abhinavp's picture
Training in progress, epoch 1, checkpoint
a825f23 verified
{
"best_metric": 3.9947001934051514,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/lstm/0/checkpoints/checkpoint-1679040",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 1679040,
"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": 10.8182,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.555,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.061,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9947,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9465,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.929,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7614,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6484,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5484,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4747,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.4091,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3454,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2704,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 6.203,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 6.1436,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 6.0788,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986585759743914e-05,
"loss": 6.0283,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985747164992862e-05,
"loss": 5.9861,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.98490857024181e-05,
"loss": 5.9469,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984069975490758e-05,
"loss": 5.9076,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983231380739706e-05,
"loss": 5.8715,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 5.829,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 5.8047,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.7666,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.745,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7159,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.6932,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6635,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6382,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.975684027980238e-05,
"loss": 5.6195,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.974845433229186e-05,
"loss": 5.5953,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.5887,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5587,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.5501,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714926921053515e-05,
"loss": 5.5406,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.52,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5063,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.9689785457325684e-05,
"loss": 5.4725,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.9681399509815164e-05,
"loss": 5.468,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4457,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 5.4408,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 5.4234,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 5.4148,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.3846,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 5.3958,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 5.3854,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 5.3759,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.3638,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959762192872862e-05,
"loss": 5.3371,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 5.3301,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 5.3326,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 5.3175,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 5.3069,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 5.2817,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 5.2819,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 5.2701,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 5.2957,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 5.2485,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 5.2529,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 5.2476,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 5.2275,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 5.2286,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 5.2126,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 5.1987,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 5.1974,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2144,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.1869,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1787,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1617,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 5.1635,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 5.1727,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1679,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.1546,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.1624,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1552,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371250482355776e-05,
"loss": 5.1435,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 5.124,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 5.1145,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346109018627945e-05,
"loss": 5.1123,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.1054,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 5.1007,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 5.0968,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.099,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 5.0907,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 5.0649,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 5.0602,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 5.0706,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 5.0711,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 5.0481,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925389635361968e-05,
"loss": 5.0507,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924551040610916e-05,
"loss": 5.0505,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.0368,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 5.0294,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 5.0291,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 5.0182,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.0223,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 5.0116,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 4.9974,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.9961,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 4.9958,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.9915,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.9916,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.9811,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.9778,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.9698,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9498,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9543,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9529,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.9491,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908624291862421e-05,
"loss": 4.9413,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907785697111369e-05,
"loss": 4.936,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906947102360317e-05,
"loss": 4.9287,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9295,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.9237,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.9239,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.916,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.9144,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.9161,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901080214863699e-05,
"loss": 4.9065,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.9127,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.9107,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.8952,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.8999,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.8849,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.889,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.8647,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.8766,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893534499984604e-05,
"loss": 4.8628,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8639,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8456,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.878,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.8645,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.8526,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.8494,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.846,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.854,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885990422985882e-05,
"loss": 4.8478,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515182823483e-05,
"loss": 4.8366,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.8424,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883474638732726e-05,
"loss": 4.8285,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882636043981674e-05,
"loss": 4.838,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881797449230622e-05,
"loss": 4.8203,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.8227,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.8204,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.8086,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.8114,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.8116,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876769156485057e-05,
"loss": 4.806,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.8099,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.7977,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.761485576629639,
"eval_runtime": 294.2132,
"eval_samples_per_second": 1296.988,
"eval_steps_per_second": 40.532,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.7878,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873416415361222e-05,
"loss": 4.783,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.7999,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.782,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.7984,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.769,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.7811,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.7585,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.7713,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.7688,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7729,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.7676,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.7497,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.7519,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.7467,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.7414,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.7514,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.7457,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.7424,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.7573,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.7315,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.7403,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.7348,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.7426,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.719,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.7273,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.7184,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.7268,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.7062,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.7104,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.7193,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.7102,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.7099,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.7162,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.709,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.7093,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.6903,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.7001,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.6835,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.6934,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.6902,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398873662425e-05,
"loss": 4.6873,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839048771491447e-05,
"loss": 4.6741,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838210176740395e-05,
"loss": 4.6899,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.6891,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.6807,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8356960303676126e-05,
"loss": 4.6873,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.6571,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834020478745882e-05,
"loss": 4.6598,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331818839948295e-05,
"loss": 4.6779,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323432892437775e-05,
"loss": 4.6659,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315046944927255e-05,
"loss": 4.6641,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306660997416735e-05,
"loss": 4.6444,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.6512,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.6467,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.6726,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273133586178384e-05,
"loss": 4.6412,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826474763866787e-05,
"loss": 4.6495,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.655,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824797574364683e-05,
"loss": 4.6354,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823958979613631e-05,
"loss": 4.643,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823120384862579e-05,
"loss": 4.6359,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822281790111527e-05,
"loss": 4.6264,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.631,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.6456,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.6334,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.6234,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.6214,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817251859485588e-05,
"loss": 4.6211,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816414902614909e-05,
"loss": 4.6378,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815576307863857e-05,
"loss": 4.6378,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.6278,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138991183617535e-05,
"loss": 4.6405,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813060523610701e-05,
"loss": 4.6375,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.6325,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811383334108597e-05,
"loss": 4.6174,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810544739357545e-05,
"loss": 4.6164,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809707782486866e-05,
"loss": 4.6128,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808869187735814e-05,
"loss": 4.6126,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808030592984762e-05,
"loss": 4.6087,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.6149,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806353403482658e-05,
"loss": 4.6206,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805514808731606e-05,
"loss": 4.6108,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804676213980554e-05,
"loss": 4.5963,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803837619229502e-05,
"loss": 4.5948,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.6015,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802162067607771e-05,
"loss": 4.6128,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801323472856719e-05,
"loss": 4.5931,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.80048651598604e-05,
"loss": 4.5998,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799647921234988e-05,
"loss": 4.6035,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798809326483936e-05,
"loss": 4.5946,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797970731732884e-05,
"loss": 4.589,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797133774862205e-05,
"loss": 4.5875,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796295180111153e-05,
"loss": 4.5891,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795456585360101e-05,
"loss": 4.5897,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794617990609049e-05,
"loss": 4.5912,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793779395857997e-05,
"loss": 4.5757,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792940801106946e-05,
"loss": 4.5822,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.5791,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.5864,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790426654734163e-05,
"loss": 4.5814,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895880599831107e-05,
"loss": 4.5804,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887494652320587e-05,
"loss": 4.5775,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879108704810067e-05,
"loss": 4.5747,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870722757299546e-05,
"loss": 4.5586,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786233680978902e-05,
"loss": 4.5619,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853983619885965e-05,
"loss": 4.5682,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845597672375445e-05,
"loss": 4.563,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.5601,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.5579,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782043982984389e-05,
"loss": 4.5532,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.78120702611371e-05,
"loss": 4.5573,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780368431362658e-05,
"loss": 4.5558,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779529836611606e-05,
"loss": 4.5541,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778691241860554e-05,
"loss": 4.5563,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777852647109502e-05,
"loss": 4.5563,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777014052358449e-05,
"loss": 4.5575,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776175457607397e-05,
"loss": 4.5515,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775336862856345e-05,
"loss": 4.5608,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774499905985666e-05,
"loss": 4.5602,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773661311234615e-05,
"loss": 4.5476,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772822716483563e-05,
"loss": 4.5576,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771984121732511e-05,
"loss": 4.544,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771147164861832e-05,
"loss": 4.5521,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.77030857011078e-05,
"loss": 4.5263,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769469975359728e-05,
"loss": 4.544,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768631380608676e-05,
"loss": 4.5275,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767792785857624e-05,
"loss": 4.5346,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766954191106572e-05,
"loss": 4.5197,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.76611559635552e-05,
"loss": 4.5531,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.543,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.7644416826141616e-05,
"loss": 4.5374,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.7636030878631096e-05,
"loss": 4.5288,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762764493112058e-05,
"loss": 4.5333,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761925898361006e-05,
"loss": 4.5411,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761087303609954e-05,
"loss": 4.5363,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760248708858902e-05,
"loss": 4.5296,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941011410785e-05,
"loss": 4.5322,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758571519356798e-05,
"loss": 4.5249,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757732924605746e-05,
"loss": 4.5374,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756895967735067e-05,
"loss": 4.5198,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756057372984015e-05,
"loss": 4.5234,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755218778232963e-05,
"loss": 4.5223,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754380183481911e-05,
"loss": 4.5155,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753541588730859e-05,
"loss": 4.5194,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752702993979807e-05,
"loss": 4.5187,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751866037109128e-05,
"loss": 4.5192,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751027442358077e-05,
"loss": 4.5175,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750188847607025e-05,
"loss": 4.5122,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.480395793914795,
"eval_runtime": 293.1861,
"eval_samples_per_second": 1301.532,
"eval_steps_per_second": 40.674,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749350252855973e-05,
"loss": 4.5036,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748511658104921e-05,
"loss": 4.4978,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747673063353868e-05,
"loss": 4.5172,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746834468602816e-05,
"loss": 4.5029,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745995873851764e-05,
"loss": 4.5231,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745157279100712e-05,
"loss": 4.4938,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.74431868434966e-05,
"loss": 4.506,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743480089598608e-05,
"loss": 4.4878,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742641494847556e-05,
"loss": 4.5046,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741802900096504e-05,
"loss": 4.5015,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740964305345452e-05,
"loss": 4.5054,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401257105944e-05,
"loss": 4.5033,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392887537237216e-05,
"loss": 4.4849,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384501589726696e-05,
"loss": 4.4943,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376115642216176e-05,
"loss": 4.4892,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367729694705656e-05,
"loss": 4.4865,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359360125998865e-05,
"loss": 4.4888,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350974178488345e-05,
"loss": 4.4906,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342588230977825e-05,
"loss": 4.4867,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.7334202283467305e-05,
"loss": 4.5055,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325816335956784e-05,
"loss": 4.481,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317430388446264e-05,
"loss": 4.4875,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730904444093574e-05,
"loss": 4.4869,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730065849342522e-05,
"loss": 4.4958,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292288924718433e-05,
"loss": 4.4746,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728390297720791e-05,
"loss": 4.4864,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727551702969739e-05,
"loss": 4.4762,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726713108218687e-05,
"loss": 4.4816,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725874513467635e-05,
"loss": 4.4683,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725035918716583e-05,
"loss": 4.4694,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724198961845904e-05,
"loss": 4.4787,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723360367094852e-05,
"loss": 4.4783,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225217723438e-05,
"loss": 4.4761,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721683177592748e-05,
"loss": 4.4807,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720846220722069e-05,
"loss": 4.4746,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720007625971017e-05,
"loss": 4.4802,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719169031219965e-05,
"loss": 4.4593,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718330436468914e-05,
"loss": 4.4754,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717493479598235e-05,
"loss": 4.4567,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716654884847183e-05,
"loss": 4.4672,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715816290096131e-05,
"loss": 4.4634,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714977695345079e-05,
"loss": 4.4673,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714139100594027e-05,
"loss": 4.4592,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713300505842975e-05,
"loss": 4.4624,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712461911091923e-05,
"loss": 4.4703,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116249542212436e-05,
"loss": 4.4636,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107863594701916e-05,
"loss": 4.466,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099477647191396e-05,
"loss": 4.4472,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091091699680876e-05,
"loss": 4.4398,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708272213097409e-05,
"loss": 4.4579,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707433618346357e-05,
"loss": 4.4519,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706595023595305e-05,
"loss": 4.4518,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705756428844253e-05,
"loss": 4.4352,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704917834093201e-05,
"loss": 4.4407,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704079239342149e-05,
"loss": 4.4413,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.70324228247147e-05,
"loss": 4.4558,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702405325600791e-05,
"loss": 4.4346,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701566730849739e-05,
"loss": 4.4438,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700728136098687e-05,
"loss": 4.4475,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699889541347635e-05,
"loss": 4.4346,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699050946596583e-05,
"loss": 4.4384,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698212351845531e-05,
"loss": 4.4336,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697373757094479e-05,
"loss": 4.4233,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965351623434276e-05,
"loss": 4.4364,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956965675923756e-05,
"loss": 4.4385,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694857972841323e-05,
"loss": 4.4423,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694019378090271e-05,
"loss": 4.4197,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693180783339219e-05,
"loss": 4.4264,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.69234382646854e-05,
"loss": 4.4247,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691505231717488e-05,
"loss": 4.4504,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690666636966436e-05,
"loss": 4.4361,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898296800957574e-05,
"loss": 4.436,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688991085344705e-05,
"loss": 4.449,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688152490593653e-05,
"loss": 4.4472,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873138958426014e-05,
"loss": 4.4406,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686476938971923e-05,
"loss": 4.4281,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.68563834422087e-05,
"loss": 4.4299,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684799749469818e-05,
"loss": 4.4262,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683961154718766e-05,
"loss": 4.4232,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683122559967714e-05,
"loss": 4.4246,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682285603097035e-05,
"loss": 4.4264,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681447008345983e-05,
"loss": 4.4347,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680608413594931e-05,
"loss": 4.4248,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679769818843879e-05,
"loss": 4.4159,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678931224092827e-05,
"loss": 4.4106,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678094267222148e-05,
"loss": 4.4204,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677255672471097e-05,
"loss": 4.4278,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676417077720045e-05,
"loss": 4.4185,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675578482968993e-05,
"loss": 4.4173,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747415260983136e-05,
"loss": 4.4263,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739029313472616e-05,
"loss": 4.4068,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730643365962096e-05,
"loss": 4.4164,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722257418451576e-05,
"loss": 4.4109,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713871470941056e-05,
"loss": 4.4182,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705485523430536e-05,
"loss": 4.4143,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697099575920016e-05,
"loss": 4.4116,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688713628409496e-05,
"loss": 4.4037,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680327680898976e-05,
"loss": 4.4126,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6671958112192185e-05,
"loss": 4.4019,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.66635885434854e-05,
"loss": 4.4189,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665520259597488e-05,
"loss": 4.4108,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664681664846436e-05,
"loss": 4.4093,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663843070095384e-05,
"loss": 4.4034,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663004475344332e-05,
"loss": 4.4121,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.66216588059328e-05,
"loss": 4.3872,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661327285842228e-05,
"loss": 4.3945,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660488691091176e-05,
"loss": 4.3991,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596500963401234e-05,
"loss": 4.3993,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588115015890714e-05,
"loss": 4.3917,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657974544718393e-05,
"loss": 4.3954,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657135949967341e-05,
"loss": 4.386,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656297355216288e-05,
"loss": 4.394,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.65546039834561e-05,
"loss": 4.3921,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546218035945586e-05,
"loss": 4.3883,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6537832088435065e-05,
"loss": 4.3993,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652944614092454e-05,
"loss": 4.3986,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652106019341402e-05,
"loss": 4.4006,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.65126742459035e-05,
"loss": 4.3893,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650428829839298e-05,
"loss": 4.3998,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649590235088246e-05,
"loss": 4.3968,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648753278217567e-05,
"loss": 4.3901,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647914683466515e-05,
"loss": 4.4049,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647076088715463e-05,
"loss": 4.3837,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646237493964411e-05,
"loss": 4.395,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645398899213359e-05,
"loss": 4.3754,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644560304462307e-05,
"loss": 4.3898,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437217097112554e-05,
"loss": 4.3706,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428831149602034e-05,
"loss": 4.3818,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642046158089524e-05,
"loss": 4.3707,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641207563338472e-05,
"loss": 4.3973,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640370606467793e-05,
"loss": 4.3887,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639532011716741e-05,
"loss": 4.3881,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638695054846062e-05,
"loss": 4.3774,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.63785646009501e-05,
"loss": 4.3801,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637017865343958e-05,
"loss": 4.3956,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636180908473279e-05,
"loss": 4.3829,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635342313722228e-05,
"loss": 4.3784,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634503718971176e-05,
"loss": 4.3882,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633665124220124e-05,
"loss": 4.3776,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632826529469072e-05,
"loss": 4.3853,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.63198793471802e-05,
"loss": 4.3722,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631149339966968e-05,
"loss": 4.3789,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630310745215916e-05,
"loss": 4.3746,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629472150464864e-05,
"loss": 4.3745,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628633555713812e-05,
"loss": 4.3704,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277949609627597e-05,
"loss": 4.3785,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626956366211707e-05,
"loss": 4.3688,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626117771460655e-05,
"loss": 4.3728,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625279176709603e-05,
"loss": 4.3702,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.345595836639404,
"eval_runtime": 311.3159,
"eval_samples_per_second": 1225.736,
"eval_steps_per_second": 38.305,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.6244422198389246e-05,
"loss": 4.3665,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623605262968246e-05,
"loss": 4.3566,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622766668217194e-05,
"loss": 4.3757,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621928073466142e-05,
"loss": 4.3601,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.6210894787150895e-05,
"loss": 4.3856,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202508839640374e-05,
"loss": 4.352,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194122892129854e-05,
"loss": 4.3651,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185736944619334e-05,
"loss": 4.3496,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177350997108814e-05,
"loss": 4.3659,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6168965049598294e-05,
"loss": 4.3666,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.6160579102087774e-05,
"loss": 4.3644,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.6152193154577254e-05,
"loss": 4.3671,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614382358587046e-05,
"loss": 4.3479,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613543763835994e-05,
"loss": 4.3586,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612705169084942e-05,
"loss": 4.3539,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611866574333891e-05,
"loss": 4.3524,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611029617463212e-05,
"loss": 4.3534,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.61019102271216e-05,
"loss": 4.3564,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609352427961108e-05,
"loss": 4.3549,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608513833210056e-05,
"loss": 4.3679,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607675238459004e-05,
"loss": 4.35,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606836643707952e-05,
"loss": 4.3555,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.605999686837273e-05,
"loss": 4.3552,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605161092086221e-05,
"loss": 4.3654,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604322497335169e-05,
"loss": 4.3444,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603483902584117e-05,
"loss": 4.3569,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602646945713438e-05,
"loss": 4.3449,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018083509623864e-05,
"loss": 4.348,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009697562113344e-05,
"loss": 4.3367,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001311614602824e-05,
"loss": 4.3468,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599294204589603e-05,
"loss": 4.3459,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598455609838551e-05,
"loss": 4.3524,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597617015087499e-05,
"loss": 4.3473,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596778420336447e-05,
"loss": 4.353,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595939825585395e-05,
"loss": 4.346,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595101230834343e-05,
"loss": 4.3521,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594265911844037e-05,
"loss": 4.3375,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593427317092985e-05,
"loss": 4.3476,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592588722341933e-05,
"loss": 4.3319,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591750127590882e-05,
"loss": 4.3425,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.5909131707202026e-05,
"loss": 4.3408,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900745759691506e-05,
"loss": 4.3438,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.5892359812180986e-05,
"loss": 4.3342,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5883973864670466e-05,
"loss": 4.341,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.5875587917159946e-05,
"loss": 4.3449,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867201969649426e-05,
"loss": 4.3407,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858816022138906e-05,
"loss": 4.3421,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585043007462838e-05,
"loss": 4.3323,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584204412711786e-05,
"loss": 4.3125,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.5833674558411075e-05,
"loss": 4.3381,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.5825288610900555e-05,
"loss": 4.3317,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.5816902663390035e-05,
"loss": 4.3276,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808516715879515e-05,
"loss": 4.3224,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800130768368995e-05,
"loss": 4.3204,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791744820858475e-05,
"loss": 4.317,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783375252151684e-05,
"loss": 4.3385,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5774989304641164e-05,
"loss": 4.3178,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766603357130644e-05,
"loss": 4.3247,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575823378842385e-05,
"loss": 4.3348,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.574984784091333e-05,
"loss": 4.3179,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574146189340281e-05,
"loss": 4.3188,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573307594589229e-05,
"loss": 4.3226,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572468999838177e-05,
"loss": 4.304,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571630405087125e-05,
"loss": 4.3215,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570791810336074e-05,
"loss": 4.3237,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569953215585022e-05,
"loss": 4.3237,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569116258714343e-05,
"loss": 4.3076,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568277663963291e-05,
"loss": 4.3151,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567439069212239e-05,
"loss": 4.3098,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566600474461187e-05,
"loss": 4.3309,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565763517590508e-05,
"loss": 4.3236,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564924922839456e-05,
"loss": 4.3249,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564086328088404e-05,
"loss": 4.334,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563247733337352e-05,
"loss": 4.3355,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624107764666726e-05,
"loss": 4.332,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615721817156206e-05,
"loss": 4.3118,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560733586964569e-05,
"loss": 4.3188,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559894992213517e-05,
"loss": 4.3206,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559056397462465e-05,
"loss": 4.3109,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558217802711413e-05,
"loss": 4.3188,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557380845840734e-05,
"loss": 4.3141,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556542251089682e-05,
"loss": 4.3229,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.55570365633863e-05,
"loss": 4.3184,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554865061587578e-05,
"loss": 4.2996,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554028104716899e-05,
"loss": 4.3052,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553189509965847e-05,
"loss": 4.3133,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552350915214795e-05,
"loss": 4.317,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551512320463743e-05,
"loss": 4.3096,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550673725712691e-05,
"loss": 4.3086,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549836768842013e-05,
"loss": 4.3164,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.548998174090961e-05,
"loss": 4.3023,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548159579339909e-05,
"loss": 4.3045,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547320984588857e-05,
"loss": 4.3062,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546482389837804e-05,
"loss": 4.3127,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545643795086752e-05,
"loss": 4.3115,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448052003357e-05,
"loss": 4.3039,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543966605584648e-05,
"loss": 4.2939,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543129648713969e-05,
"loss": 4.3101,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542291053962917e-05,
"loss": 4.2957,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.5414540970922385e-05,
"loss": 4.3168,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406155023411865e-05,
"loss": 4.3087,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5397769075901345e-05,
"loss": 4.3032,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389383128390824e-05,
"loss": 4.2987,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5380997180880304e-05,
"loss": 4.3094,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372627612173514e-05,
"loss": 4.2857,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364241664662994e-05,
"loss": 4.2965,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5355855717152473e-05,
"loss": 4.2914,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347469769641953e-05,
"loss": 4.2974,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533910020093516e-05,
"loss": 4.2899,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533071425342464e-05,
"loss": 4.2971,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532232830591412e-05,
"loss": 4.2895,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.53139423584036e-05,
"loss": 4.2857,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530557278969682e-05,
"loss": 4.2946,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.52971868421863e-05,
"loss": 4.2856,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.5288817273479514e-05,
"loss": 4.3024,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528043132596899e-05,
"loss": 4.2986,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527204537845847e-05,
"loss": 4.2997,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526365943094795e-05,
"loss": 4.2907,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525527348343743e-05,
"loss": 4.2996,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524688753592691e-05,
"loss": 4.3011,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.5238517967220116e-05,
"loss": 4.2909,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.5230132019709596e-05,
"loss": 4.3038,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.5221746072199076e-05,
"loss": 4.288,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.5213376503492285e-05,
"loss": 4.2953,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520499055598177e-05,
"loss": 4.2812,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519660460847125e-05,
"loss": 4.2923,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518821866096073e-05,
"loss": 4.2745,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517983271345021e-05,
"loss": 4.2859,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517144676593969e-05,
"loss": 4.2765,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516306081842917e-05,
"loss": 4.2952,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515467487091865e-05,
"loss": 4.2889,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514628892340813e-05,
"loss": 4.2937,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513790297589761e-05,
"loss": 4.2811,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512951702838709e-05,
"loss": 4.2883,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512113108087657e-05,
"loss": 4.2974,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.5112745133366045e-05,
"loss": 4.2888,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510439194346299e-05,
"loss": 4.2852,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509600599595247e-05,
"loss": 4.2943,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087620048441956e-05,
"loss": 4.2821,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079234100931436e-05,
"loss": 4.2935,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070848153420916e-05,
"loss": 4.2754,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062462205910396e-05,
"loss": 4.287,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.5054076258399876e-05,
"loss": 4.2803,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504569031088935e-05,
"loss": 4.2796,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503730436337883e-05,
"loss": 4.2827,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502891841586831e-05,
"loss": 4.2796,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502054884716152e-05,
"loss": 4.2786,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012162899651e-05,
"loss": 4.2795,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500377695214048e-05,
"loss": 4.2828,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.262184143066406,
"eval_runtime": 304.8532,
"eval_samples_per_second": 1251.72,
"eval_steps_per_second": 39.117,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499539100462996e-05,
"loss": 4.2711,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498700505711944e-05,
"loss": 4.2633,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978619109608925e-05,
"loss": 4.2846,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970233162098405e-05,
"loss": 4.27,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4961847214587885e-05,
"loss": 4.2908,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953461267077365e-05,
"loss": 4.2707,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945075319566845e-05,
"loss": 4.269,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936689372056325e-05,
"loss": 4.2596,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928303424545805e-05,
"loss": 4.2752,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4919933855839014e-05,
"loss": 4.2804,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911547908328494e-05,
"loss": 4.2731,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903161960817974e-05,
"loss": 4.2722,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489479239211118e-05,
"loss": 4.2626,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488640644460066e-05,
"loss": 4.2703,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487802049709014e-05,
"loss": 4.2676,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486963454957962e-05,
"loss": 4.2596,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.48612486020691e-05,
"loss": 4.2676,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485286265455859e-05,
"loss": 4.2717,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484447670704806e-05,
"loss": 4.2651,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483609075953754e-05,
"loss": 4.2775,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482770481202702e-05,
"loss": 4.269,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.48193188645165e-05,
"loss": 4.2701,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481093291700598e-05,
"loss": 4.2683,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480254696949546e-05,
"loss": 4.2792,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479416102198494e-05,
"loss": 4.2579,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478577507447442e-05,
"loss": 4.2675,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477740550576763e-05,
"loss": 4.2641,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476901955825711e-05,
"loss": 4.2593,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476063361074659e-05,
"loss": 4.2532,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475224766323607e-05,
"loss": 4.2592,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474386171572556e-05,
"loss": 4.2667,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473547576821504e-05,
"loss": 4.2661,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472708982070452e-05,
"loss": 4.2659,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471872025199773e-05,
"loss": 4.2652,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471033430448721e-05,
"loss": 4.263,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470194835697669e-05,
"loss": 4.2677,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469356240946617e-05,
"loss": 4.2589,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468517646195565e-05,
"loss": 4.2607,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4676806893248856e-05,
"loss": 4.2526,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668420945738336e-05,
"loss": 4.2592,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660034998227816e-05,
"loss": 4.2566,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651649050717296e-05,
"loss": 4.2621,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.4643263103206776e-05,
"loss": 4.2546,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4634877155696256e-05,
"loss": 4.2588,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626491208185736e-05,
"loss": 4.2661,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618105260675215e-05,
"loss": 4.2565,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4609735691968425e-05,
"loss": 4.2581,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460136612326164e-05,
"loss": 4.2502,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459298017575112e-05,
"loss": 4.2318,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584594228240594e-05,
"loss": 4.2607,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576208280730074e-05,
"loss": 4.251,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4567822333219554e-05,
"loss": 4.2482,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559436385709033e-05,
"loss": 4.2365,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551050438198513e-05,
"loss": 4.2449,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454266449068799e-05,
"loss": 4.2356,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453429492198121e-05,
"loss": 4.2583,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452590897447069e-05,
"loss": 4.2404,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451752302696017e-05,
"loss": 4.2438,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450913707944965e-05,
"loss": 4.2551,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450075113193913e-05,
"loss": 4.2383,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449238156323234e-05,
"loss": 4.24,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448399561572182e-05,
"loss": 4.2466,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.44756096682113e-05,
"loss": 4.2249,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446722372070078e-05,
"loss": 4.2444,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445883777319026e-05,
"loss": 4.2412,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445045182567974e-05,
"loss": 4.249,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444208225697295e-05,
"loss": 4.2311,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443369630946243e-05,
"loss": 4.2383,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.4425310361951914e-05,
"loss": 4.2288,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.4416924414441394e-05,
"loss": 4.2541,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.44085548457346e-05,
"loss": 4.2464,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440016889822408e-05,
"loss": 4.2451,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439178295071356e-05,
"loss": 4.2594,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438339700320304e-05,
"loss": 4.2543,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437501105569252e-05,
"loss": 4.2637,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436664148698573e-05,
"loss": 4.2368,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435825553947521e-05,
"loss": 4.2421,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.434986959196469e-05,
"loss": 4.245,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434148364445417e-05,
"loss": 4.2327,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433311407574738e-05,
"loss": 4.2446,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432472812823687e-05,
"loss": 4.2387,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431634218072635e-05,
"loss": 4.246,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430795623321583e-05,
"loss": 4.2427,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429957028570531e-05,
"loss": 4.2284,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429118433819479e-05,
"loss": 4.2398,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4282814769487996e-05,
"loss": 4.2296,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274428821977476e-05,
"loss": 4.2452,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266042874466956e-05,
"loss": 4.238,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425765692695643e-05,
"loss": 4.233,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424927097944591e-05,
"loss": 4.2423,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424088503193539e-05,
"loss": 4.2344,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232531842032334e-05,
"loss": 4.2274,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422414589452182e-05,
"loss": 4.2324,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.42157599470113e-05,
"loss": 4.2428,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420737399950078e-05,
"loss": 4.238,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419898805199026e-05,
"loss": 4.2342,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190602104479734e-05,
"loss": 4.2212,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182216156969214e-05,
"loss": 4.2358,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4173830209458694e-05,
"loss": 4.2264,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.4165444261948174e-05,
"loss": 4.2421,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157058314437654e-05,
"loss": 4.2406,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.4148672366927134e-05,
"loss": 4.2321,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.4140286419416614e-05,
"loss": 4.2272,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413191685070982e-05,
"loss": 4.2426,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412354728200304e-05,
"loss": 4.2118,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411516133449252e-05,
"loss": 4.2265,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106775386982e-05,
"loss": 4.2177,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409838943947148e-05,
"loss": 4.2331,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409000349196096e-05,
"loss": 4.2147,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408161754445044e-05,
"loss": 4.2242,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407324797574365e-05,
"loss": 4.2194,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406486202823313e-05,
"loss": 4.2169,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405647608072261e-05,
"loss": 4.2223,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404809013321209e-05,
"loss": 4.2194,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.403970418570157e-05,
"loss": 4.2322,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403131823819105e-05,
"loss": 4.2299,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.4022948669484257e-05,
"loss": 4.2281,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401456272197374e-05,
"loss": 4.2207,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400617677446322e-05,
"loss": 4.2309,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.39977908269527e-05,
"loss": 4.2289,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398940487944218e-05,
"loss": 4.2209,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398101893193166e-05,
"loss": 4.2373,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397264936322487e-05,
"loss": 4.2203,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396426341571435e-05,
"loss": 4.2248,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395587746820383e-05,
"loss": 4.2142,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394750789949704e-05,
"loss": 4.2247,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393912195198652e-05,
"loss": 4.2099,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3930736004476e-05,
"loss": 4.2159,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392235005696548e-05,
"loss": 4.2133,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391396410945496e-05,
"loss": 4.2282,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390557816194444e-05,
"loss": 4.2206,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389719221443392e-05,
"loss": 4.225,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.38888062669234e-05,
"loss": 4.2121,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388042031941288e-05,
"loss": 4.2246,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387203437190236e-05,
"loss": 4.2327,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386364842439184e-05,
"loss": 4.2213,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385526247688132e-05,
"loss": 4.2187,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384689290817453e-05,
"loss": 4.2268,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383850696066401e-05,
"loss": 4.2153,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383012101315349e-05,
"loss": 4.2259,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382173506564297e-05,
"loss": 4.2111,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381336549693618e-05,
"loss": 4.2205,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380497954942566e-05,
"loss": 4.2128,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796593601915145e-05,
"loss": 4.2153,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788207654404625e-05,
"loss": 4.2164,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3779821706894105e-05,
"loss": 4.214,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771435759383585e-05,
"loss": 4.2167,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763049811873065e-05,
"loss": 4.2095,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3754680243166274e-05,
"loss": 4.2219,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.205575466156006,
"eval_runtime": 295.4756,
"eval_samples_per_second": 1291.447,
"eval_steps_per_second": 40.359,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.3746294295655754e-05,
"loss": 4.2119,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.3737908348145234e-05,
"loss": 4.1986,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.3729522400634714e-05,
"loss": 4.2211,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.3721136453124194e-05,
"loss": 4.2086,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.3712750505613674e-05,
"loss": 4.2241,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.370438093690688e-05,
"loss": 4.2101,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.369599498939636e-05,
"loss": 4.1993,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368760904188584e-05,
"loss": 4.2044,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367923947317906e-05,
"loss": 4.2057,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367085352566854e-05,
"loss": 4.2166,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366246757815802e-05,
"loss": 4.2089,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.36540816306475e-05,
"loss": 4.2103,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.364571206194071e-05,
"loss": 4.2024,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.363732611443019e-05,
"loss": 4.2012,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.362894016691967e-05,
"loss": 4.208,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.362055421940915e-05,
"loss": 4.1976,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.361216827189863e-05,
"loss": 4.2032,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.36037823243881e-05,
"loss": 4.2086,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.359539637687758e-05,
"loss": 4.2066,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.358701042936707e-05,
"loss": 4.212,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.3578640860660284e-05,
"loss": 4.2079,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.357025491314976e-05,
"loss": 4.2085,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.356186896563924e-05,
"loss": 4.2071,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.355348301812872e-05,
"loss": 4.2135,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.3545113449421926e-05,
"loss": 4.1967,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.3536727501911406e-05,
"loss": 4.2112,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.3528341554400886e-05,
"loss": 4.1968,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.3519955606890366e-05,
"loss": 4.1978,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.3511586038183575e-05,
"loss": 4.1932,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.3503200090673055e-05,
"loss": 4.1979,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.3494814143162535e-05,
"loss": 4.203,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.348642819565202e-05,
"loss": 4.2033,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.34780422481415e-05,
"loss": 4.2081,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.346965630063098e-05,
"loss": 4.209,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.346127035312046e-05,
"loss": 4.1985,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345288440560994e-05,
"loss": 4.206,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344451483690315e-05,
"loss": 4.2003,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.343614526819636e-05,
"loss": 4.1995,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.342775932068584e-05,
"loss": 4.1945,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.341937337317532e-05,
"loss": 4.1949,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.34109874256648e-05,
"loss": 4.202,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.340261785695801e-05,
"loss": 4.2054,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.339423190944749e-05,
"loss": 4.1927,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.3385845961936975e-05,
"loss": 4.1984,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.3377460014426455e-05,
"loss": 4.2048,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.3369074066915935e-05,
"loss": 4.1995,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.3360704498209144e-05,
"loss": 4.2006,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.3352318550698624e-05,
"loss": 4.1933,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.3343932603188104e-05,
"loss": 4.1688,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.3335546655677584e-05,
"loss": 4.2057,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.3327160708167064e-05,
"loss": 4.1923,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.331879113946027e-05,
"loss": 4.1925,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331040519194975e-05,
"loss": 4.1833,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.330201924443923e-05,
"loss": 4.1784,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.329363329692871e-05,
"loss": 4.1817,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328526372822193e-05,
"loss": 4.1948,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.327687778071141e-05,
"loss": 4.1833,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326849183320089e-05,
"loss": 4.1886,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326010588569037e-05,
"loss": 4.1945,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.325173631698358e-05,
"loss": 4.1825,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.324335036947306e-05,
"loss": 4.1829,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.323496442196254e-05,
"loss": 4.1918,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322657847445202e-05,
"loss": 4.1706,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.32181925269415e-05,
"loss": 4.1822,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.320980657943098e-05,
"loss": 4.1833,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.320142063192046e-05,
"loss": 4.1946,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.319303468440994e-05,
"loss": 4.1706,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.3184665115703146e-05,
"loss": 4.1832,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.3176279168192626e-05,
"loss": 4.1709,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.3167893220682106e-05,
"loss": 4.1955,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.3159507273171586e-05,
"loss": 4.1906,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.31511377044648e-05,
"loss": 4.1888,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.314275175695428e-05,
"loss": 4.1994,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313436580944376e-05,
"loss": 4.2005,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.3125979861933235e-05,
"loss": 4.2073,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311762667203018e-05,
"loss": 4.1824,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310924072451966e-05,
"loss": 4.187,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310085477700914e-05,
"loss": 4.186,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.309246882949862e-05,
"loss": 4.1745,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308409926079183e-05,
"loss": 4.1912,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.3075713313281316e-05,
"loss": 4.1826,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.3067327365770796e-05,
"loss": 4.1914,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.3058941418260276e-05,
"loss": 4.1881,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.3050555470749756e-05,
"loss": 4.1732,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.3042169523239236e-05,
"loss": 4.1842,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.303378357572871e-05,
"loss": 4.1739,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.3025414007021925e-05,
"loss": 4.1897,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.3017028059511405e-05,
"loss": 4.1868,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.3008658490804614e-05,
"loss": 4.1738,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.3000272543294094e-05,
"loss": 4.1913,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.2991886595783574e-05,
"loss": 4.1794,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.2983500648273054e-05,
"loss": 4.1746,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.2975114700762534e-05,
"loss": 4.1779,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.2966728753252014e-05,
"loss": 4.1874,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.2958342805741494e-05,
"loss": 4.1824,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.2949956858230974e-05,
"loss": 4.186,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294158728952418e-05,
"loss": 4.1675,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293320134201366e-05,
"loss": 4.1802,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.292481539450314e-05,
"loss": 4.1738,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.291642944699262e-05,
"loss": 4.1873,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.29080434994821e-05,
"loss": 4.1887,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.289965755197158e-05,
"loss": 4.1755,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289127160446106e-05,
"loss": 4.1791,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288288565695054e-05,
"loss": 4.1853,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.287453246704749e-05,
"loss": 4.1604,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286614651953697e-05,
"loss": 4.1718,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.285776057202645e-05,
"loss": 4.1643,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.284937462451593e-05,
"loss": 4.1771,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284098867700541e-05,
"loss": 4.1666,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.283260272949489e-05,
"loss": 4.1749,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.282421678198437e-05,
"loss": 4.1659,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281583083447385e-05,
"loss": 4.1659,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.2807461265767056e-05,
"loss": 4.1722,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.2799075318256536e-05,
"loss": 4.1648,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.2790705749549745e-05,
"loss": 4.1809,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.2782319802039225e-05,
"loss": 4.1759,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.2773933854528705e-05,
"loss": 4.1778,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276554790701819e-05,
"loss": 4.1679,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.27571783383114e-05,
"loss": 4.177,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.274879239080088e-05,
"loss": 4.1798,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.274040644329036e-05,
"loss": 4.1679,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273202049577984e-05,
"loss": 4.1877,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.272363454826932e-05,
"loss": 4.1649,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.27152486007588e-05,
"loss": 4.175,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.270686265324828e-05,
"loss": 4.16,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.269847670573776e-05,
"loss": 4.1762,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.269010713703097e-05,
"loss": 4.158,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.268173756832418e-05,
"loss": 4.1671,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.2673367999617395e-05,
"loss": 4.1582,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.2664982052106875e-05,
"loss": 4.1819,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.2656596104596355e-05,
"loss": 4.1669,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.2648226535889564e-05,
"loss": 4.174,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.2639840588379044e-05,
"loss": 4.1617,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.2631454640868524e-05,
"loss": 4.175,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.2623068693358004e-05,
"loss": 4.1793,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.2614682745847484e-05,
"loss": 4.1723,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.2606296798336964e-05,
"loss": 4.1726,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.2597910850826443e-05,
"loss": 4.1723,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.2589524903315923e-05,
"loss": 4.1674,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.2581138955805403e-05,
"loss": 4.1783,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.257275300829488e-05,
"loss": 4.1611,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256436706078436e-05,
"loss": 4.1703,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255598111327384e-05,
"loss": 4.1659,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254759516576332e-05,
"loss": 4.1659,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253922559705654e-05,
"loss": 4.166,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253083964954602e-05,
"loss": 4.1596,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252245370203549e-05,
"loss": 4.1745,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251406775452497e-05,
"loss": 4.155,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250568180701445e-05,
"loss": 4.1741,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 4.163763046264648,
"eval_runtime": 289.5615,
"eval_samples_per_second": 1317.824,
"eval_steps_per_second": 41.183,
"step": 457920
},
{
"epoch": 0.0,
"learning_rate": 4.249729585950393e-05,
"loss": 4.1635,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.248890991199341e-05,
"loss": 4.1493,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.248052396448289e-05,
"loss": 4.1697,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.247213801697237e-05,
"loss": 4.1625,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.246375206946185e-05,
"loss": 4.1728,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.245536612195133e-05,
"loss": 4.1616,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.244698017444081e-05,
"loss": 4.152,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.243859422693029e-05,
"loss": 4.1524,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.243020827941978e-05,
"loss": 4.1599,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.242182233190926e-05,
"loss": 4.1684,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.241343638439873e-05,
"loss": 4.1619,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.240505043688821e-05,
"loss": 4.158,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239668086818143e-05,
"loss": 4.1607,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238829492067091e-05,
"loss": 4.1534,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.237990897316038e-05,
"loss": 4.1578,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237152302564986e-05,
"loss": 4.1451,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.236313707813934e-05,
"loss": 4.1575,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.235475113062882e-05,
"loss": 4.1575,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.23463651831183e-05,
"loss": 4.1579,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.233797923560778e-05,
"loss": 4.1654,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.232959328809726e-05,
"loss": 4.1664,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.2321223719390476e-05,
"loss": 4.1574,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.2312837771879956e-05,
"loss": 4.1569,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.2304451824369436e-05,
"loss": 4.1688,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.2296065876858916e-05,
"loss": 4.145,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.2287679929348396e-05,
"loss": 4.1691,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.2279293981837876e-05,
"loss": 4.1492,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.2270908034327356e-05,
"loss": 4.1483,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.2262538465620565e-05,
"loss": 4.147,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.2254152518110045e-05,
"loss": 4.1541,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.2245766570599525e-05,
"loss": 4.1536,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.2237380623089005e-05,
"loss": 4.1597,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.2228994675578485e-05,
"loss": 4.159,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.2220608728067965e-05,
"loss": 4.162,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.2212222780557445e-05,
"loss": 4.1495,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.2203836833046925e-05,
"loss": 4.1624,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.219548364314387e-05,
"loss": 4.1579,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.218709769563335e-05,
"loss": 4.1479,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.217871174812283e-05,
"loss": 4.1476,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.217032580061231e-05,
"loss": 4.1523,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.216193985310179e-05,
"loss": 4.1512,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.215355390559126e-05,
"loss": 4.1602,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.214516795808074e-05,
"loss": 4.1457,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.213679838937396e-05,
"loss": 4.1516,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.212842882066717e-05,
"loss": 4.1606,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.212004287315665e-05,
"loss": 4.1498,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.2111656925646134e-05,
"loss": 4.1581,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.2103270978135614e-05,
"loss": 4.1473,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.2094885030625094e-05,
"loss": 4.1171,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.20865154619183e-05,
"loss": 4.1638,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.207812951440778e-05,
"loss": 4.1459,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.206974356689726e-05,
"loss": 4.1492,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.2061357619386736e-05,
"loss": 4.1394,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.2052971671876216e-05,
"loss": 4.1285,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.2044585724365696e-05,
"loss": 4.1399,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.203621615565891e-05,
"loss": 4.1461,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.2027830208148385e-05,
"loss": 4.1404,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.201944426063787e-05,
"loss": 4.1408,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.201105831312735e-05,
"loss": 4.1535,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.200267236561683e-05,
"loss": 4.1359,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.199428641810631e-05,
"loss": 4.134,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.198590047059579e-05,
"loss": 4.1493,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.197751452308527e-05,
"loss": 4.1232,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.196914495437848e-05,
"loss": 4.1384,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196075900686796e-05,
"loss": 4.1394,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195237305935744e-05,
"loss": 4.1528,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.194398711184692e-05,
"loss": 4.1254,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.19356011643364e-05,
"loss": 4.1425,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.192721521682588e-05,
"loss": 4.1245,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.191884564811909e-05,
"loss": 4.1525,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.191045970060857e-05,
"loss": 4.1491,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.1902073753098057e-05,
"loss": 4.1453,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.1893687805587537e-05,
"loss": 4.1513,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.1885301858077017e-05,
"loss": 4.1554,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.1876932289370226e-05,
"loss": 4.1646,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.1868562720663435e-05,
"loss": 4.1392,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.1860176773152915e-05,
"loss": 4.1448,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.1851790825642395e-05,
"loss": 4.1461,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.1843404878131875e-05,
"loss": 4.1298,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.1835018930621355e-05,
"loss": 4.145,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.1826632983110834e-05,
"loss": 4.1416,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.1818247035600314e-05,
"loss": 4.1467,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.1809861088089794e-05,
"loss": 4.1538,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.1801475140579274e-05,
"loss": 4.1308,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.1793089193068754e-05,
"loss": 4.135,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.1784703245558234e-05,
"loss": 4.1347,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.1776317298047714e-05,
"loss": 4.1475,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.176794772934093e-05,
"loss": 4.1407,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.17595617818304e-05,
"loss": 4.1375,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.175119221312362e-05,
"loss": 4.1356,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.17428062656131e-05,
"loss": 4.1438,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.173442031810257e-05,
"loss": 4.1338,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.172603437059205e-05,
"loss": 4.136,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.171764842308153e-05,
"loss": 4.15,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.170926247557101e-05,
"loss": 4.1373,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.170087652806049e-05,
"loss": 4.1408,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.169249058054998e-05,
"loss": 4.125,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.168412101184319e-05,
"loss": 4.138,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.16757514431364e-05,
"loss": 4.1328,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.166736549562588e-05,
"loss": 4.1447,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.165897954811536e-05,
"loss": 4.1437,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.165059360060484e-05,
"loss": 4.1403,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.164220765309432e-05,
"loss": 4.1386,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.16338217055838e-05,
"loss": 4.1407,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.162543575807328e-05,
"loss": 4.1205,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.1617066189366486e-05,
"loss": 4.1328,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.1608680241855966e-05,
"loss": 4.1181,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.1600294294345446e-05,
"loss": 4.1383,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.1591908346834926e-05,
"loss": 4.1253,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.158352239932441e-05,
"loss": 4.1309,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.157515283061762e-05,
"loss": 4.1232,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.15667668831071e-05,
"loss": 4.1262,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.155838093559658e-05,
"loss": 4.1317,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.154999498808606e-05,
"loss": 4.1233,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.154162541937927e-05,
"loss": 4.1355,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.153325585067248e-05,
"loss": 4.1405,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.152486990316196e-05,
"loss": 4.1318,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.151648395565144e-05,
"loss": 4.1358,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.150809800814092e-05,
"loss": 4.131,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.14997120606304e-05,
"loss": 4.1371,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.149132611311988e-05,
"loss": 4.1335,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.1482940165609366e-05,
"loss": 4.1424,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.1474554218098846e-05,
"loss": 4.1248,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.1466168270588326e-05,
"loss": 4.1361,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.1457782323077806e-05,
"loss": 4.1241,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.1449396375567286e-05,
"loss": 4.1278,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.144101042805676e-05,
"loss": 4.1237,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.1432640859349975e-05,
"loss": 4.1254,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.1424271290643184e-05,
"loss": 4.1203,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.1415885343132664e-05,
"loss": 4.1366,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.1407499395622144e-05,
"loss": 4.1293,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.1399113448111624e-05,
"loss": 4.1334,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.1390727500601104e-05,
"loss": 4.1202,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.138235793189432e-05,
"loss": 4.1373,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.13739719843838e-05,
"loss": 4.1372,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.136558603687328e-05,
"loss": 4.1344,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.135720008936276e-05,
"loss": 4.1342,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.134881414185223e-05,
"loss": 4.1291,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.134042819434171e-05,
"loss": 4.1294,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.133204224683119e-05,
"loss": 4.1407,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.132365629932067e-05,
"loss": 4.1193,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.131528673061388e-05,
"loss": 4.1289,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.130690078310336e-05,
"loss": 4.1303,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.129853121439658e-05,
"loss": 4.1267,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.129014526688606e-05,
"loss": 4.1196,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.1281775698179273e-05,
"loss": 4.1196,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.1273389750668753e-05,
"loss": 4.1358,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.126500380315823e-05,
"loss": 4.1195,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.1256617855647707e-05,
"loss": 4.1361,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 4.132443904876709,
"eval_runtime": 339.1955,
"eval_samples_per_second": 1124.988,
"eval_steps_per_second": 35.157,
"step": 534240
},
{
"epoch": 1.0,
"learning_rate": 4.124824828694092e-05,
"loss": 4.1229,
"step": 534528
},
{
"epoch": 1.0,
"learning_rate": 4.12398623394304e-05,
"loss": 4.111,
"step": 535040
},
{
"epoch": 1.0,
"learning_rate": 4.123147639191988e-05,
"loss": 4.1319,
"step": 535552
},
{
"epoch": 1.0,
"learning_rate": 4.1223090444409356e-05,
"loss": 4.1196,
"step": 536064
},
{
"epoch": 1.0,
"learning_rate": 4.1214704496898835e-05,
"loss": 4.131,
"step": 536576
},
{
"epoch": 1.0,
"learning_rate": 4.1206318549388315e-05,
"loss": 4.1273,
"step": 537088
},
{
"epoch": 1.0,
"learning_rate": 4.1197932601877795e-05,
"loss": 4.1174,
"step": 537600
},
{
"epoch": 1.0,
"learning_rate": 4.1189546654367275e-05,
"loss": 4.1149,
"step": 538112
},
{
"epoch": 1.0,
"learning_rate": 4.1181160706856755e-05,
"loss": 4.1207,
"step": 538624
},
{
"epoch": 1.0,
"learning_rate": 4.117277475934624e-05,
"loss": 4.1288,
"step": 539136
},
{
"epoch": 1.0,
"learning_rate": 4.116438881183572e-05,
"loss": 4.1208,
"step": 539648
},
{
"epoch": 1.0,
"learning_rate": 4.11560028643252e-05,
"loss": 4.1196,
"step": 540160
},
{
"epoch": 1.0,
"learning_rate": 4.114763329561841e-05,
"loss": 4.119,
"step": 540672
},
{
"epoch": 1.0,
"learning_rate": 4.113924734810789e-05,
"loss": 4.1161,
"step": 541184
},
{
"epoch": 1.0,
"learning_rate": 4.113086140059737e-05,
"loss": 4.1196,
"step": 541696
},
{
"epoch": 1.0,
"learning_rate": 4.112247545308685e-05,
"loss": 4.1107,
"step": 542208
},
{
"epoch": 1.0,
"learning_rate": 4.111408950557633e-05,
"loss": 4.1172,
"step": 542720
},
{
"epoch": 1.0,
"learning_rate": 4.110571993686954e-05,
"loss": 4.1203,
"step": 543232
},
{
"epoch": 1.0,
"learning_rate": 4.109733398935902e-05,
"loss": 4.1204,
"step": 543744
},
{
"epoch": 1.0,
"learning_rate": 4.10889480418485e-05,
"loss": 4.123,
"step": 544256
},
{
"epoch": 1.0,
"learning_rate": 4.108056209433798e-05,
"loss": 4.1313,
"step": 544768
},
{
"epoch": 1.0,
"learning_rate": 4.1072208904434925e-05,
"loss": 4.1216,
"step": 545280
},
{
"epoch": 1.0,
"learning_rate": 4.1063822956924405e-05,
"loss": 4.1198,
"step": 545792
},
{
"epoch": 1.0,
"learning_rate": 4.1055437009413885e-05,
"loss": 4.126,
"step": 546304
},
{
"epoch": 1.0,
"learning_rate": 4.1047051061903365e-05,
"loss": 4.1141,
"step": 546816
},
{
"epoch": 1.0,
"learning_rate": 4.1038681493196574e-05,
"loss": 4.1274,
"step": 547328
},
{
"epoch": 1.0,
"learning_rate": 4.103031192448978e-05,
"loss": 4.1112,
"step": 547840
},
{
"epoch": 1.0,
"learning_rate": 4.102192597697926e-05,
"loss": 4.117,
"step": 548352
},
{
"epoch": 1.0,
"learning_rate": 4.101354002946874e-05,
"loss": 4.1123,
"step": 548864
},
{
"epoch": 1.0,
"learning_rate": 4.100515408195822e-05,
"loss": 4.1133,
"step": 549376
},
{
"epoch": 1.01,
"learning_rate": 4.09967681344477e-05,
"loss": 4.1135,
"step": 549888
},
{
"epoch": 1.01,
"learning_rate": 4.098838218693718e-05,
"loss": 4.121,
"step": 550400
},
{
"epoch": 1.01,
"learning_rate": 4.097999623942666e-05,
"loss": 4.1205,
"step": 550912
},
{
"epoch": 1.01,
"learning_rate": 4.097161029191615e-05,
"loss": 4.1235,
"step": 551424
},
{
"epoch": 1.01,
"learning_rate": 4.096322434440563e-05,
"loss": 4.1124,
"step": 551936
},
{
"epoch": 1.01,
"learning_rate": 4.095485477569884e-05,
"loss": 4.1272,
"step": 552448
},
{
"epoch": 1.01,
"learning_rate": 4.094646882818832e-05,
"loss": 4.1212,
"step": 552960
},
{
"epoch": 1.01,
"learning_rate": 4.09380828806778e-05,
"loss": 4.1073,
"step": 553472
},
{
"epoch": 1.01,
"learning_rate": 4.092969693316728e-05,
"loss": 4.1151,
"step": 553984
},
{
"epoch": 1.01,
"learning_rate": 4.092131098565676e-05,
"loss": 4.1129,
"step": 554496
},
{
"epoch": 1.01,
"learning_rate": 4.091292503814624e-05,
"loss": 4.1125,
"step": 555008
},
{
"epoch": 1.01,
"learning_rate": 4.090455546943945e-05,
"loss": 4.1203,
"step": 555520
},
{
"epoch": 1.01,
"learning_rate": 4.089616952192893e-05,
"loss": 4.1109,
"step": 556032
},
{
"epoch": 1.01,
"learning_rate": 4.088778357441841e-05,
"loss": 4.1153,
"step": 556544
},
{
"epoch": 1.01,
"learning_rate": 4.087939762690789e-05,
"loss": 4.1233,
"step": 557056
},
{
"epoch": 1.01,
"learning_rate": 4.0871028058201096e-05,
"loss": 4.1144,
"step": 557568
},
{
"epoch": 1.01,
"learning_rate": 4.086264211069058e-05,
"loss": 4.117,
"step": 558080
},
{
"epoch": 1.01,
"learning_rate": 4.085425616318006e-05,
"loss": 4.1158,
"step": 558592
},
{
"epoch": 1.01,
"learning_rate": 4.084587021566954e-05,
"loss": 4.0774,
"step": 559104
},
{
"epoch": 1.01,
"learning_rate": 4.0837484268159016e-05,
"loss": 4.1289,
"step": 559616
},
{
"epoch": 1.01,
"learning_rate": 4.082911469945223e-05,
"loss": 4.107,
"step": 560128
},
{
"epoch": 1.01,
"learning_rate": 4.082072875194171e-05,
"loss": 4.1169,
"step": 560640
},
{
"epoch": 1.01,
"learning_rate": 4.081234280443119e-05,
"loss": 4.0995,
"step": 561152
},
{
"epoch": 1.01,
"learning_rate": 4.0803956856920665e-05,
"loss": 4.0947,
"step": 561664
},
{
"epoch": 1.01,
"learning_rate": 4.0795570909410145e-05,
"loss": 4.1019,
"step": 562176
},
{
"epoch": 1.01,
"learning_rate": 4.078720134070336e-05,
"loss": 4.1079,
"step": 562688
},
{
"epoch": 1.01,
"learning_rate": 4.0778815393192834e-05,
"loss": 4.1078,
"step": 563200
},
{
"epoch": 1.01,
"learning_rate": 4.077042944568232e-05,
"loss": 4.1018,
"step": 563712
},
{
"epoch": 1.01,
"learning_rate": 4.07620434981718e-05,
"loss": 4.1211,
"step": 564224
},
{
"epoch": 1.01,
"learning_rate": 4.075365755066128e-05,
"loss": 4.1023,
"step": 564736
},
{
"epoch": 1.01,
"learning_rate": 4.074527160315076e-05,
"loss": 4.0987,
"step": 565248
},
{
"epoch": 1.01,
"learning_rate": 4.073688565564024e-05,
"loss": 4.1138,
"step": 565760
},
{
"epoch": 1.01,
"learning_rate": 4.072849970812972e-05,
"loss": 4.0886,
"step": 566272
},
{
"epoch": 1.01,
"learning_rate": 4.072013013942293e-05,
"loss": 4.0983,
"step": 566784
},
{
"epoch": 1.01,
"learning_rate": 4.071174419191241e-05,
"loss": 4.1059,
"step": 567296
},
{
"epoch": 1.01,
"learning_rate": 4.070335824440189e-05,
"loss": 4.1157,
"step": 567808
},
{
"epoch": 1.01,
"learning_rate": 4.06949886756951e-05,
"loss": 4.0911,
"step": 568320
},
{
"epoch": 1.01,
"learning_rate": 4.068660272818458e-05,
"loss": 4.1061,
"step": 568832
},
{
"epoch": 1.01,
"learning_rate": 4.067821678067406e-05,
"loss": 4.0901,
"step": 569344
},
{
"epoch": 1.01,
"learning_rate": 4.066983083316354e-05,
"loss": 4.1171,
"step": 569856
},
{
"epoch": 1.01,
"learning_rate": 4.066144488565302e-05,
"loss": 4.1108,
"step": 570368
},
{
"epoch": 1.01,
"learning_rate": 4.0653058938142505e-05,
"loss": 4.1116,
"step": 570880
},
{
"epoch": 1.01,
"learning_rate": 4.0644672990631985e-05,
"loss": 4.1135,
"step": 571392
},
{
"epoch": 1.01,
"learning_rate": 4.0636303421925194e-05,
"loss": 4.1217,
"step": 571904
},
{
"epoch": 1.01,
"learning_rate": 4.06279338532184e-05,
"loss": 4.1288,
"step": 572416
},
{
"epoch": 1.01,
"learning_rate": 4.061956428451161e-05,
"loss": 4.1053,
"step": 572928
},
{
"epoch": 1.01,
"learning_rate": 4.061117833700109e-05,
"loss": 4.108,
"step": 573440
},
{
"epoch": 1.01,
"learning_rate": 4.060279238949057e-05,
"loss": 4.1129,
"step": 573952
},
{
"epoch": 1.01,
"learning_rate": 4.059440644198005e-05,
"loss": 4.0939,
"step": 574464
},
{
"epoch": 1.01,
"learning_rate": 4.058602049446953e-05,
"loss": 4.1059,
"step": 574976
},
{
"epoch": 1.01,
"learning_rate": 4.057763454695901e-05,
"loss": 4.1083,
"step": 575488
},
{
"epoch": 1.01,
"learning_rate": 4.056924859944849e-05,
"loss": 4.1126,
"step": 576000
},
{
"epoch": 1.01,
"learning_rate": 4.056086265193797e-05,
"loss": 4.1148,
"step": 576512
},
{
"epoch": 1.01,
"learning_rate": 4.055247670442746e-05,
"loss": 4.0989,
"step": 577024
},
{
"epoch": 1.01,
"learning_rate": 4.054409075691694e-05,
"loss": 4.0985,
"step": 577536
},
{
"epoch": 1.01,
"learning_rate": 4.053570480940642e-05,
"loss": 4.1021,
"step": 578048
},
{
"epoch": 1.01,
"learning_rate": 4.05273188618959e-05,
"loss": 4.1122,
"step": 578560
},
{
"epoch": 1.01,
"learning_rate": 4.051893291438538e-05,
"loss": 4.1074,
"step": 579072
},
{
"epoch": 1.01,
"learning_rate": 4.051056334567859e-05,
"loss": 4.1017,
"step": 579584
},
{
"epoch": 1.02,
"learning_rate": 4.050217739816807e-05,
"loss": 4.1001,
"step": 580096
},
{
"epoch": 1.02,
"learning_rate": 4.049379145065755e-05,
"loss": 4.1098,
"step": 580608
},
{
"epoch": 1.02,
"learning_rate": 4.048540550314702e-05,
"loss": 4.1005,
"step": 581120
},
{
"epoch": 1.02,
"learning_rate": 4.04770195556365e-05,
"loss": 4.1001,
"step": 581632
},
{
"epoch": 1.02,
"learning_rate": 4.046863360812598e-05,
"loss": 4.1153,
"step": 582144
},
{
"epoch": 1.02,
"learning_rate": 4.046024766061546e-05,
"loss": 4.1037,
"step": 582656
},
{
"epoch": 1.02,
"learning_rate": 4.045186171310494e-05,
"loss": 4.1046,
"step": 583168
},
{
"epoch": 1.02,
"learning_rate": 4.0443492144398157e-05,
"loss": 4.0956,
"step": 583680
},
{
"epoch": 1.02,
"learning_rate": 4.0435106196887637e-05,
"loss": 4.0999,
"step": 584192
},
{
"epoch": 1.02,
"learning_rate": 4.0426720249377116e-05,
"loss": 4.0973,
"step": 584704
},
{
"epoch": 1.02,
"learning_rate": 4.0418334301866596e-05,
"loss": 4.113,
"step": 585216
},
{
"epoch": 1.02,
"learning_rate": 4.0409964733159806e-05,
"loss": 4.1078,
"step": 585728
},
{
"epoch": 1.02,
"learning_rate": 4.0401578785649285e-05,
"loss": 4.1069,
"step": 586240
},
{
"epoch": 1.02,
"learning_rate": 4.0393192838138765e-05,
"loss": 4.1067,
"step": 586752
},
{
"epoch": 1.02,
"learning_rate": 4.0384823269431975e-05,
"loss": 4.1036,
"step": 587264
},
{
"epoch": 1.02,
"learning_rate": 4.0376437321921454e-05,
"loss": 4.0917,
"step": 587776
},
{
"epoch": 1.02,
"learning_rate": 4.0368051374410934e-05,
"loss": 4.0922,
"step": 588288
},
{
"epoch": 1.02,
"learning_rate": 4.0359665426900414e-05,
"loss": 4.0866,
"step": 588800
},
{
"epoch": 1.02,
"learning_rate": 4.0351279479389894e-05,
"loss": 4.1055,
"step": 589312
},
{
"epoch": 1.02,
"learning_rate": 4.0342893531879374e-05,
"loss": 4.0916,
"step": 589824
},
{
"epoch": 1.02,
"learning_rate": 4.033450758436886e-05,
"loss": 4.0955,
"step": 590336
},
{
"epoch": 1.02,
"learning_rate": 4.032613801566207e-05,
"loss": 4.0876,
"step": 590848
},
{
"epoch": 1.02,
"learning_rate": 4.031775206815155e-05,
"loss": 4.0971,
"step": 591360
},
{
"epoch": 1.02,
"learning_rate": 4.030936612064103e-05,
"loss": 4.0966,
"step": 591872
},
{
"epoch": 1.02,
"learning_rate": 4.030098017313051e-05,
"loss": 4.088,
"step": 592384
},
{
"epoch": 1.02,
"learning_rate": 4.029259422561999e-05,
"loss": 4.1078,
"step": 592896
},
{
"epoch": 1.02,
"learning_rate": 4.028420827810947e-05,
"loss": 4.1025,
"step": 593408
},
{
"epoch": 1.02,
"learning_rate": 4.027582233059895e-05,
"loss": 4.0984,
"step": 593920
},
{
"epoch": 1.02,
"learning_rate": 4.026743638308843e-05,
"loss": 4.1042,
"step": 594432
},
{
"epoch": 1.02,
"learning_rate": 4.025906681438164e-05,
"loss": 4.0979,
"step": 594944
},
{
"epoch": 1.02,
"learning_rate": 4.025069724567485e-05,
"loss": 4.1013,
"step": 595456
},
{
"epoch": 1.02,
"learning_rate": 4.024231129816433e-05,
"loss": 4.1037,
"step": 595968
},
{
"epoch": 1.02,
"learning_rate": 4.0233925350653815e-05,
"loss": 4.1045,
"step": 596480
},
{
"epoch": 1.02,
"learning_rate": 4.0225539403143295e-05,
"loss": 4.0937,
"step": 596992
},
{
"epoch": 1.02,
"learning_rate": 4.0217153455632775e-05,
"loss": 4.1015,
"step": 597504
},
{
"epoch": 1.02,
"learning_rate": 4.0208767508122255e-05,
"loss": 4.0943,
"step": 598016
},
{
"epoch": 1.02,
"learning_rate": 4.0200397939415464e-05,
"loss": 4.0955,
"step": 598528
},
{
"epoch": 1.02,
"learning_rate": 4.0192011991904944e-05,
"loss": 4.0867,
"step": 599040
},
{
"epoch": 1.02,
"learning_rate": 4.0183626044394424e-05,
"loss": 4.0928,
"step": 599552
},
{
"epoch": 1.02,
"learning_rate": 4.0175240096883904e-05,
"loss": 4.0884,
"step": 600064
},
{
"epoch": 1.02,
"learning_rate": 4.0166854149373383e-05,
"loss": 4.1025,
"step": 600576
},
{
"epoch": 1.02,
"learning_rate": 4.015846820186286e-05,
"loss": 4.0949,
"step": 601088
},
{
"epoch": 1.02,
"learning_rate": 4.015008225435234e-05,
"loss": 4.1009,
"step": 601600
},
{
"epoch": 1.02,
"learning_rate": 4.0141696306841817e-05,
"loss": 4.084,
"step": 602112
},
{
"epoch": 1.02,
"learning_rate": 4.0133310359331297e-05,
"loss": 4.1088,
"step": 602624
},
{
"epoch": 1.02,
"learning_rate": 4.012492441182078e-05,
"loss": 4.1011,
"step": 603136
},
{
"epoch": 1.02,
"learning_rate": 4.011655484311399e-05,
"loss": 4.1018,
"step": 603648
},
{
"epoch": 1.02,
"learning_rate": 4.010816889560347e-05,
"loss": 4.1018,
"step": 604160
},
{
"epoch": 1.02,
"learning_rate": 4.009978294809295e-05,
"loss": 4.097,
"step": 604672
},
{
"epoch": 1.02,
"learning_rate": 4.009139700058243e-05,
"loss": 4.0944,
"step": 605184
},
{
"epoch": 1.02,
"learning_rate": 4.008302743187564e-05,
"loss": 4.1064,
"step": 605696
},
{
"epoch": 1.02,
"learning_rate": 4.007464148436512e-05,
"loss": 4.0882,
"step": 606208
},
{
"epoch": 1.02,
"learning_rate": 4.00662555368546e-05,
"loss": 4.0976,
"step": 606720
},
{
"epoch": 1.02,
"learning_rate": 4.005786958934408e-05,
"loss": 4.0987,
"step": 607232
},
{
"epoch": 1.02,
"learning_rate": 4.004950002063729e-05,
"loss": 4.0937,
"step": 607744
},
{
"epoch": 1.02,
"learning_rate": 4.004111407312677e-05,
"loss": 4.0867,
"step": 608256
},
{
"epoch": 1.02,
"learning_rate": 4.003272812561625e-05,
"loss": 4.0879,
"step": 608768
},
{
"epoch": 1.02,
"learning_rate": 4.0024358556909466e-05,
"loss": 4.1021,
"step": 609280
},
{
"epoch": 1.02,
"learning_rate": 4.0015972609398946e-05,
"loss": 4.0894,
"step": 609792
},
{
"epoch": 1.02,
"learning_rate": 4.0007586661888426e-05,
"loss": 4.1019,
"step": 610304
},
{
"epoch": 1.03,
"eval_loss": 4.107419490814209,
"eval_runtime": 325.8697,
"eval_samples_per_second": 1170.993,
"eval_steps_per_second": 36.594,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.9999200714377906e-05,
"loss": 4.0853,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.9990814766867386e-05,
"loss": 4.0836,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.9982428819356866e-05,
"loss": 4.0917,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.9974042871846346e-05,
"loss": 4.0905,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.9965656924335826e-05,
"loss": 4.1006,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.9957270976825306e-05,
"loss": 4.0942,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.9948885029314786e-05,
"loss": 4.0848,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.9940499081804266e-05,
"loss": 4.0847,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.9932113134293746e-05,
"loss": 4.0863,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.992372718678322e-05,
"loss": 4.0982,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.9915341239272706e-05,
"loss": 4.0884,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.9906955291762185e-05,
"loss": 4.0861,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.9898569344251665e-05,
"loss": 4.0968,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.9890183396741145e-05,
"loss": 4.0772,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.9881797449230625e-05,
"loss": 4.0839,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.9873411501720105e-05,
"loss": 4.0811,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.9865025554209585e-05,
"loss": 4.0861,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.9856639606699065e-05,
"loss": 4.0888,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.9848253659188545e-05,
"loss": 4.0887,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.9839884090481754e-05,
"loss": 4.0888,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.9831498142971234e-05,
"loss": 4.1026,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.982312857426444e-05,
"loss": 4.0896,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.981474262675392e-05,
"loss": 4.0913,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.98063566792434e-05,
"loss": 4.0895,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.979797073173288e-05,
"loss": 4.0863,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.978958478422237e-05,
"loss": 4.0946,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.978119883671185e-05,
"loss": 4.0824,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.977281288920133e-05,
"loss": 4.0862,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.976442694169081e-05,
"loss": 4.0752,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.975604099418029e-05,
"loss": 4.0828,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.97476714254735e-05,
"loss": 4.0802,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.973928547796298e-05,
"loss": 4.0884,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.973089953045246e-05,
"loss": 4.0928,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.972251358294193e-05,
"loss": 4.0943,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971412763543141e-05,
"loss": 4.0836,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.970574168792089e-05,
"loss": 4.0897,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.969735574041037e-05,
"loss": 4.0933,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.968896979289985e-05,
"loss": 4.0806,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.968060022419307e-05,
"loss": 4.081,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.967221427668255e-05,
"loss": 4.0826,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.966382832917203e-05,
"loss": 4.0867,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.965544238166151e-05,
"loss": 4.0825,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.9647072812954717e-05,
"loss": 4.0871,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.9638686865444197e-05,
"loss": 4.0853,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.9630300917933676e-05,
"loss": 4.09,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.9621914970423156e-05,
"loss": 4.0854,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.9613545401716366e-05,
"loss": 4.0857,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.9605159454205845e-05,
"loss": 4.085,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.9596773506695325e-05,
"loss": 4.0481,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.9588387559184805e-05,
"loss": 4.0961,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.958001799047802e-05,
"loss": 4.0763,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.957164842177124e-05,
"loss": 4.0876,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.956326247426071e-05,
"loss": 4.0714,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.955487652675019e-05,
"loss": 4.0659,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.954649057923967e-05,
"loss": 4.068,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.953812101053288e-05,
"loss": 4.0768,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.952973506302236e-05,
"loss": 4.077,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.952134911551184e-05,
"loss": 4.0733,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.951296316800132e-05,
"loss": 4.0864,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.95045772204908e-05,
"loss": 4.0761,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.949619127298028e-05,
"loss": 4.0682,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.948780532546976e-05,
"loss": 4.0823,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.9479419377959246e-05,
"loss": 4.0619,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.9471049809252455e-05,
"loss": 4.0665,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.9462663861741935e-05,
"loss": 4.0763,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.9454277914231415e-05,
"loss": 4.083,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.9445891966720895e-05,
"loss": 4.0655,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.9437522398014104e-05,
"loss": 4.0742,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.942915282930731e-05,
"loss": 4.0588,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.942076688179679e-05,
"loss": 4.084,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.941238093428627e-05,
"loss": 4.0831,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.940399498677575e-05,
"loss": 4.0795,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.939560903926523e-05,
"loss": 4.085,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.938722309175471e-05,
"loss": 4.0898,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.93788371442442e-05,
"loss": 4.1005,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.937046757553741e-05,
"loss": 4.0772,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.936208162802689e-05,
"loss": 4.0784,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.93537120593201e-05,
"loss": 4.0777,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.934532611180958e-05,
"loss": 4.0717,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.933694016429906e-05,
"loss": 4.0734,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.932855421678854e-05,
"loss": 4.0817,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.932016826927802e-05,
"loss": 4.0836,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.93117823217675e-05,
"loss": 4.0893,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.930339637425698e-05,
"loss": 4.0678,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.929501042674646e-05,
"loss": 4.0676,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.928662447923594e-05,
"loss": 4.0717,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.927823853172542e-05,
"loss": 4.0857,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.92698525842149e-05,
"loss": 4.0808,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.926148301550811e-05,
"loss": 4.0687,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.925309706799759e-05,
"loss": 4.0715,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.9244711120487066e-05,
"loss": 4.0804,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.9236325172976546e-05,
"loss": 4.0737,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.9227939225466026e-05,
"loss": 4.0685,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.9219553277955506e-05,
"loss": 4.0857,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.9211167330444986e-05,
"loss": 4.078,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.9202781382934466e-05,
"loss": 4.0754,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.9194395435423946e-05,
"loss": 4.0689,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.9186025866717155e-05,
"loss": 4.07,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.9177639919206635e-05,
"loss": 4.0695,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.9169253971696115e-05,
"loss": 4.0822,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.91608680241856e-05,
"loss": 4.0803,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.915249845547881e-05,
"loss": 4.0761,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.914411250796829e-05,
"loss": 4.0805,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.913572656045777e-05,
"loss": 4.0712,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.912734061294725e-05,
"loss": 4.0709,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.911897104424046e-05,
"loss": 4.0629,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.911058509672994e-05,
"loss": 4.0568,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.910219914921942e-05,
"loss": 4.079,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.90938132017089e-05,
"loss": 4.0661,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.908542725419838e-05,
"loss": 4.063,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.907704130668786e-05,
"loss": 4.0602,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.906867173798107e-05,
"loss": 4.0613,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.9060285790470555e-05,
"loss": 4.0722,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.9051899842960035e-05,
"loss": 4.0641,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.9043513895449515e-05,
"loss": 4.0766,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.9035144326742724e-05,
"loss": 4.0748,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.9026758379232204e-05,
"loss": 4.0743,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.9018372431721684e-05,
"loss": 4.0742,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.9009986484211164e-05,
"loss": 4.0702,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.900161691550437e-05,
"loss": 4.0724,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.899323096799385e-05,
"loss": 4.0775,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.898484502048333e-05,
"loss": 4.0753,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.897645907297281e-05,
"loss": 4.0685,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.896808950426602e-05,
"loss": 4.0724,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.895970355675551e-05,
"loss": 4.0677,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.895133398804872e-05,
"loss": 4.0671,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.89429480405382e-05,
"loss": 4.0586,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.893456209302768e-05,
"loss": 4.0639,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.892617614551716e-05,
"loss": 4.0595,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.891779019800664e-05,
"loss": 4.0738,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.890940425049612e-05,
"loss": 4.0658,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.89010183029856e-05,
"loss": 4.0786,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.889263235547508e-05,
"loss": 4.056,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.888424640796455e-05,
"loss": 4.0806,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.887586046045403e-05,
"loss": 4.0741,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.886747451294351e-05,
"loss": 4.0764,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.885910494423673e-05,
"loss": 4.0732,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.885071899672621e-05,
"loss": 4.0687,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884233304921569e-05,
"loss": 4.0692,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.8833947101705167e-05,
"loss": 4.0803,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.8825561154194647e-05,
"loss": 4.0588,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.8817175206684127e-05,
"loss": 4.0722,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.880882201678107e-05,
"loss": 4.0696,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.880043606927055e-05,
"loss": 4.0655,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.8792050121760025e-05,
"loss": 4.0645,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.8783664174249505e-05,
"loss": 4.0622,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.877529460554272e-05,
"loss": 4.0743,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.87669086580322e-05,
"loss": 4.0658,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.875852271052168e-05,
"loss": 4.0734,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 4.087892532348633,
"eval_runtime": 294.9945,
"eval_samples_per_second": 1293.553,
"eval_steps_per_second": 40.424,
"step": 686880
},
{
"epoch": 1.0,
"learning_rate": 3.875013676301116e-05,
"loss": 4.0577,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.874175081550064e-05,
"loss": 4.0592,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.873336486799012e-05,
"loss": 4.0623,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.87249789204796e-05,
"loss": 4.0642,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.871660935177281e-05,
"loss": 4.077,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.870822340426229e-05,
"loss": 4.0662,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.869983745675177e-05,
"loss": 4.06,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.869145150924125e-05,
"loss": 4.0613,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.868306556173073e-05,
"loss": 4.0575,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.867469599302394e-05,
"loss": 4.0715,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.866631004551342e-05,
"loss": 4.0618,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.86579240980029e-05,
"loss": 4.0612,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.864953815049238e-05,
"loss": 4.0698,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.8641152202981865e-05,
"loss": 4.0509,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.8632782634275074e-05,
"loss": 4.0565,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.8624396686764554e-05,
"loss": 4.0534,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.8616010739254034e-05,
"loss": 4.0622,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.8607624791743514e-05,
"loss": 4.0582,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.8599238844232994e-05,
"loss": 4.066,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.85908692755262e-05,
"loss": 4.0631,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.858248332801568e-05,
"loss": 4.076,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.857409738050516e-05,
"loss": 4.0627,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.856571143299464e-05,
"loss": 4.067,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.855732548548412e-05,
"loss": 4.0602,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.85489395379736e-05,
"loss": 4.0643,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.854055359046308e-05,
"loss": 4.066,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.85321840217563e-05,
"loss": 4.0533,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.852379807424578e-05,
"loss": 4.0647,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.851541212673526e-05,
"loss": 4.0501,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.850702617922474e-05,
"loss": 4.0568,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.849864023171421e-05,
"loss": 4.0562,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.849025428420369e-05,
"loss": 4.0601,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.848186833669317e-05,
"loss": 4.0696,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.847348238918265e-05,
"loss": 4.0675,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.846509644167213e-05,
"loss": 4.0598,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.8456743251769076e-05,
"loss": 4.0601,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.8448357304258556e-05,
"loss": 4.072,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.8439971356748036e-05,
"loss": 4.055,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.8431585409237516e-05,
"loss": 4.0542,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.8423199461726996e-05,
"loss": 4.0559,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.8414813514216476e-05,
"loss": 4.0617,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.8406427566705956e-05,
"loss": 4.058,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.8398041619195436e-05,
"loss": 4.0575,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.8389655671684916e-05,
"loss": 4.0616,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.8381286102978125e-05,
"loss": 4.0606,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.8372900155467605e-05,
"loss": 4.0619,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.8364514207957085e-05,
"loss": 4.0606,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.8356144639250294e-05,
"loss": 4.0609,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.8347758691739774e-05,
"loss": 4.0247,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.8339372744229254e-05,
"loss": 4.067,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.833098679671874e-05,
"loss": 4.0507,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.832260084920822e-05,
"loss": 4.0648,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.83142149016977e-05,
"loss": 4.0472,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.830582895418718e-05,
"loss": 4.0409,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.829745938548039e-05,
"loss": 4.0439,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.828907343796987e-05,
"loss": 4.0508,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.828068749045935e-05,
"loss": 4.0605,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.827230154294883e-05,
"loss": 4.0429,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.826391559543831e-05,
"loss": 4.0634,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.825552964792779e-05,
"loss": 4.053,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.824714370041727e-05,
"loss": 4.0383,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.823875775290675e-05,
"loss": 4.0575,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.823038818419996e-05,
"loss": 4.0417,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.8222018615493174e-05,
"loss": 4.0395,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.8213632667982654e-05,
"loss": 4.0536,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.8205246720472134e-05,
"loss": 4.0595,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.8196860772961614e-05,
"loss": 4.0433,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.8188474825451094e-05,
"loss": 4.048,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.8180088877940574e-05,
"loss": 4.0386,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.817170293043005e-05,
"loss": 4.0572,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.816331698291953e-05,
"loss": 4.0596,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.815494741421274e-05,
"loss": 4.0543,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.814656146670222e-05,
"loss": 4.0614,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.8138175519191696e-05,
"loss": 4.0655,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.812980595048491e-05,
"loss": 4.074,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.812142000297439e-05,
"loss": 4.0544,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.811303405546387e-05,
"loss": 4.0561,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.810464810795335e-05,
"loss": 4.0501,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.809626216044283e-05,
"loss": 4.0519,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.808787621293231e-05,
"loss": 4.0469,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.807950664422552e-05,
"loss": 4.0589,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.8071120696715e-05,
"loss": 4.0572,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.806273474920448e-05,
"loss": 4.0662,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.805434880169396e-05,
"loss": 4.0411,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.804596285418344e-05,
"loss": 4.0442,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.803759328547665e-05,
"loss": 4.0506,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.802920733796613e-05,
"loss": 4.0547,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.802082139045561e-05,
"loss": 4.0573,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.8012435442945097e-05,
"loss": 4.0497,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.8004049495434577e-05,
"loss": 4.0472,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.7995679926727786e-05,
"loss": 4.0561,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.7987293979217266e-05,
"loss": 4.0488,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.7978908031706746e-05,
"loss": 4.043,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.7970522084196225e-05,
"loss": 4.0614,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.7962152515489435e-05,
"loss": 4.0533,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.7953766567978915e-05,
"loss": 4.0541,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.7945380620468395e-05,
"loss": 4.0437,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.7936994672957874e-05,
"loss": 4.0449,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.7928608725447354e-05,
"loss": 4.0456,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.7920222777936834e-05,
"loss": 4.0578,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.791185320923005e-05,
"loss": 4.0611,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.790346726171953e-05,
"loss": 4.0492,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.789508131420901e-05,
"loss": 4.0584,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.788669536669849e-05,
"loss": 4.0479,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.787830941918797e-05,
"loss": 4.05,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.786993985048118e-05,
"loss": 4.038,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.786155390297066e-05,
"loss": 4.0377,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.785316795546014e-05,
"loss": 4.0488,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.784478200794962e-05,
"loss": 4.0484,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.78363960604391e-05,
"loss": 4.0363,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.782801011292858e-05,
"loss": 4.0383,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.781962416541805e-05,
"loss": 4.0391,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.781123821790753e-05,
"loss": 4.0482,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.780286864920075e-05,
"loss": 4.0401,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.7794482701690235e-05,
"loss": 4.0525,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.7786113132983444e-05,
"loss": 4.0517,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.7777727185472924e-05,
"loss": 4.0502,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.7769341237962404e-05,
"loss": 4.0454,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.7760955290451884e-05,
"loss": 4.0517,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.775256934294136e-05,
"loss": 4.0481,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.774418339543084e-05,
"loss": 4.0555,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.773579744792032e-05,
"loss": 4.0525,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.77274115004098e-05,
"loss": 4.0435,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.7719041931703006e-05,
"loss": 4.0494,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.7710655984192486e-05,
"loss": 4.0474,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.770227003668197e-05,
"loss": 4.0405,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.769388408917145e-05,
"loss": 4.0395,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.768549814166093e-05,
"loss": 4.0422,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.767714495175788e-05,
"loss": 4.0335,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.766875900424736e-05,
"loss": 4.0525,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.766037305673683e-05,
"loss": 4.0433,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.765198710922631e-05,
"loss": 4.0532,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.764360116171579e-05,
"loss": 4.0337,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.763521521420527e-05,
"loss": 4.0531,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.762684564549848e-05,
"loss": 4.0532,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.761845969798796e-05,
"loss": 4.0527,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.761007375047744e-05,
"loss": 4.0499,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.7601687802966926e-05,
"loss": 4.0441,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.7593301855456406e-05,
"loss": 4.0513,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.7584932286749615e-05,
"loss": 4.0547,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.7576546339239095e-05,
"loss": 4.0381,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.7568160391728575e-05,
"loss": 4.0492,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.7559790823021784e-05,
"loss": 4.0485,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.7551404875511264e-05,
"loss": 4.0437,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.7543018928000744e-05,
"loss": 4.0411,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.7534632980490224e-05,
"loss": 4.0374,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.7526247032979704e-05,
"loss": 4.0498,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.7517861085469184e-05,
"loss": 4.0458,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.7509475137958664e-05,
"loss": 4.0511,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 4.071868896484375,
"eval_runtime": 297.0603,
"eval_samples_per_second": 1284.557,
"eval_steps_per_second": 40.143,
"step": 763200
},
{
"epoch": 0.0,
"learning_rate": 3.7501089190448144e-05,
"loss": 4.0278,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.7492703242937624e-05,
"loss": 4.0381,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.7484317295427104e-05,
"loss": 4.0386,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.747593134791659e-05,
"loss": 4.0418,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.746754540040607e-05,
"loss": 4.0532,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.7459159452895544e-05,
"loss": 4.0487,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.7450773505385024e-05,
"loss": 4.0349,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.7442387557874504e-05,
"loss": 4.039,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.7434001610363984e-05,
"loss": 4.0355,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.7425615662853463e-05,
"loss": 4.0452,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.7417229715342943e-05,
"loss": 4.0411,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.7408843767832423e-05,
"loss": 4.0417,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.74004578203219e-05,
"loss": 4.0471,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.739207187281138e-05,
"loss": 4.0261,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.738368592530086e-05,
"loss": 4.036,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.737529997779034e-05,
"loss": 4.0296,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.736693040908356e-05,
"loss": 4.045,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.735854446157304e-05,
"loss": 4.0358,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.735015851406252e-05,
"loss": 4.0421,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.7341772566552e-05,
"loss": 4.0396,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.733338661904148e-05,
"loss": 4.0534,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.732501705033469e-05,
"loss": 4.0393,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.731663110282417e-05,
"loss": 4.0493,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.730824515531365e-05,
"loss": 4.0414,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.729985920780313e-05,
"loss": 4.0413,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.72914732602926e-05,
"loss": 4.0422,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.7283120070389546e-05,
"loss": 4.0305,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.7274734122879026e-05,
"loss": 4.0402,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.726634817536851e-05,
"loss": 4.0326,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.725796222785799e-05,
"loss": 4.0334,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.724957628034747e-05,
"loss": 4.0371,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.724119033283695e-05,
"loss": 4.0388,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.723280438532643e-05,
"loss": 4.0412,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.7224418437815906e-05,
"loss": 4.0512,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.7216032490305386e-05,
"loss": 4.0358,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.720767930040233e-05,
"loss": 4.0377,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.719929335289181e-05,
"loss": 4.052,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.719090740538129e-05,
"loss": 4.0309,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.718252145787077e-05,
"loss": 4.0326,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.717413551036025e-05,
"loss": 4.0373,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.716574956284973e-05,
"loss": 4.0334,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.715736361533921e-05,
"loss": 4.0391,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.714897766782869e-05,
"loss": 4.0323,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.714059172031817e-05,
"loss": 4.0436,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.713222215161138e-05,
"loss": 4.0355,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.712383620410086e-05,
"loss": 4.0409,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.711545025659034e-05,
"loss": 4.0363,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.710706430907982e-05,
"loss": 4.0433,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.709869474037303e-05,
"loss": 4.0055,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.7090325171666244e-05,
"loss": 4.0456,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.7081939224155724e-05,
"loss": 4.0261,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.7073553276645204e-05,
"loss": 4.0416,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.7065167329134684e-05,
"loss": 4.026,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.7056781381624164e-05,
"loss": 4.0204,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.7048395434113644e-05,
"loss": 4.0207,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.7040009486603124e-05,
"loss": 4.0293,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.7031623539092604e-05,
"loss": 4.0374,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.7023237591582084e-05,
"loss": 4.0222,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.7014851644071564e-05,
"loss": 4.0433,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.7006465696561044e-05,
"loss": 4.0359,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.699809612785425e-05,
"loss": 4.0143,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.698971018034373e-05,
"loss": 4.0373,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.698132423283321e-05,
"loss": 4.0181,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.697293828532269e-05,
"loss": 4.0191,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.69645687166159e-05,
"loss": 4.0331,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.695618276910538e-05,
"loss": 4.037,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.694779682159487e-05,
"loss": 4.0176,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.693941087408435e-05,
"loss": 4.033,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.693102492657383e-05,
"loss": 4.0178,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.692263897906331e-05,
"loss": 4.0299,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.691426941035652e-05,
"loss": 4.0364,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.690589984164973e-05,
"loss": 4.0348,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.689751389413921e-05,
"loss": 4.0411,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.6889127946628687e-05,
"loss": 4.0399,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.6880741999118167e-05,
"loss": 4.0552,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.6872356051607646e-05,
"loss": 4.0346,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.6863970104097126e-05,
"loss": 4.0391,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.6855584156586606e-05,
"loss": 4.0256,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.6847198209076086e-05,
"loss": 4.0305,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.6838812261565566e-05,
"loss": 4.027,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.683044269285878e-05,
"loss": 4.035,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.682205674534826e-05,
"loss": 4.0396,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.6813670797837735e-05,
"loss": 4.0445,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.6805284850327215e-05,
"loss": 4.0203,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.6796898902816695e-05,
"loss": 4.0262,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.678852933410991e-05,
"loss": 4.0273,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.6780143386599384e-05,
"loss": 4.0348,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.6771757439088864e-05,
"loss": 4.0341,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.6763371491578344e-05,
"loss": 4.0283,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.675500192287156e-05,
"loss": 4.0291,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.6746632354164776e-05,
"loss": 4.0327,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.6738246406654256e-05,
"loss": 4.0271,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.6729860459143736e-05,
"loss": 4.0231,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.672147451163321e-05,
"loss": 4.0401,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.671308856412269e-05,
"loss": 4.0365,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.670470261661217e-05,
"loss": 4.0343,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.669631666910165e-05,
"loss": 4.0222,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.668793072159113e-05,
"loss": 4.0239,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.667954477408061e-05,
"loss": 4.0267,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.667117520537382e-05,
"loss": 4.0345,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.66627892578633e-05,
"loss": 4.0419,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.665440331035278e-05,
"loss": 4.0242,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.664601736284226e-05,
"loss": 4.0406,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.6637631415331745e-05,
"loss": 4.0297,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.6629261846624954e-05,
"loss": 4.0264,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.662089227791816e-05,
"loss": 4.0191,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.661250633040764e-05,
"loss": 4.0169,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.660412038289712e-05,
"loss": 4.0264,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.65957344353866e-05,
"loss": 4.0254,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.658734848787608e-05,
"loss": 4.0187,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.657896254036556e-05,
"loss": 4.0197,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.657057659285504e-05,
"loss": 4.0126,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.656219064534452e-05,
"loss": 4.0283,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.6553804697834e-05,
"loss": 4.022,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.654543512912721e-05,
"loss": 4.0296,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.65370491816167e-05,
"loss": 4.0322,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.652866323410618e-05,
"loss": 4.0291,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.652027728659566e-05,
"loss": 4.0275,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.651189133908514e-05,
"loss": 4.0323,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.650350539157462e-05,
"loss": 4.0276,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.64951194440641e-05,
"loss": 4.0385,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.648673349655357e-05,
"loss": 4.0288,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.647836392784679e-05,
"loss": 4.027,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.646997798033627e-05,
"loss": 4.0276,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.6461608411629476e-05,
"loss": 4.026,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.6453222464118956e-05,
"loss": 4.0211,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.6444836516608436e-05,
"loss": 4.0203,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.6436450569097916e-05,
"loss": 4.018,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.642808100039113e-05,
"loss": 4.0159,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.641969505288061e-05,
"loss": 4.0326,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.641130910537009e-05,
"loss": 4.0249,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.640292315785957e-05,
"loss": 4.0318,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.639455358915278e-05,
"loss": 4.0183,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.638616764164226e-05,
"loss": 4.0329,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.637778169413174e-05,
"loss": 4.0329,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.636939574662122e-05,
"loss": 4.0305,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.6361009799110694e-05,
"loss": 4.0287,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.635264023040391e-05,
"loss": 4.0253,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.634425428289339e-05,
"loss": 4.0349,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.633586833538287e-05,
"loss": 4.0376,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.632748238787235e-05,
"loss": 4.0181,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.631909644036183e-05,
"loss": 4.0268,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.631071049285131e-05,
"loss": 4.0291,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.630232454534079e-05,
"loss": 4.0227,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.6293954976634e-05,
"loss": 4.0209,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.628556902912348e-05,
"loss": 4.0222,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.627718308161296e-05,
"loss": 4.0284,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.626879713410244e-05,
"loss": 4.025,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.626042756539565e-05,
"loss": 4.0305,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 4.05925989151001,
"eval_runtime": 302.8737,
"eval_samples_per_second": 1259.901,
"eval_steps_per_second": 39.373,
"step": 839520
},
{
"epoch": 1.0,
"learning_rate": 3.625204161788513e-05,
"loss": 4.0157,
"step": 839680
},
{
"epoch": 1.0,
"learning_rate": 3.6243672049178337e-05,
"loss": 4.017,
"step": 840192
},
{
"epoch": 1.0,
"learning_rate": 3.623528610166782e-05,
"loss": 4.0185,
"step": 840704
},
{
"epoch": 1.0,
"learning_rate": 3.62269001541573e-05,
"loss": 4.0247,
"step": 841216
},
{
"epoch": 1.0,
"learning_rate": 3.621851420664678e-05,
"loss": 4.0319,
"step": 841728
},
{
"epoch": 1.0,
"learning_rate": 3.621012825913626e-05,
"loss": 4.03,
"step": 842240
},
{
"epoch": 1.0,
"learning_rate": 3.620174231162574e-05,
"loss": 4.0173,
"step": 842752
},
{
"epoch": 1.0,
"learning_rate": 3.619335636411522e-05,
"loss": 4.0215,
"step": 843264
},
{
"epoch": 1.0,
"learning_rate": 3.61849704166047e-05,
"loss": 4.0138,
"step": 843776
},
{
"epoch": 1.0,
"learning_rate": 3.617660084789791e-05,
"loss": 4.0223,
"step": 844288
},
{
"epoch": 1.0,
"learning_rate": 3.616821490038739e-05,
"loss": 4.028,
"step": 844800
},
{
"epoch": 1.0,
"learning_rate": 3.615986171048434e-05,
"loss": 4.0227,
"step": 845312
},
{
"epoch": 1.0,
"learning_rate": 3.615147576297381e-05,
"loss": 4.0258,
"step": 845824
},
{
"epoch": 1.0,
"learning_rate": 3.614308981546329e-05,
"loss": 4.0105,
"step": 846336
},
{
"epoch": 1.0,
"learning_rate": 3.613470386795278e-05,
"loss": 4.0186,
"step": 846848
},
{
"epoch": 1.0,
"learning_rate": 3.612631792044226e-05,
"loss": 4.0047,
"step": 847360
},
{
"epoch": 1.0,
"learning_rate": 3.611793197293174e-05,
"loss": 4.0267,
"step": 847872
},
{
"epoch": 1.0,
"learning_rate": 3.610954602542122e-05,
"loss": 4.0193,
"step": 848384
},
{
"epoch": 1.0,
"learning_rate": 3.61011600779107e-05,
"loss": 4.021,
"step": 848896
},
{
"epoch": 1.0,
"learning_rate": 3.609277413040018e-05,
"loss": 4.0193,
"step": 849408
},
{
"epoch": 1.0,
"learning_rate": 3.608438818288966e-05,
"loss": 4.039,
"step": 849920
},
{
"epoch": 1.0,
"learning_rate": 3.607600223537914e-05,
"loss": 4.0163,
"step": 850432
},
{
"epoch": 1.0,
"learning_rate": 3.6067616287868617e-05,
"loss": 4.0304,
"step": 850944
},
{
"epoch": 1.0,
"learning_rate": 3.6059230340358097e-05,
"loss": 4.0197,
"step": 851456
},
{
"epoch": 1.0,
"learning_rate": 3.6050844392847576e-05,
"loss": 4.0236,
"step": 851968
},
{
"epoch": 1.0,
"learning_rate": 3.6042474824140786e-05,
"loss": 4.0261,
"step": 852480
},
{
"epoch": 1.0,
"learning_rate": 3.6034088876630266e-05,
"loss": 4.0098,
"step": 852992
},
{
"epoch": 1.0,
"learning_rate": 3.6025702929119745e-05,
"loss": 4.0197,
"step": 853504
},
{
"epoch": 1.0,
"learning_rate": 3.6017316981609225e-05,
"loss": 4.0132,
"step": 854016
},
{
"epoch": 1.0,
"learning_rate": 3.600894741290244e-05,
"loss": 4.0141,
"step": 854528
},
{
"epoch": 1.01,
"learning_rate": 3.600056146539192e-05,
"loss": 4.0186,
"step": 855040
},
{
"epoch": 1.01,
"learning_rate": 3.59921755178814e-05,
"loss": 4.0192,
"step": 855552
},
{
"epoch": 1.01,
"learning_rate": 3.598378957037088e-05,
"loss": 4.017,
"step": 856064
},
{
"epoch": 1.01,
"learning_rate": 3.5975403622860354e-05,
"loss": 4.0362,
"step": 856576
},
{
"epoch": 1.01,
"learning_rate": 3.5967017675349834e-05,
"loss": 4.0194,
"step": 857088
},
{
"epoch": 1.01,
"learning_rate": 3.595864810664305e-05,
"loss": 4.0185,
"step": 857600
},
{
"epoch": 1.01,
"learning_rate": 3.595026215913253e-05,
"loss": 4.0294,
"step": 858112
},
{
"epoch": 1.01,
"learning_rate": 3.5941876211622e-05,
"loss": 4.0104,
"step": 858624
},
{
"epoch": 1.01,
"learning_rate": 3.593349026411148e-05,
"loss": 4.0157,
"step": 859136
},
{
"epoch": 1.01,
"learning_rate": 3.592510431660096e-05,
"loss": 4.0224,
"step": 859648
},
{
"epoch": 1.01,
"learning_rate": 3.591673474789418e-05,
"loss": 4.0142,
"step": 860160
},
{
"epoch": 1.01,
"learning_rate": 3.590834880038366e-05,
"loss": 4.0192,
"step": 860672
},
{
"epoch": 1.01,
"learning_rate": 3.589996285287314e-05,
"loss": 4.0204,
"step": 861184
},
{
"epoch": 1.01,
"learning_rate": 3.589157690536262e-05,
"loss": 4.0168,
"step": 861696
},
{
"epoch": 1.01,
"learning_rate": 3.588320733665583e-05,
"loss": 4.0222,
"step": 862208
},
{
"epoch": 1.01,
"learning_rate": 3.587482138914531e-05,
"loss": 4.0218,
"step": 862720
},
{
"epoch": 1.01,
"learning_rate": 3.586643544163479e-05,
"loss": 4.0173,
"step": 863232
},
{
"epoch": 1.01,
"learning_rate": 3.585804949412427e-05,
"loss": 4.0236,
"step": 863744
},
{
"epoch": 1.01,
"learning_rate": 3.584966354661375e-05,
"loss": 3.9887,
"step": 864256
},
{
"epoch": 1.01,
"learning_rate": 3.584127759910323e-05,
"loss": 4.022,
"step": 864768
},
{
"epoch": 1.01,
"learning_rate": 3.583289165159271e-05,
"loss": 4.0115,
"step": 865280
},
{
"epoch": 1.01,
"learning_rate": 3.582450570408219e-05,
"loss": 4.0218,
"step": 865792
},
{
"epoch": 1.01,
"learning_rate": 3.581611975657167e-05,
"loss": 4.0092,
"step": 866304
},
{
"epoch": 1.01,
"learning_rate": 3.5807750187864884e-05,
"loss": 3.9977,
"step": 866816
},
{
"epoch": 1.01,
"learning_rate": 3.5799364240354364e-05,
"loss": 4.0057,
"step": 867328
},
{
"epoch": 1.01,
"learning_rate": 3.579099467164757e-05,
"loss": 4.0091,
"step": 867840
},
{
"epoch": 1.01,
"learning_rate": 3.578260872413705e-05,
"loss": 4.0173,
"step": 868352
},
{
"epoch": 1.01,
"learning_rate": 3.577422277662653e-05,
"loss": 4.0,
"step": 868864
},
{
"epoch": 1.01,
"learning_rate": 3.576583682911601e-05,
"loss": 4.0259,
"step": 869376
},
{
"epoch": 1.01,
"learning_rate": 3.575745088160549e-05,
"loss": 4.02,
"step": 869888
},
{
"epoch": 1.01,
"learning_rate": 3.574906493409497e-05,
"loss": 3.9936,
"step": 870400
},
{
"epoch": 1.01,
"learning_rate": 3.574069536538818e-05,
"loss": 4.0163,
"step": 870912
},
{
"epoch": 1.01,
"learning_rate": 3.573230941787766e-05,
"loss": 4.0012,
"step": 871424
},
{
"epoch": 1.01,
"learning_rate": 3.572392347036714e-05,
"loss": 3.9994,
"step": 871936
},
{
"epoch": 1.01,
"learning_rate": 3.571553752285662e-05,
"loss": 4.0107,
"step": 872448
},
{
"epoch": 1.01,
"learning_rate": 3.57071515753461e-05,
"loss": 4.0226,
"step": 872960
},
{
"epoch": 1.01,
"learning_rate": 3.569878200663932e-05,
"loss": 3.999,
"step": 873472
},
{
"epoch": 1.01,
"learning_rate": 3.56903960591288e-05,
"loss": 4.0162,
"step": 873984
},
{
"epoch": 1.01,
"learning_rate": 3.568201011161828e-05,
"loss": 3.9953,
"step": 874496
},
{
"epoch": 1.01,
"learning_rate": 3.567362416410776e-05,
"loss": 4.0128,
"step": 875008
},
{
"epoch": 1.01,
"learning_rate": 3.566523821659724e-05,
"loss": 4.0173,
"step": 875520
},
{
"epoch": 1.01,
"learning_rate": 3.565685226908672e-05,
"loss": 4.0209,
"step": 876032
},
{
"epoch": 1.01,
"learning_rate": 3.564846632157619e-05,
"loss": 4.0197,
"step": 876544
},
{
"epoch": 1.01,
"learning_rate": 3.564008037406567e-05,
"loss": 4.0211,
"step": 877056
},
{
"epoch": 1.01,
"learning_rate": 3.5631710805358886e-05,
"loss": 4.0372,
"step": 877568
},
{
"epoch": 1.01,
"learning_rate": 3.5623341236652095e-05,
"loss": 4.0157,
"step": 878080
},
{
"epoch": 1.01,
"learning_rate": 3.5614955289141575e-05,
"loss": 4.0214,
"step": 878592
},
{
"epoch": 1.01,
"learning_rate": 3.5606569341631055e-05,
"loss": 4.0059,
"step": 879104
},
{
"epoch": 1.01,
"learning_rate": 3.5598183394120535e-05,
"loss": 4.0116,
"step": 879616
},
{
"epoch": 1.01,
"learning_rate": 3.5589797446610015e-05,
"loss": 4.0094,
"step": 880128
},
{
"epoch": 1.01,
"learning_rate": 3.5581411499099495e-05,
"loss": 4.012,
"step": 880640
},
{
"epoch": 1.01,
"learning_rate": 3.5573025551588975e-05,
"loss": 4.0219,
"step": 881152
},
{
"epoch": 1.01,
"learning_rate": 3.5564639604078455e-05,
"loss": 4.0239,
"step": 881664
},
{
"epoch": 1.01,
"learning_rate": 3.5556270035371664e-05,
"loss": 4.008,
"step": 882176
},
{
"epoch": 1.01,
"learning_rate": 3.5547884087861144e-05,
"loss": 4.0077,
"step": 882688
},
{
"epoch": 1.01,
"learning_rate": 3.5539498140350624e-05,
"loss": 4.0025,
"step": 883200
},
{
"epoch": 1.01,
"learning_rate": 3.5531112192840104e-05,
"loss": 4.0237,
"step": 883712
},
{
"epoch": 1.01,
"learning_rate": 3.5522726245329584e-05,
"loss": 4.0129,
"step": 884224
},
{
"epoch": 1.01,
"learning_rate": 3.551435667662279e-05,
"loss": 4.0081,
"step": 884736
},
{
"epoch": 1.01,
"learning_rate": 3.550597072911227e-05,
"loss": 4.0159,
"step": 885248
},
{
"epoch": 1.02,
"learning_rate": 3.549758478160175e-05,
"loss": 4.0123,
"step": 885760
},
{
"epoch": 1.02,
"learning_rate": 3.548919883409124e-05,
"loss": 4.0096,
"step": 886272
},
{
"epoch": 1.02,
"learning_rate": 3.548081288658072e-05,
"loss": 4.0072,
"step": 886784
},
{
"epoch": 1.02,
"learning_rate": 3.54724269390702e-05,
"loss": 4.0202,
"step": 887296
},
{
"epoch": 1.02,
"learning_rate": 3.546404099155968e-05,
"loss": 4.0151,
"step": 887808
},
{
"epoch": 1.02,
"learning_rate": 3.545565504404916e-05,
"loss": 4.0182,
"step": 888320
},
{
"epoch": 1.02,
"learning_rate": 3.544728547534237e-05,
"loss": 4.0031,
"step": 888832
},
{
"epoch": 1.02,
"learning_rate": 3.543889952783185e-05,
"loss": 4.0066,
"step": 889344
},
{
"epoch": 1.02,
"learning_rate": 3.543051358032133e-05,
"loss": 4.0103,
"step": 889856
},
{
"epoch": 1.02,
"learning_rate": 3.542214401161454e-05,
"loss": 4.0178,
"step": 890368
},
{
"epoch": 1.02,
"learning_rate": 3.541375806410402e-05,
"loss": 4.0191,
"step": 890880
},
{
"epoch": 1.02,
"learning_rate": 3.54053721165935e-05,
"loss": 4.0121,
"step": 891392
},
{
"epoch": 1.02,
"learning_rate": 3.539698616908298e-05,
"loss": 4.0182,
"step": 891904
},
{
"epoch": 1.02,
"learning_rate": 3.538860022157246e-05,
"loss": 4.0133,
"step": 892416
},
{
"epoch": 1.02,
"learning_rate": 3.538021427406194e-05,
"loss": 4.0106,
"step": 892928
},
{
"epoch": 1.02,
"learning_rate": 3.537184470535515e-05,
"loss": 4.0002,
"step": 893440
},
{
"epoch": 1.02,
"learning_rate": 3.536345875784463e-05,
"loss": 4.0028,
"step": 893952
},
{
"epoch": 1.02,
"learning_rate": 3.535507281033411e-05,
"loss": 4.0035,
"step": 894464
},
{
"epoch": 1.02,
"learning_rate": 3.534668686282359e-05,
"loss": 4.0082,
"step": 894976
},
{
"epoch": 1.02,
"learning_rate": 3.53383172941168e-05,
"loss": 3.9993,
"step": 895488
},
{
"epoch": 1.02,
"learning_rate": 3.532993134660628e-05,
"loss": 4.0004,
"step": 896000
},
{
"epoch": 1.02,
"learning_rate": 3.532154539909576e-05,
"loss": 3.999,
"step": 896512
},
{
"epoch": 1.02,
"learning_rate": 3.531315945158524e-05,
"loss": 4.0069,
"step": 897024
},
{
"epoch": 1.02,
"learning_rate": 3.530477350407472e-05,
"loss": 4.0079,
"step": 897536
},
{
"epoch": 1.02,
"learning_rate": 3.529640393536793e-05,
"loss": 4.0082,
"step": 898048
},
{
"epoch": 1.02,
"learning_rate": 3.528801798785741e-05,
"loss": 4.0133,
"step": 898560
},
{
"epoch": 1.02,
"learning_rate": 3.527963204034689e-05,
"loss": 4.015,
"step": 899072
},
{
"epoch": 1.02,
"learning_rate": 3.527124609283637e-05,
"loss": 4.0092,
"step": 899584
},
{
"epoch": 1.02,
"learning_rate": 3.526287652412959e-05,
"loss": 4.016,
"step": 900096
},
{
"epoch": 1.02,
"learning_rate": 3.5254490576619067e-05,
"loss": 4.0096,
"step": 900608
},
{
"epoch": 1.02,
"learning_rate": 3.5246104629108547e-05,
"loss": 4.0201,
"step": 901120
},
{
"epoch": 1.02,
"learning_rate": 3.5237718681598027e-05,
"loss": 4.0118,
"step": 901632
},
{
"epoch": 1.02,
"learning_rate": 3.52293327340875e-05,
"loss": 4.0082,
"step": 902144
},
{
"epoch": 1.02,
"learning_rate": 3.522094678657698e-05,
"loss": 4.007,
"step": 902656
},
{
"epoch": 1.02,
"learning_rate": 3.521256083906646e-05,
"loss": 4.0114,
"step": 903168
},
{
"epoch": 1.02,
"learning_rate": 3.520417489155594e-05,
"loss": 4.0029,
"step": 903680
},
{
"epoch": 1.02,
"learning_rate": 3.519578894404542e-05,
"loss": 4.005,
"step": 904192
},
{
"epoch": 1.02,
"learning_rate": 3.51874029965349e-05,
"loss": 3.9948,
"step": 904704
},
{
"epoch": 1.02,
"learning_rate": 3.517903342782811e-05,
"loss": 4.0028,
"step": 905216
},
{
"epoch": 1.02,
"learning_rate": 3.5170647480317595e-05,
"loss": 4.0123,
"step": 905728
},
{
"epoch": 1.02,
"learning_rate": 3.5162261532807075e-05,
"loss": 4.0084,
"step": 906240
},
{
"epoch": 1.02,
"learning_rate": 3.5153875585296555e-05,
"loss": 4.0132,
"step": 906752
},
{
"epoch": 1.02,
"learning_rate": 3.5145489637786035e-05,
"loss": 3.995,
"step": 907264
},
{
"epoch": 1.02,
"learning_rate": 3.5137120069079244e-05,
"loss": 4.0204,
"step": 907776
},
{
"epoch": 1.02,
"learning_rate": 3.5128734121568724e-05,
"loss": 4.0161,
"step": 908288
},
{
"epoch": 1.02,
"learning_rate": 3.5120348174058204e-05,
"loss": 4.0172,
"step": 908800
},
{
"epoch": 1.02,
"learning_rate": 3.5111962226547684e-05,
"loss": 4.003,
"step": 909312
},
{
"epoch": 1.02,
"learning_rate": 3.5103576279037164e-05,
"loss": 4.0099,
"step": 909824
},
{
"epoch": 1.02,
"learning_rate": 3.509520671033037e-05,
"loss": 4.0179,
"step": 910336
},
{
"epoch": 1.02,
"learning_rate": 3.508682076281985e-05,
"loss": 4.019,
"step": 910848
},
{
"epoch": 1.02,
"learning_rate": 3.507843481530933e-05,
"loss": 4.0029,
"step": 911360
},
{
"epoch": 1.02,
"learning_rate": 3.507004886779881e-05,
"loss": 4.0044,
"step": 911872
},
{
"epoch": 1.02,
"learning_rate": 3.506166292028829e-05,
"loss": 4.0111,
"step": 912384
},
{
"epoch": 1.02,
"learning_rate": 3.505327697277778e-05,
"loss": 4.0114,
"step": 912896
},
{
"epoch": 1.02,
"learning_rate": 3.504489102526726e-05,
"loss": 4.0023,
"step": 913408
},
{
"epoch": 1.02,
"learning_rate": 3.503650507775674e-05,
"loss": 4.0072,
"step": 913920
},
{
"epoch": 1.02,
"learning_rate": 3.502813550904995e-05,
"loss": 4.0069,
"step": 914432
},
{
"epoch": 1.02,
"learning_rate": 3.501974956153943e-05,
"loss": 4.0076,
"step": 914944
},
{
"epoch": 1.02,
"learning_rate": 3.501137999283264e-05,
"loss": 4.0145,
"step": 915456
},
{
"epoch": 1.03,
"eval_loss": 4.047857761383057,
"eval_runtime": 297.363,
"eval_samples_per_second": 1283.25,
"eval_steps_per_second": 40.102,
"step": 915840
},
{
"epoch": 0.0,
"learning_rate": 3.500299404532212e-05,
"loss": 4.0043,
"step": 915968
},
{
"epoch": 0.0,
"learning_rate": 3.49946080978116e-05,
"loss": 3.9938,
"step": 916480
},
{
"epoch": 0.0,
"learning_rate": 3.498622215030108e-05,
"loss": 4.0047,
"step": 916992
},
{
"epoch": 0.0,
"learning_rate": 3.497783620279056e-05,
"loss": 4.0094,
"step": 917504
},
{
"epoch": 0.0,
"learning_rate": 3.496945025528003e-05,
"loss": 4.0058,
"step": 918016
},
{
"epoch": 0.0,
"learning_rate": 3.496106430776952e-05,
"loss": 4.0164,
"step": 918528
},
{
"epoch": 0.0,
"learning_rate": 3.4952678360259e-05,
"loss": 4.0022,
"step": 919040
},
{
"epoch": 0.0,
"learning_rate": 3.494429241274848e-05,
"loss": 4.0024,
"step": 919552
},
{
"epoch": 0.0,
"learning_rate": 3.493590646523796e-05,
"loss": 3.9937,
"step": 920064
},
{
"epoch": 0.0,
"learning_rate": 3.492752051772744e-05,
"loss": 4.0056,
"step": 920576
},
{
"epoch": 0.0,
"learning_rate": 3.491913457021692e-05,
"loss": 4.0097,
"step": 921088
},
{
"epoch": 0.0,
"learning_rate": 3.49107486227064e-05,
"loss": 4.0041,
"step": 921600
},
{
"epoch": 0.0,
"learning_rate": 3.4902379053999606e-05,
"loss": 4.0141,
"step": 922112
},
{
"epoch": 0.0,
"learning_rate": 3.4893993106489086e-05,
"loss": 3.9882,
"step": 922624
},
{
"epoch": 0.0,
"learning_rate": 3.4885607158978566e-05,
"loss": 3.9975,
"step": 923136
},
{
"epoch": 0.0,
"learning_rate": 3.4877221211468046e-05,
"loss": 3.9924,
"step": 923648
},
{
"epoch": 0.0,
"learning_rate": 3.4868835263957526e-05,
"loss": 4.0086,
"step": 924160
},
{
"epoch": 0.0,
"learning_rate": 3.4860449316447006e-05,
"loss": 4.0015,
"step": 924672
},
{
"epoch": 0.0,
"learning_rate": 3.4852063368936486e-05,
"loss": 4.0019,
"step": 925184
},
{
"epoch": 0.0,
"learning_rate": 3.4843677421425966e-05,
"loss": 3.999,
"step": 925696
},
{
"epoch": 0.0,
"learning_rate": 3.4835291473915446e-05,
"loss": 4.0217,
"step": 926208
},
{
"epoch": 0.0,
"learning_rate": 3.4826905526404926e-05,
"loss": 3.9997,
"step": 926720
},
{
"epoch": 0.0,
"learning_rate": 3.4818519578894406e-05,
"loss": 4.0123,
"step": 927232
},
{
"epoch": 0.0,
"learning_rate": 3.4810133631383886e-05,
"loss": 4.0035,
"step": 927744
},
{
"epoch": 0.0,
"learning_rate": 3.48017640626771e-05,
"loss": 4.0086,
"step": 928256
},
{
"epoch": 0.0,
"learning_rate": 3.4793378115166575e-05,
"loss": 4.0081,
"step": 928768
},
{
"epoch": 0.0,
"learning_rate": 3.478500854645979e-05,
"loss": 3.9917,
"step": 929280
},
{
"epoch": 0.0,
"learning_rate": 3.477662259894927e-05,
"loss": 4.0011,
"step": 929792
},
{
"epoch": 0.0,
"learning_rate": 3.4768236651438744e-05,
"loss": 3.9952,
"step": 930304
},
{
"epoch": 0.0,
"learning_rate": 3.4759850703928224e-05,
"loss": 3.9964,
"step": 930816
},
{
"epoch": 0.01,
"learning_rate": 3.4751464756417704e-05,
"loss": 4.0047,
"step": 931328
},
{
"epoch": 0.01,
"learning_rate": 3.474309518771092e-05,
"loss": 4.0023,
"step": 931840
},
{
"epoch": 0.01,
"learning_rate": 3.47347092402004e-05,
"loss": 4.0026,
"step": 932352
},
{
"epoch": 0.01,
"learning_rate": 3.472632329268988e-05,
"loss": 4.017,
"step": 932864
},
{
"epoch": 0.01,
"learning_rate": 3.471793734517936e-05,
"loss": 4.0016,
"step": 933376
},
{
"epoch": 0.01,
"learning_rate": 3.470955139766884e-05,
"loss": 4.0039,
"step": 933888
},
{
"epoch": 0.01,
"learning_rate": 3.470118182896205e-05,
"loss": 4.0133,
"step": 934400
},
{
"epoch": 0.01,
"learning_rate": 3.469279588145153e-05,
"loss": 3.9906,
"step": 934912
},
{
"epoch": 0.01,
"learning_rate": 3.468440993394101e-05,
"loss": 4.0001,
"step": 935424
},
{
"epoch": 0.01,
"learning_rate": 3.467602398643049e-05,
"loss": 4.0017,
"step": 935936
},
{
"epoch": 0.01,
"learning_rate": 3.466763803891997e-05,
"loss": 3.9976,
"step": 936448
},
{
"epoch": 0.01,
"learning_rate": 3.465926847021318e-05,
"loss": 4.0058,
"step": 936960
},
{
"epoch": 0.01,
"learning_rate": 3.465088252270266e-05,
"loss": 4.0064,
"step": 937472
},
{
"epoch": 0.01,
"learning_rate": 3.464249657519214e-05,
"loss": 3.9983,
"step": 937984
},
{
"epoch": 0.01,
"learning_rate": 3.463411062768162e-05,
"loss": 4.0075,
"step": 938496
},
{
"epoch": 0.01,
"learning_rate": 3.462574105897483e-05,
"loss": 4.0036,
"step": 939008
},
{
"epoch": 0.01,
"learning_rate": 3.461735511146431e-05,
"loss": 4.0004,
"step": 939520
},
{
"epoch": 0.01,
"learning_rate": 3.460896916395379e-05,
"loss": 4.0061,
"step": 940032
},
{
"epoch": 0.01,
"learning_rate": 3.460058321644327e-05,
"loss": 3.9754,
"step": 940544
},
{
"epoch": 0.01,
"learning_rate": 3.459219726893275e-05,
"loss": 4.0006,
"step": 941056
},
{
"epoch": 0.01,
"learning_rate": 3.458382770022596e-05,
"loss": 4.0008,
"step": 941568
},
{
"epoch": 0.01,
"learning_rate": 3.457544175271544e-05,
"loss": 4.0057,
"step": 942080
},
{
"epoch": 0.01,
"learning_rate": 3.456705580520492e-05,
"loss": 3.9909,
"step": 942592
},
{
"epoch": 0.01,
"learning_rate": 3.45586698576944e-05,
"loss": 3.9825,
"step": 943104
},
{
"epoch": 0.01,
"learning_rate": 3.455028391018388e-05,
"loss": 3.9861,
"step": 943616
},
{
"epoch": 0.01,
"learning_rate": 3.454191434147709e-05,
"loss": 3.989,
"step": 944128
},
{
"epoch": 0.01,
"learning_rate": 3.453352839396657e-05,
"loss": 4.0067,
"step": 944640
},
{
"epoch": 0.01,
"learning_rate": 3.452514244645606e-05,
"loss": 3.9791,
"step": 945152
},
{
"epoch": 0.01,
"learning_rate": 3.451675649894554e-05,
"loss": 4.0098,
"step": 945664
},
{
"epoch": 0.01,
"learning_rate": 3.450837055143502e-05,
"loss": 4.0012,
"step": 946176
},
{
"epoch": 0.01,
"learning_rate": 3.44999846039245e-05,
"loss": 3.9798,
"step": 946688
},
{
"epoch": 0.01,
"learning_rate": 3.449161503521771e-05,
"loss": 3.9998,
"step": 947200
},
{
"epoch": 0.01,
"learning_rate": 3.448322908770719e-05,
"loss": 3.9832,
"step": 947712
},
{
"epoch": 0.01,
"learning_rate": 3.447484314019667e-05,
"loss": 3.9852,
"step": 948224
},
{
"epoch": 0.01,
"learning_rate": 3.446645719268615e-05,
"loss": 3.9895,
"step": 948736
},
{
"epoch": 0.01,
"learning_rate": 3.4458071245175627e-05,
"loss": 4.0047,
"step": 949248
},
{
"epoch": 0.01,
"learning_rate": 3.4449685297665107e-05,
"loss": 3.988,
"step": 949760
},
{
"epoch": 0.01,
"learning_rate": 3.4441315728958316e-05,
"loss": 4.0001,
"step": 950272
},
{
"epoch": 0.01,
"learning_rate": 3.4432929781447796e-05,
"loss": 3.9757,
"step": 950784
},
{
"epoch": 0.01,
"learning_rate": 3.4424543833937276e-05,
"loss": 3.995,
"step": 951296
},
{
"epoch": 0.01,
"learning_rate": 3.4416157886426756e-05,
"loss": 4.0014,
"step": 951808
},
{
"epoch": 0.01,
"learning_rate": 3.4407771938916235e-05,
"loss": 4.0042,
"step": 952320
},
{
"epoch": 0.01,
"learning_rate": 3.4399385991405715e-05,
"loss": 4.0033,
"step": 952832
},
{
"epoch": 0.01,
"learning_rate": 3.4391000043895195e-05,
"loss": 4.0056,
"step": 953344
},
{
"epoch": 0.01,
"learning_rate": 3.4382614096384675e-05,
"loss": 4.0166,
"step": 953856
},
{
"epoch": 0.01,
"learning_rate": 3.4374244527677884e-05,
"loss": 4.0017,
"step": 954368
},
{
"epoch": 0.01,
"learning_rate": 3.4365858580167364e-05,
"loss": 4.0046,
"step": 954880
},
{
"epoch": 0.01,
"learning_rate": 3.4357472632656844e-05,
"loss": 3.9888,
"step": 955392
},
{
"epoch": 0.01,
"learning_rate": 3.4349086685146324e-05,
"loss": 3.9941,
"step": 955904
},
{
"epoch": 0.01,
"learning_rate": 3.4340717116439533e-05,
"loss": 3.9924,
"step": 956416
},
{
"epoch": 0.01,
"learning_rate": 3.433233116892901e-05,
"loss": 3.995,
"step": 956928
},
{
"epoch": 0.01,
"learning_rate": 3.432394522141849e-05,
"loss": 4.0054,
"step": 957440
},
{
"epoch": 0.01,
"learning_rate": 3.431557565271171e-05,
"loss": 4.0091,
"step": 957952
},
{
"epoch": 0.01,
"learning_rate": 3.430718970520119e-05,
"loss": 3.997,
"step": 958464
},
{
"epoch": 0.01,
"learning_rate": 3.429880375769067e-05,
"loss": 3.9872,
"step": 958976
},
{
"epoch": 0.01,
"learning_rate": 3.429041781018015e-05,
"loss": 3.9886,
"step": 959488
},
{
"epoch": 0.01,
"learning_rate": 3.428203186266963e-05,
"loss": 4.0054,
"step": 960000
},
{
"epoch": 0.01,
"learning_rate": 3.427366229396284e-05,
"loss": 3.9958,
"step": 960512
},
{
"epoch": 0.01,
"learning_rate": 3.426527634645232e-05,
"loss": 3.9925,
"step": 961024
},
{
"epoch": 0.01,
"learning_rate": 3.42568903989418e-05,
"loss": 3.999,
"step": 961536
},
{
"epoch": 0.02,
"learning_rate": 3.424850445143128e-05,
"loss": 3.9966,
"step": 962048
},
{
"epoch": 0.02,
"learning_rate": 3.424013488272449e-05,
"loss": 3.9927,
"step": 962560
},
{
"epoch": 0.02,
"learning_rate": 3.423174893521397e-05,
"loss": 3.9897,
"step": 963072
},
{
"epoch": 0.02,
"learning_rate": 3.422336298770345e-05,
"loss": 4.0027,
"step": 963584
},
{
"epoch": 0.02,
"learning_rate": 3.4214977040192934e-05,
"loss": 4.0037,
"step": 964096
},
{
"epoch": 0.02,
"learning_rate": 3.4206591092682414e-05,
"loss": 4.0017,
"step": 964608
},
{
"epoch": 0.02,
"learning_rate": 3.4198205145171894e-05,
"loss": 3.987,
"step": 965120
},
{
"epoch": 0.02,
"learning_rate": 3.4189819197661374e-05,
"loss": 3.9926,
"step": 965632
},
{
"epoch": 0.02,
"learning_rate": 3.4181433250150854e-05,
"loss": 3.9951,
"step": 966144
},
{
"epoch": 0.02,
"learning_rate": 3.417306368144406e-05,
"loss": 3.9998,
"step": 966656
},
{
"epoch": 0.02,
"learning_rate": 3.416467773393354e-05,
"loss": 4.0039,
"step": 967168
},
{
"epoch": 0.02,
"learning_rate": 3.415630816522675e-05,
"loss": 3.9937,
"step": 967680
},
{
"epoch": 0.02,
"learning_rate": 3.414792221771623e-05,
"loss": 4.0017,
"step": 968192
},
{
"epoch": 0.02,
"learning_rate": 3.413953627020571e-05,
"loss": 3.9974,
"step": 968704
},
{
"epoch": 0.02,
"learning_rate": 3.413115032269519e-05,
"loss": 3.9952,
"step": 969216
},
{
"epoch": 0.02,
"learning_rate": 3.41227807539884e-05,
"loss": 3.9854,
"step": 969728
},
{
"epoch": 0.02,
"learning_rate": 3.411439480647789e-05,
"loss": 3.9873,
"step": 970240
},
{
"epoch": 0.02,
"learning_rate": 3.410600885896737e-05,
"loss": 3.9899,
"step": 970752
},
{
"epoch": 0.02,
"learning_rate": 3.409762291145685e-05,
"loss": 3.9924,
"step": 971264
},
{
"epoch": 0.02,
"learning_rate": 3.408923696394633e-05,
"loss": 3.9826,
"step": 971776
},
{
"epoch": 0.02,
"learning_rate": 3.408085101643581e-05,
"loss": 3.9874,
"step": 972288
},
{
"epoch": 0.02,
"learning_rate": 3.407246506892529e-05,
"loss": 3.9781,
"step": 972800
},
{
"epoch": 0.02,
"learning_rate": 3.406407912141477e-05,
"loss": 3.9961,
"step": 973312
},
{
"epoch": 0.02,
"learning_rate": 3.405569317390424e-05,
"loss": 3.9924,
"step": 973824
},
{
"epoch": 0.02,
"learning_rate": 3.404730722639372e-05,
"loss": 3.9938,
"step": 974336
},
{
"epoch": 0.02,
"learning_rate": 3.40389212788832e-05,
"loss": 3.9943,
"step": 974848
},
{
"epoch": 0.02,
"learning_rate": 3.403053533137268e-05,
"loss": 3.9981,
"step": 975360
},
{
"epoch": 0.02,
"learning_rate": 3.402216576266589e-05,
"loss": 3.9939,
"step": 975872
},
{
"epoch": 0.02,
"learning_rate": 3.401377981515537e-05,
"loss": 3.9945,
"step": 976384
},
{
"epoch": 0.02,
"learning_rate": 3.400539386764485e-05,
"loss": 3.9978,
"step": 976896
},
{
"epoch": 0.02,
"learning_rate": 3.3997007920134336e-05,
"loss": 4.0013,
"step": 977408
},
{
"epoch": 0.02,
"learning_rate": 3.3988638351427545e-05,
"loss": 3.9964,
"step": 977920
},
{
"epoch": 0.02,
"learning_rate": 3.3980252403917025e-05,
"loss": 3.9948,
"step": 978432
},
{
"epoch": 0.02,
"learning_rate": 3.3971866456406505e-05,
"loss": 3.9928,
"step": 978944
},
{
"epoch": 0.02,
"learning_rate": 3.3963480508895985e-05,
"loss": 3.9925,
"step": 979456
},
{
"epoch": 0.02,
"learning_rate": 3.395512731899293e-05,
"loss": 3.9868,
"step": 979968
},
{
"epoch": 0.02,
"learning_rate": 3.394674137148241e-05,
"loss": 3.9894,
"step": 980480
},
{
"epoch": 0.02,
"learning_rate": 3.393835542397189e-05,
"loss": 3.9774,
"step": 980992
},
{
"epoch": 0.02,
"learning_rate": 3.392996947646136e-05,
"loss": 3.9901,
"step": 981504
},
{
"epoch": 0.02,
"learning_rate": 3.392158352895084e-05,
"loss": 3.9929,
"step": 982016
},
{
"epoch": 0.02,
"learning_rate": 3.391319758144032e-05,
"loss": 3.9957,
"step": 982528
},
{
"epoch": 0.02,
"learning_rate": 3.390482801273354e-05,
"loss": 3.9935,
"step": 983040
},
{
"epoch": 0.02,
"learning_rate": 3.389644206522302e-05,
"loss": 3.9861,
"step": 983552
},
{
"epoch": 0.02,
"learning_rate": 3.38880561177125e-05,
"loss": 3.9996,
"step": 984064
},
{
"epoch": 0.02,
"learning_rate": 3.387967017020198e-05,
"loss": 3.9997,
"step": 984576
},
{
"epoch": 0.02,
"learning_rate": 3.387130060149519e-05,
"loss": 3.9957,
"step": 985088
},
{
"epoch": 0.02,
"learning_rate": 3.386291465398467e-05,
"loss": 3.9916,
"step": 985600
},
{
"epoch": 0.02,
"learning_rate": 3.385452870647415e-05,
"loss": 3.995,
"step": 986112
},
{
"epoch": 0.02,
"learning_rate": 3.384614275896363e-05,
"loss": 4.0032,
"step": 986624
},
{
"epoch": 0.02,
"learning_rate": 3.383775681145311e-05,
"loss": 3.9999,
"step": 987136
},
{
"epoch": 0.02,
"learning_rate": 3.382937086394259e-05,
"loss": 3.9894,
"step": 987648
},
{
"epoch": 0.02,
"learning_rate": 3.382098491643207e-05,
"loss": 3.9884,
"step": 988160
},
{
"epoch": 0.02,
"learning_rate": 3.381259896892155e-05,
"loss": 3.9952,
"step": 988672
},
{
"epoch": 0.02,
"learning_rate": 3.380421302141103e-05,
"loss": 3.9929,
"step": 989184
},
{
"epoch": 0.02,
"learning_rate": 3.379582707390051e-05,
"loss": 3.9884,
"step": 989696
},
{
"epoch": 0.02,
"learning_rate": 3.378744112638999e-05,
"loss": 3.9907,
"step": 990208
},
{
"epoch": 0.02,
"learning_rate": 3.3779055178879474e-05,
"loss": 3.9908,
"step": 990720
},
{
"epoch": 0.02,
"learning_rate": 3.377068561017268e-05,
"loss": 3.9941,
"step": 991232
},
{
"epoch": 0.02,
"learning_rate": 3.376229966266216e-05,
"loss": 3.9977,
"step": 991744
},
{
"epoch": 0.03,
"eval_loss": 4.038654804229736,
"eval_runtime": 296.7732,
"eval_samples_per_second": 1285.8,
"eval_steps_per_second": 40.182,
"step": 992160
},
{
"epoch": 1.0,
"learning_rate": 3.375391371515164e-05,
"loss": 3.9896,
"step": 992256
},
{
"epoch": 1.0,
"learning_rate": 3.374552776764112e-05,
"loss": 3.977,
"step": 992768
},
{
"epoch": 1.0,
"learning_rate": 3.373715819893433e-05,
"loss": 3.9846,
"step": 993280
},
{
"epoch": 1.0,
"learning_rate": 3.372877225142381e-05,
"loss": 3.998,
"step": 993792
},
{
"epoch": 1.0,
"learning_rate": 3.372038630391329e-05,
"loss": 3.9927,
"step": 994304
},
{
"epoch": 1.0,
"learning_rate": 3.371200035640277e-05,
"loss": 3.9996,
"step": 994816
},
{
"epoch": 1.0,
"learning_rate": 3.370363078769598e-05,
"loss": 3.9832,
"step": 995328
},
{
"epoch": 1.0,
"learning_rate": 3.369524484018546e-05,
"loss": 3.9887,
"step": 995840
},
{
"epoch": 1.0,
"learning_rate": 3.368687527147868e-05,
"loss": 3.9773,
"step": 996352
},
{
"epoch": 1.0,
"learning_rate": 3.367848932396816e-05,
"loss": 3.994,
"step": 996864
},
{
"epoch": 1.0,
"learning_rate": 3.367010337645764e-05,
"loss": 3.9899,
"step": 997376
},
{
"epoch": 1.0,
"learning_rate": 3.366171742894712e-05,
"loss": 3.992,
"step": 997888
},
{
"epoch": 1.0,
"learning_rate": 3.3653347860240326e-05,
"loss": 3.9986,
"step": 998400
},
{
"epoch": 1.0,
"learning_rate": 3.3644961912729806e-05,
"loss": 3.9723,
"step": 998912
},
{
"epoch": 1.0,
"learning_rate": 3.3636575965219286e-05,
"loss": 3.9871,
"step": 999424
},
{
"epoch": 1.0,
"learning_rate": 3.3628190017708766e-05,
"loss": 3.9746,
"step": 999936
},
{
"epoch": 1.0,
"learning_rate": 3.3619804070198246e-05,
"loss": 3.992,
"step": 1000448
},
{
"epoch": 1.0,
"learning_rate": 3.3611418122687726e-05,
"loss": 3.9833,
"step": 1000960
},
{
"epoch": 1.0,
"learning_rate": 3.3603048553980935e-05,
"loss": 3.9907,
"step": 1001472
},
{
"epoch": 1.0,
"learning_rate": 3.3594662606470415e-05,
"loss": 3.9823,
"step": 1001984
},
{
"epoch": 1.0,
"learning_rate": 3.3586276658959895e-05,
"loss": 4.0052,
"step": 1002496
},
{
"epoch": 1.0,
"learning_rate": 3.3577890711449375e-05,
"loss": 3.9872,
"step": 1003008
},
{
"epoch": 1.0,
"learning_rate": 3.3569504763938855e-05,
"loss": 3.9936,
"step": 1003520
},
{
"epoch": 1.0,
"learning_rate": 3.3561118816428334e-05,
"loss": 3.9906,
"step": 1004032
},
{
"epoch": 1.0,
"learning_rate": 3.3552732868917814e-05,
"loss": 3.9933,
"step": 1004544
},
{
"epoch": 1.0,
"learning_rate": 3.3544363300211024e-05,
"loss": 3.9896,
"step": 1005056
},
{
"epoch": 1.0,
"learning_rate": 3.3535977352700503e-05,
"loss": 3.979,
"step": 1005568
},
{
"epoch": 1.0,
"learning_rate": 3.3527591405189983e-05,
"loss": 3.9894,
"step": 1006080
},
{
"epoch": 1.0,
"learning_rate": 3.3519205457679463e-05,
"loss": 3.9787,
"step": 1006592
},
{
"epoch": 1.0,
"learning_rate": 3.351083588897267e-05,
"loss": 3.9808,
"step": 1007104
},
{
"epoch": 1.01,
"learning_rate": 3.350244994146215e-05,
"loss": 3.986,
"step": 1007616
},
{
"epoch": 1.01,
"learning_rate": 3.349406399395163e-05,
"loss": 3.9832,
"step": 1008128
},
{
"epoch": 1.01,
"learning_rate": 3.348567804644111e-05,
"loss": 3.9881,
"step": 1008640
},
{
"epoch": 1.01,
"learning_rate": 3.34772920989306e-05,
"loss": 4.0004,
"step": 1009152
},
{
"epoch": 1.01,
"learning_rate": 3.346890615142008e-05,
"loss": 3.9878,
"step": 1009664
},
{
"epoch": 1.01,
"learning_rate": 3.346053658271329e-05,
"loss": 3.9928,
"step": 1010176
},
{
"epoch": 1.01,
"learning_rate": 3.345215063520277e-05,
"loss": 3.9941,
"step": 1010688
},
{
"epoch": 1.01,
"learning_rate": 3.344376468769225e-05,
"loss": 3.9777,
"step": 1011200
},
{
"epoch": 1.01,
"learning_rate": 3.343537874018173e-05,
"loss": 3.9906,
"step": 1011712
},
{
"epoch": 1.01,
"learning_rate": 3.342699279267121e-05,
"loss": 3.9832,
"step": 1012224
},
{
"epoch": 1.01,
"learning_rate": 3.341862322396442e-05,
"loss": 3.9808,
"step": 1012736
},
{
"epoch": 1.01,
"learning_rate": 3.34102372764539e-05,
"loss": 3.9911,
"step": 1013248
},
{
"epoch": 1.01,
"learning_rate": 3.3401867707747106e-05,
"loss": 3.9928,
"step": 1013760
},
{
"epoch": 1.01,
"learning_rate": 3.3393481760236586e-05,
"loss": 3.9787,
"step": 1014272
},
{
"epoch": 1.01,
"learning_rate": 3.3385095812726066e-05,
"loss": 3.9923,
"step": 1014784
},
{
"epoch": 1.01,
"learning_rate": 3.337670986521555e-05,
"loss": 3.9908,
"step": 1015296
},
{
"epoch": 1.01,
"learning_rate": 3.336832391770503e-05,
"loss": 3.9842,
"step": 1015808
},
{
"epoch": 1.01,
"learning_rate": 3.335993797019451e-05,
"loss": 3.9925,
"step": 1016320
},
{
"epoch": 1.01,
"learning_rate": 3.335155202268399e-05,
"loss": 3.9594,
"step": 1016832
},
{
"epoch": 1.01,
"learning_rate": 3.334316607517347e-05,
"loss": 3.9857,
"step": 1017344
},
{
"epoch": 1.01,
"learning_rate": 3.333478012766295e-05,
"loss": 3.9844,
"step": 1017856
},
{
"epoch": 1.01,
"learning_rate": 3.332639418015243e-05,
"loss": 3.9898,
"step": 1018368
},
{
"epoch": 1.01,
"learning_rate": 3.331800823264191e-05,
"loss": 3.9779,
"step": 1018880
},
{
"epoch": 1.01,
"learning_rate": 3.3309622285131386e-05,
"loss": 3.9688,
"step": 1019392
},
{
"epoch": 1.01,
"learning_rate": 3.33012527164246e-05,
"loss": 3.9694,
"step": 1019904
},
{
"epoch": 1.01,
"learning_rate": 3.329289952652154e-05,
"loss": 3.9724,
"step": 1020416
},
{
"epoch": 1.01,
"learning_rate": 3.328451357901102e-05,
"loss": 3.9929,
"step": 1020928
},
{
"epoch": 1.01,
"learning_rate": 3.3276127631500506e-05,
"loss": 3.9681,
"step": 1021440
},
{
"epoch": 1.01,
"learning_rate": 3.3267741683989986e-05,
"loss": 3.9918,
"step": 1021952
},
{
"epoch": 1.01,
"learning_rate": 3.3259355736479466e-05,
"loss": 3.9831,
"step": 1022464
},
{
"epoch": 1.01,
"learning_rate": 3.3250969788968946e-05,
"loss": 3.9719,
"step": 1022976
},
{
"epoch": 1.01,
"learning_rate": 3.3242583841458426e-05,
"loss": 3.9822,
"step": 1023488
},
{
"epoch": 1.01,
"learning_rate": 3.3234197893947906e-05,
"loss": 3.9696,
"step": 1024000
},
{
"epoch": 1.01,
"learning_rate": 3.3225811946437386e-05,
"loss": 3.9706,
"step": 1024512
},
{
"epoch": 1.01,
"learning_rate": 3.321742599892686e-05,
"loss": 3.9743,
"step": 1025024
},
{
"epoch": 1.01,
"learning_rate": 3.320904005141634e-05,
"loss": 3.9901,
"step": 1025536
},
{
"epoch": 1.01,
"learning_rate": 3.320065410390582e-05,
"loss": 3.9745,
"step": 1026048
},
{
"epoch": 1.01,
"learning_rate": 3.319228453519903e-05,
"loss": 3.9772,
"step": 1026560
},
{
"epoch": 1.01,
"learning_rate": 3.318389858768851e-05,
"loss": 3.9673,
"step": 1027072
},
{
"epoch": 1.01,
"learning_rate": 3.317551264017799e-05,
"loss": 3.9775,
"step": 1027584
},
{
"epoch": 1.01,
"learning_rate": 3.3167143071471204e-05,
"loss": 3.989,
"step": 1028096
},
{
"epoch": 1.01,
"learning_rate": 3.3158757123960684e-05,
"loss": 3.9889,
"step": 1028608
},
{
"epoch": 1.01,
"learning_rate": 3.3150371176450164e-05,
"loss": 3.9878,
"step": 1029120
},
{
"epoch": 1.01,
"learning_rate": 3.3141985228939644e-05,
"loss": 3.9888,
"step": 1029632
},
{
"epoch": 1.01,
"learning_rate": 3.3133599281429124e-05,
"loss": 4.0015,
"step": 1030144
},
{
"epoch": 1.01,
"learning_rate": 3.312522971272233e-05,
"loss": 3.9877,
"step": 1030656
},
{
"epoch": 1.01,
"learning_rate": 3.311684376521181e-05,
"loss": 3.9918,
"step": 1031168
},
{
"epoch": 1.01,
"learning_rate": 3.310845781770129e-05,
"loss": 3.9784,
"step": 1031680
},
{
"epoch": 1.01,
"learning_rate": 3.310007187019077e-05,
"loss": 3.9825,
"step": 1032192
},
{
"epoch": 1.01,
"learning_rate": 3.309170230148398e-05,
"loss": 3.9775,
"step": 1032704
},
{
"epoch": 1.01,
"learning_rate": 3.308331635397346e-05,
"loss": 3.9782,
"step": 1033216
},
{
"epoch": 1.01,
"learning_rate": 3.307493040646294e-05,
"loss": 3.9903,
"step": 1033728
},
{
"epoch": 1.01,
"learning_rate": 3.306654445895243e-05,
"loss": 3.993,
"step": 1034240
},
{
"epoch": 1.01,
"learning_rate": 3.305817489024564e-05,
"loss": 3.9889,
"step": 1034752
},
{
"epoch": 1.01,
"learning_rate": 3.304978894273512e-05,
"loss": 3.968,
"step": 1035264
},
{
"epoch": 1.01,
"learning_rate": 3.30414029952246e-05,
"loss": 3.9737,
"step": 1035776
},
{
"epoch": 1.01,
"learning_rate": 3.303301704771408e-05,
"loss": 3.9886,
"step": 1036288
},
{
"epoch": 1.01,
"learning_rate": 3.302463110020356e-05,
"loss": 3.9836,
"step": 1036800
},
{
"epoch": 1.01,
"learning_rate": 3.301624515269304e-05,
"loss": 3.9791,
"step": 1037312
},
{
"epoch": 1.01,
"learning_rate": 3.300787558398625e-05,
"loss": 3.9814,
"step": 1037824
},
{
"epoch": 1.02,
"learning_rate": 3.2999489636475727e-05,
"loss": 3.9836,
"step": 1038336
},
{
"epoch": 1.02,
"learning_rate": 3.2991103688965207e-05,
"loss": 3.9795,
"step": 1038848
},
{
"epoch": 1.02,
"learning_rate": 3.2982717741454686e-05,
"loss": 3.9788,
"step": 1039360
},
{
"epoch": 1.02,
"learning_rate": 3.2974331793944166e-05,
"loss": 3.9905,
"step": 1039872
},
{
"epoch": 1.02,
"learning_rate": 3.2965945846433646e-05,
"loss": 3.984,
"step": 1040384
},
{
"epoch": 1.02,
"learning_rate": 3.295757627772686e-05,
"loss": 3.9874,
"step": 1040896
},
{
"epoch": 1.02,
"learning_rate": 3.294919033021634e-05,
"loss": 3.9702,
"step": 1041408
},
{
"epoch": 1.02,
"learning_rate": 3.294080438270582e-05,
"loss": 3.9751,
"step": 1041920
},
{
"epoch": 1.02,
"learning_rate": 3.29324184351953e-05,
"loss": 3.9833,
"step": 1042432
},
{
"epoch": 1.02,
"learning_rate": 3.292404886648851e-05,
"loss": 3.9852,
"step": 1042944
},
{
"epoch": 1.02,
"learning_rate": 3.291566291897799e-05,
"loss": 3.9896,
"step": 1043456
},
{
"epoch": 1.02,
"learning_rate": 3.290727697146747e-05,
"loss": 3.9815,
"step": 1043968
},
{
"epoch": 1.02,
"learning_rate": 3.289889102395695e-05,
"loss": 3.9844,
"step": 1044480
},
{
"epoch": 1.02,
"learning_rate": 3.289052145525016e-05,
"loss": 3.9798,
"step": 1044992
},
{
"epoch": 1.02,
"learning_rate": 3.288213550773964e-05,
"loss": 3.982,
"step": 1045504
},
{
"epoch": 1.02,
"learning_rate": 3.287374956022912e-05,
"loss": 3.9718,
"step": 1046016
},
{
"epoch": 1.02,
"learning_rate": 3.28653636127186e-05,
"loss": 3.9706,
"step": 1046528
},
{
"epoch": 1.02,
"learning_rate": 3.2856994044011816e-05,
"loss": 3.9793,
"step": 1047040
},
{
"epoch": 1.02,
"learning_rate": 3.2848608096501296e-05,
"loss": 3.9786,
"step": 1047552
},
{
"epoch": 1.02,
"learning_rate": 3.2840222148990776e-05,
"loss": 3.9694,
"step": 1048064
},
{
"epoch": 1.02,
"learning_rate": 3.2831836201480256e-05,
"loss": 3.9702,
"step": 1048576
},
{
"epoch": 1.02,
"learning_rate": 3.2823466632773465e-05,
"loss": 3.9664,
"step": 1049088
},
{
"epoch": 1.02,
"learning_rate": 3.2815080685262945e-05,
"loss": 3.9755,
"step": 1049600
},
{
"epoch": 1.02,
"learning_rate": 3.2806694737752425e-05,
"loss": 3.9794,
"step": 1050112
},
{
"epoch": 1.02,
"learning_rate": 3.2798308790241905e-05,
"loss": 3.9762,
"step": 1050624
},
{
"epoch": 1.02,
"learning_rate": 3.2789922842731385e-05,
"loss": 3.9791,
"step": 1051136
},
{
"epoch": 1.02,
"learning_rate": 3.2781536895220865e-05,
"loss": 3.9873,
"step": 1051648
},
{
"epoch": 1.02,
"learning_rate": 3.277315094771034e-05,
"loss": 3.9788,
"step": 1052160
},
{
"epoch": 1.02,
"learning_rate": 3.2764781379003554e-05,
"loss": 3.98,
"step": 1052672
},
{
"epoch": 1.02,
"learning_rate": 3.2756395431493034e-05,
"loss": 3.987,
"step": 1053184
},
{
"epoch": 1.02,
"learning_rate": 3.2748009483982514e-05,
"loss": 3.9856,
"step": 1053696
},
{
"epoch": 1.02,
"learning_rate": 3.273963991527573e-05,
"loss": 3.9796,
"step": 1054208
},
{
"epoch": 1.02,
"learning_rate": 3.273125396776521e-05,
"loss": 3.9844,
"step": 1054720
},
{
"epoch": 1.02,
"learning_rate": 3.272286802025469e-05,
"loss": 3.9799,
"step": 1055232
},
{
"epoch": 1.02,
"learning_rate": 3.271448207274416e-05,
"loss": 3.9749,
"step": 1055744
},
{
"epoch": 1.02,
"learning_rate": 3.270609612523364e-05,
"loss": 3.9683,
"step": 1056256
},
{
"epoch": 1.02,
"learning_rate": 3.269771017772312e-05,
"loss": 3.981,
"step": 1056768
},
{
"epoch": 1.02,
"learning_rate": 3.26893242302126e-05,
"loss": 3.9713,
"step": 1057280
},
{
"epoch": 1.02,
"learning_rate": 3.268093828270208e-05,
"loss": 3.9768,
"step": 1057792
},
{
"epoch": 1.02,
"learning_rate": 3.267256871399529e-05,
"loss": 3.9701,
"step": 1058304
},
{
"epoch": 1.02,
"learning_rate": 3.266418276648477e-05,
"loss": 3.9834,
"step": 1058816
},
{
"epoch": 1.02,
"learning_rate": 3.265579681897425e-05,
"loss": 3.9783,
"step": 1059328
},
{
"epoch": 1.02,
"learning_rate": 3.264741087146374e-05,
"loss": 3.9702,
"step": 1059840
},
{
"epoch": 1.02,
"learning_rate": 3.263902492395322e-05,
"loss": 3.9853,
"step": 1060352
},
{
"epoch": 1.02,
"learning_rate": 3.26306389764427e-05,
"loss": 3.9853,
"step": 1060864
},
{
"epoch": 1.02,
"learning_rate": 3.262225302893218e-05,
"loss": 3.9855,
"step": 1061376
},
{
"epoch": 1.02,
"learning_rate": 3.261388346022539e-05,
"loss": 3.9803,
"step": 1061888
},
{
"epoch": 1.02,
"learning_rate": 3.260549751271487e-05,
"loss": 3.9757,
"step": 1062400
},
{
"epoch": 1.02,
"learning_rate": 3.259711156520435e-05,
"loss": 3.9917,
"step": 1062912
},
{
"epoch": 1.02,
"learning_rate": 3.258872561769383e-05,
"loss": 3.9781,
"step": 1063424
},
{
"epoch": 1.02,
"learning_rate": 3.258033967018331e-05,
"loss": 3.982,
"step": 1063936
},
{
"epoch": 1.02,
"learning_rate": 3.257195372267279e-05,
"loss": 3.972,
"step": 1064448
},
{
"epoch": 1.02,
"learning_rate": 3.2563584153965996e-05,
"loss": 3.9798,
"step": 1064960
},
{
"epoch": 1.02,
"learning_rate": 3.2555198206455476e-05,
"loss": 3.9761,
"step": 1065472
},
{
"epoch": 1.02,
"learning_rate": 3.2546812258944956e-05,
"loss": 3.9752,
"step": 1065984
},
{
"epoch": 1.02,
"learning_rate": 3.2538426311434436e-05,
"loss": 3.9797,
"step": 1066496
},
{
"epoch": 1.02,
"learning_rate": 3.253004036392392e-05,
"loss": 3.9777,
"step": 1067008
},
{
"epoch": 1.02,
"learning_rate": 3.25216544164134e-05,
"loss": 3.981,
"step": 1067520
},
{
"epoch": 1.02,
"learning_rate": 3.251328484770661e-05,
"loss": 3.9796,
"step": 1068032
},
{
"epoch": 1.03,
"eval_loss": 4.03078031539917,
"eval_runtime": 299.8455,
"eval_samples_per_second": 1272.625,
"eval_steps_per_second": 39.77,
"step": 1068480
},
{
"epoch": 0.0,
"learning_rate": 3.250489890019609e-05,
"loss": 3.9645,
"step": 1068544
},
{
"epoch": 0.0,
"learning_rate": 3.249651295268557e-05,
"loss": 3.9671,
"step": 1069056
},
{
"epoch": 0.0,
"learning_rate": 3.248812700517505e-05,
"loss": 3.9692,
"step": 1069568
},
{
"epoch": 0.0,
"learning_rate": 3.2479741057664525e-05,
"loss": 3.9839,
"step": 1070080
},
{
"epoch": 0.0,
"learning_rate": 3.2471355110154005e-05,
"loss": 3.9788,
"step": 1070592
},
{
"epoch": 0.0,
"learning_rate": 3.2462969162643485e-05,
"loss": 3.9879,
"step": 1071104
},
{
"epoch": 0.0,
"learning_rate": 3.2454583215132965e-05,
"loss": 3.9697,
"step": 1071616
},
{
"epoch": 0.0,
"learning_rate": 3.2446197267622445e-05,
"loss": 3.9745,
"step": 1072128
},
{
"epoch": 0.0,
"learning_rate": 3.2437811320111924e-05,
"loss": 3.966,
"step": 1072640
},
{
"epoch": 0.0,
"learning_rate": 3.2429425372601404e-05,
"loss": 3.9774,
"step": 1073152
},
{
"epoch": 0.0,
"learning_rate": 3.2421039425090884e-05,
"loss": 3.9769,
"step": 1073664
},
{
"epoch": 0.0,
"learning_rate": 3.241265347758037e-05,
"loss": 3.9763,
"step": 1074176
},
{
"epoch": 0.0,
"learning_rate": 3.240428390887358e-05,
"loss": 3.9821,
"step": 1074688
},
{
"epoch": 0.0,
"learning_rate": 3.239589796136306e-05,
"loss": 3.9626,
"step": 1075200
},
{
"epoch": 0.0,
"learning_rate": 3.238751201385254e-05,
"loss": 3.9683,
"step": 1075712
},
{
"epoch": 0.0,
"learning_rate": 3.237912606634202e-05,
"loss": 3.9644,
"step": 1076224
},
{
"epoch": 0.0,
"learning_rate": 3.23707401188315e-05,
"loss": 3.9786,
"step": 1076736
},
{
"epoch": 0.0,
"learning_rate": 3.236235417132098e-05,
"loss": 3.9693,
"step": 1077248
},
{
"epoch": 0.0,
"learning_rate": 3.235396822381046e-05,
"loss": 3.9783,
"step": 1077760
},
{
"epoch": 0.0,
"learning_rate": 3.234558227629994e-05,
"loss": 3.9671,
"step": 1078272
},
{
"epoch": 0.0,
"learning_rate": 3.233719632878941e-05,
"loss": 3.9903,
"step": 1078784
},
{
"epoch": 0.0,
"learning_rate": 3.232882676008263e-05,
"loss": 3.9745,
"step": 1079296
},
{
"epoch": 0.0,
"learning_rate": 3.232044081257211e-05,
"loss": 3.9769,
"step": 1079808
},
{
"epoch": 0.0,
"learning_rate": 3.231205486506159e-05,
"loss": 3.9761,
"step": 1080320
},
{
"epoch": 0.0,
"learning_rate": 3.230366891755107e-05,
"loss": 3.9815,
"step": 1080832
},
{
"epoch": 0.0,
"learning_rate": 3.229528297004055e-05,
"loss": 3.9764,
"step": 1081344
},
{
"epoch": 0.0,
"learning_rate": 3.228689702253003e-05,
"loss": 3.965,
"step": 1081856
},
{
"epoch": 0.0,
"learning_rate": 3.227851107501951e-05,
"loss": 3.9778,
"step": 1082368
},
{
"epoch": 0.0,
"learning_rate": 3.227012512750899e-05,
"loss": 3.9611,
"step": 1082880
},
{
"epoch": 0.0,
"learning_rate": 3.22617555588022e-05,
"loss": 3.9671,
"step": 1083392
},
{
"epoch": 0.01,
"learning_rate": 3.2253385990095414e-05,
"loss": 3.9704,
"step": 1083904
},
{
"epoch": 0.01,
"learning_rate": 3.224500004258489e-05,
"loss": 3.9697,
"step": 1084416
},
{
"epoch": 0.01,
"learning_rate": 3.223661409507437e-05,
"loss": 3.9764,
"step": 1084928
},
{
"epoch": 0.01,
"learning_rate": 3.222822814756385e-05,
"loss": 3.9843,
"step": 1085440
},
{
"epoch": 0.01,
"learning_rate": 3.221984220005333e-05,
"loss": 3.9764,
"step": 1085952
},
{
"epoch": 0.01,
"learning_rate": 3.221145625254281e-05,
"loss": 3.9797,
"step": 1086464
},
{
"epoch": 0.01,
"learning_rate": 3.220308668383602e-05,
"loss": 3.9802,
"step": 1086976
},
{
"epoch": 0.01,
"learning_rate": 3.21947007363255e-05,
"loss": 3.9621,
"step": 1087488
},
{
"epoch": 0.01,
"learning_rate": 3.218631478881498e-05,
"loss": 3.9791,
"step": 1088000
},
{
"epoch": 0.01,
"learning_rate": 3.217792884130446e-05,
"loss": 3.9681,
"step": 1088512
},
{
"epoch": 0.01,
"learning_rate": 3.216954289379394e-05,
"loss": 3.969,
"step": 1089024
},
{
"epoch": 0.01,
"learning_rate": 3.216115694628342e-05,
"loss": 3.9751,
"step": 1089536
},
{
"epoch": 0.01,
"learning_rate": 3.21527709987729e-05,
"loss": 3.9809,
"step": 1090048
},
{
"epoch": 0.01,
"learning_rate": 3.214438505126238e-05,
"loss": 3.9615,
"step": 1090560
},
{
"epoch": 0.01,
"learning_rate": 3.213601548255559e-05,
"loss": 3.9839,
"step": 1091072
},
{
"epoch": 0.01,
"learning_rate": 3.212762953504507e-05,
"loss": 3.9723,
"step": 1091584
},
{
"epoch": 0.01,
"learning_rate": 3.211925996633828e-05,
"loss": 3.973,
"step": 1092096
},
{
"epoch": 0.01,
"learning_rate": 3.211087401882776e-05,
"loss": 3.9776,
"step": 1092608
},
{
"epoch": 0.01,
"learning_rate": 3.210248807131725e-05,
"loss": 3.9444,
"step": 1093120
},
{
"epoch": 0.01,
"learning_rate": 3.209410212380673e-05,
"loss": 3.9692,
"step": 1093632
},
{
"epoch": 0.01,
"learning_rate": 3.208571617629621e-05,
"loss": 3.9776,
"step": 1094144
},
{
"epoch": 0.01,
"learning_rate": 3.207733022878569e-05,
"loss": 3.9742,
"step": 1094656
},
{
"epoch": 0.01,
"learning_rate": 3.206894428127517e-05,
"loss": 3.9613,
"step": 1095168
},
{
"epoch": 0.01,
"learning_rate": 3.2060574712568376e-05,
"loss": 3.9559,
"step": 1095680
},
{
"epoch": 0.01,
"learning_rate": 3.2052188765057856e-05,
"loss": 3.9543,
"step": 1096192
},
{
"epoch": 0.01,
"learning_rate": 3.2043802817547336e-05,
"loss": 3.9578,
"step": 1096704
},
{
"epoch": 0.01,
"learning_rate": 3.2035416870036816e-05,
"loss": 3.9835,
"step": 1097216
},
{
"epoch": 0.01,
"learning_rate": 3.2027030922526296e-05,
"loss": 3.9526,
"step": 1097728
},
{
"epoch": 0.01,
"learning_rate": 3.2018644975015776e-05,
"loss": 3.9802,
"step": 1098240
},
{
"epoch": 0.01,
"learning_rate": 3.201025902750525e-05,
"loss": 3.9698,
"step": 1098752
},
{
"epoch": 0.01,
"learning_rate": 3.2001889458798465e-05,
"loss": 3.9561,
"step": 1099264
},
{
"epoch": 0.01,
"learning_rate": 3.1993503511287945e-05,
"loss": 3.9685,
"step": 1099776
},
{
"epoch": 0.01,
"learning_rate": 3.198511756377743e-05,
"loss": 3.9579,
"step": 1100288
},
{
"epoch": 0.01,
"learning_rate": 3.1976731616266905e-05,
"loss": 3.9598,
"step": 1100800
},
{
"epoch": 0.01,
"learning_rate": 3.196836204756012e-05,
"loss": 3.9551,
"step": 1101312
},
{
"epoch": 0.01,
"learning_rate": 3.19599761000496e-05,
"loss": 3.9756,
"step": 1101824
},
{
"epoch": 0.01,
"learning_rate": 3.1951590152539074e-05,
"loss": 3.9655,
"step": 1102336
},
{
"epoch": 0.01,
"learning_rate": 3.1943204205028554e-05,
"loss": 3.9613,
"step": 1102848
},
{
"epoch": 0.01,
"learning_rate": 3.1934818257518034e-05,
"loss": 3.9566,
"step": 1103360
},
{
"epoch": 0.01,
"learning_rate": 3.1926432310007514e-05,
"loss": 3.9621,
"step": 1103872
},
{
"epoch": 0.01,
"learning_rate": 3.191806274130072e-05,
"loss": 3.9745,
"step": 1104384
},
{
"epoch": 0.01,
"learning_rate": 3.19096767937902e-05,
"loss": 3.9759,
"step": 1104896
},
{
"epoch": 0.01,
"learning_rate": 3.190129084627968e-05,
"loss": 3.972,
"step": 1105408
},
{
"epoch": 0.01,
"learning_rate": 3.189290489876917e-05,
"loss": 3.9753,
"step": 1105920
},
{
"epoch": 0.01,
"learning_rate": 3.188451895125865e-05,
"loss": 3.9871,
"step": 1106432
},
{
"epoch": 0.01,
"learning_rate": 3.187614938255186e-05,
"loss": 3.9735,
"step": 1106944
},
{
"epoch": 0.01,
"learning_rate": 3.186776343504134e-05,
"loss": 3.9775,
"step": 1107456
},
{
"epoch": 0.01,
"learning_rate": 3.185937748753082e-05,
"loss": 3.9654,
"step": 1107968
},
{
"epoch": 0.01,
"learning_rate": 3.18509915400203e-05,
"loss": 3.9702,
"step": 1108480
},
{
"epoch": 0.01,
"learning_rate": 3.184260559250978e-05,
"loss": 3.9643,
"step": 1108992
},
{
"epoch": 0.01,
"learning_rate": 3.183423602380299e-05,
"loss": 3.9613,
"step": 1109504
},
{
"epoch": 0.01,
"learning_rate": 3.182585007629247e-05,
"loss": 3.9785,
"step": 1110016
},
{
"epoch": 0.01,
"learning_rate": 3.181746412878195e-05,
"loss": 3.9801,
"step": 1110528
},
{
"epoch": 0.01,
"learning_rate": 3.180907818127143e-05,
"loss": 3.9756,
"step": 1111040
},
{
"epoch": 0.01,
"learning_rate": 3.180069223376091e-05,
"loss": 3.9511,
"step": 1111552
},
{
"epoch": 0.01,
"learning_rate": 3.179230628625039e-05,
"loss": 3.9613,
"step": 1112064
},
{
"epoch": 0.01,
"learning_rate": 3.178392033873987e-05,
"loss": 3.9743,
"step": 1112576
},
{
"epoch": 0.01,
"learning_rate": 3.177553439122935e-05,
"loss": 3.9713,
"step": 1113088
},
{
"epoch": 0.01,
"learning_rate": 3.176716482252256e-05,
"loss": 3.9646,
"step": 1113600
},
{
"epoch": 0.01,
"learning_rate": 3.175877887501204e-05,
"loss": 3.9715,
"step": 1114112
},
{
"epoch": 0.02,
"learning_rate": 3.175039292750152e-05,
"loss": 3.9672,
"step": 1114624
},
{
"epoch": 0.02,
"learning_rate": 3.174203973759846e-05,
"loss": 3.9649,
"step": 1115136
},
{
"epoch": 0.02,
"learning_rate": 3.173365379008794e-05,
"loss": 3.9643,
"step": 1115648
},
{
"epoch": 0.02,
"learning_rate": 3.172526784257742e-05,
"loss": 3.9763,
"step": 1116160
},
{
"epoch": 0.02,
"learning_rate": 3.17168818950669e-05,
"loss": 3.9667,
"step": 1116672
},
{
"epoch": 0.02,
"learning_rate": 3.170849594755638e-05,
"loss": 3.9784,
"step": 1117184
},
{
"epoch": 0.02,
"learning_rate": 3.170011000004586e-05,
"loss": 3.9585,
"step": 1117696
},
{
"epoch": 0.02,
"learning_rate": 3.169172405253534e-05,
"loss": 3.9623,
"step": 1118208
},
{
"epoch": 0.02,
"learning_rate": 3.168333810502482e-05,
"loss": 3.9715,
"step": 1118720
},
{
"epoch": 0.02,
"learning_rate": 3.16749521575143e-05,
"loss": 3.9725,
"step": 1119232
},
{
"epoch": 0.02,
"learning_rate": 3.166656621000379e-05,
"loss": 3.9748,
"step": 1119744
},
{
"epoch": 0.02,
"learning_rate": 3.165818026249327e-05,
"loss": 3.9692,
"step": 1120256
},
{
"epoch": 0.02,
"learning_rate": 3.164979431498274e-05,
"loss": 3.9708,
"step": 1120768
},
{
"epoch": 0.02,
"learning_rate": 3.1641424746275956e-05,
"loss": 3.9673,
"step": 1121280
},
{
"epoch": 0.02,
"learning_rate": 3.1633038798765436e-05,
"loss": 3.9722,
"step": 1121792
},
{
"epoch": 0.02,
"learning_rate": 3.1624669230058645e-05,
"loss": 3.9538,
"step": 1122304
},
{
"epoch": 0.02,
"learning_rate": 3.1616283282548125e-05,
"loss": 3.9617,
"step": 1122816
},
{
"epoch": 0.02,
"learning_rate": 3.1607897335037605e-05,
"loss": 3.9609,
"step": 1123328
},
{
"epoch": 0.02,
"learning_rate": 3.1599511387527085e-05,
"loss": 3.9639,
"step": 1123840
},
{
"epoch": 0.02,
"learning_rate": 3.159112544001656e-05,
"loss": 3.9603,
"step": 1124352
},
{
"epoch": 0.02,
"learning_rate": 3.158273949250604e-05,
"loss": 3.956,
"step": 1124864
},
{
"epoch": 0.02,
"learning_rate": 3.1574353544995525e-05,
"loss": 3.9491,
"step": 1125376
},
{
"epoch": 0.02,
"learning_rate": 3.1565983976288734e-05,
"loss": 3.9673,
"step": 1125888
},
{
"epoch": 0.02,
"learning_rate": 3.1557598028778214e-05,
"loss": 3.9638,
"step": 1126400
},
{
"epoch": 0.02,
"learning_rate": 3.1549212081267694e-05,
"loss": 3.9647,
"step": 1126912
},
{
"epoch": 0.02,
"learning_rate": 3.1540826133757174e-05,
"loss": 3.9668,
"step": 1127424
},
{
"epoch": 0.02,
"learning_rate": 3.1532440186246654e-05,
"loss": 3.9731,
"step": 1127936
},
{
"epoch": 0.02,
"learning_rate": 3.1524054238736134e-05,
"loss": 3.9668,
"step": 1128448
},
{
"epoch": 0.02,
"learning_rate": 3.151568467002934e-05,
"loss": 3.9632,
"step": 1128960
},
{
"epoch": 0.02,
"learning_rate": 3.150729872251882e-05,
"loss": 3.9745,
"step": 1129472
},
{
"epoch": 0.02,
"learning_rate": 3.14989127750083e-05,
"loss": 3.9698,
"step": 1129984
},
{
"epoch": 0.02,
"learning_rate": 3.149052682749778e-05,
"loss": 3.9602,
"step": 1130496
},
{
"epoch": 0.02,
"learning_rate": 3.148214087998726e-05,
"loss": 3.9705,
"step": 1131008
},
{
"epoch": 0.02,
"learning_rate": 3.147375493247674e-05,
"loss": 3.9662,
"step": 1131520
},
{
"epoch": 0.02,
"learning_rate": 3.146536898496622e-05,
"loss": 3.9657,
"step": 1132032
},
{
"epoch": 0.02,
"learning_rate": 3.145698303745571e-05,
"loss": 3.9531,
"step": 1132544
},
{
"epoch": 0.02,
"learning_rate": 3.144861346874892e-05,
"loss": 3.9673,
"step": 1133056
},
{
"epoch": 0.02,
"learning_rate": 3.14402275212384e-05,
"loss": 3.9578,
"step": 1133568
},
{
"epoch": 0.02,
"learning_rate": 3.143184157372788e-05,
"loss": 3.9635,
"step": 1134080
},
{
"epoch": 0.02,
"learning_rate": 3.142347200502109e-05,
"loss": 3.9511,
"step": 1134592
},
{
"epoch": 0.02,
"learning_rate": 3.141508605751057e-05,
"loss": 3.9771,
"step": 1135104
},
{
"epoch": 0.02,
"learning_rate": 3.140671648880378e-05,
"loss": 3.9671,
"step": 1135616
},
{
"epoch": 0.02,
"learning_rate": 3.139833054129326e-05,
"loss": 3.9548,
"step": 1136128
},
{
"epoch": 0.02,
"learning_rate": 3.1389944593782737e-05,
"loss": 3.9728,
"step": 1136640
},
{
"epoch": 0.02,
"learning_rate": 3.1381558646272217e-05,
"loss": 3.9703,
"step": 1137152
},
{
"epoch": 0.02,
"learning_rate": 3.1373172698761697e-05,
"loss": 3.9734,
"step": 1137664
},
{
"epoch": 0.02,
"learning_rate": 3.1364786751251176e-05,
"loss": 3.9656,
"step": 1138176
},
{
"epoch": 0.02,
"learning_rate": 3.1356400803740656e-05,
"loss": 3.9672,
"step": 1138688
},
{
"epoch": 0.02,
"learning_rate": 3.134801485623014e-05,
"loss": 3.9777,
"step": 1139200
},
{
"epoch": 0.02,
"learning_rate": 3.133962890871962e-05,
"loss": 3.9644,
"step": 1139712
},
{
"epoch": 0.02,
"learning_rate": 3.1331242961209096e-05,
"loss": 3.9691,
"step": 1140224
},
{
"epoch": 0.02,
"learning_rate": 3.1322857013698576e-05,
"loss": 3.9593,
"step": 1140736
},
{
"epoch": 0.02,
"learning_rate": 3.131448744499179e-05,
"loss": 3.9673,
"step": 1141248
},
{
"epoch": 0.02,
"learning_rate": 3.130610149748127e-05,
"loss": 3.9598,
"step": 1141760
},
{
"epoch": 0.02,
"learning_rate": 3.1297715549970745e-05,
"loss": 3.9586,
"step": 1142272
},
{
"epoch": 0.02,
"learning_rate": 3.1289329602460225e-05,
"loss": 3.9663,
"step": 1142784
},
{
"epoch": 0.02,
"learning_rate": 3.1280943654949705e-05,
"loss": 3.967,
"step": 1143296
},
{
"epoch": 0.02,
"learning_rate": 3.127257408624292e-05,
"loss": 3.9711,
"step": 1143808
},
{
"epoch": 0.02,
"learning_rate": 3.126420451753613e-05,
"loss": 3.9665,
"step": 1144320
},
{
"epoch": 0.03,
"eval_loss": 4.022707939147949,
"eval_runtime": 293.8732,
"eval_samples_per_second": 1298.489,
"eval_steps_per_second": 40.579,
"step": 1144800
},
{
"epoch": 1.0,
"learning_rate": 3.125581857002561e-05,
"loss": 3.9593,
"step": 1144832
},
{
"epoch": 1.0,
"learning_rate": 3.12474326225151e-05,
"loss": 3.9595,
"step": 1145344
},
{
"epoch": 1.0,
"learning_rate": 3.123904667500457e-05,
"loss": 3.957,
"step": 1145856
},
{
"epoch": 1.0,
"learning_rate": 3.123066072749405e-05,
"loss": 3.9691,
"step": 1146368
},
{
"epoch": 1.0,
"learning_rate": 3.122227477998353e-05,
"loss": 3.9642,
"step": 1146880
},
{
"epoch": 1.0,
"learning_rate": 3.121388883247301e-05,
"loss": 3.9763,
"step": 1147392
},
{
"epoch": 1.0,
"learning_rate": 3.120550288496249e-05,
"loss": 3.9553,
"step": 1147904
},
{
"epoch": 1.0,
"learning_rate": 3.119711693745197e-05,
"loss": 3.9609,
"step": 1148416
},
{
"epoch": 1.0,
"learning_rate": 3.118873098994145e-05,
"loss": 3.9526,
"step": 1148928
},
{
"epoch": 1.0,
"learning_rate": 3.118034504243093e-05,
"loss": 3.9667,
"step": 1149440
},
{
"epoch": 1.0,
"learning_rate": 3.117197547372414e-05,
"loss": 3.9596,
"step": 1149952
},
{
"epoch": 1.0,
"learning_rate": 3.116358952621362e-05,
"loss": 3.9669,
"step": 1150464
},
{
"epoch": 1.0,
"learning_rate": 3.1155219957506835e-05,
"loss": 3.9697,
"step": 1150976
},
{
"epoch": 1.0,
"learning_rate": 3.1146834009996315e-05,
"loss": 3.9516,
"step": 1151488
},
{
"epoch": 1.0,
"learning_rate": 3.1138448062485795e-05,
"loss": 3.953,
"step": 1152000
},
{
"epoch": 1.0,
"learning_rate": 3.1130062114975274e-05,
"loss": 3.9522,
"step": 1152512
},
{
"epoch": 1.0,
"learning_rate": 3.1121676167464754e-05,
"loss": 3.9632,
"step": 1153024
},
{
"epoch": 1.0,
"learning_rate": 3.1113290219954234e-05,
"loss": 3.9595,
"step": 1153536
},
{
"epoch": 1.0,
"learning_rate": 3.1104904272443714e-05,
"loss": 3.9611,
"step": 1154048
},
{
"epoch": 1.0,
"learning_rate": 3.1096518324933194e-05,
"loss": 3.9548,
"step": 1154560
},
{
"epoch": 1.0,
"learning_rate": 3.1088132377422674e-05,
"loss": 3.9755,
"step": 1155072
},
{
"epoch": 1.0,
"learning_rate": 3.1079746429912154e-05,
"loss": 3.9582,
"step": 1155584
},
{
"epoch": 1.0,
"learning_rate": 3.107137686120536e-05,
"loss": 3.9644,
"step": 1156096
},
{
"epoch": 1.0,
"learning_rate": 3.106299091369484e-05,
"loss": 3.9667,
"step": 1156608
},
{
"epoch": 1.0,
"learning_rate": 3.105460496618432e-05,
"loss": 3.9707,
"step": 1157120
},
{
"epoch": 1.0,
"learning_rate": 3.10462190186738e-05,
"loss": 3.9627,
"step": 1157632
},
{
"epoch": 1.0,
"learning_rate": 3.103783307116328e-05,
"loss": 3.9536,
"step": 1158144
},
{
"epoch": 1.0,
"learning_rate": 3.102944712365276e-05,
"loss": 3.9624,
"step": 1158656
},
{
"epoch": 1.0,
"learning_rate": 3.102106117614224e-05,
"loss": 3.9464,
"step": 1159168
},
{
"epoch": 1.0,
"learning_rate": 3.101267522863172e-05,
"loss": 3.9581,
"step": 1159680
},
{
"epoch": 1.01,
"learning_rate": 3.100430565992493e-05,
"loss": 3.9534,
"step": 1160192
},
{
"epoch": 1.01,
"learning_rate": 3.099593609121815e-05,
"loss": 3.9633,
"step": 1160704
},
{
"epoch": 1.01,
"learning_rate": 3.098755014370763e-05,
"loss": 3.9606,
"step": 1161216
},
{
"epoch": 1.01,
"learning_rate": 3.097916419619711e-05,
"loss": 3.9675,
"step": 1161728
},
{
"epoch": 1.01,
"learning_rate": 3.097077824868658e-05,
"loss": 3.9672,
"step": 1162240
},
{
"epoch": 1.01,
"learning_rate": 3.09624086799798e-05,
"loss": 3.9664,
"step": 1162752
},
{
"epoch": 1.01,
"learning_rate": 3.095402273246928e-05,
"loss": 3.9658,
"step": 1163264
},
{
"epoch": 1.01,
"learning_rate": 3.094563678495876e-05,
"loss": 3.9511,
"step": 1163776
},
{
"epoch": 1.01,
"learning_rate": 3.093725083744824e-05,
"loss": 3.9667,
"step": 1164288
},
{
"epoch": 1.01,
"learning_rate": 3.092886488993772e-05,
"loss": 3.9527,
"step": 1164800
},
{
"epoch": 1.01,
"learning_rate": 3.09204789424272e-05,
"loss": 3.9549,
"step": 1165312
},
{
"epoch": 1.01,
"learning_rate": 3.0912109373720406e-05,
"loss": 3.9639,
"step": 1165824
},
{
"epoch": 1.01,
"learning_rate": 3.0903723426209886e-05,
"loss": 3.9661,
"step": 1166336
},
{
"epoch": 1.01,
"learning_rate": 3.0895337478699366e-05,
"loss": 3.9536,
"step": 1166848
},
{
"epoch": 1.01,
"learning_rate": 3.0886951531188846e-05,
"loss": 3.9676,
"step": 1167360
},
{
"epoch": 1.01,
"learning_rate": 3.0878565583678326e-05,
"loss": 3.9603,
"step": 1167872
},
{
"epoch": 1.01,
"learning_rate": 3.0870179636167806e-05,
"loss": 3.9601,
"step": 1168384
},
{
"epoch": 1.01,
"learning_rate": 3.0861793688657286e-05,
"loss": 3.9674,
"step": 1168896
},
{
"epoch": 1.01,
"learning_rate": 3.0853407741146765e-05,
"loss": 3.9363,
"step": 1169408
},
{
"epoch": 1.01,
"learning_rate": 3.0845038172439975e-05,
"loss": 3.9519,
"step": 1169920
},
{
"epoch": 1.01,
"learning_rate": 3.0836652224929455e-05,
"loss": 3.9661,
"step": 1170432
},
{
"epoch": 1.01,
"learning_rate": 3.082826627741894e-05,
"loss": 3.9613,
"step": 1170944
},
{
"epoch": 1.01,
"learning_rate": 3.081988032990842e-05,
"loss": 3.9504,
"step": 1171456
},
{
"epoch": 1.01,
"learning_rate": 3.081151076120163e-05,
"loss": 3.9401,
"step": 1171968
},
{
"epoch": 1.01,
"learning_rate": 3.080312481369111e-05,
"loss": 3.9475,
"step": 1172480
},
{
"epoch": 1.01,
"learning_rate": 3.079473886618059e-05,
"loss": 3.9387,
"step": 1172992
},
{
"epoch": 1.01,
"learning_rate": 3.078635291867007e-05,
"loss": 3.975,
"step": 1173504
},
{
"epoch": 1.01,
"learning_rate": 3.077798334996328e-05,
"loss": 3.9389,
"step": 1174016
},
{
"epoch": 1.01,
"learning_rate": 3.076959740245276e-05,
"loss": 3.9664,
"step": 1174528
},
{
"epoch": 1.01,
"learning_rate": 3.076121145494224e-05,
"loss": 3.9577,
"step": 1175040
},
{
"epoch": 1.01,
"learning_rate": 3.075282550743172e-05,
"loss": 3.9474,
"step": 1175552
},
{
"epoch": 1.01,
"learning_rate": 3.07444395599212e-05,
"loss": 3.9534,
"step": 1176064
},
{
"epoch": 1.01,
"learning_rate": 3.073605361241068e-05,
"loss": 3.9482,
"step": 1176576
},
{
"epoch": 1.01,
"learning_rate": 3.072768404370389e-05,
"loss": 3.9448,
"step": 1177088
},
{
"epoch": 1.01,
"learning_rate": 3.0719298096193375e-05,
"loss": 3.944,
"step": 1177600
},
{
"epoch": 1.01,
"learning_rate": 3.0710912148682855e-05,
"loss": 3.967,
"step": 1178112
},
{
"epoch": 1.01,
"learning_rate": 3.0702526201172335e-05,
"loss": 3.952,
"step": 1178624
},
{
"epoch": 1.01,
"learning_rate": 3.0694156632465544e-05,
"loss": 3.949,
"step": 1179136
},
{
"epoch": 1.01,
"learning_rate": 3.0685770684955024e-05,
"loss": 3.9416,
"step": 1179648
},
{
"epoch": 1.01,
"learning_rate": 3.0677384737444504e-05,
"loss": 3.9513,
"step": 1180160
},
{
"epoch": 1.01,
"learning_rate": 3.0668998789933984e-05,
"loss": 3.9621,
"step": 1180672
},
{
"epoch": 1.01,
"learning_rate": 3.0660612842423464e-05,
"loss": 3.9656,
"step": 1181184
},
{
"epoch": 1.01,
"learning_rate": 3.0652226894912944e-05,
"loss": 3.9636,
"step": 1181696
},
{
"epoch": 1.01,
"learning_rate": 3.064384094740242e-05,
"loss": 3.9606,
"step": 1182208
},
{
"epoch": 1.01,
"learning_rate": 3.063547137869563e-05,
"loss": 3.9746,
"step": 1182720
},
{
"epoch": 1.01,
"learning_rate": 3.062708543118511e-05,
"loss": 3.963,
"step": 1183232
},
{
"epoch": 1.01,
"learning_rate": 3.061869948367459e-05,
"loss": 3.963,
"step": 1183744
},
{
"epoch": 1.01,
"learning_rate": 3.061031353616407e-05,
"loss": 3.9525,
"step": 1184256
},
{
"epoch": 1.01,
"learning_rate": 3.060192758865355e-05,
"loss": 3.9579,
"step": 1184768
},
{
"epoch": 1.01,
"learning_rate": 3.059354164114303e-05,
"loss": 3.9486,
"step": 1185280
},
{
"epoch": 1.01,
"learning_rate": 3.058515569363251e-05,
"loss": 3.9543,
"step": 1185792
},
{
"epoch": 1.01,
"learning_rate": 3.057676974612199e-05,
"loss": 3.9651,
"step": 1186304
},
{
"epoch": 1.01,
"learning_rate": 3.05684001774152e-05,
"loss": 3.9697,
"step": 1186816
},
{
"epoch": 1.01,
"learning_rate": 3.056003060870842e-05,
"loss": 3.9603,
"step": 1187328
},
{
"epoch": 1.01,
"learning_rate": 3.055164466119789e-05,
"loss": 3.9448,
"step": 1187840
},
{
"epoch": 1.01,
"learning_rate": 3.054325871368737e-05,
"loss": 3.9492,
"step": 1188352
},
{
"epoch": 1.01,
"learning_rate": 3.053487276617685e-05,
"loss": 3.9575,
"step": 1188864
},
{
"epoch": 1.01,
"learning_rate": 3.052648681866633e-05,
"loss": 3.9651,
"step": 1189376
},
{
"epoch": 1.01,
"learning_rate": 3.051810087115581e-05,
"loss": 3.9494,
"step": 1189888
},
{
"epoch": 1.01,
"learning_rate": 3.0509714923645294e-05,
"loss": 3.9595,
"step": 1190400
},
{
"epoch": 1.02,
"learning_rate": 3.0501328976134774e-05,
"loss": 3.9587,
"step": 1190912
},
{
"epoch": 1.02,
"learning_rate": 3.0492959407427986e-05,
"loss": 3.95,
"step": 1191424
},
{
"epoch": 1.02,
"learning_rate": 3.0484573459917466e-05,
"loss": 3.9533,
"step": 1191936
},
{
"epoch": 1.02,
"learning_rate": 3.0476187512406946e-05,
"loss": 3.9634,
"step": 1192448
},
{
"epoch": 1.02,
"learning_rate": 3.0467801564896426e-05,
"loss": 3.9536,
"step": 1192960
},
{
"epoch": 1.02,
"learning_rate": 3.0459415617385906e-05,
"loss": 3.9667,
"step": 1193472
},
{
"epoch": 1.02,
"learning_rate": 3.0451029669875386e-05,
"loss": 3.9501,
"step": 1193984
},
{
"epoch": 1.02,
"learning_rate": 3.0442643722364866e-05,
"loss": 3.9491,
"step": 1194496
},
{
"epoch": 1.02,
"learning_rate": 3.0434257774854346e-05,
"loss": 3.955,
"step": 1195008
},
{
"epoch": 1.02,
"learning_rate": 3.042588820614756e-05,
"loss": 3.964,
"step": 1195520
},
{
"epoch": 1.02,
"learning_rate": 3.041750225863704e-05,
"loss": 3.9598,
"step": 1196032
},
{
"epoch": 1.02,
"learning_rate": 3.0409132689930247e-05,
"loss": 3.9587,
"step": 1196544
},
{
"epoch": 1.02,
"learning_rate": 3.0400746742419727e-05,
"loss": 3.9607,
"step": 1197056
},
{
"epoch": 1.02,
"learning_rate": 3.0392360794909207e-05,
"loss": 3.9576,
"step": 1197568
},
{
"epoch": 1.02,
"learning_rate": 3.0383974847398687e-05,
"loss": 3.9567,
"step": 1198080
},
{
"epoch": 1.02,
"learning_rate": 3.0375588899888167e-05,
"loss": 3.9408,
"step": 1198592
},
{
"epoch": 1.02,
"learning_rate": 3.036720295237765e-05,
"loss": 3.9479,
"step": 1199104
},
{
"epoch": 1.02,
"learning_rate": 3.035881700486713e-05,
"loss": 3.9549,
"step": 1199616
},
{
"epoch": 1.02,
"learning_rate": 3.0350431057356604e-05,
"loss": 3.9503,
"step": 1200128
},
{
"epoch": 1.02,
"learning_rate": 3.034206148864982e-05,
"loss": 3.9484,
"step": 1200640
},
{
"epoch": 1.02,
"learning_rate": 3.03336755411393e-05,
"loss": 3.946,
"step": 1201152
},
{
"epoch": 1.02,
"learning_rate": 3.0325289593628776e-05,
"loss": 3.9406,
"step": 1201664
},
{
"epoch": 1.02,
"learning_rate": 3.0316903646118256e-05,
"loss": 3.9541,
"step": 1202176
},
{
"epoch": 1.02,
"learning_rate": 3.0308534077411472e-05,
"loss": 3.949,
"step": 1202688
},
{
"epoch": 1.02,
"learning_rate": 3.030016450870468e-05,
"loss": 3.9571,
"step": 1203200
},
{
"epoch": 1.02,
"learning_rate": 3.029177856119416e-05,
"loss": 3.9522,
"step": 1203712
},
{
"epoch": 1.02,
"learning_rate": 3.028339261368364e-05,
"loss": 3.9623,
"step": 1204224
},
{
"epoch": 1.02,
"learning_rate": 3.027500666617312e-05,
"loss": 3.956,
"step": 1204736
},
{
"epoch": 1.02,
"learning_rate": 3.0266620718662604e-05,
"loss": 3.9524,
"step": 1205248
},
{
"epoch": 1.02,
"learning_rate": 3.0258234771152077e-05,
"loss": 3.9598,
"step": 1205760
},
{
"epoch": 1.02,
"learning_rate": 3.0249848823641557e-05,
"loss": 3.9591,
"step": 1206272
},
{
"epoch": 1.02,
"learning_rate": 3.0241462876131037e-05,
"loss": 3.9549,
"step": 1206784
},
{
"epoch": 1.02,
"learning_rate": 3.0233076928620517e-05,
"loss": 3.9588,
"step": 1207296
},
{
"epoch": 1.02,
"learning_rate": 3.0224690981109997e-05,
"loss": 3.954,
"step": 1207808
},
{
"epoch": 1.02,
"learning_rate": 3.021630503359948e-05,
"loss": 3.9549,
"step": 1208320
},
{
"epoch": 1.02,
"learning_rate": 3.020791908608896e-05,
"loss": 3.9458,
"step": 1208832
},
{
"epoch": 1.02,
"learning_rate": 3.019953313857844e-05,
"loss": 3.9504,
"step": 1209344
},
{
"epoch": 1.02,
"learning_rate": 3.019116356987165e-05,
"loss": 3.9477,
"step": 1209856
},
{
"epoch": 1.02,
"learning_rate": 3.018277762236113e-05,
"loss": 3.9491,
"step": 1210368
},
{
"epoch": 1.02,
"learning_rate": 3.017439167485061e-05,
"loss": 3.9388,
"step": 1210880
},
{
"epoch": 1.02,
"learning_rate": 3.016600572734009e-05,
"loss": 3.9698,
"step": 1211392
},
{
"epoch": 1.02,
"learning_rate": 3.0157619779829573e-05,
"loss": 3.9543,
"step": 1211904
},
{
"epoch": 1.02,
"learning_rate": 3.0149233832319053e-05,
"loss": 3.9502,
"step": 1212416
},
{
"epoch": 1.02,
"learning_rate": 3.0140847884808533e-05,
"loss": 3.9548,
"step": 1212928
},
{
"epoch": 1.02,
"learning_rate": 3.0132461937298013e-05,
"loss": 3.9559,
"step": 1213440
},
{
"epoch": 1.02,
"learning_rate": 3.0124092368591222e-05,
"loss": 3.9656,
"step": 1213952
},
{
"epoch": 1.02,
"learning_rate": 3.0115706421080702e-05,
"loss": 3.9545,
"step": 1214464
},
{
"epoch": 1.02,
"learning_rate": 3.010732047357018e-05,
"loss": 3.9533,
"step": 1214976
},
{
"epoch": 1.02,
"learning_rate": 3.0098934526059665e-05,
"loss": 3.9637,
"step": 1215488
},
{
"epoch": 1.02,
"learning_rate": 3.0090564957352874e-05,
"loss": 3.9499,
"step": 1216000
},
{
"epoch": 1.02,
"learning_rate": 3.0082195388646083e-05,
"loss": 3.9593,
"step": 1216512
},
{
"epoch": 1.02,
"learning_rate": 3.0073809441135563e-05,
"loss": 3.9501,
"step": 1217024
},
{
"epoch": 1.02,
"learning_rate": 3.0065423493625043e-05,
"loss": 3.9609,
"step": 1217536
},
{
"epoch": 1.02,
"learning_rate": 3.0057037546114526e-05,
"loss": 3.9544,
"step": 1218048
},
{
"epoch": 1.02,
"learning_rate": 3.0048651598604006e-05,
"loss": 3.9427,
"step": 1218560
},
{
"epoch": 1.02,
"learning_rate": 3.0040265651093486e-05,
"loss": 3.9573,
"step": 1219072
},
{
"epoch": 1.02,
"learning_rate": 3.0031879703582966e-05,
"loss": 3.9558,
"step": 1219584
},
{
"epoch": 1.02,
"learning_rate": 3.002349375607244e-05,
"loss": 3.9553,
"step": 1220096
},
{
"epoch": 1.02,
"learning_rate": 3.0015124187365655e-05,
"loss": 3.9536,
"step": 1220608
},
{
"epoch": 1.03,
"learning_rate": 3.0006738239855135e-05,
"loss": 3.953,
"step": 1221120
},
{
"epoch": 1.03,
"eval_loss": 4.016727447509766,
"eval_runtime": 289.1819,
"eval_samples_per_second": 1319.554,
"eval_steps_per_second": 41.237,
"step": 1221120
},
{
"epoch": 0.0,
"learning_rate": 2.9998352292344612e-05,
"loss": 3.9455,
"step": 1221632
},
{
"epoch": 0.0,
"learning_rate": 2.9989966344834092e-05,
"loss": 3.9419,
"step": 1222144
},
{
"epoch": 0.0,
"learning_rate": 2.9981580397323572e-05,
"loss": 3.959,
"step": 1222656
},
{
"epoch": 0.0,
"learning_rate": 2.9973194449813052e-05,
"loss": 3.9546,
"step": 1223168
},
{
"epoch": 0.0,
"learning_rate": 2.9964808502302532e-05,
"loss": 3.965,
"step": 1223680
},
{
"epoch": 0.0,
"learning_rate": 2.9956422554792012e-05,
"loss": 3.9469,
"step": 1224192
},
{
"epoch": 0.0,
"learning_rate": 2.994803660728149e-05,
"loss": 3.9482,
"step": 1224704
},
{
"epoch": 0.0,
"learning_rate": 2.9939650659770975e-05,
"loss": 3.9389,
"step": 1225216
},
{
"epoch": 0.0,
"learning_rate": 2.9931264712260455e-05,
"loss": 3.9579,
"step": 1225728
},
{
"epoch": 0.0,
"learning_rate": 2.9922878764749935e-05,
"loss": 3.9488,
"step": 1226240
},
{
"epoch": 0.0,
"learning_rate": 2.9914492817239415e-05,
"loss": 3.9575,
"step": 1226752
},
{
"epoch": 0.0,
"learning_rate": 2.9906106869728895e-05,
"loss": 3.9557,
"step": 1227264
},
{
"epoch": 0.0,
"learning_rate": 2.9897737301022104e-05,
"loss": 3.9459,
"step": 1227776
},
{
"epoch": 0.0,
"learning_rate": 2.9889351353511584e-05,
"loss": 3.9418,
"step": 1228288
},
{
"epoch": 0.0,
"learning_rate": 2.9880965406001067e-05,
"loss": 3.9431,
"step": 1228800
},
{
"epoch": 0.0,
"learning_rate": 2.9872579458490547e-05,
"loss": 3.9444,
"step": 1229312
},
{
"epoch": 0.0,
"learning_rate": 2.9864193510980027e-05,
"loss": 3.9517,
"step": 1229824
},
{
"epoch": 0.0,
"learning_rate": 2.98558075634695e-05,
"loss": 3.9482,
"step": 1230336
},
{
"epoch": 0.0,
"learning_rate": 2.984742161595898e-05,
"loss": 3.9427,
"step": 1230848
},
{
"epoch": 0.0,
"learning_rate": 2.983903566844846e-05,
"loss": 3.9681,
"step": 1231360
},
{
"epoch": 0.0,
"learning_rate": 2.9830649720937944e-05,
"loss": 3.947,
"step": 1231872
},
{
"epoch": 0.0,
"learning_rate": 2.9822280152231153e-05,
"loss": 3.9571,
"step": 1232384
},
{
"epoch": 0.0,
"learning_rate": 2.9813894204720633e-05,
"loss": 3.9541,
"step": 1232896
},
{
"epoch": 0.0,
"learning_rate": 2.9805508257210113e-05,
"loss": 3.9588,
"step": 1233408
},
{
"epoch": 0.0,
"learning_rate": 2.9797122309699593e-05,
"loss": 3.9465,
"step": 1233920
},
{
"epoch": 0.0,
"learning_rate": 2.9788752740992805e-05,
"loss": 3.9486,
"step": 1234432
},
{
"epoch": 0.0,
"learning_rate": 2.9780366793482285e-05,
"loss": 3.9459,
"step": 1234944
},
{
"epoch": 0.0,
"learning_rate": 2.9771980845971765e-05,
"loss": 3.9439,
"step": 1235456
},
{
"epoch": 0.0,
"learning_rate": 2.9763611277264974e-05,
"loss": 3.9437,
"step": 1235968
},
{
"epoch": 0.01,
"learning_rate": 2.9755225329754454e-05,
"loss": 3.9407,
"step": 1236480
},
{
"epoch": 0.01,
"learning_rate": 2.9746839382243934e-05,
"loss": 3.9525,
"step": 1236992
},
{
"epoch": 0.01,
"learning_rate": 2.9738453434733414e-05,
"loss": 3.9515,
"step": 1237504
},
{
"epoch": 0.01,
"learning_rate": 2.9730067487222897e-05,
"loss": 3.9544,
"step": 1238016
},
{
"epoch": 0.01,
"learning_rate": 2.9721681539712377e-05,
"loss": 3.9574,
"step": 1238528
},
{
"epoch": 0.01,
"learning_rate": 2.9713311971005586e-05,
"loss": 3.9543,
"step": 1239040
},
{
"epoch": 0.01,
"learning_rate": 2.9704926023495066e-05,
"loss": 3.9533,
"step": 1239552
},
{
"epoch": 0.01,
"learning_rate": 2.9696540075984546e-05,
"loss": 3.9456,
"step": 1240064
},
{
"epoch": 0.01,
"learning_rate": 2.9688154128474026e-05,
"loss": 3.9501,
"step": 1240576
},
{
"epoch": 0.01,
"learning_rate": 2.9679768180963506e-05,
"loss": 3.9456,
"step": 1241088
},
{
"epoch": 0.01,
"learning_rate": 2.967138223345299e-05,
"loss": 3.9499,
"step": 1241600
},
{
"epoch": 0.01,
"learning_rate": 2.966299628594247e-05,
"loss": 3.9496,
"step": 1242112
},
{
"epoch": 0.01,
"learning_rate": 2.965461033843195e-05,
"loss": 3.9548,
"step": 1242624
},
{
"epoch": 0.01,
"learning_rate": 2.964624076972516e-05,
"loss": 3.9415,
"step": 1243136
},
{
"epoch": 0.01,
"learning_rate": 2.963785482221464e-05,
"loss": 3.9546,
"step": 1243648
},
{
"epoch": 0.01,
"learning_rate": 2.962946887470412e-05,
"loss": 3.9529,
"step": 1244160
},
{
"epoch": 0.01,
"learning_rate": 2.96210829271936e-05,
"loss": 3.9531,
"step": 1244672
},
{
"epoch": 0.01,
"learning_rate": 2.961271335848681e-05,
"loss": 3.9528,
"step": 1245184
},
{
"epoch": 0.01,
"learning_rate": 2.960432741097629e-05,
"loss": 3.9262,
"step": 1245696
},
{
"epoch": 0.01,
"learning_rate": 2.959594146346577e-05,
"loss": 3.9408,
"step": 1246208
},
{
"epoch": 0.01,
"learning_rate": 2.958755551595525e-05,
"loss": 3.9538,
"step": 1246720
},
{
"epoch": 0.01,
"learning_rate": 2.957916956844473e-05,
"loss": 3.951,
"step": 1247232
},
{
"epoch": 0.01,
"learning_rate": 2.957078362093421e-05,
"loss": 3.9407,
"step": 1247744
},
{
"epoch": 0.01,
"learning_rate": 2.9562397673423687e-05,
"loss": 3.9288,
"step": 1248256
},
{
"epoch": 0.01,
"learning_rate": 2.9554011725913167e-05,
"loss": 3.937,
"step": 1248768
},
{
"epoch": 0.01,
"learning_rate": 2.9545642157206383e-05,
"loss": 3.9308,
"step": 1249280
},
{
"epoch": 0.01,
"learning_rate": 2.9537256209695863e-05,
"loss": 3.9622,
"step": 1249792
},
{
"epoch": 0.01,
"learning_rate": 2.9528886640989072e-05,
"loss": 3.9334,
"step": 1250304
},
{
"epoch": 0.01,
"learning_rate": 2.9520500693478552e-05,
"loss": 3.9518,
"step": 1250816
},
{
"epoch": 0.01,
"learning_rate": 2.9512114745968032e-05,
"loss": 3.9475,
"step": 1251328
},
{
"epoch": 0.01,
"learning_rate": 2.9503728798457515e-05,
"loss": 3.9332,
"step": 1251840
},
{
"epoch": 0.01,
"learning_rate": 2.9495359229750724e-05,
"loss": 3.9447,
"step": 1252352
},
{
"epoch": 0.01,
"learning_rate": 2.9486973282240204e-05,
"loss": 3.9396,
"step": 1252864
},
{
"epoch": 0.01,
"learning_rate": 2.9478587334729684e-05,
"loss": 3.9303,
"step": 1253376
},
{
"epoch": 0.01,
"learning_rate": 2.947020138721916e-05,
"loss": 3.9325,
"step": 1253888
},
{
"epoch": 0.01,
"learning_rate": 2.946181543970864e-05,
"loss": 3.9587,
"step": 1254400
},
{
"epoch": 0.01,
"learning_rate": 2.945342949219812e-05,
"loss": 3.9458,
"step": 1254912
},
{
"epoch": 0.01,
"learning_rate": 2.94450435446876e-05,
"loss": 3.9372,
"step": 1255424
},
{
"epoch": 0.01,
"learning_rate": 2.943665759717708e-05,
"loss": 3.9322,
"step": 1255936
},
{
"epoch": 0.01,
"learning_rate": 2.942827164966656e-05,
"loss": 3.9388,
"step": 1256448
},
{
"epoch": 0.01,
"learning_rate": 2.941988570215604e-05,
"loss": 3.9505,
"step": 1256960
},
{
"epoch": 0.01,
"learning_rate": 2.941149975464552e-05,
"loss": 3.956,
"step": 1257472
},
{
"epoch": 0.01,
"learning_rate": 2.9403113807135e-05,
"loss": 3.9494,
"step": 1257984
},
{
"epoch": 0.01,
"learning_rate": 2.9394744238428213e-05,
"loss": 3.9554,
"step": 1258496
},
{
"epoch": 0.01,
"learning_rate": 2.9386374669721422e-05,
"loss": 3.9614,
"step": 1259008
},
{
"epoch": 0.01,
"learning_rate": 2.9377988722210902e-05,
"loss": 3.9533,
"step": 1259520
},
{
"epoch": 0.01,
"learning_rate": 2.9369602774700382e-05,
"loss": 3.9496,
"step": 1260032
},
{
"epoch": 0.01,
"learning_rate": 2.9361216827189862e-05,
"loss": 3.9432,
"step": 1260544
},
{
"epoch": 0.01,
"learning_rate": 2.9352830879679345e-05,
"loss": 3.9489,
"step": 1261056
},
{
"epoch": 0.01,
"learning_rate": 2.9344444932168825e-05,
"loss": 3.9436,
"step": 1261568
},
{
"epoch": 0.01,
"learning_rate": 2.9336075363462034e-05,
"loss": 3.9423,
"step": 1262080
},
{
"epoch": 0.01,
"learning_rate": 2.9327689415951514e-05,
"loss": 3.9508,
"step": 1262592
},
{
"epoch": 0.01,
"learning_rate": 2.9319303468440994e-05,
"loss": 3.9568,
"step": 1263104
},
{
"epoch": 0.01,
"learning_rate": 2.9310917520930474e-05,
"loss": 3.9521,
"step": 1263616
},
{
"epoch": 0.01,
"learning_rate": 2.9302547952223687e-05,
"loss": 3.9331,
"step": 1264128
},
{
"epoch": 0.01,
"learning_rate": 2.9294162004713167e-05,
"loss": 3.9354,
"step": 1264640
},
{
"epoch": 0.01,
"learning_rate": 2.9285776057202647e-05,
"loss": 3.9486,
"step": 1265152
},
{
"epoch": 0.01,
"learning_rate": 2.9277406488495856e-05,
"loss": 3.9533,
"step": 1265664
},
{
"epoch": 0.01,
"learning_rate": 2.9269020540985336e-05,
"loss": 3.9395,
"step": 1266176
},
{
"epoch": 0.01,
"learning_rate": 2.9260634593474816e-05,
"loss": 3.9475,
"step": 1266688
},
{
"epoch": 0.02,
"learning_rate": 2.92522486459643e-05,
"loss": 3.9521,
"step": 1267200
},
{
"epoch": 0.02,
"learning_rate": 2.924386269845378e-05,
"loss": 3.9402,
"step": 1267712
},
{
"epoch": 0.02,
"learning_rate": 2.923547675094326e-05,
"loss": 3.9414,
"step": 1268224
},
{
"epoch": 0.02,
"learning_rate": 2.922709080343274e-05,
"loss": 3.9476,
"step": 1268736
},
{
"epoch": 0.02,
"learning_rate": 2.921870485592222e-05,
"loss": 3.9447,
"step": 1269248
},
{
"epoch": 0.02,
"learning_rate": 2.92103189084117e-05,
"loss": 3.9543,
"step": 1269760
},
{
"epoch": 0.02,
"learning_rate": 2.9201932960901175e-05,
"loss": 3.9452,
"step": 1270272
},
{
"epoch": 0.02,
"learning_rate": 2.9193547013390655e-05,
"loss": 3.9339,
"step": 1270784
},
{
"epoch": 0.02,
"learning_rate": 2.9185161065880135e-05,
"loss": 3.9498,
"step": 1271296
},
{
"epoch": 0.02,
"learning_rate": 2.9176791497173344e-05,
"loss": 3.9513,
"step": 1271808
},
{
"epoch": 0.02,
"learning_rate": 2.916842192846656e-05,
"loss": 3.9483,
"step": 1272320
},
{
"epoch": 0.02,
"learning_rate": 2.916003598095604e-05,
"loss": 3.9517,
"step": 1272832
},
{
"epoch": 0.02,
"learning_rate": 2.915165003344552e-05,
"loss": 3.9462,
"step": 1273344
},
{
"epoch": 0.02,
"learning_rate": 2.9143264085934997e-05,
"loss": 3.9475,
"step": 1273856
},
{
"epoch": 0.02,
"learning_rate": 2.9134878138424477e-05,
"loss": 3.9515,
"step": 1274368
},
{
"epoch": 0.02,
"learning_rate": 2.9126492190913957e-05,
"loss": 3.9301,
"step": 1274880
},
{
"epoch": 0.02,
"learning_rate": 2.9118122622207172e-05,
"loss": 3.9345,
"step": 1275392
},
{
"epoch": 0.02,
"learning_rate": 2.9109736674696646e-05,
"loss": 3.946,
"step": 1275904
},
{
"epoch": 0.02,
"learning_rate": 2.910135072718613e-05,
"loss": 3.9437,
"step": 1276416
},
{
"epoch": 0.02,
"learning_rate": 2.909296477967561e-05,
"loss": 3.9342,
"step": 1276928
},
{
"epoch": 0.02,
"learning_rate": 2.908457883216509e-05,
"loss": 3.9359,
"step": 1277440
},
{
"epoch": 0.02,
"learning_rate": 2.907619288465457e-05,
"loss": 3.9335,
"step": 1277952
},
{
"epoch": 0.02,
"learning_rate": 2.906780693714405e-05,
"loss": 3.9424,
"step": 1278464
},
{
"epoch": 0.02,
"learning_rate": 2.9059437368437258e-05,
"loss": 3.9394,
"step": 1278976
},
{
"epoch": 0.02,
"learning_rate": 2.9051051420926738e-05,
"loss": 3.9435,
"step": 1279488
},
{
"epoch": 0.02,
"learning_rate": 2.904266547341622e-05,
"loss": 3.9425,
"step": 1280000
},
{
"epoch": 0.02,
"learning_rate": 2.90342795259057e-05,
"loss": 3.9501,
"step": 1280512
},
{
"epoch": 0.02,
"learning_rate": 2.902589357839518e-05,
"loss": 3.9471,
"step": 1281024
},
{
"epoch": 0.02,
"learning_rate": 2.901750763088466e-05,
"loss": 3.947,
"step": 1281536
},
{
"epoch": 0.02,
"learning_rate": 2.900913806217787e-05,
"loss": 3.9509,
"step": 1282048
},
{
"epoch": 0.02,
"learning_rate": 2.900075211466735e-05,
"loss": 3.9503,
"step": 1282560
},
{
"epoch": 0.02,
"learning_rate": 2.899236616715683e-05,
"loss": 3.9383,
"step": 1283072
},
{
"epoch": 0.02,
"learning_rate": 2.8983980219646313e-05,
"loss": 3.9508,
"step": 1283584
},
{
"epoch": 0.02,
"learning_rate": 2.8975594272135793e-05,
"loss": 3.9403,
"step": 1284096
},
{
"epoch": 0.02,
"learning_rate": 2.8967224703429002e-05,
"loss": 3.9512,
"step": 1284608
},
{
"epoch": 0.02,
"learning_rate": 2.8958838755918482e-05,
"loss": 3.93,
"step": 1285120
},
{
"epoch": 0.02,
"learning_rate": 2.895046918721169e-05,
"loss": 3.9455,
"step": 1285632
},
{
"epoch": 0.02,
"learning_rate": 2.8942083239701175e-05,
"loss": 3.9331,
"step": 1286144
},
{
"epoch": 0.02,
"learning_rate": 2.8933697292190655e-05,
"loss": 3.9384,
"step": 1286656
},
{
"epoch": 0.02,
"learning_rate": 2.8925311344680135e-05,
"loss": 3.9283,
"step": 1287168
},
{
"epoch": 0.02,
"learning_rate": 2.8916925397169615e-05,
"loss": 3.9589,
"step": 1287680
},
{
"epoch": 0.02,
"learning_rate": 2.8908539449659095e-05,
"loss": 3.9508,
"step": 1288192
},
{
"epoch": 0.02,
"learning_rate": 2.8900169880952304e-05,
"loss": 3.9373,
"step": 1288704
},
{
"epoch": 0.02,
"learning_rate": 2.8891783933441784e-05,
"loss": 3.942,
"step": 1289216
},
{
"epoch": 0.02,
"learning_rate": 2.8883397985931264e-05,
"loss": 3.9462,
"step": 1289728
},
{
"epoch": 0.02,
"learning_rate": 2.8875012038420747e-05,
"loss": 3.9546,
"step": 1290240
},
{
"epoch": 0.02,
"learning_rate": 2.8866642469713956e-05,
"loss": 3.9489,
"step": 1290752
},
{
"epoch": 0.02,
"learning_rate": 2.8858256522203436e-05,
"loss": 3.9434,
"step": 1291264
},
{
"epoch": 0.02,
"learning_rate": 2.8849870574692916e-05,
"loss": 3.9535,
"step": 1291776
},
{
"epoch": 0.02,
"learning_rate": 2.8841484627182396e-05,
"loss": 3.937,
"step": 1292288
},
{
"epoch": 0.02,
"learning_rate": 2.8833098679671876e-05,
"loss": 3.9524,
"step": 1292800
},
{
"epoch": 0.02,
"learning_rate": 2.882472911096509e-05,
"loss": 3.9427,
"step": 1293312
},
{
"epoch": 0.02,
"learning_rate": 2.881634316345457e-05,
"loss": 3.9455,
"step": 1293824
},
{
"epoch": 0.02,
"learning_rate": 2.880795721594405e-05,
"loss": 3.9445,
"step": 1294336
},
{
"epoch": 0.02,
"learning_rate": 2.8799571268433528e-05,
"loss": 3.9359,
"step": 1294848
},
{
"epoch": 0.02,
"learning_rate": 2.8791185320923008e-05,
"loss": 3.9462,
"step": 1295360
},
{
"epoch": 0.02,
"learning_rate": 2.8782799373412485e-05,
"loss": 3.9452,
"step": 1295872
},
{
"epoch": 0.02,
"learning_rate": 2.8774413425901965e-05,
"loss": 3.9464,
"step": 1296384
},
{
"epoch": 0.02,
"learning_rate": 2.876604385719518e-05,
"loss": 3.9441,
"step": 1296896
},
{
"epoch": 0.02,
"learning_rate": 2.8757657909684654e-05,
"loss": 3.9407,
"step": 1297408
},
{
"epoch": 0.03,
"eval_loss": 4.011997699737549,
"eval_runtime": 299.7104,
"eval_samples_per_second": 1273.199,
"eval_steps_per_second": 39.788,
"step": 1297440
},
{
"epoch": 1.0,
"learning_rate": 2.8749271962174134e-05,
"loss": 3.9351,
"step": 1297920
},
{
"epoch": 1.0,
"learning_rate": 2.8740886014663614e-05,
"loss": 3.9352,
"step": 1298432
},
{
"epoch": 1.0,
"learning_rate": 2.873251644595683e-05,
"loss": 3.9504,
"step": 1298944
},
{
"epoch": 1.0,
"learning_rate": 2.8724130498446306e-05,
"loss": 3.939,
"step": 1299456
},
{
"epoch": 1.0,
"learning_rate": 2.8715744550935786e-05,
"loss": 3.9578,
"step": 1299968
},
{
"epoch": 1.0,
"learning_rate": 2.8707358603425266e-05,
"loss": 3.9331,
"step": 1300480
},
{
"epoch": 1.0,
"learning_rate": 2.8698972655914746e-05,
"loss": 3.94,
"step": 1300992
},
{
"epoch": 1.0,
"learning_rate": 2.8690586708404226e-05,
"loss": 3.9282,
"step": 1301504
},
{
"epoch": 1.0,
"learning_rate": 2.8682200760893706e-05,
"loss": 3.9469,
"step": 1302016
},
{
"epoch": 1.0,
"learning_rate": 2.8673814813383186e-05,
"loss": 3.9413,
"step": 1302528
},
{
"epoch": 1.0,
"learning_rate": 2.866542886587267e-05,
"loss": 3.9457,
"step": 1303040
},
{
"epoch": 1.0,
"learning_rate": 2.865704291836215e-05,
"loss": 3.9454,
"step": 1303552
},
{
"epoch": 1.0,
"learning_rate": 2.864867334965536e-05,
"loss": 3.9335,
"step": 1304064
},
{
"epoch": 1.0,
"learning_rate": 2.8640287402144838e-05,
"loss": 3.9329,
"step": 1304576
},
{
"epoch": 1.0,
"learning_rate": 2.8631901454634318e-05,
"loss": 3.9342,
"step": 1305088
},
{
"epoch": 1.0,
"learning_rate": 2.862353188592753e-05,
"loss": 3.9316,
"step": 1305600
},
{
"epoch": 1.0,
"learning_rate": 2.861514593841701e-05,
"loss": 3.9422,
"step": 1306112
},
{
"epoch": 1.0,
"learning_rate": 2.860675999090649e-05,
"loss": 3.9388,
"step": 1306624
},
{
"epoch": 1.0,
"learning_rate": 2.859837404339597e-05,
"loss": 3.9368,
"step": 1307136
},
{
"epoch": 1.0,
"learning_rate": 2.858998809588545e-05,
"loss": 3.9595,
"step": 1307648
},
{
"epoch": 1.0,
"learning_rate": 2.858160214837493e-05,
"loss": 3.9339,
"step": 1308160
},
{
"epoch": 1.0,
"learning_rate": 2.857321620086441e-05,
"loss": 3.9473,
"step": 1308672
},
{
"epoch": 1.0,
"learning_rate": 2.856483025335389e-05,
"loss": 3.9465,
"step": 1309184
},
{
"epoch": 1.0,
"learning_rate": 2.8556444305843367e-05,
"loss": 3.9526,
"step": 1309696
},
{
"epoch": 1.0,
"learning_rate": 2.8548058358332847e-05,
"loss": 3.9311,
"step": 1310208
},
{
"epoch": 1.0,
"learning_rate": 2.8539672410822327e-05,
"loss": 3.9388,
"step": 1310720
},
{
"epoch": 1.0,
"learning_rate": 2.8531286463311807e-05,
"loss": 3.9342,
"step": 1311232
},
{
"epoch": 1.0,
"learning_rate": 2.8522916894605016e-05,
"loss": 3.9425,
"step": 1311744
},
{
"epoch": 1.0,
"learning_rate": 2.85145309470945e-05,
"loss": 3.9274,
"step": 1312256
},
{
"epoch": 1.01,
"learning_rate": 2.8506161378387715e-05,
"loss": 3.9333,
"step": 1312768
},
{
"epoch": 1.01,
"learning_rate": 2.8497775430877195e-05,
"loss": 3.9433,
"step": 1313280
},
{
"epoch": 1.01,
"learning_rate": 2.8489389483366668e-05,
"loss": 3.942,
"step": 1313792
},
{
"epoch": 1.01,
"learning_rate": 2.8481003535856148e-05,
"loss": 3.9422,
"step": 1314304
},
{
"epoch": 1.01,
"learning_rate": 2.8472617588345628e-05,
"loss": 3.9496,
"step": 1314816
},
{
"epoch": 1.01,
"learning_rate": 2.846424801963884e-05,
"loss": 3.9442,
"step": 1315328
},
{
"epoch": 1.01,
"learning_rate": 2.845586207212832e-05,
"loss": 3.9421,
"step": 1315840
},
{
"epoch": 1.01,
"learning_rate": 2.84474761246178e-05,
"loss": 3.9351,
"step": 1316352
},
{
"epoch": 1.01,
"learning_rate": 2.843909017710728e-05,
"loss": 3.9464,
"step": 1316864
},
{
"epoch": 1.01,
"learning_rate": 2.843070422959676e-05,
"loss": 3.9317,
"step": 1317376
},
{
"epoch": 1.01,
"learning_rate": 2.842233466088997e-05,
"loss": 3.9381,
"step": 1317888
},
{
"epoch": 1.01,
"learning_rate": 2.8413948713379453e-05,
"loss": 3.9439,
"step": 1318400
},
{
"epoch": 1.01,
"learning_rate": 2.8405562765868933e-05,
"loss": 3.9442,
"step": 1318912
},
{
"epoch": 1.01,
"learning_rate": 2.8397176818358413e-05,
"loss": 3.9315,
"step": 1319424
},
{
"epoch": 1.01,
"learning_rate": 2.8388790870847893e-05,
"loss": 3.9408,
"step": 1319936
},
{
"epoch": 1.01,
"learning_rate": 2.8380404923337373e-05,
"loss": 3.9467,
"step": 1320448
},
{
"epoch": 1.01,
"learning_rate": 2.8372035354630582e-05,
"loss": 3.9417,
"step": 1320960
},
{
"epoch": 1.01,
"learning_rate": 2.8363649407120062e-05,
"loss": 3.9453,
"step": 1321472
},
{
"epoch": 1.01,
"learning_rate": 2.8355263459609542e-05,
"loss": 3.9168,
"step": 1321984
},
{
"epoch": 1.01,
"learning_rate": 2.8346877512099025e-05,
"loss": 3.9283,
"step": 1322496
},
{
"epoch": 1.01,
"learning_rate": 2.8338491564588505e-05,
"loss": 3.9467,
"step": 1323008
},
{
"epoch": 1.01,
"learning_rate": 2.8330105617077985e-05,
"loss": 3.9408,
"step": 1323520
},
{
"epoch": 1.01,
"learning_rate": 2.8321736048371194e-05,
"loss": 3.9354,
"step": 1324032
},
{
"epoch": 1.01,
"learning_rate": 2.8313350100860674e-05,
"loss": 3.9201,
"step": 1324544
},
{
"epoch": 1.01,
"learning_rate": 2.8304964153350154e-05,
"loss": 3.926,
"step": 1325056
},
{
"epoch": 1.01,
"learning_rate": 2.8296578205839634e-05,
"loss": 3.9214,
"step": 1325568
},
{
"epoch": 1.01,
"learning_rate": 2.8288208637132846e-05,
"loss": 3.9479,
"step": 1326080
},
{
"epoch": 1.01,
"learning_rate": 2.8279822689622326e-05,
"loss": 3.925,
"step": 1326592
},
{
"epoch": 1.01,
"learning_rate": 2.8271436742111806e-05,
"loss": 3.9407,
"step": 1327104
},
{
"epoch": 1.01,
"learning_rate": 2.8263050794601286e-05,
"loss": 3.9411,
"step": 1327616
},
{
"epoch": 1.01,
"learning_rate": 2.8254664847090766e-05,
"loss": 3.9252,
"step": 1328128
},
{
"epoch": 1.01,
"learning_rate": 2.8246278899580246e-05,
"loss": 3.933,
"step": 1328640
},
{
"epoch": 1.01,
"learning_rate": 2.8237892952069726e-05,
"loss": 3.9281,
"step": 1329152
},
{
"epoch": 1.01,
"learning_rate": 2.822952338336294e-05,
"loss": 3.925,
"step": 1329664
},
{
"epoch": 1.01,
"learning_rate": 2.822113743585242e-05,
"loss": 3.9261,
"step": 1330176
},
{
"epoch": 1.01,
"learning_rate": 2.82127514883419e-05,
"loss": 3.9437,
"step": 1330688
},
{
"epoch": 1.01,
"learning_rate": 2.820436554083138e-05,
"loss": 3.9375,
"step": 1331200
},
{
"epoch": 1.01,
"learning_rate": 2.8195979593320855e-05,
"loss": 3.925,
"step": 1331712
},
{
"epoch": 1.01,
"learning_rate": 2.818761002461407e-05,
"loss": 3.9248,
"step": 1332224
},
{
"epoch": 1.01,
"learning_rate": 2.817922407710355e-05,
"loss": 3.9287,
"step": 1332736
},
{
"epoch": 1.01,
"learning_rate": 2.817083812959303e-05,
"loss": 3.9408,
"step": 1333248
},
{
"epoch": 1.01,
"learning_rate": 2.8162452182082504e-05,
"loss": 3.9472,
"step": 1333760
},
{
"epoch": 1.01,
"learning_rate": 2.8154066234571984e-05,
"loss": 3.9397,
"step": 1334272
},
{
"epoch": 1.01,
"learning_rate": 2.8145680287061464e-05,
"loss": 3.949,
"step": 1334784
},
{
"epoch": 1.01,
"learning_rate": 2.8137294339550947e-05,
"loss": 3.9474,
"step": 1335296
},
{
"epoch": 1.01,
"learning_rate": 2.8128924770844156e-05,
"loss": 3.9468,
"step": 1335808
},
{
"epoch": 1.01,
"learning_rate": 2.8120538823333636e-05,
"loss": 3.9381,
"step": 1336320
},
{
"epoch": 1.01,
"learning_rate": 2.8112169254626852e-05,
"loss": 3.9367,
"step": 1336832
},
{
"epoch": 1.01,
"learning_rate": 2.8103783307116325e-05,
"loss": 3.9404,
"step": 1337344
},
{
"epoch": 1.01,
"learning_rate": 2.809539735960581e-05,
"loss": 3.9355,
"step": 1337856
},
{
"epoch": 1.01,
"learning_rate": 2.808701141209529e-05,
"loss": 3.9335,
"step": 1338368
},
{
"epoch": 1.01,
"learning_rate": 2.807862546458477e-05,
"loss": 3.9412,
"step": 1338880
},
{
"epoch": 1.01,
"learning_rate": 2.807023951707425e-05,
"loss": 3.9471,
"step": 1339392
},
{
"epoch": 1.01,
"learning_rate": 2.806185356956373e-05,
"loss": 3.9397,
"step": 1339904
},
{
"epoch": 1.01,
"learning_rate": 2.8053484000856938e-05,
"loss": 3.9273,
"step": 1340416
},
{
"epoch": 1.01,
"learning_rate": 2.8045098053346418e-05,
"loss": 3.927,
"step": 1340928
},
{
"epoch": 1.01,
"learning_rate": 2.80367121058359e-05,
"loss": 3.9361,
"step": 1341440
},
{
"epoch": 1.01,
"learning_rate": 2.802832615832538e-05,
"loss": 3.9452,
"step": 1341952
},
{
"epoch": 1.01,
"learning_rate": 2.801994021081486e-05,
"loss": 3.934,
"step": 1342464
},
{
"epoch": 1.01,
"learning_rate": 2.801157064210807e-05,
"loss": 3.9378,
"step": 1342976
},
{
"epoch": 1.02,
"learning_rate": 2.800318469459755e-05,
"loss": 3.9413,
"step": 1343488
},
{
"epoch": 1.02,
"learning_rate": 2.799479874708703e-05,
"loss": 3.9339,
"step": 1344000
},
{
"epoch": 1.02,
"learning_rate": 2.798641279957651e-05,
"loss": 3.9325,
"step": 1344512
},
{
"epoch": 1.02,
"learning_rate": 2.7978026852065993e-05,
"loss": 3.9328,
"step": 1345024
},
{
"epoch": 1.02,
"learning_rate": 2.7969657283359202e-05,
"loss": 3.9392,
"step": 1345536
},
{
"epoch": 1.02,
"learning_rate": 2.7961271335848682e-05,
"loss": 3.9413,
"step": 1346048
},
{
"epoch": 1.02,
"learning_rate": 2.7952885388338162e-05,
"loss": 3.94,
"step": 1346560
},
{
"epoch": 1.02,
"learning_rate": 2.7944499440827642e-05,
"loss": 3.9262,
"step": 1347072
},
{
"epoch": 1.02,
"learning_rate": 2.7936129872120855e-05,
"loss": 3.9403,
"step": 1347584
},
{
"epoch": 1.02,
"learning_rate": 2.7927743924610335e-05,
"loss": 3.9351,
"step": 1348096
},
{
"epoch": 1.02,
"learning_rate": 2.7919357977099815e-05,
"loss": 3.9454,
"step": 1348608
},
{
"epoch": 1.02,
"learning_rate": 2.7910972029589295e-05,
"loss": 3.9383,
"step": 1349120
},
{
"epoch": 1.02,
"learning_rate": 2.7902586082078774e-05,
"loss": 3.9404,
"step": 1349632
},
{
"epoch": 1.02,
"learning_rate": 2.7894216513371984e-05,
"loss": 3.9389,
"step": 1350144
},
{
"epoch": 1.02,
"learning_rate": 2.7885830565861464e-05,
"loss": 3.9418,
"step": 1350656
},
{
"epoch": 1.02,
"learning_rate": 2.7877444618350947e-05,
"loss": 3.9219,
"step": 1351168
},
{
"epoch": 1.02,
"learning_rate": 2.7869058670840427e-05,
"loss": 3.9281,
"step": 1351680
},
{
"epoch": 1.02,
"learning_rate": 2.7860672723329907e-05,
"loss": 3.9349,
"step": 1352192
},
{
"epoch": 1.02,
"learning_rate": 2.7852286775819387e-05,
"loss": 3.9326,
"step": 1352704
},
{
"epoch": 1.02,
"learning_rate": 2.784390082830886e-05,
"loss": 3.9276,
"step": 1353216
},
{
"epoch": 1.02,
"learning_rate": 2.783551488079834e-05,
"loss": 3.9274,
"step": 1353728
},
{
"epoch": 1.02,
"learning_rate": 2.7827128933287823e-05,
"loss": 3.924,
"step": 1354240
},
{
"epoch": 1.02,
"learning_rate": 2.7818742985777303e-05,
"loss": 3.9335,
"step": 1354752
},
{
"epoch": 1.02,
"learning_rate": 2.7810357038266783e-05,
"loss": 3.9306,
"step": 1355264
},
{
"epoch": 1.02,
"learning_rate": 2.7801971090756263e-05,
"loss": 3.9311,
"step": 1355776
},
{
"epoch": 1.02,
"learning_rate": 2.7793617900853208e-05,
"loss": 3.936,
"step": 1356288
},
{
"epoch": 1.02,
"learning_rate": 2.7785231953342688e-05,
"loss": 3.9408,
"step": 1356800
},
{
"epoch": 1.02,
"learning_rate": 2.7776846005832165e-05,
"loss": 3.9379,
"step": 1357312
},
{
"epoch": 1.02,
"learning_rate": 2.776847643712538e-05,
"loss": 3.9338,
"step": 1357824
},
{
"epoch": 1.02,
"learning_rate": 2.776009048961486e-05,
"loss": 3.9432,
"step": 1358336
},
{
"epoch": 1.02,
"learning_rate": 2.7751704542104334e-05,
"loss": 3.9418,
"step": 1358848
},
{
"epoch": 1.02,
"learning_rate": 2.7743318594593814e-05,
"loss": 3.9306,
"step": 1359360
},
{
"epoch": 1.02,
"learning_rate": 2.7734932647083294e-05,
"loss": 3.9437,
"step": 1359872
},
{
"epoch": 1.02,
"learning_rate": 2.7726546699572774e-05,
"loss": 3.9341,
"step": 1360384
},
{
"epoch": 1.02,
"learning_rate": 2.7718177130865986e-05,
"loss": 3.9429,
"step": 1360896
},
{
"epoch": 1.02,
"learning_rate": 2.7709791183355466e-05,
"loss": 3.9199,
"step": 1361408
},
{
"epoch": 1.02,
"learning_rate": 2.7701405235844946e-05,
"loss": 3.94,
"step": 1361920
},
{
"epoch": 1.02,
"learning_rate": 2.7693019288334426e-05,
"loss": 3.92,
"step": 1362432
},
{
"epoch": 1.02,
"learning_rate": 2.7684649719627635e-05,
"loss": 3.9287,
"step": 1362944
},
{
"epoch": 1.02,
"learning_rate": 2.767626377211712e-05,
"loss": 3.9209,
"step": 1363456
},
{
"epoch": 1.02,
"learning_rate": 2.7667877824606598e-05,
"loss": 3.9501,
"step": 1363968
},
{
"epoch": 1.02,
"learning_rate": 2.7659491877096078e-05,
"loss": 3.9417,
"step": 1364480
},
{
"epoch": 1.02,
"learning_rate": 2.7651105929585558e-05,
"loss": 3.933,
"step": 1364992
},
{
"epoch": 1.02,
"learning_rate": 2.7642719982075038e-05,
"loss": 3.9303,
"step": 1365504
},
{
"epoch": 1.02,
"learning_rate": 2.7634334034564518e-05,
"loss": 3.9377,
"step": 1366016
},
{
"epoch": 1.02,
"learning_rate": 2.7625948087053998e-05,
"loss": 3.9436,
"step": 1366528
},
{
"epoch": 1.02,
"learning_rate": 2.7617562139543478e-05,
"loss": 3.9392,
"step": 1367040
},
{
"epoch": 1.02,
"learning_rate": 2.7609176192032958e-05,
"loss": 3.9357,
"step": 1367552
},
{
"epoch": 1.02,
"learning_rate": 2.760079024452244e-05,
"loss": 3.9415,
"step": 1368064
},
{
"epoch": 1.02,
"learning_rate": 2.759240429701192e-05,
"loss": 3.9326,
"step": 1368576
},
{
"epoch": 1.02,
"learning_rate": 2.75840183495014e-05,
"loss": 3.9453,
"step": 1369088
},
{
"epoch": 1.02,
"learning_rate": 2.7575632401990874e-05,
"loss": 3.9312,
"step": 1369600
},
{
"epoch": 1.02,
"learning_rate": 2.7567246454480354e-05,
"loss": 3.9374,
"step": 1370112
},
{
"epoch": 1.02,
"learning_rate": 2.7558860506969834e-05,
"loss": 3.9338,
"step": 1370624
},
{
"epoch": 1.02,
"learning_rate": 2.7550507317066783e-05,
"loss": 3.9292,
"step": 1371136
},
{
"epoch": 1.02,
"learning_rate": 2.7542121369556263e-05,
"loss": 3.9366,
"step": 1371648
},
{
"epoch": 1.02,
"learning_rate": 2.7533751800849472e-05,
"loss": 3.9365,
"step": 1372160
},
{
"epoch": 1.02,
"learning_rate": 2.7525365853338952e-05,
"loss": 3.939,
"step": 1372672
},
{
"epoch": 1.02,
"learning_rate": 2.751697990582843e-05,
"loss": 3.9339,
"step": 1373184
},
{
"epoch": 1.02,
"learning_rate": 2.750859395831791e-05,
"loss": 3.9301,
"step": 1373696
},
{
"epoch": 1.03,
"eval_loss": 4.008100509643555,
"eval_runtime": 300.6516,
"eval_samples_per_second": 1269.213,
"eval_steps_per_second": 39.664,
"step": 1373760
},
{
"epoch": 0.0,
"learning_rate": 2.7500208010807395e-05,
"loss": 3.928,
"step": 1374208
},
{
"epoch": 0.0,
"learning_rate": 2.7491822063296875e-05,
"loss": 3.9272,
"step": 1374720
},
{
"epoch": 0.0,
"learning_rate": 2.7483436115786348e-05,
"loss": 3.9397,
"step": 1375232
},
{
"epoch": 0.0,
"learning_rate": 2.7475050168275828e-05,
"loss": 3.9294,
"step": 1375744
},
{
"epoch": 0.0,
"learning_rate": 2.7466664220765308e-05,
"loss": 3.9519,
"step": 1376256
},
{
"epoch": 0.0,
"learning_rate": 2.7458278273254788e-05,
"loss": 3.9226,
"step": 1376768
},
{
"epoch": 0.0,
"learning_rate": 2.744989232574427e-05,
"loss": 3.9338,
"step": 1377280
},
{
"epoch": 0.0,
"learning_rate": 2.744150637823375e-05,
"loss": 3.9199,
"step": 1377792
},
{
"epoch": 0.0,
"learning_rate": 2.743312043072323e-05,
"loss": 3.9382,
"step": 1378304
},
{
"epoch": 0.0,
"learning_rate": 2.742473448321271e-05,
"loss": 3.9315,
"step": 1378816
},
{
"epoch": 0.0,
"learning_rate": 2.741634853570219e-05,
"loss": 3.936,
"step": 1379328
},
{
"epoch": 0.0,
"learning_rate": 2.740796258819167e-05,
"loss": 3.9353,
"step": 1379840
},
{
"epoch": 0.0,
"learning_rate": 2.739959301948488e-05,
"loss": 3.9232,
"step": 1380352
},
{
"epoch": 0.0,
"learning_rate": 2.7391207071974364e-05,
"loss": 3.9266,
"step": 1380864
},
{
"epoch": 0.0,
"learning_rate": 2.7382821124463843e-05,
"loss": 3.9285,
"step": 1381376
},
{
"epoch": 0.0,
"learning_rate": 2.7374435176953323e-05,
"loss": 3.925,
"step": 1381888
},
{
"epoch": 0.0,
"learning_rate": 2.7366049229442803e-05,
"loss": 3.9292,
"step": 1382400
},
{
"epoch": 0.0,
"learning_rate": 2.7357663281932283e-05,
"loss": 3.9318,
"step": 1382912
},
{
"epoch": 0.0,
"learning_rate": 2.7349277334421763e-05,
"loss": 3.928,
"step": 1383424
},
{
"epoch": 0.0,
"learning_rate": 2.734089138691124e-05,
"loss": 3.9505,
"step": 1383936
},
{
"epoch": 0.0,
"learning_rate": 2.733250543940072e-05,
"loss": 3.9261,
"step": 1384448
},
{
"epoch": 0.0,
"learning_rate": 2.73241194918902e-05,
"loss": 3.9351,
"step": 1384960
},
{
"epoch": 0.0,
"learning_rate": 2.731574992318341e-05,
"loss": 3.9374,
"step": 1385472
},
{
"epoch": 0.0,
"learning_rate": 2.730736397567289e-05,
"loss": 3.9411,
"step": 1385984
},
{
"epoch": 0.0,
"learning_rate": 2.729897802816237e-05,
"loss": 3.9235,
"step": 1386496
},
{
"epoch": 0.0,
"learning_rate": 2.729059208065185e-05,
"loss": 3.9345,
"step": 1387008
},
{
"epoch": 0.0,
"learning_rate": 2.728220613314133e-05,
"loss": 3.9255,
"step": 1387520
},
{
"epoch": 0.0,
"learning_rate": 2.7273820185630812e-05,
"loss": 3.932,
"step": 1388032
},
{
"epoch": 0.0,
"learning_rate": 2.7265434238120292e-05,
"loss": 3.9201,
"step": 1388544
},
{
"epoch": 0.01,
"learning_rate": 2.7257048290609772e-05,
"loss": 3.9221,
"step": 1389056
},
{
"epoch": 0.01,
"learning_rate": 2.7248662343099252e-05,
"loss": 3.9338,
"step": 1389568
},
{
"epoch": 0.01,
"learning_rate": 2.724029277439246e-05,
"loss": 3.9356,
"step": 1390080
},
{
"epoch": 0.01,
"learning_rate": 2.723190682688194e-05,
"loss": 3.936,
"step": 1390592
},
{
"epoch": 0.01,
"learning_rate": 2.7223537258175153e-05,
"loss": 3.9401,
"step": 1391104
},
{
"epoch": 0.01,
"learning_rate": 2.7215151310664633e-05,
"loss": 3.9326,
"step": 1391616
},
{
"epoch": 0.01,
"learning_rate": 2.7206765363154113e-05,
"loss": 3.9358,
"step": 1392128
},
{
"epoch": 0.01,
"learning_rate": 2.7198379415643593e-05,
"loss": 3.9238,
"step": 1392640
},
{
"epoch": 0.01,
"learning_rate": 2.7189993468133073e-05,
"loss": 3.9392,
"step": 1393152
},
{
"epoch": 0.01,
"learning_rate": 2.7181607520622553e-05,
"loss": 3.9217,
"step": 1393664
},
{
"epoch": 0.01,
"learning_rate": 2.7173237951915766e-05,
"loss": 3.9301,
"step": 1394176
},
{
"epoch": 0.01,
"learning_rate": 2.7164852004405246e-05,
"loss": 3.9299,
"step": 1394688
},
{
"epoch": 0.01,
"learning_rate": 2.7156466056894726e-05,
"loss": 3.9376,
"step": 1395200
},
{
"epoch": 0.01,
"learning_rate": 2.7148080109384206e-05,
"loss": 3.9277,
"step": 1395712
},
{
"epoch": 0.01,
"learning_rate": 2.7139710540677415e-05,
"loss": 3.9285,
"step": 1396224
},
{
"epoch": 0.01,
"learning_rate": 2.7131324593166895e-05,
"loss": 3.9382,
"step": 1396736
},
{
"epoch": 0.01,
"learning_rate": 2.7122938645656375e-05,
"loss": 3.9347,
"step": 1397248
},
{
"epoch": 0.01,
"learning_rate": 2.7114552698145858e-05,
"loss": 3.9353,
"step": 1397760
},
{
"epoch": 0.01,
"learning_rate": 2.7106166750635338e-05,
"loss": 3.9168,
"step": 1398272
},
{
"epoch": 0.01,
"learning_rate": 2.7097780803124818e-05,
"loss": 3.9161,
"step": 1398784
},
{
"epoch": 0.01,
"learning_rate": 2.7089411234418027e-05,
"loss": 3.9332,
"step": 1399296
},
{
"epoch": 0.01,
"learning_rate": 2.7081025286907507e-05,
"loss": 3.931,
"step": 1399808
},
{
"epoch": 0.01,
"learning_rate": 2.7072639339396987e-05,
"loss": 3.9273,
"step": 1400320
},
{
"epoch": 0.01,
"learning_rate": 2.7064253391886467e-05,
"loss": 3.9132,
"step": 1400832
},
{
"epoch": 0.01,
"learning_rate": 2.705586744437595e-05,
"loss": 3.9161,
"step": 1401344
},
{
"epoch": 0.01,
"learning_rate": 2.7047481496865423e-05,
"loss": 3.9199,
"step": 1401856
},
{
"epoch": 0.01,
"learning_rate": 2.703911192815864e-05,
"loss": 3.9317,
"step": 1402368
},
{
"epoch": 0.01,
"learning_rate": 2.703072598064812e-05,
"loss": 3.9171,
"step": 1402880
},
{
"epoch": 0.01,
"learning_rate": 2.70223400331376e-05,
"loss": 3.9318,
"step": 1403392
},
{
"epoch": 0.01,
"learning_rate": 2.7013954085627076e-05,
"loss": 3.9286,
"step": 1403904
},
{
"epoch": 0.01,
"learning_rate": 2.700558451692029e-05,
"loss": 3.9205,
"step": 1404416
},
{
"epoch": 0.01,
"learning_rate": 2.699719856940977e-05,
"loss": 3.9233,
"step": 1404928
},
{
"epoch": 0.01,
"learning_rate": 2.6988812621899245e-05,
"loss": 3.9211,
"step": 1405440
},
{
"epoch": 0.01,
"learning_rate": 2.698044305319246e-05,
"loss": 3.9123,
"step": 1405952
},
{
"epoch": 0.01,
"learning_rate": 2.697205710568194e-05,
"loss": 3.924,
"step": 1406464
},
{
"epoch": 0.01,
"learning_rate": 2.696367115817142e-05,
"loss": 3.9267,
"step": 1406976
},
{
"epoch": 0.01,
"learning_rate": 2.6955285210660897e-05,
"loss": 3.9357,
"step": 1407488
},
{
"epoch": 0.01,
"learning_rate": 2.6946899263150377e-05,
"loss": 3.9121,
"step": 1408000
},
{
"epoch": 0.01,
"learning_rate": 2.6938513315639857e-05,
"loss": 3.9153,
"step": 1408512
},
{
"epoch": 0.01,
"learning_rate": 2.6930127368129337e-05,
"loss": 3.9166,
"step": 1409024
},
{
"epoch": 0.01,
"learning_rate": 2.6921741420618817e-05,
"loss": 3.9387,
"step": 1409536
},
{
"epoch": 0.01,
"learning_rate": 2.6913355473108297e-05,
"loss": 3.9317,
"step": 1410048
},
{
"epoch": 0.01,
"learning_rate": 2.690496952559778e-05,
"loss": 3.93,
"step": 1410560
},
{
"epoch": 0.01,
"learning_rate": 2.689658357808726e-05,
"loss": 3.943,
"step": 1411072
},
{
"epoch": 0.01,
"learning_rate": 2.688819763057674e-05,
"loss": 3.9388,
"step": 1411584
},
{
"epoch": 0.01,
"learning_rate": 2.687984444067368e-05,
"loss": 3.938,
"step": 1412096
},
{
"epoch": 0.01,
"learning_rate": 2.6871458493163158e-05,
"loss": 3.9278,
"step": 1412608
},
{
"epoch": 0.01,
"learning_rate": 2.686307254565264e-05,
"loss": 3.9319,
"step": 1413120
},
{
"epoch": 0.01,
"learning_rate": 2.685468659814212e-05,
"loss": 3.9289,
"step": 1413632
},
{
"epoch": 0.01,
"learning_rate": 2.68463006506316e-05,
"loss": 3.9243,
"step": 1414144
},
{
"epoch": 0.01,
"learning_rate": 2.683791470312108e-05,
"loss": 3.9284,
"step": 1414656
},
{
"epoch": 0.01,
"learning_rate": 2.682952875561056e-05,
"loss": 3.9294,
"step": 1415168
},
{
"epoch": 0.01,
"learning_rate": 2.682115918690377e-05,
"loss": 3.9385,
"step": 1415680
},
{
"epoch": 0.01,
"learning_rate": 2.681277323939325e-05,
"loss": 3.9294,
"step": 1416192
},
{
"epoch": 0.01,
"learning_rate": 2.680438729188273e-05,
"loss": 3.9229,
"step": 1416704
},
{
"epoch": 0.01,
"learning_rate": 2.6796001344372214e-05,
"loss": 3.9161,
"step": 1417216
},
{
"epoch": 0.01,
"learning_rate": 2.6787631775665423e-05,
"loss": 3.9277,
"step": 1417728
},
{
"epoch": 0.01,
"learning_rate": 2.6779245828154903e-05,
"loss": 3.9337,
"step": 1418240
},
{
"epoch": 0.01,
"learning_rate": 2.6770859880644383e-05,
"loss": 3.9269,
"step": 1418752
},
{
"epoch": 0.01,
"learning_rate": 2.6762473933133863e-05,
"loss": 3.926,
"step": 1419264
},
{
"epoch": 0.02,
"learning_rate": 2.6754087985623343e-05,
"loss": 3.9341,
"step": 1419776
},
{
"epoch": 0.02,
"learning_rate": 2.6745718416916555e-05,
"loss": 3.9179,
"step": 1420288
},
{
"epoch": 0.02,
"learning_rate": 2.6737332469406035e-05,
"loss": 3.929,
"step": 1420800
},
{
"epoch": 0.02,
"learning_rate": 2.6728962900699244e-05,
"loss": 3.9232,
"step": 1421312
},
{
"epoch": 0.02,
"learning_rate": 2.6720593331992457e-05,
"loss": 3.9334,
"step": 1421824
},
{
"epoch": 0.02,
"learning_rate": 2.6712207384481937e-05,
"loss": 3.9335,
"step": 1422336
},
{
"epoch": 0.02,
"learning_rate": 2.6703821436971417e-05,
"loss": 3.9272,
"step": 1422848
},
{
"epoch": 0.02,
"learning_rate": 2.6695435489460897e-05,
"loss": 3.9187,
"step": 1423360
},
{
"epoch": 0.02,
"learning_rate": 2.6687049541950377e-05,
"loss": 3.933,
"step": 1423872
},
{
"epoch": 0.02,
"learning_rate": 2.6678663594439856e-05,
"loss": 3.9219,
"step": 1424384
},
{
"epoch": 0.02,
"learning_rate": 2.6670277646929336e-05,
"loss": 3.9421,
"step": 1424896
},
{
"epoch": 0.02,
"learning_rate": 2.6661891699418816e-05,
"loss": 3.9298,
"step": 1425408
},
{
"epoch": 0.02,
"learning_rate": 2.6653505751908296e-05,
"loss": 3.9314,
"step": 1425920
},
{
"epoch": 0.02,
"learning_rate": 2.6645119804397776e-05,
"loss": 3.9261,
"step": 1426432
},
{
"epoch": 0.02,
"learning_rate": 2.663673385688726e-05,
"loss": 3.9382,
"step": 1426944
},
{
"epoch": 0.02,
"learning_rate": 2.6628347909376733e-05,
"loss": 3.9116,
"step": 1427456
},
{
"epoch": 0.02,
"learning_rate": 2.661997834066995e-05,
"loss": 3.9196,
"step": 1427968
},
{
"epoch": 0.02,
"learning_rate": 2.661159239315943e-05,
"loss": 3.9248,
"step": 1428480
},
{
"epoch": 0.02,
"learning_rate": 2.6603206445648905e-05,
"loss": 3.9249,
"step": 1428992
},
{
"epoch": 0.02,
"learning_rate": 2.6594820498138385e-05,
"loss": 3.9165,
"step": 1429504
},
{
"epoch": 0.02,
"learning_rate": 2.6586434550627865e-05,
"loss": 3.9218,
"step": 1430016
},
{
"epoch": 0.02,
"learning_rate": 2.6578048603117345e-05,
"loss": 3.9147,
"step": 1430528
},
{
"epoch": 0.02,
"learning_rate": 2.6569662655606825e-05,
"loss": 3.9245,
"step": 1431040
},
{
"epoch": 0.02,
"learning_rate": 2.6561276708096305e-05,
"loss": 3.9218,
"step": 1431552
},
{
"epoch": 0.02,
"learning_rate": 2.6552890760585785e-05,
"loss": 3.9193,
"step": 1432064
},
{
"epoch": 0.02,
"learning_rate": 2.6544521191878997e-05,
"loss": 3.9323,
"step": 1432576
},
{
"epoch": 0.02,
"learning_rate": 2.6536135244368477e-05,
"loss": 3.932,
"step": 1433088
},
{
"epoch": 0.02,
"learning_rate": 2.6527765675661687e-05,
"loss": 3.932,
"step": 1433600
},
{
"epoch": 0.02,
"learning_rate": 2.6519396106954902e-05,
"loss": 3.9223,
"step": 1434112
},
{
"epoch": 0.02,
"learning_rate": 2.6511010159444376e-05,
"loss": 3.9332,
"step": 1434624
},
{
"epoch": 0.02,
"learning_rate": 2.650262421193386e-05,
"loss": 3.9289,
"step": 1435136
},
{
"epoch": 0.02,
"learning_rate": 2.649423826442334e-05,
"loss": 3.9226,
"step": 1435648
},
{
"epoch": 0.02,
"learning_rate": 2.648585231691282e-05,
"loss": 3.9394,
"step": 1436160
},
{
"epoch": 0.02,
"learning_rate": 2.64774663694023e-05,
"loss": 3.9213,
"step": 1436672
},
{
"epoch": 0.02,
"learning_rate": 2.646908042189178e-05,
"loss": 3.9331,
"step": 1437184
},
{
"epoch": 0.02,
"learning_rate": 2.646069447438126e-05,
"loss": 3.913,
"step": 1437696
},
{
"epoch": 0.02,
"learning_rate": 2.645230852687074e-05,
"loss": 3.9303,
"step": 1438208
},
{
"epoch": 0.02,
"learning_rate": 2.644393895816395e-05,
"loss": 3.9121,
"step": 1438720
},
{
"epoch": 0.02,
"learning_rate": 2.643555301065343e-05,
"loss": 3.922,
"step": 1439232
},
{
"epoch": 0.02,
"learning_rate": 2.642716706314291e-05,
"loss": 3.9134,
"step": 1439744
},
{
"epoch": 0.02,
"learning_rate": 2.641878111563239e-05,
"loss": 3.937,
"step": 1440256
},
{
"epoch": 0.02,
"learning_rate": 2.64104115469256e-05,
"loss": 3.9298,
"step": 1440768
},
{
"epoch": 0.02,
"learning_rate": 2.640202559941508e-05,
"loss": 3.927,
"step": 1441280
},
{
"epoch": 0.02,
"learning_rate": 2.639363965190456e-05,
"loss": 3.9222,
"step": 1441792
},
{
"epoch": 0.02,
"learning_rate": 2.6385253704394043e-05,
"loss": 3.9267,
"step": 1442304
},
{
"epoch": 0.02,
"learning_rate": 2.6376867756883523e-05,
"loss": 3.9409,
"step": 1442816
},
{
"epoch": 0.02,
"learning_rate": 2.6368481809373003e-05,
"loss": 3.9267,
"step": 1443328
},
{
"epoch": 0.02,
"learning_rate": 2.6360112240666212e-05,
"loss": 3.9268,
"step": 1443840
},
{
"epoch": 0.02,
"learning_rate": 2.6351726293155692e-05,
"loss": 3.9358,
"step": 1444352
},
{
"epoch": 0.02,
"learning_rate": 2.6343340345645172e-05,
"loss": 3.9277,
"step": 1444864
},
{
"epoch": 0.02,
"learning_rate": 2.6334954398134652e-05,
"loss": 3.9331,
"step": 1445376
},
{
"epoch": 0.02,
"learning_rate": 2.6326584829427865e-05,
"loss": 3.9214,
"step": 1445888
},
{
"epoch": 0.02,
"learning_rate": 2.6318198881917345e-05,
"loss": 3.928,
"step": 1446400
},
{
"epoch": 0.02,
"learning_rate": 2.6309812934406825e-05,
"loss": 3.9251,
"step": 1446912
},
{
"epoch": 0.02,
"learning_rate": 2.6301426986896305e-05,
"loss": 3.9245,
"step": 1447424
},
{
"epoch": 0.02,
"learning_rate": 2.6293057418189514e-05,
"loss": 3.9234,
"step": 1447936
},
{
"epoch": 0.02,
"learning_rate": 2.6284671470678997e-05,
"loss": 3.9335,
"step": 1448448
},
{
"epoch": 0.02,
"learning_rate": 2.6276285523168477e-05,
"loss": 3.9229,
"step": 1448960
},
{
"epoch": 0.02,
"learning_rate": 2.6267899575657957e-05,
"loss": 3.9264,
"step": 1449472
},
{
"epoch": 0.02,
"learning_rate": 2.6259530006951166e-05,
"loss": 3.9233,
"step": 1449984
},
{
"epoch": 0.03,
"eval_loss": 4.003993988037109,
"eval_runtime": 294.7522,
"eval_samples_per_second": 1294.616,
"eval_steps_per_second": 40.458,
"step": 1450080
},
{
"epoch": 1.0,
"learning_rate": 2.6251144059440646e-05,
"loss": 3.924,
"step": 1450496
},
{
"epoch": 1.0,
"learning_rate": 2.6242758111930126e-05,
"loss": 3.9197,
"step": 1451008
},
{
"epoch": 1.0,
"learning_rate": 2.6234372164419606e-05,
"loss": 3.93,
"step": 1451520
},
{
"epoch": 1.0,
"learning_rate": 2.6225986216909086e-05,
"loss": 3.9184,
"step": 1452032
},
{
"epoch": 1.0,
"learning_rate": 2.6217600269398562e-05,
"loss": 3.9473,
"step": 1452544
},
{
"epoch": 1.0,
"learning_rate": 2.6209230700691778e-05,
"loss": 3.9128,
"step": 1453056
},
{
"epoch": 1.0,
"learning_rate": 2.6200844753181258e-05,
"loss": 3.9243,
"step": 1453568
},
{
"epoch": 1.0,
"learning_rate": 2.6192458805670738e-05,
"loss": 3.9122,
"step": 1454080
},
{
"epoch": 1.0,
"learning_rate": 2.6184072858160215e-05,
"loss": 3.9276,
"step": 1454592
},
{
"epoch": 1.0,
"learning_rate": 2.6175686910649695e-05,
"loss": 3.9253,
"step": 1455104
},
{
"epoch": 1.0,
"learning_rate": 2.6167300963139175e-05,
"loss": 3.9225,
"step": 1455616
},
{
"epoch": 1.0,
"learning_rate": 2.615893139443239e-05,
"loss": 3.9279,
"step": 1456128
},
{
"epoch": 1.0,
"learning_rate": 2.61505618257256e-05,
"loss": 3.915,
"step": 1456640
},
{
"epoch": 1.0,
"learning_rate": 2.614217587821508e-05,
"loss": 3.9203,
"step": 1457152
},
{
"epoch": 1.0,
"learning_rate": 2.613378993070456e-05,
"loss": 3.9192,
"step": 1457664
},
{
"epoch": 1.0,
"learning_rate": 2.6125403983194036e-05,
"loss": 3.9188,
"step": 1458176
},
{
"epoch": 1.0,
"learning_rate": 2.6117018035683516e-05,
"loss": 3.9181,
"step": 1458688
},
{
"epoch": 1.0,
"learning_rate": 2.6108632088172996e-05,
"loss": 3.9228,
"step": 1459200
},
{
"epoch": 1.0,
"learning_rate": 2.6100246140662476e-05,
"loss": 3.9229,
"step": 1459712
},
{
"epoch": 1.0,
"learning_rate": 2.6091860193151956e-05,
"loss": 3.9375,
"step": 1460224
},
{
"epoch": 1.0,
"learning_rate": 2.6083474245641436e-05,
"loss": 3.9189,
"step": 1460736
},
{
"epoch": 1.0,
"learning_rate": 2.607510467693465e-05,
"loss": 3.9247,
"step": 1461248
},
{
"epoch": 1.0,
"learning_rate": 2.606671872942413e-05,
"loss": 3.9281,
"step": 1461760
},
{
"epoch": 1.0,
"learning_rate": 2.6058332781913608e-05,
"loss": 3.9345,
"step": 1462272
},
{
"epoch": 1.0,
"learning_rate": 2.6049946834403088e-05,
"loss": 3.9151,
"step": 1462784
},
{
"epoch": 1.0,
"learning_rate": 2.6041577265696297e-05,
"loss": 3.9265,
"step": 1463296
},
{
"epoch": 1.0,
"learning_rate": 2.603320769698951e-05,
"loss": 3.9167,
"step": 1463808
},
{
"epoch": 1.0,
"learning_rate": 2.602482174947899e-05,
"loss": 3.9215,
"step": 1464320
},
{
"epoch": 1.0,
"learning_rate": 2.601643580196847e-05,
"loss": 3.91,
"step": 1464832
},
{
"epoch": 1.01,
"learning_rate": 2.600804985445795e-05,
"loss": 3.9197,
"step": 1465344
},
{
"epoch": 1.01,
"learning_rate": 2.599966390694743e-05,
"loss": 3.9204,
"step": 1465856
},
{
"epoch": 1.01,
"learning_rate": 2.599127795943691e-05,
"loss": 3.9281,
"step": 1466368
},
{
"epoch": 1.01,
"learning_rate": 2.598289201192639e-05,
"loss": 3.9245,
"step": 1466880
},
{
"epoch": 1.01,
"learning_rate": 2.597450606441587e-05,
"loss": 3.9322,
"step": 1467392
},
{
"epoch": 1.01,
"learning_rate": 2.5966120116905353e-05,
"loss": 3.9219,
"step": 1467904
},
{
"epoch": 1.01,
"learning_rate": 2.5957750548198562e-05,
"loss": 3.9286,
"step": 1468416
},
{
"epoch": 1.01,
"learning_rate": 2.594938097949177e-05,
"loss": 3.9166,
"step": 1468928
},
{
"epoch": 1.01,
"learning_rate": 2.594099503198125e-05,
"loss": 3.9294,
"step": 1469440
},
{
"epoch": 1.01,
"learning_rate": 2.593260908447073e-05,
"loss": 3.9123,
"step": 1469952
},
{
"epoch": 1.01,
"learning_rate": 2.5924223136960214e-05,
"loss": 3.922,
"step": 1470464
},
{
"epoch": 1.01,
"learning_rate": 2.5915837189449694e-05,
"loss": 3.9221,
"step": 1470976
},
{
"epoch": 1.01,
"learning_rate": 2.5907451241939174e-05,
"loss": 3.93,
"step": 1471488
},
{
"epoch": 1.01,
"learning_rate": 2.5899065294428654e-05,
"loss": 3.9198,
"step": 1472000
},
{
"epoch": 1.01,
"learning_rate": 2.5890695725721863e-05,
"loss": 3.9207,
"step": 1472512
},
{
"epoch": 1.01,
"learning_rate": 2.5882309778211343e-05,
"loss": 3.9285,
"step": 1473024
},
{
"epoch": 1.01,
"learning_rate": 2.5873923830700823e-05,
"loss": 3.9252,
"step": 1473536
},
{
"epoch": 1.01,
"learning_rate": 2.5865537883190307e-05,
"loss": 3.9261,
"step": 1474048
},
{
"epoch": 1.01,
"learning_rate": 2.5857151935679786e-05,
"loss": 3.915,
"step": 1474560
},
{
"epoch": 1.01,
"learning_rate": 2.5848765988169266e-05,
"loss": 3.8996,
"step": 1475072
},
{
"epoch": 1.01,
"learning_rate": 2.5840380040658746e-05,
"loss": 3.9247,
"step": 1475584
},
{
"epoch": 1.01,
"learning_rate": 2.5831994093148226e-05,
"loss": 3.9206,
"step": 1476096
},
{
"epoch": 1.01,
"learning_rate": 2.5823624524441435e-05,
"loss": 3.9153,
"step": 1476608
},
{
"epoch": 1.01,
"learning_rate": 2.5815238576930915e-05,
"loss": 3.9123,
"step": 1477120
},
{
"epoch": 1.01,
"learning_rate": 2.58068526294204e-05,
"loss": 3.9093,
"step": 1477632
},
{
"epoch": 1.01,
"learning_rate": 2.5798466681909872e-05,
"loss": 3.908,
"step": 1478144
},
{
"epoch": 1.01,
"learning_rate": 2.5790080734399352e-05,
"loss": 3.9249,
"step": 1478656
},
{
"epoch": 1.01,
"learning_rate": 2.5781711165692568e-05,
"loss": 3.9119,
"step": 1479168
},
{
"epoch": 1.01,
"learning_rate": 2.5773325218182048e-05,
"loss": 3.9188,
"step": 1479680
},
{
"epoch": 1.01,
"learning_rate": 2.576495564947526e-05,
"loss": 3.9246,
"step": 1480192
},
{
"epoch": 1.01,
"learning_rate": 2.575656970196474e-05,
"loss": 3.9119,
"step": 1480704
},
{
"epoch": 1.01,
"learning_rate": 2.574818375445422e-05,
"loss": 3.9124,
"step": 1481216
},
{
"epoch": 1.01,
"learning_rate": 2.57397978069437e-05,
"loss": 3.9185,
"step": 1481728
},
{
"epoch": 1.01,
"learning_rate": 2.5731411859433173e-05,
"loss": 3.8993,
"step": 1482240
},
{
"epoch": 1.01,
"learning_rate": 2.572304229072639e-05,
"loss": 3.9174,
"step": 1482752
},
{
"epoch": 1.01,
"learning_rate": 2.571465634321587e-05,
"loss": 3.921,
"step": 1483264
},
{
"epoch": 1.01,
"learning_rate": 2.5706270395705346e-05,
"loss": 3.9246,
"step": 1483776
},
{
"epoch": 1.01,
"learning_rate": 2.5697884448194826e-05,
"loss": 3.9064,
"step": 1484288
},
{
"epoch": 1.01,
"learning_rate": 2.5689498500684306e-05,
"loss": 3.9117,
"step": 1484800
},
{
"epoch": 1.01,
"learning_rate": 2.5681112553173786e-05,
"loss": 3.9059,
"step": 1485312
},
{
"epoch": 1.01,
"learning_rate": 2.5672726605663265e-05,
"loss": 3.9257,
"step": 1485824
},
{
"epoch": 1.01,
"learning_rate": 2.5664357036956478e-05,
"loss": 3.923,
"step": 1486336
},
{
"epoch": 1.01,
"learning_rate": 2.5655971089445958e-05,
"loss": 3.9239,
"step": 1486848
},
{
"epoch": 1.01,
"learning_rate": 2.5647585141935438e-05,
"loss": 3.9332,
"step": 1487360
},
{
"epoch": 1.01,
"learning_rate": 2.5639199194424918e-05,
"loss": 3.9309,
"step": 1487872
},
{
"epoch": 1.01,
"learning_rate": 2.5630813246914398e-05,
"loss": 3.9322,
"step": 1488384
},
{
"epoch": 1.01,
"learning_rate": 2.5622443678207607e-05,
"loss": 3.9141,
"step": 1488896
},
{
"epoch": 1.01,
"learning_rate": 2.561405773069709e-05,
"loss": 3.9233,
"step": 1489408
},
{
"epoch": 1.01,
"learning_rate": 2.560567178318657e-05,
"loss": 3.9255,
"step": 1489920
},
{
"epoch": 1.01,
"learning_rate": 2.559728583567605e-05,
"loss": 3.9154,
"step": 1490432
},
{
"epoch": 1.01,
"learning_rate": 2.558889988816553e-05,
"loss": 3.9245,
"step": 1490944
},
{
"epoch": 1.01,
"learning_rate": 2.558051394065501e-05,
"loss": 3.9197,
"step": 1491456
},
{
"epoch": 1.01,
"learning_rate": 2.557212799314449e-05,
"loss": 3.9286,
"step": 1491968
},
{
"epoch": 1.01,
"learning_rate": 2.556374204563397e-05,
"loss": 3.9228,
"step": 1492480
},
{
"epoch": 1.01,
"learning_rate": 2.555535609812345e-05,
"loss": 3.9068,
"step": 1492992
},
{
"epoch": 1.01,
"learning_rate": 2.554697015061293e-05,
"loss": 3.9117,
"step": 1493504
},
{
"epoch": 1.01,
"learning_rate": 2.553858420310241e-05,
"loss": 3.9214,
"step": 1494016
},
{
"epoch": 1.01,
"learning_rate": 2.5530198255591886e-05,
"loss": 3.9261,
"step": 1494528
},
{
"epoch": 1.01,
"learning_rate": 2.5521828686885102e-05,
"loss": 3.9184,
"step": 1495040
},
{
"epoch": 1.01,
"learning_rate": 2.5513442739374582e-05,
"loss": 3.9163,
"step": 1495552
},
{
"epoch": 1.02,
"learning_rate": 2.5505056791864055e-05,
"loss": 3.9246,
"step": 1496064
},
{
"epoch": 1.02,
"learning_rate": 2.549667084435354e-05,
"loss": 3.9129,
"step": 1496576
},
{
"epoch": 1.02,
"learning_rate": 2.548828489684302e-05,
"loss": 3.9151,
"step": 1497088
},
{
"epoch": 1.02,
"learning_rate": 2.54798989493325e-05,
"loss": 3.9178,
"step": 1497600
},
{
"epoch": 1.02,
"learning_rate": 2.5471529380625708e-05,
"loss": 3.9256,
"step": 1498112
},
{
"epoch": 1.02,
"learning_rate": 2.5463143433115188e-05,
"loss": 3.9274,
"step": 1498624
},
{
"epoch": 1.02,
"learning_rate": 2.5454757485604668e-05,
"loss": 3.9182,
"step": 1499136
},
{
"epoch": 1.02,
"learning_rate": 2.5446371538094148e-05,
"loss": 3.9054,
"step": 1499648
},
{
"epoch": 1.02,
"learning_rate": 2.543798559058363e-05,
"loss": 3.9284,
"step": 1500160
},
{
"epoch": 1.02,
"learning_rate": 2.542959964307311e-05,
"loss": 3.9113,
"step": 1500672
},
{
"epoch": 1.02,
"learning_rate": 2.542121369556259e-05,
"loss": 3.935,
"step": 1501184
},
{
"epoch": 1.02,
"learning_rate": 2.541282774805207e-05,
"loss": 3.924,
"step": 1501696
},
{
"epoch": 1.02,
"learning_rate": 2.540445817934528e-05,
"loss": 3.921,
"step": 1502208
},
{
"epoch": 1.02,
"learning_rate": 2.539607223183476e-05,
"loss": 3.9176,
"step": 1502720
},
{
"epoch": 1.02,
"learning_rate": 2.538768628432424e-05,
"loss": 3.9296,
"step": 1503232
},
{
"epoch": 1.02,
"learning_rate": 2.5379300336813723e-05,
"loss": 3.9038,
"step": 1503744
},
{
"epoch": 1.02,
"learning_rate": 2.5370930768106932e-05,
"loss": 3.9137,
"step": 1504256
},
{
"epoch": 1.02,
"learning_rate": 2.536256119940014e-05,
"loss": 3.9106,
"step": 1504768
},
{
"epoch": 1.02,
"learning_rate": 2.535417525188962e-05,
"loss": 3.9172,
"step": 1505280
},
{
"epoch": 1.02,
"learning_rate": 2.53457893043791e-05,
"loss": 3.9074,
"step": 1505792
},
{
"epoch": 1.02,
"learning_rate": 2.5337403356868585e-05,
"loss": 3.9157,
"step": 1506304
},
{
"epoch": 1.02,
"learning_rate": 2.5329017409358065e-05,
"loss": 3.9102,
"step": 1506816
},
{
"epoch": 1.02,
"learning_rate": 2.5320631461847545e-05,
"loss": 3.9095,
"step": 1507328
},
{
"epoch": 1.02,
"learning_rate": 2.5312261893140754e-05,
"loss": 3.9156,
"step": 1507840
},
{
"epoch": 1.02,
"learning_rate": 2.5303875945630234e-05,
"loss": 3.908,
"step": 1508352
},
{
"epoch": 1.02,
"learning_rate": 2.5295489998119714e-05,
"loss": 3.9272,
"step": 1508864
},
{
"epoch": 1.02,
"learning_rate": 2.5287104050609193e-05,
"loss": 3.9225,
"step": 1509376
},
{
"epoch": 1.02,
"learning_rate": 2.5278718103098677e-05,
"loss": 3.9235,
"step": 1509888
},
{
"epoch": 1.02,
"learning_rate": 2.5270348534391886e-05,
"loss": 3.9144,
"step": 1510400
},
{
"epoch": 1.02,
"learning_rate": 2.5261962586881366e-05,
"loss": 3.9222,
"step": 1510912
},
{
"epoch": 1.02,
"learning_rate": 2.5253576639370846e-05,
"loss": 3.9254,
"step": 1511424
},
{
"epoch": 1.02,
"learning_rate": 2.5245190691860326e-05,
"loss": 3.9124,
"step": 1511936
},
{
"epoch": 1.02,
"learning_rate": 2.5236804744349806e-05,
"loss": 3.9276,
"step": 1512448
},
{
"epoch": 1.02,
"learning_rate": 2.5228435175643018e-05,
"loss": 3.9145,
"step": 1512960
},
{
"epoch": 1.02,
"learning_rate": 2.5220049228132498e-05,
"loss": 3.9247,
"step": 1513472
},
{
"epoch": 1.02,
"learning_rate": 2.5211663280621978e-05,
"loss": 3.9088,
"step": 1513984
},
{
"epoch": 1.02,
"learning_rate": 2.5203293711915187e-05,
"loss": 3.9194,
"step": 1514496
},
{
"epoch": 1.02,
"learning_rate": 2.5194907764404667e-05,
"loss": 3.9044,
"step": 1515008
},
{
"epoch": 1.02,
"learning_rate": 2.5186521816894147e-05,
"loss": 3.9146,
"step": 1515520
},
{
"epoch": 1.02,
"learning_rate": 2.517813586938363e-05,
"loss": 3.9093,
"step": 1516032
},
{
"epoch": 1.02,
"learning_rate": 2.516974992187311e-05,
"loss": 3.9244,
"step": 1516544
},
{
"epoch": 1.02,
"learning_rate": 2.516136397436259e-05,
"loss": 3.9189,
"step": 1517056
},
{
"epoch": 1.02,
"learning_rate": 2.515297802685207e-05,
"loss": 3.9242,
"step": 1517568
},
{
"epoch": 1.02,
"learning_rate": 2.514460845814528e-05,
"loss": 3.9142,
"step": 1518080
},
{
"epoch": 1.02,
"learning_rate": 2.513622251063476e-05,
"loss": 3.9214,
"step": 1518592
},
{
"epoch": 1.02,
"learning_rate": 2.512783656312424e-05,
"loss": 3.931,
"step": 1519104
},
{
"epoch": 1.02,
"learning_rate": 2.5119450615613716e-05,
"loss": 3.9185,
"step": 1519616
},
{
"epoch": 1.02,
"learning_rate": 2.5111064668103196e-05,
"loss": 3.9201,
"step": 1520128
},
{
"epoch": 1.02,
"learning_rate": 2.5102678720592676e-05,
"loss": 3.9265,
"step": 1520640
},
{
"epoch": 1.02,
"learning_rate": 2.5094292773082156e-05,
"loss": 3.9169,
"step": 1521152
},
{
"epoch": 1.02,
"learning_rate": 2.5085906825571636e-05,
"loss": 3.9279,
"step": 1521664
},
{
"epoch": 1.02,
"learning_rate": 2.5077520878061116e-05,
"loss": 3.9104,
"step": 1522176
},
{
"epoch": 1.02,
"learning_rate": 2.50691349305506e-05,
"loss": 3.9225,
"step": 1522688
},
{
"epoch": 1.02,
"learning_rate": 2.5060781740647544e-05,
"loss": 3.916,
"step": 1523200
},
{
"epoch": 1.02,
"learning_rate": 2.5052395793137017e-05,
"loss": 3.9156,
"step": 1523712
},
{
"epoch": 1.02,
"learning_rate": 2.5044009845626497e-05,
"loss": 3.9194,
"step": 1524224
},
{
"epoch": 1.02,
"learning_rate": 2.5035623898115977e-05,
"loss": 3.919,
"step": 1524736
},
{
"epoch": 1.02,
"learning_rate": 2.502723795060546e-05,
"loss": 3.9166,
"step": 1525248
},
{
"epoch": 1.02,
"learning_rate": 2.501885200309494e-05,
"loss": 3.9145,
"step": 1525760
},
{
"epoch": 1.02,
"learning_rate": 2.501046605558442e-05,
"loss": 3.919,
"step": 1526272
},
{
"epoch": 1.03,
"eval_loss": 4.0003581047058105,
"eval_runtime": 294.1306,
"eval_samples_per_second": 1297.352,
"eval_steps_per_second": 40.543,
"step": 1526400
},
{
"epoch": 0.0,
"learning_rate": 2.50020801080739e-05,
"loss": 3.912,
"step": 1526784
},
{
"epoch": 0.0,
"learning_rate": 2.499369416056338e-05,
"loss": 3.9094,
"step": 1527296
},
{
"epoch": 0.0,
"learning_rate": 2.498530821305286e-05,
"loss": 3.9229,
"step": 1527808
},
{
"epoch": 0.0,
"learning_rate": 2.497692226554234e-05,
"loss": 3.9107,
"step": 1528320
},
{
"epoch": 0.0,
"learning_rate": 2.4968536318031817e-05,
"loss": 3.9352,
"step": 1528832
},
{
"epoch": 0.0,
"learning_rate": 2.49601503705213e-05,
"loss": 3.913,
"step": 1529344
},
{
"epoch": 0.0,
"learning_rate": 2.495176442301078e-05,
"loss": 3.9126,
"step": 1529856
},
{
"epoch": 0.0,
"learning_rate": 2.494337847550026e-05,
"loss": 3.9022,
"step": 1530368
},
{
"epoch": 0.0,
"learning_rate": 2.493499252798974e-05,
"loss": 3.9181,
"step": 1530880
},
{
"epoch": 0.0,
"learning_rate": 2.492660658047922e-05,
"loss": 3.9219,
"step": 1531392
},
{
"epoch": 0.0,
"learning_rate": 2.4918220632968697e-05,
"loss": 3.9139,
"step": 1531904
},
{
"epoch": 0.0,
"learning_rate": 2.4909834685458176e-05,
"loss": 3.9163,
"step": 1532416
},
{
"epoch": 0.0,
"learning_rate": 2.4901465116751392e-05,
"loss": 3.9087,
"step": 1532928
},
{
"epoch": 0.0,
"learning_rate": 2.4893079169240872e-05,
"loss": 3.9128,
"step": 1533440
},
{
"epoch": 0.0,
"learning_rate": 2.488469322173035e-05,
"loss": 3.9132,
"step": 1533952
},
{
"epoch": 0.0,
"learning_rate": 2.487630727421983e-05,
"loss": 3.9076,
"step": 1534464
},
{
"epoch": 0.0,
"learning_rate": 2.486793770551304e-05,
"loss": 3.9116,
"step": 1534976
},
{
"epoch": 0.0,
"learning_rate": 2.485955175800252e-05,
"loss": 3.9159,
"step": 1535488
},
{
"epoch": 0.0,
"learning_rate": 2.4851165810492e-05,
"loss": 3.9122,
"step": 1536000
},
{
"epoch": 0.0,
"learning_rate": 2.484277986298148e-05,
"loss": 3.9278,
"step": 1536512
},
{
"epoch": 0.0,
"learning_rate": 2.483439391547096e-05,
"loss": 3.9153,
"step": 1537024
},
{
"epoch": 0.0,
"learning_rate": 2.482600796796044e-05,
"loss": 3.9178,
"step": 1537536
},
{
"epoch": 0.0,
"learning_rate": 2.481762202044992e-05,
"loss": 3.9199,
"step": 1538048
},
{
"epoch": 0.0,
"learning_rate": 2.48092360729394e-05,
"loss": 3.9254,
"step": 1538560
},
{
"epoch": 0.0,
"learning_rate": 2.4800850125428878e-05,
"loss": 3.9075,
"step": 1539072
},
{
"epoch": 0.0,
"learning_rate": 2.4792464177918358e-05,
"loss": 3.9166,
"step": 1539584
},
{
"epoch": 0.0,
"learning_rate": 2.478407823040784e-05,
"loss": 3.9133,
"step": 1540096
},
{
"epoch": 0.0,
"learning_rate": 2.4775708661701053e-05,
"loss": 3.9106,
"step": 1540608
},
{
"epoch": 0.0,
"learning_rate": 2.476732271419053e-05,
"loss": 3.9023,
"step": 1541120
},
{
"epoch": 0.0,
"learning_rate": 2.475893676668001e-05,
"loss": 3.9096,
"step": 1541632
},
{
"epoch": 0.01,
"learning_rate": 2.475055081916949e-05,
"loss": 3.9179,
"step": 1542144
},
{
"epoch": 0.01,
"learning_rate": 2.474216487165897e-05,
"loss": 3.9194,
"step": 1542656
},
{
"epoch": 0.01,
"learning_rate": 2.473377892414845e-05,
"loss": 3.9184,
"step": 1543168
},
{
"epoch": 0.01,
"learning_rate": 2.4725409355441662e-05,
"loss": 3.921,
"step": 1543680
},
{
"epoch": 0.01,
"learning_rate": 2.4717023407931142e-05,
"loss": 3.9159,
"step": 1544192
},
{
"epoch": 0.01,
"learning_rate": 2.4708637460420622e-05,
"loss": 3.9199,
"step": 1544704
},
{
"epoch": 0.01,
"learning_rate": 2.4700251512910102e-05,
"loss": 3.9127,
"step": 1545216
},
{
"epoch": 0.01,
"learning_rate": 2.469188194420331e-05,
"loss": 3.9174,
"step": 1545728
},
{
"epoch": 0.01,
"learning_rate": 2.4683495996692795e-05,
"loss": 3.9085,
"step": 1546240
},
{
"epoch": 0.01,
"learning_rate": 2.4675110049182275e-05,
"loss": 3.9138,
"step": 1546752
},
{
"epoch": 0.01,
"learning_rate": 2.4666724101671754e-05,
"loss": 3.914,
"step": 1547264
},
{
"epoch": 0.01,
"learning_rate": 2.4658338154161234e-05,
"loss": 3.9213,
"step": 1547776
},
{
"epoch": 0.01,
"learning_rate": 2.464995220665071e-05,
"loss": 3.9109,
"step": 1548288
},
{
"epoch": 0.01,
"learning_rate": 2.4641582637943923e-05,
"loss": 3.913,
"step": 1548800
},
{
"epoch": 0.01,
"learning_rate": 2.4633196690433403e-05,
"loss": 3.9231,
"step": 1549312
},
{
"epoch": 0.01,
"learning_rate": 2.4624810742922887e-05,
"loss": 3.9137,
"step": 1549824
},
{
"epoch": 0.01,
"learning_rate": 2.4616424795412363e-05,
"loss": 3.9168,
"step": 1550336
},
{
"epoch": 0.01,
"learning_rate": 2.4608055226705576e-05,
"loss": 3.9062,
"step": 1550848
},
{
"epoch": 0.01,
"learning_rate": 2.4599669279195056e-05,
"loss": 3.8928,
"step": 1551360
},
{
"epoch": 0.01,
"learning_rate": 2.4591283331684532e-05,
"loss": 3.9193,
"step": 1551872
},
{
"epoch": 0.01,
"learning_rate": 2.4582897384174016e-05,
"loss": 3.9145,
"step": 1552384
},
{
"epoch": 0.01,
"learning_rate": 2.4574511436663496e-05,
"loss": 3.9112,
"step": 1552896
},
{
"epoch": 0.01,
"learning_rate": 2.4566125489152976e-05,
"loss": 3.8988,
"step": 1553408
},
{
"epoch": 0.01,
"learning_rate": 2.4557739541642456e-05,
"loss": 3.9032,
"step": 1553920
},
{
"epoch": 0.01,
"learning_rate": 2.4549353594131936e-05,
"loss": 3.8975,
"step": 1554432
},
{
"epoch": 0.01,
"learning_rate": 2.4540984025425145e-05,
"loss": 3.9168,
"step": 1554944
},
{
"epoch": 0.01,
"learning_rate": 2.4532598077914625e-05,
"loss": 3.9039,
"step": 1555456
},
{
"epoch": 0.01,
"learning_rate": 2.4524212130404105e-05,
"loss": 3.9076,
"step": 1555968
},
{
"epoch": 0.01,
"learning_rate": 2.4515826182893588e-05,
"loss": 3.9186,
"step": 1556480
},
{
"epoch": 0.01,
"learning_rate": 2.4507456614186797e-05,
"loss": 3.904,
"step": 1556992
},
{
"epoch": 0.01,
"learning_rate": 2.4499070666676277e-05,
"loss": 3.9059,
"step": 1557504
},
{
"epoch": 0.01,
"learning_rate": 2.4490684719165757e-05,
"loss": 3.9119,
"step": 1558016
},
{
"epoch": 0.01,
"learning_rate": 2.4482298771655237e-05,
"loss": 3.8906,
"step": 1558528
},
{
"epoch": 0.01,
"learning_rate": 2.447392920294845e-05,
"loss": 3.9089,
"step": 1559040
},
{
"epoch": 0.01,
"learning_rate": 2.446554325543793e-05,
"loss": 3.9102,
"step": 1559552
},
{
"epoch": 0.01,
"learning_rate": 2.445715730792741e-05,
"loss": 3.9171,
"step": 1560064
},
{
"epoch": 0.01,
"learning_rate": 2.444877136041689e-05,
"loss": 3.8984,
"step": 1560576
},
{
"epoch": 0.01,
"learning_rate": 2.4440401791710098e-05,
"loss": 3.9049,
"step": 1561088
},
{
"epoch": 0.01,
"learning_rate": 2.4432015844199578e-05,
"loss": 3.8945,
"step": 1561600
},
{
"epoch": 0.01,
"learning_rate": 2.4423629896689058e-05,
"loss": 3.9201,
"step": 1562112
},
{
"epoch": 0.01,
"learning_rate": 2.4415243949178538e-05,
"loss": 3.9151,
"step": 1562624
},
{
"epoch": 0.01,
"learning_rate": 2.4406858001668018e-05,
"loss": 3.9131,
"step": 1563136
},
{
"epoch": 0.01,
"learning_rate": 2.4398472054157498e-05,
"loss": 3.9268,
"step": 1563648
},
{
"epoch": 0.01,
"learning_rate": 2.439010248545071e-05,
"loss": 3.9204,
"step": 1564160
},
{
"epoch": 0.01,
"learning_rate": 2.4381716537940187e-05,
"loss": 3.9339,
"step": 1564672
},
{
"epoch": 0.01,
"learning_rate": 2.437333059042967e-05,
"loss": 3.9067,
"step": 1565184
},
{
"epoch": 0.01,
"learning_rate": 2.436494464291915e-05,
"loss": 3.9131,
"step": 1565696
},
{
"epoch": 0.01,
"learning_rate": 2.435655869540863e-05,
"loss": 3.9182,
"step": 1566208
},
{
"epoch": 0.01,
"learning_rate": 2.434817274789811e-05,
"loss": 3.9048,
"step": 1566720
},
{
"epoch": 0.01,
"learning_rate": 2.433978680038759e-05,
"loss": 3.9181,
"step": 1567232
},
{
"epoch": 0.01,
"learning_rate": 2.43314172316808e-05,
"loss": 3.9121,
"step": 1567744
},
{
"epoch": 0.01,
"learning_rate": 2.432303128417028e-05,
"loss": 3.9194,
"step": 1568256
},
{
"epoch": 0.01,
"learning_rate": 2.431464533665976e-05,
"loss": 3.9147,
"step": 1568768
},
{
"epoch": 0.01,
"learning_rate": 2.4306259389149243e-05,
"loss": 3.9016,
"step": 1569280
},
{
"epoch": 0.01,
"learning_rate": 2.429787344163872e-05,
"loss": 3.9131,
"step": 1569792
},
{
"epoch": 0.01,
"learning_rate": 2.42894874941282e-05,
"loss": 3.9041,
"step": 1570304
},
{
"epoch": 0.01,
"learning_rate": 2.428111792542141e-05,
"loss": 3.92,
"step": 1570816
},
{
"epoch": 0.01,
"learning_rate": 2.427273197791089e-05,
"loss": 3.9132,
"step": 1571328
},
{
"epoch": 0.01,
"learning_rate": 2.426434603040037e-05,
"loss": 3.9065,
"step": 1571840
},
{
"epoch": 0.02,
"learning_rate": 2.425596008288985e-05,
"loss": 3.9167,
"step": 1572352
},
{
"epoch": 0.02,
"learning_rate": 2.424757413537933e-05,
"loss": 3.9097,
"step": 1572864
},
{
"epoch": 0.02,
"learning_rate": 2.4239204566672544e-05,
"loss": 3.9057,
"step": 1573376
},
{
"epoch": 0.02,
"learning_rate": 2.4230834997965753e-05,
"loss": 3.9098,
"step": 1573888
},
{
"epoch": 0.02,
"learning_rate": 2.4222449050455233e-05,
"loss": 3.9217,
"step": 1574400
},
{
"epoch": 0.02,
"learning_rate": 2.4214063102944713e-05,
"loss": 3.9194,
"step": 1574912
},
{
"epoch": 0.02,
"learning_rate": 2.4205677155434193e-05,
"loss": 3.912,
"step": 1575424
},
{
"epoch": 0.02,
"learning_rate": 2.4197291207923673e-05,
"loss": 3.8986,
"step": 1575936
},
{
"epoch": 0.02,
"learning_rate": 2.4188905260413153e-05,
"loss": 3.9151,
"step": 1576448
},
{
"epoch": 0.02,
"learning_rate": 2.4180519312902633e-05,
"loss": 3.9053,
"step": 1576960
},
{
"epoch": 0.02,
"learning_rate": 2.4172133365392113e-05,
"loss": 3.9237,
"step": 1577472
},
{
"epoch": 0.02,
"learning_rate": 2.4163747417881593e-05,
"loss": 3.9193,
"step": 1577984
},
{
"epoch": 0.02,
"learning_rate": 2.4155377849174805e-05,
"loss": 3.9147,
"step": 1578496
},
{
"epoch": 0.02,
"learning_rate": 2.4146991901664285e-05,
"loss": 3.9108,
"step": 1579008
},
{
"epoch": 0.02,
"learning_rate": 2.4138605954153765e-05,
"loss": 3.9242,
"step": 1579520
},
{
"epoch": 0.02,
"learning_rate": 2.4130220006643245e-05,
"loss": 3.8945,
"step": 1580032
},
{
"epoch": 0.02,
"learning_rate": 2.4121834059132725e-05,
"loss": 3.9067,
"step": 1580544
},
{
"epoch": 0.02,
"learning_rate": 2.4113464490425934e-05,
"loss": 3.8997,
"step": 1581056
},
{
"epoch": 0.02,
"learning_rate": 2.4105078542915417e-05,
"loss": 3.9164,
"step": 1581568
},
{
"epoch": 0.02,
"learning_rate": 2.4096692595404897e-05,
"loss": 3.8977,
"step": 1582080
},
{
"epoch": 0.02,
"learning_rate": 2.4088306647894374e-05,
"loss": 3.9083,
"step": 1582592
},
{
"epoch": 0.02,
"learning_rate": 2.4079920700383854e-05,
"loss": 3.9047,
"step": 1583104
},
{
"epoch": 0.02,
"learning_rate": 2.4071534752873334e-05,
"loss": 3.9022,
"step": 1583616
},
{
"epoch": 0.02,
"learning_rate": 2.4063165184166546e-05,
"loss": 3.9075,
"step": 1584128
},
{
"epoch": 0.02,
"learning_rate": 2.4054779236656026e-05,
"loss": 3.9058,
"step": 1584640
},
{
"epoch": 0.02,
"learning_rate": 2.4046393289145506e-05,
"loss": 3.9187,
"step": 1585152
},
{
"epoch": 0.02,
"learning_rate": 2.4038007341634986e-05,
"loss": 3.9171,
"step": 1585664
},
{
"epoch": 0.02,
"learning_rate": 2.4029621394124466e-05,
"loss": 3.9143,
"step": 1586176
},
{
"epoch": 0.02,
"learning_rate": 2.4021235446613946e-05,
"loss": 3.9054,
"step": 1586688
},
{
"epoch": 0.02,
"learning_rate": 2.4012865877907155e-05,
"loss": 3.9171,
"step": 1587200
},
{
"epoch": 0.02,
"learning_rate": 2.4004479930396635e-05,
"loss": 3.9138,
"step": 1587712
},
{
"epoch": 0.02,
"learning_rate": 2.399609398288612e-05,
"loss": 3.9045,
"step": 1588224
},
{
"epoch": 0.02,
"learning_rate": 2.3987724414179328e-05,
"loss": 3.9243,
"step": 1588736
},
{
"epoch": 0.02,
"learning_rate": 2.3979338466668808e-05,
"loss": 3.9057,
"step": 1589248
},
{
"epoch": 0.02,
"learning_rate": 2.3970952519158288e-05,
"loss": 3.9144,
"step": 1589760
},
{
"epoch": 0.02,
"learning_rate": 2.3962566571647767e-05,
"loss": 3.9021,
"step": 1590272
},
{
"epoch": 0.02,
"learning_rate": 2.3954180624137247e-05,
"loss": 3.9143,
"step": 1590784
},
{
"epoch": 0.02,
"learning_rate": 2.3945794676626727e-05,
"loss": 3.9012,
"step": 1591296
},
{
"epoch": 0.02,
"learning_rate": 2.393742510791994e-05,
"loss": 3.9042,
"step": 1591808
},
{
"epoch": 0.02,
"learning_rate": 2.392903916040942e-05,
"loss": 3.9045,
"step": 1592320
},
{
"epoch": 0.02,
"learning_rate": 2.39206532128989e-05,
"loss": 3.916,
"step": 1592832
},
{
"epoch": 0.02,
"learning_rate": 2.3912267265388376e-05,
"loss": 3.9107,
"step": 1593344
},
{
"epoch": 0.02,
"learning_rate": 2.3903881317877856e-05,
"loss": 3.9151,
"step": 1593856
},
{
"epoch": 0.02,
"learning_rate": 2.3895495370367336e-05,
"loss": 3.9036,
"step": 1594368
},
{
"epoch": 0.02,
"learning_rate": 2.388710942285682e-05,
"loss": 3.9174,
"step": 1594880
},
{
"epoch": 0.02,
"learning_rate": 2.38787234753463e-05,
"loss": 3.9222,
"step": 1595392
},
{
"epoch": 0.02,
"learning_rate": 2.387033752783578e-05,
"loss": 3.9142,
"step": 1595904
},
{
"epoch": 0.02,
"learning_rate": 2.386195158032526e-05,
"loss": 3.9117,
"step": 1596416
},
{
"epoch": 0.02,
"learning_rate": 2.3853565632814736e-05,
"loss": 3.918,
"step": 1596928
},
{
"epoch": 0.02,
"learning_rate": 2.384519606410795e-05,
"loss": 3.909,
"step": 1597440
},
{
"epoch": 0.02,
"learning_rate": 2.383681011659743e-05,
"loss": 3.9203,
"step": 1597952
},
{
"epoch": 0.02,
"learning_rate": 2.3828424169086912e-05,
"loss": 3.9051,
"step": 1598464
},
{
"epoch": 0.02,
"learning_rate": 2.382003822157639e-05,
"loss": 3.9149,
"step": 1598976
},
{
"epoch": 0.02,
"learning_rate": 2.38116686528696e-05,
"loss": 3.9082,
"step": 1599488
},
{
"epoch": 0.02,
"learning_rate": 2.380328270535908e-05,
"loss": 3.9111,
"step": 1600000
},
{
"epoch": 0.02,
"learning_rate": 2.3794896757848557e-05,
"loss": 3.9107,
"step": 1600512
},
{
"epoch": 0.02,
"learning_rate": 2.3786527189141773e-05,
"loss": 3.9122,
"step": 1601024
},
{
"epoch": 0.02,
"learning_rate": 2.3778141241631253e-05,
"loss": 3.9106,
"step": 1601536
},
{
"epoch": 0.02,
"learning_rate": 2.3769755294120733e-05,
"loss": 3.9029,
"step": 1602048
},
{
"epoch": 0.02,
"learning_rate": 2.376136934661021e-05,
"loss": 3.9145,
"step": 1602560
},
{
"epoch": 0.03,
"eval_loss": 3.9975011348724365,
"eval_runtime": 290.9243,
"eval_samples_per_second": 1311.651,
"eval_steps_per_second": 40.99,
"step": 1602720
},
{
"epoch": 1.0,
"learning_rate": 2.3752999777903422e-05,
"loss": 3.908,
"step": 1603072
},
{
"epoch": 1.0,
"learning_rate": 2.3744613830392902e-05,
"loss": 3.9008,
"step": 1603584
},
{
"epoch": 1.0,
"learning_rate": 2.3736227882882382e-05,
"loss": 3.9169,
"step": 1604096
},
{
"epoch": 1.0,
"learning_rate": 2.3727841935371862e-05,
"loss": 3.9058,
"step": 1604608
},
{
"epoch": 1.0,
"learning_rate": 2.3719455987861342e-05,
"loss": 3.9235,
"step": 1605120
},
{
"epoch": 1.0,
"learning_rate": 2.3711070040350822e-05,
"loss": 3.9096,
"step": 1605632
},
{
"epoch": 1.0,
"learning_rate": 2.3702684092840302e-05,
"loss": 3.8979,
"step": 1606144
},
{
"epoch": 1.0,
"learning_rate": 2.3694298145329782e-05,
"loss": 3.902,
"step": 1606656
},
{
"epoch": 1.0,
"learning_rate": 2.3685912197819262e-05,
"loss": 3.9053,
"step": 1607168
},
{
"epoch": 1.0,
"learning_rate": 2.3677526250308742e-05,
"loss": 3.914,
"step": 1607680
},
{
"epoch": 1.0,
"learning_rate": 2.3669140302798222e-05,
"loss": 3.9052,
"step": 1608192
},
{
"epoch": 1.0,
"learning_rate": 2.3660770734091434e-05,
"loss": 3.9097,
"step": 1608704
},
{
"epoch": 1.0,
"learning_rate": 2.3652401165384643e-05,
"loss": 3.9026,
"step": 1609216
},
{
"epoch": 1.0,
"learning_rate": 2.3644015217874123e-05,
"loss": 3.8999,
"step": 1609728
},
{
"epoch": 1.0,
"learning_rate": 2.3635629270363603e-05,
"loss": 3.9104,
"step": 1610240
},
{
"epoch": 1.0,
"learning_rate": 2.3627243322853083e-05,
"loss": 3.8993,
"step": 1610752
},
{
"epoch": 1.0,
"learning_rate": 2.3618857375342567e-05,
"loss": 3.903,
"step": 1611264
},
{
"epoch": 1.0,
"learning_rate": 2.3610471427832043e-05,
"loss": 3.9077,
"step": 1611776
},
{
"epoch": 1.0,
"learning_rate": 2.3602085480321523e-05,
"loss": 3.9094,
"step": 1612288
},
{
"epoch": 1.0,
"learning_rate": 2.3593699532811003e-05,
"loss": 3.9172,
"step": 1612800
},
{
"epoch": 1.0,
"learning_rate": 2.3585329964104212e-05,
"loss": 3.9123,
"step": 1613312
},
{
"epoch": 1.0,
"learning_rate": 2.3576960395397428e-05,
"loss": 3.9116,
"step": 1613824
},
{
"epoch": 1.0,
"learning_rate": 2.3568574447886908e-05,
"loss": 3.9123,
"step": 1614336
},
{
"epoch": 1.0,
"learning_rate": 2.3560188500376388e-05,
"loss": 3.9147,
"step": 1614848
},
{
"epoch": 1.0,
"learning_rate": 2.3551802552865865e-05,
"loss": 3.8993,
"step": 1615360
},
{
"epoch": 1.0,
"learning_rate": 2.3543416605355344e-05,
"loss": 3.9144,
"step": 1615872
},
{
"epoch": 1.0,
"learning_rate": 2.3535047036648557e-05,
"loss": 3.9022,
"step": 1616384
},
{
"epoch": 1.0,
"learning_rate": 2.3526661089138037e-05,
"loss": 3.9022,
"step": 1616896
},
{
"epoch": 1.0,
"learning_rate": 2.3518275141627517e-05,
"loss": 3.8994,
"step": 1617408
},
{
"epoch": 1.0,
"learning_rate": 2.3509889194116997e-05,
"loss": 3.9017,
"step": 1617920
},
{
"epoch": 1.01,
"learning_rate": 2.350151962541021e-05,
"loss": 3.9099,
"step": 1618432
},
{
"epoch": 1.01,
"learning_rate": 2.3493133677899686e-05,
"loss": 3.9096,
"step": 1618944
},
{
"epoch": 1.01,
"learning_rate": 2.3484747730389166e-05,
"loss": 3.9151,
"step": 1619456
},
{
"epoch": 1.01,
"learning_rate": 2.347636178287865e-05,
"loss": 3.9157,
"step": 1619968
},
{
"epoch": 1.01,
"learning_rate": 2.346797583536813e-05,
"loss": 3.9046,
"step": 1620480
},
{
"epoch": 1.01,
"learning_rate": 2.345958988785761e-05,
"loss": 3.9115,
"step": 1620992
},
{
"epoch": 1.01,
"learning_rate": 2.345120394034709e-05,
"loss": 3.9058,
"step": 1621504
},
{
"epoch": 1.01,
"learning_rate": 2.344281799283657e-05,
"loss": 3.9074,
"step": 1622016
},
{
"epoch": 1.01,
"learning_rate": 2.3434432045326046e-05,
"loss": 3.9015,
"step": 1622528
},
{
"epoch": 1.01,
"learning_rate": 2.3426046097815526e-05,
"loss": 3.9017,
"step": 1623040
},
{
"epoch": 1.01,
"learning_rate": 2.3417660150305005e-05,
"loss": 3.9091,
"step": 1623552
},
{
"epoch": 1.01,
"learning_rate": 2.340927420279449e-05,
"loss": 3.9156,
"step": 1624064
},
{
"epoch": 1.01,
"learning_rate": 2.340088825528397e-05,
"loss": 3.9021,
"step": 1624576
},
{
"epoch": 1.01,
"learning_rate": 2.339250230777345e-05,
"loss": 3.9063,
"step": 1625088
},
{
"epoch": 1.01,
"learning_rate": 2.3384132739066658e-05,
"loss": 3.9146,
"step": 1625600
},
{
"epoch": 1.01,
"learning_rate": 2.3375746791556138e-05,
"loss": 3.9086,
"step": 1626112
},
{
"epoch": 1.01,
"learning_rate": 2.3367360844045618e-05,
"loss": 3.91,
"step": 1626624
},
{
"epoch": 1.01,
"learning_rate": 2.3358974896535098e-05,
"loss": 3.902,
"step": 1627136
},
{
"epoch": 1.01,
"learning_rate": 2.3350588949024578e-05,
"loss": 3.881,
"step": 1627648
},
{
"epoch": 1.01,
"learning_rate": 2.3342203001514058e-05,
"loss": 3.9168,
"step": 1628160
},
{
"epoch": 1.01,
"learning_rate": 2.3333817054003538e-05,
"loss": 3.9054,
"step": 1628672
},
{
"epoch": 1.01,
"learning_rate": 2.3325431106493018e-05,
"loss": 3.9052,
"step": 1629184
},
{
"epoch": 1.01,
"learning_rate": 2.3317045158982497e-05,
"loss": 3.8976,
"step": 1629696
},
{
"epoch": 1.01,
"learning_rate": 2.3308659211471977e-05,
"loss": 3.89,
"step": 1630208
},
{
"epoch": 1.01,
"learning_rate": 2.330028964276519e-05,
"loss": 3.8913,
"step": 1630720
},
{
"epoch": 1.01,
"learning_rate": 2.329190369525467e-05,
"loss": 3.9044,
"step": 1631232
},
{
"epoch": 1.01,
"learning_rate": 2.328353412654788e-05,
"loss": 3.8974,
"step": 1631744
},
{
"epoch": 1.01,
"learning_rate": 2.327514817903736e-05,
"loss": 3.9055,
"step": 1632256
},
{
"epoch": 1.01,
"learning_rate": 2.326676223152684e-05,
"loss": 3.9084,
"step": 1632768
},
{
"epoch": 1.01,
"learning_rate": 2.325837628401632e-05,
"loss": 3.8983,
"step": 1633280
},
{
"epoch": 1.01,
"learning_rate": 2.325000671530953e-05,
"loss": 3.8988,
"step": 1633792
},
{
"epoch": 1.01,
"learning_rate": 2.324162076779901e-05,
"loss": 3.9073,
"step": 1634304
},
{
"epoch": 1.01,
"learning_rate": 2.323323482028849e-05,
"loss": 3.8878,
"step": 1634816
},
{
"epoch": 1.01,
"learning_rate": 2.322484887277797e-05,
"loss": 3.8982,
"step": 1635328
},
{
"epoch": 1.01,
"learning_rate": 2.321646292526745e-05,
"loss": 3.9009,
"step": 1635840
},
{
"epoch": 1.01,
"learning_rate": 2.320809335656066e-05,
"loss": 3.9124,
"step": 1636352
},
{
"epoch": 1.01,
"learning_rate": 2.3199707409050144e-05,
"loss": 3.8891,
"step": 1636864
},
{
"epoch": 1.01,
"learning_rate": 2.3191321461539624e-05,
"loss": 3.9009,
"step": 1637376
},
{
"epoch": 1.01,
"learning_rate": 2.3182935514029103e-05,
"loss": 3.8887,
"step": 1637888
},
{
"epoch": 1.01,
"learning_rate": 2.317454956651858e-05,
"loss": 3.9107,
"step": 1638400
},
{
"epoch": 1.01,
"learning_rate": 2.3166179997811793e-05,
"loss": 3.9073,
"step": 1638912
},
{
"epoch": 1.01,
"learning_rate": 2.3157794050301272e-05,
"loss": 3.9054,
"step": 1639424
},
{
"epoch": 1.01,
"learning_rate": 2.3149408102790752e-05,
"loss": 3.9165,
"step": 1639936
},
{
"epoch": 1.01,
"learning_rate": 2.3141022155280232e-05,
"loss": 3.9131,
"step": 1640448
},
{
"epoch": 1.01,
"learning_rate": 2.3132636207769712e-05,
"loss": 3.925,
"step": 1640960
},
{
"epoch": 1.01,
"learning_rate": 2.3124266639062925e-05,
"loss": 3.9022,
"step": 1641472
},
{
"epoch": 1.01,
"learning_rate": 2.3115880691552405e-05,
"loss": 3.9071,
"step": 1641984
},
{
"epoch": 1.01,
"learning_rate": 2.310749474404188e-05,
"loss": 3.9063,
"step": 1642496
},
{
"epoch": 1.01,
"learning_rate": 2.309910879653136e-05,
"loss": 3.895,
"step": 1643008
},
{
"epoch": 1.01,
"learning_rate": 2.3090722849020845e-05,
"loss": 3.9134,
"step": 1643520
},
{
"epoch": 1.01,
"learning_rate": 2.3082353280314054e-05,
"loss": 3.9044,
"step": 1644032
},
{
"epoch": 1.01,
"learning_rate": 2.3073967332803534e-05,
"loss": 3.9123,
"step": 1644544
},
{
"epoch": 1.01,
"learning_rate": 2.3065581385293014e-05,
"loss": 3.9081,
"step": 1645056
},
{
"epoch": 1.01,
"learning_rate": 2.3057195437782494e-05,
"loss": 3.8956,
"step": 1645568
},
{
"epoch": 1.01,
"learning_rate": 2.3048825869075706e-05,
"loss": 3.905,
"step": 1646080
},
{
"epoch": 1.01,
"learning_rate": 2.3040439921565186e-05,
"loss": 3.8968,
"step": 1646592
},
{
"epoch": 1.01,
"learning_rate": 2.3032053974054666e-05,
"loss": 3.9124,
"step": 1647104
},
{
"epoch": 1.01,
"learning_rate": 2.302368440534788e-05,
"loss": 3.9092,
"step": 1647616
},
{
"epoch": 1.01,
"learning_rate": 2.3015298457837355e-05,
"loss": 3.8949,
"step": 1648128
},
{
"epoch": 1.02,
"learning_rate": 2.3006912510326835e-05,
"loss": 3.9144,
"step": 1648640
},
{
"epoch": 1.02,
"learning_rate": 2.2998526562816315e-05,
"loss": 3.9033,
"step": 1649152
},
{
"epoch": 1.02,
"learning_rate": 2.29901406153058e-05,
"loss": 3.8989,
"step": 1649664
},
{
"epoch": 1.02,
"learning_rate": 2.2981754667795278e-05,
"loss": 3.9003,
"step": 1650176
},
{
"epoch": 1.02,
"learning_rate": 2.2973368720284758e-05,
"loss": 3.9145,
"step": 1650688
},
{
"epoch": 1.02,
"learning_rate": 2.2964982772774235e-05,
"loss": 3.9097,
"step": 1651200
},
{
"epoch": 1.02,
"learning_rate": 2.2956596825263715e-05,
"loss": 3.9111,
"step": 1651712
},
{
"epoch": 1.02,
"learning_rate": 2.2948210877753195e-05,
"loss": 3.8918,
"step": 1652224
},
{
"epoch": 1.02,
"learning_rate": 2.2939824930242675e-05,
"loss": 3.9078,
"step": 1652736
},
{
"epoch": 1.02,
"learning_rate": 2.2931438982732155e-05,
"loss": 3.9011,
"step": 1653248
},
{
"epoch": 1.02,
"learning_rate": 2.2923069414025367e-05,
"loss": 3.9151,
"step": 1653760
},
{
"epoch": 1.02,
"learning_rate": 2.291469984531858e-05,
"loss": 3.9122,
"step": 1654272
},
{
"epoch": 1.02,
"learning_rate": 2.290631389780806e-05,
"loss": 3.9027,
"step": 1654784
},
{
"epoch": 1.02,
"learning_rate": 2.2897927950297536e-05,
"loss": 3.9078,
"step": 1655296
},
{
"epoch": 1.02,
"learning_rate": 2.2889542002787016e-05,
"loss": 3.9134,
"step": 1655808
},
{
"epoch": 1.02,
"learning_rate": 2.28811560552765e-05,
"loss": 3.8897,
"step": 1656320
},
{
"epoch": 1.02,
"learning_rate": 2.287280286537344e-05,
"loss": 3.8999,
"step": 1656832
},
{
"epoch": 1.02,
"learning_rate": 2.286441691786292e-05,
"loss": 3.8924,
"step": 1657344
},
{
"epoch": 1.02,
"learning_rate": 2.28560309703524e-05,
"loss": 3.9055,
"step": 1657856
},
{
"epoch": 1.02,
"learning_rate": 2.284764502284188e-05,
"loss": 3.8962,
"step": 1658368
},
{
"epoch": 1.02,
"learning_rate": 2.283925907533136e-05,
"loss": 3.9053,
"step": 1658880
},
{
"epoch": 1.02,
"learning_rate": 2.283087312782084e-05,
"loss": 3.8959,
"step": 1659392
},
{
"epoch": 1.02,
"learning_rate": 2.282248718031032e-05,
"loss": 3.8969,
"step": 1659904
},
{
"epoch": 1.02,
"learning_rate": 2.28141012327998e-05,
"loss": 3.9025,
"step": 1660416
},
{
"epoch": 1.02,
"learning_rate": 2.280571528528928e-05,
"loss": 3.8966,
"step": 1660928
},
{
"epoch": 1.02,
"learning_rate": 2.279732933777876e-05,
"loss": 3.9111,
"step": 1661440
},
{
"epoch": 1.02,
"learning_rate": 2.2788943390268237e-05,
"loss": 3.9076,
"step": 1661952
},
{
"epoch": 1.02,
"learning_rate": 2.278055744275772e-05,
"loss": 3.9095,
"step": 1662464
},
{
"epoch": 1.02,
"learning_rate": 2.2772187874050933e-05,
"loss": 3.8982,
"step": 1662976
},
{
"epoch": 1.02,
"learning_rate": 2.2763801926540413e-05,
"loss": 3.9077,
"step": 1663488
},
{
"epoch": 1.02,
"learning_rate": 2.275541597902989e-05,
"loss": 3.9101,
"step": 1664000
},
{
"epoch": 1.02,
"learning_rate": 2.274703003151937e-05,
"loss": 3.8974,
"step": 1664512
},
{
"epoch": 1.02,
"learning_rate": 2.273864408400885e-05,
"loss": 3.9192,
"step": 1665024
},
{
"epoch": 1.02,
"learning_rate": 2.273025813649833e-05,
"loss": 3.8946,
"step": 1665536
},
{
"epoch": 1.02,
"learning_rate": 2.2721872188987813e-05,
"loss": 3.9087,
"step": 1666048
},
{
"epoch": 1.02,
"learning_rate": 2.2713502620281022e-05,
"loss": 3.8918,
"step": 1666560
},
{
"epoch": 1.02,
"learning_rate": 2.2705116672770502e-05,
"loss": 3.9097,
"step": 1667072
},
{
"epoch": 1.02,
"learning_rate": 2.269674710406371e-05,
"loss": 3.8917,
"step": 1667584
},
{
"epoch": 1.02,
"learning_rate": 2.268836115655319e-05,
"loss": 3.8995,
"step": 1668096
},
{
"epoch": 1.02,
"learning_rate": 2.2679975209042674e-05,
"loss": 3.8924,
"step": 1668608
},
{
"epoch": 1.02,
"learning_rate": 2.2671589261532154e-05,
"loss": 3.9141,
"step": 1669120
},
{
"epoch": 1.02,
"learning_rate": 2.2663203314021634e-05,
"loss": 3.9005,
"step": 1669632
},
{
"epoch": 1.02,
"learning_rate": 2.2654817366511114e-05,
"loss": 3.9084,
"step": 1670144
},
{
"epoch": 1.02,
"learning_rate": 2.2646431419000594e-05,
"loss": 3.8964,
"step": 1670656
},
{
"epoch": 1.02,
"learning_rate": 2.263804547149007e-05,
"loss": 3.9111,
"step": 1671168
},
{
"epoch": 1.02,
"learning_rate": 2.262965952397955e-05,
"loss": 3.9129,
"step": 1671680
},
{
"epoch": 1.02,
"learning_rate": 2.262127357646903e-05,
"loss": 3.9081,
"step": 1672192
},
{
"epoch": 1.02,
"learning_rate": 2.2612887628958514e-05,
"loss": 3.908,
"step": 1672704
},
{
"epoch": 1.02,
"learning_rate": 2.2604501681447994e-05,
"loss": 3.9073,
"step": 1673216
},
{
"epoch": 1.02,
"learning_rate": 2.2596148491544935e-05,
"loss": 3.9039,
"step": 1673728
},
{
"epoch": 1.02,
"learning_rate": 2.2587762544034415e-05,
"loss": 3.9128,
"step": 1674240
},
{
"epoch": 1.02,
"learning_rate": 2.2579376596523892e-05,
"loss": 3.8968,
"step": 1674752
},
{
"epoch": 1.02,
"learning_rate": 2.2570990649013375e-05,
"loss": 3.9069,
"step": 1675264
},
{
"epoch": 1.02,
"learning_rate": 2.2562621080306588e-05,
"loss": 3.9034,
"step": 1675776
},
{
"epoch": 1.02,
"learning_rate": 2.2554235132796068e-05,
"loss": 3.905,
"step": 1676288
},
{
"epoch": 1.02,
"learning_rate": 2.2545849185285544e-05,
"loss": 3.9043,
"step": 1676800
},
{
"epoch": 1.02,
"learning_rate": 2.2537463237775024e-05,
"loss": 3.9004,
"step": 1677312
},
{
"epoch": 1.02,
"learning_rate": 2.2529077290264504e-05,
"loss": 3.9119,
"step": 1677824
},
{
"epoch": 1.02,
"learning_rate": 2.2520707721557717e-05,
"loss": 3.8911,
"step": 1678336
},
{
"epoch": 1.02,
"learning_rate": 2.2512321774047197e-05,
"loss": 3.9119,
"step": 1678848
},
{
"epoch": 1.03,
"eval_loss": 3.9947001934051514,
"eval_runtime": 293.7078,
"eval_samples_per_second": 1299.22,
"eval_steps_per_second": 40.602,
"step": 1679040
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 6.93169763403851e+17,
"trial_name": null,
"trial_params": null
}