abhinavp's picture
Training in progress, epoch 1, checkpoint
331c994 verified
{
"best_metric": 3.8758106231689453,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/passive/transformer/2/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": 10.9849,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.816,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1947,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9869,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8217,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.702,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6137,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5369,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4547,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4049,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3541,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3138,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2656,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2167,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1785,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1299,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1155,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0824,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0521,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0241,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0148,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9816,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9577,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9294,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9264,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8884,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8763,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8478,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8376,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8234,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8052,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.797,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7829,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7678,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7654,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7438,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7398,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.6986,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7114,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6752,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.686,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6677,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6654,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6434,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6531,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6385,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.634,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6279,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5949,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5986,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.6002,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.5895,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5809,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5626,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5597,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5419,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5649,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5185,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5429,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5333,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.514,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5125,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5039,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4977,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4882,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5005,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4782,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4722,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.466,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4677,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4758,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4702,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4465,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4606,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.463,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4319,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4402,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.431,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4258,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4164,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4216,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4238,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4262,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.403,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.3816,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.3954,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.3962,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.3956,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.383,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 4.3847,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.383,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.379,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.3675,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3725,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3598,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3726,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3598,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.341,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3528,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3524,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3576,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3399,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3402,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3266,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3366,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3176,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.326,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.322,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.3214,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.3123,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.3138,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.3062,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.3128,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3045,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.2999,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3147,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.3032,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.3016,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.2891,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.2927,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2884,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.2848,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.2948,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2798,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2848,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2656,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2695,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.2756,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2662,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2594,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.2856,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2647,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.2583,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.2593,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.2592,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.2609,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2566,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2532,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2596,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2565,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2489,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.242,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2479,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.2377,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2407,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.2345,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2335,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2394,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2269,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2246,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.199779987335205,
"eval_runtime": 302.9366,
"eval_samples_per_second": 1259.64,
"eval_steps_per_second": 39.365,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.2099,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.2096,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2358,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2209,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2153,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2108,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.21,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.198,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2101,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.2069,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2056,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2089,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642000625015155e-05,
"loss": 4.1927,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.1879,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.1804,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.1797,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.1903,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.1789,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.1846,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.2011,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.1819,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.1836,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.1741,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.188,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.1699,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853301606498585e-05,
"loss": 4.1706,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.1635,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.1675,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.1617,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.84994886537475e-05,
"loss": 4.1579,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.1614,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.1704,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1596,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846596124250916e-05,
"loss": 4.1637,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845757529499864e-05,
"loss": 4.155,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.1642,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.1376,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843243383127081e-05,
"loss": 4.1543,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842404788376029e-05,
"loss": 4.1303,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.152,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.1363,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398906420032456e-05,
"loss": 4.1491,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.8390520472521936e-05,
"loss": 4.1339,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382134525011416e-05,
"loss": 4.1449,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83737485775009e-05,
"loss": 4.144,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836537900879411e-05,
"loss": 4.1419,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835699306128359e-05,
"loss": 4.1454,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834860711377307e-05,
"loss": 4.1165,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834023754506628e-05,
"loss": 4.1255,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833185159755576e-05,
"loss": 4.1368,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832346565004524e-05,
"loss": 4.1341,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831507970253472e-05,
"loss": 4.1275,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.83066937550242e-05,
"loss": 4.1222,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829830780751368e-05,
"loss": 4.1166,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828992186000316e-05,
"loss": 4.1094,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828153591249264e-05,
"loss": 4.1247,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273166343785856e-05,
"loss": 4.1044,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264780396275336e-05,
"loss": 4.1159,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256394448764816e-05,
"loss": 4.1253,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248008501254296e-05,
"loss": 4.1055,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239638932547505e-05,
"loss": 4.1064,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231252985036985e-05,
"loss": 4.1042,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222867037526465e-05,
"loss": 4.0971,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214481090015945e-05,
"loss": 4.0972,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206111521309154e-05,
"loss": 4.1153,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197725573798634e-05,
"loss": 4.0989,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189339626288114e-05,
"loss": 4.0956,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180953678777594e-05,
"loss": 4.0942,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817258411007081e-05,
"loss": 4.0932,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816419816256029e-05,
"loss": 4.1085,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815581221504977e-05,
"loss": 4.1036,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814742626753924e-05,
"loss": 4.0936,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813905669883246e-05,
"loss": 4.1034,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813067075132194e-05,
"loss": 4.1074,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812228480381141e-05,
"loss": 4.0872,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811391523510463e-05,
"loss": 4.0948,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810552928759411e-05,
"loss": 4.0921,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809714334008359e-05,
"loss": 4.0901,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808875739257306e-05,
"loss": 4.083,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808037144506255e-05,
"loss": 4.0868,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807198549755203e-05,
"loss": 4.0954,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806359955004151e-05,
"loss": 4.0929,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805521360253099e-05,
"loss": 4.0834,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046844033824197e-05,
"loss": 4.0603,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803847446511741e-05,
"loss": 4.0758,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8030088517606886e-05,
"loss": 4.0824,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.8021702570096366e-05,
"loss": 4.0814,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013316622585846e-05,
"loss": 4.0761,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004930675075325e-05,
"loss": 4.0727,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996561106368535e-05,
"loss": 4.0824,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988175158858015e-05,
"loss": 4.071,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979789211347494e-05,
"loss": 4.0651,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797140326383698e-05,
"loss": 4.0805,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796301731632646e-05,
"loss": 4.0613,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795464774761967e-05,
"loss": 4.0827,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794626180010915e-05,
"loss": 4.0733,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793787585259863e-05,
"loss": 4.053,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792948990508811e-05,
"loss": 4.0672,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792110395757759e-05,
"loss": 4.0664,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791271801006707e-05,
"loss": 4.0758,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790433206255655e-05,
"loss": 4.0645,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789594611504603e-05,
"loss": 4.0606,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788757654633924e-05,
"loss": 4.052,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787919059882872e-05,
"loss": 4.0669,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.78708046513182e-05,
"loss": 4.0452,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862435082611415e-05,
"loss": 4.0553,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854049135100895e-05,
"loss": 4.0584,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845663187590375e-05,
"loss": 4.0557,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837277240079855e-05,
"loss": 4.0447,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828891292569335e-05,
"loss": 4.0549,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820505345058815e-05,
"loss": 4.0483,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812119397548295e-05,
"loss": 4.052,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803749828841504e-05,
"loss": 4.0512,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795363881330984e-05,
"loss": 4.0446,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786977933820464e-05,
"loss": 4.0684,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778591986309944e-05,
"loss": 4.0542,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777022241760315e-05,
"loss": 4.0516,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776183647009263e-05,
"loss": 4.0392,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775345052258212e-05,
"loss": 4.0453,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450645750716e-05,
"loss": 4.0458,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773667862756108e-05,
"loss": 4.0367,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772829268005055e-05,
"loss": 4.055,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771990673254003e-05,
"loss": 4.0434,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771152078502951e-05,
"loss": 4.0428,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770315121632272e-05,
"loss": 4.0354,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.76947652688122e-05,
"loss": 4.0371,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768637932130168e-05,
"loss": 4.0401,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767799337379116e-05,
"loss": 4.0364,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766962380508437e-05,
"loss": 4.0251,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.7661254236377586e-05,
"loss": 4.0555,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765286828886707e-05,
"loss": 4.0436,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764448234135655e-05,
"loss": 4.0321,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.7636096393846026e-05,
"loss": 4.0311,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.7627710446335506e-05,
"loss": 4.0291,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761934087762872e-05,
"loss": 4.0395,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610954930118195e-05,
"loss": 4.0352,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602568982607675e-05,
"loss": 4.0312,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594183035097155e-05,
"loss": 4.041,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758581346639037e-05,
"loss": 4.0341,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577427518879844e-05,
"loss": 4.0359,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569041571369324e-05,
"loss": 4.0263,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756065562385881e-05,
"loss": 4.0349,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755226967634829e-05,
"loss": 4.028,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754388372883777e-05,
"loss": 4.0255,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753551416013098e-05,
"loss": 4.0272,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752712821262046e-05,
"loss": 4.0283,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751874226510994e-05,
"loss": 4.0301,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751035631759942e-05,
"loss": 4.0183,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.75019703700889e-05,
"loss": 4.0196,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.0316243171691895,
"eval_runtime": 302.8009,
"eval_samples_per_second": 1260.204,
"eval_steps_per_second": 39.382,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749358442257838e-05,
"loss": 4.0061,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748519847506786e-05,
"loss": 4.0062,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747681252755734e-05,
"loss": 4.0333,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746842658004682e-05,
"loss": 4.0255,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.74600406325363e-05,
"loss": 4.017,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745165468502578e-05,
"loss": 4.0128,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744326873751526e-05,
"loss": 4.0168,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743488279000474e-05,
"loss": 4.0023,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742649684249422e-05,
"loss": 4.0198,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.74181108949837e-05,
"loss": 4.0145,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740974132627691e-05,
"loss": 4.0128,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740135537876639e-05,
"loss": 4.0161,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392985810059604e-05,
"loss": 4.0028,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384599862549084e-05,
"loss": 4.0011,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737621391503856e-05,
"loss": 3.9981,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736782796752804e-05,
"loss": 3.9969,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735944202001752e-05,
"loss": 4.0018,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7351056072507e-05,
"loss": 3.996,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734267012499648e-05,
"loss": 4.002,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733428417748596e-05,
"loss": 4.0235,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732591460877917e-05,
"loss": 4.0003,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731752866126865e-05,
"loss": 4.0036,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730914271375813e-05,
"loss": 4.001,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730075676624761e-05,
"loss": 4.0075,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729238719754082e-05,
"loss": 3.9895,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.72840012500303e-05,
"loss": 4.0009,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727561530251978e-05,
"loss": 3.9888,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726722935500926e-05,
"loss": 3.9915,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725884340749874e-05,
"loss": 3.9873,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725045745998822e-05,
"loss": 3.9858,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724208789128143e-05,
"loss": 3.9898,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723370194377091e-05,
"loss": 3.9999,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.72253159962604e-05,
"loss": 3.9913,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721693004874988e-05,
"loss": 3.9961,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720854410123936e-05,
"loss": 3.982,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200174532532566e-05,
"loss": 4.001,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191788585022046e-05,
"loss": 3.9708,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183402637511526e-05,
"loss": 3.9911,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175016690001006e-05,
"loss": 3.967,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166647121294215e-05,
"loss": 3.9875,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158261173783695e-05,
"loss": 3.9744,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149875226273175e-05,
"loss": 3.9913,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141489278762655e-05,
"loss": 3.976,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133119710055864e-05,
"loss": 3.9817,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712473376254535e-05,
"loss": 3.9852,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711634781503483e-05,
"loss": 3.9855,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710796186752431e-05,
"loss": 3.9844,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709959229881752e-05,
"loss": 3.9648,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091206351307e-05,
"loss": 3.9649,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708282040379648e-05,
"loss": 3.9827,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707443445628596e-05,
"loss": 3.9784,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706606488757917e-05,
"loss": 3.9733,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705767894006865e-05,
"loss": 3.9697,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704929299255813e-05,
"loss": 3.9675,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704090704504761e-05,
"loss": 3.9539,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703253747634082e-05,
"loss": 3.9714,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024151528830305e-05,
"loss": 3.9555,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015765581319785e-05,
"loss": 3.9679,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007379633809265e-05,
"loss": 3.9773,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6999010065102474e-05,
"loss": 3.9554,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990624117591954e-05,
"loss": 3.9585,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982238170081434e-05,
"loss": 3.9609,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973852222570914e-05,
"loss": 3.9508,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696548265386412e-05,
"loss": 3.9482,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69570967063536e-05,
"loss": 3.9708,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694871075884308e-05,
"loss": 3.9579,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694032481133256e-05,
"loss": 3.9506,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693193886382204e-05,
"loss": 3.9523,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692356929511526e-05,
"loss": 3.9534,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691518334760474e-05,
"loss": 3.9637,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690679740009422e-05,
"loss": 3.9624,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689841145258369e-05,
"loss": 3.9525,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689004188387691e-05,
"loss": 3.9644,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688165593636639e-05,
"loss": 3.9621,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687326998885587e-05,
"loss": 3.949,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686488404134534e-05,
"loss": 3.9558,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856514472638556e-05,
"loss": 3.9589,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848128525128036e-05,
"loss": 3.9516,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683974257761751e-05,
"loss": 3.9487,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831356630106996e-05,
"loss": 3.9496,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822987061400205e-05,
"loss": 3.9571,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681460111388969e-05,
"loss": 3.9598,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806215166379165e-05,
"loss": 3.9446,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797829218868645e-05,
"loss": 3.9321,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678945965016186e-05,
"loss": 3.9404,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678107370265134e-05,
"loss": 3.9495,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772687755140814e-05,
"loss": 3.9512,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764301807630294e-05,
"loss": 3.9414,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9397,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674754629141298e-05,
"loss": 3.9548,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673916034390246e-05,
"loss": 3.9371,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673077439639194e-05,
"loss": 3.9379,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672240482768516e-05,
"loss": 3.9483,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671401888017464e-05,
"loss": 3.9363,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705649311467855e-05,
"loss": 3.956,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697263363957335e-05,
"loss": 3.9419,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688877416446815e-05,
"loss": 3.9281,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668049146893629e-05,
"loss": 3.9414,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667210552142577e-05,
"loss": 3.9379,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666371957391525e-05,
"loss": 3.9519,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665533362640473e-05,
"loss": 3.9426,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664694767889421e-05,
"loss": 3.9334,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663857811018742e-05,
"loss": 3.923,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66301921626769e-05,
"loss": 3.9416,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621806215166383e-05,
"loss": 3.9236,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613420267655863e-05,
"loss": 3.9338,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660505069894907e-05,
"loss": 3.9351,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659666475143855e-05,
"loss": 3.9334,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658827880392803e-05,
"loss": 3.9224,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657989285641751e-05,
"loss": 3.939,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657152328771072e-05,
"loss": 3.9254,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.65631373402002e-05,
"loss": 3.9285,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655475139268968e-05,
"loss": 3.9349,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654636544517916e-05,
"loss": 3.9263,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653799587647237e-05,
"loss": 3.9457,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652960992896185e-05,
"loss": 3.9354,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652122398145134e-05,
"loss": 3.9348,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651283803394082e-05,
"loss": 3.9217,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.6504468465234026e-05,
"loss": 3.9283,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6496082517723506e-05,
"loss": 3.93,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487696570212986e-05,
"loss": 3.9156,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479310622702466e-05,
"loss": 3.9344,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470941053995675e-05,
"loss": 3.9287,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462555106485155e-05,
"loss": 3.9258,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454169158974635e-05,
"loss": 3.9233,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445799590267844e-05,
"loss": 3.9234,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437413642757324e-05,
"loss": 3.918,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429027695246804e-05,
"loss": 3.9258,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642064174773629e-05,
"loss": 3.9137,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.64122721790295e-05,
"loss": 3.9369,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640388623151898e-05,
"loss": 3.9339,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639550028400846e-05,
"loss": 3.9192,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638711433649794e-05,
"loss": 3.9163,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637874476779115e-05,
"loss": 3.92,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637035882028063e-05,
"loss": 3.9275,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636197287277011e-05,
"loss": 3.9239,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635358692525959e-05,
"loss": 3.919,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.63452173565528e-05,
"loss": 3.9268,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633683140904228e-05,
"loss": 3.9232,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632844546153176e-05,
"loss": 3.9282,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320059514021244e-05,
"loss": 3.9147,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311689945314454e-05,
"loss": 3.9284,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303303997803934e-05,
"loss": 3.9204,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294918050293413e-05,
"loss": 3.9127,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286532102782893e-05,
"loss": 3.9218,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.62781625340761e-05,
"loss": 3.9228,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626977658656558e-05,
"loss": 3.9187,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626139063905506e-05,
"loss": 3.9085,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625300469154454e-05,
"loss": 3.9115,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9574666023254395,
"eval_runtime": 308.0985,
"eval_samples_per_second": 1238.536,
"eval_steps_per_second": 38.705,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624463512283775e-05,
"loss": 3.9087,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623624917532723e-05,
"loss": 3.9004,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622786322781671e-05,
"loss": 3.9249,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.62194772803062e-05,
"loss": 3.9198,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621110771159941e-05,
"loss": 3.9197,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620272176408889e-05,
"loss": 3.9016,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619433581657837e-05,
"loss": 3.915,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618594986906785e-05,
"loss": 3.8951,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177580300361056e-05,
"loss": 3.918,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6169194352850536e-05,
"loss": 3.912,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.6160808405340016e-05,
"loss": 3.905,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.6152422457829496e-05,
"loss": 3.9162,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6144052889122705e-05,
"loss": 3.8978,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135666941612185e-05,
"loss": 3.9013,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.6127280994101665e-05,
"loss": 3.8933,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611889504659115e-05,
"loss": 3.9002,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611050909908063e-05,
"loss": 3.8967,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610212315157011e-05,
"loss": 3.8974,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609373720405959e-05,
"loss": 3.8991,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.6085351256549065e-05,
"loss": 3.9191,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607698168784228e-05,
"loss": 3.9007,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606859574033176e-05,
"loss": 3.9055,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606020979282124e-05,
"loss": 3.9013,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051823845310714e-05,
"loss": 3.9073,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604345427660393e-05,
"loss": 3.8919,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603506832909341e-05,
"loss": 3.9017,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602668238158289e-05,
"loss": 3.8928,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601829643407237e-05,
"loss": 3.8932,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009926865365585e-05,
"loss": 3.8873,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001540917855065e-05,
"loss": 3.8941,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599315497034454e-05,
"loss": 3.8903,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.5984785401637754e-05,
"loss": 3.9022,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.5976399454127234e-05,
"loss": 3.8959,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5968013506616714e-05,
"loss": 3.8972,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595962755910619e-05,
"loss": 3.8895,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595124161159567e-05,
"loss": 3.9027,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594285566408515e-05,
"loss": 3.8832,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593446971657463e-05,
"loss": 3.8944,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592608376906411e-05,
"loss": 3.8721,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591771420035732e-05,
"loss": 3.8911,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.59093282528468e-05,
"loss": 3.8855,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590094230533628e-05,
"loss": 3.8985,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589255635782576e-05,
"loss": 3.8852,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588418678911897e-05,
"loss": 3.8886,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587580084160845e-05,
"loss": 3.8902,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586741489409793e-05,
"loss": 3.8955,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585902894658741e-05,
"loss": 3.8881,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585065937788062e-05,
"loss": 3.8769,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.58422734303701e-05,
"loss": 3.8701,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583388748285958e-05,
"loss": 3.8922,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582550153534906e-05,
"loss": 3.8885,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581713196664228e-05,
"loss": 3.8843,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580874601913176e-05,
"loss": 3.8767,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580036007162124e-05,
"loss": 3.8812,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579197412411072e-05,
"loss": 3.8628,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.57835881766002e-05,
"loss": 3.8852,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577520222908968e-05,
"loss": 3.8656,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576681628157916e-05,
"loss": 3.8779,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758446712872366e-05,
"loss": 3.8851,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5750060765361846e-05,
"loss": 3.8746,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741674817851326e-05,
"loss": 3.8664,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733288870340806e-05,
"loss": 3.8743,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724919301634015e-05,
"loss": 3.8632,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716533354123495e-05,
"loss": 3.8654,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5708147406612975e-05,
"loss": 3.8786,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569976145910246e-05,
"loss": 3.8694,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569139189039567e-05,
"loss": 3.864,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568300594288515e-05,
"loss": 3.8619,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567461999537463e-05,
"loss": 3.8684,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566623404786411e-05,
"loss": 3.8736,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565786447915732e-05,
"loss": 3.8771,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.56494785316468e-05,
"loss": 3.8693,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564110896294001e-05,
"loss": 3.8774,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563272301542949e-05,
"loss": 3.8782,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562433706791897e-05,
"loss": 3.865,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561595112040845e-05,
"loss": 3.8678,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560756517289793e-05,
"loss": 3.8746,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.5599179225387415e-05,
"loss": 3.8702,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.5590793277876895e-05,
"loss": 3.8646,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582407330366375e-05,
"loss": 3.8654,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.5574037761659584e-05,
"loss": 3.8717,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.5565651814149064e-05,
"loss": 3.8761,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.5557265866638544e-05,
"loss": 3.8635,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554889629793175e-05,
"loss": 3.8511,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554051035042123e-05,
"loss": 3.8525,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553212440291071e-05,
"loss": 3.8621,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552373845540019e-05,
"loss": 3.8691,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515352507889666e-05,
"loss": 3.864,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550696656037915e-05,
"loss": 3.8526,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549858061286863e-05,
"loss": 3.8697,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549021104416185e-05,
"loss": 3.8621,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548184147545506e-05,
"loss": 3.8563,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547345552794454e-05,
"loss": 3.8604,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546506958043402e-05,
"loss": 3.8629,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.54566836329235e-05,
"loss": 3.8732,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544829768541297e-05,
"loss": 3.8564,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543991173790245e-05,
"loss": 3.8438,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543152579039193e-05,
"loss": 3.865,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542315622168514e-05,
"loss": 3.8573,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541477027417462e-05,
"loss": 3.8703,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406384326664106e-05,
"loss": 3.8652,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5397998379153586e-05,
"loss": 3.853,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389612431643066e-05,
"loss": 3.8453,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5381226484132546e-05,
"loss": 3.8628,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372840536622026e-05,
"loss": 3.843,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364454589111506e-05,
"loss": 3.8559,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5356085020404715e-05,
"loss": 3.8526,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347699072894195e-05,
"loss": 3.8586,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339313125383675e-05,
"loss": 3.8426,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330927177873155e-05,
"loss": 3.8609,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322557609166364e-05,
"loss": 3.8478,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314188040459573e-05,
"loss": 3.8485,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530580209294906e-05,
"loss": 3.8595,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529741614543854e-05,
"loss": 3.8484,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528903019792802e-05,
"loss": 3.8692,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.52806442504175e-05,
"loss": 3.8585,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527227468171071e-05,
"loss": 3.8555,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526388873420019e-05,
"loss": 3.8464,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525550278668967e-05,
"loss": 3.8537,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524711683917915e-05,
"loss": 3.8486,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523873089166863e-05,
"loss": 3.8431,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523034494415811e-05,
"loss": 3.8562,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522195899664759e-05,
"loss": 3.8518,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521357304913707e-05,
"loss": 3.8498,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520520348043028e-05,
"loss": 3.846,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519681753291976e-05,
"loss": 3.8498,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518843158540924e-05,
"loss": 3.8459,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5180062016702454e-05,
"loss": 3.8521,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171676069191934e-05,
"loss": 3.8383,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163290121681414e-05,
"loss": 3.8598,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.5154904174170894e-05,
"loss": 3.8541,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146518226660373e-05,
"loss": 3.8501,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513814865795358e-05,
"loss": 3.8403,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512976271044306e-05,
"loss": 3.8465,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512137676293254e-05,
"loss": 3.8521,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511299081542202e-05,
"loss": 3.8521,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.51046048679115e-05,
"loss": 3.8413,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509623529920471e-05,
"loss": 3.8531,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508784935169419e-05,
"loss": 3.8483,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507946340418368e-05,
"loss": 3.8571,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507107745667316e-05,
"loss": 3.8442,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506269150916263e-05,
"loss": 3.8548,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505430556165211e-05,
"loss": 3.8489,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504591961414159e-05,
"loss": 3.8395,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503753366663107e-05,
"loss": 3.8449,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502916409792428e-05,
"loss": 3.8539,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502077815041376e-05,
"loss": 3.8453,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501239220290324e-05,
"loss": 3.8324,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500400625539272e-05,
"loss": 3.8466,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.9174954891204834,
"eval_runtime": 308.9088,
"eval_samples_per_second": 1235.287,
"eval_steps_per_second": 38.604,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.49956203078822e-05,
"loss": 3.8323,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498723436037168e-05,
"loss": 3.8296,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497884841286116e-05,
"loss": 3.8513,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497046246535065e-05,
"loss": 3.85,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4962092896643856e-05,
"loss": 3.8475,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953706949133336e-05,
"loss": 3.8353,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945321001622816e-05,
"loss": 3.8411,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936935054112296e-05,
"loss": 3.8226,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928549106601776e-05,
"loss": 3.8467,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4920163159091256e-05,
"loss": 3.8443,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911793590384465e-05,
"loss": 3.836,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903407642873945e-05,
"loss": 3.8453,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.4895021695363425e-05,
"loss": 3.829,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.4886635747852905e-05,
"loss": 3.8318,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4878249800342385e-05,
"loss": 3.827,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.48698802316356e-05,
"loss": 3.8261,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486149428412508e-05,
"loss": 3.8303,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485310833661456e-05,
"loss": 3.8302,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484472238910404e-05,
"loss": 3.8329,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483633644159352e-05,
"loss": 3.8484,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.4827950494082993e-05,
"loss": 3.8342,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481956454657247e-05,
"loss": 3.8395,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481119497786569e-05,
"loss": 3.8327,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480280903035516e-05,
"loss": 3.8359,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479442308284464e-05,
"loss": 3.8257,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478603713533412e-05,
"loss": 3.8351,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.47776511878236e-05,
"loss": 3.8298,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476926524031308e-05,
"loss": 3.822,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476087929280256e-05,
"loss": 3.8199,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475249334529205e-05,
"loss": 3.8266,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474412377658526e-05,
"loss": 3.8267,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473575420787847e-05,
"loss": 3.8351,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472736826036795e-05,
"loss": 3.8305,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471898231285743e-05,
"loss": 3.8314,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471059636534691e-05,
"loss": 3.8209,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.4702226796640116e-05,
"loss": 3.8374,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693840849129596e-05,
"loss": 3.8185,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.4685454901619076e-05,
"loss": 3.8258,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4677068954108556e-05,
"loss": 3.8069,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668683006598036e-05,
"loss": 3.8248,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660297059087516e-05,
"loss": 3.8197,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465192749038073e-05,
"loss": 3.8328,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464354154287021e-05,
"loss": 3.8193,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463515559535969e-05,
"loss": 3.8242,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462676964784917e-05,
"loss": 3.8273,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461838370033865e-05,
"loss": 3.8289,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.461001413163186e-05,
"loss": 3.8254,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460162818412134e-05,
"loss": 3.8119,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459324223661082e-05,
"loss": 3.8039,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.45848562891003e-05,
"loss": 3.8282,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457647034158978e-05,
"loss": 3.8241,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456810077288299e-05,
"loss": 3.8199,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455971482537247e-05,
"loss": 3.8152,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551328877861956e-05,
"loss": 3.817,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542942930351436e-05,
"loss": 3.7981,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534556982840916e-05,
"loss": 3.816,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4526187414134125e-05,
"loss": 3.8053,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.4517801466623605e-05,
"loss": 3.8141,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.4509415519113085e-05,
"loss": 3.8222,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.4501029571602565e-05,
"loss": 3.8114,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.4492643624092045e-05,
"loss": 3.8025,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.4484257676581525e-05,
"loss": 3.8171,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.4475871729071e-05,
"loss": 3.7977,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446748578156048e-05,
"loss": 3.8049,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445913259165742e-05,
"loss": 3.8152,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445074664414691e-05,
"loss": 3.81,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444236069663639e-05,
"loss": 3.8007,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443397474912587e-05,
"loss": 3.8035,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442560518041908e-05,
"loss": 3.8025,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441721923290856e-05,
"loss": 3.8112,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440883328539804e-05,
"loss": 3.8123,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440044733788752e-05,
"loss": 3.8086,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.4392061390377e-05,
"loss": 3.8165,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438369182167021e-05,
"loss": 3.8189,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437530587415969e-05,
"loss": 3.8051,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436691992664917e-05,
"loss": 3.8016,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435853397913865e-05,
"loss": 3.8199,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.4350164410431864e-05,
"loss": 3.8104,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.4341778462921344e-05,
"loss": 3.8021,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333392515410824e-05,
"loss": 3.8059,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.43250065679003e-05,
"loss": 3.8114,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431662062038978e-05,
"loss": 3.819,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4308234672879257e-05,
"loss": 3.7997,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429986510417247e-05,
"loss": 3.7896,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291479156661946e-05,
"loss": 3.7991,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4283093209151426e-05,
"loss": 3.7962,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274707261640906e-05,
"loss": 3.8081,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426633769293412e-05,
"loss": 3.8052,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.42579517454236e-05,
"loss": 3.7914,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424956579791308e-05,
"loss": 3.8091,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424117985040256e-05,
"loss": 3.8001,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423279390289204e-05,
"loss": 3.803,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422442433418525e-05,
"loss": 3.799,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421603838667473e-05,
"loss": 3.8033,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420765243916421e-05,
"loss": 3.8167,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419926649165369e-05,
"loss": 3.8023,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.41908969229469e-05,
"loss": 3.7832,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418251097543638e-05,
"loss": 3.8041,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417412502792586e-05,
"loss": 3.7981,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416573908041534e-05,
"loss": 3.806,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157369511708555e-05,
"loss": 3.81,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.4148983564198035e-05,
"loss": 3.797,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.4140597616687515e-05,
"loss": 3.79,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4132211669176995e-05,
"loss": 3.8024,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123842100470204e-05,
"loss": 3.7836,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115456152959684e-05,
"loss": 3.7996,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4107070205449164e-05,
"loss": 3.7945,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098684257938644e-05,
"loss": 3.8018,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.4090298310428124e-05,
"loss": 3.7863,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408192874172133e-05,
"loss": 3.8032,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407354279421081e-05,
"loss": 3.7876,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406515684670029e-05,
"loss": 3.7906,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405677089918977e-05,
"loss": 3.8049,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404838495167925e-05,
"loss": 3.7953,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.403999900416873e-05,
"loss": 3.8097,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403162943546195e-05,
"loss": 3.8018,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402324348795143e-05,
"loss": 3.7942,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401485754044091e-05,
"loss": 3.7976,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400647159293039e-05,
"loss": 3.7928,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399808564541987e-05,
"loss": 3.7959,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398971607671308e-05,
"loss": 3.7861,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398133012920256e-05,
"loss": 3.8015,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397294418169204e-05,
"loss": 3.7932,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396455823418152e-05,
"loss": 3.7912,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3956188665474726e-05,
"loss": 3.7884,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.3947802717964206e-05,
"loss": 3.798,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939416770453686e-05,
"loss": 3.7902,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393103082294317e-05,
"loss": 3.7958,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392264487543265e-05,
"loss": 3.785,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391427530672586e-05,
"loss": 3.8035,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390588935921534e-05,
"loss": 3.7954,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389750341170482e-05,
"loss": 3.7951,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.38891174641943e-05,
"loss": 3.7878,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388074789548751e-05,
"loss": 3.7878,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387236194797699e-05,
"loss": 3.8012,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386397600046647e-05,
"loss": 3.7937,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385559005295595e-05,
"loss": 3.7842,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384722048424916e-05,
"loss": 3.7978,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383883453673864e-05,
"loss": 3.792,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383044858922813e-05,
"loss": 3.8061,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382206264171761e-05,
"loss": 3.7905,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381367669420708e-05,
"loss": 3.7991,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3805307125500296e-05,
"loss": 3.7924,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796921177989776e-05,
"loss": 3.7847,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788535230479256e-05,
"loss": 3.7934,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378014928296873e-05,
"loss": 3.7953,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377176333545821e-05,
"loss": 3.7944,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763393766751425e-05,
"loss": 3.7781,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.37550078192409e-05,
"loss": 3.7925,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.892263650894165,
"eval_runtime": 306.9131,
"eval_samples_per_second": 1243.319,
"eval_steps_per_second": 38.855,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.374662187173038e-05,
"loss": 3.7853,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.3738235924219865e-05,
"loss": 3.7756,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.3729849976709345e-05,
"loss": 3.7981,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.3721480408002554e-05,
"loss": 3.7979,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.3713094460492034e-05,
"loss": 3.7927,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.3704708512981514e-05,
"loss": 3.7831,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.3696322565470993e-05,
"loss": 3.7858,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.3687936617960473e-05,
"loss": 3.771,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367956704925368e-05,
"loss": 3.7909,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367118110174316e-05,
"loss": 3.7923,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366279515423264e-05,
"loss": 3.7821,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.365440920672212e-05,
"loss": 3.7907,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.364603963801533e-05,
"loss": 3.7751,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.363765369050482e-05,
"loss": 3.7815,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.36292677429943e-05,
"loss": 3.7731,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.362088179548378e-05,
"loss": 3.7759,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.361251222677699e-05,
"loss": 3.775,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.360412627926647e-05,
"loss": 3.7784,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.359574033175595e-05,
"loss": 3.7814,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.358735438424543e-05,
"loss": 3.7926,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.3578984815538636e-05,
"loss": 3.7865,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.3570598868028116e-05,
"loss": 3.7871,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.3562212920517596e-05,
"loss": 3.7815,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.3553826973007076e-05,
"loss": 3.7844,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.3545441025496556e-05,
"loss": 3.7713,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.353707145678977e-05,
"loss": 3.7863,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.352868550927925e-05,
"loss": 3.7769,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.352029956176873e-05,
"loss": 3.7682,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.351192999306194e-05,
"loss": 3.7718,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.350354404555142e-05,
"loss": 3.7718,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.34951580980409e-05,
"loss": 3.778,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.348677215053038e-05,
"loss": 3.7806,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.347838620301986e-05,
"loss": 3.7827,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.347001663431307e-05,
"loss": 3.782,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.346163068680255e-05,
"loss": 3.7717,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345324473929203e-05,
"loss": 3.7835,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344485879178151e-05,
"loss": 3.7726,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.3436489223074726e-05,
"loss": 3.7691,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.3428103275564206e-05,
"loss": 3.7631,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.3419717328053685e-05,
"loss": 3.7709,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.3411331380543165e-05,
"loss": 3.7737,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.3402961811836375e-05,
"loss": 3.7792,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.3394575864325854e-05,
"loss": 3.7715,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.3386189916815334e-05,
"loss": 3.7721,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.3377803969304814e-05,
"loss": 3.779,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.3369418021794294e-05,
"loss": 3.7776,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.3361048453087503e-05,
"loss": 3.7788,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.3352662505576983e-05,
"loss": 3.763,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334427655806646e-05,
"loss": 3.7508,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.333589061055594e-05,
"loss": 3.7817,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.332752104184916e-05,
"loss": 3.776,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.331913509433864e-05,
"loss": 3.7727,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331074914682812e-05,
"loss": 3.7692,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.33023631993176e-05,
"loss": 3.7616,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.329399363061081e-05,
"loss": 3.7538,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328560768310029e-05,
"loss": 3.7648,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.327722173558977e-05,
"loss": 3.7555,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326883578807925e-05,
"loss": 3.7649,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326044984056873e-05,
"loss": 3.7735,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.325208027186194e-05,
"loss": 3.761,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.324369432435142e-05,
"loss": 3.7535,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.32353083768409e-05,
"loss": 3.7718,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322692242933038e-05,
"loss": 3.7519,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.321853648181986e-05,
"loss": 3.7531,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.321016691311307e-05,
"loss": 3.7687,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.320178096560255e-05,
"loss": 3.7652,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.319339501809203e-05,
"loss": 3.7529,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.3185009070581506e-05,
"loss": 3.755,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.317663950187472e-05,
"loss": 3.7548,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.31682535543642e-05,
"loss": 3.7605,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.315986760685368e-05,
"loss": 3.7672,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.3151481659343155e-05,
"loss": 3.7582,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.3143095711832635e-05,
"loss": 3.7679,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313472614312585e-05,
"loss": 3.7695,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.312634019561533e-05,
"loss": 3.7662,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311795424810481e-05,
"loss": 3.7513,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310956830059429e-05,
"loss": 3.7701,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.3101198731887506e-05,
"loss": 3.7659,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.309281278437698e-05,
"loss": 3.7506,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308442683686646e-05,
"loss": 3.7656,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.307604088935594e-05,
"loss": 3.7604,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.306765494184542e-05,
"loss": 3.7716,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.305928537313863e-05,
"loss": 3.7552,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.305089942562811e-05,
"loss": 3.7394,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.304251347811759e-05,
"loss": 3.7549,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.3034143909410804e-05,
"loss": 3.752,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.3025757961900284e-05,
"loss": 3.7579,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.3017372014389764e-05,
"loss": 3.7569,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.3008986066879244e-05,
"loss": 3.7493,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.3000600119368724e-05,
"loss": 3.7588,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.299223055066193e-05,
"loss": 3.7566,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.298384460315141e-05,
"loss": 3.7495,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.297545865564089e-05,
"loss": 3.7558,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.296707270813037e-05,
"loss": 3.7606,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.295870313942358e-05,
"loss": 3.7695,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.295031719191306e-05,
"loss": 3.7536,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294193124440254e-05,
"loss": 3.741,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293354529689202e-05,
"loss": 3.758,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.292517572818524e-05,
"loss": 3.7541,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.291678978067472e-05,
"loss": 3.7607,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.29084038331642e-05,
"loss": 3.7645,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.290001788565368e-05,
"loss": 3.7447,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289164831694689e-05,
"loss": 3.7459,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288326236943637e-05,
"loss": 3.7599,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.287487642192585e-05,
"loss": 3.7402,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286649047441533e-05,
"loss": 3.7574,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.2858120905708536e-05,
"loss": 3.743,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.2849734958198016e-05,
"loss": 3.7606,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.2841349010687496e-05,
"loss": 3.743,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.2832963063176976e-05,
"loss": 3.7566,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.282459349447019e-05,
"loss": 3.7485,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281620754695967e-05,
"loss": 3.7418,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.280782159944915e-05,
"loss": 3.7583,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.279943565193863e-05,
"loss": 3.7477,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.279104970442811e-05,
"loss": 3.7634,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.278268013572132e-05,
"loss": 3.7613,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.27742941882108e-05,
"loss": 3.7478,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276590824070028e-05,
"loss": 3.7563,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.275752229318976e-05,
"loss": 3.747,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.274915272448297e-05,
"loss": 3.7486,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.274076677697245e-05,
"loss": 3.7474,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273238082946193e-05,
"loss": 3.7542,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.272399488195141e-05,
"loss": 3.7474,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.2715625313244625e-05,
"loss": 3.7455,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.2707239365734105e-05,
"loss": 3.7503,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.2698853418223585e-05,
"loss": 3.7512,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.2690467470713065e-05,
"loss": 3.7446,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.2682081523202545e-05,
"loss": 3.7518,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.2673711954495754e-05,
"loss": 3.7397,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.2665326006985234e-05,
"loss": 3.765,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.2656940059474714e-05,
"loss": 3.7454,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.2648554111964194e-05,
"loss": 3.7559,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.26401845432574e-05,
"loss": 3.7428,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.263179859574688e-05,
"loss": 3.7478,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.262341264823636e-05,
"loss": 3.7571,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.261502670072584e-05,
"loss": 3.7479,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.260665713201906e-05,
"loss": 3.7433,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.259827118450854e-05,
"loss": 3.7562,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.258988523699802e-05,
"loss": 3.7492,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.25814992894875e-05,
"loss": 3.7601,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.257312972078071e-05,
"loss": 3.7435,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256474377327019e-05,
"loss": 3.7544,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255635782575967e-05,
"loss": 3.7495,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254797187824915e-05,
"loss": 3.7447,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253960230954236e-05,
"loss": 3.7494,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253121636203184e-05,
"loss": 3.7504,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252283041452132e-05,
"loss": 3.7575,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.25144444670108e-05,
"loss": 3.728,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250607489830401e-05,
"loss": 3.7547,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 3.8758106231689453,
"eval_runtime": 306.086,
"eval_samples_per_second": 1246.679,
"eval_steps_per_second": 38.96,
"step": 457920
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.187466835543245e+17,
"trial_name": null,
"trial_params": null
}