abhinavp's picture
Training in progress, epoch 0, checkpoint
08b062f verified
{
"best_metric": 3.951378107070923,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/transformer/1/checkpoints/checkpoint-228960",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 228960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.9442,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8159,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1825,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9707,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8071,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7081,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5931,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5266,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4395,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3928,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3424,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3031,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2534,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2032,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1676,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1263,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.0976,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0754,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0474,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0163,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0041,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9666,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9505,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9255,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9149,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8877,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.868,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8473,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8306,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8159,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7985,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7944,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7736,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.7668,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7599,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7426,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969820416244367e-05,
"loss": 4.7332,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7059,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7025,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6833,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.683,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6713,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6618,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6407,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.652,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6377,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.631,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6229,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 4.5922,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 4.5904,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.5977,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.5871,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5702,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5507,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5534,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5408,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.567,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.525,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5374,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5326,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5087,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5133,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 4.5017,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 4.4855,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 4.485,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5051,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.4823,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 4.4708,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 4.4625,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.464,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4755,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4733,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4607,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4662,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4659,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4519,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4405,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4304,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4308,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4242,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4181,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4202,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4205,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.4165,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.3917,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.3912,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.4003,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.4041,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3836,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3861,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3913,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.376,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.3708,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3744,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3661,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3728,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3604,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3474,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3544,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3565,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.35,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3492,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.3441,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.341,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.34,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3174,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3196,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3271,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.323,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.3137,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.3104,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.3079,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.3122,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3059,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3073,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3015,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.3073,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.3013,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901080214863699e-05,
"loss": 4.2978,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.3002,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.2978,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.2876,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.2935,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.281,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2909,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2679,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2787,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.2645,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2691,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.254,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.2842,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.272,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2579,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2597,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.2622,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.2675,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2645,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2512,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2596,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2461,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2582,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.2432,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.245,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.2438,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2345,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.2405,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2353,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.235,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.2367,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.2283,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.194109916687012,
"eval_runtime": 367.2307,
"eval_samples_per_second": 1039.104,
"eval_steps_per_second": 32.473,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.2116,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873416415361222e-05,
"loss": 4.2104,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.2294,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.213,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.2306,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.2022,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2096,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.1932,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.2088,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.2033,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.2083,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.203,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.1892,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.1912,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.1859,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.1815,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.1882,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.1843,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.1804,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.1994,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.1726,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.1829,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.1785,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.1884,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.1634,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.1707,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.165,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.1697,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.1546,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.1581,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.1658,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.1614,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.1617,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.1652,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.1595,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.1591,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.147,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.1529,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.1399,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.1465,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840725960993552e-05,
"loss": 4.1473,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398873662425e-05,
"loss": 4.1452,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839048771491447e-05,
"loss": 4.1357,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838210176740395e-05,
"loss": 4.1441,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.1474,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365346251186646e-05,
"loss": 4.1401,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8356960303676126e-05,
"loss": 4.1424,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.8348574356165606e-05,
"loss": 4.1138,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834020478745882e-05,
"loss": 4.1202,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331818839948295e-05,
"loss": 4.1387,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323432892437775e-05,
"loss": 4.1304,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315046944927255e-05,
"loss": 4.126,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830667737622047e-05,
"loss": 4.1089,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298291428709944e-05,
"loss": 4.1144,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289905481199424e-05,
"loss": 4.1075,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281519533688904e-05,
"loss": 4.132,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273133586178384e-05,
"loss": 4.1058,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.82647640174716e-05,
"loss": 4.1194,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825637806996108e-05,
"loss": 4.1235,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824799212245056e-05,
"loss": 4.103,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823960617494004e-05,
"loss": 4.1104,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823123660623325e-05,
"loss": 4.1026,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822285065872273e-05,
"loss": 4.0981,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821446471121221e-05,
"loss": 4.0991,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820607876370169e-05,
"loss": 4.1143,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.81977091949949e-05,
"loss": 4.1051,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818932324748438e-05,
"loss": 4.0947,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818093729997386e-05,
"loss": 4.0934,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817255135246334e-05,
"loss": 4.0944,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164181783756554e-05,
"loss": 4.1095,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155795836246034e-05,
"loss": 4.1114,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147409888735514e-05,
"loss": 4.1042,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139023941224994e-05,
"loss": 4.1135,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130637993714474e-05,
"loss": 4.1096,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122252046203954e-05,
"loss": 4.106,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811388247749716e-05,
"loss": 4.0945,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810549652998664e-05,
"loss": 4.0927,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809711058247612e-05,
"loss": 4.0939,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887246349656e-05,
"loss": 4.0904,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808035506625881e-05,
"loss": 4.0852,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807196911874829e-05,
"loss": 4.0935,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806358317123777e-05,
"loss": 4.0998,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805519722372726e-05,
"loss": 4.0913,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804681127621674e-05,
"loss": 4.0773,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803844170750995e-05,
"loss": 4.0759,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803005575999943e-05,
"loss": 4.0839,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802166981248891e-05,
"loss": 4.0918,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801328386497839e-05,
"loss": 4.0746,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004914296271596e-05,
"loss": 4.0783,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996528348761076e-05,
"loss": 4.0856,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988142401250556e-05,
"loss": 4.0764,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979756453740036e-05,
"loss": 4.0704,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971386885033245e-05,
"loss": 4.0742,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7963000937522725e-05,
"loss": 4.077,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795461499001221e-05,
"loss": 4.0771,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794622904250169e-05,
"loss": 4.0763,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.79378594737949e-05,
"loss": 4.0616,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792947352628438e-05,
"loss": 4.0725,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792108757877386e-05,
"loss": 4.069,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791270163126334e-05,
"loss": 4.0762,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790433206255655e-05,
"loss": 4.0706,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789594611504603e-05,
"loss": 4.07,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788756016753551e-05,
"loss": 4.0659,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787917422002499e-05,
"loss": 4.069,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.78708046513182e-05,
"loss": 4.0482,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786241870380768e-05,
"loss": 4.0528,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854049135100895e-05,
"loss": 4.0618,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845663187590375e-05,
"loss": 4.0581,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837277240079855e-05,
"loss": 4.0517,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828891292569335e-05,
"loss": 4.0497,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820505345058815e-05,
"loss": 4.0479,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812119397548295e-05,
"loss": 4.0566,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803733450037775e-05,
"loss": 4.0503,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795363881330984e-05,
"loss": 4.0519,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786977933820464e-05,
"loss": 4.0551,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778591986309944e-05,
"loss": 4.0582,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770206038799423e-05,
"loss": 4.052,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776183647009263e-05,
"loss": 4.0491,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775345052258212e-05,
"loss": 4.056,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450645750716e-05,
"loss": 4.0548,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773667862756108e-05,
"loss": 4.0451,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772829268005055e-05,
"loss": 4.053,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771992311134377e-05,
"loss": 4.0428,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771153716383325e-05,
"loss": 4.0548,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770315121632272e-05,
"loss": 4.029,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.76947652688122e-05,
"loss": 4.0461,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.0306,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76780097525949e-05,
"loss": 4.0343,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766962380508437e-05,
"loss": 4.0255,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766123785757386e-05,
"loss": 4.0551,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765286828886707e-05,
"loss": 4.044,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764448234135655e-05,
"loss": 4.0366,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.7636096393846026e-05,
"loss": 4.0315,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.7627710446335506e-05,
"loss": 4.0402,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761934087762872e-05,
"loss": 4.0456,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610954930118195e-05,
"loss": 4.042,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602568982607675e-05,
"loss": 4.0352,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594183035097155e-05,
"loss": 4.039,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758581346639037e-05,
"loss": 4.0305,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577427518879844e-05,
"loss": 4.0457,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569041571369324e-05,
"loss": 4.0272,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756065562385881e-05,
"loss": 4.0304,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755228605515202e-05,
"loss": 4.0294,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.75439001076415e-05,
"loss": 4.0232,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535530538934716e-05,
"loss": 4.0342,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527144591424196e-05,
"loss": 4.0256,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751875864391367e-05,
"loss": 4.0302,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751037269640315e-05,
"loss": 4.0269,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750198674889263e-05,
"loss": 4.0243,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.026165962219238,
"eval_runtime": 354.9808,
"eval_samples_per_second": 1074.962,
"eval_steps_per_second": 33.593,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749360080138211e-05,
"loss": 4.0097,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748521485387159e-05,
"loss": 4.0084,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747682890636107e-05,
"loss": 4.0273,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746844295885055e-05,
"loss": 4.0119,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.746005701134003e-05,
"loss": 4.0362,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745167106382951e-05,
"loss": 4.0045,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744328511631899e-05,
"loss": 4.0167,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434899168808475e-05,
"loss": 3.9997,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426513221297955e-05,
"loss": 4.0174,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418127273787435e-05,
"loss": 4.0109,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740974132627691e-05,
"loss": 4.0149,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401371757570124e-05,
"loss": 4.0112,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739301856766706e-05,
"loss": 4.0004,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738463262015654e-05,
"loss": 4.0064,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737624667264602e-05,
"loss": 4.0007,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.73678607251355e-05,
"loss": 3.9969,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735947477762498e-05,
"loss": 3.998,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735108883011446e-05,
"loss": 4.0028,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734270288260394e-05,
"loss": 3.9958,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733431693509343e-05,
"loss": 4.0181,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732594736638664e-05,
"loss": 3.9939,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731756141887612e-05,
"loss": 4.0035,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73091754713656e-05,
"loss": 3.9996,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730078952385508e-05,
"loss": 4.0097,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729240357634456e-05,
"loss": 3.988,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728401762883403e-05,
"loss": 3.999,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727563168132351e-05,
"loss": 3.9922,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726726211261673e-05,
"loss": 3.9942,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725887616510621e-05,
"loss": 3.9809,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250506596399416e-05,
"loss": 3.9863,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7242120648888896e-05,
"loss": 3.9952,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723373470137838e-05,
"loss": 3.9948,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225348753867856e-05,
"loss": 3.9947,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216962806357336e-05,
"loss": 3.996,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208576858846816e-05,
"loss": 3.9907,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200190911336296e-05,
"loss": 3.994,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191804963825775e-05,
"loss": 3.9811,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183435395118985e-05,
"loss": 3.9929,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175049447608465e-05,
"loss": 3.9755,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.7166663500097945e-05,
"loss": 3.9836,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158277552587424e-05,
"loss": 3.9808,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714992436268437e-05,
"loss": 3.9876,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714153841517385e-05,
"loss": 3.9812,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713315246766333e-05,
"loss": 3.9789,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712476652015281e-05,
"loss": 3.9888,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711638057264229e-05,
"loss": 3.9837,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710799462513177e-05,
"loss": 3.9824,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709962505642498e-05,
"loss": 3.9643,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709123910891446e-05,
"loss": 3.9616,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708285316140394e-05,
"loss": 3.9782,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707446721389342e-05,
"loss": 3.9764,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706609764518663e-05,
"loss": 3.9733,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705771169767611e-05,
"loss": 3.9569,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704932575016559e-05,
"loss": 3.9623,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040939802655074e-05,
"loss": 3.9606,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032553855144554e-05,
"loss": 3.9739,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024167907634034e-05,
"loss": 3.9578,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015781960123514e-05,
"loss": 3.9719,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007396012612994e-05,
"loss": 3.9704,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.69990264439062e-05,
"loss": 3.9571,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699065687519941e-05,
"loss": 3.9626,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698227092768889e-05,
"loss": 3.9589,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697388498017837e-05,
"loss": 3.9502,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696549903266785e-05,
"loss": 3.9581,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695711308515733e-05,
"loss": 3.9629,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694872713764681e-05,
"loss": 3.9682,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694034119013629e-05,
"loss": 3.9456,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693197162142951e-05,
"loss": 3.9514,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692358567391899e-05,
"loss": 3.9491,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691519972640847e-05,
"loss": 3.9749,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690681377889795e-05,
"loss": 3.9631,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689842783138743e-05,
"loss": 3.9635,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689004188387691e-05,
"loss": 3.9764,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688165593636639e-05,
"loss": 3.9716,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687326998885587e-05,
"loss": 3.9664,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864900420149076e-05,
"loss": 3.9558,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856514472638556e-05,
"loss": 3.9581,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848128525128036e-05,
"loss": 3.957,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683974257761751e-05,
"loss": 3.9546,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831373008910725e-05,
"loss": 3.9535,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822987061400205e-05,
"loss": 3.9563,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681460111388969e-05,
"loss": 3.9649,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806215166379165e-05,
"loss": 3.9551,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679784559767238e-05,
"loss": 3.9475,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678945965016186e-05,
"loss": 3.94,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678107370265134e-05,
"loss": 3.953,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677270413394455e-05,
"loss": 3.9588,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676431818643403e-05,
"loss": 3.9468,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9445,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674754629141298e-05,
"loss": 3.9566,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673916034390246e-05,
"loss": 3.9369,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673079077519568e-05,
"loss": 3.9457,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672240482768516e-05,
"loss": 3.9444,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671401888017464e-05,
"loss": 3.9508,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670563293266412e-05,
"loss": 3.95,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.66972469851536e-05,
"loss": 3.945,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668886103764308e-05,
"loss": 3.9351,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668047509013256e-05,
"loss": 3.9477,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667208914262204e-05,
"loss": 3.9395,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666371957391525e-05,
"loss": 3.9531,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665535000520846e-05,
"loss": 3.9447,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664696405769794e-05,
"loss": 3.9465,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663857811018742e-05,
"loss": 3.936,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66301921626769e-05,
"loss": 3.9492,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662182259397011e-05,
"loss": 3.9226,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661343664645959e-05,
"loss": 3.9295,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660505069894907e-05,
"loss": 3.9373,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659666475143855e-05,
"loss": 3.9375,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658827880392803e-05,
"loss": 3.9263,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657990923522124e-05,
"loss": 3.9296,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657152328771072e-05,
"loss": 3.9262,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.65631373402002e-05,
"loss": 3.9374,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655475139268968e-05,
"loss": 3.93,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654636544517916e-05,
"loss": 3.9281,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653799587647237e-05,
"loss": 3.941,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652960992896185e-05,
"loss": 3.9405,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652122398145134e-05,
"loss": 3.938,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651283803394082e-05,
"loss": 3.9291,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.6504468465234026e-05,
"loss": 3.9389,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6496082517723506e-05,
"loss": 3.9335,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487696570212986e-05,
"loss": 3.9278,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479310622702466e-05,
"loss": 3.941,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470924675191946e-05,
"loss": 3.922,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462538727681426e-05,
"loss": 3.9374,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454152780170906e-05,
"loss": 3.9171,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445766832660386e-05,
"loss": 3.932,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437397263953595e-05,
"loss": 3.9146,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429027695246804e-05,
"loss": 3.9201,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642064174773629e-05,
"loss": 3.9137,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641225580022577e-05,
"loss": 3.9399,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640386985271525e-05,
"loss": 3.9297,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639548390520473e-05,
"loss": 3.9252,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638709795769421e-05,
"loss": 3.9192,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637872838898742e-05,
"loss": 3.9251,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.63703424414769e-05,
"loss": 3.9374,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636195649396638e-05,
"loss": 3.9257,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635357054645586e-05,
"loss": 3.9217,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634520097774907e-05,
"loss": 3.9321,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633681503023855e-05,
"loss": 3.9222,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632842908272803e-05,
"loss": 3.9308,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632004313521751e-05,
"loss": 3.918,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631165718770699e-05,
"loss": 3.9215,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303271240196475e-05,
"loss": 3.9202,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294901671489684e-05,
"loss": 3.9174,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286515723979164e-05,
"loss": 3.9208,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6278129776468644e-05,
"loss": 3.9231,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626974382895812e-05,
"loss": 3.9161,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.62613578814476e-05,
"loss": 3.9171,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625298831274081e-05,
"loss": 3.9173,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.951378107070923,
"eval_runtime": 304.2171,
"eval_samples_per_second": 1254.338,
"eval_steps_per_second": 39.199,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.5923255332787712e+17,
"trial_name": null,
"trial_params": null
}