abhinavp's picture
Training in progress, epoch 0, checkpoint
87c8ccd verified
raw history blame
No virus
56.1 kB
{
"best_metric": 3.961202383041382,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/transformer/4/checkpoints/checkpoint-228960",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 228960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 11.0021,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8322,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.2089,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9977,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8315,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7266,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6137,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5416,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4641,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4047,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3631,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3173,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2716,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 5.2186,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 5.1948,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 5.1472,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1231,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0978,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0645,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0348,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0195,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9879,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9705,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9455,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9378,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.9039,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8893,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8609,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8559,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8306,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 4.8227,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.813,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7958,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.7863,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 4.7715,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7567,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7541,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7236,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7143,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6927,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6956,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6799,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6817,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.661,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6555,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.65,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6449,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6324,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6142,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 4.6051,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.6232,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.6141,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5911,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5789,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5871,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5626,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5747,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5429,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5658,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.549,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5287,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5233,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.534,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4946,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.5095,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5155,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.5014,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4933,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4757,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4755,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.472,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4865,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4634,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.474,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4681,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4675,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4497,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4475,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.444,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4412,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4318,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4261,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4272,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.4262,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.4049,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.4137,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.4128,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.4128,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3974,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3968,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3878,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3828,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3841,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 4.3874,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.3791,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3883,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3787,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.361,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3605,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3702,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3666,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3651,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.3532,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3443,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3571,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3348,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3404,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3354,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.3343,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.3249,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.3262,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.3201,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.3269,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3217,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3121,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3238,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.3301,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.316,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.3032,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.3016,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.2991,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.3049,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.3011,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2897,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2993,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2898,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2889,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2834,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2855,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2788,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.288,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2854,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.2842,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.2617,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.2775,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.2715,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2761,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.2636,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2728,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2619,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2793,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.249,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.2662,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.2512,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2479,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.2504,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2386,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.2424,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.2488,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.2396,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.205402851104736,
"eval_runtime": 302.2482,
"eval_samples_per_second": 1262.509,
"eval_steps_per_second": 39.454,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.2324,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.2284,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.2426,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.2329,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.2409,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.22,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2222,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.2103,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.2209,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.2185,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.2146,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.2183,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.1972,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.2125,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.197,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.1975,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.2034,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.1958,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.1979,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.213,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.188,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856651071861674e-05,
"loss": 4.1929,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558124771106226e-05,
"loss": 4.1916,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.1969,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.1906,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.1887,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.1757,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.1824,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.1696,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.1799,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.1753,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.1783,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.1815,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.1704,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.1753,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.1716,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.1611,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.1549,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.147,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.1548,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.153,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.1635,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.1494,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.1493,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.1528,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.1484,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.1487,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.8348574356165606e-05,
"loss": 4.1347,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.1331,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.1565,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.1541,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.1367,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.1368,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.1413,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.1242,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.1424,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.1169,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.1443,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.1396,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824797574364683e-05,
"loss": 4.1207,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823958979613631e-05,
"loss": 4.1167,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823120384862579e-05,
"loss": 4.1344,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822281790111527e-05,
"loss": 4.1,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821443195360475e-05,
"loss": 4.1173,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.1279,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819766005858371e-05,
"loss": 4.1215,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189274111073184e-05,
"loss": 4.1126,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818092092117013e-05,
"loss": 4.1014,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817253497365961e-05,
"loss": 4.1068,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816414902614909e-05,
"loss": 4.1081,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815576307863857e-05,
"loss": 4.1168,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.1066,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.115,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.1185,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122235667400224e-05,
"loss": 4.115,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.101,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.1077,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097094203672393e-05,
"loss": 4.1073,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.8088708256161873e-05,
"loss": 4.1023,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.1028,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.097,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806356679243404e-05,
"loss": 4.1033,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805518084492352e-05,
"loss": 4.0998,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046794897413e-05,
"loss": 4.0842,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803840894990248e-05,
"loss": 4.0923,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.80300393811957e-05,
"loss": 4.0941,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802165343368518e-05,
"loss": 4.1003,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.0889,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800488153866413e-05,
"loss": 4.086,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799651196995735e-05,
"loss": 4.0844,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798812602244683e-05,
"loss": 4.0781,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.79797400749363e-05,
"loss": 4.0813,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.0901,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7962984558718996e-05,
"loss": 4.0861,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954598611208476e-05,
"loss": 4.0958,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946212663697956e-05,
"loss": 4.0858,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937826716187436e-05,
"loss": 4.0751,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792945714748065e-05,
"loss": 4.0745,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792107119997013e-05,
"loss": 4.0826,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912685252459605e-05,
"loss": 4.0864,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904299304949085e-05,
"loss": 4.0861,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.78959297362423e-05,
"loss": 4.0773,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887543788731774e-05,
"loss": 4.0677,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879157841221254e-05,
"loss": 4.086,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870771893710734e-05,
"loss": 4.0628,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786240232500395e-05,
"loss": 4.0731,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785401637749343e-05,
"loss": 4.0711,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784563042998291e-05,
"loss": 4.0691,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783724448247239e-05,
"loss": 4.0598,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828874913765606e-05,
"loss": 4.0688,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782048896625508e-05,
"loss": 4.0594,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781210301874456e-05,
"loss": 4.0688,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780371707123404e-05,
"loss": 4.0635,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779534750252725e-05,
"loss": 4.0558,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778696155501673e-05,
"loss": 4.0766,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777857560750621e-05,
"loss": 4.0772,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770206038799423e-05,
"loss": 4.0675,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761820091288903e-05,
"loss": 4.0579,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.7753434143778383e-05,
"loss": 4.0524,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774504819626786e-05,
"loss": 4.0584,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773666224875734e-05,
"loss": 4.0559,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772827630124682e-05,
"loss": 4.0651,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.77198903537363e-05,
"loss": 4.0461,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771150440622578e-05,
"loss": 4.0559,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770313483751899e-05,
"loss": 4.0586,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769474889000847e-05,
"loss": 4.0581,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768636294249795e-05,
"loss": 4.0451,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767797699498743e-05,
"loss": 4.053,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766960742628064e-05,
"loss": 4.0514,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766122147877012e-05,
"loss": 4.0542,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.76528355312596e-05,
"loss": 4.058,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764444958374909e-05,
"loss": 4.0565,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.76360800150423e-05,
"loss": 4.0368,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762769406753178e-05,
"loss": 4.051,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761930812002126e-05,
"loss": 4.0526,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761092217251074e-05,
"loss": 4.0494,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602552603803946e-05,
"loss": 4.0454,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594166656293426e-05,
"loss": 4.0511,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.7585780708782906e-05,
"loss": 4.0456,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577394761272386e-05,
"loss": 4.0609,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569025192565595e-05,
"loss": 4.0356,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560639245055075e-05,
"loss": 4.0501,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552253297544555e-05,
"loss": 4.0409,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543867350034035e-05,
"loss": 4.0349,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753549778132725e-05,
"loss": 4.0418,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752711183381673e-05,
"loss": 4.0326,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751872588630621e-05,
"loss": 4.0335,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751033993879569e-05,
"loss": 4.0357,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750195399128517e-05,
"loss": 4.0324,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.034352779388428,
"eval_runtime": 302.1567,
"eval_samples_per_second": 1262.891,
"eval_steps_per_second": 39.466,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749356804377465e-05,
"loss": 4.0286,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748518209626413e-05,
"loss": 4.0231,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747679614875361e-05,
"loss": 4.0407,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468410201243084e-05,
"loss": 4.0303,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460024253732563e-05,
"loss": 4.0463,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451638306222043e-05,
"loss": 4.0213,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744325235871152e-05,
"loss": 4.0274,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434866411201e-05,
"loss": 4.0121,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742649684249422e-05,
"loss": 4.0295,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.74181108949837e-05,
"loss": 4.0244,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740972494747318e-05,
"loss": 4.0198,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740133899996266e-05,
"loss": 4.0317,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739295305245214e-05,
"loss": 4.0076,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738456710494162e-05,
"loss": 4.0242,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.73761811574311e-05,
"loss": 4.0071,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736779520992058e-05,
"loss": 4.01,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735942564121379e-05,
"loss": 4.0106,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735103969370327e-05,
"loss": 4.0194,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734265374619275e-05,
"loss": 4.0109,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733426779868223e-05,
"loss": 4.0318,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325898229975444e-05,
"loss": 4.0098,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317512282464924e-05,
"loss": 4.0137,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7309126334954404e-05,
"loss": 4.0109,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300740387443884e-05,
"loss": 4.0195,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729237081873709e-05,
"loss": 4.0086,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728398487122657e-05,
"loss": 4.0136,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727559892371605e-05,
"loss": 4.0028,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726721297620553e-05,
"loss": 4.0067,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725884340749874e-05,
"loss": 3.9938,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725045745998822e-05,
"loss": 4.0092,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.72420715124777e-05,
"loss": 4.0065,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723368556496718e-05,
"loss": 4.0076,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.72253159962604e-05,
"loss": 4.0136,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721693004874988e-05,
"loss": 4.0018,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720854410123936e-05,
"loss": 3.9994,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720015815372884e-05,
"loss": 4.007,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191788585022046e-05,
"loss": 3.9991,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183402637511526e-05,
"loss": 3.9889,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175016690001006e-05,
"loss": 3.9814,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166630742490486e-05,
"loss": 3.9897,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158261173783695e-05,
"loss": 3.9918,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149875226273175e-05,
"loss": 3.9991,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141489278762655e-05,
"loss": 3.9934,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133103331252135e-05,
"loss": 3.9826,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712473376254535e-05,
"loss": 3.997,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711634781503483e-05,
"loss": 3.9898,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710796186752431e-05,
"loss": 3.9865,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709957592001379e-05,
"loss": 3.9797,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091206351307e-05,
"loss": 3.9741,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708282040379648e-05,
"loss": 4.0005,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707443445628596e-05,
"loss": 3.9971,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706604850877544e-05,
"loss": 3.9826,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705767894006865e-05,
"loss": 3.9823,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704930937136186e-05,
"loss": 3.9911,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704092342385134e-05,
"loss": 3.9684,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703253747634082e-05,
"loss": 3.9894,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024151528830305e-05,
"loss": 3.9684,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015765581319785e-05,
"loss": 3.9887,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007379633809265e-05,
"loss": 3.9947,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998993686298745e-05,
"loss": 3.9747,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990624117591954e-05,
"loss": 3.9653,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982238170081434e-05,
"loss": 3.9869,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973852222570914e-05,
"loss": 3.9578,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965466275060394e-05,
"loss": 3.9714,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69570967063536e-05,
"loss": 3.9798,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694871075884308e-05,
"loss": 3.9792,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694032481133256e-05,
"loss": 3.9716,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693193886382204e-05,
"loss": 3.9576,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692356929511526e-05,
"loss": 3.9612,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691518334760474e-05,
"loss": 3.9644,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690679740009422e-05,
"loss": 3.9755,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689841145258369e-05,
"loss": 3.9638,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689004188387691e-05,
"loss": 3.9758,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688165593636639e-05,
"loss": 3.9772,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687326998885587e-05,
"loss": 3.9766,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686488404134534e-05,
"loss": 3.9605,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856514472638556e-05,
"loss": 3.9698,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848128525128036e-05,
"loss": 3.973,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683974257761751e-05,
"loss": 3.9625,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831356630106996e-05,
"loss": 3.9665,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822987061400205e-05,
"loss": 3.9644,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681460111388969e-05,
"loss": 3.9622,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806215166379165e-05,
"loss": 3.9669,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797829218868645e-05,
"loss": 3.9485,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678945965016186e-05,
"loss": 3.9605,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678107370265134e-05,
"loss": 3.9588,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772687755140814e-05,
"loss": 3.9662,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764301807630294e-05,
"loss": 3.9569,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9549,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674754629141298e-05,
"loss": 3.9548,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673916034390246e-05,
"loss": 3.9493,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673079077519568e-05,
"loss": 3.9467,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672240482768516e-05,
"loss": 3.9569,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671401888017464e-05,
"loss": 3.9674,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670563293266412e-05,
"loss": 3.9633,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.66972469851536e-05,
"loss": 3.9546,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668886103764308e-05,
"loss": 3.9485,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668047509013256e-05,
"loss": 3.9502,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667208914262204e-05,
"loss": 3.9523,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666371957391525e-05,
"loss": 3.9599,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665533362640473e-05,
"loss": 3.9587,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664694767889421e-05,
"loss": 3.9512,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663856173138369e-05,
"loss": 3.9427,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663017578387317e-05,
"loss": 3.9631,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662178983636265e-05,
"loss": 3.9399,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661340388885213e-05,
"loss": 3.951,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660503432014534e-05,
"loss": 3.9429,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659664837263482e-05,
"loss": 3.9472,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.65882624251243e-05,
"loss": 3.9371,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657987647761378e-05,
"loss": 3.9481,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657149053010326e-05,
"loss": 3.9401,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656310458259274e-05,
"loss": 3.9411,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655473501388595e-05,
"loss": 3.9507,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654634906637543e-05,
"loss": 3.9335,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653796311886491e-05,
"loss": 3.9572,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652957717135439e-05,
"loss": 3.9556,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.65212076026476e-05,
"loss": 3.9481,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651282165513708e-05,
"loss": 3.9392,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650443570762657e-05,
"loss": 3.9359,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649604976011605e-05,
"loss": 3.9391,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648768019140926e-05,
"loss": 3.9381,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647929424389874e-05,
"loss": 3.9453,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647090829638822e-05,
"loss": 3.9282,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.64625223488777e-05,
"loss": 3.9405,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645413640136718e-05,
"loss": 3.9443,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644575045385665e-05,
"loss": 3.9426,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643736450634613e-05,
"loss": 3.9308,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428994937639346e-05,
"loss": 3.9364,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642060899012882e-05,
"loss": 3.9383,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412223042618306e-05,
"loss": 3.9402,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403837095107786e-05,
"loss": 3.9401,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395451147597266e-05,
"loss": 3.9456,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387065200086746e-05,
"loss": 3.9227,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378679252576226e-05,
"loss": 3.938,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370309683869435e-05,
"loss": 3.9415,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6361923736358915e-05,
"loss": 3.935,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353537788848395e-05,
"loss": 3.9334,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345151841337874e-05,
"loss": 3.943,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336782272631084e-05,
"loss": 3.935,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328396325120564e-05,
"loss": 3.9494,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320010377610043e-05,
"loss": 3.9258,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311624430099523e-05,
"loss": 3.9347,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630325486139274e-05,
"loss": 3.9342,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629486891388222e-05,
"loss": 3.9267,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628649934517543e-05,
"loss": 3.9313,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627811339766491e-05,
"loss": 3.926,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626972745015439e-05,
"loss": 3.9223,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626134150264387e-05,
"loss": 3.9272,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625295555513335e-05,
"loss": 3.9268,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.961202383041382,
"eval_runtime": 302.9755,
"eval_samples_per_second": 1259.478,
"eval_steps_per_second": 39.36,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.563515463083858e+17,
"trial_name": null,
"trial_params": null
}