abhinavp's picture
Training in progress, epoch 0, checkpoint
20e75aa verified
{
"best_metric": 3.9570462703704834,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/passive/transformer/4/checkpoints/checkpoint-228960",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 228960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.8561,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8176,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1919,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9799,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8114,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.6909,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.603,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5253,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4414,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3939,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3412,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3023,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.255,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2062,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1693,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1215,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1055,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0733,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0435,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0154,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.007,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9759,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9499,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9225,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9189,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8826,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8713,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8405,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8297,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8173,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7993,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740117521192533e-05,
"loss": 4.7907,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731731573682013e-05,
"loss": 4.7769,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7621,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7611,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7388,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7351,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.6953,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7054,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6703,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6806,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6643,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6617,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6372,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6503,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6356,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6297,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6262,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5916,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5952,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.5981,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.5851,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5785,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5596,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5571,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5379,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5619,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5177,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5398,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5326,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5116,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5098,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5015,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4927,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4863,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.4967,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4744,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4728,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4649,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4653,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4734,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4668,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4454,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4596,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4603,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4319,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4396,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4289,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4248,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4153,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4197,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4225,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4257,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930422841748654e-05,
"loss": 4.4028,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.3795,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.3955,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.3947,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.3946,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.3839,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.3846,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3789,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3773,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.3653,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3699,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3599,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3702,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3591,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3395,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.3518,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3495,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.3556,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.3392,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3377,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913657498249106e-05,
"loss": 4.324,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3342,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3165,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3229,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3205,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3196,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3109,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3119,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3045,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3129,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3028,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3002,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3128,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.3016,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.2998,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.2873,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.2925,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2863,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.2832,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.2946,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2772,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2832,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2652,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2675,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2742,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.265,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2561,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2818,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2636,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.257,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2563,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.2574,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.2588,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.256,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2496,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2569,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2548,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2482,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2384,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.246,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.2379,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2377,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.2347,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2325,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2383,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2239,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2239,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.200042724609375,
"eval_runtime": 304.655,
"eval_samples_per_second": 1252.535,
"eval_steps_per_second": 39.143,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.2071,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873421329002341e-05,
"loss": 4.2087,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872582734251289e-05,
"loss": 4.2361,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.2199,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.2134,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.2105,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.2063,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.1967,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2077,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.2042,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2069,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2059,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642017003818885e-05,
"loss": 4.1909,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633631056308365e-05,
"loss": 4.1866,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625245108797845e-05,
"loss": 4.1803,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616859161287324e-05,
"loss": 4.1779,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608473213776804e-05,
"loss": 4.1879,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860008726626628e-05,
"loss": 4.177,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591701318755764e-05,
"loss": 4.1814,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583315371245244e-05,
"loss": 4.1997,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.1792,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.1827,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.1736,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854978796000689e-05,
"loss": 4.1864,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.1678,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853303244378958e-05,
"loss": 4.1689,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852464649627906e-05,
"loss": 4.1599,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851626054876854e-05,
"loss": 4.1663,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850787460125802e-05,
"loss": 4.1598,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.84994886537475e-05,
"loss": 4.1553,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849111908504072e-05,
"loss": 4.1604,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.84827331375302e-05,
"loss": 4.1667,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847434719001968e-05,
"loss": 4.1571,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846596124250916e-05,
"loss": 4.162,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845757529499864e-05,
"loss": 4.1537,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844920572629185e-05,
"loss": 4.1606,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844081977878133e-05,
"loss": 4.1375,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843243383127081e-05,
"loss": 4.1519,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842404788376029e-05,
"loss": 4.1286,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.1503,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.8407292367542976e-05,
"loss": 4.134,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398906420032456e-05,
"loss": 4.1481,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.8390520472521936e-05,
"loss": 4.1301,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382134525011416e-05,
"loss": 4.144,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83737485775009e-05,
"loss": 4.1425,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836537900879411e-05,
"loss": 4.1397,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835699306128359e-05,
"loss": 4.1451,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834860711377307e-05,
"loss": 4.1149,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834022116626255e-05,
"loss": 4.1249,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833185159755576e-05,
"loss": 4.1348,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832346565004524e-05,
"loss": 4.1322,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831507970253472e-05,
"loss": 4.1248,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.83066937550242e-05,
"loss": 4.1208,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829830780751368e-05,
"loss": 4.116,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828993823880689e-05,
"loss": 4.1084,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828155229129637e-05,
"loss": 4.123,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273166343785856e-05,
"loss": 4.103,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264780396275336e-05,
"loss": 4.1143,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256410827568545e-05,
"loss": 4.1248,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248024880058025e-05,
"loss": 4.1035,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239638932547505e-05,
"loss": 4.1045,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231252985036985e-05,
"loss": 4.1044,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222883416330194e-05,
"loss": 4.0972,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214497468819674e-05,
"loss": 4.0953,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206111521309154e-05,
"loss": 4.1139,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197725573798634e-05,
"loss": 4.0978,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189339626288114e-05,
"loss": 4.0962,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818097005758132e-05,
"loss": 4.0925,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817260048887454e-05,
"loss": 4.0926,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816421454136402e-05,
"loss": 4.107,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.81558285938535e-05,
"loss": 4.1007,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814744264634298e-05,
"loss": 4.0926,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813905669883246e-05,
"loss": 4.1034,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813067075132194e-05,
"loss": 4.1032,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812228480381141e-05,
"loss": 4.0863,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811391523510463e-05,
"loss": 4.093,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810552928759411e-05,
"loss": 4.0885,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809714334008359e-05,
"loss": 4.0875,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808875739257306e-05,
"loss": 4.0803,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808037144506255e-05,
"loss": 4.0832,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807198549755203e-05,
"loss": 4.0942,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806359955004151e-05,
"loss": 4.0926,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805521360253099e-05,
"loss": 4.0811,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804682765502047e-05,
"loss": 4.06,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.8038458086313677e-05,
"loss": 4.0746,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8030072138803156e-05,
"loss": 4.0803,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.8021686191292636e-05,
"loss": 4.0798,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013300243782116e-05,
"loss": 4.0765,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004930675075325e-05,
"loss": 4.0709,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996544727564805e-05,
"loss": 4.0788,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988158780054285e-05,
"loss": 4.0698,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979772832543765e-05,
"loss": 4.0632,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797140326383698e-05,
"loss": 4.077,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796301731632646e-05,
"loss": 4.0613,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795464774761967e-05,
"loss": 4.0805,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794626180010915e-05,
"loss": 4.0709,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793787585259863e-05,
"loss": 4.0502,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792948990508811e-05,
"loss": 4.0661,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792110395757759e-05,
"loss": 4.0642,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791271801006707e-05,
"loss": 4.0737,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790433206255655e-05,
"loss": 4.064,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789594611504603e-05,
"loss": 4.0595,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788757654633924e-05,
"loss": 4.0487,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787919059882872e-05,
"loss": 4.0661,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.78708046513182e-05,
"loss": 4.0454,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862435082611415e-05,
"loss": 4.0531,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854049135100895e-05,
"loss": 4.056,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845663187590375e-05,
"loss": 4.0549,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837277240079855e-05,
"loss": 4.0449,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828891292569335e-05,
"loss": 4.0532,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820505345058815e-05,
"loss": 4.0461,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812119397548295e-05,
"loss": 4.0517,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803733450037775e-05,
"loss": 4.05,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779534750252725e-05,
"loss": 4.0437,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786977933820464e-05,
"loss": 4.0666,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778591986309944e-05,
"loss": 4.0536,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777022241760315e-05,
"loss": 4.0507,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776183647009263e-05,
"loss": 4.0394,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775345052258212e-05,
"loss": 4.0477,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450645750716e-05,
"loss": 4.0439,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773667862756108e-05,
"loss": 4.037,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772829268005055e-05,
"loss": 4.0535,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771990673254003e-05,
"loss": 4.0405,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771152078502951e-05,
"loss": 4.0408,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770315121632272e-05,
"loss": 4.0354,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.76947652688122e-05,
"loss": 4.0342,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768637932130168e-05,
"loss": 4.0385,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76780097525949e-05,
"loss": 4.0349,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766962380508437e-05,
"loss": 4.0239,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766123785757386e-05,
"loss": 4.0545,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765285191006334e-05,
"loss": 4.042,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764446596255282e-05,
"loss": 4.0307,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.76360800150423e-05,
"loss": 4.0299,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762769406753178e-05,
"loss": 4.0282,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761930812002126e-05,
"loss": 4.0394,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610938551314466e-05,
"loss": 4.033,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602552603803946e-05,
"loss": 4.028,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594166656293426e-05,
"loss": 4.0399,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.7585780708782906e-05,
"loss": 4.0327,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577411140076115e-05,
"loss": 4.0366,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569025192565595e-05,
"loss": 4.0232,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560639245055075e-05,
"loss": 4.0336,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552253297544555e-05,
"loss": 4.0264,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754388372883777e-05,
"loss": 4.0245,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753549778132725e-05,
"loss": 4.026,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752711183381673e-05,
"loss": 4.0259,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751872588630621e-05,
"loss": 4.0273,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751035631759942e-05,
"loss": 4.015,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.75019703700889e-05,
"loss": 4.0185,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.031122207641602,
"eval_runtime": 304.633,
"eval_samples_per_second": 1252.625,
"eval_steps_per_second": 39.145,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749358442257838e-05,
"loss": 4.0032,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748519847506786e-05,
"loss": 4.0041,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747681252755734e-05,
"loss": 4.0324,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746842658004682e-05,
"loss": 4.0253,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.74600406325363e-05,
"loss": 4.0161,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745165468502578e-05,
"loss": 4.0104,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744326873751526e-05,
"loss": 4.0125,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743488279000474e-05,
"loss": 3.999,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742649684249422e-05,
"loss": 4.0188,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.74181108949837e-05,
"loss": 4.0114,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740972494747318e-05,
"loss": 4.0115,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740135537876639e-05,
"loss": 4.0119,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739300218886333e-05,
"loss": 4.001,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738461624135281e-05,
"loss": 3.9996,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737623029384229e-05,
"loss": 3.9964,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736784434633177e-05,
"loss": 3.9946,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735945839882125e-05,
"loss": 4.0002,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735107245131073e-05,
"loss": 3.9932,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734268650380021e-05,
"loss": 3.9993,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733430055628969e-05,
"loss": 4.0225,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732591460877917e-05,
"loss": 3.9978,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731752866126865e-05,
"loss": 4.0016,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730914271375813e-05,
"loss": 3.9982,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730077314505134e-05,
"loss": 4.0062,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729238719754082e-05,
"loss": 3.9877,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.72840012500303e-05,
"loss": 3.9975,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727561530251978e-05,
"loss": 3.9873,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726724573381299e-05,
"loss": 3.9891,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725885978630247e-05,
"loss": 3.9845,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725047383879195e-05,
"loss": 3.9847,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724208789128143e-05,
"loss": 3.9883,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233718322574647e-05,
"loss": 3.9972,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225332375064127e-05,
"loss": 3.9882,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216946427553606e-05,
"loss": 3.9956,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208560480043086e-05,
"loss": 3.9804,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200174532532566e-05,
"loss": 3.9978,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191788585022046e-05,
"loss": 3.9697,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183402637511526e-05,
"loss": 3.9913,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175033068804735e-05,
"loss": 3.9648,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166647121294215e-05,
"loss": 3.9856,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158261173783695e-05,
"loss": 3.9716,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149875226273175e-05,
"loss": 3.989,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141505657566384e-05,
"loss": 3.9724,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133119710055864e-05,
"loss": 3.9792,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712473376254535e-05,
"loss": 3.9816,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711634781503483e-05,
"loss": 3.9833,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710797824632804e-05,
"loss": 3.9845,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709959229881752e-05,
"loss": 3.963,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091206351307e-05,
"loss": 3.9646,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708282040379648e-05,
"loss": 3.981,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707445083508969e-05,
"loss": 3.9774,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706606488757917e-05,
"loss": 3.9686,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705767894006865e-05,
"loss": 3.9675,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704929299255813e-05,
"loss": 3.9654,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704092342385134e-05,
"loss": 3.9512,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703253747634082e-05,
"loss": 3.9693,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024151528830305e-05,
"loss": 3.9538,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015765581319785e-05,
"loss": 3.9676,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007396012612994e-05,
"loss": 3.9753,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6999010065102474e-05,
"loss": 3.9537,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990624117591954e-05,
"loss": 3.9573,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982238170081434e-05,
"loss": 3.9595,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697386860137464e-05,
"loss": 3.9495,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696548265386412e-05,
"loss": 3.9465,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69570967063536e-05,
"loss": 3.9683,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694871075884308e-05,
"loss": 3.954,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694034119013629e-05,
"loss": 3.9498,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693195524262577e-05,
"loss": 3.9492,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692358567391899e-05,
"loss": 3.9519,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691519972640847e-05,
"loss": 3.9629,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690681377889795e-05,
"loss": 3.96,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689842783138743e-05,
"loss": 3.9515,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689004188387691e-05,
"loss": 3.9635,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688165593636639e-05,
"loss": 3.9583,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687326998885587e-05,
"loss": 3.9481,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864900420149076e-05,
"loss": 3.9548,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856514472638556e-05,
"loss": 3.9562,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848128525128036e-05,
"loss": 3.9485,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683974257761751e-05,
"loss": 3.9467,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831356630106996e-05,
"loss": 3.9467,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822970682596476e-05,
"loss": 3.9567,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814584735085956e-05,
"loss": 3.9587,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806198787575436e-05,
"loss": 3.9438,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797829218868645e-05,
"loss": 3.9308,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789443271358125e-05,
"loss": 3.9388,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.6781057323847605e-05,
"loss": 3.9454,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772671376337085e-05,
"loss": 3.9486,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764301807630294e-05,
"loss": 3.9421,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755915860119774e-05,
"loss": 3.9381,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674754629141298e-05,
"loss": 3.9499,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673916034390246e-05,
"loss": 3.9352,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673077439639194e-05,
"loss": 3.9357,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672238844888143e-05,
"loss": 3.944,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671400250137091e-05,
"loss": 3.9343,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670563293266412e-05,
"loss": 3.9538,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.66972469851536e-05,
"loss": 3.9388,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668886103764308e-05,
"loss": 3.9252,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668047509013256e-05,
"loss": 3.9404,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667208914262204e-05,
"loss": 3.9338,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666370319511152e-05,
"loss": 3.9506,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655317247601e-05,
"loss": 3.9416,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664693130009048e-05,
"loss": 3.9321,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663856173138369e-05,
"loss": 3.9217,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663017578387317e-05,
"loss": 3.9403,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621806215166383e-05,
"loss": 3.9218,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613420267655863e-05,
"loss": 3.9301,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660503432014534e-05,
"loss": 3.9343,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659664837263482e-05,
"loss": 3.9308,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658827880392803e-05,
"loss": 3.9219,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657989285641751e-05,
"loss": 3.9377,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657150690890699e-05,
"loss": 3.923,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656312096139647e-05,
"loss": 3.929,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655473501388595e-05,
"loss": 3.9315,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654634906637543e-05,
"loss": 3.923,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653796311886491e-05,
"loss": 3.9438,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652959355015812e-05,
"loss": 3.9333,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.65212076026476e-05,
"loss": 3.9338,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651282165513708e-05,
"loss": 3.9204,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650443570762657e-05,
"loss": 3.929,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649606613891978e-05,
"loss": 3.9274,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648768019140926e-05,
"loss": 3.9161,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647929424389874e-05,
"loss": 3.9316,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647090829638822e-05,
"loss": 3.9271,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.64625223488777e-05,
"loss": 3.924,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645413640136718e-05,
"loss": 3.9226,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644575045385665e-05,
"loss": 3.9218,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643736450634613e-05,
"loss": 3.9162,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429011316443075e-05,
"loss": 3.9242,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420625368932555e-05,
"loss": 3.9136,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412239421422035e-05,
"loss": 3.9364,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640385347391152e-05,
"loss": 3.9326,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395467526401e-05,
"loss": 3.9159,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638709795769421e-05,
"loss": 3.9149,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637871201018369e-05,
"loss": 3.9166,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637032606267317e-05,
"loss": 3.9257,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636194011516265e-05,
"loss": 3.923,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353554167652124e-05,
"loss": 3.9169,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345168220141604e-05,
"loss": 3.9261,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633679865143482e-05,
"loss": 3.9202,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632841270392429e-05,
"loss": 3.9277,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632002675641377e-05,
"loss": 3.9117,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631164080890326e-05,
"loss": 3.9281,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630325486139274e-05,
"loss": 3.9185,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629486891388222e-05,
"loss": 3.9106,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.62864829663717e-05,
"loss": 3.9217,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627809701886118e-05,
"loss": 3.9205,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626974382895812e-05,
"loss": 3.9166,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.62613578814476e-05,
"loss": 3.9036,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625297193393708e-05,
"loss": 3.9082,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9570462703704834,
"eval_runtime": 308.8428,
"eval_samples_per_second": 1235.551,
"eval_steps_per_second": 38.612,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.5937334177716224e+17,
"trial_name": null,
"trial_params": null
}