": 961024
},
{
"epoch": 0.01,
"learning_rate": 3.425800415759554e-05,
"loss": 3.5673,
"step": 961536
},
{
"epoch": 0.02,
"learning_rate": 3.424961821008502e-05,
"loss": 3.5779,
"step": 962048
},
{
"epoch": 0.02,
"learning_rate": 3.42412322625745e-05,
"loss": 3.575,
"step": 962560
},
{
"epoch": 0.02,
"learning_rate": 3.423284631506398e-05,
"loss": 3.5723,
"step": 963072
},
{
"epoch": 0.02,
"learning_rate": 3.422447674635719e-05,
"loss": 3.5848,
"step": 963584
},
{
"epoch": 0.02,
"learning_rate": 3.421609079884667e-05,
"loss": 3.59,
"step": 964096
},
{
"epoch": 0.02,
"learning_rate": 3.420770485133615e-05,
"loss": 3.5863,
"step": 964608
},
{
"epoch": 0.02,
"learning_rate": 3.419931890382563e-05,
"loss": 3.5655,
"step": 965120
},
{
"epoch": 0.02,
"learning_rate": 3.419094933511885e-05,
"loss": 3.5753,
"step": 965632
},
{
"epoch": 0.02,
"learning_rate": 3.418256338760833e-05,
"loss": 3.5727,
"step": 966144
},
{
"epoch": 0.02,
"learning_rate": 3.417417744009781e-05,
"loss": 3.584,
"step": 966656
},
{
"epoch": 0.02,
"learning_rate": 3.416579149258729e-05,
"loss": 3.5811,
"step": 967168
},
{
"epoch": 0.02,
"learning_rate": 3.4157421923880496e-05,
"loss": 3.5756,
"step": 967680
},
{
"epoch": 0.02,
"learning_rate": 3.4149035976369976e-05,
"loss": 3.5778,
"step": 968192
},
{
"epoch": 0.02,
"learning_rate": 3.4140650028859456e-05,
"loss": 3.5791,
"step": 968704
},
{
"epoch": 0.02,
"learning_rate": 3.4132264081348936e-05,
"loss": 3.5786,
"step": 969216
},
{
"epoch": 0.02,
"learning_rate": 3.4123894512642145e-05,
"loss": 3.5759,
"step": 969728
},
{
"epoch": 0.02,
"learning_rate": 3.4115508565131625e-05,
"loss": 3.5707,
"step": 970240
},
{
"epoch": 0.02,
"learning_rate": 3.4107122617621105e-05,
"loss": 3.5672,
"step": 970752
},
{
"epoch": 0.02,
"learning_rate": 3.4098736670110585e-05,
"loss": 3.5716,
"step": 971264
},
{
"epoch": 0.02,
"learning_rate": 3.4090350722600065e-05,
"loss": 3.5708,
"step": 971776
},
{
"epoch": 0.02,
"learning_rate": 3.408198115389328e-05,
"loss": 3.5694,
"step": 972288
},
{
"epoch": 0.02,
"learning_rate": 3.407359520638276e-05,
"loss": 3.5738,
"step": 972800
},
{
"epoch": 0.02,
"learning_rate": 3.406520925887224e-05,
"loss": 3.5795,
"step": 973312
},
{
"epoch": 0.02,
"learning_rate": 3.4056823311361714e-05,
"loss": 3.5651,
"step": 973824
},
{
"epoch": 0.02,
"learning_rate": 3.404845374265493e-05,
"loss": 3.584,
"step": 974336
},
{
"epoch": 0.02,
"learning_rate": 3.404006779514441e-05,
"loss": 3.5914,
"step": 974848
},
{
"epoch": 0.02,
"learning_rate": 3.403168184763389e-05,
"loss": 3.5791,
"step": 975360
},
{
"epoch": 0.02,
"learning_rate": 3.402329590012336e-05,
"loss": 3.5808,
"step": 975872
},
{
"epoch": 0.02,
"learning_rate": 3.401492633141658e-05,
"loss": 3.5805,
"step": 976384
},
{
"epoch": 0.02,
"learning_rate": 3.400654038390606e-05,
"loss": 3.5704,
"step": 976896
},
{
"epoch": 0.02,
"learning_rate": 3.399815443639554e-05,
"loss": 3.5827,
"step": 977408
},
{
"epoch": 0.02,
"learning_rate": 3.398976848888502e-05,
"loss": 3.5576,
"step": 977920
},
{
"epoch": 0.02,
"learning_rate": 3.39813825413745e-05,
"loss": 3.5749,
"step": 978432
},
{
"epoch": 0.02,
"learning_rate": 3.3973012972667714e-05,
"loss": 3.5754,
"step": 978944
},
{
"epoch": 0.02,
"learning_rate": 3.396462702515719e-05,
"loss": 3.5798,
"step": 979456
},
{
"epoch": 0.02,
"learning_rate": 3.395624107764667e-05,
"loss": 3.5724,
"step": 979968
},
{
"epoch": 0.02,
"learning_rate": 3.394785513013615e-05,
"loss": 3.5803,
"step": 980480
},
{
"epoch": 0.02,
"learning_rate": 3.393948556142936e-05,
"loss": 3.5726,
"step": 980992
},
{
"epoch": 0.02,
"learning_rate": 3.3931099613918836e-05,
"loss": 3.5688,
"step": 981504
},
{
"epoch": 0.02,
"learning_rate": 3.3922713666408316e-05,
"loss": 3.5818,
"step": 982016
},
{
"epoch": 0.02,
"learning_rate": 3.3914327718897796e-05,
"loss": 3.5789,
"step": 982528
},
{
"epoch": 0.02,
"learning_rate": 3.390595815019101e-05,
"loss": 3.5846,
"step": 983040
},
{
"epoch": 0.02,
"learning_rate": 3.3897572202680485e-05,
"loss": 3.5703,
"step": 983552
},
{
"epoch": 0.02,
"learning_rate": 3.388918625516997e-05,
"loss": 3.5857,
"step": 984064
},
{
"epoch": 0.02,
"learning_rate": 3.388080030765945e-05,
"loss": 3.5761,
"step": 984576
},
{
"epoch": 0.02,
"learning_rate": 3.387243073895266e-05,
"loss": 3.5782,
"step": 985088
},
{
"epoch": 0.02,
"learning_rate": 3.386404479144214e-05,
"loss": 3.5813,
"step": 985600
},
{
"epoch": 0.02,
"learning_rate": 3.385565884393162e-05,
"loss": 3.5741,
"step": 986112
},
{
"epoch": 0.02,
"learning_rate": 3.38472728964211e-05,
"loss": 3.5716,
"step": 986624
},
{
"epoch": 0.02,
"learning_rate": 3.383890332771431e-05,
"loss": 3.5884,
"step": 987136
},
{
"epoch": 0.02,
"learning_rate": 3.383051738020379e-05,
"loss": 3.5662,
"step": 987648
},
{
"epoch": 0.02,
"learning_rate": 3.382213143269327e-05,
"loss": 3.5731,
"step": 988160
},
{
"epoch": 0.02,
"learning_rate": 3.381374548518275e-05,
"loss": 3.5793,
"step": 988672
},
{
"epoch": 0.02,
"learning_rate": 3.380537591647596e-05,
"loss": 3.5756,
"step": 989184
},
{
"epoch": 0.02,
"learning_rate": 3.379698996896544e-05,
"loss": 3.5767,
"step": 989696
},
{
"epoch": 0.02,
"learning_rate": 3.3788604021454926e-05,
"loss": 3.5741,
"step": 990208
},
{
"epoch": 0.02,
"learning_rate": 3.3780218073944406e-05,
"loss": 3.5767,
"step": 990720
},
{
"epoch": 0.02,
"learning_rate": 3.3771832126433886e-05,
"loss": 3.5839,
"step": 991232
},
{
"epoch": 0.02,
"learning_rate": 3.3763462557727095e-05,
"loss": 3.5781,
"step": 991744
},
{
"epoch": 0.03,
"eval_loss": 3.841749429702759,
"eval_runtime": 321.3937,
"eval_samples_per_second": 1187.301,
"eval_steps_per_second": 37.104,
"step": 992160
},
{
"epoch": 1.0,
"learning_rate": 3.3755076610216575e-05,
"loss": 3.5679,
"step": 992256
},
{
"epoch": 1.0,
"learning_rate": 3.3746690662706055e-05,
"loss": 3.5608,
"step": 992768
},
{
"epoch": 1.0,
"learning_rate": 3.3738304715195535e-05,
"loss": 3.5718,
"step": 993280
},
{
"epoch": 1.0,
"learning_rate": 3.3729935146488744e-05,
"loss": 3.5874,
"step": 993792
},
{
"epoch": 1.0,
"learning_rate": 3.3721549198978224e-05,
"loss": 3.5758,
"step": 994304
},
{
"epoch": 1.0,
"learning_rate": 3.3713163251467704e-05,
"loss": 3.5721,
"step": 994816
},
{
"epoch": 1.0,
"learning_rate": 3.3704777303957184e-05,
"loss": 3.5759,
"step": 995328
},
{
"epoch": 1.0,
"learning_rate": 3.3696391356446664e-05,
"loss": 3.5727,
"step": 995840
},
{
"epoch": 1.0,
"learning_rate": 3.368802178773988e-05,
"loss": 3.5616,
"step": 996352
},
{
"epoch": 1.0,
"learning_rate": 3.367963584022936e-05,
"loss": 3.5711,
"step": 996864
},
{
"epoch": 1.0,
"learning_rate": 3.367124989271884e-05,
"loss": 3.5772,
"step": 997376
},
{
"epoch": 1.0,
"learning_rate": 3.366286394520832e-05,
"loss": 3.5815,
"step": 997888
},
{
"epoch": 1.0,
"learning_rate": 3.365449437650153e-05,
"loss": 3.5815,
"step": 998400
},
{
"epoch": 1.0,
"learning_rate": 3.364610842899101e-05,
"loss": 3.5511,
"step": 998912
},
{
"epoch": 1.0,
"learning_rate": 3.363772248148049e-05,
"loss": 3.5682,
"step": 999424
},
{
"epoch": 1.0,
"learning_rate": 3.362933653396997e-05,
"loss": 3.5581,
"step": 999936
},
{
"epoch": 1.0,
"learning_rate": 3.362096696526318e-05,
"loss": 3.5704,
"step": 1000448
},
{
"epoch": 1.0,
"learning_rate": 3.361258101775266e-05,
"loss": 3.5665,
"step": 1000960
},
{
"epoch": 1.0,
"learning_rate": 3.360419507024214e-05,
"loss": 3.5686,
"step": 1001472
},
{
"epoch": 1.0,
"learning_rate": 3.359580912273162e-05,
"loss": 3.5668,
"step": 1001984
},
{
"epoch": 1.0,
"learning_rate": 3.358743955402483e-05,
"loss": 3.585,
"step": 1002496
},
{
"epoch": 1.0,
"learning_rate": 3.357905360651431e-05,
"loss": 3.5694,
"step": 1003008
},
{
"epoch": 1.0,
"learning_rate": 3.357066765900379e-05,
"loss": 3.5729,
"step": 1003520
},
{
"epoch": 1.0,
"learning_rate": 3.356228171149327e-05,
"loss": 3.5662,
"step": 1004032
},
{
"epoch": 1.0,
"learning_rate": 3.355391214278648e-05,
"loss": 3.576,
"step": 1004544
},
{
"epoch": 1.0,
"learning_rate": 3.354552619527596e-05,
"loss": 3.5721,
"step": 1005056
},
{
"epoch": 1.0,
"learning_rate": 3.353714024776544e-05,
"loss": 3.5639,
"step": 1005568
},
{
"epoch": 1.0,
"learning_rate": 3.352875430025492e-05,
"loss": 3.5698,
"step": 1006080
},
{
"epoch": 1.0,
"learning_rate": 3.352038473154813e-05,
"loss": 3.563,
"step": 1006592
},
{
"epoch": 1.0,
"learning_rate": 3.351199878403761e-05,
"loss": 3.5625,
"step": 1007104
},
{
"epoch": 1.01,
"learning_rate": 3.350361283652709e-05,
"loss": 3.5691,
"step": 1007616
},
{
"epoch": 1.01,
"learning_rate": 3.349522688901657e-05,
"loss": 3.568,
"step": 1008128
},
{
"epoch": 1.01,
"learning_rate": 3.348685732030979e-05,
"loss": 3.5735,
"step": 1008640
},
{
"epoch": 1.01,
"learning_rate": 3.347847137279927e-05,
"loss": 3.5738,
"step": 1009152
},
{
"epoch": 1.01,
"learning_rate": 3.347008542528875e-05,
"loss": 3.5675,
"step": 1009664
},
{
"epoch": 1.01,
"learning_rate": 3.346169947777823e-05,
"loss": 3.5676,
"step": 1010176
},
{
"epoch": 1.01,
"learning_rate": 3.3453329909071436e-05,
"loss": 3.5786,
"step": 1010688
},
{
"epoch": 1.01,
"learning_rate": 3.3444943961560916e-05,
"loss": 3.5561,
"step": 1011200
},
{
"epoch": 1.01,
"learning_rate": 3.3436558014050396e-05,
"loss": 3.5627,
"step": 1011712
},
{
"epoch": 1.01,
"learning_rate": 3.3428172066539876e-05,
"loss": 3.5656,
"step": 1012224
},
{
"epoch": 1.01,
"learning_rate": 3.3419802497833085e-05,
"loss": 3.5559,
"step": 1012736
},
{
"epoch": 1.01,
"learning_rate": 3.3411416550322565e-05,
"loss": 3.5652,
"step": 1013248
},
{
"epoch": 1.01,
"learning_rate": 3.3403030602812045e-05,
"loss": 3.567,
"step": 1013760
},
{
"epoch": 1.01,
"learning_rate": 3.3394644655301525e-05,
"loss": 3.5671,
"step": 1014272
},
{
"epoch": 1.01,
"learning_rate": 3.338627508659474e-05,
"loss": 3.5695,
"step": 1014784
},
{
"epoch": 1.01,
"learning_rate": 3.337788913908422e-05,
"loss": 3.5697,
"step": 1015296
},
{
"epoch": 1.01,
"learning_rate": 3.33695031915737e-05,
"loss": 3.5745,
"step": 1015808
},
{
"epoch": 1.01,
"learning_rate": 3.336111724406318e-05,
"loss": 3.5673,
"step": 1016320
},
{
"epoch": 1.01,
"learning_rate": 3.335274767535639e-05,
"loss": 3.5497,
"step": 1016832
},
{
"epoch": 1.01,
"learning_rate": 3.334436172784587e-05,
"loss": 3.5689,
"step": 1017344
},
{
"epoch": 1.01,
"learning_rate": 3.333597578033535e-05,
"loss": 3.5658,
"step": 1017856
},
{
"epoch": 1.01,
"learning_rate": 3.332758983282483e-05,
"loss": 3.5714,
"step": 1018368
},
{
"epoch": 1.01,
"learning_rate": 3.331920388531431e-05,
"loss": 3.5643,
"step": 1018880
},
{
"epoch": 1.01,
"learning_rate": 3.331083431660752e-05,
"loss": 3.5569,
"step": 1019392
},
{
"epoch": 1.01,
"learning_rate": 3.3302448369097e-05,
"loss": 3.5531,
"step": 1019904
},
{
"epoch": 1.01,
"learning_rate": 3.329406242158648e-05,
"loss": 3.5578,
"step": 1020416
},
{
"epoch": 1.01,
"learning_rate": 3.328567647407596e-05,
"loss": 3.567,
"step": 1020928
},
{
"epoch": 1.01,
"learning_rate": 3.3277306905369174e-05,
"loss": 3.5515,
"step": 1021440
},
{
"epoch": 1.01,
"learning_rate": 3.3268920957858654e-05,
"loss": 3.5742,
"step": 1021952
},
{
"epoch": 1.01,
"learning_rate": 3.3260535010348134e-05,
"loss": 3.5669,
"step": 1022464
},
{
"epoch": 1.01,
"learning_rate": 3.3252149062837614e-05,
"loss": 3.5456,
"step": 1022976
},
{
"epoch": 1.01,
"learning_rate": 3.324377949413082e-05,
"loss": 3.5754,
"step": 1023488
},
{
"epoch": 1.01,
"learning_rate": 3.32353935466203e-05,
"loss": 3.5541,
"step": 1024000
},
{
"epoch": 1.01,
"learning_rate": 3.322700759910978e-05,
"loss": 3.5544,
"step": 1024512
},
{
"epoch": 1.01,
"learning_rate": 3.321862165159926e-05,
"loss": 3.5552,
"step": 1025024
},
{
"epoch": 1.01,
"learning_rate": 3.321025208289247e-05,
"loss": 3.5682,
"step": 1025536
},
{
"epoch": 1.01,
"learning_rate": 3.320186613538195e-05,
"loss": 3.5492,
"step": 1026048
},
{
"epoch": 1.01,
"learning_rate": 3.319348018787143e-05,
"loss": 3.5641,
"step": 1026560
},
{
"epoch": 1.01,
"learning_rate": 3.318509424036091e-05,
"loss": 3.5454,
"step": 1027072
},
{
"epoch": 1.01,
"learning_rate": 3.317672467165413e-05,
"loss": 3.5543,
"step": 1027584
},
{
"epoch": 1.01,
"learning_rate": 3.316833872414361e-05,
"loss": 3.5701,
"step": 1028096
},
{
"epoch": 1.01,
"learning_rate": 3.315995277663309e-05,
"loss": 3.555,
"step": 1028608
},
{
"epoch": 1.01,
"learning_rate": 3.315156682912257e-05,
"loss": 3.5714,
"step": 1029120
},
{
"epoch": 1.01,
"learning_rate": 3.314318088161204e-05,
"loss": 3.5631,
"step": 1029632
},
{
"epoch": 1.01,
"learning_rate": 3.313481131290526e-05,
"loss": 3.5797,
"step": 1030144
},
{
"epoch": 1.01,
"learning_rate": 3.3126425365394737e-05,
"loss": 3.5521,
"step": 1030656
},
{
"epoch": 1.01,
"learning_rate": 3.311803941788421e-05,
"loss": 3.5704,
"step": 1031168
},
{
"epoch": 1.01,
"learning_rate": 3.310965347037369e-05,
"loss": 3.5579,
"step": 1031680
},
{
"epoch": 1.01,
"learning_rate": 3.3101283901666906e-05,
"loss": 3.5585,
"step": 1032192
},
{
"epoch": 1.01,
"learning_rate": 3.3092897954156386e-05,
"loss": 3.5655,
"step": 1032704
},
{
"epoch": 1.01,
"learning_rate": 3.3084512006645866e-05,
"loss": 3.5734,
"step": 1033216
},
{
"epoch": 1.01,
"learning_rate": 3.3076126059135345e-05,
"loss": 3.5618,
"step": 1033728
},
{
"epoch": 1.01,
"learning_rate": 3.306775649042856e-05,
"loss": 3.5721,
"step": 1034240
},
{
"epoch": 1.01,
"learning_rate": 3.305937054291804e-05,
"loss": 3.548,
"step": 1034752
},
{
"epoch": 1.01,
"learning_rate": 3.3050984595407514e-05,
"loss": 3.5469,
"step": 1035264
},
{
"epoch": 1.01,
"learning_rate": 3.3042598647896994e-05,
"loss": 3.5536,
"step": 1035776
},
{
"epoch": 1.01,
"learning_rate": 3.303422907919021e-05,
"loss": 3.5616,
"step": 1036288
},
{
"epoch": 1.01,
"learning_rate": 3.3025843131679683e-05,
"loss": 3.5599,
"step": 1036800
},
{
"epoch": 1.01,
"learning_rate": 3.3017457184169163e-05,
"loss": 3.5566,
"step": 1037312
},
{
"epoch": 1.01,
"learning_rate": 3.300907123665864e-05,
"loss": 3.5568,
"step": 1037824
},
{
"epoch": 1.02,
"learning_rate": 3.300070166795186e-05,
"loss": 3.5572,
"step": 1038336
},
{
"epoch": 1.02,
"learning_rate": 3.299231572044133e-05,
"loss": 3.5611,
"step": 1038848
},
{
"epoch": 1.02,
"learning_rate": 3.298392977293082e-05,
"loss": 3.5566,
"step": 1039360
},
{
"epoch": 1.02,
"learning_rate": 3.29755438254203e-05,
"loss": 3.5648,
"step": 1039872
},
{
"epoch": 1.02,
"learning_rate": 3.296717425671351e-05,
"loss": 3.5752,
"step": 1040384
},
{
"epoch": 1.02,
"learning_rate": 3.295878830920299e-05,
"loss": 3.5687,
"step": 1040896
},
{
"epoch": 1.02,
"learning_rate": 3.295040236169247e-05,
"loss": 3.5519,
"step": 1041408
},
{
"epoch": 1.02,
"learning_rate": 3.294201641418195e-05,
"loss": 3.5561,
"step": 1041920
},
{
"epoch": 1.02,
"learning_rate": 3.293364684547516e-05,
"loss": 3.5576,
"step": 1042432
},
{
"epoch": 1.02,
"learning_rate": 3.292526089796464e-05,
"loss": 3.5643,
"step": 1042944
},
{
"epoch": 1.02,
"learning_rate": 3.291687495045412e-05,
"loss": 3.5612,
"step": 1043456
},
{
"epoch": 1.02,
"learning_rate": 3.29084890029436e-05,
"loss": 3.559,
"step": 1043968
},
{
"epoch": 1.02,
"learning_rate": 3.2900119434236806e-05,
"loss": 3.5599,
"step": 1044480
},
{
"epoch": 1.02,
"learning_rate": 3.2891733486726286e-05,
"loss": 3.5655,
"step": 1044992
},
{
"epoch": 1.02,
"learning_rate": 3.288334753921577e-05,
"loss": 3.5591,
"step": 1045504
},
{
"epoch": 1.02,
"learning_rate": 3.287496159170525e-05,
"loss": 3.5602,
"step": 1046016
},
{
"epoch": 1.02,
"learning_rate": 3.286659202299846e-05,
"loss": 3.5535,
"step": 1046528
},
{
"epoch": 1.02,
"learning_rate": 3.285820607548794e-05,
"loss": 3.5516,
"step": 1047040
},
{
"epoch": 1.02,
"learning_rate": 3.284982012797742e-05,
"loss": 3.5579,
"step": 1047552
},
{
"epoch": 1.02,
"learning_rate": 3.28414341804669e-05,
"loss": 3.5503,
"step": 1048064
},
{
"epoch": 1.02,
"learning_rate": 3.283306461176011e-05,
"loss": 3.5528,
"step": 1048576
},
{
"epoch": 1.02,
"learning_rate": 3.282467866424959e-05,
"loss": 3.5546,
"step": 1049088
},
{
"epoch": 1.02,
"learning_rate": 3.281629271673907e-05,
"loss": 3.5609,
"step": 1049600
},
{
"epoch": 1.02,
"learning_rate": 3.280790676922855e-05,
"loss": 3.5547,
"step": 1050112
},
{
"epoch": 1.02,
"learning_rate": 3.279953720052176e-05,
"loss": 3.5625,
"step": 1050624
},
{
"epoch": 1.02,
"learning_rate": 3.279115125301124e-05,
"loss": 3.5714,
"step": 1051136
},
{
"epoch": 1.02,
"learning_rate": 3.2782765305500727e-05,
"loss": 3.5673,
"step": 1051648
},
{
"epoch": 1.02,
"learning_rate": 3.2774379357990206e-05,
"loss": 3.5672,
"step": 1052160
},
{
"epoch": 1.02,
"learning_rate": 3.2766009789283416e-05,
"loss": 3.5585,
"step": 1052672
},
{
"epoch": 1.02,
"learning_rate": 3.2757623841772896e-05,
"loss": 3.5593,
"step": 1053184
},
{
"epoch": 1.02,
"learning_rate": 3.2749237894262375e-05,
"loss": 3.5617,
"step": 1053696
},
{
"epoch": 1.02,
"learning_rate": 3.2740851946751855e-05,
"loss": 3.5446,
"step": 1054208
},
{
"epoch": 1.02,
"learning_rate": 3.2732465999241335e-05,
"loss": 3.5589,
"step": 1054720
},
{
"epoch": 1.02,
"learning_rate": 3.2724096430534544e-05,
"loss": 3.5527,
"step": 1055232
},
{
"epoch": 1.02,
"learning_rate": 3.2715710483024024e-05,
"loss": 3.5656,
"step": 1055744
},
{
"epoch": 1.02,
"learning_rate": 3.2707324535513504e-05,
"loss": 3.5592,
"step": 1056256
},
{
"epoch": 1.02,
"learning_rate": 3.2698938588002984e-05,
"loss": 3.5594,
"step": 1056768
},
{
"epoch": 1.02,
"learning_rate": 3.2690569019296193e-05,
"loss": 3.5528,
"step": 1057280
},
{
"epoch": 1.02,
"learning_rate": 3.268218307178568e-05,
"loss": 3.5539,
"step": 1057792
},
{
"epoch": 1.02,
"learning_rate": 3.267379712427516e-05,
"loss": 3.5643,
"step": 1058304
},
{
"epoch": 1.02,
"learning_rate": 3.266541117676464e-05,
"loss": 3.5624,
"step": 1058816
},
{
"epoch": 1.02,
"learning_rate": 3.265704160805785e-05,
"loss": 3.5674,
"step": 1059328
},
{
"epoch": 1.02,
"learning_rate": 3.264865566054733e-05,
"loss": 3.5544,
"step": 1059840
},
{
"epoch": 1.02,
"learning_rate": 3.264026971303681e-05,
"loss": 3.5669,
"step": 1060352
},
{
"epoch": 1.02,
"learning_rate": 3.263188376552629e-05,
"loss": 3.5585,
"step": 1060864
},
{
"epoch": 1.02,
"learning_rate": 3.26235141968195e-05,
"loss": 3.5606,
"step": 1061376
},
{
"epoch": 1.02,
"learning_rate": 3.261512824930898e-05,
"loss": 3.5654,
"step": 1061888
},
{
"epoch": 1.02,
"learning_rate": 3.260674230179846e-05,
"loss": 3.5592,
"step": 1062400
},
{
"epoch": 1.02,
"learning_rate": 3.259835635428794e-05,
"loss": 3.5583,
"step": 1062912
},
{
"epoch": 1.02,
"learning_rate": 3.258998678558115e-05,
"loss": 3.5697,
"step": 1063424
},
{
"epoch": 1.02,
"learning_rate": 3.2581600838070634e-05,
"loss": 3.5541,
"step": 1063936
},
{
"epoch": 1.02,
"learning_rate": 3.2573214890560114e-05,
"loss": 3.553,
"step": 1064448
},
{
"epoch": 1.02,
"learning_rate": 3.2564828943049594e-05,
"loss": 3.5648,
"step": 1064960
},
{
"epoch": 1.02,
"learning_rate": 3.25564593743428e-05,
"loss": 3.5618,
"step": 1065472
},
{
"epoch": 1.02,
"learning_rate": 3.254807342683228e-05,
"loss": 3.5568,
"step": 1065984
},
{
"epoch": 1.02,
"learning_rate": 3.253968747932176e-05,
"loss": 3.5599,
"step": 1066496
},
{
"epoch": 1.02,
"learning_rate": 3.253130153181124e-05,
"loss": 3.5544,
"step": 1067008
},
{
"epoch": 1.02,
"learning_rate": 3.252293196310445e-05,
"loss": 3.5713,
"step": 1067520
},
{
"epoch": 1.02,
"learning_rate": 3.251454601559393e-05,
"loss": 3.5586,
"step": 1068032
},
{
"epoch": 1.03,
"eval_loss": 3.841827869415283,
"eval_runtime": 320.5974,
"eval_samples_per_second": 1190.25,
"eval_steps_per_second": 37.196,
"step": 1068480
},
{
"epoch": 0.0,
"learning_rate": 3.250616006808341e-05,
"loss": 3.5427,
"step": 1068544
},
{
"epoch": 0.0,
"learning_rate": 3.249777412057289e-05,
"loss": 3.5467,
"step": 1069056
},
{
"epoch": 0.0,
"learning_rate": 3.248938817306237e-05,
"loss": 3.5534,
"step": 1069568
},
{
"epoch": 0.0,
"learning_rate": 3.248100222555185e-05,
"loss": 3.5715,
"step": 1070080
},
{
"epoch": 0.0,
"learning_rate": 3.247263265684507e-05,
"loss": 3.5635,
"step": 1070592
},
{
"epoch": 0.0,
"learning_rate": 3.246424670933455e-05,
"loss": 3.5555,
"step": 1071104
},
{
"epoch": 0.0,
"learning_rate": 3.245586076182403e-05,
"loss": 3.5544,
"step": 1071616
},
{
"epoch": 0.0,
"learning_rate": 3.244747481431351e-05,
"loss": 3.5564,
"step": 1072128
},
{
"epoch": 0.0,
"learning_rate": 3.2439105245606716e-05,
"loss": 3.5444,
"step": 1072640
},
{
"epoch": 0.0,
"learning_rate": 3.2430719298096196e-05,
"loss": 3.558,
"step": 1073152
},
{
"epoch": 0.0,
"learning_rate": 3.2422333350585676e-05,
"loss": 3.5567,
"step": 1073664
},
{
"epoch": 0.0,
"learning_rate": 3.2413947403075156e-05,
"loss": 3.5694,
"step": 1074176
},
{
"epoch": 0.0,
"learning_rate": 3.2405577834368365e-05,
"loss": 3.5641,
"step": 1074688
},
{
"epoch": 0.0,
"learning_rate": 3.2397191886857845e-05,
"loss": 3.5351,
"step": 1075200
},
{
"epoch": 0.0,
"learning_rate": 3.2388805939347325e-05,
"loss": 3.5533,
"step": 1075712
},
{
"epoch": 0.0,
"learning_rate": 3.2380419991836805e-05,
"loss": 3.5413,
"step": 1076224
},
{
"epoch": 0.0,
"learning_rate": 3.2372034044326285e-05,
"loss": 3.5544,
"step": 1076736
},
{
"epoch": 0.0,
"learning_rate": 3.23636644756195e-05,
"loss": 3.5505,
"step": 1077248
},
{
"epoch": 0.0,
"learning_rate": 3.235527852810898e-05,
"loss": 3.5547,
"step": 1077760
},
{
"epoch": 0.0,
"learning_rate": 3.234689258059846e-05,
"loss": 3.5482,
"step": 1078272
},
{
"epoch": 0.0,
"learning_rate": 3.233852301189167e-05,
"loss": 3.5657,
"step": 1078784
},
{
"epoch": 0.0,
"learning_rate": 3.233013706438115e-05,
"loss": 3.5544,
"step": 1079296
},
{
"epoch": 0.0,
"learning_rate": 3.232175111687063e-05,
"loss": 3.5565,
"step": 1079808
},
{
"epoch": 0.0,
"learning_rate": 3.231336516936011e-05,
"loss": 3.5487,
"step": 1080320
},
{
"epoch": 0.0,
"learning_rate": 3.230499560065332e-05,
"loss": 3.5648,
"step": 1080832
},
{
"epoch": 0.0,
"learning_rate": 3.22966096531428e-05,
"loss": 3.5511,
"step": 1081344
},
{
"epoch": 0.0,
"learning_rate": 3.228822370563228e-05,
"loss": 3.5483,
"step": 1081856
},
{
"epoch": 0.0,
"learning_rate": 3.227983775812176e-05,
"loss": 3.5524,
"step": 1082368
},
{
"epoch": 0.0,
"learning_rate": 3.227145181061124e-05,
"loss": 3.5503,
"step": 1082880
},
{
"epoch": 0.0,
"learning_rate": 3.2263082241904455e-05,
"loss": 3.543,
"step": 1083392
},
{
"epoch": 0.01,
"learning_rate": 3.2254696294393935e-05,
"loss": 3.5524,
"step": 1083904
},
{
"epoch": 0.01,
"learning_rate": 3.2246310346883415e-05,
"loss": 3.5499,
"step": 1084416
},
{
"epoch": 0.01,
"learning_rate": 3.223792439937289e-05,
"loss": 3.5584,
"step": 1084928
},
{
"epoch": 0.01,
"learning_rate": 3.2229554830666104e-05,
"loss": 3.5566,
"step": 1085440
},
{
"epoch": 0.01,
"learning_rate": 3.2221168883155584e-05,
"loss": 3.5529,
"step": 1085952
},
{
"epoch": 0.01,
"learning_rate": 3.221278293564506e-05,
"loss": 3.555,
"step": 1086464
},
{
"epoch": 0.01,
"learning_rate": 3.220439698813454e-05,
"loss": 3.5563,
"step": 1086976
},
{
"epoch": 0.01,
"learning_rate": 3.219602741942775e-05,
"loss": 3.542,
"step": 1087488
},
{
"epoch": 0.01,
"learning_rate": 3.218764147191723e-05,
"loss": 3.5492,
"step": 1088000
},
{
"epoch": 0.01,
"learning_rate": 3.217925552440671e-05,
"loss": 3.5481,
"step": 1088512
},
{
"epoch": 0.01,
"learning_rate": 3.217086957689619e-05,
"loss": 3.5379,
"step": 1089024
},
{
"epoch": 0.01,
"learning_rate": 3.216250000818941e-05,
"loss": 3.5503,
"step": 1089536
},
{
"epoch": 0.01,
"learning_rate": 3.215411406067889e-05,
"loss": 3.5563,
"step": 1090048
},
{
"epoch": 0.01,
"learning_rate": 3.214572811316836e-05,
"loss": 3.5452,
"step": 1090560
},
{
"epoch": 0.01,
"learning_rate": 3.213734216565784e-05,
"loss": 3.5535,
"step": 1091072
},
{
"epoch": 0.01,
"learning_rate": 3.212897259695106e-05,
"loss": 3.5551,
"step": 1091584
},
{
"epoch": 0.01,
"learning_rate": 3.212058664944053e-05,
"loss": 3.5575,
"step": 1092096
},
{
"epoch": 0.01,
"learning_rate": 3.211220070193001e-05,
"loss": 3.553,
"step": 1092608
},
{
"epoch": 0.01,
"learning_rate": 3.210381475441949e-05,
"loss": 3.5338,
"step": 1093120
},
{
"epoch": 0.01,
"learning_rate": 3.2095445185712706e-05,
"loss": 3.5532,
"step": 1093632
},
{
"epoch": 0.01,
"learning_rate": 3.208705923820218e-05,
"loss": 3.5502,
"step": 1094144
},
{
"epoch": 0.01,
"learning_rate": 3.2078673290691666e-05,
"loss": 3.5571,
"step": 1094656
},
{
"epoch": 0.01,
"learning_rate": 3.2070287343181146e-05,
"loss": 3.5442,
"step": 1095168
},
{
"epoch": 0.01,
"learning_rate": 3.206191777447436e-05,
"loss": 3.5439,
"step": 1095680
},
{
"epoch": 0.01,
"learning_rate": 3.2053531826963835e-05,
"loss": 3.5386,
"step": 1096192
},
{
"epoch": 0.01,
"learning_rate": 3.2045145879453315e-05,
"loss": 3.539,
"step": 1096704
},
{
"epoch": 0.01,
"learning_rate": 3.2036759931942795e-05,
"loss": 3.551,
"step": 1097216
},
{
"epoch": 0.01,
"learning_rate": 3.2028390363236004e-05,
"loss": 3.5323,
"step": 1097728
},
{
"epoch": 0.01,
"learning_rate": 3.2020004415725484e-05,
"loss": 3.5605,
"step": 1098240
},
{
"epoch": 0.01,
"learning_rate": 3.2011618468214964e-05,
"loss": 3.5518,
"step": 1098752
},
{
"epoch": 0.01,
"learning_rate": 3.2003232520704444e-05,
"loss": 3.5311,
"step": 1099264
},
{
"epoch": 0.01,
"learning_rate": 3.199486295199765e-05,
"loss": 3.5618,
"step": 1099776
},
{
"epoch": 0.01,
"learning_rate": 3.198647700448713e-05,
"loss": 3.5375,
"step": 1100288
},
{
"epoch": 0.01,
"learning_rate": 3.197809105697662e-05,
"loss": 3.5428,
"step": 1100800
},
{
"epoch": 0.01,
"learning_rate": 3.19697051094661e-05,
"loss": 3.5366,
"step": 1101312
},
{
"epoch": 0.01,
"learning_rate": 3.196133554075931e-05,
"loss": 3.5508,
"step": 1101824
},
{
"epoch": 0.01,
"learning_rate": 3.195294959324879e-05,
"loss": 3.5354,
"step": 1102336
},
{
"epoch": 0.01,
"learning_rate": 3.194456364573827e-05,
"loss": 3.5491,
"step": 1102848
},
{
"epoch": 0.01,
"learning_rate": 3.193617769822775e-05,
"loss": 3.5273,
"step": 1103360
},
{
"epoch": 0.01,
"learning_rate": 3.192780812952096e-05,
"loss": 3.5406,
"step": 1103872
},
{
"epoch": 0.01,
"learning_rate": 3.191942218201044e-05,
"loss": 3.5518,
"step": 1104384
},
{
"epoch": 0.01,
"learning_rate": 3.191103623449992e-05,
"loss": 3.5431,
"step": 1104896
},
{
"epoch": 0.01,
"learning_rate": 3.19026502869894e-05,
"loss": 3.5531,
"step": 1105408
},
{
"epoch": 0.01,
"learning_rate": 3.189428071828261e-05,
"loss": 3.5478,
"step": 1105920
},
{
"epoch": 0.01,
"learning_rate": 3.188589477077209e-05,
"loss": 3.5625,
"step": 1106432
},
{
"epoch": 0.01,
"learning_rate": 3.1877508823261574e-05,
"loss": 3.5402,
"step": 1106944
},
{
"epoch": 0.01,
"learning_rate": 3.1869122875751054e-05,
"loss": 3.5578,
"step": 1107456
},
{
"epoch": 0.01,
"learning_rate": 3.186075330704426e-05,
"loss": 3.5405,
"step": 1107968
},
{
"epoch": 0.01,
"learning_rate": 3.185236735953374e-05,
"loss": 3.5413,
"step": 1108480
},
{
"epoch": 0.01,
"learning_rate": 3.184398141202322e-05,
"loss": 3.5484,
"step": 1108992
},
{
"epoch": 0.01,
"learning_rate": 3.18355954645127e-05,
"loss": 3.5539,
"step": 1109504
},
{
"epoch": 0.01,
"learning_rate": 3.182722589580591e-05,
"loss": 3.5482,
"step": 1110016
},
{
"epoch": 0.01,
"learning_rate": 3.181883994829539e-05,
"loss": 3.5539,
"step": 1110528
},
{
"epoch": 0.01,
"learning_rate": 3.181045400078487e-05,
"loss": 3.5366,
"step": 1111040
},
{
"epoch": 0.01,
"learning_rate": 3.180206805327435e-05,
"loss": 3.529,
"step": 1111552
},
{
"epoch": 0.01,
"learning_rate": 3.179369848456756e-05,
"loss": 3.5397,
"step": 1112064
},
{
"epoch": 0.01,
"learning_rate": 3.178531253705704e-05,
"loss": 3.5474,
"step": 1112576
},
{
"epoch": 0.01,
"learning_rate": 3.177692658954653e-05,
"loss": 3.5431,
"step": 1113088
},
{
"epoch": 0.01,
"learning_rate": 3.176854064203601e-05,
"loss": 3.54,
"step": 1113600
},
{
"epoch": 0.01,
"learning_rate": 3.1760171073329216e-05,
"loss": 3.5438,
"step": 1114112
},
{
"epoch": 0.02,
"learning_rate": 3.1751801504622425e-05,
"loss": 3.541,
"step": 1114624
},
{
"epoch": 0.02,
"learning_rate": 3.1743415557111905e-05,
"loss": 3.5451,
"step": 1115136
},
{
"epoch": 0.02,
"learning_rate": 3.1735029609601385e-05,
"loss": 3.5401,
"step": 1115648
},
{
"epoch": 0.02,
"learning_rate": 3.1726643662090865e-05,
"loss": 3.5504,
"step": 1116160
},
{
"epoch": 0.02,
"learning_rate": 3.1718257714580345e-05,
"loss": 3.5589,
"step": 1116672
},
{
"epoch": 0.02,
"learning_rate": 3.1709871767069825e-05,
"loss": 3.5549,
"step": 1117184
},
{
"epoch": 0.02,
"learning_rate": 3.1701485819559305e-05,
"loss": 3.5338,
"step": 1117696
},
{
"epoch": 0.02,
"learning_rate": 3.1693116250852514e-05,
"loss": 3.5428,
"step": 1118208
},
{
"epoch": 0.02,
"learning_rate": 3.1684730303341994e-05,
"loss": 3.5438,
"step": 1118720
},
{
"epoch": 0.02,
"learning_rate": 3.167634435583148e-05,
"loss": 3.5481,
"step": 1119232
},
{
"epoch": 0.02,
"learning_rate": 3.166795840832096e-05,
"loss": 3.5462,
"step": 1119744
},
{
"epoch": 0.02,
"learning_rate": 3.165958883961417e-05,
"loss": 3.5416,
"step": 1120256
},
{
"epoch": 0.02,
"learning_rate": 3.165120289210365e-05,
"loss": 3.5437,
"step": 1120768
},
{
"epoch": 0.02,
"learning_rate": 3.164281694459313e-05,
"loss": 3.5459,
"step": 1121280
},
{
"epoch": 0.02,
"learning_rate": 3.163443099708261e-05,
"loss": 3.5468,
"step": 1121792
},
{
"epoch": 0.02,
"learning_rate": 3.162606142837582e-05,
"loss": 3.5407,
"step": 1122304
},
{
"epoch": 0.02,
"learning_rate": 3.16176754808653e-05,
"loss": 3.5441,
"step": 1122816
},
{
"epoch": 0.02,
"learning_rate": 3.160928953335478e-05,
"loss": 3.5333,
"step": 1123328
},
{
"epoch": 0.02,
"learning_rate": 3.160090358584426e-05,
"loss": 3.5431,
"step": 1123840
},
{
"epoch": 0.02,
"learning_rate": 3.159251763833374e-05,
"loss": 3.5336,
"step": 1124352
},
{
"epoch": 0.02,
"learning_rate": 3.158414806962695e-05,
"loss": 3.5391,
"step": 1124864
},
{
"epoch": 0.02,
"learning_rate": 3.1575762122116435e-05,
"loss": 3.5389,
"step": 1125376
},
{
"epoch": 0.02,
"learning_rate": 3.1567376174605915e-05,
"loss": 3.5478,
"step": 1125888
},
{
"epoch": 0.02,
"learning_rate": 3.1558990227095394e-05,
"loss": 3.5374,
"step": 1126400
},
{
"epoch": 0.02,
"learning_rate": 3.1550620658388604e-05,
"loss": 3.5451,
"step": 1126912
},
{
"epoch": 0.02,
"learning_rate": 3.1542234710878084e-05,
"loss": 3.5557,
"step": 1127424
},
{
"epoch": 0.02,
"learning_rate": 3.1533848763367564e-05,
"loss": 3.5535,
"step": 1127936
},
{
"epoch": 0.02,
"learning_rate": 3.1525462815857043e-05,
"loss": 3.5522,
"step": 1128448
},
{
"epoch": 0.02,
"learning_rate": 3.151709324715025e-05,
"loss": 3.5452,
"step": 1128960
},
{
"epoch": 0.02,
"learning_rate": 3.150870729963973e-05,
"loss": 3.5446,
"step": 1129472
},
{
"epoch": 0.02,
"learning_rate": 3.150032135212921e-05,
"loss": 3.5424,
"step": 1129984
},
{
"epoch": 0.02,
"learning_rate": 3.149195178342242e-05,
"loss": 3.5285,
"step": 1130496
},
{
"epoch": 0.02,
"learning_rate": 3.14835658359119e-05,
"loss": 3.5447,
"step": 1131008
},
{
"epoch": 0.02,
"learning_rate": 3.147517988840139e-05,
"loss": 3.5383,
"step": 1131520
},
{
"epoch": 0.02,
"learning_rate": 3.146679394089087e-05,
"loss": 3.5515,
"step": 1132032
},
{
"epoch": 0.02,
"learning_rate": 3.145842437218408e-05,
"loss": 3.5398,
"step": 1132544
},
{
"epoch": 0.02,
"learning_rate": 3.145003842467356e-05,
"loss": 3.5444,
"step": 1133056
},
{
"epoch": 0.02,
"learning_rate": 3.144165247716304e-05,
"loss": 3.5392,
"step": 1133568
},
{
"epoch": 0.02,
"learning_rate": 3.143326652965252e-05,
"loss": 3.5394,
"step": 1134080
},
{
"epoch": 0.02,
"learning_rate": 3.1424880582142e-05,
"loss": 3.5498,
"step": 1134592
},
{
"epoch": 0.02,
"learning_rate": 3.1416511013435206e-05,
"loss": 3.5449,
"step": 1135104
},
{
"epoch": 0.02,
"learning_rate": 3.1408125065924686e-05,
"loss": 3.5556,
"step": 1135616
},
{
"epoch": 0.02,
"learning_rate": 3.1399739118414166e-05,
"loss": 3.5405,
"step": 1136128
},
{
"epoch": 0.02,
"learning_rate": 3.1391353170903646e-05,
"loss": 3.5501,
"step": 1136640
},
{
"epoch": 0.02,
"learning_rate": 3.1382983602196855e-05,
"loss": 3.5472,
"step": 1137152
},
{
"epoch": 0.02,
"learning_rate": 3.1374597654686335e-05,
"loss": 3.5465,
"step": 1137664
},
{
"epoch": 0.02,
"learning_rate": 3.136621170717582e-05,
"loss": 3.5443,
"step": 1138176
},
{
"epoch": 0.02,
"learning_rate": 3.13578257596653e-05,
"loss": 3.5422,
"step": 1138688
},
{
"epoch": 0.02,
"learning_rate": 3.134945619095851e-05,
"loss": 3.5493,
"step": 1139200
},
{
"epoch": 0.02,
"learning_rate": 3.134107024344799e-05,
"loss": 3.5531,
"step": 1139712
},
{
"epoch": 0.02,
"learning_rate": 3.133268429593747e-05,
"loss": 3.5392,
"step": 1140224
},
{
"epoch": 0.02,
"learning_rate": 3.132429834842695e-05,
"loss": 3.5368,
"step": 1140736
},
{
"epoch": 0.02,
"learning_rate": 3.131592877972016e-05,
"loss": 3.545,
"step": 1141248
},
{
"epoch": 0.02,
"learning_rate": 3.130754283220964e-05,
"loss": 3.5451,
"step": 1141760
},
{
"epoch": 0.02,
"learning_rate": 3.129915688469912e-05,
"loss": 3.5427,
"step": 1142272
},
{
"epoch": 0.02,
"learning_rate": 3.12907709371886e-05,
"loss": 3.5444,
"step": 1142784
},
{
"epoch": 0.02,
"learning_rate": 3.128240136848181e-05,
"loss": 3.5404,
"step": 1143296
},
{
"epoch": 0.02,
"learning_rate": 3.127401542097129e-05,
"loss": 3.5586,
"step": 1143808
},
{
"epoch": 0.02,
"learning_rate": 3.1265629473460776e-05,
"loss": 3.5407,
"step": 1144320
},
{
"epoch": 0.03,
"eval_loss": 3.8439102172851562,
"eval_runtime": 331.9381,
"eval_samples_per_second": 1149.585,
"eval_steps_per_second": 35.925,
"step": 1144800
},
{
"epoch": 1.0,
"learning_rate": 3.1257243525950256e-05,
"loss": 3.536,
"step": 1144832
},
{
"epoch": 1.0,
"learning_rate": 3.1248873957243465e-05,
"loss": 3.5329,
"step": 1145344
},
{
"epoch": 1.0,
"learning_rate": 3.1240488009732945e-05,
"loss": 3.5354,
"step": 1145856
},
{
"epoch": 1.0,
"learning_rate": 3.1232102062222425e-05,
"loss": 3.556,
"step": 1146368
},
{
"epoch": 1.0,
"learning_rate": 3.1223716114711904e-05,
"loss": 3.546,
"step": 1146880
},
{
"epoch": 1.0,
"learning_rate": 3.1215346546005114e-05,
"loss": 3.5442,
"step": 1147392
},
{
"epoch": 1.0,
"learning_rate": 3.1206960598494594e-05,
"loss": 3.5387,
"step": 1147904
},
{
"epoch": 1.0,
"learning_rate": 3.1198574650984073e-05,
"loss": 3.5392,
"step": 1148416
},
{
"epoch": 1.0,
"learning_rate": 3.1190188703473553e-05,
"loss": 3.5317,
"step": 1148928
},
{
"epoch": 1.0,
"learning_rate": 3.118181913476676e-05,
"loss": 3.5418,
"step": 1149440
},
{
"epoch": 1.0,
"learning_rate": 3.117343318725624e-05,
"loss": 3.541,
"step": 1149952
},
{
"epoch": 1.0,
"learning_rate": 3.116506361854946e-05,
"loss": 3.5532,
"step": 1150464
},
{
"epoch": 1.0,
"learning_rate": 3.115667767103894e-05,
"loss": 3.5484,
"step": 1150976
},
{
"epoch": 1.0,
"learning_rate": 3.114829172352842e-05,
"loss": 3.5212,
"step": 1151488
},
{
"epoch": 1.0,
"learning_rate": 3.11399057760179e-05,
"loss": 3.5371,
"step": 1152000
},
{
"epoch": 1.0,
"learning_rate": 3.113151982850738e-05,
"loss": 3.5282,
"step": 1152512
},
{
"epoch": 1.0,
"learning_rate": 3.112313388099686e-05,
"loss": 3.5373,
"step": 1153024
},
{
"epoch": 1.0,
"learning_rate": 3.111474793348633e-05,
"loss": 3.5357,
"step": 1153536
},
{
"epoch": 1.0,
"learning_rate": 3.110636198597581e-05,
"loss": 3.5395,
"step": 1154048
},
{
"epoch": 1.0,
"learning_rate": 3.109799241726903e-05,
"loss": 3.5321,
"step": 1154560
},
{
"epoch": 1.0,
"learning_rate": 3.10896064697585e-05,
"loss": 3.5519,
"step": 1155072
},
{
"epoch": 1.0,
"learning_rate": 3.108122052224798e-05,
"loss": 3.5422,
"step": 1155584
},
{
"epoch": 1.0,
"learning_rate": 3.107283457473747e-05,
"loss": 3.5356,
"step": 1156096
},
{
"epoch": 1.0,
"learning_rate": 3.106446500603068e-05,
"loss": 3.5333,
"step": 1156608
},
{
"epoch": 1.0,
"learning_rate": 3.1056079058520156e-05,
"loss": 3.548,
"step": 1157120
},
{
"epoch": 1.0,
"learning_rate": 3.1047693111009636e-05,
"loss": 3.5358,
"step": 1157632
},
{
"epoch": 1.0,
"learning_rate": 3.1039307163499116e-05,
"loss": 3.5309,
"step": 1158144
},
{
"epoch": 1.0,
"learning_rate": 3.1030937594792325e-05,
"loss": 3.5412,
"step": 1158656
},
{
"epoch": 1.0,
"learning_rate": 3.1022551647281805e-05,
"loss": 3.5309,
"step": 1159168
},
{
"epoch": 1.0,
"learning_rate": 3.1014165699771285e-05,
"loss": 3.5305,
"step": 1159680
},
{
"epoch": 1.01,
"learning_rate": 3.1005779752260765e-05,
"loss": 3.5356,
"step": 1160192
},
{
"epoch": 1.01,
"learning_rate": 3.0997410183553974e-05,
"loss": 3.5353,
"step": 1160704
},
{
"epoch": 1.01,
"learning_rate": 3.0989024236043454e-05,
"loss": 3.541,
"step": 1161216
},
{
"epoch": 1.01,
"learning_rate": 3.0980638288532934e-05,
"loss": 3.5389,
"step": 1161728
},
{
"epoch": 1.01,
"learning_rate": 3.097225234102242e-05,
"loss": 3.5415,
"step": 1162240
},
{
"epoch": 1.01,
"learning_rate": 3.096388277231563e-05,
"loss": 3.5371,
"step": 1162752
},
{
"epoch": 1.01,
"learning_rate": 3.095549682480511e-05,
"loss": 3.5408,
"step": 1163264
},
{
"epoch": 1.01,
"learning_rate": 3.094711087729459e-05,
"loss": 3.5261,
"step": 1163776
},
{
"epoch": 1.01,
"learning_rate": 3.093872492978407e-05,
"loss": 3.537,
"step": 1164288
},
{
"epoch": 1.01,
"learning_rate": 3.093035536107728e-05,
"loss": 3.5317,
"step": 1164800
},
{
"epoch": 1.01,
"learning_rate": 3.092196941356676e-05,
"loss": 3.5296,
"step": 1165312
},
{
"epoch": 1.01,
"learning_rate": 3.091358346605624e-05,
"loss": 3.5319,
"step": 1165824
},
{
"epoch": 1.01,
"learning_rate": 3.090519751854572e-05,
"loss": 3.5411,
"step": 1166336
},
{
"epoch": 1.01,
"learning_rate": 3.089682794983893e-05,
"loss": 3.5296,
"step": 1166848
},
{
"epoch": 1.01,
"learning_rate": 3.088844200232841e-05,
"loss": 3.539,
"step": 1167360
},
{
"epoch": 1.01,
"learning_rate": 3.088005605481789e-05,
"loss": 3.5399,
"step": 1167872
},
{
"epoch": 1.01,
"learning_rate": 3.0871670107307374e-05,
"loss": 3.5425,
"step": 1168384
},
{
"epoch": 1.01,
"learning_rate": 3.0863300538600583e-05,
"loss": 3.5383,
"step": 1168896
},
{
"epoch": 1.01,
"learning_rate": 3.0854914591090063e-05,
"loss": 3.5183,
"step": 1169408
},
{
"epoch": 1.01,
"learning_rate": 3.084654502238327e-05,
"loss": 3.5352,
"step": 1169920
},
{
"epoch": 1.01,
"learning_rate": 3.083815907487275e-05,
"loss": 3.5386,
"step": 1170432
},
{
"epoch": 1.01,
"learning_rate": 3.082977312736223e-05,
"loss": 3.5401,
"step": 1170944
},
{
"epoch": 1.01,
"learning_rate": 3.082138717985171e-05,
"loss": 3.5286,
"step": 1171456
},
{
"epoch": 1.01,
"learning_rate": 3.081300123234119e-05,
"loss": 3.5281,
"step": 1171968
},
{
"epoch": 1.01,
"learning_rate": 3.080461528483067e-05,
"loss": 3.5236,
"step": 1172480
},
{
"epoch": 1.01,
"learning_rate": 3.079622933732015e-05,
"loss": 3.5193,
"step": 1172992
},
{
"epoch": 1.01,
"learning_rate": 3.078784338980963e-05,
"loss": 3.5377,
"step": 1173504
},
{
"epoch": 1.01,
"learning_rate": 3.077947382110284e-05,
"loss": 3.5209,
"step": 1174016
},
{
"epoch": 1.01,
"learning_rate": 3.077108787359233e-05,
"loss": 3.5423,
"step": 1174528
},
{
"epoch": 1.01,
"learning_rate": 3.076270192608181e-05,
"loss": 3.5332,
"step": 1175040
},
{
"epoch": 1.01,
"learning_rate": 3.075431597857129e-05,
"loss": 3.5223,
"step": 1175552
},
{
"epoch": 1.01,
"learning_rate": 3.07459464098645e-05,
"loss": 3.5434,
"step": 1176064
},
{
"epoch": 1.01,
"learning_rate": 3.073756046235398e-05,
"loss": 3.521,
"step": 1176576
},
{
"epoch": 1.01,
"learning_rate": 3.072917451484346e-05,
"loss": 3.5265,
"step": 1177088
},
{
"epoch": 1.01,
"learning_rate": 3.072078856733294e-05,
"loss": 3.5209,
"step": 1177600
},
{
"epoch": 1.01,
"learning_rate": 3.0712418998626146e-05,
"loss": 3.5388,
"step": 1178112
},
{
"epoch": 1.01,
"learning_rate": 3.0704033051115626e-05,
"loss": 3.519,
"step": 1178624
},
{
"epoch": 1.01,
"learning_rate": 3.0695647103605106e-05,
"loss": 3.532,
"step": 1179136
},
{
"epoch": 1.01,
"learning_rate": 3.0687261156094586e-05,
"loss": 3.5118,
"step": 1179648
},
{
"epoch": 1.01,
"learning_rate": 3.0678891587387795e-05,
"loss": 3.5238,
"step": 1180160
},
{
"epoch": 1.01,
"learning_rate": 3.067050563987728e-05,
"loss": 3.5384,
"step": 1180672
},
{
"epoch": 1.01,
"learning_rate": 3.066211969236676e-05,
"loss": 3.5311,
"step": 1181184
},
{
"epoch": 1.01,
"learning_rate": 3.065373374485624e-05,
"loss": 3.5345,
"step": 1181696
},
{
"epoch": 1.01,
"learning_rate": 3.064536417614945e-05,
"loss": 3.5351,
"step": 1182208
},
{
"epoch": 1.01,
"learning_rate": 3.063697822863893e-05,
"loss": 3.5444,
"step": 1182720
},
{
"epoch": 1.01,
"learning_rate": 3.062859228112841e-05,
"loss": 3.5282,
"step": 1183232
},
{
"epoch": 1.01,
"learning_rate": 3.062020633361789e-05,
"loss": 3.5423,
"step": 1183744
},
{
"epoch": 1.01,
"learning_rate": 3.06118367649111e-05,
"loss": 3.5242,
"step": 1184256
},
{
"epoch": 1.01,
"learning_rate": 3.060345081740058e-05,
"loss": 3.5265,
"step": 1184768
},
{
"epoch": 1.01,
"learning_rate": 3.059506486989006e-05,
"loss": 3.5331,
"step": 1185280
},
{
"epoch": 1.01,
"learning_rate": 3.058667892237954e-05,
"loss": 3.5395,
"step": 1185792
},
{
"epoch": 1.01,
"learning_rate": 3.057830935367275e-05,
"loss": 3.5332,
"step": 1186304
},
{
"epoch": 1.01,
"learning_rate": 3.056992340616223e-05,
"loss": 3.5419,
"step": 1186816
},
{
"epoch": 1.01,
"learning_rate": 3.0561537458651715e-05,
"loss": 3.5238,
"step": 1187328
},
{
"epoch": 1.01,
"learning_rate": 3.0553151511141195e-05,
"loss": 3.5133,
"step": 1187840
},
{
"epoch": 1.01,
"learning_rate": 3.0544781942434404e-05,
"loss": 3.5225,
"step": 1188352
},
{
"epoch": 1.01,
"learning_rate": 3.0536395994923884e-05,
"loss": 3.5338,
"step": 1188864
},
{
"epoch": 1.01,
"learning_rate": 3.0528010047413364e-05,
"loss": 3.5256,
"step": 1189376
},
{
"epoch": 1.01,
"learning_rate": 3.0519624099902844e-05,
"loss": 3.5265,
"step": 1189888
},
{
"epoch": 1.01,
"learning_rate": 3.0511254531196053e-05,
"loss": 3.53,
"step": 1190400
},
{
"epoch": 1.02,
"learning_rate": 3.0502868583685533e-05,
"loss": 3.5258,
"step": 1190912
},
{
"epoch": 1.02,
"learning_rate": 3.0494482636175013e-05,
"loss": 3.5264,
"step": 1191424
},
{
"epoch": 1.02,
"learning_rate": 3.0486096688664497e-05,
"loss": 3.5267,
"step": 1191936
},
{
"epoch": 1.02,
"learning_rate": 3.0477727119957706e-05,
"loss": 3.5378,
"step": 1192448
},
{
"epoch": 1.02,
"learning_rate": 3.0469341172447186e-05,
"loss": 3.5419,
"step": 1192960
},
{
"epoch": 1.02,
"learning_rate": 3.0460955224936666e-05,
"loss": 3.5365,
"step": 1193472
},
{
"epoch": 1.02,
"learning_rate": 3.0452569277426146e-05,
"loss": 3.5198,
"step": 1193984
},
{
"epoch": 1.02,
"learning_rate": 3.0444199708719358e-05,
"loss": 3.53,
"step": 1194496
},
{
"epoch": 1.02,
"learning_rate": 3.0435813761208838e-05,
"loss": 3.5259,
"step": 1195008
},
{
"epoch": 1.02,
"learning_rate": 3.0427427813698318e-05,
"loss": 3.5344,
"step": 1195520
},
{
"epoch": 1.02,
"learning_rate": 3.0419041866187798e-05,
"loss": 3.5325,
"step": 1196032
},
{
"epoch": 1.02,
"learning_rate": 3.0410672297481007e-05,
"loss": 3.5262,
"step": 1196544
},
{
"epoch": 1.02,
"learning_rate": 3.0402286349970487e-05,
"loss": 3.5283,
"step": 1197056
},
{
"epoch": 1.02,
"learning_rate": 3.0393900402459967e-05,
"loss": 3.5362,
"step": 1197568
},
{
"epoch": 1.02,
"learning_rate": 3.038551445494945e-05,
"loss": 3.5325,
"step": 1198080
},
{
"epoch": 1.02,
"learning_rate": 3.037714488624266e-05,
"loss": 3.5269,
"step": 1198592
},
{
"epoch": 1.02,
"learning_rate": 3.036875893873214e-05,
"loss": 3.5278,
"step": 1199104
},
{
"epoch": 1.02,
"learning_rate": 3.036037299122162e-05,
"loss": 3.52,
"step": 1199616
},
{
"epoch": 1.02,
"learning_rate": 3.03519870437111e-05,
"loss": 3.5251,
"step": 1200128
},
{
"epoch": 1.02,
"learning_rate": 3.034361747500431e-05,
"loss": 3.5189,
"step": 1200640
},
{
"epoch": 1.02,
"learning_rate": 3.033523152749379e-05,
"loss": 3.5255,
"step": 1201152
},
{
"epoch": 1.02,
"learning_rate": 3.032684557998327e-05,
"loss": 3.5216,
"step": 1201664
},
{
"epoch": 1.02,
"learning_rate": 3.031845963247275e-05,
"loss": 3.5338,
"step": 1202176
},
{
"epoch": 1.02,
"learning_rate": 3.031009006376596e-05,
"loss": 3.5275,
"step": 1202688
},
{
"epoch": 1.02,
"learning_rate": 3.030170411625544e-05,
"loss": 3.5252,
"step": 1203200
},
{
"epoch": 1.02,
"learning_rate": 3.029331816874492e-05,
"loss": 3.5446,
"step": 1203712
},
{
"epoch": 1.02,
"learning_rate": 3.0284932221234404e-05,
"loss": 3.54,
"step": 1204224
},
{
"epoch": 1.02,
"learning_rate": 3.0276562652527613e-05,
"loss": 3.5355,
"step": 1204736
},
{
"epoch": 1.02,
"learning_rate": 3.0268176705017093e-05,
"loss": 3.5284,
"step": 1205248
},
{
"epoch": 1.02,
"learning_rate": 3.0259790757506573e-05,
"loss": 3.5308,
"step": 1205760
},
{
"epoch": 1.02,
"learning_rate": 3.0251404809996053e-05,
"loss": 3.527,
"step": 1206272
},
{
"epoch": 1.02,
"learning_rate": 3.0243035241289265e-05,
"loss": 3.5179,
"step": 1206784
},
{
"epoch": 1.02,
"learning_rate": 3.0234649293778745e-05,
"loss": 3.5284,
"step": 1207296
},
{
"epoch": 1.02,
"learning_rate": 3.0226263346268225e-05,
"loss": 3.5236,
"step": 1207808
},
{
"epoch": 1.02,
"learning_rate": 3.0217877398757705e-05,
"loss": 3.5338,
"step": 1208320
},
{
"epoch": 1.02,
"learning_rate": 3.0209507830050914e-05,
"loss": 3.5271,
"step": 1208832
},
{
"epoch": 1.02,
"learning_rate": 3.0201121882540394e-05,
"loss": 3.5324,
"step": 1209344
},
{
"epoch": 1.02,
"learning_rate": 3.0192735935029874e-05,
"loss": 3.5288,
"step": 1209856
},
{
"epoch": 1.02,
"learning_rate": 3.0184366366323087e-05,
"loss": 3.5237,
"step": 1210368
},
{
"epoch": 1.02,
"learning_rate": 3.0175996797616296e-05,
"loss": 3.5285,
"step": 1210880
},
{
"epoch": 1.02,
"learning_rate": 3.0167610850105776e-05,
"loss": 3.5344,
"step": 1211392
},
{
"epoch": 1.02,
"learning_rate": 3.0159224902595256e-05,
"loss": 3.5363,
"step": 1211904
},
{
"epoch": 1.02,
"learning_rate": 3.0150838955084736e-05,
"loss": 3.5288,
"step": 1212416
},
{
"epoch": 1.02,
"learning_rate": 3.0142453007574216e-05,
"loss": 3.5338,
"step": 1212928
},
{
"epoch": 1.02,
"learning_rate": 3.01340670600637e-05,
"loss": 3.5337,
"step": 1213440
},
{
"epoch": 1.02,
"learning_rate": 3.012568111255318e-05,
"loss": 3.5311,
"step": 1213952
},
{
"epoch": 1.02,
"learning_rate": 3.0117295165042652e-05,
"loss": 3.5311,
"step": 1214464
},
{
"epoch": 1.02,
"learning_rate": 3.0108925596335868e-05,
"loss": 3.5278,
"step": 1214976
},
{
"epoch": 1.02,
"learning_rate": 3.0100539648825348e-05,
"loss": 3.5348,
"step": 1215488
},
{
"epoch": 1.02,
"learning_rate": 3.0092153701314825e-05,
"loss": 3.5354,
"step": 1216000
},
{
"epoch": 1.02,
"learning_rate": 3.0083767753804304e-05,
"loss": 3.5254,
"step": 1216512
},
{
"epoch": 1.02,
"learning_rate": 3.007539818509752e-05,
"loss": 3.5245,
"step": 1217024
},
{
"epoch": 1.02,
"learning_rate": 3.0067012237587e-05,
"loss": 3.5307,
"step": 1217536
},
{
"epoch": 1.02,
"learning_rate": 3.0058626290076473e-05,
"loss": 3.5305,
"step": 1218048
},
{
"epoch": 1.02,
"learning_rate": 3.005025672136969e-05,
"loss": 3.5245,
"step": 1218560
},
{
"epoch": 1.02,
"learning_rate": 3.004187077385917e-05,
"loss": 3.5369,
"step": 1219072
},
{
"epoch": 1.02,
"learning_rate": 3.0033484826348653e-05,
"loss": 3.5243,
"step": 1219584
},
{
"epoch": 1.02,
"learning_rate": 3.0025098878838126e-05,
"loss": 3.5431,
"step": 1220096
},
{
"epoch": 1.02,
"learning_rate": 3.001672931013134e-05,
"loss": 3.5283,
"step": 1220608
},
{
"epoch": 1.03,
"learning_rate": 3.000834336262082e-05,
"loss": 3.525,
"step": 1221120
},
{
"epoch": 1.03,
"eval_loss": 3.8446850776672363,
"eval_runtime": 323.3157,
"eval_samples_per_second": 1180.243,
"eval_steps_per_second": 36.883,
"step": 1221120
},
{
"epoch": 0.0,
"learning_rate": 2.9999957415110298e-05,
"loss": 3.5183,
"step": 1221632
},
{
"epoch": 0.0,
"learning_rate": 2.9991571467599778e-05,
"loss": 3.519,
"step": 1222144
},
{
"epoch": 0.0,
"learning_rate": 2.9983185520089258e-05,
"loss": 3.5386,
"step": 1222656
},
{
"epoch": 0.0,
"learning_rate": 2.9974815951382474e-05,
"loss": 3.534,
"step": 1223168
},
{
"epoch": 0.0,
"learning_rate": 2.9966430003871947e-05,
"loss": 3.5299,
"step": 1223680
},
{
"epoch": 0.0,
"learning_rate": 2.9958044056361427e-05,
"loss": 3.5237,
"step": 1224192
},
{
"epoch": 0.0,
"learning_rate": 2.9949658108850907e-05,
"loss": 3.5262,
"step": 1224704
},
{
"epoch": 0.0,
"learning_rate": 2.9941288540144123e-05,
"loss": 3.5141,
"step": 1225216
},
{
"epoch": 0.0,
"learning_rate": 2.99329025926336e-05,
"loss": 3.5308,
"step": 1225728
},
{
"epoch": 0.0,
"learning_rate": 2.992451664512308e-05,
"loss": 3.5217,
"step": 1226240
},
{
"epoch": 0.0,
"learning_rate": 2.9916147076416295e-05,
"loss": 3.5438,
"step": 1226752
},
{
"epoch": 0.0,
"learning_rate": 2.990776112890577e-05,
"loss": 3.5338,
"step": 1227264
},
{
"epoch": 0.0,
"learning_rate": 2.9899375181395252e-05,
"loss": 3.507,
"step": 1227776
},
{
"epoch": 0.0,
"learning_rate": 2.9890989233884732e-05,
"loss": 3.5195,
"step": 1228288
},
{
"epoch": 0.0,
"learning_rate": 2.9882603286374212e-05,
"loss": 3.5171,
"step": 1228800
},
{
"epoch": 0.0,
"learning_rate": 2.9874217338863692e-05,
"loss": 3.5168,
"step": 1229312
},
{
"epoch": 0.0,
"learning_rate": 2.9865831391353172e-05,
"loss": 3.5247,
"step": 1229824
},
{
"epoch": 0.0,
"learning_rate": 2.985744544384265e-05,
"loss": 3.5253,
"step": 1230336
},
{
"epoch": 0.0,
"learning_rate": 2.984907587513586e-05,
"loss": 3.5152,
"step": 1230848
},
{
"epoch": 0.0,
"learning_rate": 2.9840689927625344e-05,
"loss": 3.5387,
"step": 1231360
},
{
"epoch": 0.0,
"learning_rate": 2.9832303980114824e-05,
"loss": 3.5244,
"step": 1231872
},
{
"epoch": 0.0,
"learning_rate": 2.9823918032604304e-05,
"loss": 3.5236,
"step": 1232384
},
{
"epoch": 0.0,
"learning_rate": 2.9815548463897513e-05,
"loss": 3.5189,
"step": 1232896
},
{
"epoch": 0.0,
"learning_rate": 2.9807162516386993e-05,
"loss": 3.5352,
"step": 1233408
},
{
"epoch": 0.0,
"learning_rate": 2.9798776568876473e-05,
"loss": 3.5208,
"step": 1233920
},
{
"epoch": 0.0,
"learning_rate": 2.9790390621365953e-05,
"loss": 3.5184,
"step": 1234432
},
{
"epoch": 0.0,
"learning_rate": 2.9782021052659165e-05,
"loss": 3.5254,
"step": 1234944
},
{
"epoch": 0.0,
"learning_rate": 2.9773635105148645e-05,
"loss": 3.5178,
"step": 1235456
},
{
"epoch": 0.0,
"learning_rate": 2.9765249157638125e-05,
"loss": 3.5173,
"step": 1235968
},
{
"epoch": 0.01,
"learning_rate": 2.9756863210127605e-05,
"loss": 3.5209,
"step": 1236480
},
{
"epoch": 0.01,
"learning_rate": 2.9748493641420814e-05,
"loss": 3.5249,
"step": 1236992
},
{
"epoch": 0.01,
"learning_rate": 2.9740107693910298e-05,
"loss": 3.5242,
"step": 1237504
},
{
"epoch": 0.01,
"learning_rate": 2.9731721746399778e-05,
"loss": 3.5248,
"step": 1238016
},
{
"epoch": 0.01,
"learning_rate": 2.9723335798889258e-05,
"loss": 3.5255,
"step": 1238528
},
{
"epoch": 0.01,
"learning_rate": 2.9714982608986196e-05,
"loss": 3.5253,
"step": 1239040
},
{
"epoch": 0.01,
"learning_rate": 2.9706596661475676e-05,
"loss": 3.5286,
"step": 1239552
},
{
"epoch": 0.01,
"learning_rate": 2.969821071396516e-05,
"loss": 3.5156,
"step": 1240064
},
{
"epoch": 0.01,
"learning_rate": 2.968982476645464e-05,
"loss": 3.522,
"step": 1240576
},
{
"epoch": 0.01,
"learning_rate": 2.968143881894412e-05,
"loss": 3.5128,
"step": 1241088
},
{
"epoch": 0.01,
"learning_rate": 2.96730528714336e-05,
"loss": 3.5179,
"step": 1241600
},
{
"epoch": 0.01,
"learning_rate": 2.966466692392308e-05,
"loss": 3.5144,
"step": 1242112
},
{
"epoch": 0.01,
"learning_rate": 2.965628097641256e-05,
"loss": 3.5303,
"step": 1242624
},
{
"epoch": 0.01,
"learning_rate": 2.9647911407705768e-05,
"loss": 3.5169,
"step": 1243136
},
{
"epoch": 0.01,
"learning_rate": 2.963952546019525e-05,
"loss": 3.5247,
"step": 1243648
},
{
"epoch": 0.01,
"learning_rate": 2.963113951268473e-05,
"loss": 3.5242,
"step": 1244160
},
{
"epoch": 0.01,
"learning_rate": 2.962275356517421e-05,
"loss": 3.5303,
"step": 1244672
},
{
"epoch": 0.01,
"learning_rate": 2.961438399646742e-05,
"loss": 3.5235,
"step": 1245184
},
{
"epoch": 0.01,
"learning_rate": 2.96059980489569e-05,
"loss": 3.5062,
"step": 1245696
},
{
"epoch": 0.01,
"learning_rate": 2.9597628480250113e-05,
"loss": 3.5146,
"step": 1246208
},
{
"epoch": 0.01,
"learning_rate": 2.9589242532739593e-05,
"loss": 3.5313,
"step": 1246720
},
{
"epoch": 0.01,
"learning_rate": 2.9580856585229073e-05,
"loss": 3.5239,
"step": 1247232
},
{
"epoch": 0.01,
"learning_rate": 2.9572470637718553e-05,
"loss": 3.5121,
"step": 1247744
},
{
"epoch": 0.01,
"learning_rate": 2.9564084690208033e-05,
"loss": 3.5111,
"step": 1248256
},
{
"epoch": 0.01,
"learning_rate": 2.9555698742697513e-05,
"loss": 3.5148,
"step": 1248768
},
{
"epoch": 0.01,
"learning_rate": 2.9547312795186993e-05,
"loss": 3.5043,
"step": 1249280
},
{
"epoch": 0.01,
"learning_rate": 2.9538926847676473e-05,
"loss": 3.5279,
"step": 1249792
},
{
"epoch": 0.01,
"learning_rate": 2.9530557278969685e-05,
"loss": 3.5081,
"step": 1250304
},
{
"epoch": 0.01,
"learning_rate": 2.9522171331459165e-05,
"loss": 3.5203,
"step": 1250816
},
{
"epoch": 0.01,
"learning_rate": 2.9513785383948645e-05,
"loss": 3.5231,
"step": 1251328
},
{
"epoch": 0.01,
"learning_rate": 2.9505399436438125e-05,
"loss": 3.5067,
"step": 1251840
},
{
"epoch": 0.01,
"learning_rate": 2.9497029867731334e-05,
"loss": 3.5289,
"step": 1252352
},
{
"epoch": 0.01,
"learning_rate": 2.9488643920220814e-05,
"loss": 3.5091,
"step": 1252864
},
{
"epoch": 0.01,
"learning_rate": 2.9480257972710297e-05,
"loss": 3.5172,
"step": 1253376
},
{
"epoch": 0.01,
"learning_rate": 2.9471872025199777e-05,
"loss": 3.5026,
"step": 1253888
},
{
"epoch": 0.01,
"learning_rate": 2.9463502456492986e-05,
"loss": 3.5265,
"step": 1254400
},
{
"epoch": 0.01,
"learning_rate": 2.9455116508982466e-05,
"loss": 3.5067,
"step": 1254912
},
{
"epoch": 0.01,
"learning_rate": 2.9446730561471946e-05,
"loss": 3.5105,
"step": 1255424
},
{
"epoch": 0.01,
"learning_rate": 2.9438344613961426e-05,
"loss": 3.5037,
"step": 1255936
},
{
"epoch": 0.01,
"learning_rate": 2.942997504525464e-05,
"loss": 3.5099,
"step": 1256448
},
{
"epoch": 0.01,
"learning_rate": 2.942158909774412e-05,
"loss": 3.5188,
"step": 1256960
},
{
"epoch": 0.01,
"learning_rate": 2.94132031502336e-05,
"loss": 3.5223,
"step": 1257472
},
{
"epoch": 0.01,
"learning_rate": 2.940481720272308e-05,
"loss": 3.5199,
"step": 1257984
},
{
"epoch": 0.01,
"learning_rate": 2.9396447634016288e-05,
"loss": 3.5213,
"step": 1258496
},
{
"epoch": 0.01,
"learning_rate": 2.9388061686505768e-05,
"loss": 3.5298,
"step": 1259008
},
{
"epoch": 0.01,
"learning_rate": 2.9379675738995248e-05,
"loss": 3.5134,
"step": 1259520
},
{
"epoch": 0.01,
"learning_rate": 2.937128979148473e-05,
"loss": 3.5289,
"step": 1260032
},
{
"epoch": 0.01,
"learning_rate": 2.936292022277794e-05,
"loss": 3.512,
"step": 1260544
},
{
"epoch": 0.01,
"learning_rate": 2.935453427526742e-05,
"loss": 3.5127,
"step": 1261056
},
{
"epoch": 0.01,
"learning_rate": 2.93461483277569e-05,
"loss": 3.5192,
"step": 1261568
},
{
"epoch": 0.01,
"learning_rate": 2.9337762380246377e-05,
"loss": 3.5236,
"step": 1262080
},
{
"epoch": 0.01,
"learning_rate": 2.9329392811539592e-05,
"loss": 3.5174,
"step": 1262592
},
{
"epoch": 0.01,
"learning_rate": 2.9321006864029072e-05,
"loss": 3.528,
"step": 1263104
},
{
"epoch": 0.01,
"learning_rate": 2.9312620916518552e-05,
"loss": 3.5144,
"step": 1263616
},
{
"epoch": 0.01,
"learning_rate": 2.9304234969008025e-05,
"loss": 3.4956,
"step": 1264128
},
{
"epoch": 0.01,
"learning_rate": 2.929586540030124e-05,
"loss": 3.5093,
"step": 1264640
},
{
"epoch": 0.01,
"learning_rate": 2.928747945279072e-05,
"loss": 3.5175,
"step": 1265152
},
{
"epoch": 0.01,
"learning_rate": 2.92790935052802e-05,
"loss": 3.5128,
"step": 1265664
},
{
"epoch": 0.01,
"learning_rate": 2.9270707557769678e-05,
"loss": 3.513,
"step": 1266176
},
{
"epoch": 0.01,
"learning_rate": 2.9262337989062894e-05,
"loss": 3.518,
"step": 1266688
},
{
"epoch": 0.02,
"learning_rate": 2.9253968420356103e-05,
"loss": 3.5094,
"step": 1267200
},
{
"epoch": 0.02,
"learning_rate": 2.9245582472845583e-05,
"loss": 3.5162,
"step": 1267712
},
{
"epoch": 0.02,
"learning_rate": 2.9237196525335063e-05,
"loss": 3.5129,
"step": 1268224
},
{
"epoch": 0.02,
"learning_rate": 2.9228810577824546e-05,
"loss": 3.5208,
"step": 1268736
},
{
"epoch": 0.02,
"learning_rate": 2.9220424630314026e-05,
"loss": 3.5264,
"step": 1269248
},
{
"epoch": 0.02,
"learning_rate": 2.92120386828035e-05,
"loss": 3.5275,
"step": 1269760
},
{
"epoch": 0.02,
"learning_rate": 2.920365273529298e-05,
"loss": 3.5003,
"step": 1270272
},
{
"epoch": 0.02,
"learning_rate": 2.919526678778246e-05,
"loss": 3.5154,
"step": 1270784
},
{
"epoch": 0.02,
"learning_rate": 2.9186897219075675e-05,
"loss": 3.516,
"step": 1271296
},
{
"epoch": 0.02,
"learning_rate": 2.917851127156515e-05,
"loss": 3.5178,
"step": 1271808
},
{
"epoch": 0.02,
"learning_rate": 2.917012532405463e-05,
"loss": 3.5214,
"step": 1272320
},
{
"epoch": 0.02,
"learning_rate": 2.916173937654411e-05,
"loss": 3.5133,
"step": 1272832
},
{
"epoch": 0.02,
"learning_rate": 2.915336980783732e-05,
"loss": 3.5129,
"step": 1273344
},
{
"epoch": 0.02,
"learning_rate": 2.91449838603268e-05,
"loss": 3.5228,
"step": 1273856
},
{
"epoch": 0.02,
"learning_rate": 2.9136597912816284e-05,
"loss": 3.5179,
"step": 1274368
},
{
"epoch": 0.02,
"learning_rate": 2.9128211965305764e-05,
"loss": 3.511,
"step": 1274880
},
{
"epoch": 0.02,
"learning_rate": 2.9119842396598973e-05,
"loss": 3.5166,
"step": 1275392
},
{
"epoch": 0.02,
"learning_rate": 2.9111456449088453e-05,
"loss": 3.5098,
"step": 1275904
},
{
"epoch": 0.02,
"learning_rate": 2.9103070501577933e-05,
"loss": 3.5085,
"step": 1276416
},
{
"epoch": 0.02,
"learning_rate": 2.9094684554067413e-05,
"loss": 3.5074,
"step": 1276928
},
{
"epoch": 0.02,
"learning_rate": 2.9086314985360625e-05,
"loss": 3.5113,
"step": 1277440
},
{
"epoch": 0.02,
"learning_rate": 2.9077929037850105e-05,
"loss": 3.5068,
"step": 1277952
},
{
"epoch": 0.02,
"learning_rate": 2.9069543090339585e-05,
"loss": 3.5216,
"step": 1278464
},
{
"epoch": 0.02,
"learning_rate": 2.9061157142829065e-05,
"loss": 3.51,
"step": 1278976
},
{
"epoch": 0.02,
"learning_rate": 2.9052787574122274e-05,
"loss": 3.5116,
"step": 1279488
},
{
"epoch": 0.02,
"learning_rate": 2.9044401626611754e-05,
"loss": 3.5286,
"step": 1280000
},
{
"epoch": 0.02,
"learning_rate": 2.9036015679101238e-05,
"loss": 3.5282,
"step": 1280512
},
{
"epoch": 0.02,
"learning_rate": 2.9027629731590717e-05,
"loss": 3.5171,
"step": 1281024
},
{
"epoch": 0.02,
"learning_rate": 2.9019260162883927e-05,
"loss": 3.5176,
"step": 1281536
},
{
"epoch": 0.02,
"learning_rate": 2.9010874215373407e-05,
"loss": 3.5156,
"step": 1282048
},
{
"epoch": 0.02,
"learning_rate": 2.9002488267862886e-05,
"loss": 3.5121,
"step": 1282560
},
{
"epoch": 0.02,
"learning_rate": 2.8994102320352366e-05,
"loss": 3.5046,
"step": 1283072
},
{
"epoch": 0.02,
"learning_rate": 2.898573275164558e-05,
"loss": 3.5121,
"step": 1283584
},
{
"epoch": 0.02,
"learning_rate": 2.897734680413506e-05,
"loss": 3.5129,
"step": 1284096
},
{
"epoch": 0.02,
"learning_rate": 2.896896085662454e-05,
"loss": 3.5197,
"step": 1284608
},
{
"epoch": 0.02,
"learning_rate": 2.896057490911402e-05,
"loss": 3.512,
"step": 1285120
},
{
"epoch": 0.02,
"learning_rate": 2.8952205340407228e-05,
"loss": 3.519,
"step": 1285632
},
{
"epoch": 0.02,
"learning_rate": 2.8943819392896708e-05,
"loss": 3.5148,
"step": 1286144
},
{
"epoch": 0.02,
"learning_rate": 2.893544982418992e-05,
"loss": 3.512,
"step": 1286656
},
{
"epoch": 0.02,
"learning_rate": 2.89270638766794e-05,
"loss": 3.5088,
"step": 1287168
},
{
"epoch": 0.02,
"learning_rate": 2.891867792916888e-05,
"loss": 3.5246,
"step": 1287680
},
{
"epoch": 0.02,
"learning_rate": 2.891029198165836e-05,
"loss": 3.5209,
"step": 1288192
},
{
"epoch": 0.02,
"learning_rate": 2.890190603414784e-05,
"loss": 3.5128,
"step": 1288704
},
{
"epoch": 0.02,
"learning_rate": 2.889352008663732e-05,
"loss": 3.5168,
"step": 1289216
},
{
"epoch": 0.02,
"learning_rate": 2.88851341391268e-05,
"loss": 3.5212,
"step": 1289728
},
{
"epoch": 0.02,
"learning_rate": 2.8876748191616283e-05,
"loss": 3.5167,
"step": 1290240
},
{
"epoch": 0.02,
"learning_rate": 2.8868378622909493e-05,
"loss": 3.5192,
"step": 1290752
},
{
"epoch": 0.02,
"learning_rate": 2.8859992675398972e-05,
"loss": 3.5145,
"step": 1291264
},
{
"epoch": 0.02,
"learning_rate": 2.8851606727888452e-05,
"loss": 3.5207,
"step": 1291776
},
{
"epoch": 0.02,
"learning_rate": 2.8843220780377932e-05,
"loss": 3.5174,
"step": 1292288
},
{
"epoch": 0.02,
"learning_rate": 2.8834851211671145e-05,
"loss": 3.5139,
"step": 1292800
},
{
"epoch": 0.02,
"learning_rate": 2.8826465264160625e-05,
"loss": 3.5143,
"step": 1293312
},
{
"epoch": 0.02,
"learning_rate": 2.8818079316650105e-05,
"loss": 3.5138,
"step": 1293824
},
{
"epoch": 0.02,
"learning_rate": 2.8809693369139585e-05,
"loss": 3.5176,
"step": 1294336
},
{
"epoch": 0.02,
"learning_rate": 2.8801323800432794e-05,
"loss": 3.5122,
"step": 1294848
},
{
"epoch": 0.02,
"learning_rate": 2.8792937852922274e-05,
"loss": 3.5232,
"step": 1295360
},
{
"epoch": 0.02,
"learning_rate": 2.8784551905411754e-05,
"loss": 3.5137,
"step": 1295872
},
{
"epoch": 0.02,
"learning_rate": 2.8776165957901237e-05,
"loss": 3.5225,
"step": 1296384
},
{
"epoch": 0.02,
"learning_rate": 2.8767796389194446e-05,
"loss": 3.5182,
"step": 1296896
},
{
"epoch": 0.02,
"learning_rate": 2.8759410441683926e-05,
"loss": 3.5057,
"step": 1297408
},
{
"epoch": 0.03,
"eval_loss": 3.8446714878082275,
"eval_runtime": 303.7291,
"eval_samples_per_second": 1256.353,
"eval_steps_per_second": 39.262,
"step": 1297440
},
{
"epoch": 1.0,
"learning_rate": 2.8751024494173406e-05,
"loss": 3.5067,
"step": 1297920
},
{
"epoch": 1.0,
"learning_rate": 2.8742638546662886e-05,
"loss": 3.5071,
"step": 1298432
},
{
"epoch": 1.0,
"learning_rate": 2.87342689779561e-05,
"loss": 3.5297,
"step": 1298944
},
{
"epoch": 1.0,
"learning_rate": 2.872588303044558e-05,
"loss": 3.5109,
"step": 1299456
},
{
"epoch": 1.0,
"learning_rate": 2.871749708293506e-05,
"loss": 3.5192,
"step": 1299968
},
{
"epoch": 1.0,
"learning_rate": 2.8709127514228268e-05,
"loss": 3.5101,
"step": 1300480
},
{
"epoch": 1.0,
"learning_rate": 2.8700741566717747e-05,
"loss": 3.5084,
"step": 1300992
},
{
"epoch": 1.0,
"learning_rate": 2.8692355619207227e-05,
"loss": 3.5024,
"step": 1301504
},
{
"epoch": 1.0,
"learning_rate": 2.8683969671696707e-05,
"loss": 3.5166,
"step": 1302016
},
{
"epoch": 1.0,
"learning_rate": 2.867560010298992e-05,
"loss": 3.5093,
"step": 1302528
},
{
"epoch": 1.0,
"learning_rate": 2.866723053428313e-05,
"loss": 3.5287,
"step": 1303040
},
{
"epoch": 1.0,
"learning_rate": 2.865884458677261e-05,
"loss": 3.5199,
"step": 1303552
},
{
"epoch": 1.0,
"learning_rate": 2.865045863926209e-05,
"loss": 3.4989,
"step": 1304064
},
{
"epoch": 1.0,
"learning_rate": 2.864207269175157e-05,
"loss": 3.5031,
"step": 1304576
},
{
"epoch": 1.0,
"learning_rate": 2.8633686744241052e-05,
"loss": 3.509,
"step": 1305088
},
{
"epoch": 1.0,
"learning_rate": 2.8625300796730532e-05,
"loss": 3.4988,
"step": 1305600
},
{
"epoch": 1.0,
"learning_rate": 2.8616914849220012e-05,
"loss": 3.5136,
"step": 1306112
},
{
"epoch": 1.0,
"learning_rate": 2.8608528901709492e-05,
"loss": 3.5116,
"step": 1306624
},
{
"epoch": 1.0,
"learning_rate": 2.86001593330027e-05,
"loss": 3.5021,
"step": 1307136
},
{
"epoch": 1.0,
"learning_rate": 2.859177338549218e-05,
"loss": 3.5261,
"step": 1307648
},
{
"epoch": 1.0,
"learning_rate": 2.858338743798166e-05,
"loss": 3.5128,
"step": 1308160
},
{
"epoch": 1.0,
"learning_rate": 2.8575001490471144e-05,
"loss": 3.513,
"step": 1308672
},
{
"epoch": 1.0,
"learning_rate": 2.8566631921764354e-05,
"loss": 3.5051,
"step": 1309184
},
{
"epoch": 1.0,
"learning_rate": 2.8558245974253833e-05,
"loss": 3.5217,
"step": 1309696
},
{
"epoch": 1.0,
"learning_rate": 2.8549860026743313e-05,
"loss": 3.5025,
"step": 1310208
},
{
"epoch": 1.0,
"learning_rate": 2.8541474079232793e-05,
"loss": 3.5105,
"step": 1310720
},
{
"epoch": 1.0,
"learning_rate": 2.8533104510526006e-05,
"loss": 3.5074,
"step": 1311232
},
{
"epoch": 1.0,
"learning_rate": 2.8524718563015486e-05,
"loss": 3.507,
"step": 1311744
},
{
"epoch": 1.0,
"learning_rate": 2.8516332615504966e-05,
"loss": 3.5013,
"step": 1312256
},
{
"epoch": 1.01,
"learning_rate": 2.8507946667994446e-05,
"loss": 3.5073,
"step": 1312768
},
{
"epoch": 1.01,
"learning_rate": 2.8499577099287655e-05,
"loss": 3.5118,
"step": 1313280
},
{
"epoch": 1.01,
"learning_rate": 2.8491191151777135e-05,
"loss": 3.512,
"step": 1313792
},
{
"epoch": 1.01,
"learning_rate": 2.8482805204266615e-05,
"loss": 3.5116,
"step": 1314304
},
{
"epoch": 1.01,
"learning_rate": 2.8474419256756095e-05,
"loss": 3.5147,
"step": 1314816
},
{
"epoch": 1.01,
"learning_rate": 2.8466066066853036e-05,
"loss": 3.509,
"step": 1315328
},
{
"epoch": 1.01,
"learning_rate": 2.8457680119342516e-05,
"loss": 3.5138,
"step": 1315840
},
{
"epoch": 1.01,
"learning_rate": 2.8449294171831996e-05,
"loss": 3.5031,
"step": 1316352
},
{
"epoch": 1.01,
"learning_rate": 2.8440908224321476e-05,
"loss": 3.5094,
"step": 1316864
},
{
"epoch": 1.01,
"learning_rate": 2.8432522276810956e-05,
"loss": 3.4993,
"step": 1317376
},
{
"epoch": 1.01,
"learning_rate": 2.842413632930044e-05,
"loss": 3.5056,
"step": 1317888
},
{
"epoch": 1.01,
"learning_rate": 2.841575038178992e-05,
"loss": 3.5038,
"step": 1318400
},
{
"epoch": 1.01,
"learning_rate": 2.84073644342794e-05,
"loss": 3.5181,
"step": 1318912
},
{
"epoch": 1.01,
"learning_rate": 2.839899486557261e-05,
"loss": 3.5007,
"step": 1319424
},
{
"epoch": 1.01,
"learning_rate": 2.839060891806209e-05,
"loss": 3.5149,
"step": 1319936
},
{
"epoch": 1.01,
"learning_rate": 2.838222297055157e-05,
"loss": 3.5097,
"step": 1320448
},
{
"epoch": 1.01,
"learning_rate": 2.837383702304105e-05,
"loss": 3.5153,
"step": 1320960
},
{
"epoch": 1.01,
"learning_rate": 2.836546745433426e-05,
"loss": 3.5085,
"step": 1321472
},
{
"epoch": 1.01,
"learning_rate": 2.835708150682374e-05,
"loss": 3.4941,
"step": 1321984
},
{
"epoch": 1.01,
"learning_rate": 2.834871193811695e-05,
"loss": 3.5041,
"step": 1322496
},
{
"epoch": 1.01,
"learning_rate": 2.834032599060643e-05,
"loss": 3.5147,
"step": 1323008
},
{
"epoch": 1.01,
"learning_rate": 2.833194004309591e-05,
"loss": 3.5081,
"step": 1323520
},
{
"epoch": 1.01,
"learning_rate": 2.8323554095585393e-05,
"loss": 3.5018,
"step": 1324032
},
{
"epoch": 1.01,
"learning_rate": 2.8315168148074873e-05,
"loss": 3.4957,
"step": 1324544
},
{
"epoch": 1.01,
"learning_rate": 2.8306782200564346e-05,
"loss": 3.5045,
"step": 1325056
},
{
"epoch": 1.01,
"learning_rate": 2.8298396253053826e-05,
"loss": 3.4863,
"step": 1325568
},
{
"epoch": 1.01,
"learning_rate": 2.8290010305543306e-05,
"loss": 3.5182,
"step": 1326080
},
{
"epoch": 1.01,
"learning_rate": 2.8281640736836522e-05,
"loss": 3.493,
"step": 1326592
},
{
"epoch": 1.01,
"learning_rate": 2.8273254789326e-05,
"loss": 3.5087,
"step": 1327104
},
{
"epoch": 1.01,
"learning_rate": 2.826486884181548e-05,
"loss": 3.506,
"step": 1327616
},
{
"epoch": 1.01,
"learning_rate": 2.825648289430496e-05,
"loss": 3.496,
"step": 1328128
},
{
"epoch": 1.01,
"learning_rate": 2.8248113325598168e-05,
"loss": 3.5107,
"step": 1328640
},
{
"epoch": 1.01,
"learning_rate": 2.8239727378087648e-05,
"loss": 3.4996,
"step": 1329152
},
{
"epoch": 1.01,
"learning_rate": 2.823134143057713e-05,
"loss": 3.503,
"step": 1329664
},
{
"epoch": 1.01,
"learning_rate": 2.822295548306661e-05,
"loss": 3.4893,
"step": 1330176
},
{
"epoch": 1.01,
"learning_rate": 2.821458591435982e-05,
"loss": 3.514,
"step": 1330688
},
{
"epoch": 1.01,
"learning_rate": 2.82061999668493e-05,
"loss": 3.4945,
"step": 1331200
},
{
"epoch": 1.01,
"learning_rate": 2.819781401933878e-05,
"loss": 3.5,
"step": 1331712
},
{
"epoch": 1.01,
"learning_rate": 2.818942807182826e-05,
"loss": 3.4872,
"step": 1332224
},
{
"epoch": 1.01,
"learning_rate": 2.8181058503121472e-05,
"loss": 3.4999,
"step": 1332736
},
{
"epoch": 1.01,
"learning_rate": 2.8172672555610952e-05,
"loss": 3.5064,
"step": 1333248
},
{
"epoch": 1.01,
"learning_rate": 2.8164286608100432e-05,
"loss": 3.5062,
"step": 1333760
},
{
"epoch": 1.01,
"learning_rate": 2.8155900660589912e-05,
"loss": 3.5053,
"step": 1334272
},
{
"epoch": 1.01,
"learning_rate": 2.814753109188312e-05,
"loss": 3.5093,
"step": 1334784
},
{
"epoch": 1.01,
"learning_rate": 2.81391451443726e-05,
"loss": 3.5136,
"step": 1335296
},
{
"epoch": 1.01,
"learning_rate": 2.8130759196862085e-05,
"loss": 3.5033,
"step": 1335808
},
{
"epoch": 1.01,
"learning_rate": 2.8122373249351565e-05,
"loss": 3.5114,
"step": 1336320
},
{
"epoch": 1.01,
"learning_rate": 2.8114003680644774e-05,
"loss": 3.502,
"step": 1336832
},
{
"epoch": 1.01,
"learning_rate": 2.8105617733134254e-05,
"loss": 3.5008,
"step": 1337344
},
{
"epoch": 1.01,
"learning_rate": 2.8097231785623734e-05,
"loss": 3.5018,
"step": 1337856
},
{
"epoch": 1.01,
"learning_rate": 2.8088845838113214e-05,
"loss": 3.5108,
"step": 1338368
},
{
"epoch": 1.01,
"learning_rate": 2.8080476269406426e-05,
"loss": 3.5066,
"step": 1338880
},
{
"epoch": 1.01,
"learning_rate": 2.8072090321895906e-05,
"loss": 3.5133,
"step": 1339392
},
{
"epoch": 1.01,
"learning_rate": 2.8063704374385386e-05,
"loss": 3.5043,
"step": 1339904
},
{
"epoch": 1.01,
"learning_rate": 2.8055318426874866e-05,
"loss": 3.4825,
"step": 1340416
},
{
"epoch": 1.01,
"learning_rate": 2.8046948858168075e-05,
"loss": 3.4945,
"step": 1340928
},
{
"epoch": 1.01,
"learning_rate": 2.8038562910657555e-05,
"loss": 3.5048,
"step": 1341440
},
{
"epoch": 1.01,
"learning_rate": 2.8030176963147038e-05,
"loss": 3.5016,
"step": 1341952
},
{
"epoch": 1.01,
"learning_rate": 2.8021791015636518e-05,
"loss": 3.498,
"step": 1342464
},
{
"epoch": 1.01,
"learning_rate": 2.8013421446929727e-05,
"loss": 3.5075,
"step": 1342976
},
{
"epoch": 1.02,
"learning_rate": 2.8005051878222943e-05,
"loss": 3.4943,
"step": 1343488
},
{
"epoch": 1.02,
"learning_rate": 2.7996665930712416e-05,
"loss": 3.4987,
"step": 1344000
},
{
"epoch": 1.02,
"learning_rate": 2.79882799832019e-05,
"loss": 3.4998,
"step": 1344512
},
{
"epoch": 1.02,
"learning_rate": 2.797989403569138e-05,
"loss": 3.5085,
"step": 1345024
},
{
"epoch": 1.02,
"learning_rate": 2.797150808818086e-05,
"loss": 3.51,
"step": 1345536
},
{
"epoch": 1.02,
"learning_rate": 2.796312214067034e-05,
"loss": 3.517,
"step": 1346048
},
{
"epoch": 1.02,
"learning_rate": 2.795473619315982e-05,
"loss": 3.4891,
"step": 1346560
},
{
"epoch": 1.02,
"learning_rate": 2.79463502456493e-05,
"loss": 3.5021,
"step": 1347072
},
{
"epoch": 1.02,
"learning_rate": 2.793798067694251e-05,
"loss": 3.5039,
"step": 1347584
},
{
"epoch": 1.02,
"learning_rate": 2.7929594729431992e-05,
"loss": 3.5015,
"step": 1348096
},
{
"epoch": 1.02,
"learning_rate": 2.7921208781921472e-05,
"loss": 3.5094,
"step": 1348608
},
{
"epoch": 1.02,
"learning_rate": 2.7912822834410952e-05,
"loss": 3.4995,
"step": 1349120
},
{
"epoch": 1.02,
"learning_rate": 2.790445326570416e-05,
"loss": 3.4991,
"step": 1349632
},
{
"epoch": 1.02,
"learning_rate": 2.789606731819364e-05,
"loss": 3.5086,
"step": 1350144
},
{
"epoch": 1.02,
"learning_rate": 2.788768137068312e-05,
"loss": 3.5082,
"step": 1350656
},
{
"epoch": 1.02,
"learning_rate": 2.78792954231726e-05,
"loss": 3.4928,
"step": 1351168
},
{
"epoch": 1.02,
"learning_rate": 2.7870925854465813e-05,
"loss": 3.5034,
"step": 1351680
},
{
"epoch": 1.02,
"learning_rate": 2.7862539906955293e-05,
"loss": 3.4999,
"step": 1352192
},
{
"epoch": 1.02,
"learning_rate": 2.7854153959444773e-05,
"loss": 3.4938,
"step": 1352704
},
{
"epoch": 1.02,
"learning_rate": 2.7845768011934253e-05,
"loss": 3.4914,
"step": 1353216
},
{
"epoch": 1.02,
"learning_rate": 2.7837398443227462e-05,
"loss": 3.4984,
"step": 1353728
},
{
"epoch": 1.02,
"learning_rate": 2.7829012495716946e-05,
"loss": 3.4934,
"step": 1354240
},
{
"epoch": 1.02,
"learning_rate": 2.7820626548206426e-05,
"loss": 3.5081,
"step": 1354752
},
{
"epoch": 1.02,
"learning_rate": 2.7812240600695906e-05,
"loss": 3.4975,
"step": 1355264
},
{
"epoch": 1.02,
"learning_rate": 2.7803871031989115e-05,
"loss": 3.5006,
"step": 1355776
},
{
"epoch": 1.02,
"learning_rate": 2.7795485084478595e-05,
"loss": 3.5158,
"step": 1356288
},
{
"epoch": 1.02,
"learning_rate": 2.7787099136968075e-05,
"loss": 3.5131,
"step": 1356800
},
{
"epoch": 1.02,
"learning_rate": 2.7778729568261287e-05,
"loss": 3.5054,
"step": 1357312
},
{
"epoch": 1.02,
"learning_rate": 2.7770343620750767e-05,
"loss": 3.5069,
"step": 1357824
},
{
"epoch": 1.02,
"learning_rate": 2.7761957673240247e-05,
"loss": 3.5018,
"step": 1358336
},
{
"epoch": 1.02,
"learning_rate": 2.7753571725729727e-05,
"loss": 3.5001,
"step": 1358848
},
{
"epoch": 1.02,
"learning_rate": 2.7745202157022936e-05,
"loss": 3.4947,
"step": 1359360
},
{
"epoch": 1.02,
"learning_rate": 2.7736816209512416e-05,
"loss": 3.4948,
"step": 1359872
},
{
"epoch": 1.02,
"learning_rate": 2.77284302620019e-05,
"loss": 3.5002,
"step": 1360384
},
{
"epoch": 1.02,
"learning_rate": 2.772004431449138e-05,
"loss": 3.5067,
"step": 1360896
},
{
"epoch": 1.02,
"learning_rate": 2.771167474578459e-05,
"loss": 3.5036,
"step": 1361408
},
{
"epoch": 1.02,
"learning_rate": 2.7703288798274068e-05,
"loss": 3.5012,
"step": 1361920
},
{
"epoch": 1.02,
"learning_rate": 2.7694902850763548e-05,
"loss": 3.5038,
"step": 1362432
},
{
"epoch": 1.02,
"learning_rate": 2.768653328205676e-05,
"loss": 3.4961,
"step": 1362944
},
{
"epoch": 1.02,
"learning_rate": 2.767814733454624e-05,
"loss": 3.4969,
"step": 1363456
},
{
"epoch": 1.02,
"learning_rate": 2.766976138703572e-05,
"loss": 3.5146,
"step": 1363968
},
{
"epoch": 1.02,
"learning_rate": 2.76613754395252e-05,
"loss": 3.5086,
"step": 1364480
},
{
"epoch": 1.02,
"learning_rate": 2.765298949201468e-05,
"loss": 3.5047,
"step": 1364992
},
{
"epoch": 1.02,
"learning_rate": 2.764460354450416e-05,
"loss": 3.5003,
"step": 1365504
},
{
"epoch": 1.02,
"learning_rate": 2.763621759699364e-05,
"loss": 3.5068,
"step": 1366016
},
{
"epoch": 1.02,
"learning_rate": 2.762783164948312e-05,
"loss": 3.5004,
"step": 1366528
},
{
"epoch": 1.02,
"learning_rate": 2.7619462080776333e-05,
"loss": 3.5105,
"step": 1367040
},
{
"epoch": 1.02,
"learning_rate": 2.7611076133265813e-05,
"loss": 3.5042,
"step": 1367552
},
{
"epoch": 1.02,
"learning_rate": 2.7602690185755293e-05,
"loss": 3.5044,
"step": 1368064
},
{
"epoch": 1.02,
"learning_rate": 2.7594304238244773e-05,
"loss": 3.5041,
"step": 1368576
},
{
"epoch": 1.02,
"learning_rate": 2.7585934669537982e-05,
"loss": 3.5018,
"step": 1369088
},
{
"epoch": 1.02,
"learning_rate": 2.7577548722027462e-05,
"loss": 3.4979,
"step": 1369600
},
{
"epoch": 1.02,
"learning_rate": 2.7569162774516942e-05,
"loss": 3.5018,
"step": 1370112
},
{
"epoch": 1.02,
"learning_rate": 2.7560776827006425e-05,
"loss": 3.5068,
"step": 1370624
},
{
"epoch": 1.02,
"learning_rate": 2.7552407258299634e-05,
"loss": 3.4947,
"step": 1371136
},
{
"epoch": 1.02,
"learning_rate": 2.7544021310789114e-05,
"loss": 3.5118,
"step": 1371648
},
{
"epoch": 1.02,
"learning_rate": 2.7535635363278594e-05,
"loss": 3.5019,
"step": 1372160
},
{
"epoch": 1.02,
"learning_rate": 2.7527249415768074e-05,
"loss": 3.5048,
"step": 1372672
},
{
"epoch": 1.02,
"learning_rate": 2.7518879847061287e-05,
"loss": 3.5063,
"step": 1373184
},
{
"epoch": 1.02,
"learning_rate": 2.7510493899550767e-05,
"loss": 3.4938,
"step": 1373696
},
{
"epoch": 1.03,
"eval_loss": 3.846285343170166,
"eval_runtime": 306.2196,
"eval_samples_per_second": 1246.135,
"eval_steps_per_second": 38.943,
"step": 1373760
},
{
"epoch": 0.0,
"learning_rate": 2.7502107952040246e-05,
"loss": 3.4913,
"step": 1374208
},
{
"epoch": 0.0,
"learning_rate": 2.749372200452972e-05,
"loss": 3.4922,
"step": 1374720
},
{
"epoch": 0.0,
"learning_rate": 2.74853360570192e-05,
"loss": 3.5131,
"step": 1375232
},
{
"epoch": 0.0,
"learning_rate": 2.747695010950868e-05,
"loss": 3.4993,
"step": 1375744
},
{
"epoch": 0.0,
"learning_rate": 2.7468580540801895e-05,
"loss": 3.5109,
"step": 1376256
},
{
"epoch": 0.0,
"learning_rate": 2.7460194593291372e-05,
"loss": 3.4953,
"step": 1376768
},
{
"epoch": 0.0,
"learning_rate": 2.7451808645780852e-05,
"loss": 3.4998,
"step": 1377280
},
{
"epoch": 0.0,
"learning_rate": 2.7443439077074068e-05,
"loss": 3.488,
"step": 1377792
},
{
"epoch": 0.0,
"learning_rate": 2.7435053129563548e-05,
"loss": 3.5028,
"step": 1378304
},
{
"epoch": 0.0,
"learning_rate": 2.7426667182053024e-05,
"loss": 3.498,
"step": 1378816
},
{
"epoch": 0.0,
"learning_rate": 2.741829761334624e-05,
"loss": 3.5114,
"step": 1379328
},
{
"epoch": 0.0,
"learning_rate": 2.740991166583572e-05,
"loss": 3.5065,
"step": 1379840
},
{
"epoch": 0.0,
"learning_rate": 2.7401525718325193e-05,
"loss": 3.4849,
"step": 1380352
},
{
"epoch": 0.0,
"learning_rate": 2.7393139770814673e-05,
"loss": 3.4908,
"step": 1380864
},
{
"epoch": 0.0,
"learning_rate": 2.7384753823304153e-05,
"loss": 3.4967,
"step": 1381376
},
{
"epoch": 0.0,
"learning_rate": 2.737638425459737e-05,
"loss": 3.4847,
"step": 1381888
},
{
"epoch": 0.0,
"learning_rate": 2.7367998307086846e-05,
"loss": 3.4961,
"step": 1382400
},
{
"epoch": 0.0,
"learning_rate": 2.7359612359576326e-05,
"loss": 3.4992,
"step": 1382912
},
{
"epoch": 0.0,
"learning_rate": 2.7351226412065806e-05,
"loss": 3.4912,
"step": 1383424
},
{
"epoch": 0.0,
"learning_rate": 2.7342840464555286e-05,
"loss": 3.5151,
"step": 1383936
},
{
"epoch": 0.0,
"learning_rate": 2.7334454517044766e-05,
"loss": 3.4975,
"step": 1384448
},
{
"epoch": 0.0,
"learning_rate": 2.7326068569534245e-05,
"loss": 3.5005,
"step": 1384960
},
{
"epoch": 0.0,
"learning_rate": 2.7317682622023725e-05,
"loss": 3.492,
"step": 1385472
},
{
"epoch": 0.0,
"learning_rate": 2.7309313053316938e-05,
"loss": 3.5088,
"step": 1385984
},
{
"epoch": 0.0,
"learning_rate": 2.7300927105806418e-05,
"loss": 3.4883,
"step": 1386496
},
{
"epoch": 0.0,
"learning_rate": 2.7292541158295898e-05,
"loss": 3.4989,
"step": 1387008
},
{
"epoch": 0.0,
"learning_rate": 2.7284155210785378e-05,
"loss": 3.4927,
"step": 1387520
},
{
"epoch": 0.0,
"learning_rate": 2.7275785642078587e-05,
"loss": 3.4959,
"step": 1388032
},
{
"epoch": 0.0,
"learning_rate": 2.726739969456807e-05,
"loss": 3.4895,
"step": 1388544
},
{
"epoch": 0.01,
"learning_rate": 2.725901374705755e-05,
"loss": 3.4934,
"step": 1389056
},
{
"epoch": 0.01,
"learning_rate": 2.725062779954703e-05,
"loss": 3.5001,
"step": 1389568
},
{
"epoch": 0.01,
"learning_rate": 2.724225823084024e-05,
"loss": 3.4978,
"step": 1390080
},
{
"epoch": 0.01,
"learning_rate": 2.723387228332972e-05,
"loss": 3.494,
"step": 1390592
},
{
"epoch": 0.01,
"learning_rate": 2.72254863358192e-05,
"loss": 3.5027,
"step": 1391104
},
{
"epoch": 0.01,
"learning_rate": 2.721711676711241e-05,
"loss": 3.4944,
"step": 1391616
},
{
"epoch": 0.01,
"learning_rate": 2.720874719840562e-05,
"loss": 3.5004,
"step": 1392128
},
{
"epoch": 0.01,
"learning_rate": 2.72003612508951e-05,
"loss": 3.4895,
"step": 1392640
},
{
"epoch": 0.01,
"learning_rate": 2.719197530338458e-05,
"loss": 3.497,
"step": 1393152
},
{
"epoch": 0.01,
"learning_rate": 2.718358935587406e-05,
"loss": 3.4826,
"step": 1393664
},
{
"epoch": 0.01,
"learning_rate": 2.717520340836354e-05,
"loss": 3.4945,
"step": 1394176
},
{
"epoch": 0.01,
"learning_rate": 2.7166817460853024e-05,
"loss": 3.4886,
"step": 1394688
},
{
"epoch": 0.01,
"learning_rate": 2.7158431513342504e-05,
"loss": 3.5063,
"step": 1395200
},
{
"epoch": 0.01,
"learning_rate": 2.7150061944635713e-05,
"loss": 3.4884,
"step": 1395712
},
{
"epoch": 0.01,
"learning_rate": 2.7141675997125193e-05,
"loss": 3.4993,
"step": 1396224
},
{
"epoch": 0.01,
"learning_rate": 2.7133290049614673e-05,
"loss": 3.5044,
"step": 1396736
},
{
"epoch": 0.01,
"learning_rate": 2.7124904102104153e-05,
"loss": 3.4991,
"step": 1397248
},
{
"epoch": 0.01,
"learning_rate": 2.7116534533397365e-05,
"loss": 3.5005,
"step": 1397760
},
{
"epoch": 0.01,
"learning_rate": 2.7108148585886845e-05,
"loss": 3.4822,
"step": 1398272
},
{
"epoch": 0.01,
"learning_rate": 2.7099779017180054e-05,
"loss": 3.4874,
"step": 1398784
},
{
"epoch": 0.01,
"learning_rate": 2.7091393069669534e-05,
"loss": 3.5032,
"step": 1399296
},
{
"epoch": 0.01,
"learning_rate": 2.7083007122159014e-05,
"loss": 3.4966,
"step": 1399808
},
{
"epoch": 0.01,
"learning_rate": 2.7074621174648494e-05,
"loss": 3.491,
"step": 1400320
},
{
"epoch": 0.01,
"learning_rate": 2.7066235227137978e-05,
"loss": 3.4815,
"step": 1400832
},
{
"epoch": 0.01,
"learning_rate": 2.7057849279627458e-05,
"loss": 3.4947,
"step": 1401344
},
{
"epoch": 0.01,
"learning_rate": 2.7049463332116937e-05,
"loss": 3.4718,
"step": 1401856
},
{
"epoch": 0.01,
"learning_rate": 2.7041077384606417e-05,
"loss": 3.5072,
"step": 1402368
},
{
"epoch": 0.01,
"learning_rate": 2.7032724194703356e-05,
"loss": 3.4785,
"step": 1402880
},
{
"epoch": 0.01,
"learning_rate": 2.702433824719284e-05,
"loss": 3.4969,
"step": 1403392
},
{
"epoch": 0.01,
"learning_rate": 2.701595229968232e-05,
"loss": 3.4964,
"step": 1403904
},
{
"epoch": 0.01,
"learning_rate": 2.70075663521718e-05,
"loss": 3.4804,
"step": 1404416
},
{
"epoch": 0.01,
"learning_rate": 2.699918040466128e-05,
"loss": 3.503,
"step": 1404928
},
{
"epoch": 0.01,
"learning_rate": 2.699079445715076e-05,
"loss": 3.4849,
"step": 1405440
},
{
"epoch": 0.01,
"learning_rate": 2.698240850964024e-05,
"loss": 3.4897,
"step": 1405952
},
{
"epoch": 0.01,
"learning_rate": 2.697402256212972e-05,
"loss": 3.4751,
"step": 1406464
},
{
"epoch": 0.01,
"learning_rate": 2.696565299342293e-05,
"loss": 3.4996,
"step": 1406976
},
{
"epoch": 0.01,
"learning_rate": 2.695726704591241e-05,
"loss": 3.4829,
"step": 1407488
},
{
"epoch": 0.01,
"learning_rate": 2.694888109840189e-05,
"loss": 3.4869,
"step": 1408000
},
{
"epoch": 0.01,
"learning_rate": 2.694049515089137e-05,
"loss": 3.4744,
"step": 1408512
},
{
"epoch": 0.01,
"learning_rate": 2.693212558218458e-05,
"loss": 3.485,
"step": 1409024
},
{
"epoch": 0.01,
"learning_rate": 2.692373963467406e-05,
"loss": 3.4926,
"step": 1409536
},
{
"epoch": 0.01,
"learning_rate": 2.691535368716354e-05,
"loss": 3.4963,
"step": 1410048
},
{
"epoch": 0.01,
"learning_rate": 2.690696773965302e-05,
"loss": 3.4881,
"step": 1410560
},
{
"epoch": 0.01,
"learning_rate": 2.6898598170946233e-05,
"loss": 3.5024,
"step": 1411072
},
{
"epoch": 0.01,
"learning_rate": 2.6890212223435713e-05,
"loss": 3.4993,
"step": 1411584
},
{
"epoch": 0.01,
"learning_rate": 2.6881826275925192e-05,
"loss": 3.4933,
"step": 1412096
},
{
"epoch": 0.01,
"learning_rate": 2.6873440328414672e-05,
"loss": 3.4942,
"step": 1412608
},
{
"epoch": 0.01,
"learning_rate": 2.6865070759707885e-05,
"loss": 3.495,
"step": 1413120
},
{
"epoch": 0.01,
"learning_rate": 2.6856684812197365e-05,
"loss": 3.4884,
"step": 1413632
},
{
"epoch": 0.01,
"learning_rate": 2.6848298864686845e-05,
"loss": 3.4888,
"step": 1414144
},
{
"epoch": 0.01,
"learning_rate": 2.6839912917176325e-05,
"loss": 3.4959,
"step": 1414656
},
{
"epoch": 0.01,
"learning_rate": 2.6831543348469534e-05,
"loss": 3.4987,
"step": 1415168
},
{
"epoch": 0.01,
"learning_rate": 2.6823157400959014e-05,
"loss": 3.5019,
"step": 1415680
},
{
"epoch": 0.01,
"learning_rate": 2.6814771453448494e-05,
"loss": 3.4877,
"step": 1416192
},
{
"epoch": 0.01,
"learning_rate": 2.6806385505937974e-05,
"loss": 3.4679,
"step": 1416704
},
{
"epoch": 0.01,
"learning_rate": 2.6798015937231186e-05,
"loss": 3.4827,
"step": 1417216
},
{
"epoch": 0.01,
"learning_rate": 2.6789629989720666e-05,
"loss": 3.4903,
"step": 1417728
},
{
"epoch": 0.01,
"learning_rate": 2.6781244042210146e-05,
"loss": 3.4892,
"step": 1418240
},
{
"epoch": 0.01,
"learning_rate": 2.6772858094699626e-05,
"loss": 3.4854,
"step": 1418752
},
{
"epoch": 0.01,
"learning_rate": 2.6764488525992835e-05,
"loss": 3.493,
"step": 1419264
},
{
"epoch": 0.02,
"learning_rate": 2.6756118957286048e-05,
"loss": 3.4858,
"step": 1419776
},
{
"epoch": 0.02,
"learning_rate": 2.6747733009775528e-05,
"loss": 3.4799,
"step": 1420288
},
{
"epoch": 0.02,
"learning_rate": 2.6739347062265008e-05,
"loss": 3.4883,
"step": 1420800
},
{
"epoch": 0.02,
"learning_rate": 2.6730961114754488e-05,
"loss": 3.4977,
"step": 1421312
},
{
"epoch": 0.02,
"learning_rate": 2.6722575167243967e-05,
"loss": 3.4952,
"step": 1421824
},
{
"epoch": 0.02,
"learning_rate": 2.6714189219733447e-05,
"loss": 3.5011,
"step": 1422336
},
{
"epoch": 0.02,
"learning_rate": 2.6705803272222924e-05,
"loss": 3.4831,
"step": 1422848
},
{
"epoch": 0.02,
"learning_rate": 2.6697417324712404e-05,
"loss": 3.4897,
"step": 1423360
},
{
"epoch": 0.02,
"learning_rate": 2.668904775600562e-05,
"loss": 3.4914,
"step": 1423872
},
{
"epoch": 0.02,
"learning_rate": 2.66806618084951e-05,
"loss": 3.491,
"step": 1424384
},
{
"epoch": 0.02,
"learning_rate": 2.6672275860984573e-05,
"loss": 3.4942,
"step": 1424896
},
{
"epoch": 0.02,
"learning_rate": 2.6663889913474056e-05,
"loss": 3.4882,
"step": 1425408
},
{
"epoch": 0.02,
"learning_rate": 2.6655520344767272e-05,
"loss": 3.4866,
"step": 1425920
},
{
"epoch": 0.02,
"learning_rate": 2.6647134397256745e-05,
"loss": 3.4943,
"step": 1426432
},
{
"epoch": 0.02,
"learning_rate": 2.6638748449746225e-05,
"loss": 3.4963,
"step": 1426944
},
{
"epoch": 0.02,
"learning_rate": 2.6630362502235705e-05,
"loss": 3.4782,
"step": 1427456
},
{
"epoch": 0.02,
"learning_rate": 2.662199293352892e-05,
"loss": 3.4883,
"step": 1427968
},
{
"epoch": 0.02,
"learning_rate": 2.6613606986018398e-05,
"loss": 3.4901,
"step": 1428480
},
{
"epoch": 0.02,
"learning_rate": 2.6605221038507878e-05,
"loss": 3.4821,
"step": 1428992
},
{
"epoch": 0.02,
"learning_rate": 2.6596835090997358e-05,
"loss": 3.4775,
"step": 1429504
},
{
"epoch": 0.02,
"learning_rate": 2.6588465522290574e-05,
"loss": 3.4857,
"step": 1430016
},
{
"epoch": 0.02,
"learning_rate": 2.6580079574780047e-05,
"loss": 3.4869,
"step": 1430528
},
{
"epoch": 0.02,
"learning_rate": 2.6571693627269527e-05,
"loss": 3.4913,
"step": 1431040
},
{
"epoch": 0.02,
"learning_rate": 2.656330767975901e-05,
"loss": 3.4825,
"step": 1431552
},
{
"epoch": 0.02,
"learning_rate": 2.655493811105222e-05,
"loss": 3.4879,
"step": 1432064
},
{
"epoch": 0.02,
"learning_rate": 2.65465521635417e-05,
"loss": 3.5007,
"step": 1432576
},
{
"epoch": 0.02,
"learning_rate": 2.653816621603118e-05,
"loss": 3.5047,
"step": 1433088
},
{
"epoch": 0.02,
"learning_rate": 2.652978026852066e-05,
"loss": 3.4908,
"step": 1433600
},
{
"epoch": 0.02,
"learning_rate": 2.652141069981387e-05,
"loss": 3.4938,
"step": 1434112
},
{
"epoch": 0.02,
"learning_rate": 2.651302475230335e-05,
"loss": 3.4875,
"step": 1434624
},
{
"epoch": 0.02,
"learning_rate": 2.650463880479283e-05,
"loss": 3.488,
"step": 1435136
},
{
"epoch": 0.02,
"learning_rate": 2.649626923608604e-05,
"loss": 3.4814,
"step": 1435648
},
{
"epoch": 0.02,
"learning_rate": 2.648788328857552e-05,
"loss": 3.4814,
"step": 1436160
},
{
"epoch": 0.02,
"learning_rate": 2.6479497341065e-05,
"loss": 3.4868,
"step": 1436672
},
{
"epoch": 0.02,
"learning_rate": 2.647111139355448e-05,
"loss": 3.4961,
"step": 1437184
},
{
"epoch": 0.02,
"learning_rate": 2.6462741824847693e-05,
"loss": 3.4896,
"step": 1437696
},
{
"epoch": 0.02,
"learning_rate": 2.6454355877337173e-05,
"loss": 3.4907,
"step": 1438208
},
{
"epoch": 0.02,
"learning_rate": 2.6445969929826653e-05,
"loss": 3.491,
"step": 1438720
},
{
"epoch": 0.02,
"learning_rate": 2.643760036111987e-05,
"loss": 3.4816,
"step": 1439232
},
{
"epoch": 0.02,
"learning_rate": 2.6429214413609342e-05,
"loss": 3.4835,
"step": 1439744
},
{
"epoch": 0.02,
"learning_rate": 2.6420828466098825e-05,
"loss": 3.5017,
"step": 1440256
},
{
"epoch": 0.02,
"learning_rate": 2.6412442518588305e-05,
"loss": 3.4993,
"step": 1440768
},
{
"epoch": 0.02,
"learning_rate": 2.6404056571077785e-05,
"loss": 3.491,
"step": 1441280
},
{
"epoch": 0.02,
"learning_rate": 2.6395670623567265e-05,
"loss": 3.4878,
"step": 1441792
},
{
"epoch": 0.02,
"learning_rate": 2.6387284676056745e-05,
"loss": 3.4908,
"step": 1442304
},
{
"epoch": 0.02,
"learning_rate": 2.6378898728546225e-05,
"loss": 3.4902,
"step": 1442816
},
{
"epoch": 0.02,
"learning_rate": 2.6370529159839434e-05,
"loss": 3.5022,
"step": 1443328
},
{
"epoch": 0.02,
"learning_rate": 2.6362143212328917e-05,
"loss": 3.4905,
"step": 1443840
},
{
"epoch": 0.02,
"learning_rate": 2.6353757264818397e-05,
"loss": 3.4904,
"step": 1444352
},
{
"epoch": 0.02,
"learning_rate": 2.6345371317307877e-05,
"loss": 3.49,
"step": 1444864
},
{
"epoch": 0.02,
"learning_rate": 2.6337001748601086e-05,
"loss": 3.4889,
"step": 1445376
},
{
"epoch": 0.02,
"learning_rate": 2.6328615801090566e-05,
"loss": 3.4868,
"step": 1445888
},
{
"epoch": 0.02,
"learning_rate": 2.6320229853580046e-05,
"loss": 3.4863,
"step": 1446400
},
{
"epoch": 0.02,
"learning_rate": 2.6311843906069526e-05,
"loss": 3.4936,
"step": 1446912
},
{
"epoch": 0.02,
"learning_rate": 2.630347433736274e-05,
"loss": 3.4829,
"step": 1447424
},
{
"epoch": 0.02,
"learning_rate": 2.629508838985222e-05,
"loss": 3.4961,
"step": 1447936
},
{
"epoch": 0.02,
"learning_rate": 2.62867024423417e-05,
"loss": 3.4954,
"step": 1448448
},
{
"epoch": 0.02,
"learning_rate": 2.627831649483118e-05,
"loss": 3.491,
"step": 1448960
},
{
"epoch": 0.02,
"learning_rate": 2.6269946926124388e-05,
"loss": 3.4933,
"step": 1449472
},
{
"epoch": 0.02,
"learning_rate": 2.626156097861387e-05,
"loss": 3.4784,
"step": 1449984
},
{
"epoch": 0.03,
"eval_loss": 3.847398042678833,
"eval_runtime": 305.808,
"eval_samples_per_second": 1247.812,
"eval_steps_per_second": 38.995,
"step": 1450080
},
{
"epoch": 1.0,
"learning_rate": 2.625317503110335e-05,
"loss": 3.4873,
"step": 1450496
},
{
"epoch": 1.0,
"learning_rate": 2.624478908359283e-05,
"loss": 3.4792,
"step": 1451008
},
{
"epoch": 1.0,
"learning_rate": 2.623641951488604e-05,
"loss": 3.5006,
"step": 1451520
},
{
"epoch": 1.0,
"learning_rate": 2.622803356737552e-05,
"loss": 3.4849,
"step": 1452032
},
{
"epoch": 1.0,
"learning_rate": 2.6219647619865e-05,
"loss": 3.5022,
"step": 1452544
},
{
"epoch": 1.0,
"learning_rate": 2.6211278051158212e-05,
"loss": 3.4794,
"step": 1453056
},
{
"epoch": 1.0,
"learning_rate": 2.6202892103647692e-05,
"loss": 3.4899,
"step": 1453568
},
{
"epoch": 1.0,
"learning_rate": 2.6194506156137172e-05,
"loss": 3.4724,
"step": 1454080
},
{
"epoch": 1.0,
"learning_rate": 2.6186120208626652e-05,
"loss": 3.4924,
"step": 1454592
},
{
"epoch": 1.0,
"learning_rate": 2.6177734261116132e-05,
"loss": 3.4825,
"step": 1455104
},
{
"epoch": 1.0,
"learning_rate": 2.6169381071213074e-05,
"loss": 3.5005,
"step": 1455616
},
{
"epoch": 1.0,
"learning_rate": 2.6160995123702554e-05,
"loss": 3.493,
"step": 1456128
},
{
"epoch": 1.0,
"learning_rate": 2.6152609176192034e-05,
"loss": 3.4737,
"step": 1456640
},
{
"epoch": 1.0,
"learning_rate": 2.6144223228681514e-05,
"loss": 3.4777,
"step": 1457152
},
{
"epoch": 1.0,
"learning_rate": 2.6135837281170994e-05,
"loss": 3.4857,
"step": 1457664
},
{
"epoch": 1.0,
"learning_rate": 2.6127467712464203e-05,
"loss": 3.4742,
"step": 1458176
},
{
"epoch": 1.0,
"learning_rate": 2.6119081764953686e-05,
"loss": 3.4824,
"step": 1458688
},
{
"epoch": 1.0,
"learning_rate": 2.6110695817443166e-05,
"loss": 3.4855,
"step": 1459200
},
{
"epoch": 1.0,
"learning_rate": 2.6102309869932646e-05,
"loss": 3.4782,
"step": 1459712
},
{
"epoch": 1.0,
"learning_rate": 2.6093923922422126e-05,
"loss": 3.5049,
"step": 1460224
},
{
"epoch": 1.0,
"learning_rate": 2.6085537974911606e-05,
"loss": 3.486,
"step": 1460736
},
{
"epoch": 1.0,
"learning_rate": 2.6077152027401086e-05,
"loss": 3.484,
"step": 1461248
},
{
"epoch": 1.0,
"learning_rate": 2.6068766079890566e-05,
"loss": 3.4847,
"step": 1461760
},
{
"epoch": 1.0,
"learning_rate": 2.606039651118378e-05,
"loss": 3.4912,
"step": 1462272
},
{
"epoch": 1.0,
"learning_rate": 2.6052010563673258e-05,
"loss": 3.4791,
"step": 1462784
},
{
"epoch": 1.0,
"learning_rate": 2.6043624616162738e-05,
"loss": 3.4851,
"step": 1463296
},
{
"epoch": 1.0,
"learning_rate": 2.6035238668652218e-05,
"loss": 3.4819,
"step": 1463808
},
{
"epoch": 1.0,
"learning_rate": 2.6026869099945427e-05,
"loss": 3.4849,
"step": 1464320
},
{
"epoch": 1.0,
"learning_rate": 2.6018483152434907e-05,
"loss": 3.4757,
"step": 1464832
},
{
"epoch": 1.01,
"learning_rate": 2.6010097204924387e-05,
"loss": 3.4807,
"step": 1465344
},
{
"epoch": 1.01,
"learning_rate": 2.6001711257413867e-05,
"loss": 3.4855,
"step": 1465856
},
{
"epoch": 1.01,
"learning_rate": 2.599334168870708e-05,
"loss": 3.4867,
"step": 1466368
},
{
"epoch": 1.01,
"learning_rate": 2.598495574119656e-05,
"loss": 3.4884,
"step": 1466880
},
{
"epoch": 1.01,
"learning_rate": 2.597656979368604e-05,
"loss": 3.4877,
"step": 1467392
},
{
"epoch": 1.01,
"learning_rate": 2.596820022497925e-05,
"loss": 3.4791,
"step": 1467904
},
{
"epoch": 1.01,
"learning_rate": 2.595983065627246e-05,
"loss": 3.4905,
"step": 1468416
},
{
"epoch": 1.01,
"learning_rate": 2.595144470876194e-05,
"loss": 3.4729,
"step": 1468928
},
{
"epoch": 1.01,
"learning_rate": 2.594305876125142e-05,
"loss": 3.4919,
"step": 1469440
},
{
"epoch": 1.01,
"learning_rate": 2.59346728137409e-05,
"loss": 3.4714,
"step": 1469952
},
{
"epoch": 1.01,
"learning_rate": 2.592630324503411e-05,
"loss": 3.4805,
"step": 1470464
},
{
"epoch": 1.01,
"learning_rate": 2.5917917297523593e-05,
"loss": 3.4762,
"step": 1470976
},
{
"epoch": 1.01,
"learning_rate": 2.5909531350013073e-05,
"loss": 3.4969,
"step": 1471488
},
{
"epoch": 1.01,
"learning_rate": 2.5901145402502553e-05,
"loss": 3.4757,
"step": 1472000
},
{
"epoch": 1.01,
"learning_rate": 2.5892759454992033e-05,
"loss": 3.4812,
"step": 1472512
},
{
"epoch": 1.01,
"learning_rate": 2.5884373507481513e-05,
"loss": 3.4925,
"step": 1473024
},
{
"epoch": 1.01,
"learning_rate": 2.5875987559970993e-05,
"loss": 3.489,
"step": 1473536
},
{
"epoch": 1.01,
"learning_rate": 2.5867601612460473e-05,
"loss": 3.49,
"step": 1474048
},
{
"epoch": 1.01,
"learning_rate": 2.5859232043753682e-05,
"loss": 3.4709,
"step": 1474560
},
{
"epoch": 1.01,
"learning_rate": 2.5850862475046895e-05,
"loss": 3.4732,
"step": 1475072
},
{
"epoch": 1.01,
"learning_rate": 2.5842476527536375e-05,
"loss": 3.4859,
"step": 1475584
},
{
"epoch": 1.01,
"learning_rate": 2.5834090580025855e-05,
"loss": 3.4843,
"step": 1476096
},
{
"epoch": 1.01,
"learning_rate": 2.5825704632515335e-05,
"loss": 3.4783,
"step": 1476608
},
{
"epoch": 1.01,
"learning_rate": 2.5817318685004815e-05,
"loss": 3.4753,
"step": 1477120
},
{
"epoch": 1.01,
"learning_rate": 2.5808932737494295e-05,
"loss": 3.4843,
"step": 1477632
},
{
"epoch": 1.01,
"learning_rate": 2.580054678998377e-05,
"loss": 3.4615,
"step": 1478144
},
{
"epoch": 1.01,
"learning_rate": 2.579216084247325e-05,
"loss": 3.4845,
"step": 1478656
},
{
"epoch": 1.01,
"learning_rate": 2.5783791273766467e-05,
"loss": 3.4711,
"step": 1479168
},
{
"epoch": 1.01,
"learning_rate": 2.5775405326255947e-05,
"loss": 3.4796,
"step": 1479680
},
{
"epoch": 1.01,
"learning_rate": 2.576701937874542e-05,
"loss": 3.4876,
"step": 1480192
},
{
"epoch": 1.01,
"learning_rate": 2.5758633431234903e-05,
"loss": 3.4689,
"step": 1480704
},
{
"epoch": 1.01,
"learning_rate": 2.575026386252812e-05,
"loss": 3.4852,
"step": 1481216
},
{
"epoch": 1.01,
"learning_rate": 2.5741877915017592e-05,
"loss": 3.4742,
"step": 1481728
},
{
"epoch": 1.01,
"learning_rate": 2.5733491967507072e-05,
"loss": 3.4755,
"step": 1482240
},
{
"epoch": 1.01,
"learning_rate": 2.5725106019996552e-05,
"loss": 3.4685,
"step": 1482752
},
{
"epoch": 1.01,
"learning_rate": 2.5716736451289768e-05,
"loss": 3.4832,
"step": 1483264
},
{
"epoch": 1.01,
"learning_rate": 2.5708350503779245e-05,
"loss": 3.4709,
"step": 1483776
},
{
"epoch": 1.01,
"learning_rate": 2.5699964556268725e-05,
"loss": 3.4747,
"step": 1484288
},
{
"epoch": 1.01,
"learning_rate": 2.5691578608758205e-05,
"loss": 3.4654,
"step": 1484800
},
{
"epoch": 1.01,
"learning_rate": 2.568320904005142e-05,
"loss": 3.4709,
"step": 1485312
},
{
"epoch": 1.01,
"learning_rate": 2.5674823092540894e-05,
"loss": 3.4796,
"step": 1485824
},
{
"epoch": 1.01,
"learning_rate": 2.5666437145030374e-05,
"loss": 3.4863,
"step": 1486336
},
{
"epoch": 1.01,
"learning_rate": 2.5658051197519857e-05,
"loss": 3.4765,
"step": 1486848
},
{
"epoch": 1.01,
"learning_rate": 2.5649681628813066e-05,
"loss": 3.4879,
"step": 1487360
},
{
"epoch": 1.01,
"learning_rate": 2.5641295681302546e-05,
"loss": 3.4862,
"step": 1487872
},
{
"epoch": 1.01,
"learning_rate": 2.5632909733792026e-05,
"loss": 3.4801,
"step": 1488384
},
{
"epoch": 1.01,
"learning_rate": 2.5624523786281506e-05,
"loss": 3.4825,
"step": 1488896
},
{
"epoch": 1.01,
"learning_rate": 2.561615421757472e-05,
"loss": 3.4798,
"step": 1489408
},
{
"epoch": 1.01,
"learning_rate": 2.56077682700642e-05,
"loss": 3.4766,
"step": 1489920
},
{
"epoch": 1.01,
"learning_rate": 2.559938232255368e-05,
"loss": 3.4763,
"step": 1490432
},
{
"epoch": 1.01,
"learning_rate": 2.559099637504316e-05,
"loss": 3.4839,
"step": 1490944
},
{
"epoch": 1.01,
"learning_rate": 2.5582626806336367e-05,
"loss": 3.4874,
"step": 1491456
},
{
"epoch": 1.01,
"learning_rate": 2.5574240858825847e-05,
"loss": 3.4818,
"step": 1491968
},
{
"epoch": 1.01,
"learning_rate": 2.5565854911315327e-05,
"loss": 3.4817,
"step": 1492480
},
{
"epoch": 1.01,
"learning_rate": 2.555746896380481e-05,
"loss": 3.459,
"step": 1492992
},
{
"epoch": 1.01,
"learning_rate": 2.554909939509802e-05,
"loss": 3.4688,
"step": 1493504
},
{
"epoch": 1.01,
"learning_rate": 2.55407134475875e-05,
"loss": 3.4764,
"step": 1494016
},
{
"epoch": 1.01,
"learning_rate": 2.553232750007698e-05,
"loss": 3.4789,
"step": 1494528
},
{
"epoch": 1.01,
"learning_rate": 2.552394155256646e-05,
"loss": 3.4733,
"step": 1495040
},
{
"epoch": 1.01,
"learning_rate": 2.5515571983859672e-05,
"loss": 3.4797,
"step": 1495552
},
{
"epoch": 1.02,
"learning_rate": 2.5507202415152888e-05,
"loss": 3.4748,
"step": 1496064
},
{
"epoch": 1.02,
"learning_rate": 2.5498816467642368e-05,
"loss": 3.4705,
"step": 1496576
},
{
"epoch": 1.02,
"learning_rate": 2.549043052013184e-05,
"loss": 3.4762,
"step": 1497088
},
{
"epoch": 1.02,
"learning_rate": 2.548204457262132e-05,
"loss": 3.482,
"step": 1497600
},
{
"epoch": 1.02,
"learning_rate": 2.54736586251108e-05,
"loss": 3.4833,
"step": 1498112
},
{
"epoch": 1.02,
"learning_rate": 2.546527267760028e-05,
"loss": 3.4876,
"step": 1498624
},
{
"epoch": 1.02,
"learning_rate": 2.5456886730089764e-05,
"loss": 3.4737,
"step": 1499136
},
{
"epoch": 1.02,
"learning_rate": 2.5448500782579244e-05,
"loss": 3.4725,
"step": 1499648
},
{
"epoch": 1.02,
"learning_rate": 2.5440131213872453e-05,
"loss": 3.4791,
"step": 1500160
},
{
"epoch": 1.02,
"learning_rate": 2.5431745266361933e-05,
"loss": 3.4777,
"step": 1500672
},
{
"epoch": 1.02,
"learning_rate": 2.5423359318851413e-05,
"loss": 3.4839,
"step": 1501184
},
{
"epoch": 1.02,
"learning_rate": 2.5414973371340893e-05,
"loss": 3.4762,
"step": 1501696
},
{
"epoch": 1.02,
"learning_rate": 2.5406603802634106e-05,
"loss": 3.4767,
"step": 1502208
},
{
"epoch": 1.02,
"learning_rate": 2.5398217855123586e-05,
"loss": 3.4794,
"step": 1502720
},
{
"epoch": 1.02,
"learning_rate": 2.5389831907613066e-05,
"loss": 3.486,
"step": 1503232
},
{
"epoch": 1.02,
"learning_rate": 2.5381445960102546e-05,
"loss": 3.4695,
"step": 1503744
},
{
"epoch": 1.02,
"learning_rate": 2.5373076391395755e-05,
"loss": 3.4784,
"step": 1504256
},
{
"epoch": 1.02,
"learning_rate": 2.5364690443885235e-05,
"loss": 3.4774,
"step": 1504768
},
{
"epoch": 1.02,
"learning_rate": 2.5356304496374718e-05,
"loss": 3.4691,
"step": 1505280
},
{
"epoch": 1.02,
"learning_rate": 2.5347918548864198e-05,
"loss": 3.4638,
"step": 1505792
},
{
"epoch": 1.02,
"learning_rate": 2.5339548980157407e-05,
"loss": 3.4758,
"step": 1506304
},
{
"epoch": 1.02,
"learning_rate": 2.5331163032646887e-05,
"loss": 3.4755,
"step": 1506816
},
{
"epoch": 1.02,
"learning_rate": 2.5322777085136367e-05,
"loss": 3.4762,
"step": 1507328
},
{
"epoch": 1.02,
"learning_rate": 2.5314391137625847e-05,
"loss": 3.4715,
"step": 1507840
},
{
"epoch": 1.02,
"learning_rate": 2.530602156891906e-05,
"loss": 3.4724,
"step": 1508352
},
{
"epoch": 1.02,
"learning_rate": 2.529763562140854e-05,
"loss": 3.4899,
"step": 1508864
},
{
"epoch": 1.02,
"learning_rate": 2.528924967389802e-05,
"loss": 3.4909,
"step": 1509376
},
{
"epoch": 1.02,
"learning_rate": 2.52808637263875e-05,
"loss": 3.4826,
"step": 1509888
},
{
"epoch": 1.02,
"learning_rate": 2.527249415768071e-05,
"loss": 3.4825,
"step": 1510400
},
{
"epoch": 1.02,
"learning_rate": 2.526410821017019e-05,
"loss": 3.4764,
"step": 1510912
},
{
"epoch": 1.02,
"learning_rate": 2.5255722262659672e-05,
"loss": 3.4752,
"step": 1511424
},
{
"epoch": 1.02,
"learning_rate": 2.5247336315149152e-05,
"loss": 3.469,
"step": 1511936
},
{
"epoch": 1.02,
"learning_rate": 2.523896674644236e-05,
"loss": 3.4694,
"step": 1512448
},
{
"epoch": 1.02,
"learning_rate": 2.523058079893184e-05,
"loss": 3.4755,
"step": 1512960
},
{
"epoch": 1.02,
"learning_rate": 2.522219485142132e-05,
"loss": 3.484,
"step": 1513472
},
{
"epoch": 1.02,
"learning_rate": 2.5213825282714533e-05,
"loss": 3.4751,
"step": 1513984
},
{
"epoch": 1.02,
"learning_rate": 2.5205439335204013e-05,
"loss": 3.4818,
"step": 1514496
},
{
"epoch": 1.02,
"learning_rate": 2.5197053387693493e-05,
"loss": 3.4755,
"step": 1515008
},
{
"epoch": 1.02,
"learning_rate": 2.5188683818986702e-05,
"loss": 3.4714,
"step": 1515520
},
{
"epoch": 1.02,
"learning_rate": 2.5180297871476182e-05,
"loss": 3.4706,
"step": 1516032
},
{
"epoch": 1.02,
"learning_rate": 2.5171911923965662e-05,
"loss": 3.4904,
"step": 1516544
},
{
"epoch": 1.02,
"learning_rate": 2.5163525976455142e-05,
"loss": 3.49,
"step": 1517056
},
{
"epoch": 1.02,
"learning_rate": 2.5155140028944625e-05,
"loss": 3.4779,
"step": 1517568
},
{
"epoch": 1.02,
"learning_rate": 2.5146754081434105e-05,
"loss": 3.4744,
"step": 1518080
},
{
"epoch": 1.02,
"learning_rate": 2.5138368133923585e-05,
"loss": 3.4822,
"step": 1518592
},
{
"epoch": 1.02,
"learning_rate": 2.5129982186413065e-05,
"loss": 3.4751,
"step": 1519104
},
{
"epoch": 1.02,
"learning_rate": 2.5121612617706274e-05,
"loss": 3.4867,
"step": 1519616
},
{
"epoch": 1.02,
"learning_rate": 2.5113226670195754e-05,
"loss": 3.4754,
"step": 1520128
},
{
"epoch": 1.02,
"learning_rate": 2.5104840722685234e-05,
"loss": 3.4812,
"step": 1520640
},
{
"epoch": 1.02,
"learning_rate": 2.5096454775174714e-05,
"loss": 3.4742,
"step": 1521152
},
{
"epoch": 1.02,
"learning_rate": 2.5088085206467927e-05,
"loss": 3.4829,
"step": 1521664
},
{
"epoch": 1.02,
"learning_rate": 2.5079699258957407e-05,
"loss": 3.4721,
"step": 1522176
},
{
"epoch": 1.02,
"learning_rate": 2.5071313311446887e-05,
"loss": 3.4742,
"step": 1522688
},
{
"epoch": 1.02,
"learning_rate": 2.5062927363936367e-05,
"loss": 3.4807,
"step": 1523200
},
{
"epoch": 1.02,
"learning_rate": 2.5054557795229576e-05,
"loss": 3.4731,
"step": 1523712
},
{
"epoch": 1.02,
"learning_rate": 2.504617184771906e-05,
"loss": 3.4827,
"step": 1524224
},
{
"epoch": 1.02,
"learning_rate": 2.503778590020854e-05,
"loss": 3.4867,
"step": 1524736
},
{
"epoch": 1.02,
"learning_rate": 2.502939995269802e-05,
"loss": 3.478,
"step": 1525248
},
{
"epoch": 1.02,
"learning_rate": 2.5021030383991228e-05,
"loss": 3.4772,
"step": 1525760
},
{
"epoch": 1.02,
"learning_rate": 2.5012644436480708e-05,
"loss": 3.4732,
"step": 1526272
},
{
"epoch": 1.03,
"eval_loss": 3.8484647274017334,
"eval_runtime": 305.5789,
"eval_samples_per_second": 1248.748,
"eval_steps_per_second": 39.024,
"step": 1526400
},
{
"epoch": 0.0,
"learning_rate": 2.5004258488970188e-05,
"loss": 3.4665,
"step": 1526784
},
{
"epoch": 0.0,
"learning_rate": 2.4995872541459668e-05,
"loss": 3.4673,
"step": 1527296
},
{
"epoch": 0.0,
"learning_rate": 2.4987486593949148e-05,
"loss": 3.4849,
"step": 1527808
},
{
"epoch": 0.0,
"learning_rate": 2.4979100646438628e-05,
"loss": 3.4783,
"step": 1528320
},
{
"epoch": 0.0,
"learning_rate": 2.4970731077731837e-05,
"loss": 3.4903,
"step": 1528832
},
{
"epoch": 0.0,
"learning_rate": 2.4962345130221317e-05,
"loss": 3.4683,
"step": 1529344
},
{
"epoch": 0.0,
"learning_rate": 2.4953959182710797e-05,
"loss": 3.4803,
"step": 1529856
},
{
"epoch": 0.0,
"learning_rate": 2.494557323520028e-05,
"loss": 3.4585,
"step": 1530368
},
{
"epoch": 0.0,
"learning_rate": 2.493720366649349e-05,
"loss": 3.4836,
"step": 1530880
},
{
"epoch": 0.0,
"learning_rate": 2.492881771898297e-05,
"loss": 3.4713,
"step": 1531392
},
{
"epoch": 0.0,
"learning_rate": 2.492044815027618e-05,
"loss": 3.4823,
"step": 1531904
},
{
"epoch": 0.0,
"learning_rate": 2.4912062202765658e-05,
"loss": 3.4856,
"step": 1532416
},
{
"epoch": 0.0,
"learning_rate": 2.490367625525514e-05,
"loss": 3.4569,
"step": 1532928
},
{
"epoch": 0.0,
"learning_rate": 2.489529030774462e-05,
"loss": 3.47,
"step": 1533440
},
{
"epoch": 0.0,
"learning_rate": 2.48869043602341e-05,
"loss": 3.4747,
"step": 1533952
},
{
"epoch": 0.0,
"learning_rate": 2.487853479152731e-05,
"loss": 3.4627,
"step": 1534464
},
{
"epoch": 0.0,
"learning_rate": 2.487014884401679e-05,
"loss": 3.4703,
"step": 1534976
},
{
"epoch": 0.0,
"learning_rate": 2.486176289650627e-05,
"loss": 3.4711,
"step": 1535488
},
{
"epoch": 0.0,
"learning_rate": 2.485337694899575e-05,
"loss": 3.47,
"step": 1536000
},
{
"epoch": 0.0,
"learning_rate": 2.4844991001485234e-05,
"loss": 3.4883,
"step": 1536512
},
{
"epoch": 0.0,
"learning_rate": 2.483660505397471e-05,
"loss": 3.4725,
"step": 1537024
},
{
"epoch": 0.0,
"learning_rate": 2.482821910646419e-05,
"loss": 3.4724,
"step": 1537536
},
{
"epoch": 0.0,
"learning_rate": 2.481983315895367e-05,
"loss": 3.4738,
"step": 1538048
},
{
"epoch": 0.0,
"learning_rate": 2.4811463590246883e-05,
"loss": 3.4786,
"step": 1538560
},
{
"epoch": 0.0,
"learning_rate": 2.480307764273636e-05,
"loss": 3.468,
"step": 1539072
},
{
"epoch": 0.0,
"learning_rate": 2.4794691695225843e-05,
"loss": 3.4779,
"step": 1539584
},
{
"epoch": 0.0,
"learning_rate": 2.4786305747715323e-05,
"loss": 3.4641,
"step": 1540096
},
{
"epoch": 0.0,
"learning_rate": 2.4777936179008535e-05,
"loss": 3.4718,
"step": 1540608
},
{
"epoch": 0.0,
"learning_rate": 2.4769550231498012e-05,
"loss": 3.4633,
"step": 1541120
},
{
"epoch": 0.0,
"learning_rate": 2.476116428398749e-05,
"loss": 3.4691,
"step": 1541632
},
{
"epoch": 0.01,
"learning_rate": 2.475277833647697e-05,
"loss": 3.4722,
"step": 1542144
},
{
"epoch": 0.01,
"learning_rate": 2.4744408767770184e-05,
"loss": 3.4748,
"step": 1542656
},
{
"epoch": 0.01,
"learning_rate": 2.4736022820259664e-05,
"loss": 3.4762,
"step": 1543168
},
{
"epoch": 0.01,
"learning_rate": 2.4727636872749144e-05,
"loss": 3.4789,
"step": 1543680
},
{
"epoch": 0.01,
"learning_rate": 2.4719267304042357e-05,
"loss": 3.4668,
"step": 1544192
},
{
"epoch": 0.01,
"learning_rate": 2.4710897735335566e-05,
"loss": 3.478,
"step": 1544704
},
{
"epoch": 0.01,
"learning_rate": 2.470251178782505e-05,
"loss": 3.467,
"step": 1545216
},
{
"epoch": 0.01,
"learning_rate": 2.469412584031453e-05,
"loss": 3.4729,
"step": 1545728
},
{
"epoch": 0.01,
"learning_rate": 2.468573989280401e-05,
"loss": 3.4624,
"step": 1546240
},
{
"epoch": 0.01,
"learning_rate": 2.4677353945293485e-05,
"loss": 3.4691,
"step": 1546752
},
{
"epoch": 0.01,
"learning_rate": 2.4668967997782965e-05,
"loss": 3.4644,
"step": 1547264
},
{
"epoch": 0.01,
"learning_rate": 2.4660582050272445e-05,
"loss": 3.4829,
"step": 1547776
},
{
"epoch": 0.01,
"learning_rate": 2.4652212481565658e-05,
"loss": 3.4656,
"step": 1548288
},
{
"epoch": 0.01,
"learning_rate": 2.4643826534055138e-05,
"loss": 3.4681,
"step": 1548800
},
{
"epoch": 0.01,
"learning_rate": 2.4635440586544618e-05,
"loss": 3.4842,
"step": 1549312
},
{
"epoch": 0.01,
"learning_rate": 2.4627054639034098e-05,
"loss": 3.4754,
"step": 1549824
},
{
"epoch": 0.01,
"learning_rate": 2.4618685070327307e-05,
"loss": 3.4777,
"step": 1550336
},
{
"epoch": 0.01,
"learning_rate": 2.4610299122816787e-05,
"loss": 3.4642,
"step": 1550848
},
{
"epoch": 0.01,
"learning_rate": 2.460192955411e-05,
"loss": 3.455,
"step": 1551360
},
{
"epoch": 0.01,
"learning_rate": 2.459354360659948e-05,
"loss": 3.4775,
"step": 1551872
},
{
"epoch": 0.01,
"learning_rate": 2.458515765908896e-05,
"loss": 3.4731,
"step": 1552384
},
{
"epoch": 0.01,
"learning_rate": 2.457677171157844e-05,
"loss": 3.4638,
"step": 1552896
},
{
"epoch": 0.01,
"learning_rate": 2.456838576406792e-05,
"loss": 3.4654,
"step": 1553408
},
{
"epoch": 0.01,
"learning_rate": 2.45599998165574e-05,
"loss": 3.472,
"step": 1553920
},
{
"epoch": 0.01,
"learning_rate": 2.455161386904688e-05,
"loss": 3.4508,
"step": 1554432
},
{
"epoch": 0.01,
"learning_rate": 2.454322792153636e-05,
"loss": 3.4732,
"step": 1554944
},
{
"epoch": 0.01,
"learning_rate": 2.453485835282957e-05,
"loss": 3.4587,
"step": 1555456
},
{
"epoch": 0.01,
"learning_rate": 2.452647240531905e-05,
"loss": 3.4685,
"step": 1555968
},
{
"epoch": 0.01,
"learning_rate": 2.451808645780853e-05,
"loss": 3.4707,
"step": 1556480
},
{
"epoch": 0.01,
"learning_rate": 2.450971688910174e-05,
"loss": 3.46,
"step": 1556992
},
{
"epoch": 0.01,
"learning_rate": 2.450133094159122e-05,
"loss": 3.4692,
"step": 1557504
},
{
"epoch": 0.01,
"learning_rate": 2.4492944994080704e-05,
"loss": 3.4635,
"step": 1558016
},
{
"epoch": 0.01,
"learning_rate": 2.4484559046570184e-05,
"loss": 3.4633,
"step": 1558528
},
{
"epoch": 0.01,
"learning_rate": 2.447617309905966e-05,
"loss": 3.4626,
"step": 1559040
},
{
"epoch": 0.01,
"learning_rate": 2.446778715154914e-05,
"loss": 3.4671,
"step": 1559552
},
{
"epoch": 0.01,
"learning_rate": 2.445940120403862e-05,
"loss": 3.4635,
"step": 1560064
},
{
"epoch": 0.01,
"learning_rate": 2.44510152565281e-05,
"loss": 3.4617,
"step": 1560576
},
{
"epoch": 0.01,
"learning_rate": 2.4442645687821313e-05,
"loss": 3.4545,
"step": 1561088
},
{
"epoch": 0.01,
"learning_rate": 2.4434259740310793e-05,
"loss": 3.4556,
"step": 1561600
},
{
"epoch": 0.01,
"learning_rate": 2.4425873792800272e-05,
"loss": 3.4662,
"step": 1562112
},
{
"epoch": 0.01,
"learning_rate": 2.4417487845289752e-05,
"loss": 3.4762,
"step": 1562624
},
{
"epoch": 0.01,
"learning_rate": 2.440911827658296e-05,
"loss": 3.4627,
"step": 1563136
},
{
"epoch": 0.01,
"learning_rate": 2.440073232907244e-05,
"loss": 3.4791,
"step": 1563648
},
{
"epoch": 0.01,
"learning_rate": 2.439234638156192e-05,
"loss": 3.4746,
"step": 1564160
},
{
"epoch": 0.01,
"learning_rate": 2.4383960434051405e-05,
"loss": 3.4664,
"step": 1564672
},
{
"epoch": 0.01,
"learning_rate": 2.4375590865344614e-05,
"loss": 3.4683,
"step": 1565184
},
{
"epoch": 0.01,
"learning_rate": 2.4367204917834094e-05,
"loss": 3.4751,
"step": 1565696
},
{
"epoch": 0.01,
"learning_rate": 2.4358818970323574e-05,
"loss": 3.4645,
"step": 1566208
},
{
"epoch": 0.01,
"learning_rate": 2.4350433022813054e-05,
"loss": 3.4649,
"step": 1566720
},
{
"epoch": 0.01,
"learning_rate": 2.4342063454106266e-05,
"loss": 3.4745,
"step": 1567232
},
{
"epoch": 0.01,
"learning_rate": 2.4333677506595746e-05,
"loss": 3.4718,
"step": 1567744
},
{
"epoch": 0.01,
"learning_rate": 2.432530793788896e-05,
"loss": 3.4718,
"step": 1568256
},
{
"epoch": 0.01,
"learning_rate": 2.4316921990378435e-05,
"loss": 3.4679,
"step": 1568768
},
{
"epoch": 0.01,
"learning_rate": 2.4308536042867915e-05,
"loss": 3.4494,
"step": 1569280
},
{
"epoch": 0.01,
"learning_rate": 2.4300150095357395e-05,
"loss": 3.4545,
"step": 1569792
},
{
"epoch": 0.01,
"learning_rate": 2.4291764147846875e-05,
"loss": 3.4656,
"step": 1570304
},
{
"epoch": 0.01,
"learning_rate": 2.428337820033636e-05,
"loss": 3.4686,
"step": 1570816
},
{
"epoch": 0.01,
"learning_rate": 2.427499225282584e-05,
"loss": 3.463,
"step": 1571328
},
{
"epoch": 0.01,
"learning_rate": 2.4266622684119048e-05,
"loss": 3.4648,
"step": 1571840
},
{
"epoch": 0.02,
"learning_rate": 2.4258253115412257e-05,
"loss": 3.4608,
"step": 1572352
},
{
"epoch": 0.02,
"learning_rate": 2.4249867167901737e-05,
"loss": 3.4593,
"step": 1572864
},
{
"epoch": 0.02,
"learning_rate": 2.424148122039122e-05,
"loss": 3.4633,
"step": 1573376
},
{
"epoch": 0.02,
"learning_rate": 2.42330952728807e-05,
"loss": 3.4662,
"step": 1573888
},
{
"epoch": 0.02,
"learning_rate": 2.422470932537018e-05,
"loss": 3.4725,
"step": 1574400
},
{
"epoch": 0.02,
"learning_rate": 2.421632337785966e-05,
"loss": 3.4719,
"step": 1574912
},
{
"epoch": 0.02,
"learning_rate": 2.420793743034914e-05,
"loss": 3.4672,
"step": 1575424
},
{
"epoch": 0.02,
"learning_rate": 2.4199551482838616e-05,
"loss": 3.4573,
"step": 1575936
},
{
"epoch": 0.02,
"learning_rate": 2.419118191413183e-05,
"loss": 3.4731,
"step": 1576448
},
{
"epoch": 0.02,
"learning_rate": 2.4182795966621312e-05,
"loss": 3.4636,
"step": 1576960
},
{
"epoch": 0.02,
"learning_rate": 2.417441001911079e-05,
"loss": 3.4704,
"step": 1577472
},
{
"epoch": 0.02,
"learning_rate": 2.416602407160027e-05,
"loss": 3.4649,
"step": 1577984
},
{
"epoch": 0.02,
"learning_rate": 2.415765450289348e-05,
"loss": 3.4605,
"step": 1578496
},
{
"epoch": 0.02,
"learning_rate": 2.414926855538296e-05,
"loss": 3.4732,
"step": 1579008
},
{
"epoch": 0.02,
"learning_rate": 2.4140882607872438e-05,
"loss": 3.4711,
"step": 1579520
},
{
"epoch": 0.02,
"learning_rate": 2.413249666036192e-05,
"loss": 3.4609,
"step": 1580032
},
{
"epoch": 0.02,
"learning_rate": 2.4124127091655133e-05,
"loss": 3.4669,
"step": 1580544
},
{
"epoch": 0.02,
"learning_rate": 2.4115741144144613e-05,
"loss": 3.4656,
"step": 1581056
},
{
"epoch": 0.02,
"learning_rate": 2.4107371575437823e-05,
"loss": 3.4513,
"step": 1581568
},
{
"epoch": 0.02,
"learning_rate": 2.4098985627927303e-05,
"loss": 3.4538,
"step": 1582080
},
{
"epoch": 0.02,
"learning_rate": 2.4090599680416782e-05,
"loss": 3.4691,
"step": 1582592
},
{
"epoch": 0.02,
"learning_rate": 2.4082213732906262e-05,
"loss": 3.4605,
"step": 1583104
},
{
"epoch": 0.02,
"learning_rate": 2.4073827785395742e-05,
"loss": 3.4648,
"step": 1583616
},
{
"epoch": 0.02,
"learning_rate": 2.4065441837885222e-05,
"loss": 3.46,
"step": 1584128
},
{
"epoch": 0.02,
"learning_rate": 2.4057055890374702e-05,
"loss": 3.4585,
"step": 1584640
},
{
"epoch": 0.02,
"learning_rate": 2.4048669942864182e-05,
"loss": 3.4783,
"step": 1585152
},
{
"epoch": 0.02,
"learning_rate": 2.404030037415739e-05,
"loss": 3.4802,
"step": 1585664
},
{
"epoch": 0.02,
"learning_rate": 2.4031914426646875e-05,
"loss": 3.4692,
"step": 1586176
},
{
"epoch": 0.02,
"learning_rate": 2.4023528479136355e-05,
"loss": 3.4714,
"step": 1586688
},
{
"epoch": 0.02,
"learning_rate": 2.4015142531625835e-05,
"loss": 3.4616,
"step": 1587200
},
{
"epoch": 0.02,
"learning_rate": 2.4006772962919044e-05,
"loss": 3.4641,
"step": 1587712
},
{
"epoch": 0.02,
"learning_rate": 2.3998387015408524e-05,
"loss": 3.4593,
"step": 1588224
},
{
"epoch": 0.02,
"learning_rate": 2.3990001067898004e-05,
"loss": 3.4621,
"step": 1588736
},
{
"epoch": 0.02,
"learning_rate": 2.3981631499191216e-05,
"loss": 3.4618,
"step": 1589248
},
{
"epoch": 0.02,
"learning_rate": 2.3973245551680696e-05,
"loss": 3.4703,
"step": 1589760
},
{
"epoch": 0.02,
"learning_rate": 2.3964859604170176e-05,
"loss": 3.4644,
"step": 1590272
},
{
"epoch": 0.02,
"learning_rate": 2.3956473656659656e-05,
"loss": 3.4655,
"step": 1590784
},
{
"epoch": 0.02,
"learning_rate": 2.3948104087952865e-05,
"loss": 3.4644,
"step": 1591296
},
{
"epoch": 0.02,
"learning_rate": 2.393973451924608e-05,
"loss": 3.46,
"step": 1591808
},
{
"epoch": 0.02,
"learning_rate": 2.3931348571735557e-05,
"loss": 3.4633,
"step": 1592320
},
{
"epoch": 0.02,
"learning_rate": 2.3922962624225037e-05,
"loss": 3.4726,
"step": 1592832
},
{
"epoch": 0.02,
"learning_rate": 2.3914576676714517e-05,
"loss": 3.4783,
"step": 1593344
},
{
"epoch": 0.02,
"learning_rate": 2.3906190729203997e-05,
"loss": 3.4687,
"step": 1593856
},
{
"epoch": 0.02,
"learning_rate": 2.3897804781693477e-05,
"loss": 3.4645,
"step": 1594368
},
{
"epoch": 0.02,
"learning_rate": 2.3889418834182957e-05,
"loss": 3.4703,
"step": 1594880
},
{
"epoch": 0.02,
"learning_rate": 2.3881032886672437e-05,
"loss": 3.4628,
"step": 1595392
},
{
"epoch": 0.02,
"learning_rate": 2.387266331796565e-05,
"loss": 3.475,
"step": 1595904
},
{
"epoch": 0.02,
"learning_rate": 2.386427737045513e-05,
"loss": 3.4629,
"step": 1596416
},
{
"epoch": 0.02,
"learning_rate": 2.385589142294461e-05,
"loss": 3.467,
"step": 1596928
},
{
"epoch": 0.02,
"learning_rate": 2.384750547543409e-05,
"loss": 3.4639,
"step": 1597440
},
{
"epoch": 0.02,
"learning_rate": 2.38391359067273e-05,
"loss": 3.4748,
"step": 1597952
},
{
"epoch": 0.02,
"learning_rate": 2.3830749959216782e-05,
"loss": 3.4582,
"step": 1598464
},
{
"epoch": 0.02,
"learning_rate": 2.3822364011706262e-05,
"loss": 3.4627,
"step": 1598976
},
{
"epoch": 0.02,
"learning_rate": 2.381397806419574e-05,
"loss": 3.4685,
"step": 1599488
},
{
"epoch": 0.02,
"learning_rate": 2.380560849548895e-05,
"loss": 3.4623,
"step": 1600000
},
{
"epoch": 0.02,
"learning_rate": 2.379722254797843e-05,
"loss": 3.4707,
"step": 1600512
},
{
"epoch": 0.02,
"learning_rate": 2.378883660046791e-05,
"loss": 3.4712,
"step": 1601024
},
{
"epoch": 0.02,
"learning_rate": 2.378045065295739e-05,
"loss": 3.4691,
"step": 1601536
},
{
"epoch": 0.02,
"learning_rate": 2.3772081084250603e-05,
"loss": 3.4624,
"step": 1602048
},
{
"epoch": 0.02,
"learning_rate": 2.3763695136740083e-05,
"loss": 3.4634,
"step": 1602560
},
{
"epoch": 0.03,
"eval_loss": 3.8500735759735107,
"eval_runtime": 305.4526,
"eval_samples_per_second": 1249.264,
"eval_steps_per_second": 39.04,
"step": 1602720
},
{
"epoch": 1.0,
"learning_rate": 2.3755309189229563e-05,
"loss": 3.4637,
"step": 1603072
},
{
"epoch": 1.0,
"learning_rate": 2.374692324171904e-05,
"loss": 3.4529,
"step": 1603584
},
{
"epoch": 1.0,
"learning_rate": 2.3738553673012252e-05,
"loss": 3.4742,
"step": 1604096
},
{
"epoch": 1.0,
"learning_rate": 2.3730167725501736e-05,
"loss": 3.4694,
"step": 1604608
},
{
"epoch": 1.0,
"learning_rate": 2.3721781777991212e-05,
"loss": 3.4743,
"step": 1605120
},
{
"epoch": 1.0,
"learning_rate": 2.3713395830480692e-05,
"loss": 3.4602,
"step": 1605632
},
{
"epoch": 1.0,
"learning_rate": 2.3705026261773905e-05,
"loss": 3.4629,
"step": 1606144
},
{
"epoch": 1.0,
"learning_rate": 2.3696640314263385e-05,
"loss": 3.4539,
"step": 1606656
},
{
"epoch": 1.0,
"learning_rate": 2.368825436675286e-05,
"loss": 3.465,
"step": 1607168
},
{
"epoch": 1.0,
"learning_rate": 2.3679868419242345e-05,
"loss": 3.4611,
"step": 1607680
},
{
"epoch": 1.0,
"learning_rate": 2.3671515229339286e-05,
"loss": 3.4708,
"step": 1608192
},
{
"epoch": 1.0,
"learning_rate": 2.3663129281828766e-05,
"loss": 3.4728,
"step": 1608704
},
{
"epoch": 1.0,
"learning_rate": 2.3654743334318246e-05,
"loss": 3.4454,
"step": 1609216
},
{
"epoch": 1.0,
"learning_rate": 2.3646357386807726e-05,
"loss": 3.4582,
"step": 1609728
},
{
"epoch": 1.0,
"learning_rate": 2.3637971439297206e-05,
"loss": 3.4624,
"step": 1610240
},
{
"epoch": 1.0,
"learning_rate": 2.362960187059042e-05,
"loss": 3.4522,
"step": 1610752
},
{
"epoch": 1.0,
"learning_rate": 2.36212159230799e-05,
"loss": 3.4579,
"step": 1611264
},
{
"epoch": 1.0,
"learning_rate": 2.361282997556938e-05,
"loss": 3.4583,
"step": 1611776
},
{
"epoch": 1.0,
"learning_rate": 2.360444402805886e-05,
"loss": 3.4576,
"step": 1612288
},
{
"epoch": 1.0,
"learning_rate": 2.3596058080548335e-05,
"loss": 3.4735,
"step": 1612800
},
{
"epoch": 1.0,
"learning_rate": 2.3587672133037815e-05,
"loss": 3.4615,
"step": 1613312
},
{
"epoch": 1.0,
"learning_rate": 2.3579286185527298e-05,
"loss": 3.4637,
"step": 1613824
},
{
"epoch": 1.0,
"learning_rate": 2.3570900238016778e-05,
"loss": 3.4613,
"step": 1614336
},
{
"epoch": 1.0,
"learning_rate": 2.3562530669309987e-05,
"loss": 3.4646,
"step": 1614848
},
{
"epoch": 1.0,
"learning_rate": 2.3554144721799467e-05,
"loss": 3.4572,
"step": 1615360
},
{
"epoch": 1.0,
"learning_rate": 2.3545758774288947e-05,
"loss": 3.4665,
"step": 1615872
},
{
"epoch": 1.0,
"learning_rate": 2.3537372826778427e-05,
"loss": 3.4597,
"step": 1616384
},
{
"epoch": 1.0,
"learning_rate": 2.352900325807164e-05,
"loss": 3.4556,
"step": 1616896
},
{
"epoch": 1.0,
"learning_rate": 2.352061731056112e-05,
"loss": 3.4539,
"step": 1617408
},
{
"epoch": 1.0,
"learning_rate": 2.35122313630506e-05,
"loss": 3.4585,
"step": 1617920
},
{
"epoch": 1.01,
"learning_rate": 2.350384541554008e-05,
"loss": 3.4608,
"step": 1618432
},
{
"epoch": 1.01,
"learning_rate": 2.349547584683329e-05,
"loss": 3.4628,
"step": 1618944
},
{
"epoch": 1.01,
"learning_rate": 2.348708989932277e-05,
"loss": 3.4686,
"step": 1619456
},
{
"epoch": 1.01,
"learning_rate": 2.3478703951812252e-05,
"loss": 3.466,
"step": 1619968
},
{
"epoch": 1.01,
"learning_rate": 2.3470318004301732e-05,
"loss": 3.4557,
"step": 1620480
},
{
"epoch": 1.01,
"learning_rate": 2.3461964814398673e-05,
"loss": 3.4649,
"step": 1620992
},
{
"epoch": 1.01,
"learning_rate": 2.3453578866888153e-05,
"loss": 3.4594,
"step": 1621504
},
{
"epoch": 1.01,
"learning_rate": 2.344519291937763e-05,
"loss": 3.4613,
"step": 1622016
},
{
"epoch": 1.01,
"learning_rate": 2.3436806971867113e-05,
"loss": 3.4477,
"step": 1622528
},
{
"epoch": 1.01,
"learning_rate": 2.3428437403160326e-05,
"loss": 3.4533,
"step": 1623040
},
{
"epoch": 1.01,
"learning_rate": 2.3420051455649806e-05,
"loss": 3.4571,
"step": 1623552
},
{
"epoch": 1.01,
"learning_rate": 2.3411665508139282e-05,
"loss": 3.469,
"step": 1624064
},
{
"epoch": 1.01,
"learning_rate": 2.3403279560628762e-05,
"loss": 3.4552,
"step": 1624576
},
{
"epoch": 1.01,
"learning_rate": 2.3394893613118242e-05,
"loss": 3.4562,
"step": 1625088
},
{
"epoch": 1.01,
"learning_rate": 2.3386507665607722e-05,
"loss": 3.4731,
"step": 1625600
},
{
"epoch": 1.01,
"learning_rate": 2.3378121718097206e-05,
"loss": 3.4619,
"step": 1626112
},
{
"epoch": 1.01,
"learning_rate": 2.3369735770586686e-05,
"loss": 3.466,
"step": 1626624
},
{
"epoch": 1.01,
"learning_rate": 2.3361366201879895e-05,
"loss": 3.4532,
"step": 1627136
},
{
"epoch": 1.01,
"learning_rate": 2.3352996633173104e-05,
"loss": 3.442,
"step": 1627648
},
{
"epoch": 1.01,
"learning_rate": 2.3344610685662584e-05,
"loss": 3.464,
"step": 1628160
},
{
"epoch": 1.01,
"learning_rate": 2.3336224738152067e-05,
"loss": 3.4626,
"step": 1628672
},
{
"epoch": 1.01,
"learning_rate": 2.3327838790641547e-05,
"loss": 3.4547,
"step": 1629184
},
{
"epoch": 1.01,
"learning_rate": 2.3319452843131027e-05,
"loss": 3.4542,
"step": 1629696
},
{
"epoch": 1.01,
"learning_rate": 2.3311066895620507e-05,
"loss": 3.46,
"step": 1630208
},
{
"epoch": 1.01,
"learning_rate": 2.3302680948109987e-05,
"loss": 3.4345,
"step": 1630720
},
{
"epoch": 1.01,
"learning_rate": 2.3294295000599463e-05,
"loss": 3.4617,
"step": 1631232
},
{
"epoch": 1.01,
"learning_rate": 2.3285925431892676e-05,
"loss": 3.4495,
"step": 1631744
},
{
"epoch": 1.01,
"learning_rate": 2.327753948438216e-05,
"loss": 3.4549,
"step": 1632256
},
{
"epoch": 1.01,
"learning_rate": 2.3269153536871636e-05,
"loss": 3.4627,
"step": 1632768
},
{
"epoch": 1.01,
"learning_rate": 2.3260783968164848e-05,
"loss": 3.4524,
"step": 1633280
},
{
"epoch": 1.01,
"learning_rate": 2.3252398020654328e-05,
"loss": 3.4553,
"step": 1633792
},
{
"epoch": 1.01,
"learning_rate": 2.3244012073143808e-05,
"loss": 3.4579,
"step": 1634304
},
{
"epoch": 1.01,
"learning_rate": 2.3235626125633285e-05,
"loss": 3.45,
"step": 1634816
},
{
"epoch": 1.01,
"learning_rate": 2.3227240178122768e-05,
"loss": 3.4453,
"step": 1635328
},
{
"epoch": 1.01,
"learning_rate": 2.3218854230612248e-05,
"loss": 3.4577,
"step": 1635840
},
{
"epoch": 1.01,
"learning_rate": 2.3210468283101728e-05,
"loss": 3.4567,
"step": 1636352
},
{
"epoch": 1.01,
"learning_rate": 2.3202082335591208e-05,
"loss": 3.4472,
"step": 1636864
},
{
"epoch": 1.01,
"learning_rate": 2.3193712766884417e-05,
"loss": 3.446,
"step": 1637376
},
{
"epoch": 1.01,
"learning_rate": 2.3185326819373897e-05,
"loss": 3.446,
"step": 1637888
},
{
"epoch": 1.01,
"learning_rate": 2.3176940871863377e-05,
"loss": 3.4509,
"step": 1638400
},
{
"epoch": 1.01,
"learning_rate": 2.316855492435286e-05,
"loss": 3.4608,
"step": 1638912
},
{
"epoch": 1.01,
"learning_rate": 2.316018535564607e-05,
"loss": 3.4511,
"step": 1639424
},
{
"epoch": 1.01,
"learning_rate": 2.315179940813555e-05,
"loss": 3.4693,
"step": 1639936
},
{
"epoch": 1.01,
"learning_rate": 2.314341346062503e-05,
"loss": 3.4636,
"step": 1640448
},
{
"epoch": 1.01,
"learning_rate": 2.313502751311451e-05,
"loss": 3.4592,
"step": 1640960
},
{
"epoch": 1.01,
"learning_rate": 2.3126657944407722e-05,
"loss": 3.4509,
"step": 1641472
},
{
"epoch": 1.01,
"learning_rate": 2.3118271996897202e-05,
"loss": 3.4641,
"step": 1641984
},
{
"epoch": 1.01,
"learning_rate": 2.310988604938668e-05,
"loss": 3.4545,
"step": 1642496
},
{
"epoch": 1.01,
"learning_rate": 2.310150010187616e-05,
"loss": 3.4496,
"step": 1643008
},
{
"epoch": 1.01,
"learning_rate": 2.309313053316937e-05,
"loss": 3.4646,
"step": 1643520
},
{
"epoch": 1.01,
"learning_rate": 2.308474458565885e-05,
"loss": 3.4578,
"step": 1644032
},
{
"epoch": 1.01,
"learning_rate": 2.307635863814833e-05,
"loss": 3.4602,
"step": 1644544
},
{
"epoch": 1.01,
"learning_rate": 2.3067972690637814e-05,
"loss": 3.4598,
"step": 1645056
},
{
"epoch": 1.01,
"learning_rate": 2.3059603121931023e-05,
"loss": 3.4433,
"step": 1645568
},
{
"epoch": 1.01,
"learning_rate": 2.3051217174420503e-05,
"loss": 3.4399,
"step": 1646080
},
{
"epoch": 1.01,
"learning_rate": 2.3042831226909983e-05,
"loss": 3.4528,
"step": 1646592
},
{
"epoch": 1.01,
"learning_rate": 2.3034445279399463e-05,
"loss": 3.4577,
"step": 1647104
},
{
"epoch": 1.01,
"learning_rate": 2.3026075710692675e-05,
"loss": 3.453,
"step": 1647616
},
{
"epoch": 1.01,
"learning_rate": 2.3017689763182155e-05,
"loss": 3.4514,
"step": 1648128
},
{
"epoch": 1.02,
"learning_rate": 2.3009320194475364e-05,
"loss": 3.4528,
"step": 1648640
},
{
"epoch": 1.02,
"learning_rate": 2.3000934246964844e-05,
"loss": 3.4438,
"step": 1649152
},
{
"epoch": 1.02,
"learning_rate": 2.2992548299454324e-05,
"loss": 3.4579,
"step": 1649664
},
{
"epoch": 1.02,
"learning_rate": 2.2984162351943804e-05,
"loss": 3.4496,
"step": 1650176
},
{
"epoch": 1.02,
"learning_rate": 2.2975776404433284e-05,
"loss": 3.463,
"step": 1650688
},
{
"epoch": 1.02,
"learning_rate": 2.2967390456922764e-05,
"loss": 3.4642,
"step": 1651200
},
{
"epoch": 1.02,
"learning_rate": 2.2959004509412244e-05,
"loss": 3.4581,
"step": 1651712
},
{
"epoch": 1.02,
"learning_rate": 2.2950618561901724e-05,
"loss": 3.4475,
"step": 1652224
},
{
"epoch": 1.02,
"learning_rate": 2.2942248993194937e-05,
"loss": 3.4568,
"step": 1652736
},
{
"epoch": 1.02,
"learning_rate": 2.2933863045684413e-05,
"loss": 3.4513,
"step": 1653248
},
{
"epoch": 1.02,
"learning_rate": 2.2925477098173893e-05,
"loss": 3.462,
"step": 1653760
},
{
"epoch": 1.02,
"learning_rate": 2.2917091150663377e-05,
"loss": 3.4519,
"step": 1654272
},
{
"epoch": 1.02,
"learning_rate": 2.290872158195659e-05,
"loss": 3.4513,
"step": 1654784
},
{
"epoch": 1.02,
"learning_rate": 2.2900335634446066e-05,
"loss": 3.4597,
"step": 1655296
},
{
"epoch": 1.02,
"learning_rate": 2.2891949686935546e-05,
"loss": 3.4579,
"step": 1655808
},
{
"epoch": 1.02,
"learning_rate": 2.2883563739425025e-05,
"loss": 3.4519,
"step": 1656320
},
{
"epoch": 1.02,
"learning_rate": 2.2875194170718238e-05,
"loss": 3.4569,
"step": 1656832
},
{
"epoch": 1.02,
"learning_rate": 2.2866808223207718e-05,
"loss": 3.4511,
"step": 1657344
},
{
"epoch": 1.02,
"learning_rate": 2.285843865450093e-05,
"loss": 3.4477,
"step": 1657856
},
{
"epoch": 1.02,
"learning_rate": 2.285005270699041e-05,
"loss": 3.4359,
"step": 1658368
},
{
"epoch": 1.02,
"learning_rate": 2.2841666759479887e-05,
"loss": 3.4583,
"step": 1658880
},
{
"epoch": 1.02,
"learning_rate": 2.2833280811969367e-05,
"loss": 3.4532,
"step": 1659392
},
{
"epoch": 1.02,
"learning_rate": 2.2824894864458847e-05,
"loss": 3.4526,
"step": 1659904
},
{
"epoch": 1.02,
"learning_rate": 2.281650891694833e-05,
"loss": 3.4512,
"step": 1660416
},
{
"epoch": 1.02,
"learning_rate": 2.280812296943781e-05,
"loss": 3.4437,
"step": 1660928
},
{
"epoch": 1.02,
"learning_rate": 2.279973702192729e-05,
"loss": 3.4668,
"step": 1661440
},
{
"epoch": 1.02,
"learning_rate": 2.27913674532205e-05,
"loss": 3.4692,
"step": 1661952
},
{
"epoch": 1.02,
"learning_rate": 2.278298150570998e-05,
"loss": 3.4603,
"step": 1662464
},
{
"epoch": 1.02,
"learning_rate": 2.277459555819946e-05,
"loss": 3.4596,
"step": 1662976
},
{
"epoch": 1.02,
"learning_rate": 2.276620961068894e-05,
"loss": 3.4506,
"step": 1663488
},
{
"epoch": 1.02,
"learning_rate": 2.275784004198215e-05,
"loss": 3.4527,
"step": 1664000
},
{
"epoch": 1.02,
"learning_rate": 2.274945409447163e-05,
"loss": 3.4476,
"step": 1664512
},
{
"epoch": 1.02,
"learning_rate": 2.274106814696111e-05,
"loss": 3.4481,
"step": 1665024
},
{
"epoch": 1.02,
"learning_rate": 2.273268219945059e-05,
"loss": 3.4559,
"step": 1665536
},
{
"epoch": 1.02,
"learning_rate": 2.27243126307438e-05,
"loss": 3.4572,
"step": 1666048
},
{
"epoch": 1.02,
"learning_rate": 2.2715926683233284e-05,
"loss": 3.4562,
"step": 1666560
},
{
"epoch": 1.02,
"learning_rate": 2.2707540735722764e-05,
"loss": 3.4517,
"step": 1667072
},
{
"epoch": 1.02,
"learning_rate": 2.2699171167015973e-05,
"loss": 3.4547,
"step": 1667584
},
{
"epoch": 1.02,
"learning_rate": 2.2690801598309182e-05,
"loss": 3.45,
"step": 1668096
},
{
"epoch": 1.02,
"learning_rate": 2.2682415650798662e-05,
"loss": 3.4538,
"step": 1668608
},
{
"epoch": 1.02,
"learning_rate": 2.2674029703288145e-05,
"loss": 3.4561,
"step": 1669120
},
{
"epoch": 1.02,
"learning_rate": 2.2665643755777625e-05,
"loss": 3.4642,
"step": 1669632
},
{
"epoch": 1.02,
"learning_rate": 2.2657257808267105e-05,
"loss": 3.4629,
"step": 1670144
},
{
"epoch": 1.02,
"learning_rate": 2.2648871860756585e-05,
"loss": 3.4502,
"step": 1670656
},
{
"epoch": 1.02,
"learning_rate": 2.2640485913246065e-05,
"loss": 3.4598,
"step": 1671168
},
{
"epoch": 1.02,
"learning_rate": 2.2632099965735542e-05,
"loss": 3.4548,
"step": 1671680
},
{
"epoch": 1.02,
"learning_rate": 2.2623730397028754e-05,
"loss": 3.4586,
"step": 1672192
},
{
"epoch": 1.02,
"learning_rate": 2.2615344449518238e-05,
"loss": 3.456,
"step": 1672704
},
{
"epoch": 1.02,
"learning_rate": 2.2606958502007714e-05,
"loss": 3.4594,
"step": 1673216
},
{
"epoch": 1.02,
"learning_rate": 2.2598572554497194e-05,
"loss": 3.4516,
"step": 1673728
},
{
"epoch": 1.02,
"learning_rate": 2.2590202985790407e-05,
"loss": 3.4602,
"step": 1674240
},
{
"epoch": 1.02,
"learning_rate": 2.2581817038279886e-05,
"loss": 3.4463,
"step": 1674752
},
{
"epoch": 1.02,
"learning_rate": 2.2573431090769363e-05,
"loss": 3.4534,
"step": 1675264
},
{
"epoch": 1.02,
"learning_rate": 2.2565045143258846e-05,
"loss": 3.4535,
"step": 1675776
},
{
"epoch": 1.02,
"learning_rate": 2.255667557455206e-05,
"loss": 3.4572,
"step": 1676288
},
{
"epoch": 1.02,
"learning_rate": 2.254828962704154e-05,
"loss": 3.4598,
"step": 1676800
},
{
"epoch": 1.02,
"learning_rate": 2.2539903679531015e-05,
"loss": 3.4551,
"step": 1677312
},
{
"epoch": 1.02,
"learning_rate": 2.2531517732020495e-05,
"loss": 3.4652,
"step": 1677824
},
{
"epoch": 1.02,
"learning_rate": 2.2523148163313708e-05,
"loss": 3.4466,
"step": 1678336
},
{
"epoch": 1.02,
"learning_rate": 2.2514762215803188e-05,
"loss": 3.4544,
"step": 1678848
},
{
"epoch": 1.03,
"eval_loss": 3.8525116443634033,
"eval_runtime": 305.8116,
"eval_samples_per_second": 1247.798,
"eval_steps_per_second": 38.995,
"step": 1679040
},
{
"epoch": 0.0,
"learning_rate": 2.2506376268292668e-05,
"loss": 3.4493,
"step": 1679360
},
{
"epoch": 0.0,
"learning_rate": 2.2497990320782148e-05,
"loss": 3.4409,
"step": 1679872
},
{
"epoch": 0.0,
"learning_rate": 2.2489604373271628e-05,
"loss": 3.4639,
"step": 1680384
},
{
"epoch": 0.0,
"learning_rate": 2.2481218425761108e-05,
"loss": 3.4573,
"step": 1680896
},
{
"epoch": 0.0,
"learning_rate": 2.2472848857054317e-05,
"loss": 3.467,
"step": 1681408
},
{
"epoch": 0.0,
"learning_rate": 2.24644629095438e-05,
"loss": 3.4467,
"step": 1681920
},
{
"epoch": 0.0,
"learning_rate": 2.245607696203328e-05,
"loss": 3.4487,
"step": 1682432
},
{
"epoch": 0.0,
"learning_rate": 2.244769101452276e-05,
"loss": 3.4456,
"step": 1682944
},
{
"epoch": 0.0,
"learning_rate": 2.243932144581597e-05,
"loss": 3.4534,
"step": 1683456
},
{
"epoch": 0.0,
"learning_rate": 2.243093549830545e-05,
"loss": 3.4503,
"step": 1683968
},
{
"epoch": 0.0,
"learning_rate": 2.242256592959866e-05,
"loss": 3.4607,
"step": 1684480
},
{
"epoch": 0.0,
"learning_rate": 2.241417998208814e-05,
"loss": 3.4625,
"step": 1684992
},
{
"epoch": 0.0,
"learning_rate": 2.240579403457762e-05,
"loss": 3.4374,
"step": 1685504
},
{
"epoch": 0.0,
"learning_rate": 2.23974080870671e-05,
"loss": 3.4426,
"step": 1686016
},
{
"epoch": 0.0,
"learning_rate": 2.238902213955658e-05,
"loss": 3.4534,
"step": 1686528
},
{
"epoch": 0.0,
"learning_rate": 2.238065257084979e-05,
"loss": 3.4407,
"step": 1687040
},
{
"epoch": 0.0,
"learning_rate": 2.237226662333927e-05,
"loss": 3.446,
"step": 1687552
},
{
"epoch": 0.0,
"learning_rate": 2.2363880675828754e-05,
"loss": 3.449,
"step": 1688064
},
{
"epoch": 0.0,
"learning_rate": 2.2355494728318234e-05,
"loss": 3.4453,
"step": 1688576
},
{
"epoch": 0.0,
"learning_rate": 2.2347108780807714e-05,
"loss": 3.4622,
"step": 1689088
},
{
"epoch": 0.0,
"learning_rate": 2.2338722833297194e-05,
"loss": 3.4515,
"step": 1689600
},
{
"epoch": 0.0,
"learning_rate": 2.233033688578667e-05,
"loss": 3.4507,
"step": 1690112
},
{
"epoch": 0.0,
"learning_rate": 2.232195093827615e-05,
"loss": 3.4491,
"step": 1690624
},
{
"epoch": 0.0,
"learning_rate": 2.2313581369569363e-05,
"loss": 3.4534,
"step": 1691136
},
{
"epoch": 0.0,
"learning_rate": 2.2305195422058843e-05,
"loss": 3.4485,
"step": 1691648
},
{
"epoch": 0.0,
"learning_rate": 2.2296809474548323e-05,
"loss": 3.4542,
"step": 1692160
},
{
"epoch": 0.0,
"learning_rate": 2.2288423527037802e-05,
"loss": 3.4457,
"step": 1692672
},
{
"epoch": 0.0,
"learning_rate": 2.2280053958331015e-05,
"loss": 3.4449,
"step": 1693184
},
{
"epoch": 0.0,
"learning_rate": 2.227166801082049e-05,
"loss": 3.4449,
"step": 1693696
},
{
"epoch": 0.0,
"learning_rate": 2.226328206330997e-05,
"loss": 3.4458,
"step": 1694208
},
{
"epoch": 0.01,
"learning_rate": 2.2254896115799455e-05,
"loss": 3.4499,
"step": 1694720
},
{
"epoch": 0.01,
"learning_rate": 2.2246526547092667e-05,
"loss": 3.4492,
"step": 1695232
},
{
"epoch": 0.01,
"learning_rate": 2.2238140599582144e-05,
"loss": 3.4559,
"step": 1695744
},
{
"epoch": 0.01,
"learning_rate": 2.2229754652071624e-05,
"loss": 3.4557,
"step": 1696256
},
{
"epoch": 0.01,
"learning_rate": 2.2221368704561104e-05,
"loss": 3.4429,
"step": 1696768
},
{
"epoch": 0.01,
"learning_rate": 2.221301551465805e-05,
"loss": 3.4527,
"step": 1697280
},
{
"epoch": 0.01,
"learning_rate": 2.220462956714753e-05,
"loss": 3.4485,
"step": 1697792
},
{
"epoch": 0.01,
"learning_rate": 2.219624361963701e-05,
"loss": 3.4477,
"step": 1698304
},
{
"epoch": 0.01,
"learning_rate": 2.218785767212649e-05,
"loss": 3.4357,
"step": 1698816
},
{
"epoch": 0.01,
"learning_rate": 2.2179488103419698e-05,
"loss": 3.4439,
"step": 1699328
},
{
"epoch": 0.01,
"learning_rate": 2.2171102155909178e-05,
"loss": 3.4458,
"step": 1699840
},
{
"epoch": 0.01,
"learning_rate": 2.216271620839866e-05,
"loss": 3.4533,
"step": 1700352
},
{
"epoch": 0.01,
"learning_rate": 2.215433026088814e-05,
"loss": 3.4457,
"step": 1700864
},
{
"epoch": 0.01,
"learning_rate": 2.2145944313377618e-05,
"loss": 3.4445,
"step": 1701376
},
{
"epoch": 0.01,
"learning_rate": 2.2137558365867098e-05,
"loss": 3.4641,
"step": 1701888
},
{
"epoch": 0.01,
"learning_rate": 2.2129172418356578e-05,
"loss": 3.4508,
"step": 1702400
},
{
"epoch": 0.01,
"learning_rate": 2.2120786470846057e-05,
"loss": 3.4558,
"step": 1702912
},
{
"epoch": 0.01,
"learning_rate": 2.211241690213927e-05,
"loss": 3.4415,
"step": 1703424
},
{
"epoch": 0.01,
"learning_rate": 2.2104047333432482e-05,
"loss": 3.4297,
"step": 1703936
},
{
"epoch": 0.01,
"learning_rate": 2.2095661385921962e-05,
"loss": 3.4563,
"step": 1704448
},
{
"epoch": 0.01,
"learning_rate": 2.208727543841144e-05,
"loss": 3.448,
"step": 1704960
},
{
"epoch": 0.01,
"learning_rate": 2.207888949090092e-05,
"loss": 3.4442,
"step": 1705472
},
{
"epoch": 0.01,
"learning_rate": 2.20705035433904e-05,
"loss": 3.4434,
"step": 1705984
},
{
"epoch": 0.01,
"learning_rate": 2.206211759587988e-05,
"loss": 3.4478,
"step": 1706496
},
{
"epoch": 0.01,
"learning_rate": 2.2053731648369362e-05,
"loss": 3.4254,
"step": 1707008
},
{
"epoch": 0.01,
"learning_rate": 2.2045345700858842e-05,
"loss": 3.4468,
"step": 1707520
},
{
"epoch": 0.01,
"learning_rate": 2.203697613215205e-05,
"loss": 3.4432,
"step": 1708032
},
{
"epoch": 0.01,
"learning_rate": 2.202859018464153e-05,
"loss": 3.4386,
"step": 1708544
},
{
"epoch": 0.01,
"learning_rate": 2.202020423713101e-05,
"loss": 3.4566,
"step": 1709056
},
{
"epoch": 0.01,
"learning_rate": 2.201181828962049e-05,
"loss": 3.4427,
"step": 1709568
},
{
"epoch": 0.01,
"learning_rate": 2.2003448720913704e-05,
"loss": 3.4432,
"step": 1710080
},
{
"epoch": 0.01,
"learning_rate": 2.1995062773403184e-05,
"loss": 3.4482,
"step": 1710592
},
{
"epoch": 0.01,
"learning_rate": 2.1986676825892663e-05,
"loss": 3.4385,
"step": 1711104
},
{
"epoch": 0.01,
"learning_rate": 2.1978290878382143e-05,
"loss": 3.4376,
"step": 1711616
},
{
"epoch": 0.01,
"learning_rate": 2.1969921309675353e-05,
"loss": 3.4431,
"step": 1712128
},
{
"epoch": 0.01,
"learning_rate": 2.1961535362164832e-05,
"loss": 3.4431,
"step": 1712640
},
{
"epoch": 0.01,
"learning_rate": 2.1953149414654316e-05,
"loss": 3.4391,
"step": 1713152
},
{
"epoch": 0.01,
"learning_rate": 2.1944763467143792e-05,
"loss": 3.4372,
"step": 1713664
},
{
"epoch": 0.01,
"learning_rate": 2.1936393898437005e-05,
"loss": 3.4282,
"step": 1714176
},
{
"epoch": 0.01,
"learning_rate": 2.1928007950926485e-05,
"loss": 3.441,
"step": 1714688
},
{
"epoch": 0.01,
"learning_rate": 2.1919622003415965e-05,
"loss": 3.4524,
"step": 1715200
},
{
"epoch": 0.01,
"learning_rate": 2.191123605590544e-05,
"loss": 3.4358,
"step": 1715712
},
{
"epoch": 0.01,
"learning_rate": 2.1902866487198657e-05,
"loss": 3.4593,
"step": 1716224
},
{
"epoch": 0.01,
"learning_rate": 2.1894480539688137e-05,
"loss": 3.4521,
"step": 1716736
},
{
"epoch": 0.01,
"learning_rate": 2.1886094592177617e-05,
"loss": 3.4516,
"step": 1717248
},
{
"epoch": 0.01,
"learning_rate": 2.1877708644667094e-05,
"loss": 3.4367,
"step": 1717760
},
{
"epoch": 0.01,
"learning_rate": 2.1869339075960306e-05,
"loss": 3.4551,
"step": 1718272
},
{
"epoch": 0.01,
"learning_rate": 2.1860953128449786e-05,
"loss": 3.4443,
"step": 1718784
},
{
"epoch": 0.01,
"learning_rate": 2.1852567180939266e-05,
"loss": 3.4373,
"step": 1719296
},
{
"epoch": 0.01,
"learning_rate": 2.1844181233428746e-05,
"loss": 3.4559,
"step": 1719808
},
{
"epoch": 0.01,
"learning_rate": 2.183581166472196e-05,
"loss": 3.447,
"step": 1720320
},
{
"epoch": 0.01,
"learning_rate": 2.182742571721144e-05,
"loss": 3.4486,
"step": 1720832
},
{
"epoch": 0.01,
"learning_rate": 2.1819039769700915e-05,
"loss": 3.4478,
"step": 1721344
},
{
"epoch": 0.01,
"learning_rate": 2.1810653822190395e-05,
"loss": 3.4284,
"step": 1721856
},
{
"epoch": 0.01,
"learning_rate": 2.180228425348361e-05,
"loss": 3.4297,
"step": 1722368
},
{
"epoch": 0.01,
"learning_rate": 2.179389830597309e-05,
"loss": 3.439,
"step": 1722880
},
{
"epoch": 0.01,
"learning_rate": 2.1785512358462567e-05,
"loss": 3.4492,
"step": 1723392
},
{
"epoch": 0.01,
"learning_rate": 2.1777126410952047e-05,
"loss": 3.4449,
"step": 1723904
},
{
"epoch": 0.01,
"learning_rate": 2.176875684224526e-05,
"loss": 3.4369,
"step": 1724416
},
{
"epoch": 0.02,
"learning_rate": 2.176037089473474e-05,
"loss": 3.4421,
"step": 1724928
},
{
"epoch": 0.02,
"learning_rate": 2.175198494722422e-05,
"loss": 3.436,
"step": 1725440
},
{
"epoch": 0.02,
"learning_rate": 2.17435989997137e-05,
"loss": 3.4421,
"step": 1725952
},
{
"epoch": 0.02,
"learning_rate": 2.1735229431006912e-05,
"loss": 3.4371,
"step": 1726464
},
{
"epoch": 0.02,
"learning_rate": 2.172684348349639e-05,
"loss": 3.457,
"step": 1726976
},
{
"epoch": 0.02,
"learning_rate": 2.171845753598587e-05,
"loss": 3.4538,
"step": 1727488
},
{
"epoch": 0.02,
"learning_rate": 2.171007158847535e-05,
"loss": 3.4454,
"step": 1728000
},
{
"epoch": 0.02,
"learning_rate": 2.1701702019768565e-05,
"loss": 3.4379,
"step": 1728512
},
{
"epoch": 0.02,
"learning_rate": 2.169331607225804e-05,
"loss": 3.449,
"step": 1729024
},
{
"epoch": 0.02,
"learning_rate": 2.168493012474752e-05,
"loss": 3.4361,
"step": 1729536
},
{
"epoch": 0.02,
"learning_rate": 2.1676544177237e-05,
"loss": 3.4538,
"step": 1730048
},
{
"epoch": 0.02,
"learning_rate": 2.166817460853021e-05,
"loss": 3.4395,
"step": 1730560
},
{
"epoch": 0.02,
"learning_rate": 2.1659788661019693e-05,
"loss": 3.4435,
"step": 1731072
},
{
"epoch": 0.02,
"learning_rate": 2.1651402713509173e-05,
"loss": 3.4461,
"step": 1731584
},
{
"epoch": 0.02,
"learning_rate": 2.1643033144802386e-05,
"loss": 3.4491,
"step": 1732096
},
{
"epoch": 0.02,
"learning_rate": 2.1634647197291862e-05,
"loss": 3.4356,
"step": 1732608
},
{
"epoch": 0.02,
"learning_rate": 2.1626261249781342e-05,
"loss": 3.4475,
"step": 1733120
},
{
"epoch": 0.02,
"learning_rate": 2.1617875302270822e-05,
"loss": 3.4378,
"step": 1733632
},
{
"epoch": 0.02,
"learning_rate": 2.1609505733564038e-05,
"loss": 3.4348,
"step": 1734144
},
{
"epoch": 0.02,
"learning_rate": 2.1601119786053515e-05,
"loss": 3.4279,
"step": 1734656
},
{
"epoch": 0.02,
"learning_rate": 2.1592733838542995e-05,
"loss": 3.4455,
"step": 1735168
},
{
"epoch": 0.02,
"learning_rate": 2.1584347891032475e-05,
"loss": 3.4446,
"step": 1735680
},
{
"epoch": 0.02,
"learning_rate": 2.1575978322325684e-05,
"loss": 3.4386,
"step": 1736192
},
{
"epoch": 0.02,
"learning_rate": 2.1567592374815164e-05,
"loss": 3.4415,
"step": 1736704
},
{
"epoch": 0.02,
"learning_rate": 2.1559206427304647e-05,
"loss": 3.435,
"step": 1737216
},
{
"epoch": 0.02,
"learning_rate": 2.1550820479794127e-05,
"loss": 3.4516,
"step": 1737728
},
{
"epoch": 0.02,
"learning_rate": 2.1542450911087336e-05,
"loss": 3.4603,
"step": 1738240
},
{
"epoch": 0.02,
"learning_rate": 2.1534064963576816e-05,
"loss": 3.4483,
"step": 1738752
},
{
"epoch": 0.02,
"learning_rate": 2.1525679016066296e-05,
"loss": 3.4456,
"step": 1739264
},
{
"epoch": 0.02,
"learning_rate": 2.1517293068555776e-05,
"loss": 3.439,
"step": 1739776
},
{
"epoch": 0.02,
"learning_rate": 2.150892349984899e-05,
"loss": 3.4435,
"step": 1740288
},
{
"epoch": 0.02,
"learning_rate": 2.150053755233847e-05,
"loss": 3.4323,
"step": 1740800
},
{
"epoch": 0.02,
"learning_rate": 2.149215160482795e-05,
"loss": 3.4391,
"step": 1741312
},
{
"epoch": 0.02,
"learning_rate": 2.148376565731743e-05,
"loss": 3.4428,
"step": 1741824
},
{
"epoch": 0.02,
"learning_rate": 2.1475396088610638e-05,
"loss": 3.442,
"step": 1742336
},
{
"epoch": 0.02,
"learning_rate": 2.1467010141100117e-05,
"loss": 3.4452,
"step": 1742848
},
{
"epoch": 0.02,
"learning_rate": 2.14586241935896e-05,
"loss": 3.4406,
"step": 1743360
},
{
"epoch": 0.02,
"learning_rate": 2.145023824607908e-05,
"loss": 3.4497,
"step": 1743872
},
{
"epoch": 0.02,
"learning_rate": 2.1441885056176022e-05,
"loss": 3.4383,
"step": 1744384
},
{
"epoch": 0.02,
"learning_rate": 2.1433499108665502e-05,
"loss": 3.4445,
"step": 1744896
},
{
"epoch": 0.02,
"learning_rate": 2.1425113161154982e-05,
"loss": 3.4435,
"step": 1745408
},
{
"epoch": 0.02,
"learning_rate": 2.1416727213644462e-05,
"loss": 3.4463,
"step": 1745920
},
{
"epoch": 0.02,
"learning_rate": 2.1408341266133942e-05,
"loss": 3.4537,
"step": 1746432
},
{
"epoch": 0.02,
"learning_rate": 2.1399955318623422e-05,
"loss": 3.4395,
"step": 1746944
},
{
"epoch": 0.02,
"learning_rate": 2.1391569371112902e-05,
"loss": 3.452,
"step": 1747456
},
{
"epoch": 0.02,
"learning_rate": 2.1383183423602382e-05,
"loss": 3.4431,
"step": 1747968
},
{
"epoch": 0.02,
"learning_rate": 2.137481385489559e-05,
"loss": 3.4469,
"step": 1748480
},
{
"epoch": 0.02,
"learning_rate": 2.136642790738507e-05,
"loss": 3.4429,
"step": 1748992
},
{
"epoch": 0.02,
"learning_rate": 2.1358041959874554e-05,
"loss": 3.4515,
"step": 1749504
},
{
"epoch": 0.02,
"learning_rate": 2.1349656012364034e-05,
"loss": 3.4383,
"step": 1750016
},
{
"epoch": 0.02,
"learning_rate": 2.1341286443657244e-05,
"loss": 3.4533,
"step": 1750528
},
{
"epoch": 0.02,
"learning_rate": 2.1332900496146723e-05,
"loss": 3.4327,
"step": 1751040
},
{
"epoch": 0.02,
"learning_rate": 2.1324514548636203e-05,
"loss": 3.444,
"step": 1751552
},
{
"epoch": 0.02,
"learning_rate": 2.1316128601125683e-05,
"loss": 3.4434,
"step": 1752064
},
{
"epoch": 0.02,
"learning_rate": 2.1307759032418896e-05,
"loss": 3.4468,
"step": 1752576
},
{
"epoch": 0.02,
"learning_rate": 2.1299373084908376e-05,
"loss": 3.4447,
"step": 1753088
},
{
"epoch": 0.02,
"learning_rate": 2.1290987137397856e-05,
"loss": 3.4455,
"step": 1753600
},
{
"epoch": 0.02,
"learning_rate": 2.1282601189887336e-05,
"loss": 3.4513,
"step": 1754112
},
{
"epoch": 0.02,
"learning_rate": 2.1274231621180545e-05,
"loss": 3.436,
"step": 1754624
},
{
"epoch": 0.02,
"learning_rate": 2.1265845673670025e-05,
"loss": 3.448,
"step": 1755136
},
{
"epoch": 0.03,
"eval_loss": 3.8526601791381836,
"eval_runtime": 310.3108,
"eval_samples_per_second": 1229.706,
"eval_steps_per_second": 38.429,
"step": 1755360
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.2216862338510735e+18,
"trial_name": null,
"trial_params": null
}