full-lstm-4 / checkpoint-457920 /trainer_state.json
abhinavp's picture
Training in progress, epoch 0, checkpoint
000d80c verified
raw
history blame
112 kB
{
"best_metric": 4.163780689239502,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full2/lstm/4/checkpoints/checkpoint-457920",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 457920,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.8217,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5568,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0575,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9931,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9484,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8791,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7241,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6207,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5202,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4443,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3852,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.33,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2719,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.2014,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1552,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.1015,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 6.0593,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 6.0156,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.9765,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.931,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.9008,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8631,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8367,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.7946,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.979875363855125e-05,
"loss": 5.7844,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.979036769104073e-05,
"loss": 5.7509,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7237,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6913,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6708,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.975684027980238e-05,
"loss": 5.6562,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.974845433229186e-05,
"loss": 5.6242,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.6161,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5889,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.5709,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714926921053515e-05,
"loss": 5.5674,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5504,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5262,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.9689785457325684e-05,
"loss": 5.4993,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.9681399509815164e-05,
"loss": 5.4884,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4629,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4628,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 5.4382,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 5.4321,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.4084,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.4089,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3942,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.3942,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960595873982795e-05,
"loss": 5.3815,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959757279231743e-05,
"loss": 5.3523,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3439,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3532,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3337,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956404538107908e-05,
"loss": 5.321,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.3028,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.3049,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2859,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.2957,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2613,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2641,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2597,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 5.2436,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 5.2499,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2204,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.2166,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.205,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.2255,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.1913,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1922,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.174,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1686,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 5.1768,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1702,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.1607,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.16,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1609,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371250482355776e-05,
"loss": 5.13,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1388,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935447858733473e-05,
"loss": 5.1158,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934609263982421e-05,
"loss": 5.1105,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933770669231369e-05,
"loss": 5.1119,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932932074480317e-05,
"loss": 5.111,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932095117609638e-05,
"loss": 5.1003,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931256522858586e-05,
"loss": 5.1084,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930417928107534e-05,
"loss": 5.0886,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295793333564825e-05,
"loss": 5.0719,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287407386054305e-05,
"loss": 5.0666,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279021438543785e-05,
"loss": 5.0796,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270635491033264e-05,
"loss": 5.0609,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262249543522744e-05,
"loss": 5.0577,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.9253879974815954e-05,
"loss": 5.0546,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.9245494027305433e-05,
"loss": 5.0424,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.9237108079794913e-05,
"loss": 5.0434,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922872213228439e-05,
"loss": 5.037,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922033618477387e-05,
"loss": 5.038,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921196661606708e-05,
"loss": 5.0346,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920358066855656e-05,
"loss": 5.0235,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919519472104604e-05,
"loss": 5.0081,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918680877353552e-05,
"loss": 5.0091,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917843920482874e-05,
"loss": 4.998,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917005325731822e-05,
"loss": 4.9966,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.91616673098077e-05,
"loss": 5.0055,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915328136229718e-05,
"loss": 4.9836,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914489541478666e-05,
"loss": 4.9879,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913650946727614e-05,
"loss": 4.9817,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912812351976562e-05,
"loss": 4.9709,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911973757225509e-05,
"loss": 4.9638,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911136800354831e-05,
"loss": 4.9625,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910298205603779e-05,
"loss": 4.9471,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909459610852727e-05,
"loss": 4.9482,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908621016101675e-05,
"loss": 4.9456,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907782421350623e-05,
"loss": 4.9452,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906943826599571e-05,
"loss": 4.9374,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906105231848519e-05,
"loss": 4.9351,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052682749778396e-05,
"loss": 4.9261,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.9044296802267876e-05,
"loss": 4.9291,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.9035910854757356e-05,
"loss": 4.9311,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027524907246836e-05,
"loss": 4.9234,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901917171734378e-05,
"loss": 4.9231,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901078576983326e-05,
"loss": 4.9091,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900239982232274e-05,
"loss": 4.9123,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994013874812214e-05,
"loss": 4.9089,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.89856279273017e-05,
"loss": 4.8942,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897724197979118e-05,
"loss": 4.892,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.896885603228066e-05,
"loss": 4.8888,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.896047008477014e-05,
"loss": 4.8899,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895208413725962e-05,
"loss": 4.8772,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.89436981897491e-05,
"loss": 4.8822,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893532862104231e-05,
"loss": 4.8761,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892694267353179e-05,
"loss": 4.8678,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891855672602127e-05,
"loss": 4.8608,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891017077851075e-05,
"loss": 4.8783,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890178483100023e-05,
"loss": 4.8675,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889339888348971e-05,
"loss": 4.8598,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888501293597919e-05,
"loss": 4.8588,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887662698846867e-05,
"loss": 4.8564,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886825741976188e-05,
"loss": 4.8544,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.8859871472251365e-05,
"loss": 4.8545,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515182823483e-05,
"loss": 4.8471,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.8406,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883474638732726e-05,
"loss": 4.8368,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882636043981674e-05,
"loss": 4.8251,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881797449230622e-05,
"loss": 4.8232,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88095885447957e-05,
"loss": 4.8228,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880120259728518e-05,
"loss": 4.8266,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879283302857839e-05,
"loss": 4.8195,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878444708106787e-05,
"loss": 4.8184,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877606113355735e-05,
"loss": 4.8147,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876767518604683e-05,
"loss": 4.8142,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875928923853632e-05,
"loss": 4.8188,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.87509032910258e-05,
"loss": 4.7959,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.763843536376953,
"eval_runtime": 293.53,
"eval_samples_per_second": 1300.007,
"eval_steps_per_second": 40.626,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874253372231901e-05,
"loss": 4.7882,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873414777480849e-05,
"loss": 4.7878,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872576182729797e-05,
"loss": 4.8056,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871737587978745e-05,
"loss": 4.7883,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870898993227693e-05,
"loss": 4.7936,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.87006039847664e-05,
"loss": 4.7843,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692234416059616e-05,
"loss": 4.7813,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683848468549096e-05,
"loss": 4.7668,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675462521038576e-05,
"loss": 4.7723,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667076573528056e-05,
"loss": 4.7691,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658690626017536e-05,
"loss": 4.7901,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.8650304678507016e-05,
"loss": 4.7725,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8641935109800225e-05,
"loss": 4.7569,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633549162289705e-05,
"loss": 4.7583,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625163214779185e-05,
"loss": 4.7582,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616777267268665e-05,
"loss": 4.7493,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608391319758145e-05,
"loss": 4.7603,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.8600005372247625e-05,
"loss": 4.753,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591619424737105e-05,
"loss": 4.7439,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583233477226585e-05,
"loss": 4.7594,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574863908519794e-05,
"loss": 4.7437,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566477961009274e-05,
"loss": 4.7449,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558092013498754e-05,
"loss": 4.7302,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854972244479197e-05,
"loss": 4.753,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854133649728145e-05,
"loss": 4.7307,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853295054977093e-05,
"loss": 4.7289,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852456460226041e-05,
"loss": 4.7202,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851617865474989e-05,
"loss": 4.7219,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850779270723937e-05,
"loss": 4.7177,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849940675972885e-05,
"loss": 4.7153,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849102081221833e-05,
"loss": 4.7203,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848263486470781e-05,
"loss": 4.7155,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847426529600102e-05,
"loss": 4.7124,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846589572729423e-05,
"loss": 4.7218,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845750977978371e-05,
"loss": 4.7131,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.8449123832273194e-05,
"loss": 4.7088,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.8440737884762674e-05,
"loss": 4.6957,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.8432351937252154e-05,
"loss": 4.698,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.8423965989741634e-05,
"loss": 4.6878,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.8415580042231114e-05,
"loss": 4.6965,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840721047352432e-05,
"loss": 4.6842,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.83988245260138e-05,
"loss": 4.6923,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839043857850328e-05,
"loss": 4.6752,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838205263099276e-05,
"loss": 4.696,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373666683482236e-05,
"loss": 4.684,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365280735971716e-05,
"loss": 4.6872,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8356894788461196e-05,
"loss": 4.6839,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834852521975441e-05,
"loss": 4.6664,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834013927224389e-05,
"loss": 4.6658,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833175332473337e-05,
"loss": 4.6821,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832336737722285e-05,
"loss": 4.6681,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831499780851606e-05,
"loss": 4.6667,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830661186100554e-05,
"loss": 4.6558,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829822591349502e-05,
"loss": 4.6659,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828985634478824e-05,
"loss": 4.6483,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828147039727771e-05,
"loss": 4.6735,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827308444976719e-05,
"loss": 4.6365,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826469850225667e-05,
"loss": 4.6577,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825631255474615e-05,
"loss": 4.6543,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824792660723563e-05,
"loss": 4.6445,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823954065972511e-05,
"loss": 4.6531,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.82311547122146e-05,
"loss": 4.6415,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222768764704077e-05,
"loss": 4.6338,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214399195997286e-05,
"loss": 4.6316,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206013248486766e-05,
"loss": 4.6551,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197627300976246e-05,
"loss": 4.6243,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189241353465726e-05,
"loss": 4.6376,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180855405955206e-05,
"loss": 4.619,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172469458444685e-05,
"loss": 4.6274,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164083510934165e-05,
"loss": 4.6381,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155713942227375e-05,
"loss": 4.6361,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147344373520584e-05,
"loss": 4.6266,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138958426010064e-05,
"loss": 4.6338,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813057247849955e-05,
"loss": 4.6363,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812218653098903e-05,
"loss": 4.6206,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811380058347851e-05,
"loss": 4.6279,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810543101477172e-05,
"loss": 4.6148,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.80970450672612e-05,
"loss": 4.6141,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808865911975068e-05,
"loss": 4.6088,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808027317224016e-05,
"loss": 4.6171,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807188722472964e-05,
"loss": 4.6175,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806350127721912e-05,
"loss": 4.6236,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.80551153297086e-05,
"loss": 4.6129,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804672938219807e-05,
"loss": 4.5931,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803834343468755e-05,
"loss": 4.5955,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.802995748717703e-05,
"loss": 4.6081,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802157153966652e-05,
"loss": 4.6005,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801320197095973e-05,
"loss": 4.5981,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004832402252944e-05,
"loss": 4.6041,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996446454742424e-05,
"loss": 4.5887,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.79880605072319e-05,
"loss": 4.5934,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797969093852511e-05,
"loss": 4.5951,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797130499101459e-05,
"loss": 4.5999,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796291904350407e-05,
"loss": 4.5964,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954533095993546e-05,
"loss": 4.597,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946147148483026e-05,
"loss": 4.5791,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937761200972506e-05,
"loss": 4.5848,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929375253461986e-05,
"loss": 4.5823,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792098930595147e-05,
"loss": 4.5795,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791261973724468e-05,
"loss": 4.5954,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.79042501685379e-05,
"loss": 4.5717,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789586422102737e-05,
"loss": 4.578,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788747827351685e-05,
"loss": 4.5787,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787909232600633e-05,
"loss": 4.5726,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.787070637849581e-05,
"loss": 4.5616,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786232043098529e-05,
"loss": 4.5727,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785393448347477e-05,
"loss": 4.5605,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784554853596425e-05,
"loss": 4.5617,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783716258845373e-05,
"loss": 4.5615,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782877664094321e-05,
"loss": 4.5606,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782040707223642e-05,
"loss": 4.5579,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812021124725906e-05,
"loss": 4.5656,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803635177215386e-05,
"loss": 4.5521,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795249229704866e-05,
"loss": 4.5611,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786863282194346e-05,
"loss": 4.5682,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778477334683826e-05,
"loss": 4.5593,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770107765977035e-05,
"loss": 4.5629,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761721818466515e-05,
"loss": 4.5548,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.7753335870955995e-05,
"loss": 4.5527,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7744949923445475e-05,
"loss": 4.5549,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736563975934955e-05,
"loss": 4.5462,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728178028424435e-05,
"loss": 4.5421,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771979208091391e-05,
"loss": 4.5442,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771140613340339e-05,
"loss": 4.5486,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770305294350034e-05,
"loss": 4.5417,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769466699598982e-05,
"loss": 4.5413,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.76862810484793e-05,
"loss": 4.5419,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767789510096878e-05,
"loss": 4.5331,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766952553226199e-05,
"loss": 4.5288,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766113958475147e-05,
"loss": 4.5518,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765275363724095e-05,
"loss": 4.5435,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764436768973043e-05,
"loss": 4.5419,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763599812102364e-05,
"loss": 4.5349,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762761217351312e-05,
"loss": 4.5367,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.76192262260026e-05,
"loss": 4.5341,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761084027849208e-05,
"loss": 4.5445,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760245433098156e-05,
"loss": 4.5347,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759406838347104e-05,
"loss": 4.5275,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758568243596052e-05,
"loss": 4.5285,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757729648845e-05,
"loss": 4.5215,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756891054093948e-05,
"loss": 4.5176,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560540972232686e-05,
"loss": 4.5242,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552155024722166e-05,
"loss": 4.5271,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543769077211646e-05,
"loss": 4.5173,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535383129701126e-05,
"loss": 4.5273,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7526997182190606e-05,
"loss": 4.5233,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518611234680086e-05,
"loss": 4.5187,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510241665973295e-05,
"loss": 4.5223,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750185571846278e-05,
"loss": 4.5079,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.4814772605896,
"eval_runtime": 293.6326,
"eval_samples_per_second": 1299.552,
"eval_steps_per_second": 40.612,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749346977095226e-05,
"loss": 4.5001,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748508382344174e-05,
"loss": 4.5029,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747669787593122e-05,
"loss": 4.5214,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.74683119284207e-05,
"loss": 4.508,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745992598091018e-05,
"loss": 4.5179,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745154003339966e-05,
"loss": 4.5036,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744315408588914e-05,
"loss": 4.5076,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743476813837862e-05,
"loss": 4.4926,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426382190868095e-05,
"loss": 4.502,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7417996243357575e-05,
"loss": 4.498,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409610295847055e-05,
"loss": 4.5186,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401224348336535e-05,
"loss": 4.5092,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392838400826015e-05,
"loss": 4.4859,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384452453315495e-05,
"loss": 4.4937,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737608288460871e-05,
"loss": 4.5003,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736769693709819e-05,
"loss": 4.4816,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735931098958767e-05,
"loss": 4.4982,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735092504207715e-05,
"loss": 4.4932,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734255547337036e-05,
"loss": 4.4868,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733416952585984e-05,
"loss": 4.5083,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732578357834932e-05,
"loss": 4.4888,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.73173976308388e-05,
"loss": 4.4951,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730901168332828e-05,
"loss": 4.4789,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730062573581776e-05,
"loss": 4.5053,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729223978830724e-05,
"loss": 4.4784,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728385384079672e-05,
"loss": 4.484,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.72754678932862e-05,
"loss": 4.4734,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267098324579415e-05,
"loss": 4.4823,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258728755872624e-05,
"loss": 4.473,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250342808362104e-05,
"loss": 4.4733,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7241956860851584e-05,
"loss": 4.4826,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233570913341064e-05,
"loss": 4.4802,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225184965830544e-05,
"loss": 4.4728,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216799018320024e-05,
"loss": 4.488,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208413070809504e-05,
"loss": 4.474,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200027123298984e-05,
"loss": 4.4765,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719164117578846e-05,
"loss": 4.4655,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718327160708167e-05,
"loss": 4.4709,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717488565957115e-05,
"loss": 4.4567,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716649971206063e-05,
"loss": 4.4721,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715811376455011e-05,
"loss": 4.4574,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714972781703959e-05,
"loss": 4.4679,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714135824833281e-05,
"loss": 4.4531,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713297230082228e-05,
"loss": 4.4692,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.71246027321155e-05,
"loss": 4.4692,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711621678460498e-05,
"loss": 4.4627,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710783083709446e-05,
"loss": 4.4693,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709944488958393e-05,
"loss": 4.4481,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091075320877147e-05,
"loss": 4.4475,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082689373366627e-05,
"loss": 4.4646,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074303425856106e-05,
"loss": 4.4519,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7065917478345586e-05,
"loss": 4.4556,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057531530835066e-05,
"loss": 4.441,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.7049145583324546e-05,
"loss": 4.455,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040759635814026e-05,
"loss": 4.4343,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032373688303506e-05,
"loss": 4.4653,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7023987740792986e-05,
"loss": 4.4274,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015601793282466e-05,
"loss": 4.4495,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007248603379404e-05,
"loss": 4.4496,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998862655868884e-05,
"loss": 4.4364,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990476708358364e-05,
"loss": 4.4518,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982090760847844e-05,
"loss": 4.4361,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973704813337324e-05,
"loss": 4.4306,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965318865826804e-05,
"loss": 4.4277,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695693291831629e-05,
"loss": 4.4507,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694854697080577e-05,
"loss": 4.4278,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694016102329525e-05,
"loss": 4.4376,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693177507578473e-05,
"loss": 4.4245,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692338912827421e-05,
"loss": 4.4265,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691500318076369e-05,
"loss": 4.441,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690664999086063e-05,
"loss": 4.4429,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689826404335011e-05,
"loss": 4.427,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688989447464332e-05,
"loss": 4.4454,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.68815085271328e-05,
"loss": 4.4415,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687312257962228e-05,
"loss": 4.4317,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686473663211176e-05,
"loss": 4.4303,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856350684601245e-05,
"loss": 4.4292,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6847964737090725e-05,
"loss": 4.4231,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839578789580204e-05,
"loss": 4.422,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831192842069684e-05,
"loss": 4.4294,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822806894559164e-05,
"loss": 4.4325,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814420947048644e-05,
"loss": 4.4397,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680603499953812e-05,
"loss": 4.4259,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.67976490520276e-05,
"loss": 4.4061,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678929586212454e-05,
"loss": 4.4102,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678092629341775e-05,
"loss": 4.4249,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677254034590723e-05,
"loss": 4.4179,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676415439839671e-05,
"loss": 4.4177,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675576845088619e-05,
"loss": 4.4213,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674738250337568e-05,
"loss": 4.4127,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673899655586516e-05,
"loss": 4.4071,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673061060835464e-05,
"loss": 4.4182,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672222466084412e-05,
"loss": 4.4214,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671383871333359e-05,
"loss": 4.418,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670545276582307e-05,
"loss": 4.4198,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669706681831255e-05,
"loss": 4.407,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668868087080203e-05,
"loss": 4.4096,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668029492329151e-05,
"loss": 4.4066,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667192535458472e-05,
"loss": 4.4104,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.66635394070742e-05,
"loss": 4.4221,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665515345956368e-05,
"loss": 4.4028,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664676751205316e-05,
"loss": 4.4045,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663838156454265e-05,
"loss": 4.4072,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663002837463959e-05,
"loss": 4.4076,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621642427129065e-05,
"loss": 4.3928,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613256479618545e-05,
"loss": 4.3997,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6604870532108025e-05,
"loss": 4.3975,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596484584597505e-05,
"loss": 4.3948,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588098637086985e-05,
"loss": 4.3943,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579712689576465e-05,
"loss": 4.3953,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571326742065945e-05,
"loss": 4.3956,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6562940794555425e-05,
"loss": 4.3968,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554571225848634e-05,
"loss": 4.3871,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546185278338114e-05,
"loss": 4.3957,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.65377993308276e-05,
"loss": 4.4061,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652941338331708e-05,
"loss": 4.4044,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652102743580656e-05,
"loss": 4.3984,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651264148829604e-05,
"loss": 4.3938,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650427191958925e-05,
"loss": 4.3929,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649588597207873e-05,
"loss": 4.3976,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648750002456821e-05,
"loss": 4.3839,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647911407705769e-05,
"loss": 4.3831,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647072812954717e-05,
"loss": 4.388,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646235856084038e-05,
"loss": 4.3943,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645397261332986e-05,
"loss": 4.3857,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644558666581934e-05,
"loss": 4.3882,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643720071830882e-05,
"loss": 4.3851,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428831149602034e-05,
"loss": 4.3791,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420445202091514e-05,
"loss": 4.3742,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412059254580994e-05,
"loss": 4.3977,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403673307070474e-05,
"loss": 4.3951,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639530373836368e-05,
"loss": 4.3857,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638691779085316e-05,
"loss": 4.3831,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637853184334264e-05,
"loss": 4.3841,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637014589583212e-05,
"loss": 4.3849,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6361759948321596e-05,
"loss": 4.3995,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353374000811076e-05,
"loss": 4.3817,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634500443210429e-05,
"loss": 4.3773,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633661848459377e-05,
"loss": 4.3782,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632823253708325e-05,
"loss": 4.3755,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631984658957273e-05,
"loss": 4.3738,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631146064206221e-05,
"loss": 4.376,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630307469455169e-05,
"loss": 4.3805,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629468874704117e-05,
"loss": 4.3743,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628630279953065e-05,
"loss": 4.3792,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627791685202013e-05,
"loss": 4.382,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626953090450961e-05,
"loss": 4.3725,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626116133580282e-05,
"loss": 4.3795,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.62527753882923e-05,
"loss": 4.3625,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.345034122467041,
"eval_runtime": 345.5584,
"eval_samples_per_second": 1104.274,
"eval_steps_per_second": 34.509,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624438944078178e-05,
"loss": 4.3681,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623601987207499e-05,
"loss": 4.3571,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.6227633924564476e-05,
"loss": 4.381,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219247977053956e-05,
"loss": 4.3638,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.6210862029543436e-05,
"loss": 4.3797,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202476082032916e-05,
"loss": 4.3622,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194090134522396e-05,
"loss": 4.3691,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185704187011876e-05,
"loss": 4.3517,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177318239501356e-05,
"loss": 4.3671,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6168932291990836e-05,
"loss": 4.355,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616054634448031e-05,
"loss": 4.3819,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615216039696979e-05,
"loss": 4.372,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6143790828263005e-05,
"loss": 4.3461,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135404880752485e-05,
"loss": 4.3579,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612701893324196e-05,
"loss": 4.3646,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611863298573144e-05,
"loss": 4.351,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.6110247038220925e-05,
"loss": 4.359,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610187746951414e-05,
"loss": 4.3598,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609350790080735e-05,
"loss": 4.3522,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608512195329683e-05,
"loss": 4.3793,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607673600578631e-05,
"loss": 4.3548,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606835005827578e-05,
"loss": 4.359,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.605996411076526e-05,
"loss": 4.3512,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605157816325474e-05,
"loss": 4.3678,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604319221574422e-05,
"loss": 4.349,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.60348062682337e-05,
"loss": 4.352,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602642032072318e-05,
"loss": 4.345,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601803437321266e-05,
"loss": 4.3498,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.600964842570214e-05,
"loss": 4.3468,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600126247819162e-05,
"loss": 4.3448,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599289290948484e-05,
"loss": 4.349,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598452334077805e-05,
"loss": 4.3542,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597613739326753e-05,
"loss": 4.3521,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5967767824560737e-05,
"loss": 4.3561,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.5959381877050217e-05,
"loss": 4.3487,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.5950995929539696e-05,
"loss": 4.3492,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.5942609982029176e-05,
"loss": 4.336,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.5934224034518656e-05,
"loss": 4.3494,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.5925838087008136e-05,
"loss": 4.3299,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.5917452139497616e-05,
"loss": 4.3437,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.5909066191987096e-05,
"loss": 4.3343,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900680244476576e-05,
"loss": 4.3476,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589231067576979e-05,
"loss": 4.3308,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588392472825927e-05,
"loss": 4.3406,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587553878074875e-05,
"loss": 4.3486,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586715283323823e-05,
"loss": 4.3415,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585876688572771e-05,
"loss": 4.3489,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585039731702092e-05,
"loss": 4.3278,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.58420113695104e-05,
"loss": 4.3258,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583362542199988e-05,
"loss": 4.3412,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582523947448936e-05,
"loss": 4.3339,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581686990578257e-05,
"loss": 4.3332,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580848395827205e-05,
"loss": 4.3254,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580009801076153e-05,
"loss": 4.337,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791712063251017e-05,
"loss": 4.3194,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783342494544226e-05,
"loss": 4.3383,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5774956547033706e-05,
"loss": 4.3151,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766570599523186e-05,
"loss": 4.3264,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758184652012666e-05,
"loss": 4.337,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5749815083305875e-05,
"loss": 4.3185,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741429135795355e-05,
"loss": 4.3313,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733043188284835e-05,
"loss": 4.3234,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724657240774315e-05,
"loss": 4.3154,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716287672067524e-05,
"loss": 4.3168,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5707901724557004e-05,
"loss": 4.3296,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.5699515777046484e-05,
"loss": 4.3146,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.5691129829535963e-05,
"loss": 4.3227,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5682743882025443e-05,
"loss": 4.3114,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.5674357934514923e-05,
"loss": 4.3105,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.56659719870044e-05,
"loss": 4.3259,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565758603949388e-05,
"loss": 4.3306,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564923284959083e-05,
"loss": 4.3146,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564084690208031e-05,
"loss": 4.3342,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563246095456979e-05,
"loss": 4.3299,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562407500705927e-05,
"loss": 4.318,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561568905954874e-05,
"loss": 4.3209,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560730311203822e-05,
"loss": 4.318,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559891716452771e-05,
"loss": 4.314,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559053121701719e-05,
"loss": 4.3134,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558214526950667e-05,
"loss": 4.3176,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557377570079988e-05,
"loss": 4.3252,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556538975328936e-05,
"loss": 4.3216,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.55570365633863e-05,
"loss": 4.3219,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554865061587578e-05,
"loss": 4.3004,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554026466836526e-05,
"loss": 4.3022,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553187872085474e-05,
"loss": 4.3161,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523492773344215e-05,
"loss": 4.313,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515106825833695e-05,
"loss": 4.3097,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.5506720878323175e-05,
"loss": 4.3134,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.5498334930812655e-05,
"loss": 4.3056,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.548994898330214e-05,
"loss": 4.3023,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548156303579162e-05,
"loss": 4.3097,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.54731770882811e-05,
"loss": 4.3125,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546479114077058e-05,
"loss": 4.3106,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545640519326006e-05,
"loss": 4.3189,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544801924574954e-05,
"loss": 4.3033,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543963329823902e-05,
"loss": 4.3026,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543126372953223e-05,
"loss": 4.3027,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542287778202171e-05,
"loss": 4.306,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541449183451119e-05,
"loss": 4.3172,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540610588700067e-05,
"loss": 4.2968,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539771993949015e-05,
"loss": 4.3035,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538935037078336e-05,
"loss": 4.3045,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5380980802076575e-05,
"loss": 4.3058,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372594854566055e-05,
"loss": 4.2932,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364208907055535e-05,
"loss": 4.2977,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5355822959545015e-05,
"loss": 4.2976,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347437012034495e-05,
"loss": 4.2927,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339051064523975e-05,
"loss": 4.2896,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330665117013455e-05,
"loss": 4.2948,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322295548306664e-05,
"loss": 4.2986,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5313909600796144e-05,
"loss": 4.2948,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.5305523653285624e-05,
"loss": 4.2887,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297137705775104e-05,
"loss": 4.2926,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528875175826458e-05,
"loss": 4.3095,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.5280365810754064e-05,
"loss": 4.3046,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.5271979863243544e-05,
"loss": 4.301,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.5263593915733024e-05,
"loss": 4.297,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.5255207968222504e-05,
"loss": 4.2942,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524683839951571e-05,
"loss": 4.2957,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523845245200519e-05,
"loss": 4.2853,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523006650449467e-05,
"loss": 4.2884,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522169693578788e-05,
"loss": 4.2892,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521331098827736e-05,
"loss": 4.298,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520492504076684e-05,
"loss": 4.2872,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519653909325632e-05,
"loss": 4.2941,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.51881531457458e-05,
"loss": 4.2833,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517976719823528e-05,
"loss": 4.288,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517138125072476e-05,
"loss": 4.2772,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516299530321425e-05,
"loss": 4.3012,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515462573450746e-05,
"loss": 4.3011,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146256165800667e-05,
"loss": 4.2924,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5137870218290147e-05,
"loss": 4.2867,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.5129484270779626e-05,
"loss": 4.2912,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.5121098323269106e-05,
"loss": 4.2868,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.5112712375758586e-05,
"loss": 4.3029,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104326428248066e-05,
"loss": 4.2838,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5095940480737546e-05,
"loss": 4.2881,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087554533227026e-05,
"loss": 4.2819,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079184964520235e-05,
"loss": 4.2892,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070799017009715e-05,
"loss": 4.2768,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062413069499195e-05,
"loss": 4.2808,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505402712198868e-05,
"loss": 4.2885,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504564117447816e-05,
"loss": 4.2842,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503727160577137e-05,
"loss": 4.2862,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502888565826085e-05,
"loss": 4.2907,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502049971075033e-05,
"loss": 4.2805,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501211376323981e-05,
"loss": 4.2855,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500372781572929e-05,
"loss": 4.2769,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.261603832244873,
"eval_runtime": 348.871,
"eval_samples_per_second": 1093.788,
"eval_steps_per_second": 34.182,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.49953582470225e-05,
"loss": 4.2691,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498697229951198e-05,
"loss": 4.265,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497858635200146e-05,
"loss": 4.2884,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497020040449093e-05,
"loss": 4.2764,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496181445698042e-05,
"loss": 4.2907,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.49534285094699e-05,
"loss": 4.2728,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494504256195938e-05,
"loss": 4.2805,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493665661444886e-05,
"loss": 4.2609,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492827066693834e-05,
"loss": 4.2814,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.491988471942782e-05,
"loss": 4.2645,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.49114987719173e-05,
"loss": 4.2876,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490312920321051e-05,
"loss": 4.285,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489474325569999e-05,
"loss": 4.2546,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488635730818947e-05,
"loss": 4.2739,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487797136067895e-05,
"loss": 4.2761,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486958541316843e-05,
"loss": 4.2631,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486119946565791e-05,
"loss": 4.2702,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485281351814739e-05,
"loss": 4.273,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484442757063687e-05,
"loss": 4.2684,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483604162312635e-05,
"loss": 4.2884,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482765567561583e-05,
"loss": 4.266,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481926972810531e-05,
"loss": 4.2726,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481088378059479e-05,
"loss": 4.2683,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.4802514211888004e-05,
"loss": 4.2799,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479412826437748e-05,
"loss": 4.2622,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478574231686696e-05,
"loss": 4.2724,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477735636935644e-05,
"loss": 4.256,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476897042184592e-05,
"loss": 4.2643,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.4760600853139126e-05,
"loss": 4.2605,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.4752214905628606e-05,
"loss": 4.2621,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.4743828958118086e-05,
"loss": 4.2628,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473544301060757e-05,
"loss": 4.2721,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472708982070452e-05,
"loss": 4.2675,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.4718703873194e-05,
"loss": 4.2729,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471031792568348e-05,
"loss": 4.2632,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470193197817295e-05,
"loss": 4.2682,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469354603066243e-05,
"loss": 4.2596,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468516008315191e-05,
"loss": 4.2588,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467679051444512e-05,
"loss": 4.2508,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.46684045669346e-05,
"loss": 4.2606,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466001861942408e-05,
"loss": 4.2545,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465163267191356e-05,
"loss": 4.2656,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464324672440304e-05,
"loss": 4.2489,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4634860776892526e-05,
"loss": 4.2578,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626474829382006e-05,
"loss": 4.2723,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618088881871486e-05,
"loss": 4.2594,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4609702934360966e-05,
"loss": 4.2649,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601333365654175e-05,
"loss": 4.2513,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4592947418143655e-05,
"loss": 4.2415,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584561470633135e-05,
"loss": 4.2622,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576175523122615e-05,
"loss": 4.2553,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4567789575612095e-05,
"loss": 4.2518,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559403628101575e-05,
"loss": 4.2479,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551017680591055e-05,
"loss": 4.2586,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542648111884264e-05,
"loss": 4.2371,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534262164373744e-05,
"loss": 4.2603,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4525876216863224e-05,
"loss": 4.2341,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.4517490269352704e-05,
"loss": 4.2486,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450910432184219e-05,
"loss": 4.2534,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.45007347531354e-05,
"loss": 4.2438,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449234880562488e-05,
"loss": 4.2485,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448396285811436e-05,
"loss": 4.246,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447557691060384e-05,
"loss": 4.2365,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446720734189705e-05,
"loss": 4.2443,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445882139438653e-05,
"loss": 4.2488,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445043544687601e-05,
"loss": 4.2404,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444204949936548e-05,
"loss": 4.2459,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443366355185496e-05,
"loss": 4.2347,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442527760434444e-05,
"loss": 4.232,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441690803563766e-05,
"loss": 4.2479,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440852208812714e-05,
"loss": 4.2558,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440013614061662e-05,
"loss": 4.2374,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.43917501931061e-05,
"loss": 4.2581,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438336424559558e-05,
"loss": 4.2517,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437497829808506e-05,
"loss": 4.2393,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436659235057454e-05,
"loss": 4.2411,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435820640306402e-05,
"loss": 4.251,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.43498204555535e-05,
"loss": 4.2368,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.4341450886846707e-05,
"loss": 4.239,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333064939336186e-05,
"loss": 4.2437,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4324678991825666e-05,
"loss": 4.2462,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316293044315146e-05,
"loss": 4.249,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4307907096804626e-05,
"loss": 4.244,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429953752809784e-05,
"loss": 4.2289,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429115158058732e-05,
"loss": 4.2283,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.42827656330768e-05,
"loss": 4.2383,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427437968556628e-05,
"loss": 4.2421,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426601011685949e-05,
"loss": 4.2371,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.42576405481527e-05,
"loss": 4.239,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424925460064218e-05,
"loss": 4.2317,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424086865313166e-05,
"loss": 4.2316,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423248270562114e-05,
"loss": 4.238,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422409675811062e-05,
"loss": 4.2349,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.42157108106001e-05,
"loss": 4.242,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207341241893316e-05,
"loss": 4.2395,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.4198971673186525e-05,
"loss": 4.2378,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190585725676005e-05,
"loss": 4.2276,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182199778165485e-05,
"loss": 4.2359,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4173813830654965e-05,
"loss": 4.2326,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.4165427883144445e-05,
"loss": 4.2451,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157041935633925e-05,
"loss": 4.2284,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.4148655988123405e-05,
"loss": 4.225,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.4140270040612885e-05,
"loss": 4.2402,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4131884093102365e-05,
"loss": 4.2317,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123498145591845e-05,
"loss": 4.2257,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115128576885054e-05,
"loss": 4.2291,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106742629374534e-05,
"loss": 4.2285,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409835668186402e-05,
"loss": 4.2148,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.40899707343535e-05,
"loss": 4.2209,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081584786842974e-05,
"loss": 4.2322,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.4073198839332453e-05,
"loss": 4.2249,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.4064812891821933e-05,
"loss": 4.2245,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.4056426944311413e-05,
"loss": 4.2188,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404805737560462e-05,
"loss": 4.22,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.40396714280941e-05,
"loss": 4.241,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403128548058358e-05,
"loss": 4.2377,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402291591187679e-05,
"loss": 4.2327,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401452996436627e-05,
"loss": 4.2278,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400614401685576e-05,
"loss": 4.2234,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399775806934524e-05,
"loss": 4.227,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398937212183472e-05,
"loss": 4.2179,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.39809861743242e-05,
"loss": 4.2238,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397260022681368e-05,
"loss": 4.2203,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396421427930316e-05,
"loss": 4.2287,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395584471059637e-05,
"loss": 4.2202,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394745876308585e-05,
"loss": 4.2239,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939089194379056e-05,
"loss": 4.2166,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3930703246868536e-05,
"loss": 4.2196,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.3922317299358016e-05,
"loss": 4.2147,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3913931351847496e-05,
"loss": 4.2281,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905545404336976e-05,
"loss": 4.2347,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897159456826456e-05,
"loss": 4.2285,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.3888773509315936e-05,
"loss": 4.2171,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388038756180542e-05,
"loss": 4.2267,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387201799309863e-05,
"loss": 4.2184,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386363204558811e-05,
"loss": 4.235,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385524609807759e-05,
"loss": 4.2188,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384686015056707e-05,
"loss": 4.2221,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383849058186028e-05,
"loss": 4.2165,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383010463434976e-05,
"loss": 4.2254,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382171868683924e-05,
"loss": 4.2091,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381333273932872e-05,
"loss": 4.2151,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.38049467918182e-05,
"loss": 4.2215,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379657722311141e-05,
"loss": 4.2174,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788207654404625e-05,
"loss": 4.222,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3779821706894105e-05,
"loss": 4.2236,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771435759383585e-05,
"loss": 4.2162,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763049811873065e-05,
"loss": 4.2163,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3754663864362545e-05,
"loss": 4.2133,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.204583168029785,
"eval_runtime": 288.7537,
"eval_samples_per_second": 1321.51,
"eval_steps_per_second": 41.298,
"step": 381600
},
{
"epoch": 0.0,
"learning_rate": 4.3746277916852025e-05,
"loss": 4.2082,
"step": 381952
},
{
"epoch": 0.0,
"learning_rate": 4.3737891969341505e-05,
"loss": 4.1981,
"step": 382464
},
{
"epoch": 0.0,
"learning_rate": 4.372950602183098e-05,
"loss": 4.2241,
"step": 382976
},
{
"epoch": 0.0,
"learning_rate": 4.372112007432046e-05,
"loss": 4.2143,
"step": 383488
},
{
"epoch": 0.0,
"learning_rate": 4.371273412680994e-05,
"loss": 4.2228,
"step": 384000
},
{
"epoch": 0.0,
"learning_rate": 4.370434817929942e-05,
"loss": 4.2131,
"step": 384512
},
{
"epoch": 0.0,
"learning_rate": 4.36959622317889e-05,
"loss": 4.2109,
"step": 385024
},
{
"epoch": 0.0,
"learning_rate": 4.368757628427838e-05,
"loss": 4.2024,
"step": 385536
},
{
"epoch": 0.0,
"learning_rate": 4.367919033676786e-05,
"loss": 4.2103,
"step": 386048
},
{
"epoch": 0.0,
"learning_rate": 4.3670804389257345e-05,
"loss": 4.2076,
"step": 386560
},
{
"epoch": 0.0,
"learning_rate": 4.3662418441746825e-05,
"loss": 4.2229,
"step": 387072
},
{
"epoch": 0.0,
"learning_rate": 4.3654032494236305e-05,
"loss": 4.2203,
"step": 387584
},
{
"epoch": 0.0,
"learning_rate": 4.3645646546725785e-05,
"loss": 4.1926,
"step": 388096
},
{
"epoch": 0.0,
"learning_rate": 4.3637260599215265e-05,
"loss": 4.2103,
"step": 388608
},
{
"epoch": 0.0,
"learning_rate": 4.3628874651704745e-05,
"loss": 4.2157,
"step": 389120
},
{
"epoch": 0.0,
"learning_rate": 4.3620505082997954e-05,
"loss": 4.1984,
"step": 389632
},
{
"epoch": 0.0,
"learning_rate": 4.3612119135487434e-05,
"loss": 4.2074,
"step": 390144
},
{
"epoch": 0.0,
"learning_rate": 4.3603733187976914e-05,
"loss": 4.21,
"step": 390656
},
{
"epoch": 0.0,
"learning_rate": 4.3595347240466394e-05,
"loss": 4.2056,
"step": 391168
},
{
"epoch": 0.0,
"learning_rate": 4.358696129295587e-05,
"loss": 4.222,
"step": 391680
},
{
"epoch": 0.0,
"learning_rate": 4.357857534544535e-05,
"loss": 4.2075,
"step": 392192
},
{
"epoch": 0.0,
"learning_rate": 4.357018939793483e-05,
"loss": 4.2133,
"step": 392704
},
{
"epoch": 0.0,
"learning_rate": 4.356180345042431e-05,
"loss": 4.2061,
"step": 393216
},
{
"epoch": 0.0,
"learning_rate": 4.355341750291379e-05,
"loss": 4.2169,
"step": 393728
},
{
"epoch": 0.0,
"learning_rate": 4.354503155540327e-05,
"loss": 4.201,
"step": 394240
},
{
"epoch": 0.0,
"learning_rate": 4.353664560789275e-05,
"loss": 4.2089,
"step": 394752
},
{
"epoch": 0.0,
"learning_rate": 4.352825966038223e-05,
"loss": 4.1994,
"step": 395264
},
{
"epoch": 0.0,
"learning_rate": 4.351990647047917e-05,
"loss": 4.1997,
"step": 395776
},
{
"epoch": 0.0,
"learning_rate": 4.351152052296865e-05,
"loss": 4.1993,
"step": 396288
},
{
"epoch": 0.0,
"learning_rate": 4.350313457545813e-05,
"loss": 4.203,
"step": 396800
},
{
"epoch": 0.01,
"learning_rate": 4.349474862794761e-05,
"loss": 4.2021,
"step": 397312
},
{
"epoch": 0.01,
"learning_rate": 4.348637905924082e-05,
"loss": 4.2092,
"step": 397824
},
{
"epoch": 0.01,
"learning_rate": 4.34779931117303e-05,
"loss": 4.2115,
"step": 398336
},
{
"epoch": 0.01,
"learning_rate": 4.346960716421978e-05,
"loss": 4.2109,
"step": 398848
},
{
"epoch": 0.01,
"learning_rate": 4.346122121670926e-05,
"loss": 4.2018,
"step": 399360
},
{
"epoch": 0.01,
"learning_rate": 4.345283526919875e-05,
"loss": 4.2054,
"step": 399872
},
{
"epoch": 0.01,
"learning_rate": 4.344444932168823e-05,
"loss": 4.2002,
"step": 400384
},
{
"epoch": 0.01,
"learning_rate": 4.343606337417771e-05,
"loss": 4.2014,
"step": 400896
},
{
"epoch": 0.01,
"learning_rate": 4.342767742666719e-05,
"loss": 4.1894,
"step": 401408
},
{
"epoch": 0.01,
"learning_rate": 4.341929147915667e-05,
"loss": 4.1969,
"step": 401920
},
{
"epoch": 0.01,
"learning_rate": 4.3410921910449876e-05,
"loss": 4.1983,
"step": 402432
},
{
"epoch": 0.01,
"learning_rate": 4.3402535962939356e-05,
"loss": 4.2034,
"step": 402944
},
{
"epoch": 0.01,
"learning_rate": 4.3394150015428836e-05,
"loss": 4.1908,
"step": 403456
},
{
"epoch": 0.01,
"learning_rate": 4.3385764067918316e-05,
"loss": 4.198,
"step": 403968
},
{
"epoch": 0.01,
"learning_rate": 4.3377378120407796e-05,
"loss": 4.2131,
"step": 404480
},
{
"epoch": 0.01,
"learning_rate": 4.3368992172897276e-05,
"loss": 4.2005,
"step": 404992
},
{
"epoch": 0.01,
"learning_rate": 4.3360606225386756e-05,
"loss": 4.2054,
"step": 405504
},
{
"epoch": 0.01,
"learning_rate": 4.3352236656679965e-05,
"loss": 4.1936,
"step": 406016
},
{
"epoch": 0.01,
"learning_rate": 4.3343850709169445e-05,
"loss": 4.1801,
"step": 406528
},
{
"epoch": 0.01,
"learning_rate": 4.333546476165893e-05,
"loss": 4.2018,
"step": 407040
},
{
"epoch": 0.01,
"learning_rate": 4.332707881414841e-05,
"loss": 4.1985,
"step": 407552
},
{
"epoch": 0.01,
"learning_rate": 4.331870924544162e-05,
"loss": 4.191,
"step": 408064
},
{
"epoch": 0.01,
"learning_rate": 4.33103232979311e-05,
"loss": 4.1923,
"step": 408576
},
{
"epoch": 0.01,
"learning_rate": 4.330193735042058e-05,
"loss": 4.2013,
"step": 409088
},
{
"epoch": 0.01,
"learning_rate": 4.3293551402910054e-05,
"loss": 4.1758,
"step": 409600
},
{
"epoch": 0.01,
"learning_rate": 4.3285165455399534e-05,
"loss": 4.202,
"step": 410112
},
{
"epoch": 0.01,
"learning_rate": 4.3276779507889013e-05,
"loss": 4.1802,
"step": 410624
},
{
"epoch": 0.01,
"learning_rate": 4.3268393560378493e-05,
"loss": 4.1882,
"step": 411136
},
{
"epoch": 0.01,
"learning_rate": 4.3260007612867973e-05,
"loss": 4.1991,
"step": 411648
},
{
"epoch": 0.01,
"learning_rate": 4.325163804416118e-05,
"loss": 4.1896,
"step": 412160
},
{
"epoch": 0.01,
"learning_rate": 4.32432684754544e-05,
"loss": 4.1878,
"step": 412672
},
{
"epoch": 0.01,
"learning_rate": 4.3234882527943885e-05,
"loss": 4.1946,
"step": 413184
},
{
"epoch": 0.01,
"learning_rate": 4.322649658043336e-05,
"loss": 4.1792,
"step": 413696
},
{
"epoch": 0.01,
"learning_rate": 4.321811063292284e-05,
"loss": 4.1824,
"step": 414208
},
{
"epoch": 0.01,
"learning_rate": 4.3209741064216054e-05,
"loss": 4.1923,
"step": 414720
},
{
"epoch": 0.01,
"learning_rate": 4.320135511670553e-05,
"loss": 4.1875,
"step": 415232
},
{
"epoch": 0.01,
"learning_rate": 4.319296916919501e-05,
"loss": 4.1864,
"step": 415744
},
{
"epoch": 0.01,
"learning_rate": 4.318458322168449e-05,
"loss": 4.18,
"step": 416256
},
{
"epoch": 0.01,
"learning_rate": 4.317619727417397e-05,
"loss": 4.1765,
"step": 416768
},
{
"epoch": 0.01,
"learning_rate": 4.3167827705467176e-05,
"loss": 4.1874,
"step": 417280
},
{
"epoch": 0.01,
"learning_rate": 4.3159441757956656e-05,
"loss": 4.1984,
"step": 417792
},
{
"epoch": 0.01,
"learning_rate": 4.3151055810446136e-05,
"loss": 4.1836,
"step": 418304
},
{
"epoch": 0.01,
"learning_rate": 4.314266986293562e-05,
"loss": 4.2006,
"step": 418816
},
{
"epoch": 0.01,
"learning_rate": 4.31342839154251e-05,
"loss": 4.1977,
"step": 419328
},
{
"epoch": 0.01,
"learning_rate": 4.312589796791458e-05,
"loss": 4.1888,
"step": 419840
},
{
"epoch": 0.01,
"learning_rate": 4.311751202040406e-05,
"loss": 4.1811,
"step": 420352
},
{
"epoch": 0.01,
"learning_rate": 4.310912607289354e-05,
"loss": 4.1962,
"step": 420864
},
{
"epoch": 0.01,
"learning_rate": 4.310074012538302e-05,
"loss": 4.1847,
"step": 421376
},
{
"epoch": 0.01,
"learning_rate": 4.309237055667623e-05,
"loss": 4.18,
"step": 421888
},
{
"epoch": 0.01,
"learning_rate": 4.308398460916571e-05,
"loss": 4.1924,
"step": 422400
},
{
"epoch": 0.01,
"learning_rate": 4.307561504045892e-05,
"loss": 4.1901,
"step": 422912
},
{
"epoch": 0.01,
"learning_rate": 4.30672290929484e-05,
"loss": 4.1948,
"step": 423424
},
{
"epoch": 0.01,
"learning_rate": 4.305884314543788e-05,
"loss": 4.1898,
"step": 423936
},
{
"epoch": 0.01,
"learning_rate": 4.305047357673109e-05,
"loss": 4.1756,
"step": 424448
},
{
"epoch": 0.01,
"learning_rate": 4.3042087629220577e-05,
"loss": 4.1705,
"step": 424960
},
{
"epoch": 0.01,
"learning_rate": 4.3033701681710057e-05,
"loss": 4.1835,
"step": 425472
},
{
"epoch": 0.01,
"learning_rate": 4.3025315734199536e-05,
"loss": 4.1883,
"step": 425984
},
{
"epoch": 0.01,
"learning_rate": 4.3016929786689016e-05,
"loss": 4.1818,
"step": 426496
},
{
"epoch": 0.01,
"learning_rate": 4.3008560217982226e-05,
"loss": 4.1822,
"step": 427008
},
{
"epoch": 0.02,
"learning_rate": 4.3000174270471705e-05,
"loss": 4.1802,
"step": 427520
},
{
"epoch": 0.02,
"learning_rate": 4.2991804701764915e-05,
"loss": 4.1745,
"step": 428032
},
{
"epoch": 0.02,
"learning_rate": 4.2983418754254395e-05,
"loss": 4.1861,
"step": 428544
},
{
"epoch": 0.02,
"learning_rate": 4.2975032806743874e-05,
"loss": 4.1769,
"step": 429056
},
{
"epoch": 0.02,
"learning_rate": 4.2966646859233354e-05,
"loss": 4.1885,
"step": 429568
},
{
"epoch": 0.02,
"learning_rate": 4.2958260911722834e-05,
"loss": 4.1906,
"step": 430080
},
{
"epoch": 0.02,
"learning_rate": 4.2949891343016043e-05,
"loss": 4.1844,
"step": 430592
},
{
"epoch": 0.02,
"learning_rate": 4.294150539550553e-05,
"loss": 4.1743,
"step": 431104
},
{
"epoch": 0.02,
"learning_rate": 4.293311944799501e-05,
"loss": 4.1778,
"step": 431616
},
{
"epoch": 0.02,
"learning_rate": 4.292473350048449e-05,
"loss": 4.1796,
"step": 432128
},
{
"epoch": 0.02,
"learning_rate": 4.291634755297397e-05,
"loss": 4.1936,
"step": 432640
},
{
"epoch": 0.02,
"learning_rate": 4.290796160546345e-05,
"loss": 4.1741,
"step": 433152
},
{
"epoch": 0.02,
"learning_rate": 4.289957565795293e-05,
"loss": 4.175,
"step": 433664
},
{
"epoch": 0.02,
"learning_rate": 4.289118971044241e-05,
"loss": 4.1859,
"step": 434176
},
{
"epoch": 0.02,
"learning_rate": 4.288280376293189e-05,
"loss": 4.1775,
"step": 434688
},
{
"epoch": 0.02,
"learning_rate": 4.287441781542136e-05,
"loss": 4.1748,
"step": 435200
},
{
"epoch": 0.02,
"learning_rate": 4.286603186791084e-05,
"loss": 4.176,
"step": 435712
},
{
"epoch": 0.02,
"learning_rate": 4.285764592040032e-05,
"loss": 4.1742,
"step": 436224
},
{
"epoch": 0.02,
"learning_rate": 4.284927635169354e-05,
"loss": 4.1692,
"step": 436736
},
{
"epoch": 0.02,
"learning_rate": 4.284089040418301e-05,
"loss": 4.1631,
"step": 437248
},
{
"epoch": 0.02,
"learning_rate": 4.283250445667249e-05,
"loss": 4.1796,
"step": 437760
},
{
"epoch": 0.02,
"learning_rate": 4.282411850916198e-05,
"loss": 4.1767,
"step": 438272
},
{
"epoch": 0.02,
"learning_rate": 4.281573256165146e-05,
"loss": 4.1714,
"step": 438784
},
{
"epoch": 0.02,
"learning_rate": 4.280734661414094e-05,
"loss": 4.169,
"step": 439296
},
{
"epoch": 0.02,
"learning_rate": 4.279897704543415e-05,
"loss": 4.1642,
"step": 439808
},
{
"epoch": 0.02,
"learning_rate": 4.279059109792363e-05,
"loss": 4.1894,
"step": 440320
},
{
"epoch": 0.02,
"learning_rate": 4.278220515041311e-05,
"loss": 4.1858,
"step": 440832
},
{
"epoch": 0.02,
"learning_rate": 4.277381920290259e-05,
"loss": 4.1829,
"step": 441344
},
{
"epoch": 0.02,
"learning_rate": 4.276543325539207e-05,
"loss": 4.1777,
"step": 441856
},
{
"epoch": 0.02,
"learning_rate": 4.275704730788155e-05,
"loss": 4.1707,
"step": 442368
},
{
"epoch": 0.02,
"learning_rate": 4.274866136037103e-05,
"loss": 4.1756,
"step": 442880
},
{
"epoch": 0.02,
"learning_rate": 4.274027541286051e-05,
"loss": 4.167,
"step": 443392
},
{
"epoch": 0.02,
"learning_rate": 4.2731905844153717e-05,
"loss": 4.173,
"step": 443904
},
{
"epoch": 0.02,
"learning_rate": 4.2723519896643196e-05,
"loss": 4.1728,
"step": 444416
},
{
"epoch": 0.02,
"learning_rate": 4.2715133949132676e-05,
"loss": 4.1737,
"step": 444928
},
{
"epoch": 0.02,
"learning_rate": 4.270674800162216e-05,
"loss": 4.1756,
"step": 445440
},
{
"epoch": 0.02,
"learning_rate": 4.269836205411164e-05,
"loss": 4.1688,
"step": 445952
},
{
"epoch": 0.02,
"learning_rate": 4.268997610660112e-05,
"loss": 4.1681,
"step": 446464
},
{
"epoch": 0.02,
"learning_rate": 4.26815901590906e-05,
"loss": 4.1706,
"step": 446976
},
{
"epoch": 0.02,
"learning_rate": 4.2673204211580076e-05,
"loss": 4.1654,
"step": 447488
},
{
"epoch": 0.02,
"learning_rate": 4.266483464287329e-05,
"loss": 4.1714,
"step": 448000
},
{
"epoch": 0.02,
"learning_rate": 4.26564650741665e-05,
"loss": 4.182,
"step": 448512
},
{
"epoch": 0.02,
"learning_rate": 4.264807912665598e-05,
"loss": 4.1828,
"step": 449024
},
{
"epoch": 0.02,
"learning_rate": 4.263969317914546e-05,
"loss": 4.1647,
"step": 449536
},
{
"epoch": 0.02,
"learning_rate": 4.263130723163494e-05,
"loss": 4.1779,
"step": 450048
},
{
"epoch": 0.02,
"learning_rate": 4.262292128412442e-05,
"loss": 4.1706,
"step": 450560
},
{
"epoch": 0.02,
"learning_rate": 4.26145353366139e-05,
"loss": 4.1803,
"step": 451072
},
{
"epoch": 0.02,
"learning_rate": 4.260614938910338e-05,
"loss": 4.1719,
"step": 451584
},
{
"epoch": 0.02,
"learning_rate": 4.25977798203966e-05,
"loss": 4.1767,
"step": 452096
},
{
"epoch": 0.02,
"learning_rate": 4.258939387288608e-05,
"loss": 4.1656,
"step": 452608
},
{
"epoch": 0.02,
"learning_rate": 4.258100792537555e-05,
"loss": 4.1737,
"step": 453120
},
{
"epoch": 0.02,
"learning_rate": 4.257262197786503e-05,
"loss": 4.1613,
"step": 453632
},
{
"epoch": 0.02,
"learning_rate": 4.2564252409158246e-05,
"loss": 4.167,
"step": 454144
},
{
"epoch": 0.02,
"learning_rate": 4.2555866461647726e-05,
"loss": 4.1689,
"step": 454656
},
{
"epoch": 0.02,
"learning_rate": 4.25474805141372e-05,
"loss": 4.1723,
"step": 455168
},
{
"epoch": 0.02,
"learning_rate": 4.253909456662668e-05,
"loss": 4.1712,
"step": 455680
},
{
"epoch": 0.02,
"learning_rate": 4.253070861911616e-05,
"loss": 4.1683,
"step": 456192
},
{
"epoch": 0.02,
"learning_rate": 4.2522339050409375e-05,
"loss": 4.1764,
"step": 456704
},
{
"epoch": 0.02,
"learning_rate": 4.2513953102898855e-05,
"loss": 4.1633,
"step": 457216
},
{
"epoch": 0.02,
"learning_rate": 4.250558353419207e-05,
"loss": 4.167,
"step": 457728
},
{
"epoch": 0.03,
"eval_loss": 4.163780689239502,
"eval_runtime": 291.3236,
"eval_samples_per_second": 1309.853,
"eval_steps_per_second": 40.934,
"step": 457920
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.891861849552535e+17,
"trial_name": null,
"trial_params": null
}