abhinavp's picture
Training in progress, epoch 1, checkpoint
cded57c verified
{
"best_metric": 3.8699309825897217,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-c-command/transformer/4/checkpoints/checkpoint-457920",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 457920,
"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": 10.971,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8154,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1847,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9857,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8193,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7079,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6091,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5446,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4504,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4209,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.36,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3199,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2787,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2129,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1939,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1454,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1243,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.096,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0567,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0328,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0169,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9887,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9587,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9377,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9283,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.9015,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8741,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8642,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8442,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8307,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8157,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.8021,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7877,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7701,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.766,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7659,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7421,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.7039,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 4.709,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 4.6884,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6933,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.679,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6728,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6509,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.66,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6436,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6429,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6296,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6088,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 4.6106,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.6125,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.59,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5812,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5749,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.571,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5556,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5736,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5415,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5508,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5421,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5168,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 4.5256,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.515,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.5005,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4936,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.5088,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4867,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4814,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4686,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4814,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4871,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4712,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4646,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4687,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4669,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.458,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4395,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4467,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.435,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4315,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4216,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4283,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4326,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.4228,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.3977,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.4055,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.4086,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.4042,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3994,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3937,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3892,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3766,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3817,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 4.3821,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.3737,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 4.3833,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 4.3616,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3614,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3594,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3576,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3627,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.347,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3416,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3399,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3441,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3255,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111449897566966e-05,
"loss": 4.3178,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103063950056446e-05,
"loss": 4.3277,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.9094678002545926e-05,
"loss": 4.3325,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.9086292055035406e-05,
"loss": 4.3254,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.9077906107524886e-05,
"loss": 4.3222,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.9069520160014366e-05,
"loss": 4.3114,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.9061134212503846e-05,
"loss": 4.3221,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3049,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3119,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.9035992748776015e-05,
"loss": 4.3134,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027606801265495e-05,
"loss": 4.3124,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.3014,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.3005,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.3,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.3007,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985693442516624e-05,
"loss": 4.2895,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2936,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.2884,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2913,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2749,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2714,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2777,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.279,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2693,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2824,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2736,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2597,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2663,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.2757,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.2652,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.2612,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2524,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2599,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2648,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2503,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2432,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2483,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.24,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.238,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2466,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.236,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2366,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2339,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2297,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.198172569274902,
"eval_runtime": 303.0817,
"eval_samples_per_second": 1259.037,
"eval_steps_per_second": 39.346,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.2177,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.2251,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2321,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2205,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.2239,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.2168,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.2159,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.2005,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.2256,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.2091,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2195,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2165,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642000625015155e-05,
"loss": 4.1987,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.1981,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.1957,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.1873,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.1943,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.1865,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.1822,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.2057,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.1886,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.1817,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.1789,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.1914,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.1695,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853301606498585e-05,
"loss": 4.1674,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.1716,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.1716,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.1654,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.84994886537475e-05,
"loss": 4.1652,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.1663,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.1691,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1558,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846596124250916e-05,
"loss": 4.1647,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845757529499864e-05,
"loss": 4.1718,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.164,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.1396,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843243383127081e-05,
"loss": 4.1464,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842404788376029e-05,
"loss": 4.1435,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.1504,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.1424,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.1507,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.8390520472521936e-05,
"loss": 4.1367,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382134525011416e-05,
"loss": 4.1469,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83737485775009e-05,
"loss": 4.1451,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836536262999038e-05,
"loss": 4.1454,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835699306128359e-05,
"loss": 4.1422,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834860711377307e-05,
"loss": 4.1227,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834022116626255e-05,
"loss": 4.139,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833183521875203e-05,
"loss": 4.1418,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832346565004524e-05,
"loss": 4.134,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831507970253472e-05,
"loss": 4.1267,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.83066937550242e-05,
"loss": 4.1205,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829830780751368e-05,
"loss": 4.1279,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828993823880689e-05,
"loss": 4.1106,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828155229129637e-05,
"loss": 4.1408,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273166343785856e-05,
"loss": 4.1188,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264780396275336e-05,
"loss": 4.1304,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256410827568545e-05,
"loss": 4.1292,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248024880058025e-05,
"loss": 4.1034,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239638932547505e-05,
"loss": 4.1196,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231252985036985e-05,
"loss": 4.1123,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222883416330194e-05,
"loss": 4.1013,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214497468819674e-05,
"loss": 4.0992,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206111521309154e-05,
"loss": 4.1171,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197725573798634e-05,
"loss": 4.1066,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818935600509184e-05,
"loss": 4.1019,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818097005758132e-05,
"loss": 4.0912,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817258411007081e-05,
"loss": 4.1102,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816419816256029e-05,
"loss": 4.1136,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.81558285938535e-05,
"loss": 4.1068,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814744264634298e-05,
"loss": 4.1034,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813905669883246e-05,
"loss": 4.1147,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813067075132194e-05,
"loss": 4.1088,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812230118261515e-05,
"loss": 4.1085,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811391523510463e-05,
"loss": 4.0917,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810552928759411e-05,
"loss": 4.1033,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809714334008359e-05,
"loss": 4.0952,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887737713768e-05,
"loss": 4.0935,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808038782386628e-05,
"loss": 4.09,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807200187635576e-05,
"loss": 4.0953,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063615928845243e-05,
"loss": 4.1048,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805524636013845e-05,
"loss": 4.0998,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804686041262793e-05,
"loss": 4.0741,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803847446511741e-05,
"loss": 4.0838,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8030088517606886e-05,
"loss": 4.0892,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.80217189489001e-05,
"loss": 4.0875,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801333300138958e-05,
"loss": 4.0875,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800496343268279e-05,
"loss": 4.0828,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799657748517227e-05,
"loss": 4.0834,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798819153766175e-05,
"loss": 4.0721,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797980559015123e-05,
"loss": 4.0812,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797141964264071e-05,
"loss": 4.0808,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796303369513019e-05,
"loss": 4.0778,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795464774761967e-05,
"loss": 4.086,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794626180010915e-05,
"loss": 4.0761,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793789223140236e-05,
"loss": 4.0694,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792950628389184e-05,
"loss": 4.0744,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792112033638132e-05,
"loss": 4.0743,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912750767674535e-05,
"loss": 4.0787,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790436482016401e-05,
"loss": 4.0665,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789597887265349e-05,
"loss": 4.0637,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788759292514297e-05,
"loss": 4.0647,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787920697763245e-05,
"loss": 4.0715,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870821030121935e-05,
"loss": 4.0566,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862451461415144e-05,
"loss": 4.0463,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854065513904624e-05,
"loss": 4.0621,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845679566394104e-05,
"loss": 4.0635,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837293618883584e-05,
"loss": 4.057,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828907671373064e-05,
"loss": 4.0587,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820521723862544e-05,
"loss": 4.0541,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812135776352024e-05,
"loss": 4.0613,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803749828841504e-05,
"loss": 4.0482,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779538026013471e-05,
"loss": 4.0581,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778699431262419e-05,
"loss": 4.0636,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777860836511367e-05,
"loss": 4.0628,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777023879640689e-05,
"loss": 4.0497,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776185284889637e-05,
"loss": 4.0498,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775346690138585e-05,
"loss": 4.0543,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774508095387533e-05,
"loss": 4.0564,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773669500636481e-05,
"loss": 4.041,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772830905885429e-05,
"loss": 4.0543,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771992311134377e-05,
"loss": 4.0433,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771153716383325e-05,
"loss": 4.0564,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770316759512646e-05,
"loss": 4.0379,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769478164761594e-05,
"loss": 4.0366,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.0411,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76780097525949e-05,
"loss": 4.0449,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.7669640183888106e-05,
"loss": 4.0361,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.7661254236377586e-05,
"loss": 4.0557,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765286828886707e-05,
"loss": 4.0441,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764448234135655e-05,
"loss": 4.0343,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763611277264976e-05,
"loss": 4.0356,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762772682513924e-05,
"loss": 4.0524,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761934087762872e-05,
"loss": 4.0442,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610954930118195e-05,
"loss": 4.0373,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760258536141141e-05,
"loss": 4.0327,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759419941390089e-05,
"loss": 4.0427,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758581346639037e-05,
"loss": 4.0435,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577427518879844e-05,
"loss": 4.0324,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756905795017306e-05,
"loss": 4.0302,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756067200266254e-05,
"loss": 4.0327,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755228605515202e-05,
"loss": 4.0274,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543932865248965e-05,
"loss": 4.025,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535546917738445e-05,
"loss": 4.04,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527160970227925e-05,
"loss": 4.0271,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518775022717405e-05,
"loss": 4.0274,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510389075206885e-05,
"loss": 4.026,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7502019506500094e-05,
"loss": 4.0224,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.027204513549805,
"eval_runtime": 303.964,
"eval_samples_per_second": 1255.382,
"eval_steps_per_second": 39.232,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493633558989574e-05,
"loss": 4.0115,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485247611479054e-05,
"loss": 4.0217,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476861663968534e-05,
"loss": 4.032,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468475716458014e-05,
"loss": 4.0213,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460089768947494e-05,
"loss": 4.0255,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451703821436974e-05,
"loss": 4.0163,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443317873926453e-05,
"loss": 4.0214,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434931926415933e-05,
"loss": 4.0029,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426545978905413e-05,
"loss": 4.0278,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741816003139489e-05,
"loss": 4.0225,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740977408388437e-05,
"loss": 4.0199,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740140451517758e-05,
"loss": 4.0273,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739303494647079e-05,
"loss": 4.0059,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738464899896027e-05,
"loss": 4.0075,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737626305144975e-05,
"loss": 4.0141,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736787710393923e-05,
"loss": 3.998,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735949115642871e-05,
"loss": 4.0051,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735112158772193e-05,
"loss": 4.0006,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734273564021141e-05,
"loss": 3.9996,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733434969270089e-05,
"loss": 4.026,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732596374519037e-05,
"loss": 4.0046,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731757779767985e-05,
"loss": 4.0082,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730919185016933e-05,
"loss": 3.9973,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730080590265881e-05,
"loss": 4.0145,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292436333952016e-05,
"loss": 3.9873,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7284050386441496e-05,
"loss": 3.9943,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275664438930976e-05,
"loss": 3.9933,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267294870224185e-05,
"loss": 4.0017,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258908922713665e-05,
"loss": 3.9908,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725052297520315e-05,
"loss": 3.9908,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724213702769263e-05,
"loss": 3.9973,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723375108018211e-05,
"loss": 4.0005,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722536513267159e-05,
"loss": 3.9818,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721697918516107e-05,
"loss": 3.9961,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720859323765055e-05,
"loss": 3.9991,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720022366894376e-05,
"loss": 3.9947,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719183772143324e-05,
"loss": 3.9745,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718345177392272e-05,
"loss": 3.9842,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.71750658264122e-05,
"loss": 3.971,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716667987890168e-05,
"loss": 3.9886,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158293931391154e-05,
"loss": 3.9811,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714992436268437e-05,
"loss": 3.9887,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714153841517385e-05,
"loss": 3.9778,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713315246766333e-05,
"loss": 3.9827,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712476652015281e-05,
"loss": 3.987,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116396951446025e-05,
"loss": 3.9873,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7108011003935505e-05,
"loss": 3.9844,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709962505642498e-05,
"loss": 3.9627,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709123910891446e-05,
"loss": 3.9782,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708285316140394e-05,
"loss": 3.9893,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074483592697154e-05,
"loss": 3.9735,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706609764518663e-05,
"loss": 3.9714,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705771169767611e-05,
"loss": 3.9695,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704932575016559e-05,
"loss": 3.9735,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040939802655074e-05,
"loss": 3.9591,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703257023394828e-05,
"loss": 3.9822,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702418428643776e-05,
"loss": 3.9716,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701579833892724e-05,
"loss": 3.977,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700741239141672e-05,
"loss": 3.9828,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.69990264439062e-05,
"loss": 3.9553,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699064049639568e-05,
"loss": 3.9699,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698227092768889e-05,
"loss": 3.964,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697388498017837e-05,
"loss": 3.9575,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696549903266785e-05,
"loss": 3.9523,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695711308515733e-05,
"loss": 3.968,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694874351645054e-05,
"loss": 3.9632,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694035756894003e-05,
"loss": 3.9556,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693197162142951e-05,
"loss": 3.947,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692358567391899e-05,
"loss": 3.9676,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691519972640847e-05,
"loss": 3.9724,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690681377889795e-05,
"loss": 3.9636,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898444210191157e-05,
"loss": 3.9626,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890058262680636e-05,
"loss": 3.9729,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881672315170116e-05,
"loss": 3.9663,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873286367659596e-05,
"loss": 3.9706,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864916798952806e-05,
"loss": 3.9496,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856530851442285e-05,
"loss": 3.9671,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848144903931765e-05,
"loss": 3.9611,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839758956421245e-05,
"loss": 3.9549,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683138938771446e-05,
"loss": 3.9569,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682300344020394e-05,
"loss": 3.9589,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681461749269342e-05,
"loss": 3.9697,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.68062315451829e-05,
"loss": 3.9609,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679784559767238e-05,
"loss": 3.9398,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678947602896559e-05,
"loss": 3.9477,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678109008145507e-05,
"loss": 3.954,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677270413394455e-05,
"loss": 3.9576,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676431818643403e-05,
"loss": 3.9541,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9485,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674756267021672e-05,
"loss": 3.9517,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.67391767227062e-05,
"loss": 3.941,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673079077519568e-05,
"loss": 3.9508,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672240482768516e-05,
"loss": 3.947,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671401888017464e-05,
"loss": 3.9491,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705649311467855e-05,
"loss": 3.9578,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697263363957335e-05,
"loss": 3.9509,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688877416446815e-05,
"loss": 3.9403,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668049146893629e-05,
"loss": 3.9473,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6672121900229504e-05,
"loss": 3.9461,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663735952718984e-05,
"loss": 3.9502,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665535000520846e-05,
"loss": 3.9418,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664696405769794e-05,
"loss": 3.9387,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663857811018742e-05,
"loss": 3.9352,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66301921626769e-05,
"loss": 3.9465,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662182259397011e-05,
"loss": 3.9356,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661343664645959e-05,
"loss": 3.9235,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660505069894907e-05,
"loss": 3.9368,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659666475143855e-05,
"loss": 3.9425,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658829518273176e-05,
"loss": 3.9314,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657990923522124e-05,
"loss": 3.9422,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657152328771072e-05,
"loss": 3.9277,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.65631373402002e-05,
"loss": 3.9433,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655476777149341e-05,
"loss": 3.9286,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654638182398289e-05,
"loss": 3.9319,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653799587647237e-05,
"loss": 3.9468,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652960992896185e-05,
"loss": 3.9419,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521240360255066e-05,
"loss": 3.9322,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512854412744546e-05,
"loss": 3.9341,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.6504468465234026e-05,
"loss": 3.9302,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6496082517723506e-05,
"loss": 3.9365,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487712949016715e-05,
"loss": 3.9251,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479327001506195e-05,
"loss": 3.9393,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470941053995675e-05,
"loss": 3.9264,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462555106485155e-05,
"loss": 3.9387,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454185537778364e-05,
"loss": 3.9178,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445799590267844e-05,
"loss": 3.9266,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437413642757324e-05,
"loss": 3.9226,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429027695246804e-05,
"loss": 3.9267,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642064174773629e-05,
"loss": 3.9222,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.64122721790295e-05,
"loss": 3.9442,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640388623151898e-05,
"loss": 3.9297,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639550028400846e-05,
"loss": 3.9231,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638711433649794e-05,
"loss": 3.9163,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637874476779115e-05,
"loss": 3.9367,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637035882028063e-05,
"loss": 3.9337,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636197287277011e-05,
"loss": 3.9284,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635358692525959e-05,
"loss": 3.9213,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.63452173565528e-05,
"loss": 3.9296,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633683140904228e-05,
"loss": 3.9319,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632844546153176e-05,
"loss": 3.9225,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320059514021244e-05,
"loss": 3.9198,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311673566510724e-05,
"loss": 3.9232,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303303997803934e-05,
"loss": 3.9211,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294918050293413e-05,
"loss": 3.9132,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286532102782893e-05,
"loss": 3.9266,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6278146155272373e-05,
"loss": 3.9238,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626976020776185e-05,
"loss": 3.9165,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626139063905506e-05,
"loss": 3.9151,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625300469154454e-05,
"loss": 3.9115,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.952998399734497,
"eval_runtime": 307.7424,
"eval_samples_per_second": 1239.969,
"eval_steps_per_second": 38.75,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624461874403402e-05,
"loss": 3.9151,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.62362327965235e-05,
"loss": 3.9131,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622786322781671e-05,
"loss": 3.9267,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.62194772803062e-05,
"loss": 3.9136,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621109133279568e-05,
"loss": 3.9235,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620270538528516e-05,
"loss": 3.9102,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619433581657837e-05,
"loss": 3.9166,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618594986906785e-05,
"loss": 3.8991,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617756392155733e-05,
"loss": 3.9234,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616917797404681e-05,
"loss": 3.9169,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.6160808405340016e-05,
"loss": 3.9163,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.6152422457829496e-05,
"loss": 3.9226,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6144036510318976e-05,
"loss": 3.9019,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135650562808456e-05,
"loss": 3.9065,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.6127280994101665e-05,
"loss": 3.9132,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611889504659115e-05,
"loss": 3.8999,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611050909908063e-05,
"loss": 3.9016,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610212315157011e-05,
"loss": 3.8999,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609375358286332e-05,
"loss": 3.9001,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.60853676353528e-05,
"loss": 3.9262,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607698168784228e-05,
"loss": 3.9043,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606859574033176e-05,
"loss": 3.9058,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606022617162497e-05,
"loss": 3.9001,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605184022411445e-05,
"loss": 3.9082,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604345427660393e-05,
"loss": 3.8927,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603506832909341e-05,
"loss": 3.8949,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602669876038662e-05,
"loss": 3.8961,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.60183128128761e-05,
"loss": 3.9044,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009926865365585e-05,
"loss": 3.8885,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001540917855065e-05,
"loss": 3.8949,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.5993171349148274e-05,
"loss": 3.8965,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.5984785401637754e-05,
"loss": 3.9059,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.5976399454127234e-05,
"loss": 3.894,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5968013506616714e-05,
"loss": 3.8962,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.5959643937909923e-05,
"loss": 3.9011,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.5951257990399403e-05,
"loss": 3.8992,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594287204288888e-05,
"loss": 3.8796,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593448609537836e-05,
"loss": 3.8904,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.5926100147867836e-05,
"loss": 3.8767,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591773057916105e-05,
"loss": 3.8939,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590934463165054e-05,
"loss": 3.8837,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590095868414001e-05,
"loss": 3.8963,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589257273662949e-05,
"loss": 3.8873,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588420316792271e-05,
"loss": 3.8855,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587581722041219e-05,
"loss": 3.896,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586743127290166e-05,
"loss": 3.8928,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585904532539114e-05,
"loss": 3.8918,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585067575668436e-05,
"loss": 3.8773,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584228980917384e-05,
"loss": 3.8826,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583390386166331e-05,
"loss": 3.8967,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582551791415279e-05,
"loss": 3.8837,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.5817148345446006e-05,
"loss": 3.878,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808762397935486e-05,
"loss": 3.8804,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800376450424966e-05,
"loss": 3.8846,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791990502914446e-05,
"loss": 3.8677,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578362093420766e-05,
"loss": 3.8877,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5775234986697135e-05,
"loss": 3.8826,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766849039186615e-05,
"loss": 3.8886,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758463091676095e-05,
"loss": 3.89,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5750077144165575e-05,
"loss": 3.8713,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741707575458784e-05,
"loss": 3.8742,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733321627948264e-05,
"loss": 3.8807,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724935680437744e-05,
"loss": 3.8683,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571654973292723e-05,
"loss": 3.8663,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570818016422044e-05,
"loss": 3.8773,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569979421670992e-05,
"loss": 3.8786,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.56914082691994e-05,
"loss": 3.8678,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568302232168888e-05,
"loss": 3.8607,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567465275298209e-05,
"loss": 3.8778,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566626680547157e-05,
"loss": 3.8843,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565788085796105e-05,
"loss": 3.8743,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564949491045053e-05,
"loss": 3.8793,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564112534174374e-05,
"loss": 3.8849,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563273939423322e-05,
"loss": 3.8815,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.56243534467227e-05,
"loss": 3.8881,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615967499212184e-05,
"loss": 3.8629,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560759793050539e-05,
"loss": 3.8804,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559921198299487e-05,
"loss": 3.8789,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559082603548435e-05,
"loss": 3.8676,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558244008797383e-05,
"loss": 3.8788,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557407051926704e-05,
"loss": 3.8722,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556568457175652e-05,
"loss": 3.8834,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.5557298624246e-05,
"loss": 3.8788,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554891267673548e-05,
"loss": 3.8534,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554052672922496e-05,
"loss": 3.8655,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553215716051817e-05,
"loss": 3.8669,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552377121300765e-05,
"loss": 3.8731,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551538526549714e-05,
"loss": 3.873,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550699931798662e-05,
"loss": 3.8657,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549862974927983e-05,
"loss": 3.8689,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549024380176931e-05,
"loss": 3.8586,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548185785425879e-05,
"loss": 3.8676,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547347190674827e-05,
"loss": 3.8626,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.5465102338041476e-05,
"loss": 3.8691,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.5456716390530956e-05,
"loss": 3.8787,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448330443020436e-05,
"loss": 3.8696,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.5439944495509916e-05,
"loss": 3.8602,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.5431574926803125e-05,
"loss": 3.8673,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.5423188979292605e-05,
"loss": 3.8637,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541480303178209e-05,
"loss": 3.8705,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540641708427157e-05,
"loss": 3.8636,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539804751556478e-05,
"loss": 3.861,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538966156805426e-05,
"loss": 3.852,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538127562054374e-05,
"loss": 3.8711,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537288967303322e-05,
"loss": 3.851,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536452010432643e-05,
"loss": 3.8485,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535613415681591e-05,
"loss": 3.8545,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534774820930539e-05,
"loss": 3.8614,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533936226179487e-05,
"loss": 3.8533,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533099269308808e-05,
"loss": 3.8693,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532260674557756e-05,
"loss": 3.8521,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314220798067045e-05,
"loss": 3.8559,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.5305834850556525e-05,
"loss": 3.8566,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297465281849734e-05,
"loss": 3.8482,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.5289079334339214e-05,
"loss": 3.8724,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.5280693386828694e-05,
"loss": 3.8626,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.52723238181219e-05,
"loss": 3.8567,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526393787061138e-05,
"loss": 3.8556,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525555192310086e-05,
"loss": 3.8485,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524716597559034e-05,
"loss": 3.8594,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523878002807982e-05,
"loss": 3.8481,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.52303940805693e-05,
"loss": 3.8653,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522200813305878e-05,
"loss": 3.8482,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521362218554826e-05,
"loss": 3.8584,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520525261684148e-05,
"loss": 3.8465,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519686666933096e-05,
"loss": 3.8509,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518848072182044e-05,
"loss": 3.8463,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.518009477430992e-05,
"loss": 3.8522,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517172520560313e-05,
"loss": 3.8454,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516333925809261e-05,
"loss": 3.8684,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515495331058209e-05,
"loss": 3.8565,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514656736307156e-05,
"loss": 3.85,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513819779436478e-05,
"loss": 3.8375,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512981184685426e-05,
"loss": 3.8616,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512142589934374e-05,
"loss": 3.8573,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511303995183322e-05,
"loss": 3.8576,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510467038312643e-05,
"loss": 3.8463,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509628443561591e-05,
"loss": 3.852,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508789848810539e-05,
"loss": 3.8561,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079512540594866e-05,
"loss": 3.8537,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507114297188808e-05,
"loss": 3.844,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506275702437756e-05,
"loss": 3.8501,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.5054371076867035e-05,
"loss": 3.8462,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.5045985129356515e-05,
"loss": 3.8396,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503761556064973e-05,
"loss": 3.8513,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502922961313921e-05,
"loss": 3.8554,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020843665628684e-05,
"loss": 3.8425,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501245771811817e-05,
"loss": 3.8398,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500407177060765e-05,
"loss": 3.8463,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.911311626434326,
"eval_runtime": 340.6022,
"eval_samples_per_second": 1120.342,
"eval_steps_per_second": 35.012,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499568582309713e-05,
"loss": 3.8378,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498729987558661e-05,
"loss": 3.8425,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497891392807609e-05,
"loss": 3.8509,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497052798056557e-05,
"loss": 3.843,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496214203305505e-05,
"loss": 3.8552,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495375608554453e-05,
"loss": 3.8385,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494537013803401e-05,
"loss": 3.8432,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493698419052349e-05,
"loss": 3.828,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.49286146218167e-05,
"loss": 3.8554,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.492022867430618e-05,
"loss": 3.8452,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491184272679566e-05,
"loss": 3.8405,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490345677928514e-05,
"loss": 3.8539,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.4895087210578355e-05,
"loss": 3.8296,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.4886701263067835e-05,
"loss": 3.8415,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4878315315557315e-05,
"loss": 3.8419,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.4869945746850524e-05,
"loss": 3.8307,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.4861559799340004e-05,
"loss": 3.8307,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.4853173851829484e-05,
"loss": 3.8306,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.4844787904318964e-05,
"loss": 3.8342,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483641833561217e-05,
"loss": 3.8514,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482803238810165e-05,
"loss": 3.8352,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481964644059113e-05,
"loss": 3.8365,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481126049308061e-05,
"loss": 3.8332,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480289092437382e-05,
"loss": 3.8411,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479450497686331e-05,
"loss": 3.8248,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478611902935279e-05,
"loss": 3.8281,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477773308184227e-05,
"loss": 3.8253,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476936351313548e-05,
"loss": 3.836,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476097756562496e-05,
"loss": 3.8201,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475259161811444e-05,
"loss": 3.8291,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474420567060392e-05,
"loss": 3.8295,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.4735836101897126e-05,
"loss": 3.8381,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.4727450154386606e-05,
"loss": 3.8254,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.4719064206876086e-05,
"loss": 3.8295,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710678259365566e-05,
"loss": 3.8317,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.4702308690658775e-05,
"loss": 3.8317,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469392274314826e-05,
"loss": 3.8179,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468553679563774e-05,
"loss": 3.8211,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467715084812722e-05,
"loss": 3.8104,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466878127942043e-05,
"loss": 3.8271,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466039533190991e-05,
"loss": 3.8194,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465200938439939e-05,
"loss": 3.8312,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464362343688887e-05,
"loss": 3.8208,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463525386818208e-05,
"loss": 3.8244,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462686792067156e-05,
"loss": 3.8292,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461848197316104e-05,
"loss": 3.8272,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.461009602565052e-05,
"loss": 3.8283,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460172645694373e-05,
"loss": 3.8153,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4593340509433216e-05,
"loss": 3.8101,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584954561922696e-05,
"loss": 3.8328,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457656861441217e-05,
"loss": 3.8182,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4568215424509114e-05,
"loss": 3.813,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559829476998594e-05,
"loss": 3.8156,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551443529488074e-05,
"loss": 3.8221,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4543057581977554e-05,
"loss": 3.8034,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534671634467034e-05,
"loss": 3.8248,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4526285686956514e-05,
"loss": 3.819,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.4517899739445994e-05,
"loss": 3.8223,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450951379193547e-05,
"loss": 3.8279,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450114422322868e-05,
"loss": 3.811,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449275827571816e-05,
"loss": 3.8089,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448437232820764e-05,
"loss": 3.8242,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447598638069712e-05,
"loss": 3.8009,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446761681199034e-05,
"loss": 3.8044,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445923086447982e-05,
"loss": 3.8175,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445084491696929e-05,
"loss": 3.8172,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444245896945877e-05,
"loss": 3.8031,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443408940075199e-05,
"loss": 3.8,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442570345324147e-05,
"loss": 3.8145,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441731750573094e-05,
"loss": 3.8193,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440893155822042e-05,
"loss": 3.8153,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.4400561989513636e-05,
"loss": 3.8137,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.4392176042003116e-05,
"loss": 3.8246,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.4383790094492596e-05,
"loss": 3.8177,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.4375404146982076e-05,
"loss": 3.8293,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436703457827529e-05,
"loss": 3.8017,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.4358648630764765e-05,
"loss": 3.8216,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.4350262683254245e-05,
"loss": 3.8154,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.4341876735743725e-05,
"loss": 3.8046,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333507167036934e-05,
"loss": 3.821,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4325121219526414e-05,
"loss": 3.8105,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316735272015894e-05,
"loss": 3.8184,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4308349324505374e-05,
"loss": 3.8209,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429997975579859e-05,
"loss": 3.7942,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429159380828807e-05,
"loss": 3.8069,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428320786077755e-05,
"loss": 3.8054,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427482191326703e-05,
"loss": 3.815,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426645234456024e-05,
"loss": 3.8115,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425806639704972e-05,
"loss": 3.8027,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.42496804495392e-05,
"loss": 3.8105,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424129450202868e-05,
"loss": 3.8024,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423292493332189e-05,
"loss": 3.8051,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422453898581137e-05,
"loss": 3.8039,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421615303830085e-05,
"loss": 3.8125,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420776709079033e-05,
"loss": 3.8186,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.4199397522083544e-05,
"loss": 3.809,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4191011574573024e-05,
"loss": 3.7996,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182625627062504e-05,
"loss": 3.8077,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4174239679551984e-05,
"loss": 3.8065,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416587011084519e-05,
"loss": 3.8123,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415748416333467e-05,
"loss": 3.8073,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414909821582415e-05,
"loss": 3.8002,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414071226831363e-05,
"loss": 3.7946,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413234269960684e-05,
"loss": 3.8088,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412395675209632e-05,
"loss": 3.7938,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.41155708045858e-05,
"loss": 3.7946,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410718485707528e-05,
"loss": 3.792,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.40988152883685e-05,
"loss": 3.8062,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409042934085798e-05,
"loss": 3.7912,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408204339334746e-05,
"loss": 3.8143,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407365744583694e-05,
"loss": 3.7903,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.4065287877130146e-05,
"loss": 3.802,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.4056901929619626e-05,
"loss": 3.7994,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.4048515982109106e-05,
"loss": 3.7898,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.4040146413402315e-05,
"loss": 3.8129,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.4031760465891795e-05,
"loss": 3.8073,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.4023374518381275e-05,
"loss": 3.7988,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.4014988570870755e-05,
"loss": 3.7995,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400661900216397e-05,
"loss": 3.793,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399823305465345e-05,
"loss": 3.804,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398984710714293e-05,
"loss": 3.785,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398146115963241e-05,
"loss": 3.8099,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397309159092562e-05,
"loss": 3.7964,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.39647056434151e-05,
"loss": 3.7975,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395631969590458e-05,
"loss": 3.7928,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394793374839406e-05,
"loss": 3.7952,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393954780088354e-05,
"loss": 3.7879,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393117823217675e-05,
"loss": 3.7984,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392279228466623e-05,
"loss": 3.7915,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391440633715571e-05,
"loss": 3.8084,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390602038964519e-05,
"loss": 3.801,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897650820938405e-05,
"loss": 3.7971,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.3889264873427885e-05,
"loss": 3.7811,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.3880878925917365e-05,
"loss": 3.803,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872492978406845e-05,
"loss": 3.8018,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3864123409700054e-05,
"loss": 3.8002,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855737462189534e-05,
"loss": 3.7921,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3847351514679014e-05,
"loss": 3.7957,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383898194597222e-05,
"loss": 3.797,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.38305959984617e-05,
"loss": 3.8029,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382221005095118e-05,
"loss": 3.7885,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381382410344066e-05,
"loss": 3.7966,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380545453473388e-05,
"loss": 3.7885,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379706858722336e-05,
"loss": 3.7867,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378869901851657e-05,
"loss": 3.801,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378031307100605e-05,
"loss": 3.7933,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377192712349553e-05,
"loss": 3.7917,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376354117598501e-05,
"loss": 3.7858,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375515522847449e-05,
"loss": 3.7908,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.8864755630493164,
"eval_runtime": 310.1007,
"eval_samples_per_second": 1230.539,
"eval_steps_per_second": 38.455,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.374676928096397e-05,
"loss": 3.7881,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.373838333345345e-05,
"loss": 3.7855,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.372999738594293e-05,
"loss": 3.8005,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.3721627817236136e-05,
"loss": 3.7918,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.3713241869725616e-05,
"loss": 3.7963,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.3704855922215096e-05,
"loss": 3.7888,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.369648635350831e-05,
"loss": 3.7865,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368810040599779e-05,
"loss": 3.7763,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367971445848727e-05,
"loss": 3.7968,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367132851097675e-05,
"loss": 3.7964,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366295894226996e-05,
"loss": 3.7879,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.365457299475944e-05,
"loss": 3.7992,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.364620342605265e-05,
"loss": 3.7779,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.363781747854213e-05,
"loss": 3.786,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.362943153103161e-05,
"loss": 3.7918,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.362104558352109e-05,
"loss": 3.7758,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.361265963601057e-05,
"loss": 3.7804,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.360427368850005e-05,
"loss": 3.7789,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.359588774098953e-05,
"loss": 3.7804,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.358750179347901e-05,
"loss": 3.7979,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.3579132224772226e-05,
"loss": 3.7857,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.3570746277261706e-05,
"loss": 3.7872,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.3562360329751186e-05,
"loss": 3.7784,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.3553974382240665e-05,
"loss": 3.7902,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.3545604813533875e-05,
"loss": 3.7724,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.3537218866023355e-05,
"loss": 3.7768,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.3528832918512834e-05,
"loss": 3.7776,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.3520446971002314e-05,
"loss": 3.7825,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.3512077402295524e-05,
"loss": 3.7683,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.3503691454785003e-05,
"loss": 3.7764,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.3495305507274483e-05,
"loss": 3.7825,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.3486919559763963e-05,
"loss": 3.7848,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.347854999105718e-05,
"loss": 3.7779,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.347016404354666e-05,
"loss": 3.7773,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.346177809603614e-05,
"loss": 3.7825,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345340852732935e-05,
"loss": 3.7776,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344502257981883e-05,
"loss": 3.7696,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.343663663230831e-05,
"loss": 3.7686,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.342825068479779e-05,
"loss": 3.7616,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.3419881116091e-05,
"loss": 3.7756,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.341149516858048e-05,
"loss": 3.771,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.340310922106996e-05,
"loss": 3.7801,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.339472327355944e-05,
"loss": 3.7712,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338635370485265e-05,
"loss": 3.772,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337796775734213e-05,
"loss": 3.7823,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.336958180983161e-05,
"loss": 3.7729,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.3361195862321086e-05,
"loss": 3.7785,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.33528262936143e-05,
"loss": 3.7634,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334444034610378e-05,
"loss": 3.7621,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.333605439859326e-05,
"loss": 3.7854,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.3327668451082735e-05,
"loss": 3.7687,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.331929888237595e-05,
"loss": 3.7658,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331092931366916e-05,
"loss": 3.765,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.330254336615864e-05,
"loss": 3.7745,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.329415741864813e-05,
"loss": 3.7537,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328577147113761e-05,
"loss": 3.7737,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.3277385523627087e-05,
"loss": 3.7708,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326899957611656e-05,
"loss": 3.7673,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326061362860604e-05,
"loss": 3.7828,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.3252244059899256e-05,
"loss": 3.7612,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.3243858112388736e-05,
"loss": 3.7631,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.323547216487821e-05,
"loss": 3.7756,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322708621736769e-05,
"loss": 3.756,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.3218716648660905e-05,
"loss": 3.7564,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.321033070115038e-05,
"loss": 3.7642,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.3201944753639864e-05,
"loss": 3.7687,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.3193558806129344e-05,
"loss": 3.7578,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.318518923742256e-05,
"loss": 3.7526,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.3176803289912033e-05,
"loss": 3.762,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.3168417342401513e-05,
"loss": 3.7684,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.3160031394890993e-05,
"loss": 3.769,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.315166182618421e-05,
"loss": 3.7685,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.314327587867368e-05,
"loss": 3.7733,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313488993116316e-05,
"loss": 3.7728,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.312650398365264e-05,
"loss": 3.7832,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311813441494585e-05,
"loss": 3.7532,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310974846743533e-05,
"loss": 3.7768,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310136251992482e-05,
"loss": 3.7709,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.30929765724143e-05,
"loss": 3.7508,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308460700370751e-05,
"loss": 3.7766,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.307622105619699e-05,
"loss": 3.761,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.306783510868647e-05,
"loss": 3.7718,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.3059465539979676e-05,
"loss": 3.7743,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.3051079592469156e-05,
"loss": 3.7493,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.3042693644958636e-05,
"loss": 3.7555,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.3034307697448116e-05,
"loss": 3.7576,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.3025921749937596e-05,
"loss": 3.7683,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.3017535802427076e-05,
"loss": 3.7625,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.3009149854916556e-05,
"loss": 3.7593,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.3000763907406036e-05,
"loss": 3.7576,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.299239433869925e-05,
"loss": 3.7609,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.298400839118873e-05,
"loss": 3.7587,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.297562244367821e-05,
"loss": 3.756,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.296725287497142e-05,
"loss": 3.7688,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.29588669274609e-05,
"loss": 3.7679,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.295048097995038e-05,
"loss": 3.7694,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294209503243986e-05,
"loss": 3.7497,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293372546373307e-05,
"loss": 3.7617,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.292533951622255e-05,
"loss": 3.7573,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.291695356871203e-05,
"loss": 3.765,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.290856762120151e-05,
"loss": 3.7625,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.2900198052494725e-05,
"loss": 3.7561,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.2891812104984205e-05,
"loss": 3.7479,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.2883426157473685e-05,
"loss": 3.7625,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.2875040209963165e-05,
"loss": 3.7524,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.2866670641256374e-05,
"loss": 3.7473,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.2858284693745854e-05,
"loss": 3.7435,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.2849915125039063e-05,
"loss": 3.7586,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.2841529177528543e-05,
"loss": 3.7524,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.2833143230018023e-05,
"loss": 3.7668,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.28247572825075e-05,
"loss": 3.7484,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281637133499698e-05,
"loss": 3.7559,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.280798538748646e-05,
"loss": 3.7567,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.279959943997594e-05,
"loss": 3.7455,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.279121349246542e-05,
"loss": 3.7686,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.278284392375864e-05,
"loss": 3.7622,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.277447435505185e-05,
"loss": 3.7552,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276608840754133e-05,
"loss": 3.755,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.275770246003081e-05,
"loss": 3.7498,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.274931651252029e-05,
"loss": 3.7602,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.274093056500977e-05,
"loss": 3.7379,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273254461749925e-05,
"loss": 3.7658,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.272415866998873e-05,
"loss": 3.7477,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.271577272247821e-05,
"loss": 3.7503,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.270740315377142e-05,
"loss": 3.7515,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.26990172062609e-05,
"loss": 3.7485,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.269064763755411e-05,
"loss": 3.7484,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.268226169004359e-05,
"loss": 3.7523,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.267387574253307e-05,
"loss": 3.7492,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.266548979502255e-05,
"loss": 3.7625,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.265710384751203e-05,
"loss": 3.754,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.264871790000151e-05,
"loss": 3.7576,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.2640331952490986e-05,
"loss": 3.7351,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.2631946004980466e-05,
"loss": 3.7628,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.262357643627368e-05,
"loss": 3.7553,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.261519048876316e-05,
"loss": 3.757,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.2606804541252635e-05,
"loss": 3.7485,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.2598418593742115e-05,
"loss": 3.7509,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.259004902503533e-05,
"loss": 3.7586,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.258166307752481e-05,
"loss": 3.7608,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.257327713001429e-05,
"loss": 3.7441,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256489118250377e-05,
"loss": 3.7503,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.2556521613796986e-05,
"loss": 3.7493,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254813566628646e-05,
"loss": 3.7431,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.2539766097579675e-05,
"loss": 3.7584,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.2531380150069155e-05,
"loss": 3.749,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.2522994202558635e-05,
"loss": 3.7528,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251460825504811e-05,
"loss": 3.738,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250622230753759e-05,
"loss": 3.7515,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 3.8699309825897217,
"eval_runtime": 305.6067,
"eval_samples_per_second": 1248.634,
"eval_steps_per_second": 39.021,
"step": 457920
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.200394765351813e+17,
"trial_name": null,
"trial_params": null
}