npi-only-lstm-3 / checkpoint-1908000 /trainer_state.json
abhinavp's picture
Training in progress, epoch 1, checkpoint
acdb1d1 verified
{
"best_metric": 3.9842660427093506,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-only/lstm/3/checkpoints/checkpoint-1908000",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 1908000,
"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": 10.8208,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5525,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0564,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9917,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9456,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8947,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7148,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.608,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5116,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4526,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.4085,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3554,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2919,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.2369,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1912,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.1306,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0968,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 6.0456,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.9932,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9602,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.9203,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 5.8789,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 5.8514,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.8072,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.786,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7572,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7303,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6995,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6648,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.975684027980238e-05,
"loss": 5.652,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.974845433229186e-05,
"loss": 5.6281,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.6148,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5876,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.5684,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714926921053515e-05,
"loss": 5.5576,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706540973542995e-05,
"loss": 5.5397,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5201,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.9689785457325684e-05,
"loss": 5.4885,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.9681399509815164e-05,
"loss": 5.4832,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.9673013562304644e-05,
"loss": 5.4514,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4533,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.427,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.4288,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.3997,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963110020355577e-05,
"loss": 5.3924,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3859,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.3776,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.3604,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 5.3383,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3357,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3381,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3259,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956404538107908e-05,
"loss": 5.3046,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955565943356856e-05,
"loss": 5.2941,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954727348605804e-05,
"loss": 5.2901,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2767,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.2868,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2426,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2558,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.9505360127309166e-05,
"loss": 5.2416,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.9496974179798646e-05,
"loss": 5.2263,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.234,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948021866358134e-05,
"loss": 5.212,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947183271607082e-05,
"loss": 5.2018,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.94634467685603e-05,
"loss": 5.1982,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.209,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.1833,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1782,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1637,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1557,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.161,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940477789359412e-05,
"loss": 5.165,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.93963919460836e-05,
"loss": 5.1376,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938800599857309e-05,
"loss": 5.148,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.937962005106256e-05,
"loss": 5.1488,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.937123410355204e-05,
"loss": 5.1286,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1109,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935447858733473e-05,
"loss": 5.1119,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934609263982421e-05,
"loss": 5.1045,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933770669231369e-05,
"loss": 5.0941,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932932074480317e-05,
"loss": 5.0918,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932095117609638e-05,
"loss": 5.0943,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931256522858586e-05,
"loss": 5.0933,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930417928107534e-05,
"loss": 5.0756,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295809712368554e-05,
"loss": 5.0548,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.0617,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.0651,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.0534,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262265922326474e-05,
"loss": 5.0504,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.9253879974815954e-05,
"loss": 5.0318,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.9245494027305433e-05,
"loss": 5.0316,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.9237108079794913e-05,
"loss": 5.0262,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922873851108812e-05,
"loss": 5.0245,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92203525635776e-05,
"loss": 5.0253,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921196661606708e-05,
"loss": 5.0075,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920358066855656e-05,
"loss": 5.0243,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 5.0082,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918682515233926e-05,
"loss": 4.989,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917843920482874e-05,
"loss": 4.9839,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917005325731822e-05,
"loss": 4.9849,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.91616673098077e-05,
"loss": 4.983,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915328136229718e-05,
"loss": 4.9812,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914489541478666e-05,
"loss": 4.9736,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913650946727614e-05,
"loss": 4.9657,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912813989856935e-05,
"loss": 4.9618,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911975395105883e-05,
"loss": 4.9411,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911136800354831e-05,
"loss": 4.945,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9102998434841516e-05,
"loss": 4.9434,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.9094612487330996e-05,
"loss": 4.9392,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.9086226539820476e-05,
"loss": 4.9336,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907785697111369e-05,
"loss": 4.9397,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906947102360317e-05,
"loss": 4.9143,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906108507609265e-05,
"loss": 4.9181,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905269912858213e-05,
"loss": 4.9116,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904431318107161e-05,
"loss": 4.9176,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903592723356109e-05,
"loss": 4.922,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027541286050565e-05,
"loss": 4.9052,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019155338540045e-05,
"loss": 4.9018,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010769391029525e-05,
"loss": 4.8923,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900239982232274e-05,
"loss": 4.9004,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994013874812214e-05,
"loss": 4.894,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.89856279273017e-05,
"loss": 4.8885,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897724197979118e-05,
"loss": 4.8824,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.896885603228066e-05,
"loss": 4.8746,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.8702,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.859,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.8638,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.8584,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8544,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8448,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.8607,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.8604,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.8495,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.8376,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.8368,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.8398,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885990422985882e-05,
"loss": 4.8364,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515182823483e-05,
"loss": 4.8313,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.8279,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883474638732726e-05,
"loss": 4.8247,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882636043981674e-05,
"loss": 4.8173,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881797449230622e-05,
"loss": 4.8127,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88095885447957e-05,
"loss": 4.8167,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880121897608891e-05,
"loss": 4.8047,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.7993,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.8073,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.7931,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876769156485057e-05,
"loss": 4.8016,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875930561734005e-05,
"loss": 4.7919,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875091966982953e-05,
"loss": 4.7826,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.750964641571045,
"eval_runtime": 293.5866,
"eval_samples_per_second": 1299.756,
"eval_steps_per_second": 40.618,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874253372231901e-05,
"loss": 4.7763,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873414777480849e-05,
"loss": 4.7778,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872576182729797e-05,
"loss": 4.7878,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871737587978745e-05,
"loss": 4.7761,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870898993227693e-05,
"loss": 4.7784,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.87006039847664e-05,
"loss": 4.7652,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692234416059616e-05,
"loss": 4.7664,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683848468549096e-05,
"loss": 4.7531,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675478899842306e-05,
"loss": 4.7645,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.7619,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7686,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.7477,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864195148860396e-05,
"loss": 4.7477,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863356554109344e-05,
"loss": 4.7431,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862517959358292e-05,
"loss": 4.7345,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.86167936460724e-05,
"loss": 4.7372,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608407698561874e-05,
"loss": 4.7457,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.7284,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.7292,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858326623483405e-05,
"loss": 4.7434,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857488028732352e-05,
"loss": 4.7308,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856649433981301e-05,
"loss": 4.7303,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855810839230249e-05,
"loss": 4.7171,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.85497388235957e-05,
"loss": 4.7321,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854135287608518e-05,
"loss": 4.7177,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853296692857466e-05,
"loss": 4.7157,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852458098106414e-05,
"loss": 4.7097,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851619503355362e-05,
"loss": 4.705,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850782546484683e-05,
"loss": 4.699,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849943951733631e-05,
"loss": 4.6999,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849105356982579e-05,
"loss": 4.7092,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848266762231527e-05,
"loss": 4.7047,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847428167480475e-05,
"loss": 4.697,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846589572729423e-05,
"loss": 4.7064,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.8457526158587444e-05,
"loss": 4.6982,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.6946,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844077064237013e-05,
"loss": 4.6795,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.6843,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842399874734909e-05,
"loss": 4.6725,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841561279983857e-05,
"loss": 4.6825,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840722685232805e-05,
"loss": 4.6668,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839884090481753e-05,
"loss": 4.6819,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839045495730701e-05,
"loss": 4.6633,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838206900979649e-05,
"loss": 4.6715,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837368306228597e-05,
"loss": 4.6691,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836529711477545e-05,
"loss": 4.6671,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835691116726493e-05,
"loss": 4.6621,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834854159855814e-05,
"loss": 4.6513,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.649,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833178608234084e-05,
"loss": 4.6657,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.6578,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.6506,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.6399,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.6497,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.6381,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281486776081446e-05,
"loss": 4.6633,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273100828570926e-05,
"loss": 4.6257,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264714881060406e-05,
"loss": 4.6468,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256328933549886e-05,
"loss": 4.6374,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247942986039366e-05,
"loss": 4.6262,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239557038528846e-05,
"loss": 4.6387,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.6323,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222801522311535e-05,
"loss": 4.6164,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214415574801015e-05,
"loss": 4.624,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206029627290495e-05,
"loss": 4.6368,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197643679779975e-05,
"loss": 4.6212,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189274111073184e-05,
"loss": 4.6185,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180888163562664e-05,
"loss": 4.6144,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172502216052144e-05,
"loss": 4.6104,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164116268541624e-05,
"loss": 4.6206,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155730321031104e-05,
"loss": 4.6318,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147344373520584e-05,
"loss": 4.6074,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.81389748048138e-05,
"loss": 4.6249,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813058885730328e-05,
"loss": 4.625,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812220290979276e-05,
"loss": 4.6135,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811381696228224e-05,
"loss": 4.6,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810543101477172e-05,
"loss": 4.6117,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.80970450672612e-05,
"loss": 4.6056,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808865911975068e-05,
"loss": 4.5988,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808027317224016e-05,
"loss": 4.5995,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807190360353337e-05,
"loss": 4.6023,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806353403482658e-05,
"loss": 4.6113,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805514808731606e-05,
"loss": 4.5987,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804676213980554e-05,
"loss": 4.583,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803837619229502e-05,
"loss": 4.5932,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8029990244784504e-05,
"loss": 4.5961,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802162067607771e-05,
"loss": 4.5923,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801323472856719e-05,
"loss": 4.5971,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800484878105667e-05,
"loss": 4.5837,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799646283354615e-05,
"loss": 4.5795,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798807688603563e-05,
"loss": 4.58,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797970731732884e-05,
"loss": 4.5849,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797133774862205e-05,
"loss": 4.5831,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796295180111153e-05,
"loss": 4.5763,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795456585360101e-05,
"loss": 4.5948,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794617990609049e-05,
"loss": 4.5839,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793779395857997e-05,
"loss": 4.5648,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792940801106946e-05,
"loss": 4.5683,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792102206355894e-05,
"loss": 4.5717,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791263611604842e-05,
"loss": 4.5727,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790426654734163e-05,
"loss": 4.572,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895880599831107e-05,
"loss": 4.57,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887494652320587e-05,
"loss": 4.564,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879108704810067e-05,
"loss": 4.5669,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870722757299546e-05,
"loss": 4.5441,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786233680978902e-05,
"loss": 4.559,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853967241082236e-05,
"loss": 4.5533,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845581293571715e-05,
"loss": 4.5567,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837195346061195e-05,
"loss": 4.5505,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828809398550675e-05,
"loss": 4.5605,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820423451040155e-05,
"loss": 4.5422,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781205388233337e-05,
"loss": 4.5448,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803667934822844e-05,
"loss": 4.5464,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795281987312324e-05,
"loss": 4.5464,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786896039801804e-05,
"loss": 4.5611,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777852647109502e-05,
"loss": 4.5486,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777015690238823e-05,
"loss": 4.5466,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776177095487771e-05,
"loss": 4.5397,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775338500736719e-05,
"loss": 4.546,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774499905985666e-05,
"loss": 4.544,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773661311234615e-05,
"loss": 4.538,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772824354363936e-05,
"loss": 4.5403,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719857596128845e-05,
"loss": 4.534,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771147164861832e-05,
"loss": 4.5328,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.77030857011078e-05,
"loss": 4.5224,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769469975359728e-05,
"loss": 4.5278,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768631380608676e-05,
"loss": 4.524,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767792785857624e-05,
"loss": 4.5293,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766954191106572e-05,
"loss": 4.516,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.76611559635552e-05,
"loss": 4.5374,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.5426,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764440044733789e-05,
"loss": 4.5288,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763601449982737e-05,
"loss": 4.5201,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762762855231685e-05,
"loss": 4.5232,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761924260480633e-05,
"loss": 4.5259,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610856657295813e-05,
"loss": 4.5263,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602470709785293e-05,
"loss": 4.5224,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941011410785e-05,
"loss": 4.5195,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758571519356798e-05,
"loss": 4.5177,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757732924605746e-05,
"loss": 4.5209,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756894329854694e-05,
"loss": 4.5103,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756055735103642e-05,
"loss": 4.5213,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.75521714035259e-05,
"loss": 4.5115,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754380183481911e-05,
"loss": 4.5051,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753541588730859e-05,
"loss": 4.5171,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752702993979807e-05,
"loss": 4.5045,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751864399228755e-05,
"loss": 4.512,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751025804477703e-05,
"loss": 4.5008,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750187209726651e-05,
"loss": 4.5004,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.470288276672363,
"eval_runtime": 282.4462,
"eval_samples_per_second": 1351.022,
"eval_steps_per_second": 42.22,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749348614975599e-05,
"loss": 4.4972,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748510020224547e-05,
"loss": 4.491,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747671425473495e-05,
"loss": 4.5106,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746832830722443e-05,
"loss": 4.4964,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745994235971391e-05,
"loss": 4.5059,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745155641220339e-05,
"loss": 4.4891,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744317046469287e-05,
"loss": 4.4973,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743478451718235e-05,
"loss": 4.4792,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742639856967183e-05,
"loss": 4.4956,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741801262216131e-05,
"loss": 4.4983,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740962667465079e-05,
"loss": 4.4997,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401240727140264e-05,
"loss": 4.489,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739285477962975e-05,
"loss": 4.48,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738446883211923e-05,
"loss": 4.4833,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737608288460871e-05,
"loss": 4.4784,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736769693709819e-05,
"loss": 4.4797,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.73593273683914e-05,
"loss": 4.4857,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735094142088088e-05,
"loss": 4.4739,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734255547337036e-05,
"loss": 4.4768,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733416952585984e-05,
"loss": 4.4957,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732578357834932e-05,
"loss": 4.4815,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.73173976308388e-05,
"loss": 4.4834,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730901168332828e-05,
"loss": 4.4703,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730062573581776e-05,
"loss": 4.4891,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729225616711097e-05,
"loss": 4.4653,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728387021960045e-05,
"loss": 4.4734,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727548427208993e-05,
"loss": 4.4686,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267098324579415e-05,
"loss": 4.4693,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258712377068895e-05,
"loss": 4.4566,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250326429558375e-05,
"loss": 4.463,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7241940482047855e-05,
"loss": 4.4729,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233554534537335e-05,
"loss": 4.4728,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225184965830544e-05,
"loss": 4.4674,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721681539712375e-05,
"loss": 4.4687,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720842944961323e-05,
"loss": 4.4658,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720004350210271e-05,
"loss": 4.4669,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719165755459219e-05,
"loss": 4.4524,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718327160708167e-05,
"loss": 4.4562,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717488565957115e-05,
"loss": 4.4474,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716649971206063e-05,
"loss": 4.4611,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715813014335385e-05,
"loss": 4.4457,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714974419584333e-05,
"loss": 4.4562,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714135824833281e-05,
"loss": 4.4491,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713297230082228e-05,
"loss": 4.4472,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712458635331176e-05,
"loss": 4.4575,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711620040580124e-05,
"loss": 4.4482,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710781445829072e-05,
"loss": 4.4485,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.70994285107802e-05,
"loss": 4.4322,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709105894207341e-05,
"loss": 4.4375,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708267299456289e-05,
"loss": 4.4509,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707428704705237e-05,
"loss": 4.4429,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706590109954185e-05,
"loss": 4.4429,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057531530835066e-05,
"loss": 4.4276,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704917834093201e-05,
"loss": 4.4413,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704079239342149e-05,
"loss": 4.4287,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703240644591097e-05,
"loss": 4.4546,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702402049840045e-05,
"loss": 4.4208,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015634550889924e-05,
"loss": 4.442,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007248603379404e-05,
"loss": 4.4364,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998862655868884e-05,
"loss": 4.4201,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990476708358364e-05,
"loss": 4.4316,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982090760847844e-05,
"loss": 4.4365,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973704813337324e-05,
"loss": 4.4185,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965318865826804e-05,
"loss": 4.4261,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695694929712002e-05,
"loss": 4.4355,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.69485633496095e-05,
"loss": 4.4294,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694017740209898e-05,
"loss": 4.419,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693179145458846e-05,
"loss": 4.4228,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692340550707794e-05,
"loss": 4.4135,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691501955956742e-05,
"loss": 4.4269,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.69066336120569e-05,
"loss": 4.4402,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689824766454638e-05,
"loss": 4.4184,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688987809583959e-05,
"loss": 4.435,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688149214832907e-05,
"loss": 4.434,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687312257962228e-05,
"loss": 4.4256,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686473663211176e-05,
"loss": 4.4126,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856350684601245e-05,
"loss": 4.4289,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6847964737090725e-05,
"loss": 4.419,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839578789580204e-05,
"loss": 4.4188,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831192842069684e-05,
"loss": 4.4143,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822806894559164e-05,
"loss": 4.4195,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814420947048644e-05,
"loss": 4.4322,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806051378341853e-05,
"loss": 4.4151,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797665430831333e-05,
"loss": 4.4034,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678927948332081e-05,
"loss": 4.4099,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.6780893535810287e-05,
"loss": 4.4171,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772507588299766e-05,
"loss": 4.4154,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764121640789246e-05,
"loss": 4.4224,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675575207208246e-05,
"loss": 4.405,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674736612457194e-05,
"loss": 4.4059,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673898017706142e-05,
"loss": 4.3993,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.67305942295509e-05,
"loss": 4.4078,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672222466084412e-05,
"loss": 4.4098,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671383871333359e-05,
"loss": 4.4068,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670545276582307e-05,
"loss": 4.4244,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669706681831255e-05,
"loss": 4.4058,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668868087080203e-05,
"loss": 4.4006,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668029492329151e-05,
"loss": 4.3965,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667190897578099e-05,
"loss": 4.3999,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666352302827047e-05,
"loss": 4.4068,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665515345956368e-05,
"loss": 4.4051,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664676751205316e-05,
"loss": 4.401,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663838156454265e-05,
"loss": 4.3965,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.662999561703213e-05,
"loss": 4.4026,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621626048325336e-05,
"loss": 4.3782,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613240100814816e-05,
"loss": 4.3951,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6604870532108025e-05,
"loss": 4.3881,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596484584597505e-05,
"loss": 4.3939,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588098637086985e-05,
"loss": 4.3901,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579712689576465e-05,
"loss": 4.3991,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571343120869674e-05,
"loss": 4.3813,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656297355216288e-05,
"loss": 4.3812,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655458760465237e-05,
"loss": 4.3902,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654620165714185e-05,
"loss": 4.3828,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653781570963133e-05,
"loss": 4.4028,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652942976212081e-05,
"loss": 4.3955,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652106019341402e-05,
"loss": 4.3913,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.65126742459035e-05,
"loss": 4.3806,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650428829839298e-05,
"loss": 4.3867,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649590235088246e-05,
"loss": 4.3885,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648751640337194e-05,
"loss": 4.3842,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647913045586142e-05,
"loss": 4.3874,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.64707445083509e-05,
"loss": 4.3767,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646235856084038e-05,
"loss": 4.381,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645397261332986e-05,
"loss": 4.3701,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644558666581934e-05,
"loss": 4.3766,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437217097112554e-05,
"loss": 4.3713,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428831149602034e-05,
"loss": 4.3768,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420445202091514e-05,
"loss": 4.3648,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412059254580994e-05,
"loss": 4.3885,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403673307070474e-05,
"loss": 4.3918,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639528735955995e-05,
"loss": 4.3809,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638690141204943e-05,
"loss": 4.368,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637851546453891e-05,
"loss": 4.3765,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637014589583212e-05,
"loss": 4.3763,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6361759948321596e-05,
"loss": 4.3806,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353374000811076e-05,
"loss": 4.3758,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6344988053300556e-05,
"loss": 4.3718,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633661848459377e-05,
"loss": 4.3726,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632823253708325e-05,
"loss": 4.3779,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631984658957273e-05,
"loss": 4.3686,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631146064206221e-05,
"loss": 4.3746,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630309107335542e-05,
"loss": 4.3677,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.62947051258449e-05,
"loss": 4.3642,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628631917833438e-05,
"loss": 4.376,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627793323082386e-05,
"loss": 4.3687,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626956366211707e-05,
"loss": 4.3641,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626117771460655e-05,
"loss": 4.3594,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625279176709603e-05,
"loss": 4.3575,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.33747673034668,
"eval_runtime": 344.3519,
"eval_samples_per_second": 1108.142,
"eval_steps_per_second": 34.63,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624440581958551e-05,
"loss": 4.3641,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.6236036250878726e-05,
"loss": 4.3525,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.6227650303368205e-05,
"loss": 4.3696,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219264355857685e-05,
"loss": 4.3571,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.6210878408347165e-05,
"loss": 4.3673,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202492460836645e-05,
"loss": 4.354,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194106513326125e-05,
"loss": 4.3577,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185720565815605e-05,
"loss": 4.3429,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177350997108814e-05,
"loss": 4.3607,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6168965049598294e-05,
"loss": 4.3618,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.6160579102087774e-05,
"loss": 4.3627,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.6152193154577254e-05,
"loss": 4.3556,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6143807207066734e-05,
"loss": 4.347,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613543763835994e-05,
"loss": 4.3507,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612705169084942e-05,
"loss": 4.3444,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611866574333891e-05,
"loss": 4.3483,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611027979582839e-05,
"loss": 4.3522,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610189384831787e-05,
"loss": 4.3428,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609350790080735e-05,
"loss": 4.3441,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608513833210056e-05,
"loss": 4.3687,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607675238459004e-05,
"loss": 4.3499,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606836643707952e-05,
"loss": 4.351,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6059980489569e-05,
"loss": 4.3438,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605159454205848e-05,
"loss": 4.3568,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604320859454796e-05,
"loss": 4.3381,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603483902584117e-05,
"loss": 4.3517,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602645307833065e-05,
"loss": 4.3382,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601806713082013e-05,
"loss": 4.3399,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.600968118330961e-05,
"loss": 4.3288,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600129523579909e-05,
"loss": 4.3388,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599290928828857e-05,
"loss": 4.3432,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598452334077805e-05,
"loss": 4.347,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597613739326753e-05,
"loss": 4.3434,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5967767824560737e-05,
"loss": 4.345,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.5959381877050217e-05,
"loss": 4.3394,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.5950995929539696e-05,
"loss": 4.3451,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.5942609982029176e-05,
"loss": 4.3259,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.5934240413322386e-05,
"loss": 4.3364,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.5925854465811865e-05,
"loss": 4.3234,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.5917468518301345e-05,
"loss": 4.3359,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590908257079083e-05,
"loss": 4.3272,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590072938088778e-05,
"loss": 4.335,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589234343337726e-05,
"loss": 4.3316,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588395748586673e-05,
"loss": 4.3238,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587557153835621e-05,
"loss": 4.3381,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586718559084569e-05,
"loss": 4.3291,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858816022138906e-05,
"loss": 4.3281,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585043007462838e-05,
"loss": 4.315,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584204412711786e-05,
"loss": 4.318,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583365817960734e-05,
"loss": 4.3302,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582527223209682e-05,
"loss": 4.3261,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.58168862845863e-05,
"loss": 4.3233,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808500337075786e-05,
"loss": 4.3128,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800114389565266e-05,
"loss": 4.3263,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791744820858475e-05,
"loss": 4.3102,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783358873347955e-05,
"loss": 4.3331,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5774972925837435e-05,
"loss": 4.3116,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766586978326915e-05,
"loss": 4.3215,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758217409620124e-05,
"loss": 4.322,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5749831462109604e-05,
"loss": 4.3079,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741445514599084e-05,
"loss": 4.3136,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733059567088564e-05,
"loss": 4.3208,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572468999838177e-05,
"loss": 4.3039,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571630405087125e-05,
"loss": 4.316,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570791810336074e-05,
"loss": 4.317,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569953215585022e-05,
"loss": 4.3193,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569116258714343e-05,
"loss": 4.3074,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568277663963291e-05,
"loss": 4.3128,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567439069212239e-05,
"loss": 4.301,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566600474461187e-05,
"loss": 4.3136,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565763517590508e-05,
"loss": 4.3251,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564924922839456e-05,
"loss": 4.3092,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564086328088404e-05,
"loss": 4.3223,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563247733337352e-05,
"loss": 4.3237,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624091385863e-05,
"loss": 4.3206,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561573819595994e-05,
"loss": 4.2976,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560735224844942e-05,
"loss": 4.3185,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.55989663009389e-05,
"loss": 4.3155,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559058035342838e-05,
"loss": 4.3046,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558219440591786e-05,
"loss": 4.3078,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557380845840734e-05,
"loss": 4.312,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556543888970055e-05,
"loss": 4.3248,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555705294219003e-05,
"loss": 4.3063,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554866699467951e-05,
"loss": 4.2949,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554028104716899e-05,
"loss": 4.3072,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553189509965847e-05,
"loss": 4.306,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552350915214795e-05,
"loss": 4.3086,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551512320463743e-05,
"loss": 4.3126,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550673725712691e-05,
"loss": 4.3016,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549836768842013e-05,
"loss": 4.3,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.548998174090961e-05,
"loss": 4.2939,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548159579339909e-05,
"loss": 4.2988,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547320984588857e-05,
"loss": 4.3013,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.5464840277181776e-05,
"loss": 4.3093,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.5456454329671256e-05,
"loss": 4.3214,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448068382160736e-05,
"loss": 4.2992,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.5439682434650216e-05,
"loss": 4.2935,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543129648713969e-05,
"loss": 4.2968,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.5422943297236634e-05,
"loss": 4.2964,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.5414557349726114e-05,
"loss": 4.306,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406171402215594e-05,
"loss": 4.2967,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539778545470508e-05,
"loss": 4.3006,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538939950719456e-05,
"loss": 4.2946,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538101355968404e-05,
"loss": 4.3015,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537264399097725e-05,
"loss": 4.2773,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536425804346673e-05,
"loss": 4.2919,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535587209595621e-05,
"loss": 4.2858,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534748614844569e-05,
"loss": 4.2972,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533910020093516e-05,
"loss": 4.2888,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533073063222838e-05,
"loss": 4.2966,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532234468471786e-05,
"loss": 4.2825,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531395873720733e-05,
"loss": 4.2838,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530557278969682e-05,
"loss": 4.2865,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.52971868421863e-05,
"loss": 4.2897,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528880089467578e-05,
"loss": 4.3011,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528041494716526e-05,
"loss": 4.2997,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.52720617572622e-05,
"loss": 4.2929,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526367580975168e-05,
"loss": 4.2836,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525528986224116e-05,
"loss": 4.2877,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.5246903914730636e-05,
"loss": 4.2933,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.5238517967220116e-05,
"loss": 4.2831,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.5230132019709596e-05,
"loss": 4.2899,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.5221746072199076e-05,
"loss": 4.2846,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.5213360124688556e-05,
"loss": 4.28,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.5204974177178036e-05,
"loss": 4.2795,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519660460847125e-05,
"loss": 4.2801,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518821866096073e-05,
"loss": 4.2745,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517983271345021e-05,
"loss": 4.285,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517144676593969e-05,
"loss": 4.2674,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516306081842917e-05,
"loss": 4.2958,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515467487091865e-05,
"loss": 4.2923,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514630530221186e-05,
"loss": 4.2927,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513791935470134e-05,
"loss": 4.2705,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512953340719082e-05,
"loss": 4.2846,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.51211474596803e-05,
"loss": 4.2871,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511276151216978e-05,
"loss": 4.2838,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510437556465926e-05,
"loss": 4.2817,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509598961714874e-05,
"loss": 4.2806,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508760366963822e-05,
"loss": 4.2805,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079234100931436e-05,
"loss": 4.2867,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070848153420916e-05,
"loss": 4.2739,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062462205910396e-05,
"loss": 4.2812,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.5054076258399876e-05,
"loss": 4.2774,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.5045706689693085e-05,
"loss": 4.2707,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.5037320742182565e-05,
"loss": 4.2829,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5028934794672045e-05,
"loss": 4.2795,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502054884716152e-05,
"loss": 4.2757,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012179278454734e-05,
"loss": 4.2681,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.5003793330944214e-05,
"loss": 4.2671,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.25527811050415,
"eval_runtime": 345.7769,
"eval_samples_per_second": 1103.576,
"eval_steps_per_second": 34.488,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.4995407383433694e-05,
"loss": 4.2705,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987021435923174e-05,
"loss": 4.2616,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978635488412654e-05,
"loss": 4.2787,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970249540902134e-05,
"loss": 4.2698,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4961863593391614e-05,
"loss": 4.2834,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953477645881094e-05,
"loss": 4.2639,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945091698370574e-05,
"loss": 4.2667,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936705750860054e-05,
"loss": 4.2532,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928319803349534e-05,
"loss": 4.2763,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4919933855839014e-05,
"loss": 4.2747,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911547908328494e-05,
"loss": 4.2708,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903161960817974e-05,
"loss": 4.27,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489479239211118e-05,
"loss": 4.2568,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488640644460066e-05,
"loss": 4.2688,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487802049709014e-05,
"loss": 4.2567,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486963454957962e-05,
"loss": 4.2641,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.48612486020691e-05,
"loss": 4.2617,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485286265455859e-05,
"loss": 4.2571,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484447670704806e-05,
"loss": 4.2644,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483609075953754e-05,
"loss": 4.2781,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482770481202702e-05,
"loss": 4.2624,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.48193188645165e-05,
"loss": 4.2668,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481093291700598e-05,
"loss": 4.2602,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480256334829919e-05,
"loss": 4.2707,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479417740078867e-05,
"loss": 4.257,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478579145327815e-05,
"loss": 4.2646,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477740550576763e-05,
"loss": 4.2557,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476901955825711e-05,
"loss": 4.2528,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476063361074659e-05,
"loss": 4.2487,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475224766323607e-05,
"loss": 4.2542,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474386171572556e-05,
"loss": 4.2594,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473549214701877e-05,
"loss": 4.2637,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.4727122578311976e-05,
"loss": 4.2619,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.4718736630801456e-05,
"loss": 4.2602,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710350683290936e-05,
"loss": 4.257,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.4701964735780416e-05,
"loss": 4.2624,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693578788269896e-05,
"loss": 4.2521,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.4685192840759376e-05,
"loss": 4.2516,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4676806893248856e-05,
"loss": 4.2389,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668420945738336e-05,
"loss": 4.252,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660051377031545e-05,
"loss": 4.2487,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651665429521025e-05,
"loss": 4.2555,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464327948201051e-05,
"loss": 4.2513,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463489353449999e-05,
"loss": 4.2423,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462650758698947e-05,
"loss": 4.2579,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461812163947895e-05,
"loss": 4.2482,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460975207077216e-05,
"loss": 4.2481,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460136612326164e-05,
"loss": 4.2382,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459298017575112e-05,
"loss": 4.2359,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584594228240594e-05,
"loss": 4.2493,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576208280730074e-05,
"loss": 4.2468,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4567822333219554e-05,
"loss": 4.2442,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559436385709033e-05,
"loss": 4.2359,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551050438198513e-05,
"loss": 4.248,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454268086949173e-05,
"loss": 4.232,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534311300784945e-05,
"loss": 4.2526,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4525925353274425e-05,
"loss": 4.2302,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.45175394057639e-05,
"loss": 4.2443,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450915345825338e-05,
"loss": 4.2417,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450076751074286e-05,
"loss": 4.2358,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449238156323234e-05,
"loss": 4.2345,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448399561572182e-05,
"loss": 4.2418,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.44756096682113e-05,
"loss": 4.2271,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446724009950451e-05,
"loss": 4.2393,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445885415199399e-05,
"loss": 4.2423,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445046820448347e-05,
"loss": 4.2417,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444208225697295e-05,
"loss": 4.2326,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443371268826616e-05,
"loss": 4.235,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442534311955937e-05,
"loss": 4.228,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441695717204885e-05,
"loss": 4.2332,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440857122453833e-05,
"loss": 4.247,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440018527702781e-05,
"loss": 4.2367,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439179932951729e-05,
"loss": 4.2466,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438341338200677e-05,
"loss": 4.2484,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437502743449625e-05,
"loss": 4.2478,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436664148698573e-05,
"loss": 4.2259,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435828829708267e-05,
"loss": 4.2375,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.4349918728375886e-05,
"loss": 4.2466,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.4341532780865366e-05,
"loss": 4.2295,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333146833354846e-05,
"loss": 4.2326,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4324760885844326e-05,
"loss": 4.235,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316374938333806e-05,
"loss": 4.2527,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4307988990823286e-05,
"loss": 4.2363,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299603043312766e-05,
"loss": 4.2184,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291217095802245e-05,
"loss": 4.2329,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4282831148291725e-05,
"loss": 4.2323,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274461579584935e-05,
"loss": 4.237,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266075632074415e-05,
"loss": 4.2404,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257689684563894e-05,
"loss": 4.2279,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249303737053374e-05,
"loss": 4.2264,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4240917789542854e-05,
"loss": 4.2259,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423254822083607e-05,
"loss": 4.2218,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422416227332555e-05,
"loss": 4.2325,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421577632581503e-05,
"loss": 4.2362,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420739037830451e-05,
"loss": 4.2473,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419900443079399e-05,
"loss": 4.2342,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419061848328347e-05,
"loss": 4.2195,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418223253577295e-05,
"loss": 4.2246,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417384658826243e-05,
"loss": 4.2225,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416547701955564e-05,
"loss": 4.2362,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415712382965258e-05,
"loss": 4.2301,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414873788214206e-05,
"loss": 4.2299,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.4140351934631544e-05,
"loss": 4.2223,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4131965987121024e-05,
"loss": 4.232,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123580039610504e-05,
"loss": 4.2095,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115194092099984e-05,
"loss": 4.2242,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106808144589464e-05,
"loss": 4.2119,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098422197078944e-05,
"loss": 4.2308,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.4090036249568424e-05,
"loss": 4.2195,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081650302057904e-05,
"loss": 4.2251,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407326435454738e-05,
"loss": 4.2148,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406487840703686e-05,
"loss": 4.217,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405650883833007e-05,
"loss": 4.2206,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404812289081955e-05,
"loss": 4.2189,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.4039736943309026e-05,
"loss": 4.2324,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403135099579851e-05,
"loss": 4.2302,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402299780589546e-05,
"loss": 4.2253,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401462823718867e-05,
"loss": 4.2173,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.4006242289678147e-05,
"loss": 4.2178,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.3997856342167627e-05,
"loss": 4.2292,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.3989470394657106e-05,
"loss": 4.2101,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.3981084447146586e-05,
"loss": 4.2272,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.3972698499636066e-05,
"loss": 4.2108,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.3964312552125546e-05,
"loss": 4.2153,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3955926604615026e-05,
"loss": 4.2148,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.3947557035908235e-05,
"loss": 4.2129,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939171088397715e-05,
"loss": 4.2045,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3930785140887195e-05,
"loss": 4.2226,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.3922399193376675e-05,
"loss": 4.202,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3914013245866155e-05,
"loss": 4.2272,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905627298355635e-05,
"loss": 4.221,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897241350845115e-05,
"loss": 4.231,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.3888855403334595e-05,
"loss": 4.2009,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.3880485834627804e-05,
"loss": 4.2212,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872099887117284e-05,
"loss": 4.221,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3863713939606764e-05,
"loss": 4.2203,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855327992096244e-05,
"loss": 4.2153,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384695842338945e-05,
"loss": 4.2187,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383858885468267e-05,
"loss": 4.2133,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383020290717215e-05,
"loss": 4.2218,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382181695966163e-05,
"loss": 4.2038,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381343101215111e-05,
"loss": 4.2184,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380504506464059e-05,
"loss": 4.2118,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379665911713007e-05,
"loss": 4.2103,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378828954842328e-05,
"loss": 4.2155,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.377990360091276e-05,
"loss": 4.2187,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377151765340224e-05,
"loss": 4.2101,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376313170589172e-05,
"loss": 4.2012,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.37547457583812e-05,
"loss": 4.2064,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.199290752410889,
"eval_runtime": 296.6809,
"eval_samples_per_second": 1286.2,
"eval_steps_per_second": 40.195,
"step": 381600
},
{
"epoch": 0.0,
"learning_rate": 4.374635981087068e-05,
"loss": 4.2093,
"step": 381952
},
{
"epoch": 0.0,
"learning_rate": 4.373797386336016e-05,
"loss": 4.1969,
"step": 382464
},
{
"epoch": 0.0,
"learning_rate": 4.372958791584964e-05,
"loss": 4.2109,
"step": 382976
},
{
"epoch": 0.0,
"learning_rate": 4.372120196833912e-05,
"loss": 4.2111,
"step": 383488
},
{
"epoch": 0.0,
"learning_rate": 4.37128160208286e-05,
"loss": 4.2154,
"step": 384000
},
{
"epoch": 0.0,
"learning_rate": 4.3704430073318084e-05,
"loss": 4.2062,
"step": 384512
},
{
"epoch": 0.0,
"learning_rate": 4.3696044125807564e-05,
"loss": 4.2008,
"step": 385024
},
{
"epoch": 0.0,
"learning_rate": 4.368765817829704e-05,
"loss": 4.1914,
"step": 385536
},
{
"epoch": 0.0,
"learning_rate": 4.367927223078652e-05,
"loss": 4.2088,
"step": 386048
},
{
"epoch": 0.0,
"learning_rate": 4.3670886283276e-05,
"loss": 4.2148,
"step": 386560
},
{
"epoch": 0.0,
"learning_rate": 4.366250033576548e-05,
"loss": 4.2086,
"step": 387072
},
{
"epoch": 0.0,
"learning_rate": 4.365411438825496e-05,
"loss": 4.2079,
"step": 387584
},
{
"epoch": 0.0,
"learning_rate": 4.364572844074444e-05,
"loss": 4.1961,
"step": 388096
},
{
"epoch": 0.0,
"learning_rate": 4.363734249323392e-05,
"loss": 4.2075,
"step": 388608
},
{
"epoch": 0.0,
"learning_rate": 4.3628972924527126e-05,
"loss": 4.1978,
"step": 389120
},
{
"epoch": 0.0,
"learning_rate": 4.3620586977016606e-05,
"loss": 4.2012,
"step": 389632
},
{
"epoch": 0.0,
"learning_rate": 4.3612201029506086e-05,
"loss": 4.1965,
"step": 390144
},
{
"epoch": 0.0,
"learning_rate": 4.3603815081995566e-05,
"loss": 4.2011,
"step": 390656
},
{
"epoch": 0.0,
"learning_rate": 4.359542913448505e-05,
"loss": 4.1962,
"step": 391168
},
{
"epoch": 0.0,
"learning_rate": 4.358705956577826e-05,
"loss": 4.2146,
"step": 391680
},
{
"epoch": 0.0,
"learning_rate": 4.357867361826774e-05,
"loss": 4.2038,
"step": 392192
},
{
"epoch": 0.0,
"learning_rate": 4.357028767075722e-05,
"loss": 4.2114,
"step": 392704
},
{
"epoch": 0.0,
"learning_rate": 4.35619017232467e-05,
"loss": 4.1962,
"step": 393216
},
{
"epoch": 0.0,
"learning_rate": 4.355351577573618e-05,
"loss": 4.2101,
"step": 393728
},
{
"epoch": 0.0,
"learning_rate": 4.354512982822566e-05,
"loss": 4.1946,
"step": 394240
},
{
"epoch": 0.0,
"learning_rate": 4.353674388071514e-05,
"loss": 4.2044,
"step": 394752
},
{
"epoch": 0.0,
"learning_rate": 4.352835793320462e-05,
"loss": 4.1989,
"step": 395264
},
{
"epoch": 0.0,
"learning_rate": 4.35199719856941e-05,
"loss": 4.1881,
"step": 395776
},
{
"epoch": 0.0,
"learning_rate": 4.3511586038183575e-05,
"loss": 4.1857,
"step": 396288
},
{
"epoch": 0.0,
"learning_rate": 4.3503200090673055e-05,
"loss": 4.1945,
"step": 396800
},
{
"epoch": 0.01,
"learning_rate": 4.3494814143162535e-05,
"loss": 4.1994,
"step": 397312
},
{
"epoch": 0.01,
"learning_rate": 4.348644457445575e-05,
"loss": 4.2018,
"step": 397824
},
{
"epoch": 0.01,
"learning_rate": 4.347805862694523e-05,
"loss": 4.2012,
"step": 398336
},
{
"epoch": 0.01,
"learning_rate": 4.346967267943471e-05,
"loss": 4.2042,
"step": 398848
},
{
"epoch": 0.01,
"learning_rate": 4.346128673192419e-05,
"loss": 4.1983,
"step": 399360
},
{
"epoch": 0.01,
"learning_rate": 4.34529171632174e-05,
"loss": 4.2008,
"step": 399872
},
{
"epoch": 0.01,
"learning_rate": 4.3444547594510615e-05,
"loss": 4.1928,
"step": 400384
},
{
"epoch": 0.01,
"learning_rate": 4.3436161647000095e-05,
"loss": 4.1921,
"step": 400896
},
{
"epoch": 0.01,
"learning_rate": 4.3427775699489575e-05,
"loss": 4.1798,
"step": 401408
},
{
"epoch": 0.01,
"learning_rate": 4.341938975197905e-05,
"loss": 4.1959,
"step": 401920
},
{
"epoch": 0.01,
"learning_rate": 4.341100380446853e-05,
"loss": 4.189,
"step": 402432
},
{
"epoch": 0.01,
"learning_rate": 4.3402634235761744e-05,
"loss": 4.1975,
"step": 402944
},
{
"epoch": 0.01,
"learning_rate": 4.3394248288251224e-05,
"loss": 4.1921,
"step": 403456
},
{
"epoch": 0.01,
"learning_rate": 4.3385862340740704e-05,
"loss": 4.1872,
"step": 403968
},
{
"epoch": 0.01,
"learning_rate": 4.3377476393230184e-05,
"loss": 4.1999,
"step": 404480
},
{
"epoch": 0.01,
"learning_rate": 4.3369090445719664e-05,
"loss": 4.1874,
"step": 404992
},
{
"epoch": 0.01,
"learning_rate": 4.336072087701287e-05,
"loss": 4.1913,
"step": 405504
},
{
"epoch": 0.01,
"learning_rate": 4.335235130830609e-05,
"loss": 4.1802,
"step": 406016
},
{
"epoch": 0.01,
"learning_rate": 4.334396536079557e-05,
"loss": 4.1774,
"step": 406528
},
{
"epoch": 0.01,
"learning_rate": 4.333557941328505e-05,
"loss": 4.1905,
"step": 407040
},
{
"epoch": 0.01,
"learning_rate": 4.332719346577452e-05,
"loss": 4.19,
"step": 407552
},
{
"epoch": 0.01,
"learning_rate": 4.3318807518264e-05,
"loss": 4.1856,
"step": 408064
},
{
"epoch": 0.01,
"learning_rate": 4.331042157075348e-05,
"loss": 4.1814,
"step": 408576
},
{
"epoch": 0.01,
"learning_rate": 4.330203562324296e-05,
"loss": 4.1904,
"step": 409088
},
{
"epoch": 0.01,
"learning_rate": 4.329364967573244e-05,
"loss": 4.1704,
"step": 409600
},
{
"epoch": 0.01,
"learning_rate": 4.328526372822193e-05,
"loss": 4.1963,
"step": 410112
},
{
"epoch": 0.01,
"learning_rate": 4.327687778071141e-05,
"loss": 4.1744,
"step": 410624
},
{
"epoch": 0.01,
"learning_rate": 4.326849183320089e-05,
"loss": 4.1864,
"step": 411136
},
{
"epoch": 0.01,
"learning_rate": 4.326010588569037e-05,
"loss": 4.1836,
"step": 411648
},
{
"epoch": 0.01,
"learning_rate": 4.325173631698358e-05,
"loss": 4.1804,
"step": 412160
},
{
"epoch": 0.01,
"learning_rate": 4.324335036947306e-05,
"loss": 4.1762,
"step": 412672
},
{
"epoch": 0.01,
"learning_rate": 4.323496442196254e-05,
"loss": 4.1841,
"step": 413184
},
{
"epoch": 0.01,
"learning_rate": 4.322659485325575e-05,
"loss": 4.1757,
"step": 413696
},
{
"epoch": 0.01,
"learning_rate": 4.321820890574523e-05,
"loss": 4.181,
"step": 414208
},
{
"epoch": 0.01,
"learning_rate": 4.3209822958234707e-05,
"loss": 4.1839,
"step": 414720
},
{
"epoch": 0.01,
"learning_rate": 4.3201437010724187e-05,
"loss": 4.1853,
"step": 415232
},
{
"epoch": 0.01,
"learning_rate": 4.3193051063213666e-05,
"loss": 4.1737,
"step": 415744
},
{
"epoch": 0.01,
"learning_rate": 4.3184665115703146e-05,
"loss": 4.1845,
"step": 416256
},
{
"epoch": 0.01,
"learning_rate": 4.3176279168192626e-05,
"loss": 4.1692,
"step": 416768
},
{
"epoch": 0.01,
"learning_rate": 4.3167893220682106e-05,
"loss": 4.1781,
"step": 417280
},
{
"epoch": 0.01,
"learning_rate": 4.315952365197532e-05,
"loss": 4.1915,
"step": 417792
},
{
"epoch": 0.01,
"learning_rate": 4.315115408326853e-05,
"loss": 4.1856,
"step": 418304
},
{
"epoch": 0.01,
"learning_rate": 4.314276813575801e-05,
"loss": 4.188,
"step": 418816
},
{
"epoch": 0.01,
"learning_rate": 4.313438218824749e-05,
"loss": 4.188,
"step": 419328
},
{
"epoch": 0.01,
"learning_rate": 4.312599624073697e-05,
"loss": 4.197,
"step": 419840
},
{
"epoch": 0.01,
"learning_rate": 4.311762667203018e-05,
"loss": 4.1751,
"step": 420352
},
{
"epoch": 0.01,
"learning_rate": 4.310924072451966e-05,
"loss": 4.1788,
"step": 420864
},
{
"epoch": 0.01,
"learning_rate": 4.310085477700914e-05,
"loss": 4.1902,
"step": 421376
},
{
"epoch": 0.01,
"learning_rate": 4.309246882949862e-05,
"loss": 4.171,
"step": 421888
},
{
"epoch": 0.01,
"learning_rate": 4.30840828819881e-05,
"loss": 4.1835,
"step": 422400
},
{
"epoch": 0.01,
"learning_rate": 4.3075713313281316e-05,
"loss": 4.1826,
"step": 422912
},
{
"epoch": 0.01,
"learning_rate": 4.3067327365770796e-05,
"loss": 4.191,
"step": 423424
},
{
"epoch": 0.01,
"learning_rate": 4.3058941418260276e-05,
"loss": 4.1837,
"step": 423936
},
{
"epoch": 0.01,
"learning_rate": 4.3050555470749756e-05,
"loss": 4.1676,
"step": 424448
},
{
"epoch": 0.01,
"learning_rate": 4.3042169523239236e-05,
"loss": 4.1764,
"step": 424960
},
{
"epoch": 0.01,
"learning_rate": 4.303378357572871e-05,
"loss": 4.177,
"step": 425472
},
{
"epoch": 0.01,
"learning_rate": 4.302539762821819e-05,
"loss": 4.1827,
"step": 425984
},
{
"epoch": 0.01,
"learning_rate": 4.301701168070767e-05,
"loss": 4.1817,
"step": 426496
},
{
"epoch": 0.01,
"learning_rate": 4.300862573319715e-05,
"loss": 4.1777,
"step": 427008
},
{
"epoch": 0.02,
"learning_rate": 4.300023978568663e-05,
"loss": 4.1748,
"step": 427520
},
{
"epoch": 0.02,
"learning_rate": 4.299185383817611e-05,
"loss": 4.1712,
"step": 428032
},
{
"epoch": 0.02,
"learning_rate": 4.298348426946932e-05,
"loss": 4.1657,
"step": 428544
},
{
"epoch": 0.02,
"learning_rate": 4.29750983219588e-05,
"loss": 4.1741,
"step": 429056
},
{
"epoch": 0.02,
"learning_rate": 4.2966712374448285e-05,
"loss": 4.1839,
"step": 429568
},
{
"epoch": 0.02,
"learning_rate": 4.2958326426937765e-05,
"loss": 4.1948,
"step": 430080
},
{
"epoch": 0.02,
"learning_rate": 4.2949940479427244e-05,
"loss": 4.1823,
"step": 430592
},
{
"epoch": 0.02,
"learning_rate": 4.2941554531916724e-05,
"loss": 4.1619,
"step": 431104
},
{
"epoch": 0.02,
"learning_rate": 4.2933168584406204e-05,
"loss": 4.1738,
"step": 431616
},
{
"epoch": 0.02,
"learning_rate": 4.2924782636895684e-05,
"loss": 4.1722,
"step": 432128
},
{
"epoch": 0.02,
"learning_rate": 4.2916413068188893e-05,
"loss": 4.1811,
"step": 432640
},
{
"epoch": 0.02,
"learning_rate": 4.29080434994821e-05,
"loss": 4.1741,
"step": 433152
},
{
"epoch": 0.02,
"learning_rate": 4.289965755197158e-05,
"loss": 4.1766,
"step": 433664
},
{
"epoch": 0.02,
"learning_rate": 4.289127160446106e-05,
"loss": 4.1722,
"step": 434176
},
{
"epoch": 0.02,
"learning_rate": 4.288288565695054e-05,
"loss": 4.1733,
"step": 434688
},
{
"epoch": 0.02,
"learning_rate": 4.287449970944002e-05,
"loss": 4.1628,
"step": 435200
},
{
"epoch": 0.02,
"learning_rate": 4.286613014073324e-05,
"loss": 4.1703,
"step": 435712
},
{
"epoch": 0.02,
"learning_rate": 4.285774419322272e-05,
"loss": 4.1592,
"step": 436224
},
{
"epoch": 0.02,
"learning_rate": 4.28493582457122e-05,
"loss": 4.1803,
"step": 436736
},
{
"epoch": 0.02,
"learning_rate": 4.284097229820168e-05,
"loss": 4.1668,
"step": 437248
},
{
"epoch": 0.02,
"learning_rate": 4.283258635069116e-05,
"loss": 4.1686,
"step": 437760
},
{
"epoch": 0.02,
"learning_rate": 4.282420040318064e-05,
"loss": 4.1587,
"step": 438272
},
{
"epoch": 0.02,
"learning_rate": 4.281581445567012e-05,
"loss": 4.1703,
"step": 438784
},
{
"epoch": 0.02,
"learning_rate": 4.28074285081596e-05,
"loss": 4.1667,
"step": 439296
},
{
"epoch": 0.02,
"learning_rate": 4.279905893945281e-05,
"loss": 4.1674,
"step": 439808
},
{
"epoch": 0.02,
"learning_rate": 4.279067299194229e-05,
"loss": 4.1819,
"step": 440320
},
{
"epoch": 0.02,
"learning_rate": 4.278228704443177e-05,
"loss": 4.1793,
"step": 440832
},
{
"epoch": 0.02,
"learning_rate": 4.2773917475724976e-05,
"loss": 4.174,
"step": 441344
},
{
"epoch": 0.02,
"learning_rate": 4.2765531528214456e-05,
"loss": 4.1691,
"step": 441856
},
{
"epoch": 0.02,
"learning_rate": 4.2757145580703936e-05,
"loss": 4.161,
"step": 442368
},
{
"epoch": 0.02,
"learning_rate": 4.2748759633193416e-05,
"loss": 4.1782,
"step": 442880
},
{
"epoch": 0.02,
"learning_rate": 4.2740373685682896e-05,
"loss": 4.1608,
"step": 443392
},
{
"epoch": 0.02,
"learning_rate": 4.2731987738172376e-05,
"loss": 4.1759,
"step": 443904
},
{
"epoch": 0.02,
"learning_rate": 4.2723601790661856e-05,
"loss": 4.1578,
"step": 444416
},
{
"epoch": 0.02,
"learning_rate": 4.271523222195507e-05,
"loss": 4.1685,
"step": 444928
},
{
"epoch": 0.02,
"learning_rate": 4.2706846274444545e-05,
"loss": 4.1573,
"step": 445440
},
{
"epoch": 0.02,
"learning_rate": 4.2698460326934025e-05,
"loss": 4.165,
"step": 445952
},
{
"epoch": 0.02,
"learning_rate": 4.2690074379423505e-05,
"loss": 4.1585,
"step": 446464
},
{
"epoch": 0.02,
"learning_rate": 4.2681688431912985e-05,
"loss": 4.1648,
"step": 446976
},
{
"epoch": 0.02,
"learning_rate": 4.2673318863206194e-05,
"loss": 4.1566,
"step": 447488
},
{
"epoch": 0.02,
"learning_rate": 4.2664932915695674e-05,
"loss": 4.1758,
"step": 448000
},
{
"epoch": 0.02,
"learning_rate": 4.2656546968185154e-05,
"loss": 4.1747,
"step": 448512
},
{
"epoch": 0.02,
"learning_rate": 4.264816102067464e-05,
"loss": 4.1762,
"step": 449024
},
{
"epoch": 0.02,
"learning_rate": 4.263977507316412e-05,
"loss": 4.1513,
"step": 449536
},
{
"epoch": 0.02,
"learning_rate": 4.26313891256536e-05,
"loss": 4.1727,
"step": 450048
},
{
"epoch": 0.02,
"learning_rate": 4.262300317814308e-05,
"loss": 4.1697,
"step": 450560
},
{
"epoch": 0.02,
"learning_rate": 4.261461723063256e-05,
"loss": 4.1709,
"step": 451072
},
{
"epoch": 0.02,
"learning_rate": 4.260624766192577e-05,
"loss": 4.1658,
"step": 451584
},
{
"epoch": 0.02,
"learning_rate": 4.259786171441525e-05,
"loss": 4.1706,
"step": 452096
},
{
"epoch": 0.02,
"learning_rate": 4.258947576690473e-05,
"loss": 4.1653,
"step": 452608
},
{
"epoch": 0.02,
"learning_rate": 4.258108981939421e-05,
"loss": 4.1736,
"step": 453120
},
{
"epoch": 0.02,
"learning_rate": 4.257272025068742e-05,
"loss": 4.1544,
"step": 453632
},
{
"epoch": 0.02,
"learning_rate": 4.25643343031769e-05,
"loss": 4.1708,
"step": 454144
},
{
"epoch": 0.02,
"learning_rate": 4.255594835566638e-05,
"loss": 4.1598,
"step": 454656
},
{
"epoch": 0.02,
"learning_rate": 4.254756240815586e-05,
"loss": 4.162,
"step": 455168
},
{
"epoch": 0.02,
"learning_rate": 4.2539192839449074e-05,
"loss": 4.1651,
"step": 455680
},
{
"epoch": 0.02,
"learning_rate": 4.2530806891938554e-05,
"loss": 4.1633,
"step": 456192
},
{
"epoch": 0.02,
"learning_rate": 4.2522420944428034e-05,
"loss": 4.1664,
"step": 456704
},
{
"epoch": 0.02,
"learning_rate": 4.251406775452497e-05,
"loss": 4.1503,
"step": 457216
},
{
"epoch": 0.02,
"learning_rate": 4.250568180701445e-05,
"loss": 4.1595,
"step": 457728
},
{
"epoch": 0.03,
"eval_loss": 4.158834457397461,
"eval_runtime": 291.4896,
"eval_samples_per_second": 1309.107,
"eval_steps_per_second": 40.911,
"step": 457920
},
{
"epoch": 1.0,
"learning_rate": 4.249729585950393e-05,
"loss": 4.1626,
"step": 458240
},
{
"epoch": 1.0,
"learning_rate": 4.248890991199341e-05,
"loss": 4.148,
"step": 458752
},
{
"epoch": 1.0,
"learning_rate": 4.248052396448289e-05,
"loss": 4.1624,
"step": 459264
},
{
"epoch": 1.0,
"learning_rate": 4.247213801697237e-05,
"loss": 4.1626,
"step": 459776
},
{
"epoch": 1.0,
"learning_rate": 4.246375206946185e-05,
"loss": 4.1673,
"step": 460288
},
{
"epoch": 1.0,
"learning_rate": 4.245536612195133e-05,
"loss": 4.1567,
"step": 460800
},
{
"epoch": 1.0,
"learning_rate": 4.244698017444081e-05,
"loss": 4.1491,
"step": 461312
},
{
"epoch": 1.0,
"learning_rate": 4.243859422693029e-05,
"loss": 4.1503,
"step": 461824
},
{
"epoch": 1.0,
"learning_rate": 4.243022465822351e-05,
"loss": 4.1561,
"step": 462336
},
{
"epoch": 1.0,
"learning_rate": 4.242183871071299e-05,
"loss": 4.1668,
"step": 462848
},
{
"epoch": 1.0,
"learning_rate": 4.241345276320247e-05,
"loss": 4.1594,
"step": 463360
},
{
"epoch": 1.0,
"learning_rate": 4.240506681569195e-05,
"loss": 4.1588,
"step": 463872
},
{
"epoch": 1.0,
"learning_rate": 4.239668086818143e-05,
"loss": 4.1523,
"step": 464384
},
{
"epoch": 1.0,
"learning_rate": 4.238829492067091e-05,
"loss": 4.1555,
"step": 464896
},
{
"epoch": 1.0,
"learning_rate": 4.237990897316038e-05,
"loss": 4.1521,
"step": 465408
},
{
"epoch": 1.0,
"learning_rate": 4.2371539404453596e-05,
"loss": 4.1531,
"step": 465920
},
{
"epoch": 1.0,
"learning_rate": 4.2363153456943076e-05,
"loss": 4.1497,
"step": 466432
},
{
"epoch": 1.0,
"learning_rate": 4.2354783888236286e-05,
"loss": 4.1496,
"step": 466944
},
{
"epoch": 1.0,
"learning_rate": 4.2346397940725765e-05,
"loss": 4.1526,
"step": 467456
},
{
"epoch": 1.0,
"learning_rate": 4.2338011993215245e-05,
"loss": 4.1661,
"step": 467968
},
{
"epoch": 1.0,
"learning_rate": 4.232962604570473e-05,
"loss": 4.1577,
"step": 468480
},
{
"epoch": 1.0,
"learning_rate": 4.2321240098194205e-05,
"loss": 4.1643,
"step": 468992
},
{
"epoch": 1.0,
"learning_rate": 4.2312854150683685e-05,
"loss": 4.146,
"step": 469504
},
{
"epoch": 1.0,
"learning_rate": 4.2304468203173165e-05,
"loss": 4.1645,
"step": 470016
},
{
"epoch": 1.0,
"learning_rate": 4.2296082255662645e-05,
"loss": 4.1466,
"step": 470528
},
{
"epoch": 1.0,
"learning_rate": 4.2287696308152125e-05,
"loss": 4.1589,
"step": 471040
},
{
"epoch": 1.0,
"learning_rate": 4.2279310360641605e-05,
"loss": 4.1489,
"step": 471552
},
{
"epoch": 1.0,
"learning_rate": 4.2270924413131085e-05,
"loss": 4.1405,
"step": 472064
},
{
"epoch": 1.0,
"learning_rate": 4.2262538465620565e-05,
"loss": 4.1458,
"step": 472576
},
{
"epoch": 1.0,
"learning_rate": 4.2254168896913774e-05,
"loss": 4.1477,
"step": 473088
},
{
"epoch": 1.01,
"learning_rate": 4.2245782949403254e-05,
"loss": 4.1507,
"step": 473600
},
{
"epoch": 1.01,
"learning_rate": 4.223741338069647e-05,
"loss": 4.1538,
"step": 474112
},
{
"epoch": 1.01,
"learning_rate": 4.222904381198968e-05,
"loss": 4.1538,
"step": 474624
},
{
"epoch": 1.01,
"learning_rate": 4.222065786447916e-05,
"loss": 4.1614,
"step": 475136
},
{
"epoch": 1.01,
"learning_rate": 4.221227191696864e-05,
"loss": 4.145,
"step": 475648
},
{
"epoch": 1.01,
"learning_rate": 4.220388596945812e-05,
"loss": 4.1575,
"step": 476160
},
{
"epoch": 1.01,
"learning_rate": 4.21955000219476e-05,
"loss": 4.1521,
"step": 476672
},
{
"epoch": 1.01,
"learning_rate": 4.218711407443708e-05,
"loss": 4.1402,
"step": 477184
},
{
"epoch": 1.01,
"learning_rate": 4.217872812692656e-05,
"loss": 4.1369,
"step": 477696
},
{
"epoch": 1.01,
"learning_rate": 4.217034217941604e-05,
"loss": 4.1433,
"step": 478208
},
{
"epoch": 1.01,
"learning_rate": 4.216195623190552e-05,
"loss": 4.147,
"step": 478720
},
{
"epoch": 1.01,
"learning_rate": 4.215358666319873e-05,
"loss": 4.15,
"step": 479232
},
{
"epoch": 1.01,
"learning_rate": 4.214520071568821e-05,
"loss": 4.1432,
"step": 479744
},
{
"epoch": 1.01,
"learning_rate": 4.213681476817769e-05,
"loss": 4.142,
"step": 480256
},
{
"epoch": 1.01,
"learning_rate": 4.212842882066717e-05,
"loss": 4.1587,
"step": 480768
},
{
"epoch": 1.01,
"learning_rate": 4.2120059251960384e-05,
"loss": 4.1439,
"step": 481280
},
{
"epoch": 1.01,
"learning_rate": 4.2111673304449864e-05,
"loss": 4.1445,
"step": 481792
},
{
"epoch": 1.01,
"learning_rate": 4.2103287356939343e-05,
"loss": 4.1352,
"step": 482304
},
{
"epoch": 1.01,
"learning_rate": 4.2094901409428823e-05,
"loss": 4.1302,
"step": 482816
},
{
"epoch": 1.01,
"learning_rate": 4.20865154619183e-05,
"loss": 4.1481,
"step": 483328
},
{
"epoch": 1.01,
"learning_rate": 4.207812951440778e-05,
"loss": 4.1442,
"step": 483840
},
{
"epoch": 1.01,
"learning_rate": 4.206974356689726e-05,
"loss": 4.1397,
"step": 484352
},
{
"epoch": 1.01,
"learning_rate": 4.2061357619386736e-05,
"loss": 4.1343,
"step": 484864
},
{
"epoch": 1.01,
"learning_rate": 4.205298805067995e-05,
"loss": 4.1471,
"step": 485376
},
{
"epoch": 1.01,
"learning_rate": 4.204460210316943e-05,
"loss": 4.1239,
"step": 485888
},
{
"epoch": 1.01,
"learning_rate": 4.203623253446264e-05,
"loss": 4.1507,
"step": 486400
},
{
"epoch": 1.01,
"learning_rate": 4.202784658695212e-05,
"loss": 4.1302,
"step": 486912
},
{
"epoch": 1.01,
"learning_rate": 4.20194606394416e-05,
"loss": 4.1385,
"step": 487424
},
{
"epoch": 1.01,
"learning_rate": 4.201107469193109e-05,
"loss": 4.1409,
"step": 487936
},
{
"epoch": 1.01,
"learning_rate": 4.200268874442057e-05,
"loss": 4.1337,
"step": 488448
},
{
"epoch": 1.01,
"learning_rate": 4.199430279691004e-05,
"loss": 4.1343,
"step": 488960
},
{
"epoch": 1.01,
"learning_rate": 4.198593322820326e-05,
"loss": 4.1458,
"step": 489472
},
{
"epoch": 1.01,
"learning_rate": 4.197754728069274e-05,
"loss": 4.129,
"step": 489984
},
{
"epoch": 1.01,
"learning_rate": 4.196916133318221e-05,
"loss": 4.136,
"step": 490496
},
{
"epoch": 1.01,
"learning_rate": 4.196077538567169e-05,
"loss": 4.1416,
"step": 491008
},
{
"epoch": 1.01,
"learning_rate": 4.1952405816964906e-05,
"loss": 4.1418,
"step": 491520
},
{
"epoch": 1.01,
"learning_rate": 4.1944019869454386e-05,
"loss": 4.1303,
"step": 492032
},
{
"epoch": 1.01,
"learning_rate": 4.193563392194386e-05,
"loss": 4.1393,
"step": 492544
},
{
"epoch": 1.01,
"learning_rate": 4.192724797443334e-05,
"loss": 4.1245,
"step": 493056
},
{
"epoch": 1.01,
"learning_rate": 4.1918862026922826e-05,
"loss": 4.1357,
"step": 493568
},
{
"epoch": 1.01,
"learning_rate": 4.191049245821604e-05,
"loss": 4.1454,
"step": 494080
},
{
"epoch": 1.01,
"learning_rate": 4.1902106510705515e-05,
"loss": 4.1404,
"step": 494592
},
{
"epoch": 1.01,
"learning_rate": 4.1893720563194995e-05,
"loss": 4.1468,
"step": 495104
},
{
"epoch": 1.01,
"learning_rate": 4.1885334615684475e-05,
"loss": 4.1405,
"step": 495616
},
{
"epoch": 1.01,
"learning_rate": 4.1876965046977684e-05,
"loss": 4.1578,
"step": 496128
},
{
"epoch": 1.01,
"learning_rate": 4.1868579099467164e-05,
"loss": 4.1294,
"step": 496640
},
{
"epoch": 1.01,
"learning_rate": 4.1860193151956644e-05,
"loss": 4.1423,
"step": 497152
},
{
"epoch": 1.01,
"learning_rate": 4.1851807204446124e-05,
"loss": 4.1487,
"step": 497664
},
{
"epoch": 1.01,
"learning_rate": 4.1843421256935604e-05,
"loss": 4.125,
"step": 498176
},
{
"epoch": 1.01,
"learning_rate": 4.1835035309425084e-05,
"loss": 4.1398,
"step": 498688
},
{
"epoch": 1.01,
"learning_rate": 4.182666574071829e-05,
"loss": 4.1396,
"step": 499200
},
{
"epoch": 1.01,
"learning_rate": 4.181827979320778e-05,
"loss": 4.1506,
"step": 499712
},
{
"epoch": 1.01,
"learning_rate": 4.180989384569726e-05,
"loss": 4.1388,
"step": 500224
},
{
"epoch": 1.01,
"learning_rate": 4.180150789818674e-05,
"loss": 4.1259,
"step": 500736
},
{
"epoch": 1.01,
"learning_rate": 4.179312195067622e-05,
"loss": 4.1315,
"step": 501248
},
{
"epoch": 1.01,
"learning_rate": 4.17847360031657e-05,
"loss": 4.1335,
"step": 501760
},
{
"epoch": 1.01,
"learning_rate": 4.177635005565518e-05,
"loss": 4.1411,
"step": 502272
},
{
"epoch": 1.01,
"learning_rate": 4.176796410814466e-05,
"loss": 4.1407,
"step": 502784
},
{
"epoch": 1.01,
"learning_rate": 4.175959453943787e-05,
"loss": 4.1397,
"step": 503296
},
{
"epoch": 1.02,
"learning_rate": 4.175122497073108e-05,
"loss": 4.1233,
"step": 503808
},
{
"epoch": 1.02,
"learning_rate": 4.174283902322056e-05,
"loss": 4.1298,
"step": 504320
},
{
"epoch": 1.02,
"learning_rate": 4.173445307571004e-05,
"loss": 4.1265,
"step": 504832
},
{
"epoch": 1.02,
"learning_rate": 4.172606712819952e-05,
"loss": 4.1332,
"step": 505344
},
{
"epoch": 1.02,
"learning_rate": 4.1717681180689e-05,
"loss": 4.1438,
"step": 505856
},
{
"epoch": 1.02,
"learning_rate": 4.170929523317848e-05,
"loss": 4.149,
"step": 506368
},
{
"epoch": 1.02,
"learning_rate": 4.170092566447169e-05,
"loss": 4.1415,
"step": 506880
},
{
"epoch": 1.02,
"learning_rate": 4.169253971696117e-05,
"loss": 4.1243,
"step": 507392
},
{
"epoch": 1.02,
"learning_rate": 4.168415376945065e-05,
"loss": 4.1293,
"step": 507904
},
{
"epoch": 1.02,
"learning_rate": 4.167576782194013e-05,
"loss": 4.1297,
"step": 508416
},
{
"epoch": 1.02,
"learning_rate": 4.166738187442961e-05,
"loss": 4.1394,
"step": 508928
},
{
"epoch": 1.02,
"learning_rate": 4.165899592691909e-05,
"loss": 4.1334,
"step": 509440
},
{
"epoch": 1.02,
"learning_rate": 4.165060997940857e-05,
"loss": 4.1372,
"step": 509952
},
{
"epoch": 1.02,
"learning_rate": 4.1642224031898046e-05,
"loss": 4.131,
"step": 510464
},
{
"epoch": 1.02,
"learning_rate": 4.163387084199499e-05,
"loss": 4.126,
"step": 510976
},
{
"epoch": 1.02,
"learning_rate": 4.162548489448447e-05,
"loss": 4.1255,
"step": 511488
},
{
"epoch": 1.02,
"learning_rate": 4.161709894697395e-05,
"loss": 4.1262,
"step": 512000
},
{
"epoch": 1.02,
"learning_rate": 4.160871299946343e-05,
"loss": 4.1177,
"step": 512512
},
{
"epoch": 1.02,
"learning_rate": 4.160032705195292e-05,
"loss": 4.1366,
"step": 513024
},
{
"epoch": 1.02,
"learning_rate": 4.15919411044424e-05,
"loss": 4.1271,
"step": 513536
},
{
"epoch": 1.02,
"learning_rate": 4.158357153573561e-05,
"loss": 4.1274,
"step": 514048
},
{
"epoch": 1.02,
"learning_rate": 4.1575185588225087e-05,
"loss": 4.1208,
"step": 514560
},
{
"epoch": 1.02,
"learning_rate": 4.1566799640714567e-05,
"loss": 4.1251,
"step": 515072
},
{
"epoch": 1.02,
"learning_rate": 4.1558413693204047e-05,
"loss": 4.1297,
"step": 515584
},
{
"epoch": 1.02,
"learning_rate": 4.155002774569352e-05,
"loss": 4.124,
"step": 516096
},
{
"epoch": 1.02,
"learning_rate": 4.1541641798183e-05,
"loss": 4.1434,
"step": 516608
},
{
"epoch": 1.02,
"learning_rate": 4.1533272229476216e-05,
"loss": 4.1342,
"step": 517120
},
{
"epoch": 1.02,
"learning_rate": 4.1524902660769425e-05,
"loss": 4.1339,
"step": 517632
},
{
"epoch": 1.02,
"learning_rate": 4.1516516713258905e-05,
"loss": 4.1323,
"step": 518144
},
{
"epoch": 1.02,
"learning_rate": 4.1508130765748385e-05,
"loss": 4.1156,
"step": 518656
},
{
"epoch": 1.02,
"learning_rate": 4.1499744818237864e-05,
"loss": 4.1404,
"step": 519168
},
{
"epoch": 1.02,
"learning_rate": 4.1491358870727344e-05,
"loss": 4.1263,
"step": 519680
},
{
"epoch": 1.02,
"learning_rate": 4.1482972923216824e-05,
"loss": 4.1304,
"step": 520192
},
{
"epoch": 1.02,
"learning_rate": 4.1474586975706304e-05,
"loss": 4.1183,
"step": 520704
},
{
"epoch": 1.02,
"learning_rate": 4.1466201028195784e-05,
"loss": 4.1267,
"step": 521216
},
{
"epoch": 1.02,
"learning_rate": 4.1457831459488993e-05,
"loss": 4.1181,
"step": 521728
},
{
"epoch": 1.02,
"learning_rate": 4.144946189078221e-05,
"loss": 4.1242,
"step": 522240
},
{
"epoch": 1.02,
"learning_rate": 4.144107594327169e-05,
"loss": 4.1167,
"step": 522752
},
{
"epoch": 1.02,
"learning_rate": 4.143268999576117e-05,
"loss": 4.1292,
"step": 523264
},
{
"epoch": 1.02,
"learning_rate": 4.142430404825064e-05,
"loss": 4.1146,
"step": 523776
},
{
"epoch": 1.02,
"learning_rate": 4.141591810074012e-05,
"loss": 4.1361,
"step": 524288
},
{
"epoch": 1.02,
"learning_rate": 4.14075321532296e-05,
"loss": 4.1296,
"step": 524800
},
{
"epoch": 1.02,
"learning_rate": 4.139914620571909e-05,
"loss": 4.1356,
"step": 525312
},
{
"epoch": 1.02,
"learning_rate": 4.139076025820857e-05,
"loss": 4.1145,
"step": 525824
},
{
"epoch": 1.02,
"learning_rate": 4.138237431069805e-05,
"loss": 4.1337,
"step": 526336
},
{
"epoch": 1.02,
"learning_rate": 4.137398836318753e-05,
"loss": 4.13,
"step": 526848
},
{
"epoch": 1.02,
"learning_rate": 4.136560241567701e-05,
"loss": 4.1284,
"step": 527360
},
{
"epoch": 1.02,
"learning_rate": 4.135723284697022e-05,
"loss": 4.1276,
"step": 527872
},
{
"epoch": 1.02,
"learning_rate": 4.13488468994597e-05,
"loss": 4.1295,
"step": 528384
},
{
"epoch": 1.02,
"learning_rate": 4.134046095194918e-05,
"loss": 4.1232,
"step": 528896
},
{
"epoch": 1.02,
"learning_rate": 4.133207500443866e-05,
"loss": 4.1406,
"step": 529408
},
{
"epoch": 1.02,
"learning_rate": 4.132368905692814e-05,
"loss": 4.1108,
"step": 529920
},
{
"epoch": 1.02,
"learning_rate": 4.131530310941762e-05,
"loss": 4.13,
"step": 530432
},
{
"epoch": 1.02,
"learning_rate": 4.13069171619071e-05,
"loss": 4.1216,
"step": 530944
},
{
"epoch": 1.02,
"learning_rate": 4.129854759320031e-05,
"loss": 4.1226,
"step": 531456
},
{
"epoch": 1.02,
"learning_rate": 4.129016164568979e-05,
"loss": 4.1259,
"step": 531968
},
{
"epoch": 1.02,
"learning_rate": 4.1281775698179273e-05,
"loss": 4.1212,
"step": 532480
},
{
"epoch": 1.02,
"learning_rate": 4.1273389750668753e-05,
"loss": 4.1293,
"step": 532992
},
{
"epoch": 1.02,
"learning_rate": 4.126502018196196e-05,
"loss": 4.1086,
"step": 533504
},
{
"epoch": 1.02,
"learning_rate": 4.125663423445144e-05,
"loss": 4.1245,
"step": 534016
},
{
"epoch": 1.03,
"eval_loss": 4.127786159515381,
"eval_runtime": 291.4561,
"eval_samples_per_second": 1309.257,
"eval_steps_per_second": 40.915,
"step": 534240
},
{
"epoch": 0.0,
"learning_rate": 4.124824828694092e-05,
"loss": 4.1226,
"step": 534528
},
{
"epoch": 0.0,
"learning_rate": 4.12398623394304e-05,
"loss": 4.1077,
"step": 535040
},
{
"epoch": 0.0,
"learning_rate": 4.123147639191988e-05,
"loss": 4.124,
"step": 535552
},
{
"epoch": 0.0,
"learning_rate": 4.1223090444409356e-05,
"loss": 4.1188,
"step": 536064
},
{
"epoch": 0.0,
"learning_rate": 4.1214704496898835e-05,
"loss": 4.1264,
"step": 536576
},
{
"epoch": 0.0,
"learning_rate": 4.1206318549388315e-05,
"loss": 4.1213,
"step": 537088
},
{
"epoch": 0.0,
"learning_rate": 4.1197932601877795e-05,
"loss": 4.1119,
"step": 537600
},
{
"epoch": 0.0,
"learning_rate": 4.1189546654367275e-05,
"loss": 4.111,
"step": 538112
},
{
"epoch": 0.0,
"learning_rate": 4.1181160706856755e-05,
"loss": 4.1208,
"step": 538624
},
{
"epoch": 0.0,
"learning_rate": 4.117277475934624e-05,
"loss": 4.1271,
"step": 539136
},
{
"epoch": 0.0,
"learning_rate": 4.116438881183572e-05,
"loss": 4.1216,
"step": 539648
},
{
"epoch": 0.0,
"learning_rate": 4.11560028643252e-05,
"loss": 4.1199,
"step": 540160
},
{
"epoch": 0.0,
"learning_rate": 4.114761691681468e-05,
"loss": 4.1171,
"step": 540672
},
{
"epoch": 0.0,
"learning_rate": 4.113923096930416e-05,
"loss": 4.1189,
"step": 541184
},
{
"epoch": 0.0,
"learning_rate": 4.113084502179364e-05,
"loss": 4.1117,
"step": 541696
},
{
"epoch": 0.0,
"learning_rate": 4.112245907428312e-05,
"loss": 4.1112,
"step": 542208
},
{
"epoch": 0.0,
"learning_rate": 4.111408950557633e-05,
"loss": 4.1151,
"step": 542720
},
{
"epoch": 0.0,
"learning_rate": 4.110570355806581e-05,
"loss": 4.1105,
"step": 543232
},
{
"epoch": 0.0,
"learning_rate": 4.109731761055529e-05,
"loss": 4.1157,
"step": 543744
},
{
"epoch": 0.0,
"learning_rate": 4.108893166304477e-05,
"loss": 4.123,
"step": 544256
},
{
"epoch": 0.0,
"learning_rate": 4.1080545715534244e-05,
"loss": 4.1249,
"step": 544768
},
{
"epoch": 0.0,
"learning_rate": 4.1072159768023724e-05,
"loss": 4.1253,
"step": 545280
},
{
"epoch": 0.0,
"learning_rate": 4.106377382051321e-05,
"loss": 4.1104,
"step": 545792
},
{
"epoch": 0.0,
"learning_rate": 4.105540425180642e-05,
"loss": 4.1231,
"step": 546304
},
{
"epoch": 0.0,
"learning_rate": 4.10470183042959e-05,
"loss": 4.1084,
"step": 546816
},
{
"epoch": 0.0,
"learning_rate": 4.103863235678538e-05,
"loss": 4.1259,
"step": 547328
},
{
"epoch": 0.0,
"learning_rate": 4.103024640927486e-05,
"loss": 4.1067,
"step": 547840
},
{
"epoch": 0.0,
"learning_rate": 4.102186046176434e-05,
"loss": 4.1065,
"step": 548352
},
{
"epoch": 0.0,
"learning_rate": 4.101349089305755e-05,
"loss": 4.1096,
"step": 548864
},
{
"epoch": 0.0,
"learning_rate": 4.100510494554703e-05,
"loss": 4.1134,
"step": 549376
},
{
"epoch": 0.01,
"learning_rate": 4.099671899803651e-05,
"loss": 4.1096,
"step": 549888
},
{
"epoch": 0.01,
"learning_rate": 4.098833305052599e-05,
"loss": 4.1194,
"step": 550400
},
{
"epoch": 0.01,
"learning_rate": 4.097994710301547e-05,
"loss": 4.1183,
"step": 550912
},
{
"epoch": 0.01,
"learning_rate": 4.097156115550495e-05,
"loss": 4.1182,
"step": 551424
},
{
"epoch": 0.01,
"learning_rate": 4.096317520799443e-05,
"loss": 4.1124,
"step": 551936
},
{
"epoch": 0.01,
"learning_rate": 4.0954805639287644e-05,
"loss": 4.1203,
"step": 552448
},
{
"epoch": 0.01,
"learning_rate": 4.0946419691777124e-05,
"loss": 4.1173,
"step": 552960
},
{
"epoch": 0.01,
"learning_rate": 4.0938033744266604e-05,
"loss": 4.1003,
"step": 553472
},
{
"epoch": 0.01,
"learning_rate": 4.0929647796756084e-05,
"loss": 4.1038,
"step": 553984
},
{
"epoch": 0.01,
"learning_rate": 4.0921261849245564e-05,
"loss": 4.105,
"step": 554496
},
{
"epoch": 0.01,
"learning_rate": 4.0912875901735044e-05,
"loss": 4.1099,
"step": 555008
},
{
"epoch": 0.01,
"learning_rate": 4.090450633302825e-05,
"loss": 4.1132,
"step": 555520
},
{
"epoch": 0.01,
"learning_rate": 4.089612038551773e-05,
"loss": 4.1073,
"step": 556032
},
{
"epoch": 0.01,
"learning_rate": 4.088773443800721e-05,
"loss": 4.1042,
"step": 556544
},
{
"epoch": 0.01,
"learning_rate": 4.087934849049669e-05,
"loss": 4.1198,
"step": 557056
},
{
"epoch": 0.01,
"learning_rate": 4.087096254298617e-05,
"loss": 4.1079,
"step": 557568
},
{
"epoch": 0.01,
"learning_rate": 4.086257659547565e-05,
"loss": 4.1122,
"step": 558080
},
{
"epoch": 0.01,
"learning_rate": 4.085419064796513e-05,
"loss": 4.0962,
"step": 558592
},
{
"epoch": 0.01,
"learning_rate": 4.084580470045461e-05,
"loss": 4.0909,
"step": 559104
},
{
"epoch": 0.01,
"learning_rate": 4.083743513174783e-05,
"loss": 4.1179,
"step": 559616
},
{
"epoch": 0.01,
"learning_rate": 4.082904918423731e-05,
"loss": 4.1044,
"step": 560128
},
{
"epoch": 0.01,
"learning_rate": 4.082066323672678e-05,
"loss": 4.1095,
"step": 560640
},
{
"epoch": 0.01,
"learning_rate": 4.081227728921626e-05,
"loss": 4.101,
"step": 561152
},
{
"epoch": 0.01,
"learning_rate": 4.080390772050948e-05,
"loss": 4.1051,
"step": 561664
},
{
"epoch": 0.01,
"learning_rate": 4.079552177299896e-05,
"loss": 4.0904,
"step": 562176
},
{
"epoch": 0.01,
"learning_rate": 4.078715220429217e-05,
"loss": 4.1084,
"step": 562688
},
{
"epoch": 0.01,
"learning_rate": 4.0778766256781647e-05,
"loss": 4.0987,
"step": 563200
},
{
"epoch": 0.01,
"learning_rate": 4.0770380309271127e-05,
"loss": 4.1022,
"step": 563712
},
{
"epoch": 0.01,
"learning_rate": 4.0761994361760607e-05,
"loss": 4.1105,
"step": 564224
},
{
"epoch": 0.01,
"learning_rate": 4.0753624793053816e-05,
"loss": 4.0992,
"step": 564736
},
{
"epoch": 0.01,
"learning_rate": 4.0745238845543296e-05,
"loss": 4.0964,
"step": 565248
},
{
"epoch": 0.01,
"learning_rate": 4.073685289803278e-05,
"loss": 4.1105,
"step": 565760
},
{
"epoch": 0.01,
"learning_rate": 4.0728466950522255e-05,
"loss": 4.0944,
"step": 566272
},
{
"epoch": 0.01,
"learning_rate": 4.0720081003011735e-05,
"loss": 4.0951,
"step": 566784
},
{
"epoch": 0.01,
"learning_rate": 4.071171143430495e-05,
"loss": 4.1073,
"step": 567296
},
{
"epoch": 0.01,
"learning_rate": 4.070332548679443e-05,
"loss": 4.1065,
"step": 567808
},
{
"epoch": 0.01,
"learning_rate": 4.069495591808764e-05,
"loss": 4.0908,
"step": 568320
},
{
"epoch": 0.01,
"learning_rate": 4.068656997057712e-05,
"loss": 4.1081,
"step": 568832
},
{
"epoch": 0.01,
"learning_rate": 4.06781840230666e-05,
"loss": 4.0901,
"step": 569344
},
{
"epoch": 0.01,
"learning_rate": 4.066979807555608e-05,
"loss": 4.0991,
"step": 569856
},
{
"epoch": 0.01,
"learning_rate": 4.0661412128045553e-05,
"loss": 4.1096,
"step": 570368
},
{
"epoch": 0.01,
"learning_rate": 4.065302618053503e-05,
"loss": 4.1081,
"step": 570880
},
{
"epoch": 0.01,
"learning_rate": 4.064465661182825e-05,
"loss": 4.1075,
"step": 571392
},
{
"epoch": 0.01,
"learning_rate": 4.063627066431773e-05,
"loss": 4.1068,
"step": 571904
},
{
"epoch": 0.01,
"learning_rate": 4.062788471680721e-05,
"loss": 4.1226,
"step": 572416
},
{
"epoch": 0.01,
"learning_rate": 4.061949876929669e-05,
"loss": 4.0966,
"step": 572928
},
{
"epoch": 0.01,
"learning_rate": 4.061111282178617e-05,
"loss": 4.1043,
"step": 573440
},
{
"epoch": 0.01,
"learning_rate": 4.060272687427565e-05,
"loss": 4.1147,
"step": 573952
},
{
"epoch": 0.01,
"learning_rate": 4.059434092676513e-05,
"loss": 4.0936,
"step": 574464
},
{
"epoch": 0.01,
"learning_rate": 4.058595497925461e-05,
"loss": 4.1018,
"step": 574976
},
{
"epoch": 0.01,
"learning_rate": 4.057756903174409e-05,
"loss": 4.1091,
"step": 575488
},
{
"epoch": 0.01,
"learning_rate": 4.056918308423357e-05,
"loss": 4.1135,
"step": 576000
},
{
"epoch": 0.01,
"learning_rate": 4.056079713672305e-05,
"loss": 4.1071,
"step": 576512
},
{
"epoch": 0.01,
"learning_rate": 4.055241118921253e-05,
"loss": 4.0928,
"step": 577024
},
{
"epoch": 0.01,
"learning_rate": 4.054404162050574e-05,
"loss": 4.09,
"step": 577536
},
{
"epoch": 0.01,
"learning_rate": 4.053565567299522e-05,
"loss": 4.1014,
"step": 578048
},
{
"epoch": 0.01,
"learning_rate": 4.05272697254847e-05,
"loss": 4.1088,
"step": 578560
},
{
"epoch": 0.01,
"learning_rate": 4.0518883777974184e-05,
"loss": 4.1053,
"step": 579072
},
{
"epoch": 0.01,
"learning_rate": 4.0510514209267394e-05,
"loss": 4.1044,
"step": 579584
},
{
"epoch": 0.02,
"learning_rate": 4.0502128261756874e-05,
"loss": 4.0857,
"step": 580096
},
{
"epoch": 0.02,
"learning_rate": 4.0493742314246353e-05,
"loss": 4.0973,
"step": 580608
},
{
"epoch": 0.02,
"learning_rate": 4.0485356366735833e-05,
"loss": 4.0948,
"step": 581120
},
{
"epoch": 0.02,
"learning_rate": 4.047698679802904e-05,
"loss": 4.1012,
"step": 581632
},
{
"epoch": 0.02,
"learning_rate": 4.046860085051852e-05,
"loss": 4.1052,
"step": 582144
},
{
"epoch": 0.02,
"learning_rate": 4.0460214903008e-05,
"loss": 4.1163,
"step": 582656
},
{
"epoch": 0.02,
"learning_rate": 4.045182895549748e-05,
"loss": 4.1046,
"step": 583168
},
{
"epoch": 0.02,
"learning_rate": 4.044344300798696e-05,
"loss": 4.0933,
"step": 583680
},
{
"epoch": 0.02,
"learning_rate": 4.043507343928017e-05,
"loss": 4.0924,
"step": 584192
},
{
"epoch": 0.02,
"learning_rate": 4.042668749176965e-05,
"loss": 4.0968,
"step": 584704
},
{
"epoch": 0.02,
"learning_rate": 4.041830154425914e-05,
"loss": 4.1065,
"step": 585216
},
{
"epoch": 0.02,
"learning_rate": 4.040991559674862e-05,
"loss": 4.0972,
"step": 585728
},
{
"epoch": 0.02,
"learning_rate": 4.040154602804183e-05,
"loss": 4.1082,
"step": 586240
},
{
"epoch": 0.02,
"learning_rate": 4.039316008053131e-05,
"loss": 4.098,
"step": 586752
},
{
"epoch": 0.02,
"learning_rate": 4.038477413302079e-05,
"loss": 4.0865,
"step": 587264
},
{
"epoch": 0.02,
"learning_rate": 4.037638818551027e-05,
"loss": 4.0964,
"step": 587776
},
{
"epoch": 0.02,
"learning_rate": 4.0368018616803476e-05,
"loss": 4.0909,
"step": 588288
},
{
"epoch": 0.02,
"learning_rate": 4.0359632669292956e-05,
"loss": 4.0877,
"step": 588800
},
{
"epoch": 0.02,
"learning_rate": 4.0351246721782436e-05,
"loss": 4.1001,
"step": 589312
},
{
"epoch": 0.02,
"learning_rate": 4.034286077427191e-05,
"loss": 4.0965,
"step": 589824
},
{
"epoch": 0.02,
"learning_rate": 4.033447482676139e-05,
"loss": 4.0903,
"step": 590336
},
{
"epoch": 0.02,
"learning_rate": 4.0326088879250876e-05,
"loss": 4.0903,
"step": 590848
},
{
"epoch": 0.02,
"learning_rate": 4.0317702931740356e-05,
"loss": 4.0877,
"step": 591360
},
{
"epoch": 0.02,
"learning_rate": 4.0309316984229836e-05,
"loss": 4.0975,
"step": 591872
},
{
"epoch": 0.02,
"learning_rate": 4.0300931036719316e-05,
"loss": 4.0891,
"step": 592384
},
{
"epoch": 0.02,
"learning_rate": 4.0292561468012525e-05,
"loss": 4.1106,
"step": 592896
},
{
"epoch": 0.02,
"learning_rate": 4.0284175520502005e-05,
"loss": 4.1031,
"step": 593408
},
{
"epoch": 0.02,
"learning_rate": 4.0275789572991485e-05,
"loss": 4.1021,
"step": 593920
},
{
"epoch": 0.02,
"learning_rate": 4.026743638308843e-05,
"loss": 4.0994,
"step": 594432
},
{
"epoch": 0.02,
"learning_rate": 4.025905043557791e-05,
"loss": 4.0835,
"step": 594944
},
{
"epoch": 0.02,
"learning_rate": 4.025066448806738e-05,
"loss": 4.1016,
"step": 595456
},
{
"epoch": 0.02,
"learning_rate": 4.024227854055686e-05,
"loss": 4.1002,
"step": 595968
},
{
"epoch": 0.02,
"learning_rate": 4.023389259304634e-05,
"loss": 4.0951,
"step": 596480
},
{
"epoch": 0.02,
"learning_rate": 4.022550664553583e-05,
"loss": 4.0856,
"step": 596992
},
{
"epoch": 0.02,
"learning_rate": 4.021712069802531e-05,
"loss": 4.0972,
"step": 597504
},
{
"epoch": 0.02,
"learning_rate": 4.020873475051479e-05,
"loss": 4.0846,
"step": 598016
},
{
"epoch": 0.02,
"learning_rate": 4.020034880300427e-05,
"loss": 4.0918,
"step": 598528
},
{
"epoch": 0.02,
"learning_rate": 4.019197923429748e-05,
"loss": 4.0824,
"step": 599040
},
{
"epoch": 0.02,
"learning_rate": 4.018359328678696e-05,
"loss": 4.098,
"step": 599552
},
{
"epoch": 0.02,
"learning_rate": 4.017520733927644e-05,
"loss": 4.0791,
"step": 600064
},
{
"epoch": 0.02,
"learning_rate": 4.016682139176592e-05,
"loss": 4.1051,
"step": 600576
},
{
"epoch": 0.02,
"learning_rate": 4.01584354442554e-05,
"loss": 4.0945,
"step": 601088
},
{
"epoch": 0.02,
"learning_rate": 4.015006587554861e-05,
"loss": 4.1038,
"step": 601600
},
{
"epoch": 0.02,
"learning_rate": 4.014167992803809e-05,
"loss": 4.0828,
"step": 602112
},
{
"epoch": 0.02,
"learning_rate": 4.013329398052757e-05,
"loss": 4.1007,
"step": 602624
},
{
"epoch": 0.02,
"learning_rate": 4.012490803301705e-05,
"loss": 4.0969,
"step": 603136
},
{
"epoch": 0.02,
"learning_rate": 4.011652208550653e-05,
"loss": 4.0989,
"step": 603648
},
{
"epoch": 0.02,
"learning_rate": 4.010815251679974e-05,
"loss": 4.0951,
"step": 604160
},
{
"epoch": 0.02,
"learning_rate": 4.009976656928922e-05,
"loss": 4.093,
"step": 604672
},
{
"epoch": 0.02,
"learning_rate": 4.00913806217787e-05,
"loss": 4.0926,
"step": 605184
},
{
"epoch": 0.02,
"learning_rate": 4.008299467426818e-05,
"loss": 4.1053,
"step": 605696
},
{
"epoch": 0.02,
"learning_rate": 4.007460872675766e-05,
"loss": 4.0802,
"step": 606208
},
{
"epoch": 0.02,
"learning_rate": 4.006622277924714e-05,
"loss": 4.0988,
"step": 606720
},
{
"epoch": 0.02,
"learning_rate": 4.005783683173662e-05,
"loss": 4.0925,
"step": 607232
},
{
"epoch": 0.02,
"learning_rate": 4.00494508842261e-05,
"loss": 4.0896,
"step": 607744
},
{
"epoch": 0.02,
"learning_rate": 4.0041064936715576e-05,
"loss": 4.0938,
"step": 608256
},
{
"epoch": 0.02,
"learning_rate": 4.003271174681252e-05,
"loss": 4.0875,
"step": 608768
},
{
"epoch": 0.02,
"learning_rate": 4.002434217810574e-05,
"loss": 4.0988,
"step": 609280
},
{
"epoch": 0.02,
"learning_rate": 4.001595623059522e-05,
"loss": 4.0761,
"step": 609792
},
{
"epoch": 0.02,
"learning_rate": 4.00075702830847e-05,
"loss": 4.0945,
"step": 610304
},
{
"epoch": 0.03,
"eval_loss": 4.103435039520264,
"eval_runtime": 286.6983,
"eval_samples_per_second": 1330.985,
"eval_steps_per_second": 41.594,
"step": 610560
},
{
"epoch": 1.0,
"learning_rate": 3.999918433557418e-05,
"loss": 4.0888,
"step": 610816
},
{
"epoch": 1.0,
"learning_rate": 3.999079838806366e-05,
"loss": 4.0807,
"step": 611328
},
{
"epoch": 1.0,
"learning_rate": 3.998241244055314e-05,
"loss": 4.0889,
"step": 611840
},
{
"epoch": 1.0,
"learning_rate": 3.997402649304262e-05,
"loss": 4.0878,
"step": 612352
},
{
"epoch": 1.0,
"learning_rate": 3.99656405455321e-05,
"loss": 4.0985,
"step": 612864
},
{
"epoch": 1.0,
"learning_rate": 3.9957254598021577e-05,
"loss": 4.0842,
"step": 613376
},
{
"epoch": 1.0,
"learning_rate": 3.9948885029314786e-05,
"loss": 4.0859,
"step": 613888
},
{
"epoch": 1.0,
"learning_rate": 3.9940499081804266e-05,
"loss": 4.0825,
"step": 614400
},
{
"epoch": 1.0,
"learning_rate": 3.9932113134293746e-05,
"loss": 4.0844,
"step": 614912
},
{
"epoch": 1.0,
"learning_rate": 3.992372718678322e-05,
"loss": 4.0982,
"step": 615424
},
{
"epoch": 1.0,
"learning_rate": 3.9915341239272706e-05,
"loss": 4.0866,
"step": 615936
},
{
"epoch": 1.0,
"learning_rate": 3.9906955291762185e-05,
"loss": 4.0914,
"step": 616448
},
{
"epoch": 1.0,
"learning_rate": 3.9898569344251665e-05,
"loss": 4.082,
"step": 616960
},
{
"epoch": 1.0,
"learning_rate": 3.9890183396741145e-05,
"loss": 4.0855,
"step": 617472
},
{
"epoch": 1.0,
"learning_rate": 3.9881797449230625e-05,
"loss": 4.0834,
"step": 617984
},
{
"epoch": 1.0,
"learning_rate": 3.9873427880523834e-05,
"loss": 4.078,
"step": 618496
},
{
"epoch": 1.0,
"learning_rate": 3.9865058311817044e-05,
"loss": 4.0825,
"step": 619008
},
{
"epoch": 1.0,
"learning_rate": 3.9856672364306523e-05,
"loss": 4.0806,
"step": 619520
},
{
"epoch": 1.0,
"learning_rate": 3.9848286416796003e-05,
"loss": 4.0851,
"step": 620032
},
{
"epoch": 1.0,
"learning_rate": 3.9839900469285483e-05,
"loss": 4.0878,
"step": 620544
},
{
"epoch": 1.0,
"learning_rate": 3.983151452177496e-05,
"loss": 4.0922,
"step": 621056
},
{
"epoch": 1.0,
"learning_rate": 3.982312857426444e-05,
"loss": 4.097,
"step": 621568
},
{
"epoch": 1.0,
"learning_rate": 3.981474262675392e-05,
"loss": 4.079,
"step": 622080
},
{
"epoch": 1.0,
"learning_rate": 3.980637305804714e-05,
"loss": 4.0917,
"step": 622592
},
{
"epoch": 1.0,
"learning_rate": 3.979798711053662e-05,
"loss": 4.0821,
"step": 623104
},
{
"epoch": 1.0,
"learning_rate": 3.97896011630261e-05,
"loss": 4.0924,
"step": 623616
},
{
"epoch": 1.0,
"learning_rate": 3.978123159431931e-05,
"loss": 4.0798,
"step": 624128
},
{
"epoch": 1.0,
"learning_rate": 3.977284564680879e-05,
"loss": 4.0777,
"step": 624640
},
{
"epoch": 1.0,
"learning_rate": 3.976445969929827e-05,
"loss": 4.0792,
"step": 625152
},
{
"epoch": 1.0,
"learning_rate": 3.975607375178775e-05,
"loss": 4.0775,
"step": 625664
},
{
"epoch": 1.01,
"learning_rate": 3.974768780427723e-05,
"loss": 4.0761,
"step": 626176
},
{
"epoch": 1.01,
"learning_rate": 3.973930185676671e-05,
"loss": 4.0903,
"step": 626688
},
{
"epoch": 1.01,
"learning_rate": 3.973091590925619e-05,
"loss": 4.0825,
"step": 627200
},
{
"epoch": 1.01,
"learning_rate": 3.972252996174567e-05,
"loss": 4.0896,
"step": 627712
},
{
"epoch": 1.01,
"learning_rate": 3.971414401423515e-05,
"loss": 4.0825,
"step": 628224
},
{
"epoch": 1.01,
"learning_rate": 3.970577444552836e-05,
"loss": 4.0901,
"step": 628736
},
{
"epoch": 1.01,
"learning_rate": 3.969738849801784e-05,
"loss": 4.0877,
"step": 629248
},
{
"epoch": 1.01,
"learning_rate": 3.9689002550507324e-05,
"loss": 4.0696,
"step": 629760
},
{
"epoch": 1.01,
"learning_rate": 3.9680616602996804e-05,
"loss": 4.0751,
"step": 630272
},
{
"epoch": 1.01,
"learning_rate": 3.9672230655486283e-05,
"loss": 4.0732,
"step": 630784
},
{
"epoch": 1.01,
"learning_rate": 3.966386108677949e-05,
"loss": 4.0758,
"step": 631296
},
{
"epoch": 1.01,
"learning_rate": 3.965547513926897e-05,
"loss": 4.0846,
"step": 631808
},
{
"epoch": 1.01,
"learning_rate": 3.964708919175845e-05,
"loss": 4.0764,
"step": 632320
},
{
"epoch": 1.01,
"learning_rate": 3.963870324424793e-05,
"loss": 4.0747,
"step": 632832
},
{
"epoch": 1.01,
"learning_rate": 3.9630317296737406e-05,
"loss": 4.0869,
"step": 633344
},
{
"epoch": 1.01,
"learning_rate": 3.9621931349226886e-05,
"loss": 4.0755,
"step": 633856
},
{
"epoch": 1.01,
"learning_rate": 3.9613545401716366e-05,
"loss": 4.0844,
"step": 634368
},
{
"epoch": 1.01,
"learning_rate": 3.960517583300958e-05,
"loss": 4.0651,
"step": 634880
},
{
"epoch": 1.01,
"learning_rate": 3.959678988549906e-05,
"loss": 4.0565,
"step": 635392
},
{
"epoch": 1.01,
"learning_rate": 3.958840393798854e-05,
"loss": 4.0884,
"step": 635904
},
{
"epoch": 1.01,
"learning_rate": 3.958001799047802e-05,
"loss": 4.0759,
"step": 636416
},
{
"epoch": 1.01,
"learning_rate": 3.95716320429675e-05,
"loss": 4.0803,
"step": 636928
},
{
"epoch": 1.01,
"learning_rate": 3.956324609545698e-05,
"loss": 4.0723,
"step": 637440
},
{
"epoch": 1.01,
"learning_rate": 3.955486014794646e-05,
"loss": 4.0692,
"step": 637952
},
{
"epoch": 1.01,
"learning_rate": 3.954647420043594e-05,
"loss": 4.0665,
"step": 638464
},
{
"epoch": 1.01,
"learning_rate": 3.953810463172915e-05,
"loss": 4.0782,
"step": 638976
},
{
"epoch": 1.01,
"learning_rate": 3.952971868421863e-05,
"loss": 4.0657,
"step": 639488
},
{
"epoch": 1.01,
"learning_rate": 3.952133273670811e-05,
"loss": 4.0753,
"step": 640000
},
{
"epoch": 1.01,
"learning_rate": 3.951294678919759e-05,
"loss": 4.0824,
"step": 640512
},
{
"epoch": 1.01,
"learning_rate": 3.950456084168707e-05,
"loss": 4.0652,
"step": 641024
},
{
"epoch": 1.01,
"learning_rate": 3.949619127298028e-05,
"loss": 4.0655,
"step": 641536
},
{
"epoch": 1.01,
"learning_rate": 3.948780532546976e-05,
"loss": 4.0825,
"step": 642048
},
{
"epoch": 1.01,
"learning_rate": 3.9479419377959246e-05,
"loss": 4.064,
"step": 642560
},
{
"epoch": 1.01,
"learning_rate": 3.9471033430448726e-05,
"loss": 4.0652,
"step": 643072
},
{
"epoch": 1.01,
"learning_rate": 3.9462647482938206e-05,
"loss": 4.0795,
"step": 643584
},
{
"epoch": 1.01,
"learning_rate": 3.9454261535427686e-05,
"loss": 4.0722,
"step": 644096
},
{
"epoch": 1.01,
"learning_rate": 3.9445875587917166e-05,
"loss": 4.0635,
"step": 644608
},
{
"epoch": 1.01,
"learning_rate": 3.9437506019210375e-05,
"loss": 4.0772,
"step": 645120
},
{
"epoch": 1.01,
"learning_rate": 3.9429120071699855e-05,
"loss": 4.0614,
"step": 645632
},
{
"epoch": 1.01,
"learning_rate": 3.9420734124189335e-05,
"loss": 4.0662,
"step": 646144
},
{
"epoch": 1.01,
"learning_rate": 3.9412348176678815e-05,
"loss": 4.0823,
"step": 646656
},
{
"epoch": 1.01,
"learning_rate": 3.9403962229168295e-05,
"loss": 4.0766,
"step": 647168
},
{
"epoch": 1.01,
"learning_rate": 3.9395592660461504e-05,
"loss": 4.076,
"step": 647680
},
{
"epoch": 1.01,
"learning_rate": 3.9387206712950984e-05,
"loss": 4.0767,
"step": 648192
},
{
"epoch": 1.01,
"learning_rate": 3.937885352304793e-05,
"loss": 4.0952,
"step": 648704
},
{
"epoch": 1.01,
"learning_rate": 3.937046757553741e-05,
"loss": 4.0652,
"step": 649216
},
{
"epoch": 1.01,
"learning_rate": 3.936208162802689e-05,
"loss": 4.077,
"step": 649728
},
{
"epoch": 1.01,
"learning_rate": 3.935369568051637e-05,
"loss": 4.0814,
"step": 650240
},
{
"epoch": 1.01,
"learning_rate": 3.934530973300585e-05,
"loss": 4.0671,
"step": 650752
},
{
"epoch": 1.01,
"learning_rate": 3.933692378549533e-05,
"loss": 4.0675,
"step": 651264
},
{
"epoch": 1.01,
"learning_rate": 3.932853783798481e-05,
"loss": 4.0824,
"step": 651776
},
{
"epoch": 1.01,
"learning_rate": 3.932016826927802e-05,
"loss": 4.0812,
"step": 652288
},
{
"epoch": 1.01,
"learning_rate": 3.93117823217675e-05,
"loss": 4.0816,
"step": 652800
},
{
"epoch": 1.01,
"learning_rate": 3.930339637425698e-05,
"loss": 4.0618,
"step": 653312
},
{
"epoch": 1.01,
"learning_rate": 3.929501042674646e-05,
"loss": 4.0596,
"step": 653824
},
{
"epoch": 1.01,
"learning_rate": 3.928662447923594e-05,
"loss": 4.0725,
"step": 654336
},
{
"epoch": 1.01,
"learning_rate": 3.927823853172542e-05,
"loss": 4.0796,
"step": 654848
},
{
"epoch": 1.01,
"learning_rate": 3.92698525842149e-05,
"loss": 4.0747,
"step": 655360
},
{
"epoch": 1.01,
"learning_rate": 3.926146663670438e-05,
"loss": 4.0758,
"step": 655872
},
{
"epoch": 1.02,
"learning_rate": 3.925308068919386e-05,
"loss": 4.0569,
"step": 656384
},
{
"epoch": 1.02,
"learning_rate": 3.924469474168334e-05,
"loss": 4.0687,
"step": 656896
},
{
"epoch": 1.02,
"learning_rate": 3.923630879417282e-05,
"loss": 4.0662,
"step": 657408
},
{
"epoch": 1.02,
"learning_rate": 3.92279228466623e-05,
"loss": 4.068,
"step": 657920
},
{
"epoch": 1.02,
"learning_rate": 3.921956965675924e-05,
"loss": 4.0795,
"step": 658432
},
{
"epoch": 1.02,
"learning_rate": 3.9211183709248715e-05,
"loss": 4.0834,
"step": 658944
},
{
"epoch": 1.02,
"learning_rate": 3.9202797761738195e-05,
"loss": 4.0771,
"step": 659456
},
{
"epoch": 1.02,
"learning_rate": 3.9194411814227675e-05,
"loss": 4.0682,
"step": 659968
},
{
"epoch": 1.02,
"learning_rate": 3.9186025866717155e-05,
"loss": 4.061,
"step": 660480
},
{
"epoch": 1.02,
"learning_rate": 3.9177639919206635e-05,
"loss": 4.0678,
"step": 660992
},
{
"epoch": 1.02,
"learning_rate": 3.916927035049985e-05,
"loss": 4.0776,
"step": 661504
},
{
"epoch": 1.02,
"learning_rate": 3.916088440298933e-05,
"loss": 4.0698,
"step": 662016
},
{
"epoch": 1.02,
"learning_rate": 3.915251483428254e-05,
"loss": 4.0789,
"step": 662528
},
{
"epoch": 1.02,
"learning_rate": 3.914412888677202e-05,
"loss": 4.0704,
"step": 663040
},
{
"epoch": 1.02,
"learning_rate": 3.91357429392615e-05,
"loss": 4.0608,
"step": 663552
},
{
"epoch": 1.02,
"learning_rate": 3.912735699175098e-05,
"loss": 4.0671,
"step": 664064
},
{
"epoch": 1.02,
"learning_rate": 3.911897104424046e-05,
"loss": 4.0609,
"step": 664576
},
{
"epoch": 1.02,
"learning_rate": 3.911058509672994e-05,
"loss": 4.061,
"step": 665088
},
{
"epoch": 1.02,
"learning_rate": 3.910219914921942e-05,
"loss": 4.071,
"step": 665600
},
{
"epoch": 1.02,
"learning_rate": 3.90938132017089e-05,
"loss": 4.0693,
"step": 666112
},
{
"epoch": 1.02,
"learning_rate": 3.908544363300211e-05,
"loss": 4.0634,
"step": 666624
},
{
"epoch": 1.02,
"learning_rate": 3.907705768549159e-05,
"loss": 4.0583,
"step": 667136
},
{
"epoch": 1.02,
"learning_rate": 3.906867173798107e-05,
"loss": 4.0572,
"step": 667648
},
{
"epoch": 1.02,
"learning_rate": 3.9060285790470555e-05,
"loss": 4.0684,
"step": 668160
},
{
"epoch": 1.02,
"learning_rate": 3.9051916221763764e-05,
"loss": 4.0609,
"step": 668672
},
{
"epoch": 1.02,
"learning_rate": 3.9043530274253244e-05,
"loss": 4.0831,
"step": 669184
},
{
"epoch": 1.02,
"learning_rate": 3.9035144326742724e-05,
"loss": 4.0769,
"step": 669696
},
{
"epoch": 1.02,
"learning_rate": 3.9026758379232204e-05,
"loss": 4.0729,
"step": 670208
},
{
"epoch": 1.02,
"learning_rate": 3.9018372431721684e-05,
"loss": 4.0688,
"step": 670720
},
{
"epoch": 1.02,
"learning_rate": 3.9009986484211164e-05,
"loss": 4.0584,
"step": 671232
},
{
"epoch": 1.02,
"learning_rate": 3.9001600536700644e-05,
"loss": 4.0705,
"step": 671744
},
{
"epoch": 1.02,
"learning_rate": 3.8993214589190124e-05,
"loss": 4.0695,
"step": 672256
},
{
"epoch": 1.02,
"learning_rate": 3.898484502048333e-05,
"loss": 4.0671,
"step": 672768
},
{
"epoch": 1.02,
"learning_rate": 3.897645907297281e-05,
"loss": 4.0599,
"step": 673280
},
{
"epoch": 1.02,
"learning_rate": 3.896807312546229e-05,
"loss": 4.0711,
"step": 673792
},
{
"epoch": 1.02,
"learning_rate": 3.895968717795177e-05,
"loss": 4.0591,
"step": 674304
},
{
"epoch": 1.02,
"learning_rate": 3.895131760924499e-05,
"loss": 4.0612,
"step": 674816
},
{
"epoch": 1.02,
"learning_rate": 3.89429480405382e-05,
"loss": 4.0515,
"step": 675328
},
{
"epoch": 1.02,
"learning_rate": 3.893456209302768e-05,
"loss": 4.0715,
"step": 675840
},
{
"epoch": 1.02,
"learning_rate": 3.892617614551716e-05,
"loss": 4.0531,
"step": 676352
},
{
"epoch": 1.02,
"learning_rate": 3.891779019800664e-05,
"loss": 4.0752,
"step": 676864
},
{
"epoch": 1.02,
"learning_rate": 3.890940425049612e-05,
"loss": 4.069,
"step": 677376
},
{
"epoch": 1.02,
"learning_rate": 3.89010183029856e-05,
"loss": 4.0749,
"step": 677888
},
{
"epoch": 1.02,
"learning_rate": 3.889263235547508e-05,
"loss": 4.0566,
"step": 678400
},
{
"epoch": 1.02,
"learning_rate": 3.888424640796455e-05,
"loss": 4.0739,
"step": 678912
},
{
"epoch": 1.02,
"learning_rate": 3.8875893218061496e-05,
"loss": 4.0664,
"step": 679424
},
{
"epoch": 1.02,
"learning_rate": 3.8867507270550976e-05,
"loss": 4.0712,
"step": 679936
},
{
"epoch": 1.02,
"learning_rate": 3.885912132304046e-05,
"loss": 4.0716,
"step": 680448
},
{
"epoch": 1.02,
"learning_rate": 3.885073537552994e-05,
"loss": 4.0619,
"step": 680960
},
{
"epoch": 1.02,
"learning_rate": 3.884234942801942e-05,
"loss": 4.0683,
"step": 681472
},
{
"epoch": 1.02,
"learning_rate": 3.883397985931263e-05,
"loss": 4.0772,
"step": 681984
},
{
"epoch": 1.02,
"learning_rate": 3.882559391180211e-05,
"loss": 4.053,
"step": 682496
},
{
"epoch": 1.02,
"learning_rate": 3.881720796429159e-05,
"loss": 4.0712,
"step": 683008
},
{
"epoch": 1.02,
"learning_rate": 3.880882201678107e-05,
"loss": 4.0714,
"step": 683520
},
{
"epoch": 1.02,
"learning_rate": 3.880043606927055e-05,
"loss": 4.0653,
"step": 684032
},
{
"epoch": 1.02,
"learning_rate": 3.879206650056376e-05,
"loss": 4.0591,
"step": 684544
},
{
"epoch": 1.02,
"learning_rate": 3.878368055305324e-05,
"loss": 4.0616,
"step": 685056
},
{
"epoch": 1.02,
"learning_rate": 3.877529460554272e-05,
"loss": 4.0708,
"step": 685568
},
{
"epoch": 1.02,
"learning_rate": 3.87669086580322e-05,
"loss": 4.0519,
"step": 686080
},
{
"epoch": 1.02,
"learning_rate": 3.875852271052168e-05,
"loss": 4.0642,
"step": 686592
},
{
"epoch": 1.03,
"eval_loss": 4.084194183349609,
"eval_runtime": 290.2379,
"eval_samples_per_second": 1314.752,
"eval_steps_per_second": 41.087,
"step": 686880
},
{
"epoch": 0.0,
"learning_rate": 3.8750153141814896e-05,
"loss": 4.058,
"step": 687104
},
{
"epoch": 0.0,
"learning_rate": 3.8741767194304376e-05,
"loss": 4.0549,
"step": 687616
},
{
"epoch": 0.0,
"learning_rate": 3.873338124679385e-05,
"loss": 4.0584,
"step": 688128
},
{
"epoch": 0.0,
"learning_rate": 3.872499529928333e-05,
"loss": 4.0642,
"step": 688640
},
{
"epoch": 0.0,
"learning_rate": 3.871660935177281e-05,
"loss": 4.0711,
"step": 689152
},
{
"epoch": 0.0,
"learning_rate": 3.870822340426229e-05,
"loss": 4.0564,
"step": 689664
},
{
"epoch": 0.0,
"learning_rate": 3.869983745675177e-05,
"loss": 4.0576,
"step": 690176
},
{
"epoch": 0.0,
"learning_rate": 3.869145150924125e-05,
"loss": 4.0577,
"step": 690688
},
{
"epoch": 0.0,
"learning_rate": 3.868306556173073e-05,
"loss": 4.0519,
"step": 691200
},
{
"epoch": 0.0,
"learning_rate": 3.867467961422021e-05,
"loss": 4.0749,
"step": 691712
},
{
"epoch": 0.0,
"learning_rate": 3.866629366670969e-05,
"loss": 4.0582,
"step": 692224
},
{
"epoch": 0.0,
"learning_rate": 3.865790771919917e-05,
"loss": 4.063,
"step": 692736
},
{
"epoch": 0.0,
"learning_rate": 3.864952177168865e-05,
"loss": 4.064,
"step": 693248
},
{
"epoch": 0.0,
"learning_rate": 3.864113582417813e-05,
"loss": 4.0535,
"step": 693760
},
{
"epoch": 0.0,
"learning_rate": 3.863274987666761e-05,
"loss": 4.0542,
"step": 694272
},
{
"epoch": 0.0,
"learning_rate": 3.862436392915709e-05,
"loss": 4.0528,
"step": 694784
},
{
"epoch": 0.0,
"learning_rate": 3.8615994360450305e-05,
"loss": 4.0574,
"step": 695296
},
{
"epoch": 0.0,
"learning_rate": 3.8607608412939785e-05,
"loss": 4.0585,
"step": 695808
},
{
"epoch": 0.0,
"learning_rate": 3.8599222465429265e-05,
"loss": 4.055,
"step": 696320
},
{
"epoch": 0.0,
"learning_rate": 3.859083651791874e-05,
"loss": 4.0608,
"step": 696832
},
{
"epoch": 0.0,
"learning_rate": 3.858245057040822e-05,
"loss": 4.0684,
"step": 697344
},
{
"epoch": 0.0,
"learning_rate": 3.85740646228977e-05,
"loss": 4.0698,
"step": 697856
},
{
"epoch": 0.0,
"learning_rate": 3.8565695054190914e-05,
"loss": 4.0589,
"step": 698368
},
{
"epoch": 0.0,
"learning_rate": 3.855730910668039e-05,
"loss": 4.0562,
"step": 698880
},
{
"epoch": 0.0,
"learning_rate": 3.854892315916987e-05,
"loss": 4.057,
"step": 699392
},
{
"epoch": 0.0,
"learning_rate": 3.854053721165935e-05,
"loss": 4.0651,
"step": 699904
},
{
"epoch": 0.0,
"learning_rate": 3.8532151264148833e-05,
"loss": 4.0557,
"step": 700416
},
{
"epoch": 0.0,
"learning_rate": 3.852376531663831e-05,
"loss": 4.0522,
"step": 700928
},
{
"epoch": 0.0,
"learning_rate": 3.851537936912779e-05,
"loss": 4.0524,
"step": 701440
},
{
"epoch": 0.0,
"learning_rate": 3.8507009800421e-05,
"loss": 4.0513,
"step": 701952
},
{
"epoch": 0.01,
"learning_rate": 3.849864023171421e-05,
"loss": 4.0491,
"step": 702464
},
{
"epoch": 0.01,
"learning_rate": 3.849025428420369e-05,
"loss": 4.0646,
"step": 702976
},
{
"epoch": 0.01,
"learning_rate": 3.848186833669317e-05,
"loss": 4.0601,
"step": 703488
},
{
"epoch": 0.01,
"learning_rate": 3.847348238918265e-05,
"loss": 4.063,
"step": 704000
},
{
"epoch": 0.01,
"learning_rate": 3.846509644167213e-05,
"loss": 4.0574,
"step": 704512
},
{
"epoch": 0.01,
"learning_rate": 3.845671049416161e-05,
"loss": 4.0568,
"step": 705024
},
{
"epoch": 0.01,
"learning_rate": 3.844832454665109e-05,
"loss": 4.0652,
"step": 705536
},
{
"epoch": 0.01,
"learning_rate": 3.843993859914057e-05,
"loss": 4.0461,
"step": 706048
},
{
"epoch": 0.01,
"learning_rate": 3.843156903043379e-05,
"loss": 4.0513,
"step": 706560
},
{
"epoch": 0.01,
"learning_rate": 3.842318308292327e-05,
"loss": 4.0441,
"step": 707072
},
{
"epoch": 0.01,
"learning_rate": 3.841479713541275e-05,
"loss": 4.0498,
"step": 707584
},
{
"epoch": 0.01,
"learning_rate": 3.840641118790223e-05,
"loss": 4.058,
"step": 708096
},
{
"epoch": 0.01,
"learning_rate": 3.839802524039171e-05,
"loss": 4.0513,
"step": 708608
},
{
"epoch": 0.01,
"learning_rate": 3.8389655671684916e-05,
"loss": 4.0501,
"step": 709120
},
{
"epoch": 0.01,
"learning_rate": 3.8381269724174396e-05,
"loss": 4.0612,
"step": 709632
},
{
"epoch": 0.01,
"learning_rate": 3.8372900155467605e-05,
"loss": 4.0525,
"step": 710144
},
{
"epoch": 0.01,
"learning_rate": 3.8364514207957085e-05,
"loss": 4.0539,
"step": 710656
},
{
"epoch": 0.01,
"learning_rate": 3.8356128260446565e-05,
"loss": 4.0464,
"step": 711168
},
{
"epoch": 0.01,
"learning_rate": 3.8347742312936045e-05,
"loss": 4.0257,
"step": 711680
},
{
"epoch": 0.01,
"learning_rate": 3.8339356365425525e-05,
"loss": 4.0666,
"step": 712192
},
{
"epoch": 0.01,
"learning_rate": 3.8330970417915005e-05,
"loss": 4.047,
"step": 712704
},
{
"epoch": 0.01,
"learning_rate": 3.8322584470404485e-05,
"loss": 4.0591,
"step": 713216
},
{
"epoch": 0.01,
"learning_rate": 3.831419852289397e-05,
"loss": 4.0419,
"step": 713728
},
{
"epoch": 0.01,
"learning_rate": 3.830582895418718e-05,
"loss": 4.0486,
"step": 714240
},
{
"epoch": 0.01,
"learning_rate": 3.829744300667666e-05,
"loss": 4.0432,
"step": 714752
},
{
"epoch": 0.01,
"learning_rate": 3.828907343796987e-05,
"loss": 4.0467,
"step": 715264
},
{
"epoch": 0.01,
"learning_rate": 3.828068749045935e-05,
"loss": 4.0429,
"step": 715776
},
{
"epoch": 0.01,
"learning_rate": 3.827230154294883e-05,
"loss": 4.0478,
"step": 716288
},
{
"epoch": 0.01,
"learning_rate": 3.826391559543831e-05,
"loss": 4.0597,
"step": 716800
},
{
"epoch": 0.01,
"learning_rate": 3.825554602673152e-05,
"loss": 4.0399,
"step": 717312
},
{
"epoch": 0.01,
"learning_rate": 3.8247160079221e-05,
"loss": 4.0389,
"step": 717824
},
{
"epoch": 0.01,
"learning_rate": 3.823877413171048e-05,
"loss": 4.0586,
"step": 718336
},
{
"epoch": 0.01,
"learning_rate": 3.823038818419996e-05,
"loss": 4.0413,
"step": 718848
},
{
"epoch": 0.01,
"learning_rate": 3.822200223668944e-05,
"loss": 4.0381,
"step": 719360
},
{
"epoch": 0.01,
"learning_rate": 3.8213632667982654e-05,
"loss": 4.054,
"step": 719872
},
{
"epoch": 0.01,
"learning_rate": 3.8205246720472134e-05,
"loss": 4.0485,
"step": 720384
},
{
"epoch": 0.01,
"learning_rate": 3.8196860772961614e-05,
"loss": 4.0396,
"step": 720896
},
{
"epoch": 0.01,
"learning_rate": 3.8188474825451094e-05,
"loss": 4.0512,
"step": 721408
},
{
"epoch": 0.01,
"learning_rate": 3.8180088877940574e-05,
"loss": 4.0362,
"step": 721920
},
{
"epoch": 0.01,
"learning_rate": 3.817170293043005e-05,
"loss": 4.0447,
"step": 722432
},
{
"epoch": 0.01,
"learning_rate": 3.816331698291953e-05,
"loss": 4.0551,
"step": 722944
},
{
"epoch": 0.01,
"learning_rate": 3.815493103540901e-05,
"loss": 4.0528,
"step": 723456
},
{
"epoch": 0.01,
"learning_rate": 3.814656146670222e-05,
"loss": 4.0549,
"step": 723968
},
{
"epoch": 0.01,
"learning_rate": 3.8138175519191696e-05,
"loss": 4.0504,
"step": 724480
},
{
"epoch": 0.01,
"learning_rate": 3.8129789571681176e-05,
"loss": 4.0685,
"step": 724992
},
{
"epoch": 0.01,
"learning_rate": 3.812140362417066e-05,
"loss": 4.0381,
"step": 725504
},
{
"epoch": 0.01,
"learning_rate": 3.811303405546387e-05,
"loss": 4.0579,
"step": 726016
},
{
"epoch": 0.01,
"learning_rate": 3.810464810795335e-05,
"loss": 4.0497,
"step": 726528
},
{
"epoch": 0.01,
"learning_rate": 3.809627853924657e-05,
"loss": 4.0468,
"step": 727040
},
{
"epoch": 0.01,
"learning_rate": 3.808789259173605e-05,
"loss": 4.0439,
"step": 727552
},
{
"epoch": 0.01,
"learning_rate": 3.807950664422552e-05,
"loss": 4.0583,
"step": 728064
},
{
"epoch": 0.01,
"learning_rate": 3.8071120696715e-05,
"loss": 4.0544,
"step": 728576
},
{
"epoch": 0.01,
"learning_rate": 3.806275112800822e-05,
"loss": 4.0597,
"step": 729088
},
{
"epoch": 0.01,
"learning_rate": 3.805436518049769e-05,
"loss": 4.0352,
"step": 729600
},
{
"epoch": 0.01,
"learning_rate": 3.804597923298717e-05,
"loss": 4.038,
"step": 730112
},
{
"epoch": 0.01,
"learning_rate": 3.803759328547665e-05,
"loss": 4.0478,
"step": 730624
},
{
"epoch": 0.01,
"learning_rate": 3.802920733796613e-05,
"loss": 4.0537,
"step": 731136
},
{
"epoch": 0.01,
"learning_rate": 3.8020837769259346e-05,
"loss": 4.0462,
"step": 731648
},
{
"epoch": 0.01,
"learning_rate": 3.8012451821748826e-05,
"loss": 4.0547,
"step": 732160
},
{
"epoch": 0.02,
"learning_rate": 3.8004065874238306e-05,
"loss": 4.0351,
"step": 732672
},
{
"epoch": 0.02,
"learning_rate": 3.7995679926727786e-05,
"loss": 4.0457,
"step": 733184
},
{
"epoch": 0.02,
"learning_rate": 3.7987293979217266e-05,
"loss": 4.0421,
"step": 733696
},
{
"epoch": 0.02,
"learning_rate": 3.7978924410510475e-05,
"loss": 4.0401,
"step": 734208
},
{
"epoch": 0.02,
"learning_rate": 3.7970538462999955e-05,
"loss": 4.0536,
"step": 734720
},
{
"epoch": 0.02,
"learning_rate": 3.7962152515489435e-05,
"loss": 4.059,
"step": 735232
},
{
"epoch": 0.02,
"learning_rate": 3.7953766567978915e-05,
"loss": 4.0557,
"step": 735744
},
{
"epoch": 0.02,
"learning_rate": 3.7945380620468395e-05,
"loss": 4.0416,
"step": 736256
},
{
"epoch": 0.02,
"learning_rate": 3.7936994672957874e-05,
"loss": 4.0379,
"step": 736768
},
{
"epoch": 0.02,
"learning_rate": 3.7928608725447354e-05,
"loss": 4.0462,
"step": 737280
},
{
"epoch": 0.02,
"learning_rate": 3.7920222777936834e-05,
"loss": 4.0513,
"step": 737792
},
{
"epoch": 0.02,
"learning_rate": 3.791185320923005e-05,
"loss": 4.0473,
"step": 738304
},
{
"epoch": 0.02,
"learning_rate": 3.790346726171953e-05,
"loss": 4.051,
"step": 738816
},
{
"epoch": 0.02,
"learning_rate": 3.789508131420901e-05,
"loss": 4.0475,
"step": 739328
},
{
"epoch": 0.02,
"learning_rate": 3.788669536669849e-05,
"loss": 4.0385,
"step": 739840
},
{
"epoch": 0.02,
"learning_rate": 3.787830941918797e-05,
"loss": 4.0413,
"step": 740352
},
{
"epoch": 0.02,
"learning_rate": 3.786992347167745e-05,
"loss": 4.0354,
"step": 740864
},
{
"epoch": 0.02,
"learning_rate": 3.786153752416693e-05,
"loss": 4.0389,
"step": 741376
},
{
"epoch": 0.02,
"learning_rate": 3.785315157665641e-05,
"loss": 4.0476,
"step": 741888
},
{
"epoch": 0.02,
"learning_rate": 3.784478200794962e-05,
"loss": 4.0452,
"step": 742400
},
{
"epoch": 0.02,
"learning_rate": 3.78363960604391e-05,
"loss": 4.0384,
"step": 742912
},
{
"epoch": 0.02,
"learning_rate": 3.782802649173231e-05,
"loss": 4.036,
"step": 743424
},
{
"epoch": 0.02,
"learning_rate": 3.781964054422179e-05,
"loss": 4.0304,
"step": 743936
},
{
"epoch": 0.02,
"learning_rate": 3.781125459671127e-05,
"loss": 4.0464,
"step": 744448
},
{
"epoch": 0.02,
"learning_rate": 3.780286864920075e-05,
"loss": 4.0368,
"step": 744960
},
{
"epoch": 0.02,
"learning_rate": 3.7794482701690235e-05,
"loss": 4.0585,
"step": 745472
},
{
"epoch": 0.02,
"learning_rate": 3.7786113132983444e-05,
"loss": 4.0491,
"step": 745984
},
{
"epoch": 0.02,
"learning_rate": 3.7777727185472924e-05,
"loss": 4.0541,
"step": 746496
},
{
"epoch": 0.02,
"learning_rate": 3.7769341237962404e-05,
"loss": 4.0443,
"step": 747008
},
{
"epoch": 0.02,
"learning_rate": 3.7760955290451884e-05,
"loss": 4.0343,
"step": 747520
},
{
"epoch": 0.02,
"learning_rate": 3.775258572174509e-05,
"loss": 4.0485,
"step": 748032
},
{
"epoch": 0.02,
"learning_rate": 3.774419977423457e-05,
"loss": 4.0493,
"step": 748544
},
{
"epoch": 0.02,
"learning_rate": 3.773581382672405e-05,
"loss": 4.0401,
"step": 749056
},
{
"epoch": 0.02,
"learning_rate": 3.7727427879213526e-05,
"loss": 4.033,
"step": 749568
},
{
"epoch": 0.02,
"learning_rate": 3.771905831050674e-05,
"loss": 4.0472,
"step": 750080
},
{
"epoch": 0.02,
"learning_rate": 3.771067236299622e-05,
"loss": 4.0357,
"step": 750592
},
{
"epoch": 0.02,
"learning_rate": 3.77022864154857e-05,
"loss": 4.0387,
"step": 751104
},
{
"epoch": 0.02,
"learning_rate": 3.769390046797518e-05,
"loss": 4.0335,
"step": 751616
},
{
"epoch": 0.02,
"learning_rate": 3.768551452046466e-05,
"loss": 4.0438,
"step": 752128
},
{
"epoch": 0.02,
"learning_rate": 3.767712857295414e-05,
"loss": 4.0307,
"step": 752640
},
{
"epoch": 0.02,
"learning_rate": 3.766874262544362e-05,
"loss": 4.0499,
"step": 753152
},
{
"epoch": 0.02,
"learning_rate": 3.76603566779331e-05,
"loss": 4.0431,
"step": 753664
},
{
"epoch": 0.02,
"learning_rate": 3.765198710922631e-05,
"loss": 4.0571,
"step": 754176
},
{
"epoch": 0.02,
"learning_rate": 3.7643617540519526e-05,
"loss": 4.0305,
"step": 754688
},
{
"epoch": 0.02,
"learning_rate": 3.7635231593009e-05,
"loss": 4.0532,
"step": 755200
},
{
"epoch": 0.02,
"learning_rate": 3.762684564549848e-05,
"loss": 4.0406,
"step": 755712
},
{
"epoch": 0.02,
"learning_rate": 3.761845969798796e-05,
"loss": 4.0512,
"step": 756224
},
{
"epoch": 0.02,
"learning_rate": 3.761007375047744e-05,
"loss": 4.0452,
"step": 756736
},
{
"epoch": 0.02,
"learning_rate": 3.7601687802966926e-05,
"loss": 4.0379,
"step": 757248
},
{
"epoch": 0.02,
"learning_rate": 3.7593301855456406e-05,
"loss": 4.0425,
"step": 757760
},
{
"epoch": 0.02,
"learning_rate": 3.7584915907945886e-05,
"loss": 4.0588,
"step": 758272
},
{
"epoch": 0.02,
"learning_rate": 3.7576546339239095e-05,
"loss": 4.0277,
"step": 758784
},
{
"epoch": 0.02,
"learning_rate": 3.7568160391728575e-05,
"loss": 4.052,
"step": 759296
},
{
"epoch": 0.02,
"learning_rate": 3.7559774444218055e-05,
"loss": 4.0437,
"step": 759808
},
{
"epoch": 0.02,
"learning_rate": 3.7551404875511264e-05,
"loss": 4.0407,
"step": 760320
},
{
"epoch": 0.02,
"learning_rate": 3.7543018928000744e-05,
"loss": 4.0363,
"step": 760832
},
{
"epoch": 0.02,
"learning_rate": 3.7534632980490224e-05,
"loss": 4.0376,
"step": 761344
},
{
"epoch": 0.02,
"learning_rate": 3.7526247032979704e-05,
"loss": 4.0451,
"step": 761856
},
{
"epoch": 0.02,
"learning_rate": 3.7517861085469184e-05,
"loss": 4.0365,
"step": 762368
},
{
"epoch": 0.02,
"learning_rate": 3.7509475137958664e-05,
"loss": 4.0397,
"step": 762880
},
{
"epoch": 0.03,
"eval_loss": 4.068386077880859,
"eval_runtime": 292.9051,
"eval_samples_per_second": 1302.78,
"eval_steps_per_second": 40.713,
"step": 763200
},
{
"epoch": 1.0,
"learning_rate": 3.7501089190448144e-05,
"loss": 4.0339,
"step": 763392
},
{
"epoch": 1.0,
"learning_rate": 3.7492703242937624e-05,
"loss": 4.0324,
"step": 763904
},
{
"epoch": 1.0,
"learning_rate": 3.7484317295427104e-05,
"loss": 4.034,
"step": 764416
},
{
"epoch": 1.0,
"learning_rate": 3.747593134791659e-05,
"loss": 4.0425,
"step": 764928
},
{
"epoch": 1.0,
"learning_rate": 3.74675617792098e-05,
"loss": 4.0466,
"step": 765440
},
{
"epoch": 1.0,
"learning_rate": 3.745919221050301e-05,
"loss": 4.038,
"step": 765952
},
{
"epoch": 1.0,
"learning_rate": 3.745080626299249e-05,
"loss": 4.0354,
"step": 766464
},
{
"epoch": 1.0,
"learning_rate": 3.744242031548197e-05,
"loss": 4.0327,
"step": 766976
},
{
"epoch": 1.0,
"learning_rate": 3.743403436797145e-05,
"loss": 4.0327,
"step": 767488
},
{
"epoch": 1.0,
"learning_rate": 3.742566479926466e-05,
"loss": 4.0478,
"step": 768000
},
{
"epoch": 1.0,
"learning_rate": 3.741727885175414e-05,
"loss": 4.0355,
"step": 768512
},
{
"epoch": 1.0,
"learning_rate": 3.740889290424362e-05,
"loss": 4.0424,
"step": 769024
},
{
"epoch": 1.0,
"learning_rate": 3.74005069567331e-05,
"loss": 4.0413,
"step": 769536
},
{
"epoch": 1.0,
"learning_rate": 3.739212100922258e-05,
"loss": 4.0312,
"step": 770048
},
{
"epoch": 1.0,
"learning_rate": 3.7383751440515793e-05,
"loss": 4.0307,
"step": 770560
},
{
"epoch": 1.0,
"learning_rate": 3.737536549300527e-05,
"loss": 4.0295,
"step": 771072
},
{
"epoch": 1.0,
"learning_rate": 3.736697954549475e-05,
"loss": 4.0367,
"step": 771584
},
{
"epoch": 1.0,
"learning_rate": 3.735859359798423e-05,
"loss": 4.0318,
"step": 772096
},
{
"epoch": 1.0,
"learning_rate": 3.735022402927744e-05,
"loss": 4.0333,
"step": 772608
},
{
"epoch": 1.0,
"learning_rate": 3.734183808176692e-05,
"loss": 4.0384,
"step": 773120
},
{
"epoch": 1.0,
"learning_rate": 3.73334521342564e-05,
"loss": 4.0428,
"step": 773632
},
{
"epoch": 1.0,
"learning_rate": 3.732506618674588e-05,
"loss": 4.046,
"step": 774144
},
{
"epoch": 1.0,
"learning_rate": 3.731668023923536e-05,
"loss": 4.0398,
"step": 774656
},
{
"epoch": 1.0,
"learning_rate": 3.7308294291724835e-05,
"loss": 4.0316,
"step": 775168
},
{
"epoch": 1.0,
"learning_rate": 3.7299908344214315e-05,
"loss": 4.0382,
"step": 775680
},
{
"epoch": 1.0,
"learning_rate": 3.7291522396703795e-05,
"loss": 4.0401,
"step": 776192
},
{
"epoch": 1.0,
"learning_rate": 3.728315282799701e-05,
"loss": 4.031,
"step": 776704
},
{
"epoch": 1.0,
"learning_rate": 3.727476688048649e-05,
"loss": 4.0357,
"step": 777216
},
{
"epoch": 1.0,
"learning_rate": 3.726638093297597e-05,
"loss": 4.0325,
"step": 777728
},
{
"epoch": 1.0,
"learning_rate": 3.725799498546545e-05,
"loss": 4.0275,
"step": 778240
},
{
"epoch": 1.01,
"learning_rate": 3.724962541675866e-05,
"loss": 4.0288,
"step": 778752
},
{
"epoch": 1.01,
"learning_rate": 3.724123946924814e-05,
"loss": 4.0375,
"step": 779264
},
{
"epoch": 1.01,
"learning_rate": 3.723285352173762e-05,
"loss": 4.0417,
"step": 779776
},
{
"epoch": 1.01,
"learning_rate": 3.72244675742271e-05,
"loss": 4.0369,
"step": 780288
},
{
"epoch": 1.01,
"learning_rate": 3.721609800552031e-05,
"loss": 4.0408,
"step": 780800
},
{
"epoch": 1.01,
"learning_rate": 3.720771205800979e-05,
"loss": 4.0298,
"step": 781312
},
{
"epoch": 1.01,
"learning_rate": 3.719932611049927e-05,
"loss": 4.0447,
"step": 781824
},
{
"epoch": 1.01,
"learning_rate": 3.719094016298875e-05,
"loss": 4.0262,
"step": 782336
},
{
"epoch": 1.01,
"learning_rate": 3.7182554215478236e-05,
"loss": 4.0283,
"step": 782848
},
{
"epoch": 1.01,
"learning_rate": 3.7174168267967716e-05,
"loss": 4.023,
"step": 783360
},
{
"epoch": 1.01,
"learning_rate": 3.7165782320457196e-05,
"loss": 4.031,
"step": 783872
},
{
"epoch": 1.01,
"learning_rate": 3.7157412751750405e-05,
"loss": 4.0289,
"step": 784384
},
{
"epoch": 1.01,
"learning_rate": 3.7149026804239885e-05,
"loss": 4.0319,
"step": 784896
},
{
"epoch": 1.01,
"learning_rate": 3.7140640856729365e-05,
"loss": 4.0308,
"step": 785408
},
{
"epoch": 1.01,
"learning_rate": 3.7132254909218845e-05,
"loss": 4.0353,
"step": 785920
},
{
"epoch": 1.01,
"learning_rate": 3.7123868961708324e-05,
"loss": 4.0298,
"step": 786432
},
{
"epoch": 1.01,
"learning_rate": 3.7115499393001534e-05,
"loss": 4.0325,
"step": 786944
},
{
"epoch": 1.01,
"learning_rate": 3.7107113445491014e-05,
"loss": 4.0259,
"step": 787456
},
{
"epoch": 1.01,
"learning_rate": 3.7098727497980494e-05,
"loss": 4.0043,
"step": 787968
},
{
"epoch": 1.01,
"learning_rate": 3.7090341550469973e-05,
"loss": 4.041,
"step": 788480
},
{
"epoch": 1.01,
"learning_rate": 3.7081955602959453e-05,
"loss": 4.0263,
"step": 788992
},
{
"epoch": 1.01,
"learning_rate": 3.707356965544893e-05,
"loss": 4.0377,
"step": 789504
},
{
"epoch": 1.01,
"learning_rate": 3.706518370793842e-05,
"loss": 4.0251,
"step": 790016
},
{
"epoch": 1.01,
"learning_rate": 3.705681413923163e-05,
"loss": 4.0246,
"step": 790528
},
{
"epoch": 1.01,
"learning_rate": 3.704842819172111e-05,
"loss": 4.0202,
"step": 791040
},
{
"epoch": 1.01,
"learning_rate": 3.704004224421059e-05,
"loss": 4.0275,
"step": 791552
},
{
"epoch": 1.01,
"learning_rate": 3.703165629670007e-05,
"loss": 4.0237,
"step": 792064
},
{
"epoch": 1.01,
"learning_rate": 3.702327034918955e-05,
"loss": 4.0206,
"step": 792576
},
{
"epoch": 1.01,
"learning_rate": 3.701488440167902e-05,
"loss": 4.0403,
"step": 793088
},
{
"epoch": 1.01,
"learning_rate": 3.70064984541685e-05,
"loss": 4.022,
"step": 793600
},
{
"epoch": 1.01,
"learning_rate": 3.699811250665798e-05,
"loss": 4.0122,
"step": 794112
},
{
"epoch": 1.01,
"learning_rate": 3.69897429379512e-05,
"loss": 4.0337,
"step": 794624
},
{
"epoch": 1.01,
"learning_rate": 3.698135699044067e-05,
"loss": 4.0222,
"step": 795136
},
{
"epoch": 1.01,
"learning_rate": 3.697298742173389e-05,
"loss": 4.0184,
"step": 795648
},
{
"epoch": 1.01,
"learning_rate": 3.6964601474223374e-05,
"loss": 4.0316,
"step": 796160
},
{
"epoch": 1.01,
"learning_rate": 3.6956215526712854e-05,
"loss": 4.0253,
"step": 796672
},
{
"epoch": 1.01,
"learning_rate": 3.694782957920233e-05,
"loss": 4.0183,
"step": 797184
},
{
"epoch": 1.01,
"learning_rate": 3.693944363169181e-05,
"loss": 4.0324,
"step": 797696
},
{
"epoch": 1.01,
"learning_rate": 3.693107406298502e-05,
"loss": 4.0142,
"step": 798208
},
{
"epoch": 1.01,
"learning_rate": 3.6922688115474496e-05,
"loss": 4.0219,
"step": 798720
},
{
"epoch": 1.01,
"learning_rate": 3.6914302167963976e-05,
"loss": 4.0332,
"step": 799232
},
{
"epoch": 1.01,
"learning_rate": 3.6905916220453456e-05,
"loss": 4.0322,
"step": 799744
},
{
"epoch": 1.01,
"learning_rate": 3.6897530272942936e-05,
"loss": 4.0343,
"step": 800256
},
{
"epoch": 1.01,
"learning_rate": 3.6889144325432416e-05,
"loss": 4.0267,
"step": 800768
},
{
"epoch": 1.01,
"learning_rate": 3.6880758377921896e-05,
"loss": 4.0515,
"step": 801280
},
{
"epoch": 1.01,
"learning_rate": 3.687238880921511e-05,
"loss": 4.0201,
"step": 801792
},
{
"epoch": 1.01,
"learning_rate": 3.686400286170459e-05,
"loss": 4.0346,
"step": 802304
},
{
"epoch": 1.01,
"learning_rate": 3.685561691419407e-05,
"loss": 4.0286,
"step": 802816
},
{
"epoch": 1.01,
"learning_rate": 3.684723096668355e-05,
"loss": 4.0263,
"step": 803328
},
{
"epoch": 1.01,
"learning_rate": 3.683886139797676e-05,
"loss": 4.0208,
"step": 803840
},
{
"epoch": 1.01,
"learning_rate": 3.683047545046624e-05,
"loss": 4.0389,
"step": 804352
},
{
"epoch": 1.01,
"learning_rate": 3.682208950295572e-05,
"loss": 4.0299,
"step": 804864
},
{
"epoch": 1.01,
"learning_rate": 3.68137035554452e-05,
"loss": 4.0417,
"step": 805376
},
{
"epoch": 1.01,
"learning_rate": 3.680531760793468e-05,
"loss": 4.0101,
"step": 805888
},
{
"epoch": 1.01,
"learning_rate": 3.679693166042416e-05,
"loss": 4.0167,
"step": 806400
},
{
"epoch": 1.01,
"learning_rate": 3.678854571291364e-05,
"loss": 4.0278,
"step": 806912
},
{
"epoch": 1.01,
"learning_rate": 3.678015976540312e-05,
"loss": 4.0359,
"step": 807424
},
{
"epoch": 1.01,
"learning_rate": 3.677179019669633e-05,
"loss": 4.0246,
"step": 807936
},
{
"epoch": 1.01,
"learning_rate": 3.676340424918581e-05,
"loss": 4.0293,
"step": 808448
},
{
"epoch": 1.01,
"learning_rate": 3.675501830167529e-05,
"loss": 4.0196,
"step": 808960
},
{
"epoch": 1.02,
"learning_rate": 3.6746632354164776e-05,
"loss": 4.0207,
"step": 809472
},
{
"epoch": 1.02,
"learning_rate": 3.6738246406654256e-05,
"loss": 4.0238,
"step": 809984
},
{
"epoch": 1.02,
"learning_rate": 3.6729876837947465e-05,
"loss": 4.019,
"step": 810496
},
{
"epoch": 1.02,
"learning_rate": 3.6721490890436945e-05,
"loss": 4.0318,
"step": 811008
},
{
"epoch": 1.02,
"learning_rate": 3.6713104942926425e-05,
"loss": 4.04,
"step": 811520
},
{
"epoch": 1.02,
"learning_rate": 3.6704735374219634e-05,
"loss": 4.0361,
"step": 812032
},
{
"epoch": 1.02,
"learning_rate": 3.6696349426709114e-05,
"loss": 4.0205,
"step": 812544
},
{
"epoch": 1.02,
"learning_rate": 3.6687963479198594e-05,
"loss": 4.0149,
"step": 813056
},
{
"epoch": 1.02,
"learning_rate": 3.6679577531688074e-05,
"loss": 4.0234,
"step": 813568
},
{
"epoch": 1.02,
"learning_rate": 3.6671191584177554e-05,
"loss": 4.0272,
"step": 814080
},
{
"epoch": 1.02,
"learning_rate": 3.666282201547076e-05,
"loss": 4.0313,
"step": 814592
},
{
"epoch": 1.02,
"learning_rate": 3.665443606796024e-05,
"loss": 4.0269,
"step": 815104
},
{
"epoch": 1.02,
"learning_rate": 3.664605012044973e-05,
"loss": 4.0299,
"step": 815616
},
{
"epoch": 1.02,
"learning_rate": 3.663766417293921e-05,
"loss": 4.0167,
"step": 816128
},
{
"epoch": 1.02,
"learning_rate": 3.662927822542868e-05,
"loss": 4.0204,
"step": 816640
},
{
"epoch": 1.02,
"learning_rate": 3.662089227791816e-05,
"loss": 4.0157,
"step": 817152
},
{
"epoch": 1.02,
"learning_rate": 3.661250633040764e-05,
"loss": 4.0175,
"step": 817664
},
{
"epoch": 1.02,
"learning_rate": 3.660412038289712e-05,
"loss": 4.0267,
"step": 818176
},
{
"epoch": 1.02,
"learning_rate": 3.659575081419033e-05,
"loss": 4.0262,
"step": 818688
},
{
"epoch": 1.02,
"learning_rate": 3.658736486667981e-05,
"loss": 4.0152,
"step": 819200
},
{
"epoch": 1.02,
"learning_rate": 3.657899529797303e-05,
"loss": 4.0161,
"step": 819712
},
{
"epoch": 1.02,
"learning_rate": 3.657060935046251e-05,
"loss": 4.0103,
"step": 820224
},
{
"epoch": 1.02,
"learning_rate": 3.656222340295198e-05,
"loss": 4.0251,
"step": 820736
},
{
"epoch": 1.02,
"learning_rate": 3.655383745544147e-05,
"loss": 4.02,
"step": 821248
},
{
"epoch": 1.02,
"learning_rate": 3.654545150793095e-05,
"loss": 4.0334,
"step": 821760
},
{
"epoch": 1.02,
"learning_rate": 3.653706556042043e-05,
"loss": 4.0314,
"step": 822272
},
{
"epoch": 1.02,
"learning_rate": 3.6528695991713636e-05,
"loss": 4.0326,
"step": 822784
},
{
"epoch": 1.02,
"learning_rate": 3.652032642300685e-05,
"loss": 4.0222,
"step": 823296
},
{
"epoch": 1.02,
"learning_rate": 3.651194047549633e-05,
"loss": 4.0185,
"step": 823808
},
{
"epoch": 1.02,
"learning_rate": 3.6503554527985805e-05,
"loss": 4.0258,
"step": 824320
},
{
"epoch": 1.02,
"learning_rate": 3.6495168580475285e-05,
"loss": 4.0298,
"step": 824832
},
{
"epoch": 1.02,
"learning_rate": 3.6486782632964765e-05,
"loss": 4.0195,
"step": 825344
},
{
"epoch": 1.02,
"learning_rate": 3.6478396685454245e-05,
"loss": 4.0133,
"step": 825856
},
{
"epoch": 1.02,
"learning_rate": 3.6470010737943725e-05,
"loss": 4.0261,
"step": 826368
},
{
"epoch": 1.02,
"learning_rate": 3.6461624790433205e-05,
"loss": 4.0182,
"step": 826880
},
{
"epoch": 1.02,
"learning_rate": 3.6453238842922685e-05,
"loss": 4.017,
"step": 827392
},
{
"epoch": 1.02,
"learning_rate": 3.6444852895412165e-05,
"loss": 4.0102,
"step": 827904
},
{
"epoch": 1.02,
"learning_rate": 3.643646694790165e-05,
"loss": 4.0271,
"step": 828416
},
{
"epoch": 1.02,
"learning_rate": 3.642808100039113e-05,
"loss": 4.0078,
"step": 828928
},
{
"epoch": 1.02,
"learning_rate": 3.641971143168434e-05,
"loss": 4.0304,
"step": 829440
},
{
"epoch": 1.02,
"learning_rate": 3.641132548417382e-05,
"loss": 4.0232,
"step": 829952
},
{
"epoch": 1.02,
"learning_rate": 3.64029395366633e-05,
"loss": 4.0337,
"step": 830464
},
{
"epoch": 1.02,
"learning_rate": 3.639455358915278e-05,
"loss": 4.0105,
"step": 830976
},
{
"epoch": 1.02,
"learning_rate": 3.638620039924972e-05,
"loss": 4.0299,
"step": 831488
},
{
"epoch": 1.02,
"learning_rate": 3.63778144517392e-05,
"loss": 4.0265,
"step": 832000
},
{
"epoch": 1.02,
"learning_rate": 3.636942850422868e-05,
"loss": 4.0259,
"step": 832512
},
{
"epoch": 1.02,
"learning_rate": 3.636104255671816e-05,
"loss": 4.0247,
"step": 833024
},
{
"epoch": 1.02,
"learning_rate": 3.635265660920764e-05,
"loss": 4.0188,
"step": 833536
},
{
"epoch": 1.02,
"learning_rate": 3.634427066169712e-05,
"loss": 4.021,
"step": 834048
},
{
"epoch": 1.02,
"learning_rate": 3.63358847141866e-05,
"loss": 4.0363,
"step": 834560
},
{
"epoch": 1.02,
"learning_rate": 3.6327515145479815e-05,
"loss": 4.0116,
"step": 835072
},
{
"epoch": 1.02,
"learning_rate": 3.6319129197969295e-05,
"loss": 4.028,
"step": 835584
},
{
"epoch": 1.02,
"learning_rate": 3.6310743250458775e-05,
"loss": 4.0253,
"step": 836096
},
{
"epoch": 1.02,
"learning_rate": 3.6302357302948254e-05,
"loss": 4.018,
"step": 836608
},
{
"epoch": 1.02,
"learning_rate": 3.6293971355437734e-05,
"loss": 4.0175,
"step": 837120
},
{
"epoch": 1.02,
"learning_rate": 3.6285585407927214e-05,
"loss": 4.021,
"step": 837632
},
{
"epoch": 1.02,
"learning_rate": 3.6277215839220423e-05,
"loss": 4.0214,
"step": 838144
},
{
"epoch": 1.02,
"learning_rate": 3.6268829891709903e-05,
"loss": 4.0215,
"step": 838656
},
{
"epoch": 1.02,
"learning_rate": 3.6260443944199383e-05,
"loss": 4.0162,
"step": 839168
},
{
"epoch": 1.03,
"eval_loss": 4.0550336837768555,
"eval_runtime": 292.8718,
"eval_samples_per_second": 1302.928,
"eval_steps_per_second": 40.717,
"step": 839520
},
{
"epoch": 0.0,
"learning_rate": 3.625205799668886e-05,
"loss": 4.0096,
"step": 839680
},
{
"epoch": 0.0,
"learning_rate": 3.6243672049178337e-05,
"loss": 4.0132,
"step": 840192
},
{
"epoch": 0.0,
"learning_rate": 3.623528610166782e-05,
"loss": 4.0137,
"step": 840704
},
{
"epoch": 0.0,
"learning_rate": 3.62269001541573e-05,
"loss": 4.0235,
"step": 841216
},
{
"epoch": 0.0,
"learning_rate": 3.621851420664678e-05,
"loss": 4.0241,
"step": 841728
},
{
"epoch": 0.0,
"learning_rate": 3.621012825913626e-05,
"loss": 4.0186,
"step": 842240
},
{
"epoch": 0.0,
"learning_rate": 3.620174231162574e-05,
"loss": 4.0166,
"step": 842752
},
{
"epoch": 0.0,
"learning_rate": 3.619335636411522e-05,
"loss": 4.0157,
"step": 843264
},
{
"epoch": 0.0,
"learning_rate": 3.61849704166047e-05,
"loss": 4.0097,
"step": 843776
},
{
"epoch": 0.0,
"learning_rate": 3.617658446909418e-05,
"loss": 4.0256,
"step": 844288
},
{
"epoch": 0.0,
"learning_rate": 3.616819852158366e-05,
"loss": 4.0199,
"step": 844800
},
{
"epoch": 0.0,
"learning_rate": 3.615981257407314e-05,
"loss": 4.0242,
"step": 845312
},
{
"epoch": 0.0,
"learning_rate": 3.615142662656262e-05,
"loss": 4.0205,
"step": 845824
},
{
"epoch": 0.0,
"learning_rate": 3.61430406790521e-05,
"loss": 4.009,
"step": 846336
},
{
"epoch": 0.0,
"learning_rate": 3.613465473154158e-05,
"loss": 4.0138,
"step": 846848
},
{
"epoch": 0.0,
"learning_rate": 3.6126268784031056e-05,
"loss": 4.0046,
"step": 847360
},
{
"epoch": 0.0,
"learning_rate": 3.6117882836520536e-05,
"loss": 4.0202,
"step": 847872
},
{
"epoch": 0.0,
"learning_rate": 3.610949688901002e-05,
"loss": 4.0147,
"step": 848384
},
{
"epoch": 0.0,
"learning_rate": 3.610112732030323e-05,
"loss": 4.0107,
"step": 848896
},
{
"epoch": 0.0,
"learning_rate": 3.609274137279271e-05,
"loss": 4.0168,
"step": 849408
},
{
"epoch": 0.0,
"learning_rate": 3.608435542528219e-05,
"loss": 4.0233,
"step": 849920
},
{
"epoch": 0.0,
"learning_rate": 3.607596947777167e-05,
"loss": 4.0274,
"step": 850432
},
{
"epoch": 0.0,
"learning_rate": 3.606758353026115e-05,
"loss": 4.0203,
"step": 850944
},
{
"epoch": 0.0,
"learning_rate": 3.605919758275063e-05,
"loss": 4.0147,
"step": 851456
},
{
"epoch": 0.0,
"learning_rate": 3.605082801404384e-05,
"loss": 4.0185,
"step": 851968
},
{
"epoch": 0.0,
"learning_rate": 3.604244206653332e-05,
"loss": 4.02,
"step": 852480
},
{
"epoch": 0.0,
"learning_rate": 3.60340561190228e-05,
"loss": 4.0079,
"step": 852992
},
{
"epoch": 0.0,
"learning_rate": 3.602567017151228e-05,
"loss": 4.0134,
"step": 853504
},
{
"epoch": 0.0,
"learning_rate": 3.601730060280549e-05,
"loss": 4.0138,
"step": 854016
},
{
"epoch": 0.0,
"learning_rate": 3.6008914655294976e-05,
"loss": 4.0074,
"step": 854528
},
{
"epoch": 0.01,
"learning_rate": 3.6000528707784456e-05,
"loss": 4.0111,
"step": 855040
},
{
"epoch": 0.01,
"learning_rate": 3.5992142760273936e-05,
"loss": 4.0182,
"step": 855552
},
{
"epoch": 0.01,
"learning_rate": 3.5983756812763416e-05,
"loss": 4.0156,
"step": 856064
},
{
"epoch": 0.01,
"learning_rate": 3.5975370865252896e-05,
"loss": 4.0278,
"step": 856576
},
{
"epoch": 0.01,
"learning_rate": 3.5967001296546105e-05,
"loss": 4.0131,
"step": 857088
},
{
"epoch": 0.01,
"learning_rate": 3.5958615349035585e-05,
"loss": 4.0152,
"step": 857600
},
{
"epoch": 0.01,
"learning_rate": 3.5950229401525065e-05,
"loss": 4.0274,
"step": 858112
},
{
"epoch": 0.01,
"learning_rate": 3.5941843454014545e-05,
"loss": 4.0046,
"step": 858624
},
{
"epoch": 0.01,
"learning_rate": 3.5933457506504025e-05,
"loss": 4.0099,
"step": 859136
},
{
"epoch": 0.01,
"learning_rate": 3.5925071558993505e-05,
"loss": 4.0037,
"step": 859648
},
{
"epoch": 0.01,
"learning_rate": 3.5916685611482985e-05,
"loss": 4.0127,
"step": 860160
},
{
"epoch": 0.01,
"learning_rate": 3.5908316042776194e-05,
"loss": 4.0095,
"step": 860672
},
{
"epoch": 0.01,
"learning_rate": 3.5899930095265674e-05,
"loss": 4.0088,
"step": 861184
},
{
"epoch": 0.01,
"learning_rate": 3.5891544147755154e-05,
"loss": 4.0137,
"step": 861696
},
{
"epoch": 0.01,
"learning_rate": 3.588315820024464e-05,
"loss": 4.0116,
"step": 862208
},
{
"epoch": 0.01,
"learning_rate": 3.587477225273412e-05,
"loss": 4.0164,
"step": 862720
},
{
"epoch": 0.01,
"learning_rate": 3.5866386305223594e-05,
"loss": 4.0083,
"step": 863232
},
{
"epoch": 0.01,
"learning_rate": 3.585801673651681e-05,
"loss": 4.0086,
"step": 863744
},
{
"epoch": 0.01,
"learning_rate": 3.584963078900629e-05,
"loss": 3.9826,
"step": 864256
},
{
"epoch": 0.01,
"learning_rate": 3.584124484149577e-05,
"loss": 4.0214,
"step": 864768
},
{
"epoch": 0.01,
"learning_rate": 3.583285889398524e-05,
"loss": 4.0064,
"step": 865280
},
{
"epoch": 0.01,
"learning_rate": 3.582447294647472e-05,
"loss": 4.0165,
"step": 865792
},
{
"epoch": 0.01,
"learning_rate": 3.581610337776794e-05,
"loss": 4.0066,
"step": 866304
},
{
"epoch": 0.01,
"learning_rate": 3.580771743025742e-05,
"loss": 4.0024,
"step": 866816
},
{
"epoch": 0.01,
"learning_rate": 3.579933148274689e-05,
"loss": 4.0015,
"step": 867328
},
{
"epoch": 0.01,
"learning_rate": 3.579096191404011e-05,
"loss": 4.0059,
"step": 867840
},
{
"epoch": 0.01,
"learning_rate": 3.5782575966529594e-05,
"loss": 4.009,
"step": 868352
},
{
"epoch": 0.01,
"learning_rate": 3.577419001901907e-05,
"loss": 3.9983,
"step": 868864
},
{
"epoch": 0.01,
"learning_rate": 3.576580407150855e-05,
"loss": 4.0205,
"step": 869376
},
{
"epoch": 0.01,
"learning_rate": 3.575741812399803e-05,
"loss": 4.0056,
"step": 869888
},
{
"epoch": 0.01,
"learning_rate": 3.574903217648751e-05,
"loss": 3.9896,
"step": 870400
},
{
"epoch": 0.01,
"learning_rate": 3.574064622897699e-05,
"loss": 4.0169,
"step": 870912
},
{
"epoch": 0.01,
"learning_rate": 3.573226028146647e-05,
"loss": 4.0067,
"step": 871424
},
{
"epoch": 0.01,
"learning_rate": 3.572387433395595e-05,
"loss": 3.9982,
"step": 871936
},
{
"epoch": 0.01,
"learning_rate": 3.571548838644543e-05,
"loss": 4.0091,
"step": 872448
},
{
"epoch": 0.01,
"learning_rate": 3.5707118817738636e-05,
"loss": 4.0077,
"step": 872960
},
{
"epoch": 0.01,
"learning_rate": 3.5698732870228116e-05,
"loss": 3.9994,
"step": 873472
},
{
"epoch": 0.01,
"learning_rate": 3.5690346922717596e-05,
"loss": 4.015,
"step": 873984
},
{
"epoch": 0.01,
"learning_rate": 3.5681960975207076e-05,
"loss": 3.9955,
"step": 874496
},
{
"epoch": 0.01,
"learning_rate": 3.567357502769656e-05,
"loss": 3.9987,
"step": 875008
},
{
"epoch": 0.01,
"learning_rate": 3.566520545898977e-05,
"loss": 4.0165,
"step": 875520
},
{
"epoch": 0.01,
"learning_rate": 3.565681951147925e-05,
"loss": 4.0086,
"step": 876032
},
{
"epoch": 0.01,
"learning_rate": 3.564843356396873e-05,
"loss": 4.0153,
"step": 876544
},
{
"epoch": 0.01,
"learning_rate": 3.564004761645821e-05,
"loss": 4.0099,
"step": 877056
},
{
"epoch": 0.01,
"learning_rate": 3.563166166894769e-05,
"loss": 4.025,
"step": 877568
},
{
"epoch": 0.01,
"learning_rate": 3.562327572143717e-05,
"loss": 4.0044,
"step": 878080
},
{
"epoch": 0.01,
"learning_rate": 3.561488977392665e-05,
"loss": 4.0172,
"step": 878592
},
{
"epoch": 0.01,
"learning_rate": 3.560650382641613e-05,
"loss": 4.0054,
"step": 879104
},
{
"epoch": 0.01,
"learning_rate": 3.559813425770934e-05,
"loss": 4.0077,
"step": 879616
},
{
"epoch": 0.01,
"learning_rate": 3.558974831019882e-05,
"loss": 4.0044,
"step": 880128
},
{
"epoch": 0.01,
"learning_rate": 3.55813623626883e-05,
"loss": 4.017,
"step": 880640
},
{
"epoch": 0.01,
"learning_rate": 3.557297641517778e-05,
"loss": 4.013,
"step": 881152
},
{
"epoch": 0.01,
"learning_rate": 3.5564606846470997e-05,
"loss": 4.0254,
"step": 881664
},
{
"epoch": 0.01,
"learning_rate": 3.5556237277764206e-05,
"loss": 3.9945,
"step": 882176
},
{
"epoch": 0.01,
"learning_rate": 3.5547851330253686e-05,
"loss": 3.9964,
"step": 882688
},
{
"epoch": 0.01,
"learning_rate": 3.5539481761546895e-05,
"loss": 4.0079,
"step": 883200
},
{
"epoch": 0.01,
"learning_rate": 3.5531095814036375e-05,
"loss": 4.0158,
"step": 883712
},
{
"epoch": 0.01,
"learning_rate": 3.5522709866525855e-05,
"loss": 4.0049,
"step": 884224
},
{
"epoch": 0.01,
"learning_rate": 3.5514323919015335e-05,
"loss": 4.015,
"step": 884736
},
{
"epoch": 0.01,
"learning_rate": 3.5505937971504814e-05,
"loss": 4.0035,
"step": 885248
},
{
"epoch": 0.02,
"learning_rate": 3.5497552023994294e-05,
"loss": 3.9976,
"step": 885760
},
{
"epoch": 0.02,
"learning_rate": 3.5489166076483774e-05,
"loss": 4.0046,
"step": 886272
},
{
"epoch": 0.02,
"learning_rate": 3.5480780128973254e-05,
"loss": 4.0002,
"step": 886784
},
{
"epoch": 0.02,
"learning_rate": 3.547241056026647e-05,
"loss": 4.0135,
"step": 887296
},
{
"epoch": 0.02,
"learning_rate": 3.546402461275595e-05,
"loss": 4.0166,
"step": 887808
},
{
"epoch": 0.02,
"learning_rate": 3.545563866524543e-05,
"loss": 4.0204,
"step": 888320
},
{
"epoch": 0.02,
"learning_rate": 3.54472527177349e-05,
"loss": 3.996,
"step": 888832
},
{
"epoch": 0.02,
"learning_rate": 3.543886677022438e-05,
"loss": 4.0004,
"step": 889344
},
{
"epoch": 0.02,
"learning_rate": 3.543048082271386e-05,
"loss": 4.006,
"step": 889856
},
{
"epoch": 0.02,
"learning_rate": 3.542209487520334e-05,
"loss": 4.0098,
"step": 890368
},
{
"epoch": 0.02,
"learning_rate": 3.541372530649655e-05,
"loss": 4.0096,
"step": 890880
},
{
"epoch": 0.02,
"learning_rate": 3.540533935898603e-05,
"loss": 4.0108,
"step": 891392
},
{
"epoch": 0.02,
"learning_rate": 3.539695341147551e-05,
"loss": 4.0097,
"step": 891904
},
{
"epoch": 0.02,
"learning_rate": 3.538856746396499e-05,
"loss": 3.998,
"step": 892416
},
{
"epoch": 0.02,
"learning_rate": 3.538018151645447e-05,
"loss": 4.0054,
"step": 892928
},
{
"epoch": 0.02,
"learning_rate": 3.537179556894395e-05,
"loss": 3.9949,
"step": 893440
},
{
"epoch": 0.02,
"learning_rate": 3.536340962143343e-05,
"loss": 4.0012,
"step": 893952
},
{
"epoch": 0.02,
"learning_rate": 3.535504005272665e-05,
"loss": 4.0048,
"step": 894464
},
{
"epoch": 0.02,
"learning_rate": 3.534665410521613e-05,
"loss": 4.0085,
"step": 894976
},
{
"epoch": 0.02,
"learning_rate": 3.533826815770561e-05,
"loss": 3.9984,
"step": 895488
},
{
"epoch": 0.02,
"learning_rate": 3.532988221019509e-05,
"loss": 4.0,
"step": 896000
},
{
"epoch": 0.02,
"learning_rate": 3.532149626268457e-05,
"loss": 3.9888,
"step": 896512
},
{
"epoch": 0.02,
"learning_rate": 3.531311031517405e-05,
"loss": 4.0122,
"step": 897024
},
{
"epoch": 0.02,
"learning_rate": 3.530472436766353e-05,
"loss": 3.9985,
"step": 897536
},
{
"epoch": 0.02,
"learning_rate": 3.529633842015301e-05,
"loss": 4.0152,
"step": 898048
},
{
"epoch": 0.02,
"learning_rate": 3.528796885144622e-05,
"loss": 4.0089,
"step": 898560
},
{
"epoch": 0.02,
"learning_rate": 3.52795829039357e-05,
"loss": 4.0139,
"step": 899072
},
{
"epoch": 0.02,
"learning_rate": 3.5271213335228906e-05,
"loss": 4.004,
"step": 899584
},
{
"epoch": 0.02,
"learning_rate": 3.5262827387718386e-05,
"loss": 3.9989,
"step": 900096
},
{
"epoch": 0.02,
"learning_rate": 3.525444144020787e-05,
"loss": 4.0118,
"step": 900608
},
{
"epoch": 0.02,
"learning_rate": 3.524605549269735e-05,
"loss": 4.0081,
"step": 901120
},
{
"epoch": 0.02,
"learning_rate": 3.523766954518683e-05,
"loss": 4.0038,
"step": 901632
},
{
"epoch": 0.02,
"learning_rate": 3.522929997648004e-05,
"loss": 3.9954,
"step": 902144
},
{
"epoch": 0.02,
"learning_rate": 3.522091402896952e-05,
"loss": 4.0044,
"step": 902656
},
{
"epoch": 0.02,
"learning_rate": 3.5212528081459e-05,
"loss": 3.999,
"step": 903168
},
{
"epoch": 0.02,
"learning_rate": 3.520414213394848e-05,
"loss": 3.9997,
"step": 903680
},
{
"epoch": 0.02,
"learning_rate": 3.519577256524169e-05,
"loss": 3.9919,
"step": 904192
},
{
"epoch": 0.02,
"learning_rate": 3.518738661773117e-05,
"loss": 4.0067,
"step": 904704
},
{
"epoch": 0.02,
"learning_rate": 3.517900067022065e-05,
"loss": 3.9897,
"step": 905216
},
{
"epoch": 0.02,
"learning_rate": 3.517061472271013e-05,
"loss": 4.0149,
"step": 905728
},
{
"epoch": 0.02,
"learning_rate": 3.516222877519961e-05,
"loss": 4.0036,
"step": 906240
},
{
"epoch": 0.02,
"learning_rate": 3.515384282768909e-05,
"loss": 4.0176,
"step": 906752
},
{
"epoch": 0.02,
"learning_rate": 3.5145473258982306e-05,
"loss": 3.9943,
"step": 907264
},
{
"epoch": 0.02,
"learning_rate": 3.5137087311471786e-05,
"loss": 4.012,
"step": 907776
},
{
"epoch": 0.02,
"learning_rate": 3.5128701363961266e-05,
"loss": 4.0065,
"step": 908288
},
{
"epoch": 0.02,
"learning_rate": 3.512031541645074e-05,
"loss": 4.0065,
"step": 908800
},
{
"epoch": 0.02,
"learning_rate": 3.511192946894022e-05,
"loss": 4.0091,
"step": 909312
},
{
"epoch": 0.02,
"learning_rate": 3.51035435214297e-05,
"loss": 4.0015,
"step": 909824
},
{
"epoch": 0.02,
"learning_rate": 3.509515757391918e-05,
"loss": 4.0049,
"step": 910336
},
{
"epoch": 0.02,
"learning_rate": 3.508677162640866e-05,
"loss": 4.018,
"step": 910848
},
{
"epoch": 0.02,
"learning_rate": 3.507840205770187e-05,
"loss": 3.9955,
"step": 911360
},
{
"epoch": 0.02,
"learning_rate": 3.507001611019135e-05,
"loss": 4.0108,
"step": 911872
},
{
"epoch": 0.02,
"learning_rate": 3.5061646541484564e-05,
"loss": 4.0087,
"step": 912384
},
{
"epoch": 0.02,
"learning_rate": 3.5053260593974044e-05,
"loss": 3.9996,
"step": 912896
},
{
"epoch": 0.02,
"learning_rate": 3.504489102526726e-05,
"loss": 4.0009,
"step": 913408
},
{
"epoch": 0.02,
"learning_rate": 3.503650507775674e-05,
"loss": 3.9992,
"step": 913920
},
{
"epoch": 0.02,
"learning_rate": 3.502811913024621e-05,
"loss": 4.0015,
"step": 914432
},
{
"epoch": 0.02,
"learning_rate": 3.501973318273569e-05,
"loss": 4.0012,
"step": 914944
},
{
"epoch": 0.02,
"learning_rate": 3.501134723522517e-05,
"loss": 3.9985,
"step": 915456
},
{
"epoch": 0.03,
"eval_loss": 4.043628692626953,
"eval_runtime": 312.5698,
"eval_samples_per_second": 1220.819,
"eval_steps_per_second": 38.151,
"step": 915840
},
{
"epoch": 1.0,
"learning_rate": 3.500296128771465e-05,
"loss": 4.0016,
"step": 915968
},
{
"epoch": 1.0,
"learning_rate": 3.499457534020413e-05,
"loss": 3.9909,
"step": 916480
},
{
"epoch": 1.0,
"learning_rate": 3.498618939269361e-05,
"loss": 3.9951,
"step": 916992
},
{
"epoch": 1.0,
"learning_rate": 3.497780344518309e-05,
"loss": 4.0078,
"step": 917504
},
{
"epoch": 1.0,
"learning_rate": 3.496941749767257e-05,
"loss": 4.0023,
"step": 918016
},
{
"epoch": 1.0,
"learning_rate": 3.496103155016205e-05,
"loss": 4.0026,
"step": 918528
},
{
"epoch": 1.0,
"learning_rate": 3.495264560265153e-05,
"loss": 4.0028,
"step": 919040
},
{
"epoch": 1.0,
"learning_rate": 3.494429241274848e-05,
"loss": 3.9973,
"step": 919552
},
{
"epoch": 1.0,
"learning_rate": 3.493590646523796e-05,
"loss": 3.9933,
"step": 920064
},
{
"epoch": 1.0,
"learning_rate": 3.492752051772744e-05,
"loss": 4.0028,
"step": 920576
},
{
"epoch": 1.0,
"learning_rate": 3.491913457021692e-05,
"loss": 4.0056,
"step": 921088
},
{
"epoch": 1.0,
"learning_rate": 3.49107486227064e-05,
"loss": 4.0046,
"step": 921600
},
{
"epoch": 1.0,
"learning_rate": 3.490236267519588e-05,
"loss": 4.0042,
"step": 922112
},
{
"epoch": 1.0,
"learning_rate": 3.489397672768536e-05,
"loss": 3.9888,
"step": 922624
},
{
"epoch": 1.0,
"learning_rate": 3.488559078017484e-05,
"loss": 3.9981,
"step": 923136
},
{
"epoch": 1.0,
"learning_rate": 3.4877221211468046e-05,
"loss": 3.9876,
"step": 923648
},
{
"epoch": 1.0,
"learning_rate": 3.4868835263957526e-05,
"loss": 4.0017,
"step": 924160
},
{
"epoch": 1.0,
"learning_rate": 3.4860449316447006e-05,
"loss": 3.9976,
"step": 924672
},
{
"epoch": 1.0,
"learning_rate": 3.4852063368936486e-05,
"loss": 3.9919,
"step": 925184
},
{
"epoch": 1.0,
"learning_rate": 3.48436938002297e-05,
"loss": 4.0014,
"step": 925696
},
{
"epoch": 1.0,
"learning_rate": 3.483530785271918e-05,
"loss": 4.004,
"step": 926208
},
{
"epoch": 1.0,
"learning_rate": 3.482692190520866e-05,
"loss": 4.0093,
"step": 926720
},
{
"epoch": 1.0,
"learning_rate": 3.481853595769814e-05,
"loss": 4.003,
"step": 927232
},
{
"epoch": 1.0,
"learning_rate": 3.481015001018762e-05,
"loss": 3.9957,
"step": 927744
},
{
"epoch": 1.0,
"learning_rate": 3.48017640626771e-05,
"loss": 4.002,
"step": 928256
},
{
"epoch": 1.0,
"learning_rate": 3.4793378115166575e-05,
"loss": 4.0037,
"step": 928768
},
{
"epoch": 1.0,
"learning_rate": 3.4784992167656055e-05,
"loss": 3.9921,
"step": 929280
},
{
"epoch": 1.0,
"learning_rate": 3.4776606220145535e-05,
"loss": 3.9958,
"step": 929792
},
{
"epoch": 1.0,
"learning_rate": 3.4768236651438744e-05,
"loss": 3.9956,
"step": 930304
},
{
"epoch": 1.0,
"learning_rate": 3.4759850703928224e-05,
"loss": 3.9899,
"step": 930816
},
{
"epoch": 1.01,
"learning_rate": 3.4751464756417704e-05,
"loss": 3.9982,
"step": 931328
},
{
"epoch": 1.01,
"learning_rate": 3.4743078808907184e-05,
"loss": 3.9982,
"step": 931840
},
{
"epoch": 1.01,
"learning_rate": 3.47347092402004e-05,
"loss": 3.9981,
"step": 932352
},
{
"epoch": 1.01,
"learning_rate": 3.472632329268988e-05,
"loss": 4.0096,
"step": 932864
},
{
"epoch": 1.01,
"learning_rate": 3.471793734517936e-05,
"loss": 3.9978,
"step": 933376
},
{
"epoch": 1.01,
"learning_rate": 3.470955139766884e-05,
"loss": 3.9982,
"step": 933888
},
{
"epoch": 1.01,
"learning_rate": 3.470118182896205e-05,
"loss": 4.0065,
"step": 934400
},
{
"epoch": 1.01,
"learning_rate": 3.469279588145153e-05,
"loss": 3.9857,
"step": 934912
},
{
"epoch": 1.01,
"learning_rate": 3.468440993394101e-05,
"loss": 3.992,
"step": 935424
},
{
"epoch": 1.01,
"learning_rate": 3.467602398643049e-05,
"loss": 3.9916,
"step": 935936
},
{
"epoch": 1.01,
"learning_rate": 3.466763803891997e-05,
"loss": 3.9899,
"step": 936448
},
{
"epoch": 1.01,
"learning_rate": 3.465926847021318e-05,
"loss": 3.9901,
"step": 936960
},
{
"epoch": 1.01,
"learning_rate": 3.465088252270266e-05,
"loss": 3.9949,
"step": 937472
},
{
"epoch": 1.01,
"learning_rate": 3.464249657519214e-05,
"loss": 3.9979,
"step": 937984
},
{
"epoch": 1.01,
"learning_rate": 3.463412700648535e-05,
"loss": 3.9941,
"step": 938496
},
{
"epoch": 1.01,
"learning_rate": 3.462574105897483e-05,
"loss": 4.0015,
"step": 939008
},
{
"epoch": 1.01,
"learning_rate": 3.461735511146431e-05,
"loss": 3.9922,
"step": 939520
},
{
"epoch": 1.01,
"learning_rate": 3.460896916395379e-05,
"loss": 3.9921,
"step": 940032
},
{
"epoch": 1.01,
"learning_rate": 3.460058321644327e-05,
"loss": 3.9693,
"step": 940544
},
{
"epoch": 1.01,
"learning_rate": 3.459219726893275e-05,
"loss": 4.0048,
"step": 941056
},
{
"epoch": 1.01,
"learning_rate": 3.458381132142223e-05,
"loss": 3.9858,
"step": 941568
},
{
"epoch": 1.01,
"learning_rate": 3.457542537391171e-05,
"loss": 3.9972,
"step": 942080
},
{
"epoch": 1.01,
"learning_rate": 3.456703942640119e-05,
"loss": 3.9879,
"step": 942592
},
{
"epoch": 1.01,
"learning_rate": 3.455865347889067e-05,
"loss": 3.986,
"step": 943104
},
{
"epoch": 1.01,
"learning_rate": 3.455026753138015e-05,
"loss": 3.9858,
"step": 943616
},
{
"epoch": 1.01,
"learning_rate": 3.454189796267336e-05,
"loss": 3.9883,
"step": 944128
},
{
"epoch": 1.01,
"learning_rate": 3.453351201516284e-05,
"loss": 3.9942,
"step": 944640
},
{
"epoch": 1.01,
"learning_rate": 3.452512606765232e-05,
"loss": 3.9794,
"step": 945152
},
{
"epoch": 1.01,
"learning_rate": 3.45167401201418e-05,
"loss": 4.004,
"step": 945664
},
{
"epoch": 1.01,
"learning_rate": 3.450837055143502e-05,
"loss": 3.9899,
"step": 946176
},
{
"epoch": 1.01,
"learning_rate": 3.44999846039245e-05,
"loss": 3.9742,
"step": 946688
},
{
"epoch": 1.01,
"learning_rate": 3.449159865641398e-05,
"loss": 3.9967,
"step": 947200
},
{
"epoch": 1.01,
"learning_rate": 3.448321270890346e-05,
"loss": 3.986,
"step": 947712
},
{
"epoch": 1.01,
"learning_rate": 3.447482676139293e-05,
"loss": 3.985,
"step": 948224
},
{
"epoch": 1.01,
"learning_rate": 3.446644081388241e-05,
"loss": 3.9896,
"step": 948736
},
{
"epoch": 1.01,
"learning_rate": 3.445805486637189e-05,
"loss": 3.9925,
"step": 949248
},
{
"epoch": 1.01,
"learning_rate": 3.444966891886137e-05,
"loss": 3.9857,
"step": 949760
},
{
"epoch": 1.01,
"learning_rate": 3.444128297135085e-05,
"loss": 3.9989,
"step": 950272
},
{
"epoch": 1.01,
"learning_rate": 3.443291340264406e-05,
"loss": 3.9764,
"step": 950784
},
{
"epoch": 1.01,
"learning_rate": 3.442452745513354e-05,
"loss": 3.9836,
"step": 951296
},
{
"epoch": 1.01,
"learning_rate": 3.4416141507623026e-05,
"loss": 3.9957,
"step": 951808
},
{
"epoch": 1.01,
"learning_rate": 3.4407755560112506e-05,
"loss": 3.9956,
"step": 952320
},
{
"epoch": 1.01,
"learning_rate": 3.4399385991405715e-05,
"loss": 3.9991,
"step": 952832
},
{
"epoch": 1.01,
"learning_rate": 3.4391000043895195e-05,
"loss": 3.991,
"step": 953344
},
{
"epoch": 1.01,
"learning_rate": 3.4382614096384675e-05,
"loss": 4.014,
"step": 953856
},
{
"epoch": 1.01,
"learning_rate": 3.4374244527677884e-05,
"loss": 3.9889,
"step": 954368
},
{
"epoch": 1.01,
"learning_rate": 3.4365858580167364e-05,
"loss": 4.0001,
"step": 954880
},
{
"epoch": 1.01,
"learning_rate": 3.4357472632656844e-05,
"loss": 3.9877,
"step": 955392
},
{
"epoch": 1.01,
"learning_rate": 3.4349086685146324e-05,
"loss": 3.9926,
"step": 955904
},
{
"epoch": 1.01,
"learning_rate": 3.4340700737635804e-05,
"loss": 3.9832,
"step": 956416
},
{
"epoch": 1.01,
"learning_rate": 3.4332314790125284e-05,
"loss": 3.9997,
"step": 956928
},
{
"epoch": 1.01,
"learning_rate": 3.432394522141849e-05,
"loss": 3.9978,
"step": 957440
},
{
"epoch": 1.01,
"learning_rate": 3.431555927390798e-05,
"loss": 4.0083,
"step": 957952
},
{
"epoch": 1.01,
"learning_rate": 3.430717332639746e-05,
"loss": 3.982,
"step": 958464
},
{
"epoch": 1.01,
"learning_rate": 3.429878737888694e-05,
"loss": 3.9808,
"step": 958976
},
{
"epoch": 1.01,
"learning_rate": 3.429040143137642e-05,
"loss": 3.9887,
"step": 959488
},
{
"epoch": 1.01,
"learning_rate": 3.42820154838659e-05,
"loss": 4.0001,
"step": 960000
},
{
"epoch": 1.01,
"learning_rate": 3.427362953635538e-05,
"loss": 3.9863,
"step": 960512
},
{
"epoch": 1.01,
"learning_rate": 3.426525996764859e-05,
"loss": 3.9981,
"step": 961024
},
{
"epoch": 1.01,
"learning_rate": 3.425687402013807e-05,
"loss": 3.9868,
"step": 961536
},
{
"epoch": 1.02,
"learning_rate": 3.424848807262755e-05,
"loss": 3.9822,
"step": 962048
},
{
"epoch": 1.02,
"learning_rate": 3.424010212511703e-05,
"loss": 3.9895,
"step": 962560
},
{
"epoch": 1.02,
"learning_rate": 3.423171617760651e-05,
"loss": 3.9809,
"step": 963072
},
{
"epoch": 1.02,
"learning_rate": 3.422334660889972e-05,
"loss": 3.9974,
"step": 963584
},
{
"epoch": 1.02,
"learning_rate": 3.42149606613892e-05,
"loss": 4.0034,
"step": 964096
},
{
"epoch": 1.02,
"learning_rate": 3.420657471387868e-05,
"loss": 4.0047,
"step": 964608
},
{
"epoch": 1.02,
"learning_rate": 3.4198205145171894e-05,
"loss": 3.983,
"step": 965120
},
{
"epoch": 1.02,
"learning_rate": 3.4189819197661374e-05,
"loss": 3.9847,
"step": 965632
},
{
"epoch": 1.02,
"learning_rate": 3.4181433250150854e-05,
"loss": 3.9911,
"step": 966144
},
{
"epoch": 1.02,
"learning_rate": 3.4173047302640333e-05,
"loss": 3.9921,
"step": 966656
},
{
"epoch": 1.02,
"learning_rate": 3.4164661355129813e-05,
"loss": 3.9965,
"step": 967168
},
{
"epoch": 1.02,
"learning_rate": 3.4156275407619293e-05,
"loss": 3.993,
"step": 967680
},
{
"epoch": 1.02,
"learning_rate": 3.41479058389125e-05,
"loss": 3.994,
"step": 968192
},
{
"epoch": 1.02,
"learning_rate": 3.413951989140198e-05,
"loss": 3.9811,
"step": 968704
},
{
"epoch": 1.02,
"learning_rate": 3.413113394389146e-05,
"loss": 3.9928,
"step": 969216
},
{
"epoch": 1.02,
"learning_rate": 3.412274799638094e-05,
"loss": 3.9762,
"step": 969728
},
{
"epoch": 1.02,
"learning_rate": 3.4114362048870416e-05,
"loss": 3.9855,
"step": 970240
},
{
"epoch": 1.02,
"learning_rate": 3.4105976101359895e-05,
"loss": 3.9876,
"step": 970752
},
{
"epoch": 1.02,
"learning_rate": 3.409760653265311e-05,
"loss": 3.9916,
"step": 971264
},
{
"epoch": 1.02,
"learning_rate": 3.40892205851426e-05,
"loss": 3.9847,
"step": 971776
},
{
"epoch": 1.02,
"learning_rate": 3.408083463763207e-05,
"loss": 3.9892,
"step": 972288
},
{
"epoch": 1.02,
"learning_rate": 3.407244869012155e-05,
"loss": 3.9707,
"step": 972800
},
{
"epoch": 1.02,
"learning_rate": 3.406406274261103e-05,
"loss": 3.9903,
"step": 973312
},
{
"epoch": 1.02,
"learning_rate": 3.405567679510051e-05,
"loss": 3.9902,
"step": 973824
},
{
"epoch": 1.02,
"learning_rate": 3.404729084758999e-05,
"loss": 3.9949,
"step": 974336
},
{
"epoch": 1.02,
"learning_rate": 3.403890490007947e-05,
"loss": 3.9963,
"step": 974848
},
{
"epoch": 1.02,
"learning_rate": 3.403053533137268e-05,
"loss": 3.9997,
"step": 975360
},
{
"epoch": 1.02,
"learning_rate": 3.402216576266589e-05,
"loss": 3.9885,
"step": 975872
},
{
"epoch": 1.02,
"learning_rate": 3.401377981515537e-05,
"loss": 3.9857,
"step": 976384
},
{
"epoch": 1.02,
"learning_rate": 3.4005410246448585e-05,
"loss": 3.9945,
"step": 976896
},
{
"epoch": 1.02,
"learning_rate": 3.3997024298938065e-05,
"loss": 3.9919,
"step": 977408
},
{
"epoch": 1.02,
"learning_rate": 3.3988638351427545e-05,
"loss": 3.9864,
"step": 977920
},
{
"epoch": 1.02,
"learning_rate": 3.3980252403917025e-05,
"loss": 3.9824,
"step": 978432
},
{
"epoch": 1.02,
"learning_rate": 3.3971866456406505e-05,
"loss": 3.9873,
"step": 978944
},
{
"epoch": 1.02,
"learning_rate": 3.3963480508895985e-05,
"loss": 3.9858,
"step": 979456
},
{
"epoch": 1.02,
"learning_rate": 3.3955094561385465e-05,
"loss": 3.9817,
"step": 979968
},
{
"epoch": 1.02,
"learning_rate": 3.3946708613874945e-05,
"loss": 3.9804,
"step": 980480
},
{
"epoch": 1.02,
"learning_rate": 3.3938339045168154e-05,
"loss": 3.9882,
"step": 980992
},
{
"epoch": 1.02,
"learning_rate": 3.3929953097657634e-05,
"loss": 3.976,
"step": 981504
},
{
"epoch": 1.02,
"learning_rate": 3.392158352895084e-05,
"loss": 3.9964,
"step": 982016
},
{
"epoch": 1.02,
"learning_rate": 3.391319758144032e-05,
"loss": 3.9871,
"step": 982528
},
{
"epoch": 1.02,
"learning_rate": 3.39048116339298e-05,
"loss": 4.0033,
"step": 983040
},
{
"epoch": 1.02,
"learning_rate": 3.389642568641929e-05,
"loss": 3.9746,
"step": 983552
},
{
"epoch": 1.02,
"learning_rate": 3.388803973890877e-05,
"loss": 3.9999,
"step": 984064
},
{
"epoch": 1.02,
"learning_rate": 3.387965379139825e-05,
"loss": 3.9945,
"step": 984576
},
{
"epoch": 1.02,
"learning_rate": 3.387126784388773e-05,
"loss": 3.9882,
"step": 985088
},
{
"epoch": 1.02,
"learning_rate": 3.386288189637721e-05,
"loss": 3.9929,
"step": 985600
},
{
"epoch": 1.02,
"learning_rate": 3.385449594886669e-05,
"loss": 3.9838,
"step": 986112
},
{
"epoch": 1.02,
"learning_rate": 3.384611000135617e-05,
"loss": 3.9962,
"step": 986624
},
{
"epoch": 1.02,
"learning_rate": 3.383772405384565e-05,
"loss": 3.9996,
"step": 987136
},
{
"epoch": 1.02,
"learning_rate": 3.382933810633513e-05,
"loss": 3.9779,
"step": 987648
},
{
"epoch": 1.02,
"learning_rate": 3.382096853762834e-05,
"loss": 3.9922,
"step": 988160
},
{
"epoch": 1.02,
"learning_rate": 3.381258259011782e-05,
"loss": 3.9918,
"step": 988672
},
{
"epoch": 1.02,
"learning_rate": 3.38041966426073e-05,
"loss": 3.9847,
"step": 989184
},
{
"epoch": 1.02,
"learning_rate": 3.379581069509678e-05,
"loss": 3.9852,
"step": 989696
},
{
"epoch": 1.02,
"learning_rate": 3.378744112638999e-05,
"loss": 3.9884,
"step": 990208
},
{
"epoch": 1.02,
"learning_rate": 3.37790715576832e-05,
"loss": 3.9827,
"step": 990720
},
{
"epoch": 1.02,
"learning_rate": 3.377068561017268e-05,
"loss": 3.9897,
"step": 991232
},
{
"epoch": 1.02,
"learning_rate": 3.376229966266216e-05,
"loss": 3.9823,
"step": 991744
},
{
"epoch": 1.03,
"eval_loss": 4.034952163696289,
"eval_runtime": 315.1062,
"eval_samples_per_second": 1210.992,
"eval_steps_per_second": 37.844,
"step": 992160
},
{
"epoch": 0.0,
"learning_rate": 3.375391371515164e-05,
"loss": 3.9973,
"step": 992256
},
{
"epoch": 0.0,
"learning_rate": 3.374552776764112e-05,
"loss": 3.9771,
"step": 992768
},
{
"epoch": 0.0,
"learning_rate": 3.37371418201306e-05,
"loss": 3.9781,
"step": 993280
},
{
"epoch": 0.0,
"learning_rate": 3.3728755872620076e-05,
"loss": 3.9954,
"step": 993792
},
{
"epoch": 0.0,
"learning_rate": 3.3720369925109556e-05,
"loss": 3.9855,
"step": 994304
},
{
"epoch": 0.0,
"learning_rate": 3.3711983977599036e-05,
"loss": 3.9876,
"step": 994816
},
{
"epoch": 0.0,
"learning_rate": 3.3703598030088516e-05,
"loss": 3.984,
"step": 995328
},
{
"epoch": 0.0,
"learning_rate": 3.3695212082577996e-05,
"loss": 3.9832,
"step": 995840
},
{
"epoch": 0.0,
"learning_rate": 3.3686826135067476e-05,
"loss": 3.9748,
"step": 996352
},
{
"epoch": 0.0,
"learning_rate": 3.3678440187556956e-05,
"loss": 3.9935,
"step": 996864
},
{
"epoch": 0.0,
"learning_rate": 3.3670054240046436e-05,
"loss": 3.989,
"step": 997376
},
{
"epoch": 0.0,
"learning_rate": 3.366168467133965e-05,
"loss": 3.9857,
"step": 997888
},
{
"epoch": 0.0,
"learning_rate": 3.365329872382913e-05,
"loss": 3.9916,
"step": 998400
},
{
"epoch": 0.0,
"learning_rate": 3.364491277631861e-05,
"loss": 3.9761,
"step": 998912
},
{
"epoch": 0.0,
"learning_rate": 3.363652682880809e-05,
"loss": 3.9799,
"step": 999424
},
{
"epoch": 0.0,
"learning_rate": 3.362814088129757e-05,
"loss": 3.9752,
"step": 999936
},
{
"epoch": 0.0,
"learning_rate": 3.361975493378705e-05,
"loss": 3.987,
"step": 1000448
},
{
"epoch": 0.0,
"learning_rate": 3.361136898627653e-05,
"loss": 3.9816,
"step": 1000960
},
{
"epoch": 0.0,
"learning_rate": 3.360298303876601e-05,
"loss": 3.9786,
"step": 1001472
},
{
"epoch": 0.0,
"learning_rate": 3.359459709125549e-05,
"loss": 3.9809,
"step": 1001984
},
{
"epoch": 0.0,
"learning_rate": 3.3586211143744964e-05,
"loss": 3.992,
"step": 1002496
},
{
"epoch": 0.0,
"learning_rate": 3.3577825196234444e-05,
"loss": 3.992,
"step": 1003008
},
{
"epoch": 0.0,
"learning_rate": 3.3569439248723924e-05,
"loss": 3.9896,
"step": 1003520
},
{
"epoch": 0.0,
"learning_rate": 3.3561053301213404e-05,
"loss": 3.9824,
"step": 1004032
},
{
"epoch": 0.0,
"learning_rate": 3.355266735370289e-05,
"loss": 3.9877,
"step": 1004544
},
{
"epoch": 0.0,
"learning_rate": 3.35442977849961e-05,
"loss": 3.985,
"step": 1005056
},
{
"epoch": 0.0,
"learning_rate": 3.353591183748558e-05,
"loss": 3.9815,
"step": 1005568
},
{
"epoch": 0.0,
"learning_rate": 3.352752588997506e-05,
"loss": 3.9818,
"step": 1006080
},
{
"epoch": 0.0,
"learning_rate": 3.351913994246454e-05,
"loss": 3.9788,
"step": 1006592
},
{
"epoch": 0.0,
"learning_rate": 3.351075399495402e-05,
"loss": 3.9761,
"step": 1007104
},
{
"epoch": 0.01,
"learning_rate": 3.35023680474435e-05,
"loss": 3.9816,
"step": 1007616
},
{
"epoch": 0.01,
"learning_rate": 3.349398209993298e-05,
"loss": 3.981,
"step": 1008128
},
{
"epoch": 0.01,
"learning_rate": 3.348561253122619e-05,
"loss": 3.9878,
"step": 1008640
},
{
"epoch": 0.01,
"learning_rate": 3.347722658371567e-05,
"loss": 3.9912,
"step": 1009152
},
{
"epoch": 0.01,
"learning_rate": 3.346884063620515e-05,
"loss": 3.9825,
"step": 1009664
},
{
"epoch": 0.01,
"learning_rate": 3.346045468869463e-05,
"loss": 3.9867,
"step": 1010176
},
{
"epoch": 0.01,
"learning_rate": 3.345206874118411e-05,
"loss": 3.9918,
"step": 1010688
},
{
"epoch": 0.01,
"learning_rate": 3.344368279367359e-05,
"loss": 3.966,
"step": 1011200
},
{
"epoch": 0.01,
"learning_rate": 3.3435296846163076e-05,
"loss": 3.9796,
"step": 1011712
},
{
"epoch": 0.01,
"learning_rate": 3.3426910898652555e-05,
"loss": 3.9778,
"step": 1012224
},
{
"epoch": 0.01,
"learning_rate": 3.3418541329945765e-05,
"loss": 3.9747,
"step": 1012736
},
{
"epoch": 0.01,
"learning_rate": 3.3410155382435245e-05,
"loss": 3.977,
"step": 1013248
},
{
"epoch": 0.01,
"learning_rate": 3.3401769434924724e-05,
"loss": 3.9841,
"step": 1013760
},
{
"epoch": 0.01,
"learning_rate": 3.3393383487414204e-05,
"loss": 3.983,
"step": 1014272
},
{
"epoch": 0.01,
"learning_rate": 3.338499753990368e-05,
"loss": 3.9786,
"step": 1014784
},
{
"epoch": 0.01,
"learning_rate": 3.3376627971196893e-05,
"loss": 3.9855,
"step": 1015296
},
{
"epoch": 0.01,
"learning_rate": 3.33682584024901e-05,
"loss": 3.9777,
"step": 1015808
},
{
"epoch": 0.01,
"learning_rate": 3.335987245497958e-05,
"loss": 3.9756,
"step": 1016320
},
{
"epoch": 0.01,
"learning_rate": 3.335148650746906e-05,
"loss": 3.9547,
"step": 1016832
},
{
"epoch": 0.01,
"learning_rate": 3.334310055995854e-05,
"loss": 3.9889,
"step": 1017344
},
{
"epoch": 0.01,
"learning_rate": 3.333471461244803e-05,
"loss": 3.9745,
"step": 1017856
},
{
"epoch": 0.01,
"learning_rate": 3.33263286649375e-05,
"loss": 3.9839,
"step": 1018368
},
{
"epoch": 0.01,
"learning_rate": 3.331794271742698e-05,
"loss": 3.9741,
"step": 1018880
},
{
"epoch": 0.01,
"learning_rate": 3.330955676991646e-05,
"loss": 3.9686,
"step": 1019392
},
{
"epoch": 0.01,
"learning_rate": 3.330117082240594e-05,
"loss": 3.9715,
"step": 1019904
},
{
"epoch": 0.01,
"learning_rate": 3.329280125369915e-05,
"loss": 3.9748,
"step": 1020416
},
{
"epoch": 0.01,
"learning_rate": 3.328441530618863e-05,
"loss": 3.9805,
"step": 1020928
},
{
"epoch": 0.01,
"learning_rate": 3.327602935867811e-05,
"loss": 3.9631,
"step": 1021440
},
{
"epoch": 0.01,
"learning_rate": 3.326764341116759e-05,
"loss": 3.9919,
"step": 1021952
},
{
"epoch": 0.01,
"learning_rate": 3.325925746365707e-05,
"loss": 3.9782,
"step": 1022464
},
{
"epoch": 0.01,
"learning_rate": 3.325087151614655e-05,
"loss": 3.9586,
"step": 1022976
},
{
"epoch": 0.01,
"learning_rate": 3.324250194743977e-05,
"loss": 3.9824,
"step": 1023488
},
{
"epoch": 0.01,
"learning_rate": 3.3234132378732976e-05,
"loss": 3.9702,
"step": 1024000
},
{
"epoch": 0.01,
"learning_rate": 3.3225746431222456e-05,
"loss": 3.974,
"step": 1024512
},
{
"epoch": 0.01,
"learning_rate": 3.3217360483711936e-05,
"loss": 3.9678,
"step": 1025024
},
{
"epoch": 0.01,
"learning_rate": 3.3208974536201416e-05,
"loss": 3.9825,
"step": 1025536
},
{
"epoch": 0.01,
"learning_rate": 3.3200588588690896e-05,
"loss": 3.968,
"step": 1026048
},
{
"epoch": 0.01,
"learning_rate": 3.3192202641180376e-05,
"loss": 3.9833,
"step": 1026560
},
{
"epoch": 0.01,
"learning_rate": 3.3183816693669856e-05,
"loss": 3.9618,
"step": 1027072
},
{
"epoch": 0.01,
"learning_rate": 3.3175430746159336e-05,
"loss": 3.9698,
"step": 1027584
},
{
"epoch": 0.01,
"learning_rate": 3.3167044798648816e-05,
"loss": 3.9809,
"step": 1028096
},
{
"epoch": 0.01,
"learning_rate": 3.3158658851138296e-05,
"loss": 3.9847,
"step": 1028608
},
{
"epoch": 0.01,
"learning_rate": 3.3150272903627776e-05,
"loss": 3.9809,
"step": 1029120
},
{
"epoch": 0.01,
"learning_rate": 3.3141886956117256e-05,
"loss": 3.9768,
"step": 1029632
},
{
"epoch": 0.01,
"learning_rate": 3.3133517387410465e-05,
"loss": 3.9983,
"step": 1030144
},
{
"epoch": 0.01,
"learning_rate": 3.3125131439899945e-05,
"loss": 3.9752,
"step": 1030656
},
{
"epoch": 0.01,
"learning_rate": 3.311676187119316e-05,
"loss": 3.9833,
"step": 1031168
},
{
"epoch": 0.01,
"learning_rate": 3.310837592368264e-05,
"loss": 3.9781,
"step": 1031680
},
{
"epoch": 0.01,
"learning_rate": 3.309998997617212e-05,
"loss": 3.9798,
"step": 1032192
},
{
"epoch": 0.01,
"learning_rate": 3.30916040286616e-05,
"loss": 3.9728,
"step": 1032704
},
{
"epoch": 0.01,
"learning_rate": 3.308321808115108e-05,
"loss": 3.9818,
"step": 1033216
},
{
"epoch": 0.01,
"learning_rate": 3.307484851244429e-05,
"loss": 3.9839,
"step": 1033728
},
{
"epoch": 0.01,
"learning_rate": 3.306646256493377e-05,
"loss": 3.9905,
"step": 1034240
},
{
"epoch": 0.01,
"learning_rate": 3.305807661742325e-05,
"loss": 3.9756,
"step": 1034752
},
{
"epoch": 0.01,
"learning_rate": 3.304969066991273e-05,
"loss": 3.9655,
"step": 1035264
},
{
"epoch": 0.01,
"learning_rate": 3.304130472240221e-05,
"loss": 3.974,
"step": 1035776
},
{
"epoch": 0.01,
"learning_rate": 3.303291877489169e-05,
"loss": 3.9814,
"step": 1036288
},
{
"epoch": 0.01,
"learning_rate": 3.302453282738117e-05,
"loss": 3.9757,
"step": 1036800
},
{
"epoch": 0.01,
"learning_rate": 3.3016163258674385e-05,
"loss": 3.9839,
"step": 1037312
},
{
"epoch": 0.01,
"learning_rate": 3.3007777311163865e-05,
"loss": 3.9727,
"step": 1037824
},
{
"epoch": 0.02,
"learning_rate": 3.299939136365334e-05,
"loss": 3.9674,
"step": 1038336
},
{
"epoch": 0.02,
"learning_rate": 3.299100541614282e-05,
"loss": 3.9736,
"step": 1038848
},
{
"epoch": 0.02,
"learning_rate": 3.2982635847436034e-05,
"loss": 3.969,
"step": 1039360
},
{
"epoch": 0.02,
"learning_rate": 3.2974249899925514e-05,
"loss": 3.9883,
"step": 1039872
},
{
"epoch": 0.02,
"learning_rate": 3.296586395241499e-05,
"loss": 3.9819,
"step": 1040384
},
{
"epoch": 0.02,
"learning_rate": 3.295747800490447e-05,
"loss": 3.9905,
"step": 1040896
},
{
"epoch": 0.02,
"learning_rate": 3.294909205739395e-05,
"loss": 3.9692,
"step": 1041408
},
{
"epoch": 0.02,
"learning_rate": 3.294070610988343e-05,
"loss": 3.9738,
"step": 1041920
},
{
"epoch": 0.02,
"learning_rate": 3.2932336541176636e-05,
"loss": 3.9746,
"step": 1042432
},
{
"epoch": 0.02,
"learning_rate": 3.292395059366612e-05,
"loss": 3.9764,
"step": 1042944
},
{
"epoch": 0.02,
"learning_rate": 3.29155646461556e-05,
"loss": 3.9863,
"step": 1043456
},
{
"epoch": 0.02,
"learning_rate": 3.290717869864508e-05,
"loss": 3.9753,
"step": 1043968
},
{
"epoch": 0.02,
"learning_rate": 3.289879275113456e-05,
"loss": 3.9812,
"step": 1044480
},
{
"epoch": 0.02,
"learning_rate": 3.289040680362404e-05,
"loss": 3.9662,
"step": 1044992
},
{
"epoch": 0.02,
"learning_rate": 3.288202085611352e-05,
"loss": 3.9836,
"step": 1045504
},
{
"epoch": 0.02,
"learning_rate": 3.2873634908603e-05,
"loss": 3.958,
"step": 1046016
},
{
"epoch": 0.02,
"learning_rate": 3.286526533989621e-05,
"loss": 3.9695,
"step": 1046528
},
{
"epoch": 0.02,
"learning_rate": 3.285687939238569e-05,
"loss": 3.9759,
"step": 1047040
},
{
"epoch": 0.02,
"learning_rate": 3.28485098236789e-05,
"loss": 3.9788,
"step": 1047552
},
{
"epoch": 0.02,
"learning_rate": 3.284014025497211e-05,
"loss": 3.9684,
"step": 1048064
},
{
"epoch": 0.02,
"learning_rate": 3.283175430746159e-05,
"loss": 3.9744,
"step": 1048576
},
{
"epoch": 0.02,
"learning_rate": 3.2823368359951076e-05,
"loss": 3.9575,
"step": 1049088
},
{
"epoch": 0.02,
"learning_rate": 3.2814982412440556e-05,
"loss": 3.9811,
"step": 1049600
},
{
"epoch": 0.02,
"learning_rate": 3.2806596464930036e-05,
"loss": 3.9694,
"step": 1050112
},
{
"epoch": 0.02,
"learning_rate": 3.2798210517419516e-05,
"loss": 3.9797,
"step": 1050624
},
{
"epoch": 0.02,
"learning_rate": 3.2789824569908996e-05,
"loss": 3.9841,
"step": 1051136
},
{
"epoch": 0.02,
"learning_rate": 3.2781438622398476e-05,
"loss": 3.9847,
"step": 1051648
},
{
"epoch": 0.02,
"learning_rate": 3.2773069053691685e-05,
"loss": 3.9725,
"step": 1052160
},
{
"epoch": 0.02,
"learning_rate": 3.2764683106181165e-05,
"loss": 3.9741,
"step": 1052672
},
{
"epoch": 0.02,
"learning_rate": 3.2756297158670645e-05,
"loss": 3.9812,
"step": 1053184
},
{
"epoch": 0.02,
"learning_rate": 3.2747911211160125e-05,
"loss": 3.9745,
"step": 1053696
},
{
"epoch": 0.02,
"learning_rate": 3.2739525263649605e-05,
"loss": 3.9756,
"step": 1054208
},
{
"epoch": 0.02,
"learning_rate": 3.2731139316139085e-05,
"loss": 3.9681,
"step": 1054720
},
{
"epoch": 0.02,
"learning_rate": 3.2722753368628565e-05,
"loss": 3.9748,
"step": 1055232
},
{
"epoch": 0.02,
"learning_rate": 3.2714383799921774e-05,
"loss": 3.9689,
"step": 1055744
},
{
"epoch": 0.02,
"learning_rate": 3.270599785241126e-05,
"loss": 3.9685,
"step": 1056256
},
{
"epoch": 0.02,
"learning_rate": 3.269761190490074e-05,
"loss": 3.9708,
"step": 1056768
},
{
"epoch": 0.02,
"learning_rate": 3.268922595739022e-05,
"loss": 3.9721,
"step": 1057280
},
{
"epoch": 0.02,
"learning_rate": 3.26808400098797e-05,
"loss": 3.9645,
"step": 1057792
},
{
"epoch": 0.02,
"learning_rate": 3.267247044117291e-05,
"loss": 3.9842,
"step": 1058304
},
{
"epoch": 0.02,
"learning_rate": 3.266408449366239e-05,
"loss": 3.9746,
"step": 1058816
},
{
"epoch": 0.02,
"learning_rate": 3.265569854615187e-05,
"loss": 3.9846,
"step": 1059328
},
{
"epoch": 0.02,
"learning_rate": 3.264732897744508e-05,
"loss": 3.9661,
"step": 1059840
},
{
"epoch": 0.02,
"learning_rate": 3.263894302993456e-05,
"loss": 3.9817,
"step": 1060352
},
{
"epoch": 0.02,
"learning_rate": 3.263055708242404e-05,
"loss": 3.981,
"step": 1060864
},
{
"epoch": 0.02,
"learning_rate": 3.262217113491352e-05,
"loss": 3.9766,
"step": 1061376
},
{
"epoch": 0.02,
"learning_rate": 3.2613785187403e-05,
"loss": 3.9737,
"step": 1061888
},
{
"epoch": 0.02,
"learning_rate": 3.260539923989248e-05,
"loss": 3.9712,
"step": 1062400
},
{
"epoch": 0.02,
"learning_rate": 3.259701329238196e-05,
"loss": 3.9799,
"step": 1062912
},
{
"epoch": 0.02,
"learning_rate": 3.258862734487144e-05,
"loss": 3.9848,
"step": 1063424
},
{
"epoch": 0.02,
"learning_rate": 3.258025777616465e-05,
"loss": 3.9702,
"step": 1063936
},
{
"epoch": 0.02,
"learning_rate": 3.257187182865413e-05,
"loss": 3.975,
"step": 1064448
},
{
"epoch": 0.02,
"learning_rate": 3.256348588114361e-05,
"loss": 3.9799,
"step": 1064960
},
{
"epoch": 0.02,
"learning_rate": 3.255509993363309e-05,
"loss": 3.9709,
"step": 1065472
},
{
"epoch": 0.02,
"learning_rate": 3.254671398612257e-05,
"loss": 3.9704,
"step": 1065984
},
{
"epoch": 0.02,
"learning_rate": 3.253832803861205e-05,
"loss": 3.9748,
"step": 1066496
},
{
"epoch": 0.02,
"learning_rate": 3.252994209110153e-05,
"loss": 3.9713,
"step": 1067008
},
{
"epoch": 0.02,
"learning_rate": 3.252155614359101e-05,
"loss": 3.9762,
"step": 1067520
},
{
"epoch": 0.02,
"learning_rate": 3.251317019608049e-05,
"loss": 3.9654,
"step": 1068032
},
{
"epoch": 0.03,
"eval_loss": 4.027137756347656,
"eval_runtime": 318.9474,
"eval_samples_per_second": 1196.407,
"eval_steps_per_second": 37.389,
"step": 1068480
},
{
"epoch": 1.0,
"learning_rate": 3.2504800627373696e-05,
"loss": 3.9734,
"step": 1068544
},
{
"epoch": 1.0,
"learning_rate": 3.2496414679863176e-05,
"loss": 3.9644,
"step": 1069056
},
{
"epoch": 1.0,
"learning_rate": 3.248804511115639e-05,
"loss": 3.9652,
"step": 1069568
},
{
"epoch": 1.0,
"learning_rate": 3.247965916364587e-05,
"loss": 3.9804,
"step": 1070080
},
{
"epoch": 1.0,
"learning_rate": 3.247127321613535e-05,
"loss": 3.9763,
"step": 1070592
},
{
"epoch": 1.0,
"learning_rate": 3.246288726862483e-05,
"loss": 3.9729,
"step": 1071104
},
{
"epoch": 1.0,
"learning_rate": 3.245450132111431e-05,
"loss": 3.9691,
"step": 1071616
},
{
"epoch": 1.0,
"learning_rate": 3.244611537360379e-05,
"loss": 3.968,
"step": 1072128
},
{
"epoch": 1.0,
"learning_rate": 3.2437745804897e-05,
"loss": 3.9618,
"step": 1072640
},
{
"epoch": 1.0,
"learning_rate": 3.242935985738648e-05,
"loss": 3.9815,
"step": 1073152
},
{
"epoch": 1.0,
"learning_rate": 3.242097390987596e-05,
"loss": 3.9738,
"step": 1073664
},
{
"epoch": 1.0,
"learning_rate": 3.241260434116917e-05,
"loss": 3.979,
"step": 1074176
},
{
"epoch": 1.0,
"learning_rate": 3.240421839365865e-05,
"loss": 3.9744,
"step": 1074688
},
{
"epoch": 1.0,
"learning_rate": 3.239583244614813e-05,
"loss": 3.9622,
"step": 1075200
},
{
"epoch": 1.0,
"learning_rate": 3.238744649863762e-05,
"loss": 3.9701,
"step": 1075712
},
{
"epoch": 1.0,
"learning_rate": 3.23790605511271e-05,
"loss": 3.9609,
"step": 1076224
},
{
"epoch": 1.0,
"learning_rate": 3.237067460361658e-05,
"loss": 3.9722,
"step": 1076736
},
{
"epoch": 1.0,
"learning_rate": 3.236228865610606e-05,
"loss": 3.9652,
"step": 1077248
},
{
"epoch": 1.0,
"learning_rate": 3.2353902708595537e-05,
"loss": 3.97,
"step": 1077760
},
{
"epoch": 1.0,
"learning_rate": 3.234551676108501e-05,
"loss": 3.9669,
"step": 1078272
},
{
"epoch": 1.0,
"learning_rate": 3.233713081357449e-05,
"loss": 3.977,
"step": 1078784
},
{
"epoch": 1.0,
"learning_rate": 3.232874486606397e-05,
"loss": 3.9786,
"step": 1079296
},
{
"epoch": 1.0,
"learning_rate": 3.232035891855345e-05,
"loss": 3.9746,
"step": 1079808
},
{
"epoch": 1.0,
"learning_rate": 3.2312005728650395e-05,
"loss": 3.9702,
"step": 1080320
},
{
"epoch": 1.0,
"learning_rate": 3.2303619781139875e-05,
"loss": 3.9785,
"step": 1080832
},
{
"epoch": 1.0,
"learning_rate": 3.2295233833629355e-05,
"loss": 3.9676,
"step": 1081344
},
{
"epoch": 1.0,
"learning_rate": 3.2286847886118835e-05,
"loss": 3.9665,
"step": 1081856
},
{
"epoch": 1.0,
"learning_rate": 3.2278461938608314e-05,
"loss": 3.9733,
"step": 1082368
},
{
"epoch": 1.0,
"learning_rate": 3.2270075991097794e-05,
"loss": 3.9611,
"step": 1082880
},
{
"epoch": 1.0,
"learning_rate": 3.2261690043587274e-05,
"loss": 3.9612,
"step": 1083392
},
{
"epoch": 1.01,
"learning_rate": 3.2253304096076754e-05,
"loss": 3.9689,
"step": 1083904
},
{
"epoch": 1.01,
"learning_rate": 3.2244934527369963e-05,
"loss": 3.9662,
"step": 1084416
},
{
"epoch": 1.01,
"learning_rate": 3.2236548579859443e-05,
"loss": 3.977,
"step": 1084928
},
{
"epoch": 1.01,
"learning_rate": 3.222816263234892e-05,
"loss": 3.9791,
"step": 1085440
},
{
"epoch": 1.01,
"learning_rate": 3.221979306364213e-05,
"loss": 3.9657,
"step": 1085952
},
{
"epoch": 1.01,
"learning_rate": 3.221140711613161e-05,
"loss": 3.9785,
"step": 1086464
},
{
"epoch": 1.01,
"learning_rate": 3.220302116862109e-05,
"loss": 3.9754,
"step": 1086976
},
{
"epoch": 1.01,
"learning_rate": 3.219463522111057e-05,
"loss": 3.9587,
"step": 1087488
},
{
"epoch": 1.01,
"learning_rate": 3.218624927360005e-05,
"loss": 3.9647,
"step": 1088000
},
{
"epoch": 1.01,
"learning_rate": 3.217786332608954e-05,
"loss": 3.9642,
"step": 1088512
},
{
"epoch": 1.01,
"learning_rate": 3.216949375738275e-05,
"loss": 3.9597,
"step": 1089024
},
{
"epoch": 1.01,
"learning_rate": 3.216110780987223e-05,
"loss": 3.9673,
"step": 1089536
},
{
"epoch": 1.01,
"learning_rate": 3.215272186236171e-05,
"loss": 3.9738,
"step": 1090048
},
{
"epoch": 1.01,
"learning_rate": 3.214433591485119e-05,
"loss": 3.9639,
"step": 1090560
},
{
"epoch": 1.01,
"learning_rate": 3.213594996734067e-05,
"loss": 3.966,
"step": 1091072
},
{
"epoch": 1.01,
"learning_rate": 3.212756401983015e-05,
"loss": 3.9719,
"step": 1091584
},
{
"epoch": 1.01,
"learning_rate": 3.211917807231963e-05,
"loss": 3.9636,
"step": 1092096
},
{
"epoch": 1.01,
"learning_rate": 3.211079212480911e-05,
"loss": 3.9629,
"step": 1092608
},
{
"epoch": 1.01,
"learning_rate": 3.210242255610232e-05,
"loss": 3.9426,
"step": 1093120
},
{
"epoch": 1.01,
"learning_rate": 3.20940366085918e-05,
"loss": 3.9716,
"step": 1093632
},
{
"epoch": 1.01,
"learning_rate": 3.208565066108128e-05,
"loss": 3.964,
"step": 1094144
},
{
"epoch": 1.01,
"learning_rate": 3.207726471357076e-05,
"loss": 3.9718,
"step": 1094656
},
{
"epoch": 1.01,
"learning_rate": 3.206887876606024e-05,
"loss": 3.9606,
"step": 1095168
},
{
"epoch": 1.01,
"learning_rate": 3.206050919735345e-05,
"loss": 3.954,
"step": 1095680
},
{
"epoch": 1.01,
"learning_rate": 3.205212324984293e-05,
"loss": 3.9614,
"step": 1096192
},
{
"epoch": 1.01,
"learning_rate": 3.204375368113614e-05,
"loss": 3.9612,
"step": 1096704
},
{
"epoch": 1.01,
"learning_rate": 3.203536773362562e-05,
"loss": 3.9666,
"step": 1097216
},
{
"epoch": 1.01,
"learning_rate": 3.20269817861151e-05,
"loss": 3.9474,
"step": 1097728
},
{
"epoch": 1.01,
"learning_rate": 3.201859583860458e-05,
"loss": 3.9769,
"step": 1098240
},
{
"epoch": 1.01,
"learning_rate": 3.201020989109406e-05,
"loss": 3.9658,
"step": 1098752
},
{
"epoch": 1.01,
"learning_rate": 3.200184032238727e-05,
"loss": 3.9508,
"step": 1099264
},
{
"epoch": 1.01,
"learning_rate": 3.199345437487675e-05,
"loss": 3.9678,
"step": 1099776
},
{
"epoch": 1.01,
"learning_rate": 3.198506842736623e-05,
"loss": 3.9565,
"step": 1100288
},
{
"epoch": 1.01,
"learning_rate": 3.197668247985571e-05,
"loss": 3.9587,
"step": 1100800
},
{
"epoch": 1.01,
"learning_rate": 3.196829653234519e-05,
"loss": 3.9543,
"step": 1101312
},
{
"epoch": 1.01,
"learning_rate": 3.195991058483467e-05,
"loss": 3.9707,
"step": 1101824
},
{
"epoch": 1.01,
"learning_rate": 3.195152463732415e-05,
"loss": 3.9581,
"step": 1102336
},
{
"epoch": 1.01,
"learning_rate": 3.194313868981363e-05,
"loss": 3.9644,
"step": 1102848
},
{
"epoch": 1.01,
"learning_rate": 3.1934769121106846e-05,
"loss": 3.9567,
"step": 1103360
},
{
"epoch": 1.01,
"learning_rate": 3.192638317359632e-05,
"loss": 3.9555,
"step": 1103872
},
{
"epoch": 1.01,
"learning_rate": 3.19179972260858e-05,
"loss": 3.9647,
"step": 1104384
},
{
"epoch": 1.01,
"learning_rate": 3.190961127857528e-05,
"loss": 3.9778,
"step": 1104896
},
{
"epoch": 1.01,
"learning_rate": 3.190124170986849e-05,
"loss": 3.9668,
"step": 1105408
},
{
"epoch": 1.01,
"learning_rate": 3.1892872141161704e-05,
"loss": 3.9635,
"step": 1105920
},
{
"epoch": 1.01,
"learning_rate": 3.1884486193651184e-05,
"loss": 3.9828,
"step": 1106432
},
{
"epoch": 1.01,
"learning_rate": 3.1876100246140664e-05,
"loss": 3.962,
"step": 1106944
},
{
"epoch": 1.01,
"learning_rate": 3.1867714298630144e-05,
"loss": 3.9674,
"step": 1107456
},
{
"epoch": 1.01,
"learning_rate": 3.1859328351119624e-05,
"loss": 3.965,
"step": 1107968
},
{
"epoch": 1.01,
"learning_rate": 3.185095878241284e-05,
"loss": 3.9703,
"step": 1108480
},
{
"epoch": 1.01,
"learning_rate": 3.184257283490232e-05,
"loss": 3.9594,
"step": 1108992
},
{
"epoch": 1.01,
"learning_rate": 3.183418688739179e-05,
"loss": 3.9647,
"step": 1109504
},
{
"epoch": 1.01,
"learning_rate": 3.182580093988127e-05,
"loss": 3.9716,
"step": 1110016
},
{
"epoch": 1.01,
"learning_rate": 3.181741499237075e-05,
"loss": 3.9785,
"step": 1110528
},
{
"epoch": 1.01,
"learning_rate": 3.180904542366396e-05,
"loss": 3.964,
"step": 1111040
},
{
"epoch": 1.01,
"learning_rate": 3.180067585495718e-05,
"loss": 3.9497,
"step": 1111552
},
{
"epoch": 1.01,
"learning_rate": 3.179228990744666e-05,
"loss": 3.9616,
"step": 1112064
},
{
"epoch": 1.01,
"learning_rate": 3.178390395993614e-05,
"loss": 3.9719,
"step": 1112576
},
{
"epoch": 1.01,
"learning_rate": 3.177551801242562e-05,
"loss": 3.9642,
"step": 1113088
},
{
"epoch": 1.01,
"learning_rate": 3.17671320649151e-05,
"loss": 3.9699,
"step": 1113600
},
{
"epoch": 1.01,
"learning_rate": 3.175874611740458e-05,
"loss": 3.961,
"step": 1114112
},
{
"epoch": 1.02,
"learning_rate": 3.175036016989406e-05,
"loss": 3.9569,
"step": 1114624
},
{
"epoch": 1.02,
"learning_rate": 3.174197422238354e-05,
"loss": 3.9598,
"step": 1115136
},
{
"epoch": 1.02,
"learning_rate": 3.173358827487302e-05,
"loss": 3.9561,
"step": 1115648
},
{
"epoch": 1.02,
"learning_rate": 3.17252023273625e-05,
"loss": 3.9707,
"step": 1116160
},
{
"epoch": 1.02,
"learning_rate": 3.171681637985198e-05,
"loss": 3.9655,
"step": 1116672
},
{
"epoch": 1.02,
"learning_rate": 3.170843043234146e-05,
"loss": 3.9815,
"step": 1117184
},
{
"epoch": 1.02,
"learning_rate": 3.170004448483094e-05,
"loss": 3.954,
"step": 1117696
},
{
"epoch": 1.02,
"learning_rate": 3.1691674916124146e-05,
"loss": 3.9627,
"step": 1118208
},
{
"epoch": 1.02,
"learning_rate": 3.1683288968613626e-05,
"loss": 3.9627,
"step": 1118720
},
{
"epoch": 1.02,
"learning_rate": 3.1674919399906836e-05,
"loss": 3.9666,
"step": 1119232
},
{
"epoch": 1.02,
"learning_rate": 3.1666533452396315e-05,
"loss": 3.9692,
"step": 1119744
},
{
"epoch": 1.02,
"learning_rate": 3.16581475048858e-05,
"loss": 3.9656,
"step": 1120256
},
{
"epoch": 1.02,
"learning_rate": 3.164976155737528e-05,
"loss": 3.9684,
"step": 1120768
},
{
"epoch": 1.02,
"learning_rate": 3.164137560986476e-05,
"loss": 3.9521,
"step": 1121280
},
{
"epoch": 1.02,
"learning_rate": 3.163298966235424e-05,
"loss": 3.9699,
"step": 1121792
},
{
"epoch": 1.02,
"learning_rate": 3.162460371484372e-05,
"loss": 3.9439,
"step": 1122304
},
{
"epoch": 1.02,
"learning_rate": 3.16162177673332e-05,
"loss": 3.9582,
"step": 1122816
},
{
"epoch": 1.02,
"learning_rate": 3.1607831819822675e-05,
"loss": 3.9628,
"step": 1123328
},
{
"epoch": 1.02,
"learning_rate": 3.159946225111589e-05,
"loss": 3.9669,
"step": 1123840
},
{
"epoch": 1.02,
"learning_rate": 3.15910926824091e-05,
"loss": 3.9575,
"step": 1124352
},
{
"epoch": 1.02,
"learning_rate": 3.158273949250604e-05,
"loss": 3.9564,
"step": 1124864
},
{
"epoch": 1.02,
"learning_rate": 3.1574353544995525e-05,
"loss": 3.9527,
"step": 1125376
},
{
"epoch": 1.02,
"learning_rate": 3.1565967597485005e-05,
"loss": 3.961,
"step": 1125888
},
{
"epoch": 1.02,
"learning_rate": 3.1557581649974485e-05,
"loss": 3.9582,
"step": 1126400
},
{
"epoch": 1.02,
"learning_rate": 3.1549195702463965e-05,
"loss": 3.9674,
"step": 1126912
},
{
"epoch": 1.02,
"learning_rate": 3.1540809754953445e-05,
"loss": 3.9713,
"step": 1127424
},
{
"epoch": 1.02,
"learning_rate": 3.1532423807442925e-05,
"loss": 3.9719,
"step": 1127936
},
{
"epoch": 1.02,
"learning_rate": 3.1524037859932405e-05,
"loss": 3.9584,
"step": 1128448
},
{
"epoch": 1.02,
"learning_rate": 3.1515651912421885e-05,
"loss": 3.9601,
"step": 1128960
},
{
"epoch": 1.02,
"learning_rate": 3.1507265964911365e-05,
"loss": 3.9688,
"step": 1129472
},
{
"epoch": 1.02,
"learning_rate": 3.1498880017400845e-05,
"loss": 3.9632,
"step": 1129984
},
{
"epoch": 1.02,
"learning_rate": 3.1490494069890325e-05,
"loss": 3.9601,
"step": 1130496
},
{
"epoch": 1.02,
"learning_rate": 3.14821081223798e-05,
"loss": 3.9594,
"step": 1131008
},
{
"epoch": 1.02,
"learning_rate": 3.147372217486928e-05,
"loss": 3.9596,
"step": 1131520
},
{
"epoch": 1.02,
"learning_rate": 3.1465352606162494e-05,
"loss": 3.9565,
"step": 1132032
},
{
"epoch": 1.02,
"learning_rate": 3.1456966658651974e-05,
"loss": 3.9525,
"step": 1132544
},
{
"epoch": 1.02,
"learning_rate": 3.1448580711141454e-05,
"loss": 3.9587,
"step": 1133056
},
{
"epoch": 1.02,
"learning_rate": 3.1440194763630934e-05,
"loss": 3.9587,
"step": 1133568
},
{
"epoch": 1.02,
"learning_rate": 3.1431808816120413e-05,
"loss": 3.9528,
"step": 1134080
},
{
"epoch": 1.02,
"learning_rate": 3.1423422868609893e-05,
"loss": 3.9631,
"step": 1134592
},
{
"epoch": 1.02,
"learning_rate": 3.14150532999031e-05,
"loss": 3.9643,
"step": 1135104
},
{
"epoch": 1.02,
"learning_rate": 3.140668373119632e-05,
"loss": 3.9719,
"step": 1135616
},
{
"epoch": 1.02,
"learning_rate": 3.13982977836858e-05,
"loss": 3.9605,
"step": 1136128
},
{
"epoch": 1.02,
"learning_rate": 3.138991183617527e-05,
"loss": 3.9661,
"step": 1136640
},
{
"epoch": 1.02,
"learning_rate": 3.138152588866475e-05,
"loss": 3.9703,
"step": 1137152
},
{
"epoch": 1.02,
"learning_rate": 3.137313994115423e-05,
"loss": 3.96,
"step": 1137664
},
{
"epoch": 1.02,
"learning_rate": 3.136475399364371e-05,
"loss": 3.967,
"step": 1138176
},
{
"epoch": 1.02,
"learning_rate": 3.135636804613319e-05,
"loss": 3.9596,
"step": 1138688
},
{
"epoch": 1.02,
"learning_rate": 3.134798209862267e-05,
"loss": 3.9683,
"step": 1139200
},
{
"epoch": 1.02,
"learning_rate": 3.133959615111216e-05,
"loss": 3.9703,
"step": 1139712
},
{
"epoch": 1.02,
"learning_rate": 3.133121020360164e-05,
"loss": 3.9586,
"step": 1140224
},
{
"epoch": 1.02,
"learning_rate": 3.132282425609112e-05,
"loss": 3.9628,
"step": 1140736
},
{
"epoch": 1.02,
"learning_rate": 3.13144383085806e-05,
"loss": 3.9694,
"step": 1141248
},
{
"epoch": 1.02,
"learning_rate": 3.1306085118677536e-05,
"loss": 3.9567,
"step": 1141760
},
{
"epoch": 1.02,
"learning_rate": 3.1297699171167016e-05,
"loss": 3.959,
"step": 1142272
},
{
"epoch": 1.02,
"learning_rate": 3.1289313223656496e-05,
"loss": 3.965,
"step": 1142784
},
{
"epoch": 1.02,
"learning_rate": 3.1280927276145976e-05,
"loss": 3.9551,
"step": 1143296
},
{
"epoch": 1.02,
"learning_rate": 3.1272541328635456e-05,
"loss": 3.9725,
"step": 1143808
},
{
"epoch": 1.02,
"learning_rate": 3.1264155381124936e-05,
"loss": 3.9503,
"step": 1144320
},
{
"epoch": 1.03,
"eval_loss": 4.02056884765625,
"eval_runtime": 301.2116,
"eval_samples_per_second": 1266.854,
"eval_steps_per_second": 39.59,
"step": 1144800
},
{
"epoch": 0.0,
"learning_rate": 3.1255769433614416e-05,
"loss": 3.9199,
"step": 1144832
},
{
"epoch": 0.0,
"learning_rate": 3.1247383486103896e-05,
"loss": 3.9576,
"step": 1145344
},
{
"epoch": 0.0,
"learning_rate": 3.1238997538593376e-05,
"loss": 3.9512,
"step": 1145856
},
{
"epoch": 0.0,
"learning_rate": 3.1230611591082856e-05,
"loss": 3.9654,
"step": 1146368
},
{
"epoch": 0.0,
"learning_rate": 3.122222564357234e-05,
"loss": 3.9644,
"step": 1146880
},
{
"epoch": 0.0,
"learning_rate": 3.1213839696061816e-05,
"loss": 3.9639,
"step": 1147392
},
{
"epoch": 0.0,
"learning_rate": 3.1205453748551296e-05,
"loss": 3.9552,
"step": 1147904
},
{
"epoch": 0.0,
"learning_rate": 3.1197067801040776e-05,
"loss": 3.9538,
"step": 1148416
},
{
"epoch": 0.0,
"learning_rate": 3.1188681853530256e-05,
"loss": 3.9536,
"step": 1148928
},
{
"epoch": 0.0,
"learning_rate": 3.1180295906019735e-05,
"loss": 3.9665,
"step": 1149440
},
{
"epoch": 0.0,
"learning_rate": 3.1171909958509215e-05,
"loss": 3.9642,
"step": 1149952
},
{
"epoch": 0.0,
"learning_rate": 3.1163524010998695e-05,
"loss": 3.966,
"step": 1150464
},
{
"epoch": 0.0,
"learning_rate": 3.1155154442291904e-05,
"loss": 3.9618,
"step": 1150976
},
{
"epoch": 0.0,
"learning_rate": 3.1146768494781384e-05,
"loss": 3.9502,
"step": 1151488
},
{
"epoch": 0.0,
"learning_rate": 3.1138382547270864e-05,
"loss": 3.9569,
"step": 1152000
},
{
"epoch": 0.0,
"learning_rate": 3.1129996599760344e-05,
"loss": 3.949,
"step": 1152512
},
{
"epoch": 0.0,
"learning_rate": 3.1121610652249824e-05,
"loss": 3.9611,
"step": 1153024
},
{
"epoch": 0.0,
"learning_rate": 3.111322470473931e-05,
"loss": 3.9542,
"step": 1153536
},
{
"epoch": 0.0,
"learning_rate": 3.110483875722879e-05,
"loss": 3.9542,
"step": 1154048
},
{
"epoch": 0.0,
"learning_rate": 3.109645280971827e-05,
"loss": 3.9562,
"step": 1154560
},
{
"epoch": 0.0,
"learning_rate": 3.108806686220775e-05,
"loss": 3.9684,
"step": 1155072
},
{
"epoch": 0.0,
"learning_rate": 3.1079680914697224e-05,
"loss": 3.9669,
"step": 1155584
},
{
"epoch": 0.0,
"learning_rate": 3.107131134599044e-05,
"loss": 3.9602,
"step": 1156096
},
{
"epoch": 0.0,
"learning_rate": 3.106292539847992e-05,
"loss": 3.9587,
"step": 1156608
},
{
"epoch": 0.0,
"learning_rate": 3.105455582977313e-05,
"loss": 3.9639,
"step": 1157120
},
{
"epoch": 0.0,
"learning_rate": 3.104616988226261e-05,
"loss": 3.9602,
"step": 1157632
},
{
"epoch": 0.0,
"learning_rate": 3.103778393475209e-05,
"loss": 3.9514,
"step": 1158144
},
{
"epoch": 0.0,
"learning_rate": 3.10294143660453e-05,
"loss": 3.9607,
"step": 1158656
},
{
"epoch": 0.0,
"learning_rate": 3.102102841853478e-05,
"loss": 3.947,
"step": 1159168
},
{
"epoch": 0.0,
"learning_rate": 3.1012642471024265e-05,
"loss": 3.9505,
"step": 1159680
},
{
"epoch": 0.01,
"learning_rate": 3.1004256523513745e-05,
"loss": 3.9564,
"step": 1160192
},
{
"epoch": 0.01,
"learning_rate": 3.0995870576003225e-05,
"loss": 3.9563,
"step": 1160704
},
{
"epoch": 0.01,
"learning_rate": 3.09874846284927e-05,
"loss": 3.9629,
"step": 1161216
},
{
"epoch": 0.01,
"learning_rate": 3.097909868098218e-05,
"loss": 3.9611,
"step": 1161728
},
{
"epoch": 0.01,
"learning_rate": 3.097071273347166e-05,
"loss": 3.9589,
"step": 1162240
},
{
"epoch": 0.01,
"learning_rate": 3.096232678596114e-05,
"loss": 3.9633,
"step": 1162752
},
{
"epoch": 0.01,
"learning_rate": 3.095394083845062e-05,
"loss": 3.9667,
"step": 1163264
},
{
"epoch": 0.01,
"learning_rate": 3.09455548909401e-05,
"loss": 3.9467,
"step": 1163776
},
{
"epoch": 0.01,
"learning_rate": 3.093716894342958e-05,
"loss": 3.9567,
"step": 1164288
},
{
"epoch": 0.01,
"learning_rate": 3.092878299591906e-05,
"loss": 3.9439,
"step": 1164800
},
{
"epoch": 0.01,
"learning_rate": 3.092039704840854e-05,
"loss": 3.9517,
"step": 1165312
},
{
"epoch": 0.01,
"learning_rate": 3.0912027479701747e-05,
"loss": 3.9533,
"step": 1165824
},
{
"epoch": 0.01,
"learning_rate": 3.0903641532191227e-05,
"loss": 3.9612,
"step": 1166336
},
{
"epoch": 0.01,
"learning_rate": 3.089525558468071e-05,
"loss": 3.9514,
"step": 1166848
},
{
"epoch": 0.01,
"learning_rate": 3.088686963717019e-05,
"loss": 3.9513,
"step": 1167360
},
{
"epoch": 0.01,
"learning_rate": 3.087848368965967e-05,
"loss": 3.9627,
"step": 1167872
},
{
"epoch": 0.01,
"learning_rate": 3.087009774214915e-05,
"loss": 3.9536,
"step": 1168384
},
{
"epoch": 0.01,
"learning_rate": 3.086171179463863e-05,
"loss": 3.9502,
"step": 1168896
},
{
"epoch": 0.01,
"learning_rate": 3.085332584712811e-05,
"loss": 3.9304,
"step": 1169408
},
{
"epoch": 0.01,
"learning_rate": 3.084497265722505e-05,
"loss": 3.9601,
"step": 1169920
},
{
"epoch": 0.01,
"learning_rate": 3.083658670971453e-05,
"loss": 3.9546,
"step": 1170432
},
{
"epoch": 0.01,
"learning_rate": 3.082820076220401e-05,
"loss": 3.9614,
"step": 1170944
},
{
"epoch": 0.01,
"learning_rate": 3.081981481469349e-05,
"loss": 3.9486,
"step": 1171456
},
{
"epoch": 0.01,
"learning_rate": 3.081142886718297e-05,
"loss": 3.944,
"step": 1171968
},
{
"epoch": 0.01,
"learning_rate": 3.080304291967245e-05,
"loss": 3.9476,
"step": 1172480
},
{
"epoch": 0.01,
"learning_rate": 3.079467335096567e-05,
"loss": 3.9444,
"step": 1172992
},
{
"epoch": 0.01,
"learning_rate": 3.078628740345515e-05,
"loss": 3.957,
"step": 1173504
},
{
"epoch": 0.01,
"learning_rate": 3.077790145594463e-05,
"loss": 3.9414,
"step": 1174016
},
{
"epoch": 0.01,
"learning_rate": 3.076951550843411e-05,
"loss": 3.9596,
"step": 1174528
},
{
"epoch": 0.01,
"learning_rate": 3.076112956092359e-05,
"loss": 3.9509,
"step": 1175040
},
{
"epoch": 0.01,
"learning_rate": 3.075274361341306e-05,
"loss": 3.9432,
"step": 1175552
},
{
"epoch": 0.01,
"learning_rate": 3.074435766590254e-05,
"loss": 3.9549,
"step": 1176064
},
{
"epoch": 0.01,
"learning_rate": 3.073597171839202e-05,
"loss": 3.9487,
"step": 1176576
},
{
"epoch": 0.01,
"learning_rate": 3.07275857708815e-05,
"loss": 3.9465,
"step": 1177088
},
{
"epoch": 0.01,
"learning_rate": 3.0719232580978445e-05,
"loss": 3.9424,
"step": 1177600
},
{
"epoch": 0.01,
"learning_rate": 3.0710846633467925e-05,
"loss": 3.9598,
"step": 1178112
},
{
"epoch": 0.01,
"learning_rate": 3.0702460685957405e-05,
"loss": 3.9493,
"step": 1178624
},
{
"epoch": 0.01,
"learning_rate": 3.0694074738446885e-05,
"loss": 3.9523,
"step": 1179136
},
{
"epoch": 0.01,
"learning_rate": 3.0685688790936365e-05,
"loss": 3.9405,
"step": 1179648
},
{
"epoch": 0.01,
"learning_rate": 3.0677302843425845e-05,
"loss": 3.9465,
"step": 1180160
},
{
"epoch": 0.01,
"learning_rate": 3.0668916895915325e-05,
"loss": 3.9511,
"step": 1180672
},
{
"epoch": 0.01,
"learning_rate": 3.0660530948404804e-05,
"loss": 3.9659,
"step": 1181184
},
{
"epoch": 0.01,
"learning_rate": 3.0652161379698014e-05,
"loss": 3.95,
"step": 1181696
},
{
"epoch": 0.01,
"learning_rate": 3.0643775432187494e-05,
"loss": 3.9571,
"step": 1182208
},
{
"epoch": 0.01,
"learning_rate": 3.0635389484676973e-05,
"loss": 3.9649,
"step": 1182720
},
{
"epoch": 0.01,
"learning_rate": 3.0627003537166453e-05,
"loss": 3.9573,
"step": 1183232
},
{
"epoch": 0.01,
"learning_rate": 3.061863396845966e-05,
"loss": 3.9503,
"step": 1183744
},
{
"epoch": 0.01,
"learning_rate": 3.061024802094914e-05,
"loss": 3.9571,
"step": 1184256
},
{
"epoch": 0.01,
"learning_rate": 3.060186207343862e-05,
"loss": 3.9579,
"step": 1184768
},
{
"epoch": 0.01,
"learning_rate": 3.05934761259281e-05,
"loss": 3.9503,
"step": 1185280
},
{
"epoch": 0.01,
"learning_rate": 3.058510655722132e-05,
"loss": 3.9532,
"step": 1185792
},
{
"epoch": 0.01,
"learning_rate": 3.05767206097108e-05,
"loss": 3.9643,
"step": 1186304
},
{
"epoch": 0.01,
"learning_rate": 3.056835104100401e-05,
"loss": 3.9651,
"step": 1186816
},
{
"epoch": 0.01,
"learning_rate": 3.055996509349349e-05,
"loss": 3.9515,
"step": 1187328
},
{
"epoch": 0.01,
"learning_rate": 3.05515955247867e-05,
"loss": 3.9359,
"step": 1187840
},
{
"epoch": 0.01,
"learning_rate": 3.054320957727618e-05,
"loss": 3.9467,
"step": 1188352
},
{
"epoch": 0.01,
"learning_rate": 3.0534823629765656e-05,
"loss": 3.9586,
"step": 1188864
},
{
"epoch": 0.01,
"learning_rate": 3.0526437682255136e-05,
"loss": 3.9519,
"step": 1189376
},
{
"epoch": 0.01,
"learning_rate": 3.0518051734744616e-05,
"loss": 3.958,
"step": 1189888
},
{
"epoch": 0.01,
"learning_rate": 3.05096657872341e-05,
"loss": 3.9517,
"step": 1190400
},
{
"epoch": 0.02,
"learning_rate": 3.050127983972358e-05,
"loss": 3.9456,
"step": 1190912
},
{
"epoch": 0.02,
"learning_rate": 3.049289389221306e-05,
"loss": 3.9443,
"step": 1191424
},
{
"epoch": 0.02,
"learning_rate": 3.048450794470254e-05,
"loss": 3.9452,
"step": 1191936
},
{
"epoch": 0.02,
"learning_rate": 3.047612199719202e-05,
"loss": 3.959,
"step": 1192448
},
{
"epoch": 0.02,
"learning_rate": 3.04677360496815e-05,
"loss": 3.951,
"step": 1192960
},
{
"epoch": 0.02,
"learning_rate": 3.045935010217098e-05,
"loss": 3.972,
"step": 1193472
},
{
"epoch": 0.02,
"learning_rate": 3.045096415466046e-05,
"loss": 3.9484,
"step": 1193984
},
{
"epoch": 0.02,
"learning_rate": 3.0442594585953672e-05,
"loss": 3.9482,
"step": 1194496
},
{
"epoch": 0.02,
"learning_rate": 3.043420863844315e-05,
"loss": 3.9507,
"step": 1195008
},
{
"epoch": 0.02,
"learning_rate": 3.042582269093263e-05,
"loss": 3.9565,
"step": 1195520
},
{
"epoch": 0.02,
"learning_rate": 3.041743674342211e-05,
"loss": 3.9572,
"step": 1196032
},
{
"epoch": 0.02,
"learning_rate": 3.040905079591159e-05,
"loss": 3.9527,
"step": 1196544
},
{
"epoch": 0.02,
"learning_rate": 3.040066484840107e-05,
"loss": 3.9566,
"step": 1197056
},
{
"epoch": 0.02,
"learning_rate": 3.0392278900890548e-05,
"loss": 3.9425,
"step": 1197568
},
{
"epoch": 0.02,
"learning_rate": 3.0383909332183764e-05,
"loss": 3.9591,
"step": 1198080
},
{
"epoch": 0.02,
"learning_rate": 3.0375523384673244e-05,
"loss": 3.9328,
"step": 1198592
},
{
"epoch": 0.02,
"learning_rate": 3.0367137437162717e-05,
"loss": 3.9456,
"step": 1199104
},
{
"epoch": 0.02,
"learning_rate": 3.0358751489652197e-05,
"loss": 3.9535,
"step": 1199616
},
{
"epoch": 0.02,
"learning_rate": 3.035036554214168e-05,
"loss": 3.9526,
"step": 1200128
},
{
"epoch": 0.02,
"learning_rate": 3.034197959463116e-05,
"loss": 3.9448,
"step": 1200640
},
{
"epoch": 0.02,
"learning_rate": 3.033359364712064e-05,
"loss": 3.949,
"step": 1201152
},
{
"epoch": 0.02,
"learning_rate": 3.032520769961012e-05,
"loss": 3.9375,
"step": 1201664
},
{
"epoch": 0.02,
"learning_rate": 3.031683813090333e-05,
"loss": 3.9535,
"step": 1202176
},
{
"epoch": 0.02,
"learning_rate": 3.030845218339281e-05,
"loss": 3.9467,
"step": 1202688
},
{
"epoch": 0.02,
"learning_rate": 3.030006623588229e-05,
"loss": 3.9557,
"step": 1203200
},
{
"epoch": 0.02,
"learning_rate": 3.0291680288371773e-05,
"loss": 3.9579,
"step": 1203712
},
{
"epoch": 0.02,
"learning_rate": 3.0283294340861253e-05,
"loss": 3.96,
"step": 1204224
},
{
"epoch": 0.02,
"learning_rate": 3.027494115095819e-05,
"loss": 3.9495,
"step": 1204736
},
{
"epoch": 0.02,
"learning_rate": 3.026655520344767e-05,
"loss": 3.9517,
"step": 1205248
},
{
"epoch": 0.02,
"learning_rate": 3.025816925593715e-05,
"loss": 3.9519,
"step": 1205760
},
{
"epoch": 0.02,
"learning_rate": 3.0249783308426634e-05,
"loss": 3.9502,
"step": 1206272
},
{
"epoch": 0.02,
"learning_rate": 3.0241397360916114e-05,
"loss": 3.9518,
"step": 1206784
},
{
"epoch": 0.02,
"learning_rate": 3.0233011413405594e-05,
"loss": 3.9464,
"step": 1207296
},
{
"epoch": 0.02,
"learning_rate": 3.0224625465895074e-05,
"loss": 3.9511,
"step": 1207808
},
{
"epoch": 0.02,
"learning_rate": 3.0216239518384554e-05,
"loss": 3.9445,
"step": 1208320
},
{
"epoch": 0.02,
"learning_rate": 3.0207853570874034e-05,
"loss": 3.9436,
"step": 1208832
},
{
"epoch": 0.02,
"learning_rate": 3.0199467623363514e-05,
"loss": 3.9458,
"step": 1209344
},
{
"epoch": 0.02,
"learning_rate": 3.0191081675852994e-05,
"loss": 3.9472,
"step": 1209856
},
{
"epoch": 0.02,
"learning_rate": 3.0182695728342474e-05,
"loss": 3.9472,
"step": 1210368
},
{
"epoch": 0.02,
"learning_rate": 3.0174342538439415e-05,
"loss": 3.9465,
"step": 1210880
},
{
"epoch": 0.02,
"learning_rate": 3.0165956590928895e-05,
"loss": 3.9551,
"step": 1211392
},
{
"epoch": 0.02,
"learning_rate": 3.0157570643418375e-05,
"loss": 3.9639,
"step": 1211904
},
{
"epoch": 0.02,
"learning_rate": 3.0149184695907855e-05,
"loss": 3.9431,
"step": 1212416
},
{
"epoch": 0.02,
"learning_rate": 3.0140815127201068e-05,
"loss": 3.9538,
"step": 1212928
},
{
"epoch": 0.02,
"learning_rate": 3.0132429179690548e-05,
"loss": 3.9593,
"step": 1213440
},
{
"epoch": 0.02,
"learning_rate": 3.0124043232180028e-05,
"loss": 3.951,
"step": 1213952
},
{
"epoch": 0.02,
"learning_rate": 3.0115657284669508e-05,
"loss": 3.9558,
"step": 1214464
},
{
"epoch": 0.02,
"learning_rate": 3.0107271337158987e-05,
"loss": 3.947,
"step": 1214976
},
{
"epoch": 0.02,
"learning_rate": 3.0098885389648467e-05,
"loss": 3.9573,
"step": 1215488
},
{
"epoch": 0.02,
"learning_rate": 3.0090499442137947e-05,
"loss": 3.9522,
"step": 1216000
},
{
"epoch": 0.02,
"learning_rate": 3.0082113494627427e-05,
"loss": 3.9508,
"step": 1216512
},
{
"epoch": 0.02,
"learning_rate": 3.007374392592064e-05,
"loss": 3.9519,
"step": 1217024
},
{
"epoch": 0.02,
"learning_rate": 3.006535797841012e-05,
"loss": 3.9521,
"step": 1217536
},
{
"epoch": 0.02,
"learning_rate": 3.00569720308996e-05,
"loss": 3.9481,
"step": 1218048
},
{
"epoch": 0.02,
"learning_rate": 3.004860246219281e-05,
"loss": 3.9458,
"step": 1218560
},
{
"epoch": 0.02,
"learning_rate": 3.004021651468229e-05,
"loss": 3.9527,
"step": 1219072
},
{
"epoch": 0.02,
"learning_rate": 3.003183056717177e-05,
"loss": 3.9455,
"step": 1219584
},
{
"epoch": 0.02,
"learning_rate": 3.0023444619661252e-05,
"loss": 3.9587,
"step": 1220096
},
{
"epoch": 0.02,
"learning_rate": 3.0015058672150732e-05,
"loss": 3.9389,
"step": 1220608
},
{
"epoch": 0.03,
"learning_rate": 3.0006672724640205e-05,
"loss": 3.9479,
"step": 1221120
},
{
"epoch": 0.03,
"eval_loss": 4.014168739318848,
"eval_runtime": 298.8924,
"eval_samples_per_second": 1276.683,
"eval_steps_per_second": 39.897,
"step": 1221120
},
{
"epoch": 1.0,
"learning_rate": 2.9998286777129685e-05,
"loss": 3.9436,
"step": 1221632
},
{
"epoch": 1.0,
"learning_rate": 2.9989900829619165e-05,
"loss": 3.9403,
"step": 1222144
},
{
"epoch": 1.0,
"learning_rate": 2.998153126091238e-05,
"loss": 3.9526,
"step": 1222656
},
{
"epoch": 1.0,
"learning_rate": 2.9973161692205593e-05,
"loss": 3.9527,
"step": 1223168
},
{
"epoch": 1.0,
"learning_rate": 2.9964775744695073e-05,
"loss": 3.9546,
"step": 1223680
},
{
"epoch": 1.0,
"learning_rate": 2.9956389797184553e-05,
"loss": 3.9433,
"step": 1224192
},
{
"epoch": 1.0,
"learning_rate": 2.9948003849674027e-05,
"loss": 3.9424,
"step": 1224704
},
{
"epoch": 1.0,
"learning_rate": 2.9939617902163507e-05,
"loss": 3.9358,
"step": 1225216
},
{
"epoch": 1.0,
"learning_rate": 2.993123195465299e-05,
"loss": 3.9575,
"step": 1225728
},
{
"epoch": 1.0,
"learning_rate": 2.9922862385946206e-05,
"loss": 3.9469,
"step": 1226240
},
{
"epoch": 1.0,
"learning_rate": 2.991447643843568e-05,
"loss": 3.9611,
"step": 1226752
},
{
"epoch": 1.0,
"learning_rate": 2.990609049092516e-05,
"loss": 3.9489,
"step": 1227264
},
{
"epoch": 1.0,
"learning_rate": 2.989770454341464e-05,
"loss": 3.9396,
"step": 1227776
},
{
"epoch": 1.0,
"learning_rate": 2.988931859590412e-05,
"loss": 3.9433,
"step": 1228288
},
{
"epoch": 1.0,
"learning_rate": 2.98809326483936e-05,
"loss": 3.9402,
"step": 1228800
},
{
"epoch": 1.0,
"learning_rate": 2.9872546700883082e-05,
"loss": 3.9469,
"step": 1229312
},
{
"epoch": 1.0,
"learning_rate": 2.9864160753372562e-05,
"loss": 3.9482,
"step": 1229824
},
{
"epoch": 1.0,
"learning_rate": 2.985579118466577e-05,
"loss": 3.9398,
"step": 1230336
},
{
"epoch": 1.0,
"learning_rate": 2.984742161595898e-05,
"loss": 3.9448,
"step": 1230848
},
{
"epoch": 1.0,
"learning_rate": 2.983903566844846e-05,
"loss": 3.9585,
"step": 1231360
},
{
"epoch": 1.0,
"learning_rate": 2.9830649720937944e-05,
"loss": 3.9488,
"step": 1231872
},
{
"epoch": 1.0,
"learning_rate": 2.9822263773427424e-05,
"loss": 3.9549,
"step": 1232384
},
{
"epoch": 1.0,
"learning_rate": 2.9813877825916903e-05,
"loss": 3.9423,
"step": 1232896
},
{
"epoch": 1.0,
"learning_rate": 2.9805491878406383e-05,
"loss": 3.9567,
"step": 1233408
},
{
"epoch": 1.0,
"learning_rate": 2.9797122309699593e-05,
"loss": 3.9465,
"step": 1233920
},
{
"epoch": 1.0,
"learning_rate": 2.9788736362189072e-05,
"loss": 3.9455,
"step": 1234432
},
{
"epoch": 1.0,
"learning_rate": 2.9780350414678552e-05,
"loss": 3.9478,
"step": 1234944
},
{
"epoch": 1.0,
"learning_rate": 2.9771964467168036e-05,
"loss": 3.934,
"step": 1235456
},
{
"epoch": 1.0,
"learning_rate": 2.9763594898461245e-05,
"loss": 3.9413,
"step": 1235968
},
{
"epoch": 1.01,
"learning_rate": 2.9755208950950725e-05,
"loss": 3.9401,
"step": 1236480
},
{
"epoch": 1.01,
"learning_rate": 2.9746823003440205e-05,
"loss": 3.949,
"step": 1236992
},
{
"epoch": 1.01,
"learning_rate": 2.9738437055929685e-05,
"loss": 3.9486,
"step": 1237504
},
{
"epoch": 1.01,
"learning_rate": 2.9730051108419165e-05,
"loss": 3.95,
"step": 1238016
},
{
"epoch": 1.01,
"learning_rate": 2.9721665160908645e-05,
"loss": 3.95,
"step": 1238528
},
{
"epoch": 1.01,
"learning_rate": 2.9713295592201857e-05,
"loss": 3.95,
"step": 1239040
},
{
"epoch": 1.01,
"learning_rate": 2.9704909644691337e-05,
"loss": 3.9517,
"step": 1239552
},
{
"epoch": 1.01,
"learning_rate": 2.9696523697180817e-05,
"loss": 3.936,
"step": 1240064
},
{
"epoch": 1.01,
"learning_rate": 2.9688137749670297e-05,
"loss": 3.947,
"step": 1240576
},
{
"epoch": 1.01,
"learning_rate": 2.9679768180963506e-05,
"loss": 3.9314,
"step": 1241088
},
{
"epoch": 1.01,
"learning_rate": 2.967138223345299e-05,
"loss": 3.9452,
"step": 1241600
},
{
"epoch": 1.01,
"learning_rate": 2.966299628594247e-05,
"loss": 3.937,
"step": 1242112
},
{
"epoch": 1.01,
"learning_rate": 2.965461033843195e-05,
"loss": 3.951,
"step": 1242624
},
{
"epoch": 1.01,
"learning_rate": 2.964624076972516e-05,
"loss": 3.9393,
"step": 1243136
},
{
"epoch": 1.01,
"learning_rate": 2.963785482221464e-05,
"loss": 3.9433,
"step": 1243648
},
{
"epoch": 1.01,
"learning_rate": 2.962946887470412e-05,
"loss": 3.9477,
"step": 1244160
},
{
"epoch": 1.01,
"learning_rate": 2.96210829271936e-05,
"loss": 3.9421,
"step": 1244672
},
{
"epoch": 1.01,
"learning_rate": 2.961269697968308e-05,
"loss": 3.9399,
"step": 1245184
},
{
"epoch": 1.01,
"learning_rate": 2.960431103217256e-05,
"loss": 3.9211,
"step": 1245696
},
{
"epoch": 1.01,
"learning_rate": 2.959592508466204e-05,
"loss": 3.9427,
"step": 1246208
},
{
"epoch": 1.01,
"learning_rate": 2.9587539137151515e-05,
"loss": 3.9476,
"step": 1246720
},
{
"epoch": 1.01,
"learning_rate": 2.9579153189640995e-05,
"loss": 3.9479,
"step": 1247232
},
{
"epoch": 1.01,
"learning_rate": 2.957078362093421e-05,
"loss": 3.9345,
"step": 1247744
},
{
"epoch": 1.01,
"learning_rate": 2.9562397673423687e-05,
"loss": 3.9325,
"step": 1248256
},
{
"epoch": 1.01,
"learning_rate": 2.9554011725913167e-05,
"loss": 3.9357,
"step": 1248768
},
{
"epoch": 1.01,
"learning_rate": 2.9545625778402647e-05,
"loss": 3.9312,
"step": 1249280
},
{
"epoch": 1.01,
"learning_rate": 2.9537239830892127e-05,
"loss": 3.9528,
"step": 1249792
},
{
"epoch": 1.01,
"learning_rate": 2.9528853883381607e-05,
"loss": 3.9259,
"step": 1250304
},
{
"epoch": 1.01,
"learning_rate": 2.9520467935871087e-05,
"loss": 3.9486,
"step": 1250816
},
{
"epoch": 1.01,
"learning_rate": 2.95120983671643e-05,
"loss": 3.9442,
"step": 1251328
},
{
"epoch": 1.01,
"learning_rate": 2.950371241965378e-05,
"loss": 3.9285,
"step": 1251840
},
{
"epoch": 1.01,
"learning_rate": 2.949532647214326e-05,
"loss": 3.9412,
"step": 1252352
},
{
"epoch": 1.01,
"learning_rate": 2.948694052463274e-05,
"loss": 3.9375,
"step": 1252864
},
{
"epoch": 1.01,
"learning_rate": 2.947855457712222e-05,
"loss": 3.9339,
"step": 1253376
},
{
"epoch": 1.01,
"learning_rate": 2.94701686296117e-05,
"loss": 3.9343,
"step": 1253888
},
{
"epoch": 1.01,
"learning_rate": 2.946178268210118e-05,
"loss": 3.9493,
"step": 1254400
},
{
"epoch": 1.01,
"learning_rate": 2.945339673459066e-05,
"loss": 3.938,
"step": 1254912
},
{
"epoch": 1.01,
"learning_rate": 2.944501078708014e-05,
"loss": 3.9357,
"step": 1255424
},
{
"epoch": 1.01,
"learning_rate": 2.943664121837335e-05,
"loss": 3.9337,
"step": 1255936
},
{
"epoch": 1.01,
"learning_rate": 2.942825527086283e-05,
"loss": 3.9334,
"step": 1256448
},
{
"epoch": 1.01,
"learning_rate": 2.941988570215604e-05,
"loss": 3.9407,
"step": 1256960
},
{
"epoch": 1.01,
"learning_rate": 2.941149975464552e-05,
"loss": 3.9545,
"step": 1257472
},
{
"epoch": 1.01,
"learning_rate": 2.9403113807135e-05,
"loss": 3.9379,
"step": 1257984
},
{
"epoch": 1.01,
"learning_rate": 2.9394727859624484e-05,
"loss": 3.9482,
"step": 1258496
},
{
"epoch": 1.01,
"learning_rate": 2.9386341912113964e-05,
"loss": 3.9554,
"step": 1259008
},
{
"epoch": 1.01,
"learning_rate": 2.9377955964603444e-05,
"loss": 3.9461,
"step": 1259520
},
{
"epoch": 1.01,
"learning_rate": 2.9369586395896653e-05,
"loss": 3.9394,
"step": 1260032
},
{
"epoch": 1.01,
"learning_rate": 2.9361200448386133e-05,
"loss": 3.945,
"step": 1260544
},
{
"epoch": 1.01,
"learning_rate": 2.9352814500875613e-05,
"loss": 3.9472,
"step": 1261056
},
{
"epoch": 1.01,
"learning_rate": 2.9344444932168825e-05,
"loss": 3.9406,
"step": 1261568
},
{
"epoch": 1.01,
"learning_rate": 2.9336058984658305e-05,
"loss": 3.9388,
"step": 1262080
},
{
"epoch": 1.01,
"learning_rate": 2.9327673037147785e-05,
"loss": 3.9531,
"step": 1262592
},
{
"epoch": 1.01,
"learning_rate": 2.9319287089637265e-05,
"loss": 3.9537,
"step": 1263104
},
{
"epoch": 1.01,
"learning_rate": 2.9310901142126745e-05,
"loss": 3.9407,
"step": 1263616
},
{
"epoch": 1.01,
"learning_rate": 2.9302515194616225e-05,
"loss": 3.9227,
"step": 1264128
},
{
"epoch": 1.01,
"learning_rate": 2.92941292471057e-05,
"loss": 3.9386,
"step": 1264640
},
{
"epoch": 1.01,
"learning_rate": 2.928574329959518e-05,
"loss": 3.9491,
"step": 1265152
},
{
"epoch": 1.01,
"learning_rate": 2.927735735208466e-05,
"loss": 3.9408,
"step": 1265664
},
{
"epoch": 1.01,
"learning_rate": 2.926897140457414e-05,
"loss": 3.9505,
"step": 1266176
},
{
"epoch": 1.01,
"learning_rate": 2.926060183586735e-05,
"loss": 3.9357,
"step": 1266688
},
{
"epoch": 1.02,
"learning_rate": 2.925221588835683e-05,
"loss": 3.9393,
"step": 1267200
},
{
"epoch": 1.02,
"learning_rate": 2.9243829940846314e-05,
"loss": 3.9342,
"step": 1267712
},
{
"epoch": 1.02,
"learning_rate": 2.9235443993335794e-05,
"loss": 3.9335,
"step": 1268224
},
{
"epoch": 1.02,
"learning_rate": 2.9227058045825274e-05,
"loss": 3.9469,
"step": 1268736
},
{
"epoch": 1.02,
"learning_rate": 2.9218672098314754e-05,
"loss": 3.9395,
"step": 1269248
},
{
"epoch": 1.02,
"learning_rate": 2.9210286150804234e-05,
"loss": 3.9575,
"step": 1269760
},
{
"epoch": 1.02,
"learning_rate": 2.9201932960901175e-05,
"loss": 3.9445,
"step": 1270272
},
{
"epoch": 1.02,
"learning_rate": 2.9193547013390655e-05,
"loss": 3.9329,
"step": 1270784
},
{
"epoch": 1.02,
"learning_rate": 2.9185161065880135e-05,
"loss": 3.9405,
"step": 1271296
},
{
"epoch": 1.02,
"learning_rate": 2.9176775118369615e-05,
"loss": 3.9468,
"step": 1271808
},
{
"epoch": 1.02,
"learning_rate": 2.9168389170859095e-05,
"loss": 3.9442,
"step": 1272320
},
{
"epoch": 1.02,
"learning_rate": 2.9160003223348575e-05,
"loss": 3.9446,
"step": 1272832
},
{
"epoch": 1.02,
"learning_rate": 2.9151617275838055e-05,
"loss": 3.944,
"step": 1273344
},
{
"epoch": 1.02,
"learning_rate": 2.9143247707131268e-05,
"loss": 3.9362,
"step": 1273856
},
{
"epoch": 1.02,
"learning_rate": 2.9134861759620747e-05,
"loss": 3.9449,
"step": 1274368
},
{
"epoch": 1.02,
"learning_rate": 2.9126475812110227e-05,
"loss": 3.9267,
"step": 1274880
},
{
"epoch": 1.02,
"learning_rate": 2.9118089864599707e-05,
"loss": 3.9349,
"step": 1275392
},
{
"epoch": 1.02,
"learning_rate": 2.9109703917089187e-05,
"loss": 3.9425,
"step": 1275904
},
{
"epoch": 1.02,
"learning_rate": 2.9101317969578667e-05,
"loss": 3.9398,
"step": 1276416
},
{
"epoch": 1.02,
"learning_rate": 2.9092932022068147e-05,
"loss": 3.9328,
"step": 1276928
},
{
"epoch": 1.02,
"learning_rate": 2.9084546074557627e-05,
"loss": 3.9434,
"step": 1277440
},
{
"epoch": 1.02,
"learning_rate": 2.9076160127047107e-05,
"loss": 3.9263,
"step": 1277952
},
{
"epoch": 1.02,
"learning_rate": 2.9067774179536587e-05,
"loss": 3.9396,
"step": 1278464
},
{
"epoch": 1.02,
"learning_rate": 2.905942098963353e-05,
"loss": 3.9317,
"step": 1278976
},
{
"epoch": 1.02,
"learning_rate": 2.905103504212301e-05,
"loss": 3.9451,
"step": 1279488
},
{
"epoch": 1.02,
"learning_rate": 2.904264909461249e-05,
"loss": 3.9495,
"step": 1280000
},
{
"epoch": 1.02,
"learning_rate": 2.903426314710197e-05,
"loss": 3.946,
"step": 1280512
},
{
"epoch": 1.02,
"learning_rate": 2.902587719959145e-05,
"loss": 3.9387,
"step": 1281024
},
{
"epoch": 1.02,
"learning_rate": 2.9017491252080932e-05,
"loss": 3.9382,
"step": 1281536
},
{
"epoch": 1.02,
"learning_rate": 2.9009105304570412e-05,
"loss": 3.9462,
"step": 1282048
},
{
"epoch": 1.02,
"learning_rate": 2.9000719357059885e-05,
"loss": 3.9386,
"step": 1282560
},
{
"epoch": 1.02,
"learning_rate": 2.8992333409549365e-05,
"loss": 3.94,
"step": 1283072
},
{
"epoch": 1.02,
"learning_rate": 2.898396384084258e-05,
"loss": 3.9377,
"step": 1283584
},
{
"epoch": 1.02,
"learning_rate": 2.897557789333206e-05,
"loss": 3.9367,
"step": 1284096
},
{
"epoch": 1.02,
"learning_rate": 2.8967191945821537e-05,
"loss": 3.939,
"step": 1284608
},
{
"epoch": 1.02,
"learning_rate": 2.8958805998311017e-05,
"loss": 3.9304,
"step": 1285120
},
{
"epoch": 1.02,
"learning_rate": 2.8950436429604233e-05,
"loss": 3.9356,
"step": 1285632
},
{
"epoch": 1.02,
"learning_rate": 2.8942050482093706e-05,
"loss": 3.9367,
"step": 1286144
},
{
"epoch": 1.02,
"learning_rate": 2.8933664534583186e-05,
"loss": 3.9352,
"step": 1286656
},
{
"epoch": 1.02,
"learning_rate": 2.892527858707267e-05,
"loss": 3.9302,
"step": 1287168
},
{
"epoch": 1.02,
"learning_rate": 2.891689263956215e-05,
"loss": 3.9501,
"step": 1287680
},
{
"epoch": 1.02,
"learning_rate": 2.890850669205163e-05,
"loss": 3.9519,
"step": 1288192
},
{
"epoch": 1.02,
"learning_rate": 2.890013712334484e-05,
"loss": 3.9412,
"step": 1288704
},
{
"epoch": 1.02,
"learning_rate": 2.889175117583432e-05,
"loss": 3.9353,
"step": 1289216
},
{
"epoch": 1.02,
"learning_rate": 2.88833652283238e-05,
"loss": 3.9433,
"step": 1289728
},
{
"epoch": 1.02,
"learning_rate": 2.887497928081328e-05,
"loss": 3.9445,
"step": 1290240
},
{
"epoch": 1.02,
"learning_rate": 2.8866593333302762e-05,
"loss": 3.9465,
"step": 1290752
},
{
"epoch": 1.02,
"learning_rate": 2.8858207385792242e-05,
"loss": 3.9407,
"step": 1291264
},
{
"epoch": 1.02,
"learning_rate": 2.8849821438281722e-05,
"loss": 3.9484,
"step": 1291776
},
{
"epoch": 1.02,
"learning_rate": 2.8841435490771202e-05,
"loss": 3.9412,
"step": 1292288
},
{
"epoch": 1.02,
"learning_rate": 2.8833049543260682e-05,
"loss": 3.941,
"step": 1292800
},
{
"epoch": 1.02,
"learning_rate": 2.8824663595750162e-05,
"loss": 3.9414,
"step": 1293312
},
{
"epoch": 1.02,
"learning_rate": 2.8816310405847103e-05,
"loss": 3.9436,
"step": 1293824
},
{
"epoch": 1.02,
"learning_rate": 2.8807924458336583e-05,
"loss": 3.9368,
"step": 1294336
},
{
"epoch": 1.02,
"learning_rate": 2.8799538510826063e-05,
"loss": 3.9348,
"step": 1294848
},
{
"epoch": 1.02,
"learning_rate": 2.8791168942119272e-05,
"loss": 3.9454,
"step": 1295360
},
{
"epoch": 1.02,
"learning_rate": 2.8782782994608752e-05,
"loss": 3.9365,
"step": 1295872
},
{
"epoch": 1.02,
"learning_rate": 2.8774397047098232e-05,
"loss": 3.9468,
"step": 1296384
},
{
"epoch": 1.02,
"learning_rate": 2.8766011099587716e-05,
"loss": 3.9349,
"step": 1296896
},
{
"epoch": 1.02,
"learning_rate": 2.8757625152077196e-05,
"loss": 3.931,
"step": 1297408
},
{
"epoch": 1.03,
"eval_loss": 4.009271144866943,
"eval_runtime": 297.3688,
"eval_samples_per_second": 1283.225,
"eval_steps_per_second": 40.102,
"step": 1297440
},
{
"epoch": 0.0,
"learning_rate": 2.8749239204566676e-05,
"loss": 3.9322,
"step": 1297920
},
{
"epoch": 0.0,
"learning_rate": 2.8740853257056155e-05,
"loss": 3.9337,
"step": 1298432
},
{
"epoch": 0.0,
"learning_rate": 2.8732467309545635e-05,
"loss": 3.9448,
"step": 1298944
},
{
"epoch": 0.0,
"learning_rate": 2.8724081362035115e-05,
"loss": 3.9396,
"step": 1299456
},
{
"epoch": 0.0,
"learning_rate": 2.8715695414524595e-05,
"loss": 3.9427,
"step": 1299968
},
{
"epoch": 0.0,
"learning_rate": 2.8707309467014072e-05,
"loss": 3.9374,
"step": 1300480
},
{
"epoch": 0.0,
"learning_rate": 2.8698923519503552e-05,
"loss": 3.9293,
"step": 1300992
},
{
"epoch": 0.0,
"learning_rate": 2.8690537571993032e-05,
"loss": 3.9296,
"step": 1301504
},
{
"epoch": 0.0,
"learning_rate": 2.8682151624482512e-05,
"loss": 3.9452,
"step": 1302016
},
{
"epoch": 0.0,
"learning_rate": 2.8673765676971992e-05,
"loss": 3.9394,
"step": 1302528
},
{
"epoch": 0.0,
"learning_rate": 2.866537972946147e-05,
"loss": 3.953,
"step": 1303040
},
{
"epoch": 0.0,
"learning_rate": 2.865699378195095e-05,
"loss": 3.936,
"step": 1303552
},
{
"epoch": 0.0,
"learning_rate": 2.864860783444043e-05,
"loss": 3.9335,
"step": 1304064
},
{
"epoch": 0.0,
"learning_rate": 2.8640221886929915e-05,
"loss": 3.932,
"step": 1304576
},
{
"epoch": 0.0,
"learning_rate": 2.8631835939419395e-05,
"loss": 3.9316,
"step": 1305088
},
{
"epoch": 0.0,
"learning_rate": 2.8623449991908875e-05,
"loss": 3.9284,
"step": 1305600
},
{
"epoch": 0.0,
"learning_rate": 2.8615064044398355e-05,
"loss": 3.9406,
"step": 1306112
},
{
"epoch": 0.0,
"learning_rate": 2.8606678096887835e-05,
"loss": 3.9316,
"step": 1306624
},
{
"epoch": 0.0,
"learning_rate": 2.8598308528181044e-05,
"loss": 3.931,
"step": 1307136
},
{
"epoch": 0.0,
"learning_rate": 2.8589922580670524e-05,
"loss": 3.9533,
"step": 1307648
},
{
"epoch": 0.0,
"learning_rate": 2.8581536633160004e-05,
"loss": 3.9393,
"step": 1308160
},
{
"epoch": 0.0,
"learning_rate": 2.8573150685649487e-05,
"loss": 3.9451,
"step": 1308672
},
{
"epoch": 0.0,
"learning_rate": 2.8564781116942696e-05,
"loss": 3.9329,
"step": 1309184
},
{
"epoch": 0.0,
"learning_rate": 2.8556395169432176e-05,
"loss": 3.9447,
"step": 1309696
},
{
"epoch": 0.0,
"learning_rate": 2.8548009221921656e-05,
"loss": 3.9325,
"step": 1310208
},
{
"epoch": 0.0,
"learning_rate": 2.8539623274411136e-05,
"loss": 3.9361,
"step": 1310720
},
{
"epoch": 0.0,
"learning_rate": 2.8531237326900613e-05,
"loss": 3.9353,
"step": 1311232
},
{
"epoch": 0.0,
"learning_rate": 2.8522851379390093e-05,
"loss": 3.9308,
"step": 1311744
},
{
"epoch": 0.0,
"learning_rate": 2.851448181068331e-05,
"loss": 3.9269,
"step": 1312256
},
{
"epoch": 0.01,
"learning_rate": 2.850609586317278e-05,
"loss": 3.9297,
"step": 1312768
},
{
"epoch": 0.01,
"learning_rate": 2.849770991566226e-05,
"loss": 3.9402,
"step": 1313280
},
{
"epoch": 0.01,
"learning_rate": 2.848932396815174e-05,
"loss": 3.9389,
"step": 1313792
},
{
"epoch": 0.01,
"learning_rate": 2.8480938020641225e-05,
"loss": 3.9374,
"step": 1314304
},
{
"epoch": 0.01,
"learning_rate": 2.8472568451934434e-05,
"loss": 3.9437,
"step": 1314816
},
{
"epoch": 0.01,
"learning_rate": 2.8464182504423914e-05,
"loss": 3.9407,
"step": 1315328
},
{
"epoch": 0.01,
"learning_rate": 2.8455796556913394e-05,
"loss": 3.9375,
"step": 1315840
},
{
"epoch": 0.01,
"learning_rate": 2.8447410609402874e-05,
"loss": 3.9283,
"step": 1316352
},
{
"epoch": 0.01,
"learning_rate": 2.8439024661892354e-05,
"loss": 3.9353,
"step": 1316864
},
{
"epoch": 0.01,
"learning_rate": 2.8430638714381834e-05,
"loss": 3.9236,
"step": 1317376
},
{
"epoch": 0.01,
"learning_rate": 2.8422252766871317e-05,
"loss": 3.937,
"step": 1317888
},
{
"epoch": 0.01,
"learning_rate": 2.8413883198164526e-05,
"loss": 3.9253,
"step": 1318400
},
{
"epoch": 0.01,
"learning_rate": 2.8405497250654006e-05,
"loss": 3.9403,
"step": 1318912
},
{
"epoch": 0.01,
"learning_rate": 2.8397111303143486e-05,
"loss": 3.928,
"step": 1319424
},
{
"epoch": 0.01,
"learning_rate": 2.8388725355632966e-05,
"loss": 3.9331,
"step": 1319936
},
{
"epoch": 0.01,
"learning_rate": 2.8380339408122446e-05,
"loss": 3.9385,
"step": 1320448
},
{
"epoch": 0.01,
"learning_rate": 2.837196983941566e-05,
"loss": 3.9328,
"step": 1320960
},
{
"epoch": 0.01,
"learning_rate": 2.836358389190514e-05,
"loss": 3.9305,
"step": 1321472
},
{
"epoch": 0.01,
"learning_rate": 2.835519794439462e-05,
"loss": 3.9182,
"step": 1321984
},
{
"epoch": 0.01,
"learning_rate": 2.83468119968841e-05,
"loss": 3.9268,
"step": 1322496
},
{
"epoch": 0.01,
"learning_rate": 2.8338442428177307e-05,
"loss": 3.9383,
"step": 1323008
},
{
"epoch": 0.01,
"learning_rate": 2.8330056480666787e-05,
"loss": 3.9349,
"step": 1323520
},
{
"epoch": 0.01,
"learning_rate": 2.832167053315627e-05,
"loss": 3.9262,
"step": 1324032
},
{
"epoch": 0.01,
"learning_rate": 2.831328458564575e-05,
"loss": 3.9204,
"step": 1324544
},
{
"epoch": 0.01,
"learning_rate": 2.830489863813523e-05,
"loss": 3.9305,
"step": 1325056
},
{
"epoch": 0.01,
"learning_rate": 2.829652906942844e-05,
"loss": 3.9183,
"step": 1325568
},
{
"epoch": 0.01,
"learning_rate": 2.828814312191792e-05,
"loss": 3.9446,
"step": 1326080
},
{
"epoch": 0.01,
"learning_rate": 2.82797571744074e-05,
"loss": 3.9168,
"step": 1326592
},
{
"epoch": 0.01,
"learning_rate": 2.827137122689688e-05,
"loss": 3.9404,
"step": 1327104
},
{
"epoch": 0.01,
"learning_rate": 2.8262985279386363e-05,
"loss": 3.9316,
"step": 1327616
},
{
"epoch": 0.01,
"learning_rate": 2.8254599331875843e-05,
"loss": 3.9215,
"step": 1328128
},
{
"epoch": 0.01,
"learning_rate": 2.8246213384365323e-05,
"loss": 3.9302,
"step": 1328640
},
{
"epoch": 0.01,
"learning_rate": 2.8237827436854796e-05,
"loss": 3.9314,
"step": 1329152
},
{
"epoch": 0.01,
"learning_rate": 2.8229457868148012e-05,
"loss": 3.9207,
"step": 1329664
},
{
"epoch": 0.01,
"learning_rate": 2.8221104678244954e-05,
"loss": 3.9273,
"step": 1330176
},
{
"epoch": 0.01,
"learning_rate": 2.8212718730734434e-05,
"loss": 3.9379,
"step": 1330688
},
{
"epoch": 0.01,
"learning_rate": 2.8204332783223913e-05,
"loss": 3.9297,
"step": 1331200
},
{
"epoch": 0.01,
"learning_rate": 2.8195946835713393e-05,
"loss": 3.926,
"step": 1331712
},
{
"epoch": 0.01,
"learning_rate": 2.8187560888202873e-05,
"loss": 3.9237,
"step": 1332224
},
{
"epoch": 0.01,
"learning_rate": 2.8179174940692353e-05,
"loss": 3.923,
"step": 1332736
},
{
"epoch": 0.01,
"learning_rate": 2.8170788993181833e-05,
"loss": 3.9314,
"step": 1333248
},
{
"epoch": 0.01,
"learning_rate": 2.8162403045671317e-05,
"loss": 3.9465,
"step": 1333760
},
{
"epoch": 0.01,
"learning_rate": 2.8154017098160797e-05,
"loss": 3.9278,
"step": 1334272
},
{
"epoch": 0.01,
"learning_rate": 2.814563115065027e-05,
"loss": 3.9415,
"step": 1334784
},
{
"epoch": 0.01,
"learning_rate": 2.8137261581943486e-05,
"loss": 3.9429,
"step": 1335296
},
{
"epoch": 0.01,
"learning_rate": 2.8128875634432966e-05,
"loss": 3.9362,
"step": 1335808
},
{
"epoch": 0.01,
"learning_rate": 2.8120489686922442e-05,
"loss": 3.9253,
"step": 1336320
},
{
"epoch": 0.01,
"learning_rate": 2.8112103739411922e-05,
"loss": 3.9382,
"step": 1336832
},
{
"epoch": 0.01,
"learning_rate": 2.8103734170705138e-05,
"loss": 3.9394,
"step": 1337344
},
{
"epoch": 0.01,
"learning_rate": 2.8095348223194618e-05,
"loss": 3.9301,
"step": 1337856
},
{
"epoch": 0.01,
"learning_rate": 2.808696227568409e-05,
"loss": 3.9313,
"step": 1338368
},
{
"epoch": 0.01,
"learning_rate": 2.807857632817357e-05,
"loss": 3.9384,
"step": 1338880
},
{
"epoch": 0.01,
"learning_rate": 2.8070190380663054e-05,
"loss": 3.9448,
"step": 1339392
},
{
"epoch": 0.01,
"learning_rate": 2.8061804433152534e-05,
"loss": 3.9314,
"step": 1339904
},
{
"epoch": 0.01,
"learning_rate": 2.8053434864445744e-05,
"loss": 3.9206,
"step": 1340416
},
{
"epoch": 0.01,
"learning_rate": 2.8045048916935223e-05,
"loss": 3.9277,
"step": 1340928
},
{
"epoch": 0.01,
"learning_rate": 2.8036662969424703e-05,
"loss": 3.937,
"step": 1341440
},
{
"epoch": 0.01,
"learning_rate": 2.8028277021914183e-05,
"loss": 3.9329,
"step": 1341952
},
{
"epoch": 0.01,
"learning_rate": 2.8019891074403663e-05,
"loss": 3.9405,
"step": 1342464
},
{
"epoch": 0.01,
"learning_rate": 2.8011521505696876e-05,
"loss": 3.9284,
"step": 1342976
},
{
"epoch": 0.02,
"learning_rate": 2.8003135558186356e-05,
"loss": 3.9247,
"step": 1343488
},
{
"epoch": 0.02,
"learning_rate": 2.7994749610675836e-05,
"loss": 3.925,
"step": 1344000
},
{
"epoch": 0.02,
"learning_rate": 2.7986363663165316e-05,
"loss": 3.9282,
"step": 1344512
},
{
"epoch": 0.02,
"learning_rate": 2.7977977715654796e-05,
"loss": 3.9316,
"step": 1345024
},
{
"epoch": 0.02,
"learning_rate": 2.7969608146948008e-05,
"loss": 3.9307,
"step": 1345536
},
{
"epoch": 0.02,
"learning_rate": 2.7961222199437488e-05,
"loss": 3.9496,
"step": 1346048
},
{
"epoch": 0.02,
"learning_rate": 2.7952836251926968e-05,
"loss": 3.9378,
"step": 1346560
},
{
"epoch": 0.02,
"learning_rate": 2.7944450304416448e-05,
"loss": 3.9211,
"step": 1347072
},
{
"epoch": 0.02,
"learning_rate": 2.7936064356905928e-05,
"loss": 3.9329,
"step": 1347584
},
{
"epoch": 0.02,
"learning_rate": 2.7927694788199137e-05,
"loss": 3.9332,
"step": 1348096
},
{
"epoch": 0.02,
"learning_rate": 2.7919308840688617e-05,
"loss": 3.9345,
"step": 1348608
},
{
"epoch": 0.02,
"learning_rate": 2.7910922893178097e-05,
"loss": 3.9357,
"step": 1349120
},
{
"epoch": 0.02,
"learning_rate": 2.790253694566758e-05,
"loss": 3.932,
"step": 1349632
},
{
"epoch": 0.02,
"learning_rate": 2.789416737696079e-05,
"loss": 3.9268,
"step": 1350144
},
{
"epoch": 0.02,
"learning_rate": 2.788578142945027e-05,
"loss": 3.937,
"step": 1350656
},
{
"epoch": 0.02,
"learning_rate": 2.787739548193975e-05,
"loss": 3.916,
"step": 1351168
},
{
"epoch": 0.02,
"learning_rate": 2.786900953442923e-05,
"loss": 3.9283,
"step": 1351680
},
{
"epoch": 0.02,
"learning_rate": 2.786062358691871e-05,
"loss": 3.9281,
"step": 1352192
},
{
"epoch": 0.02,
"learning_rate": 2.7852254018211922e-05,
"loss": 3.9321,
"step": 1352704
},
{
"epoch": 0.02,
"learning_rate": 2.78438680707014e-05,
"loss": 3.9214,
"step": 1353216
},
{
"epoch": 0.02,
"learning_rate": 2.783548212319088e-05,
"loss": 3.9326,
"step": 1353728
},
{
"epoch": 0.02,
"learning_rate": 2.782709617568036e-05,
"loss": 3.9231,
"step": 1354240
},
{
"epoch": 0.02,
"learning_rate": 2.781871022816984e-05,
"loss": 3.9276,
"step": 1354752
},
{
"epoch": 0.02,
"learning_rate": 2.781032428065932e-05,
"loss": 3.9256,
"step": 1355264
},
{
"epoch": 0.02,
"learning_rate": 2.78019383331488e-05,
"loss": 3.9304,
"step": 1355776
},
{
"epoch": 0.02,
"learning_rate": 2.7793552385638278e-05,
"loss": 3.9446,
"step": 1356288
},
{
"epoch": 0.02,
"learning_rate": 2.7785182816931494e-05,
"loss": 3.9378,
"step": 1356800
},
{
"epoch": 0.02,
"learning_rate": 2.7776813248224703e-05,
"loss": 3.933,
"step": 1357312
},
{
"epoch": 0.02,
"learning_rate": 2.7768427300714183e-05,
"loss": 3.929,
"step": 1357824
},
{
"epoch": 0.02,
"learning_rate": 2.7760041353203663e-05,
"loss": 3.9335,
"step": 1358336
},
{
"epoch": 0.02,
"learning_rate": 2.7751655405693143e-05,
"loss": 3.9308,
"step": 1358848
},
{
"epoch": 0.02,
"learning_rate": 2.7743285836986355e-05,
"loss": 3.9275,
"step": 1359360
},
{
"epoch": 0.02,
"learning_rate": 2.7734899889475835e-05,
"loss": 3.93,
"step": 1359872
},
{
"epoch": 0.02,
"learning_rate": 2.7726513941965315e-05,
"loss": 3.9264,
"step": 1360384
},
{
"epoch": 0.02,
"learning_rate": 2.7718127994454795e-05,
"loss": 3.9304,
"step": 1360896
},
{
"epoch": 0.02,
"learning_rate": 2.7709742046944275e-05,
"loss": 3.9214,
"step": 1361408
},
{
"epoch": 0.02,
"learning_rate": 2.7701356099433752e-05,
"loss": 3.9271,
"step": 1361920
},
{
"epoch": 0.02,
"learning_rate": 2.769297015192323e-05,
"loss": 3.9255,
"step": 1362432
},
{
"epoch": 0.02,
"learning_rate": 2.7684600583216448e-05,
"loss": 3.9295,
"step": 1362944
},
{
"epoch": 0.02,
"learning_rate": 2.7676214635705927e-05,
"loss": 3.9192,
"step": 1363456
},
{
"epoch": 0.02,
"learning_rate": 2.76678286881954e-05,
"loss": 3.9401,
"step": 1363968
},
{
"epoch": 0.02,
"learning_rate": 2.765944274068488e-05,
"loss": 3.946,
"step": 1364480
},
{
"epoch": 0.02,
"learning_rate": 2.7651056793174364e-05,
"loss": 3.9296,
"step": 1364992
},
{
"epoch": 0.02,
"learning_rate": 2.764268722446758e-05,
"loss": 3.9262,
"step": 1365504
},
{
"epoch": 0.02,
"learning_rate": 2.7634301276957053e-05,
"loss": 3.9323,
"step": 1366016
},
{
"epoch": 0.02,
"learning_rate": 2.7625915329446533e-05,
"loss": 3.9359,
"step": 1366528
},
{
"epoch": 0.02,
"learning_rate": 2.7617529381936013e-05,
"loss": 3.9371,
"step": 1367040
},
{
"epoch": 0.02,
"learning_rate": 2.7609143434425493e-05,
"loss": 3.933,
"step": 1367552
},
{
"epoch": 0.02,
"learning_rate": 2.7600773865718705e-05,
"loss": 3.9371,
"step": 1368064
},
{
"epoch": 0.02,
"learning_rate": 2.7592387918208185e-05,
"loss": 3.929,
"step": 1368576
},
{
"epoch": 0.02,
"learning_rate": 2.7584001970697665e-05,
"loss": 3.934,
"step": 1369088
},
{
"epoch": 0.02,
"learning_rate": 2.7575616023187145e-05,
"loss": 3.9288,
"step": 1369600
},
{
"epoch": 0.02,
"learning_rate": 2.7567230075676625e-05,
"loss": 3.9366,
"step": 1370112
},
{
"epoch": 0.02,
"learning_rate": 2.7558844128166105e-05,
"loss": 3.9307,
"step": 1370624
},
{
"epoch": 0.02,
"learning_rate": 2.7550474559459318e-05,
"loss": 3.9235,
"step": 1371136
},
{
"epoch": 0.02,
"learning_rate": 2.7542088611948798e-05,
"loss": 3.9355,
"step": 1371648
},
{
"epoch": 0.02,
"learning_rate": 2.7533702664438278e-05,
"loss": 3.9273,
"step": 1372160
},
{
"epoch": 0.02,
"learning_rate": 2.7525316716927758e-05,
"loss": 3.9356,
"step": 1372672
},
{
"epoch": 0.02,
"learning_rate": 2.7516930769417237e-05,
"loss": 3.9222,
"step": 1373184
},
{
"epoch": 0.02,
"learning_rate": 2.7508561200710447e-05,
"loss": 3.9237,
"step": 1373696
},
{
"epoch": 0.03,
"eval_loss": 4.004668235778809,
"eval_runtime": 285.3847,
"eval_samples_per_second": 1337.111,
"eval_steps_per_second": 41.786,
"step": 1373760
},
{
"epoch": 1.0,
"learning_rate": 2.7500175253199927e-05,
"loss": 3.9284,
"step": 1374208
},
{
"epoch": 1.0,
"learning_rate": 2.749178930568941e-05,
"loss": 3.9206,
"step": 1374720
},
{
"epoch": 1.0,
"learning_rate": 2.748340335817889e-05,
"loss": 3.9362,
"step": 1375232
},
{
"epoch": 1.0,
"learning_rate": 2.747501741066837e-05,
"loss": 3.9278,
"step": 1375744
},
{
"epoch": 1.0,
"learning_rate": 2.746664784196158e-05,
"loss": 3.9379,
"step": 1376256
},
{
"epoch": 1.0,
"learning_rate": 2.745826189445106e-05,
"loss": 3.9243,
"step": 1376768
},
{
"epoch": 1.0,
"learning_rate": 2.744989232574427e-05,
"loss": 3.9253,
"step": 1377280
},
{
"epoch": 1.0,
"learning_rate": 2.744150637823375e-05,
"loss": 3.9159,
"step": 1377792
},
{
"epoch": 1.0,
"learning_rate": 2.743312043072323e-05,
"loss": 3.9332,
"step": 1378304
},
{
"epoch": 1.0,
"learning_rate": 2.742473448321271e-05,
"loss": 3.9351,
"step": 1378816
},
{
"epoch": 1.0,
"learning_rate": 2.741634853570219e-05,
"loss": 3.9388,
"step": 1379328
},
{
"epoch": 1.0,
"learning_rate": 2.740796258819167e-05,
"loss": 3.929,
"step": 1379840
},
{
"epoch": 1.0,
"learning_rate": 2.739957664068115e-05,
"loss": 3.9205,
"step": 1380352
},
{
"epoch": 1.0,
"learning_rate": 2.739119069317063e-05,
"loss": 3.9242,
"step": 1380864
},
{
"epoch": 1.0,
"learning_rate": 2.738280474566011e-05,
"loss": 3.9206,
"step": 1381376
},
{
"epoch": 1.0,
"learning_rate": 2.7374418798149588e-05,
"loss": 3.9222,
"step": 1381888
},
{
"epoch": 1.0,
"learning_rate": 2.7366032850639067e-05,
"loss": 3.9288,
"step": 1382400
},
{
"epoch": 1.0,
"learning_rate": 2.7357663281932283e-05,
"loss": 3.9201,
"step": 1382912
},
{
"epoch": 1.0,
"learning_rate": 2.7349277334421763e-05,
"loss": 3.9227,
"step": 1383424
},
{
"epoch": 1.0,
"learning_rate": 2.734089138691124e-05,
"loss": 3.9451,
"step": 1383936
},
{
"epoch": 1.0,
"learning_rate": 2.733250543940072e-05,
"loss": 3.9301,
"step": 1384448
},
{
"epoch": 1.0,
"learning_rate": 2.73241194918902e-05,
"loss": 3.9361,
"step": 1384960
},
{
"epoch": 1.0,
"learning_rate": 2.731573354437968e-05,
"loss": 3.9242,
"step": 1385472
},
{
"epoch": 1.0,
"learning_rate": 2.730734759686916e-05,
"loss": 3.9392,
"step": 1385984
},
{
"epoch": 1.0,
"learning_rate": 2.729896164935864e-05,
"loss": 3.918,
"step": 1386496
},
{
"epoch": 1.0,
"learning_rate": 2.729059208065185e-05,
"loss": 3.929,
"step": 1387008
},
{
"epoch": 1.0,
"learning_rate": 2.728220613314133e-05,
"loss": 3.9256,
"step": 1387520
},
{
"epoch": 1.0,
"learning_rate": 2.7273820185630812e-05,
"loss": 3.9261,
"step": 1388032
},
{
"epoch": 1.0,
"learning_rate": 2.726545061692402e-05,
"loss": 3.9147,
"step": 1388544
},
{
"epoch": 1.01,
"learning_rate": 2.72570646694135e-05,
"loss": 3.9208,
"step": 1389056
},
{
"epoch": 1.01,
"learning_rate": 2.724867872190298e-05,
"loss": 3.9296,
"step": 1389568
},
{
"epoch": 1.01,
"learning_rate": 2.724029277439246e-05,
"loss": 3.9323,
"step": 1390080
},
{
"epoch": 1.01,
"learning_rate": 2.723190682688194e-05,
"loss": 3.9303,
"step": 1390592
},
{
"epoch": 1.01,
"learning_rate": 2.7223537258175153e-05,
"loss": 3.9331,
"step": 1391104
},
{
"epoch": 1.01,
"learning_rate": 2.7215151310664633e-05,
"loss": 3.9309,
"step": 1391616
},
{
"epoch": 1.01,
"learning_rate": 2.7206765363154113e-05,
"loss": 3.9294,
"step": 1392128
},
{
"epoch": 1.01,
"learning_rate": 2.7198395794447322e-05,
"loss": 3.9199,
"step": 1392640
},
{
"epoch": 1.01,
"learning_rate": 2.7190009846936802e-05,
"loss": 3.9243,
"step": 1393152
},
{
"epoch": 1.01,
"learning_rate": 2.7181623899426282e-05,
"loss": 3.915,
"step": 1393664
},
{
"epoch": 1.01,
"learning_rate": 2.7173237951915766e-05,
"loss": 3.9295,
"step": 1394176
},
{
"epoch": 1.01,
"learning_rate": 2.7164852004405246e-05,
"loss": 3.9194,
"step": 1394688
},
{
"epoch": 1.01,
"learning_rate": 2.7156466056894726e-05,
"loss": 3.9295,
"step": 1395200
},
{
"epoch": 1.01,
"learning_rate": 2.7148080109384206e-05,
"loss": 3.9218,
"step": 1395712
},
{
"epoch": 1.01,
"learning_rate": 2.7139694161873686e-05,
"loss": 3.9206,
"step": 1396224
},
{
"epoch": 1.01,
"learning_rate": 2.7131308214363165e-05,
"loss": 3.9344,
"step": 1396736
},
{
"epoch": 1.01,
"learning_rate": 2.7122922266852645e-05,
"loss": 3.9215,
"step": 1397248
},
{
"epoch": 1.01,
"learning_rate": 2.7114536319342125e-05,
"loss": 3.9236,
"step": 1397760
},
{
"epoch": 1.01,
"learning_rate": 2.7106166750635338e-05,
"loss": 3.9055,
"step": 1398272
},
{
"epoch": 1.01,
"learning_rate": 2.7097780803124818e-05,
"loss": 3.9192,
"step": 1398784
},
{
"epoch": 1.01,
"learning_rate": 2.7089411234418027e-05,
"loss": 3.9312,
"step": 1399296
},
{
"epoch": 1.01,
"learning_rate": 2.7081025286907507e-05,
"loss": 3.9247,
"step": 1399808
},
{
"epoch": 1.01,
"learning_rate": 2.707265571820072e-05,
"loss": 3.9218,
"step": 1400320
},
{
"epoch": 1.01,
"learning_rate": 2.70642697706902e-05,
"loss": 3.9092,
"step": 1400832
},
{
"epoch": 1.01,
"learning_rate": 2.705588382317968e-05,
"loss": 3.9233,
"step": 1401344
},
{
"epoch": 1.01,
"learning_rate": 2.704749787566916e-05,
"loss": 3.9105,
"step": 1401856
},
{
"epoch": 1.01,
"learning_rate": 2.703911192815864e-05,
"loss": 3.9341,
"step": 1402368
},
{
"epoch": 1.01,
"learning_rate": 2.703072598064812e-05,
"loss": 3.9088,
"step": 1402880
},
{
"epoch": 1.01,
"learning_rate": 2.70223400331376e-05,
"loss": 3.9291,
"step": 1403392
},
{
"epoch": 1.01,
"learning_rate": 2.7013954085627076e-05,
"loss": 3.9268,
"step": 1403904
},
{
"epoch": 1.01,
"learning_rate": 2.7005568138116556e-05,
"loss": 3.9104,
"step": 1404416
},
{
"epoch": 1.01,
"learning_rate": 2.6997182190606036e-05,
"loss": 3.9183,
"step": 1404928
},
{
"epoch": 1.01,
"learning_rate": 2.6988796243095516e-05,
"loss": 3.9252,
"step": 1405440
},
{
"epoch": 1.01,
"learning_rate": 2.6980410295584995e-05,
"loss": 3.9124,
"step": 1405952
},
{
"epoch": 1.01,
"learning_rate": 2.6972024348074475e-05,
"loss": 3.92,
"step": 1406464
},
{
"epoch": 1.01,
"learning_rate": 2.6963638400563955e-05,
"loss": 3.9269,
"step": 1406976
},
{
"epoch": 1.01,
"learning_rate": 2.6955252453053435e-05,
"loss": 3.9255,
"step": 1407488
},
{
"epoch": 1.01,
"learning_rate": 2.6946882884346648e-05,
"loss": 3.9142,
"step": 1408000
},
{
"epoch": 1.01,
"learning_rate": 2.6938496936836128e-05,
"loss": 3.9182,
"step": 1408512
},
{
"epoch": 1.01,
"learning_rate": 2.6930110989325608e-05,
"loss": 3.9097,
"step": 1409024
},
{
"epoch": 1.01,
"learning_rate": 2.6921725041815088e-05,
"loss": 3.9214,
"step": 1409536
},
{
"epoch": 1.01,
"learning_rate": 2.6913339094304568e-05,
"loss": 3.937,
"step": 1410048
},
{
"epoch": 1.01,
"learning_rate": 2.6904953146794048e-05,
"loss": 3.9192,
"step": 1410560
},
{
"epoch": 1.01,
"learning_rate": 2.6896567199283528e-05,
"loss": 3.9334,
"step": 1411072
},
{
"epoch": 1.01,
"learning_rate": 2.6888181251773008e-05,
"loss": 3.9314,
"step": 1411584
},
{
"epoch": 1.01,
"learning_rate": 2.687981168306622e-05,
"loss": 3.9295,
"step": 1412096
},
{
"epoch": 1.01,
"learning_rate": 2.68714257355557e-05,
"loss": 3.9153,
"step": 1412608
},
{
"epoch": 1.01,
"learning_rate": 2.686303978804518e-05,
"loss": 3.9323,
"step": 1413120
},
{
"epoch": 1.01,
"learning_rate": 2.685465384053466e-05,
"loss": 3.926,
"step": 1413632
},
{
"epoch": 1.01,
"learning_rate": 2.6846267893024136e-05,
"loss": 3.9249,
"step": 1414144
},
{
"epoch": 1.01,
"learning_rate": 2.6837881945513616e-05,
"loss": 3.9208,
"step": 1414656
},
{
"epoch": 1.01,
"learning_rate": 2.6829495998003096e-05,
"loss": 3.926,
"step": 1415168
},
{
"epoch": 1.01,
"learning_rate": 2.6821126429296312e-05,
"loss": 3.9383,
"step": 1415680
},
{
"epoch": 1.01,
"learning_rate": 2.6812740481785785e-05,
"loss": 3.9218,
"step": 1416192
},
{
"epoch": 1.01,
"learning_rate": 2.6804354534275265e-05,
"loss": 3.9084,
"step": 1416704
},
{
"epoch": 1.01,
"learning_rate": 2.6795968586764745e-05,
"loss": 3.9159,
"step": 1417216
},
{
"epoch": 1.01,
"learning_rate": 2.678758263925423e-05,
"loss": 3.9267,
"step": 1417728
},
{
"epoch": 1.01,
"learning_rate": 2.677919669174371e-05,
"loss": 3.9267,
"step": 1418240
},
{
"epoch": 1.01,
"learning_rate": 2.6770827123036918e-05,
"loss": 3.9317,
"step": 1418752
},
{
"epoch": 1.01,
"learning_rate": 2.6762441175526398e-05,
"loss": 3.9164,
"step": 1419264
},
{
"epoch": 1.02,
"learning_rate": 2.6754055228015878e-05,
"loss": 3.919,
"step": 1419776
},
{
"epoch": 1.02,
"learning_rate": 2.6745669280505358e-05,
"loss": 3.9126,
"step": 1420288
},
{
"epoch": 1.02,
"learning_rate": 2.673729971179857e-05,
"loss": 3.9187,
"step": 1420800
},
{
"epoch": 1.02,
"learning_rate": 2.672891376428805e-05,
"loss": 3.9242,
"step": 1421312
},
{
"epoch": 1.02,
"learning_rate": 2.672052781677753e-05,
"loss": 3.9236,
"step": 1421824
},
{
"epoch": 1.02,
"learning_rate": 2.671214186926701e-05,
"loss": 3.9398,
"step": 1422336
},
{
"epoch": 1.02,
"learning_rate": 2.670375592175649e-05,
"loss": 3.9244,
"step": 1422848
},
{
"epoch": 1.02,
"learning_rate": 2.669536997424597e-05,
"loss": 3.918,
"step": 1423360
},
{
"epoch": 1.02,
"learning_rate": 2.668698402673545e-05,
"loss": 3.9215,
"step": 1423872
},
{
"epoch": 1.02,
"learning_rate": 2.667859807922493e-05,
"loss": 3.9221,
"step": 1424384
},
{
"epoch": 1.02,
"learning_rate": 2.6670228510518142e-05,
"loss": 3.9298,
"step": 1424896
},
{
"epoch": 1.02,
"learning_rate": 2.6661842563007622e-05,
"loss": 3.9273,
"step": 1425408
},
{
"epoch": 1.02,
"learning_rate": 2.6653456615497102e-05,
"loss": 3.9232,
"step": 1425920
},
{
"epoch": 1.02,
"learning_rate": 2.6645070667986582e-05,
"loss": 3.9191,
"step": 1426432
},
{
"epoch": 1.02,
"learning_rate": 2.663670109927979e-05,
"loss": 3.9276,
"step": 1426944
},
{
"epoch": 1.02,
"learning_rate": 2.6628315151769275e-05,
"loss": 3.9055,
"step": 1427456
},
{
"epoch": 1.02,
"learning_rate": 2.6619929204258755e-05,
"loss": 3.9205,
"step": 1427968
},
{
"epoch": 1.02,
"learning_rate": 2.6611543256748234e-05,
"loss": 3.9171,
"step": 1428480
},
{
"epoch": 1.02,
"learning_rate": 2.6603173688041444e-05,
"loss": 3.9234,
"step": 1428992
},
{
"epoch": 1.02,
"learning_rate": 2.6594787740530924e-05,
"loss": 3.916,
"step": 1429504
},
{
"epoch": 1.02,
"learning_rate": 2.6586418171824136e-05,
"loss": 3.9236,
"step": 1430016
},
{
"epoch": 1.02,
"learning_rate": 2.6578032224313616e-05,
"loss": 3.9121,
"step": 1430528
},
{
"epoch": 1.02,
"learning_rate": 2.6569646276803096e-05,
"loss": 3.9183,
"step": 1431040
},
{
"epoch": 1.02,
"learning_rate": 2.6561260329292576e-05,
"loss": 3.9208,
"step": 1431552
},
{
"epoch": 1.02,
"learning_rate": 2.6552874381782056e-05,
"loss": 3.9179,
"step": 1432064
},
{
"epoch": 1.02,
"learning_rate": 2.6544488434271536e-05,
"loss": 3.9366,
"step": 1432576
},
{
"epoch": 1.02,
"learning_rate": 2.6536118865564745e-05,
"loss": 3.9306,
"step": 1433088
},
{
"epoch": 1.02,
"learning_rate": 2.6527749296857957e-05,
"loss": 3.9263,
"step": 1433600
},
{
"epoch": 1.02,
"learning_rate": 2.6519363349347437e-05,
"loss": 3.917,
"step": 1434112
},
{
"epoch": 1.02,
"learning_rate": 2.6510977401836917e-05,
"loss": 3.9228,
"step": 1434624
},
{
"epoch": 1.02,
"learning_rate": 2.6502591454326397e-05,
"loss": 3.9231,
"step": 1435136
},
{
"epoch": 1.02,
"learning_rate": 2.6494205506815877e-05,
"loss": 3.921,
"step": 1435648
},
{
"epoch": 1.02,
"learning_rate": 2.6485819559305357e-05,
"loss": 3.922,
"step": 1436160
},
{
"epoch": 1.02,
"learning_rate": 2.6477433611794837e-05,
"loss": 3.914,
"step": 1436672
},
{
"epoch": 1.02,
"learning_rate": 2.646904766428432e-05,
"loss": 3.9239,
"step": 1437184
},
{
"epoch": 1.02,
"learning_rate": 2.646067809557753e-05,
"loss": 3.9107,
"step": 1437696
},
{
"epoch": 1.02,
"learning_rate": 2.645229214806701e-05,
"loss": 3.9191,
"step": 1438208
},
{
"epoch": 1.02,
"learning_rate": 2.644390620055649e-05,
"loss": 3.915,
"step": 1438720
},
{
"epoch": 1.02,
"learning_rate": 2.643552025304597e-05,
"loss": 3.9195,
"step": 1439232
},
{
"epoch": 1.02,
"learning_rate": 2.6427134305535446e-05,
"loss": 3.9111,
"step": 1439744
},
{
"epoch": 1.02,
"learning_rate": 2.6418748358024926e-05,
"loss": 3.9341,
"step": 1440256
},
{
"epoch": 1.02,
"learning_rate": 2.6410362410514406e-05,
"loss": 3.9352,
"step": 1440768
},
{
"epoch": 1.02,
"learning_rate": 2.6401992841807622e-05,
"loss": 3.9248,
"step": 1441280
},
{
"epoch": 1.02,
"learning_rate": 2.6393606894297095e-05,
"loss": 3.913,
"step": 1441792
},
{
"epoch": 1.02,
"learning_rate": 2.6385220946786575e-05,
"loss": 3.9263,
"step": 1442304
},
{
"epoch": 1.02,
"learning_rate": 2.6376834999276058e-05,
"loss": 3.9245,
"step": 1442816
},
{
"epoch": 1.02,
"learning_rate": 2.6368449051765538e-05,
"loss": 3.9301,
"step": 1443328
},
{
"epoch": 1.02,
"learning_rate": 2.6360079483058747e-05,
"loss": 3.9222,
"step": 1443840
},
{
"epoch": 1.02,
"learning_rate": 2.6351693535548227e-05,
"loss": 3.9249,
"step": 1444352
},
{
"epoch": 1.02,
"learning_rate": 2.6343307588037707e-05,
"loss": 3.9219,
"step": 1444864
},
{
"epoch": 1.02,
"learning_rate": 2.6334921640527187e-05,
"loss": 3.9271,
"step": 1445376
},
{
"epoch": 1.02,
"learning_rate": 2.6326535693016667e-05,
"loss": 3.9219,
"step": 1445888
},
{
"epoch": 1.02,
"learning_rate": 2.6318149745506147e-05,
"loss": 3.9268,
"step": 1446400
},
{
"epoch": 1.02,
"learning_rate": 2.630976379799563e-05,
"loss": 3.9203,
"step": 1446912
},
{
"epoch": 1.02,
"learning_rate": 2.630137785048511e-05,
"loss": 3.9172,
"step": 1447424
},
{
"epoch": 1.02,
"learning_rate": 2.629299190297459e-05,
"loss": 3.9259,
"step": 1447936
},
{
"epoch": 1.02,
"learning_rate": 2.62846223342678e-05,
"loss": 3.9249,
"step": 1448448
},
{
"epoch": 1.02,
"learning_rate": 2.627623638675728e-05,
"loss": 3.9227,
"step": 1448960
},
{
"epoch": 1.02,
"learning_rate": 2.6267866818050492e-05,
"loss": 3.914,
"step": 1449472
},
{
"epoch": 1.02,
"learning_rate": 2.6259480870539972e-05,
"loss": 3.9141,
"step": 1449984
},
{
"epoch": 1.03,
"eval_loss": 4.000833988189697,
"eval_runtime": 285.9982,
"eval_samples_per_second": 1334.243,
"eval_steps_per_second": 41.696,
"step": 1450080
},
{
"epoch": 0.0,
"learning_rate": 2.6251094923029452e-05,
"loss": 3.9181,
"step": 1450496
},
{
"epoch": 0.0,
"learning_rate": 2.6242708975518932e-05,
"loss": 3.9147,
"step": 1451008
},
{
"epoch": 0.0,
"learning_rate": 2.623432302800841e-05,
"loss": 3.9255,
"step": 1451520
},
{
"epoch": 0.0,
"learning_rate": 2.622593708049789e-05,
"loss": 3.9199,
"step": 1452032
},
{
"epoch": 0.0,
"learning_rate": 2.621755113298737e-05,
"loss": 3.9313,
"step": 1452544
},
{
"epoch": 0.0,
"learning_rate": 2.620916518547685e-05,
"loss": 3.9168,
"step": 1453056
},
{
"epoch": 0.0,
"learning_rate": 2.620077923796633e-05,
"loss": 3.9173,
"step": 1453568
},
{
"epoch": 0.0,
"learning_rate": 2.6192393290455808e-05,
"loss": 3.9086,
"step": 1454080
},
{
"epoch": 0.0,
"learning_rate": 2.6184007342945288e-05,
"loss": 3.9237,
"step": 1454592
},
{
"epoch": 0.0,
"learning_rate": 2.6175621395434768e-05,
"loss": 3.9266,
"step": 1455104
},
{
"epoch": 0.0,
"learning_rate": 2.6167235447924248e-05,
"loss": 3.9294,
"step": 1455616
},
{
"epoch": 0.0,
"learning_rate": 2.6158849500413728e-05,
"loss": 3.9216,
"step": 1456128
},
{
"epoch": 0.0,
"learning_rate": 2.6150463552903208e-05,
"loss": 3.9142,
"step": 1456640
},
{
"epoch": 0.0,
"learning_rate": 2.614207760539269e-05,
"loss": 3.9165,
"step": 1457152
},
{
"epoch": 0.0,
"learning_rate": 2.613369165788217e-05,
"loss": 3.9138,
"step": 1457664
},
{
"epoch": 0.0,
"learning_rate": 2.612532208917538e-05,
"loss": 3.9146,
"step": 1458176
},
{
"epoch": 0.0,
"learning_rate": 2.611693614166486e-05,
"loss": 3.9195,
"step": 1458688
},
{
"epoch": 0.0,
"learning_rate": 2.610855019415434e-05,
"loss": 3.9122,
"step": 1459200
},
{
"epoch": 0.0,
"learning_rate": 2.610016424664382e-05,
"loss": 3.9155,
"step": 1459712
},
{
"epoch": 0.0,
"learning_rate": 2.60917782991333e-05,
"loss": 3.9384,
"step": 1460224
},
{
"epoch": 0.0,
"learning_rate": 2.6083392351622783e-05,
"loss": 3.9212,
"step": 1460736
},
{
"epoch": 0.0,
"learning_rate": 2.6075006404112263e-05,
"loss": 3.9223,
"step": 1461248
},
{
"epoch": 0.0,
"learning_rate": 2.6066620456601743e-05,
"loss": 3.9185,
"step": 1461760
},
{
"epoch": 0.0,
"learning_rate": 2.6058234509091223e-05,
"loss": 3.9276,
"step": 1462272
},
{
"epoch": 0.0,
"learning_rate": 2.6049864940384432e-05,
"loss": 3.9103,
"step": 1462784
},
{
"epoch": 0.0,
"learning_rate": 2.6041478992873912e-05,
"loss": 3.9265,
"step": 1463296
},
{
"epoch": 0.0,
"learning_rate": 2.6033093045363392e-05,
"loss": 3.9157,
"step": 1463808
},
{
"epoch": 0.0,
"learning_rate": 2.6024723476656605e-05,
"loss": 3.9169,
"step": 1464320
},
{
"epoch": 0.0,
"learning_rate": 2.6016353907949814e-05,
"loss": 3.9054,
"step": 1464832
},
{
"epoch": 0.01,
"learning_rate": 2.6007967960439294e-05,
"loss": 3.9143,
"step": 1465344
},
{
"epoch": 0.01,
"learning_rate": 2.5999582012928774e-05,
"loss": 3.9191,
"step": 1465856
},
{
"epoch": 0.01,
"learning_rate": 2.5991196065418254e-05,
"loss": 3.923,
"step": 1466368
},
{
"epoch": 0.01,
"learning_rate": 2.5982810117907737e-05,
"loss": 3.9235,
"step": 1466880
},
{
"epoch": 0.01,
"learning_rate": 2.5974424170397217e-05,
"loss": 3.926,
"step": 1467392
},
{
"epoch": 0.01,
"learning_rate": 2.5966038222886697e-05,
"loss": 3.9184,
"step": 1467904
},
{
"epoch": 0.01,
"learning_rate": 2.5957668654179906e-05,
"loss": 3.9262,
"step": 1468416
},
{
"epoch": 0.01,
"learning_rate": 2.5949282706669386e-05,
"loss": 3.9084,
"step": 1468928
},
{
"epoch": 0.01,
"learning_rate": 2.5940896759158866e-05,
"loss": 3.9209,
"step": 1469440
},
{
"epoch": 0.01,
"learning_rate": 2.5932510811648343e-05,
"loss": 3.9054,
"step": 1469952
},
{
"epoch": 0.01,
"learning_rate": 2.5924124864137823e-05,
"loss": 3.9203,
"step": 1470464
},
{
"epoch": 0.01,
"learning_rate": 2.5915738916627302e-05,
"loss": 3.9108,
"step": 1470976
},
{
"epoch": 0.01,
"learning_rate": 2.590736934792052e-05,
"loss": 3.9206,
"step": 1471488
},
{
"epoch": 0.01,
"learning_rate": 2.589898340040999e-05,
"loss": 3.9165,
"step": 1472000
},
{
"epoch": 0.01,
"learning_rate": 2.5890597452899475e-05,
"loss": 3.9091,
"step": 1472512
},
{
"epoch": 0.01,
"learning_rate": 2.5882211505388955e-05,
"loss": 3.926,
"step": 1473024
},
{
"epoch": 0.01,
"learning_rate": 2.5873825557878435e-05,
"loss": 3.9149,
"step": 1473536
},
{
"epoch": 0.01,
"learning_rate": 2.5865439610367915e-05,
"loss": 3.9134,
"step": 1474048
},
{
"epoch": 0.01,
"learning_rate": 2.5857053662857395e-05,
"loss": 3.9017,
"step": 1474560
},
{
"epoch": 0.01,
"learning_rate": 2.5848667715346875e-05,
"loss": 3.909,
"step": 1475072
},
{
"epoch": 0.01,
"learning_rate": 2.5840298146640084e-05,
"loss": 3.9179,
"step": 1475584
},
{
"epoch": 0.01,
"learning_rate": 2.5831928577933296e-05,
"loss": 3.9179,
"step": 1476096
},
{
"epoch": 0.01,
"learning_rate": 2.5823542630422776e-05,
"loss": 3.9113,
"step": 1476608
},
{
"epoch": 0.01,
"learning_rate": 2.5815156682912256e-05,
"loss": 3.9022,
"step": 1477120
},
{
"epoch": 0.01,
"learning_rate": 2.5806770735401736e-05,
"loss": 3.9152,
"step": 1477632
},
{
"epoch": 0.01,
"learning_rate": 2.5798384787891216e-05,
"loss": 3.901,
"step": 1478144
},
{
"epoch": 0.01,
"learning_rate": 2.579001521918443e-05,
"loss": 3.9216,
"step": 1478656
},
{
"epoch": 0.01,
"learning_rate": 2.578162927167391e-05,
"loss": 3.908,
"step": 1479168
},
{
"epoch": 0.01,
"learning_rate": 2.577324332416339e-05,
"loss": 3.9161,
"step": 1479680
},
{
"epoch": 0.01,
"learning_rate": 2.576485737665287e-05,
"loss": 3.9174,
"step": 1480192
},
{
"epoch": 0.01,
"learning_rate": 2.5756487807946078e-05,
"loss": 3.9071,
"step": 1480704
},
{
"epoch": 0.01,
"learning_rate": 2.5748101860435557e-05,
"loss": 3.9073,
"step": 1481216
},
{
"epoch": 0.01,
"learning_rate": 2.5739715912925037e-05,
"loss": 3.9175,
"step": 1481728
},
{
"epoch": 0.01,
"learning_rate": 2.5731329965414517e-05,
"loss": 3.9037,
"step": 1482240
},
{
"epoch": 0.01,
"learning_rate": 2.5722944017904e-05,
"loss": 3.9141,
"step": 1482752
},
{
"epoch": 0.01,
"learning_rate": 2.571455807039348e-05,
"loss": 3.9139,
"step": 1483264
},
{
"epoch": 0.01,
"learning_rate": 2.570617212288296e-05,
"loss": 3.9195,
"step": 1483776
},
{
"epoch": 0.01,
"learning_rate": 2.569778617537244e-05,
"loss": 3.9065,
"step": 1484288
},
{
"epoch": 0.01,
"learning_rate": 2.568941660666565e-05,
"loss": 3.912,
"step": 1484800
},
{
"epoch": 0.01,
"learning_rate": 2.568103065915513e-05,
"loss": 3.9004,
"step": 1485312
},
{
"epoch": 0.01,
"learning_rate": 2.567264471164461e-05,
"loss": 3.912,
"step": 1485824
},
{
"epoch": 0.01,
"learning_rate": 2.5664258764134093e-05,
"loss": 3.9258,
"step": 1486336
},
{
"epoch": 0.01,
"learning_rate": 2.5655872816623573e-05,
"loss": 3.9132,
"step": 1486848
},
{
"epoch": 0.01,
"learning_rate": 2.5647503247916782e-05,
"loss": 3.9238,
"step": 1487360
},
{
"epoch": 0.01,
"learning_rate": 2.5639117300406262e-05,
"loss": 3.9246,
"step": 1487872
},
{
"epoch": 0.01,
"learning_rate": 2.5630731352895742e-05,
"loss": 3.9253,
"step": 1488384
},
{
"epoch": 0.01,
"learning_rate": 2.5622345405385222e-05,
"loss": 3.9026,
"step": 1488896
},
{
"epoch": 0.01,
"learning_rate": 2.5613975836678434e-05,
"loss": 3.9232,
"step": 1489408
},
{
"epoch": 0.01,
"learning_rate": 2.5605589889167914e-05,
"loss": 3.9235,
"step": 1489920
},
{
"epoch": 0.01,
"learning_rate": 2.5597220320461123e-05,
"loss": 3.9112,
"step": 1490432
},
{
"epoch": 0.01,
"learning_rate": 2.5588834372950603e-05,
"loss": 3.9158,
"step": 1490944
},
{
"epoch": 0.01,
"learning_rate": 2.5580448425440083e-05,
"loss": 3.919,
"step": 1491456
},
{
"epoch": 0.01,
"learning_rate": 2.5572062477929563e-05,
"loss": 3.9318,
"step": 1491968
},
{
"epoch": 0.01,
"learning_rate": 2.5563676530419047e-05,
"loss": 3.9146,
"step": 1492480
},
{
"epoch": 0.01,
"learning_rate": 2.5555290582908527e-05,
"loss": 3.9016,
"step": 1492992
},
{
"epoch": 0.01,
"learning_rate": 2.5546937393005465e-05,
"loss": 3.9119,
"step": 1493504
},
{
"epoch": 0.01,
"learning_rate": 2.5538551445494945e-05,
"loss": 3.9146,
"step": 1494016
},
{
"epoch": 0.01,
"learning_rate": 2.5530165497984425e-05,
"loss": 3.9184,
"step": 1494528
},
{
"epoch": 0.01,
"learning_rate": 2.5521779550473908e-05,
"loss": 3.9208,
"step": 1495040
},
{
"epoch": 0.01,
"learning_rate": 2.5513393602963388e-05,
"loss": 3.9131,
"step": 1495552
},
{
"epoch": 0.02,
"learning_rate": 2.5505007655452868e-05,
"loss": 3.9118,
"step": 1496064
},
{
"epoch": 0.02,
"learning_rate": 2.5496621707942348e-05,
"loss": 3.9053,
"step": 1496576
},
{
"epoch": 0.02,
"learning_rate": 2.5488235760431828e-05,
"loss": 3.9086,
"step": 1497088
},
{
"epoch": 0.02,
"learning_rate": 2.54798498129213e-05,
"loss": 3.9122,
"step": 1497600
},
{
"epoch": 0.02,
"learning_rate": 2.5471463865410784e-05,
"loss": 3.9221,
"step": 1498112
},
{
"epoch": 0.02,
"learning_rate": 2.5463077917900264e-05,
"loss": 3.9337,
"step": 1498624
},
{
"epoch": 0.02,
"learning_rate": 2.5454708349193473e-05,
"loss": 3.9156,
"step": 1499136
},
{
"epoch": 0.02,
"learning_rate": 2.5446322401682953e-05,
"loss": 3.9063,
"step": 1499648
},
{
"epoch": 0.02,
"learning_rate": 2.5437936454172433e-05,
"loss": 3.9156,
"step": 1500160
},
{
"epoch": 0.02,
"learning_rate": 2.5429550506661913e-05,
"loss": 3.912,
"step": 1500672
},
{
"epoch": 0.02,
"learning_rate": 2.5421164559151393e-05,
"loss": 3.924,
"step": 1501184
},
{
"epoch": 0.02,
"learning_rate": 2.5412794990444606e-05,
"loss": 3.9156,
"step": 1501696
},
{
"epoch": 0.02,
"learning_rate": 2.5404409042934086e-05,
"loss": 3.9165,
"step": 1502208
},
{
"epoch": 0.02,
"learning_rate": 2.5396023095423566e-05,
"loss": 3.9119,
"step": 1502720
},
{
"epoch": 0.02,
"learning_rate": 2.5387637147913046e-05,
"loss": 3.9212,
"step": 1503232
},
{
"epoch": 0.02,
"learning_rate": 2.5379251200402526e-05,
"loss": 3.899,
"step": 1503744
},
{
"epoch": 0.02,
"learning_rate": 2.5370865252892006e-05,
"loss": 3.9103,
"step": 1504256
},
{
"epoch": 0.02,
"learning_rate": 2.5362495684185218e-05,
"loss": 3.9082,
"step": 1504768
},
{
"epoch": 0.02,
"learning_rate": 2.5354109736674698e-05,
"loss": 3.9206,
"step": 1505280
},
{
"epoch": 0.02,
"learning_rate": 2.5345723789164178e-05,
"loss": 3.9077,
"step": 1505792
},
{
"epoch": 0.02,
"learning_rate": 2.5337337841653658e-05,
"loss": 3.9152,
"step": 1506304
},
{
"epoch": 0.02,
"learning_rate": 2.5328951894143138e-05,
"loss": 3.9044,
"step": 1506816
},
{
"epoch": 0.02,
"learning_rate": 2.5320565946632618e-05,
"loss": 3.9097,
"step": 1507328
},
{
"epoch": 0.02,
"learning_rate": 2.531219637792583e-05,
"loss": 3.9094,
"step": 1507840
},
{
"epoch": 0.02,
"learning_rate": 2.530381043041531e-05,
"loss": 3.9143,
"step": 1508352
},
{
"epoch": 0.02,
"learning_rate": 2.529542448290479e-05,
"loss": 3.9242,
"step": 1508864
},
{
"epoch": 0.02,
"learning_rate": 2.528703853539427e-05,
"loss": 3.9252,
"step": 1509376
},
{
"epoch": 0.02,
"learning_rate": 2.527866896668748e-05,
"loss": 3.9165,
"step": 1509888
},
{
"epoch": 0.02,
"learning_rate": 2.527028301917696e-05,
"loss": 3.909,
"step": 1510400
},
{
"epoch": 0.02,
"learning_rate": 2.526189707166644e-05,
"loss": 3.9141,
"step": 1510912
},
{
"epoch": 0.02,
"learning_rate": 2.525351112415592e-05,
"loss": 3.917,
"step": 1511424
},
{
"epoch": 0.02,
"learning_rate": 2.5245125176645402e-05,
"loss": 3.9075,
"step": 1511936
},
{
"epoch": 0.02,
"learning_rate": 2.5236739229134882e-05,
"loss": 3.9142,
"step": 1512448
},
{
"epoch": 0.02,
"learning_rate": 2.5228353281624362e-05,
"loss": 3.9116,
"step": 1512960
},
{
"epoch": 0.02,
"learning_rate": 2.521998371291757e-05,
"loss": 3.9105,
"step": 1513472
},
{
"epoch": 0.02,
"learning_rate": 2.521159776540705e-05,
"loss": 3.9069,
"step": 1513984
},
{
"epoch": 0.02,
"learning_rate": 2.520321181789653e-05,
"loss": 3.9082,
"step": 1514496
},
{
"epoch": 0.02,
"learning_rate": 2.519482587038601e-05,
"loss": 3.9044,
"step": 1515008
},
{
"epoch": 0.02,
"learning_rate": 2.5186439922875488e-05,
"loss": 3.9138,
"step": 1515520
},
{
"epoch": 0.02,
"learning_rate": 2.5178070354168704e-05,
"loss": 3.8992,
"step": 1516032
},
{
"epoch": 0.02,
"learning_rate": 2.5169684406658184e-05,
"loss": 3.9284,
"step": 1516544
},
{
"epoch": 0.02,
"learning_rate": 2.516129845914766e-05,
"loss": 3.9238,
"step": 1517056
},
{
"epoch": 0.02,
"learning_rate": 2.515291251163714e-05,
"loss": 3.9229,
"step": 1517568
},
{
"epoch": 0.02,
"learning_rate": 2.514452656412662e-05,
"loss": 3.9016,
"step": 1518080
},
{
"epoch": 0.02,
"learning_rate": 2.51361406166161e-05,
"loss": 3.9174,
"step": 1518592
},
{
"epoch": 0.02,
"learning_rate": 2.512775466910558e-05,
"loss": 3.92,
"step": 1519104
},
{
"epoch": 0.02,
"learning_rate": 2.511936872159506e-05,
"loss": 3.9182,
"step": 1519616
},
{
"epoch": 0.02,
"learning_rate": 2.511099915288827e-05,
"loss": 3.915,
"step": 1520128
},
{
"epoch": 0.02,
"learning_rate": 2.5102629584181485e-05,
"loss": 3.9167,
"step": 1520640
},
{
"epoch": 0.02,
"learning_rate": 2.509424363667096e-05,
"loss": 3.9148,
"step": 1521152
},
{
"epoch": 0.02,
"learning_rate": 2.508585768916044e-05,
"loss": 3.9201,
"step": 1521664
},
{
"epoch": 0.02,
"learning_rate": 2.507747174164992e-05,
"loss": 3.9135,
"step": 1522176
},
{
"epoch": 0.02,
"learning_rate": 2.50690857941394e-05,
"loss": 3.917,
"step": 1522688
},
{
"epoch": 0.02,
"learning_rate": 2.506071622543261e-05,
"loss": 3.9138,
"step": 1523200
},
{
"epoch": 0.02,
"learning_rate": 2.5052330277922094e-05,
"loss": 3.9088,
"step": 1523712
},
{
"epoch": 0.02,
"learning_rate": 2.5043944330411574e-05,
"loss": 3.9194,
"step": 1524224
},
{
"epoch": 0.02,
"learning_rate": 2.5035558382901054e-05,
"loss": 3.9191,
"step": 1524736
},
{
"epoch": 0.02,
"learning_rate": 2.5027172435390534e-05,
"loss": 3.9142,
"step": 1525248
},
{
"epoch": 0.02,
"learning_rate": 2.5018802866683743e-05,
"loss": 3.904,
"step": 1525760
},
{
"epoch": 0.02,
"learning_rate": 2.5010416919173223e-05,
"loss": 3.906,
"step": 1526272
},
{
"epoch": 0.03,
"eval_loss": 3.997375726699829,
"eval_runtime": 306.6544,
"eval_samples_per_second": 1244.368,
"eval_steps_per_second": 38.887,
"step": 1526400
},
{
"epoch": 1.0,
"learning_rate": 2.5002030971662703e-05,
"loss": 3.9159,
"step": 1526784
},
{
"epoch": 1.0,
"learning_rate": 2.4993645024152186e-05,
"loss": 3.9052,
"step": 1527296
},
{
"epoch": 1.0,
"learning_rate": 2.4985259076641666e-05,
"loss": 3.9167,
"step": 1527808
},
{
"epoch": 1.0,
"learning_rate": 2.4976889507934875e-05,
"loss": 3.912,
"step": 1528320
},
{
"epoch": 1.0,
"learning_rate": 2.4968503560424355e-05,
"loss": 3.926,
"step": 1528832
},
{
"epoch": 1.0,
"learning_rate": 2.4960117612913835e-05,
"loss": 3.9058,
"step": 1529344
},
{
"epoch": 1.0,
"learning_rate": 2.4951731665403315e-05,
"loss": 3.9077,
"step": 1529856
},
{
"epoch": 1.0,
"learning_rate": 2.4943345717892795e-05,
"loss": 3.8991,
"step": 1530368
},
{
"epoch": 1.0,
"learning_rate": 2.493495977038228e-05,
"loss": 3.9198,
"step": 1530880
},
{
"epoch": 1.0,
"learning_rate": 2.4926590201675487e-05,
"loss": 3.9176,
"step": 1531392
},
{
"epoch": 1.0,
"learning_rate": 2.4918204254164967e-05,
"loss": 3.9171,
"step": 1531904
},
{
"epoch": 1.0,
"learning_rate": 2.4909818306654447e-05,
"loss": 3.9146,
"step": 1532416
},
{
"epoch": 1.0,
"learning_rate": 2.4901432359143927e-05,
"loss": 3.9039,
"step": 1532928
},
{
"epoch": 1.0,
"learning_rate": 2.4893046411633404e-05,
"loss": 3.9141,
"step": 1533440
},
{
"epoch": 1.0,
"learning_rate": 2.4884660464122887e-05,
"loss": 3.9025,
"step": 1533952
},
{
"epoch": 1.0,
"learning_rate": 2.4876274516612367e-05,
"loss": 3.9114,
"step": 1534464
},
{
"epoch": 1.0,
"learning_rate": 2.4867888569101847e-05,
"loss": 3.9071,
"step": 1534976
},
{
"epoch": 1.0,
"learning_rate": 2.4859519000395056e-05,
"loss": 3.9044,
"step": 1535488
},
{
"epoch": 1.0,
"learning_rate": 2.4851133052884536e-05,
"loss": 3.9132,
"step": 1536000
},
{
"epoch": 1.0,
"learning_rate": 2.4842747105374016e-05,
"loss": 3.9258,
"step": 1536512
},
{
"epoch": 1.0,
"learning_rate": 2.4834361157863496e-05,
"loss": 3.9091,
"step": 1537024
},
{
"epoch": 1.0,
"learning_rate": 2.482597521035298e-05,
"loss": 3.9153,
"step": 1537536
},
{
"epoch": 1.0,
"learning_rate": 2.481758926284246e-05,
"loss": 3.9117,
"step": 1538048
},
{
"epoch": 1.0,
"learning_rate": 2.480920331533194e-05,
"loss": 3.9191,
"step": 1538560
},
{
"epoch": 1.0,
"learning_rate": 2.4800817367821416e-05,
"loss": 3.9068,
"step": 1539072
},
{
"epoch": 1.0,
"learning_rate": 2.479244779911463e-05,
"loss": 3.9148,
"step": 1539584
},
{
"epoch": 1.0,
"learning_rate": 2.478406185160411e-05,
"loss": 3.9083,
"step": 1540096
},
{
"epoch": 1.0,
"learning_rate": 2.477567590409359e-05,
"loss": 3.9042,
"step": 1540608
},
{
"epoch": 1.0,
"learning_rate": 2.4767289956583068e-05,
"loss": 3.899,
"step": 1541120
},
{
"epoch": 1.0,
"learning_rate": 2.475892038787628e-05,
"loss": 3.9066,
"step": 1541632
},
{
"epoch": 1.01,
"learning_rate": 2.475053444036576e-05,
"loss": 3.909,
"step": 1542144
},
{
"epoch": 1.01,
"learning_rate": 2.4742148492855237e-05,
"loss": 3.9155,
"step": 1542656
},
{
"epoch": 1.01,
"learning_rate": 2.4733762545344717e-05,
"loss": 3.9151,
"step": 1543168
},
{
"epoch": 1.01,
"learning_rate": 2.47253765978342e-05,
"loss": 3.9144,
"step": 1543680
},
{
"epoch": 1.01,
"learning_rate": 2.4717007029127413e-05,
"loss": 3.9099,
"step": 1544192
},
{
"epoch": 1.01,
"learning_rate": 2.470862108161689e-05,
"loss": 3.918,
"step": 1544704
},
{
"epoch": 1.01,
"learning_rate": 2.470023513410637e-05,
"loss": 3.9072,
"step": 1545216
},
{
"epoch": 1.01,
"learning_rate": 2.469184918659585e-05,
"loss": 3.9084,
"step": 1545728
},
{
"epoch": 1.01,
"learning_rate": 2.468346323908533e-05,
"loss": 3.895,
"step": 1546240
},
{
"epoch": 1.01,
"learning_rate": 2.467507729157481e-05,
"loss": 3.9103,
"step": 1546752
},
{
"epoch": 1.01,
"learning_rate": 2.466669134406429e-05,
"loss": 3.9055,
"step": 1547264
},
{
"epoch": 1.01,
"learning_rate": 2.4658321775357502e-05,
"loss": 3.9128,
"step": 1547776
},
{
"epoch": 1.01,
"learning_rate": 2.464995220665071e-05,
"loss": 3.9095,
"step": 1548288
},
{
"epoch": 1.01,
"learning_rate": 2.464156625914019e-05,
"loss": 3.9004,
"step": 1548800
},
{
"epoch": 1.01,
"learning_rate": 2.463318031162967e-05,
"loss": 3.918,
"step": 1549312
},
{
"epoch": 1.01,
"learning_rate": 2.462479436411915e-05,
"loss": 3.9066,
"step": 1549824
},
{
"epoch": 1.01,
"learning_rate": 2.4616408416608634e-05,
"loss": 3.9059,
"step": 1550336
},
{
"epoch": 1.01,
"learning_rate": 2.4608022469098114e-05,
"loss": 3.8948,
"step": 1550848
},
{
"epoch": 1.01,
"learning_rate": 2.459963652158759e-05,
"loss": 3.8959,
"step": 1551360
},
{
"epoch": 1.01,
"learning_rate": 2.459125057407707e-05,
"loss": 3.911,
"step": 1551872
},
{
"epoch": 1.01,
"learning_rate": 2.4582881005370283e-05,
"loss": 3.908,
"step": 1552384
},
{
"epoch": 1.01,
"learning_rate": 2.4574495057859763e-05,
"loss": 3.9021,
"step": 1552896
},
{
"epoch": 1.01,
"learning_rate": 2.4566109110349243e-05,
"loss": 3.8961,
"step": 1553408
},
{
"epoch": 1.01,
"learning_rate": 2.4557723162838723e-05,
"loss": 3.9083,
"step": 1553920
},
{
"epoch": 1.01,
"learning_rate": 2.4549337215328203e-05,
"loss": 3.8943,
"step": 1554432
},
{
"epoch": 1.01,
"learning_rate": 2.4540951267817683e-05,
"loss": 3.9106,
"step": 1554944
},
{
"epoch": 1.01,
"learning_rate": 2.4532565320307163e-05,
"loss": 3.8956,
"step": 1555456
},
{
"epoch": 1.01,
"learning_rate": 2.4524179372796643e-05,
"loss": 3.9106,
"step": 1555968
},
{
"epoch": 1.01,
"learning_rate": 2.4515826182893588e-05,
"loss": 3.9044,
"step": 1556480
},
{
"epoch": 1.01,
"learning_rate": 2.4507440235383064e-05,
"loss": 3.9035,
"step": 1556992
},
{
"epoch": 1.01,
"learning_rate": 2.4499070666676277e-05,
"loss": 3.897,
"step": 1557504
},
{
"epoch": 1.01,
"learning_rate": 2.4490684719165757e-05,
"loss": 3.9097,
"step": 1558016
},
{
"epoch": 1.01,
"learning_rate": 2.4482298771655237e-05,
"loss": 3.8937,
"step": 1558528
},
{
"epoch": 1.01,
"learning_rate": 2.4473912824144717e-05,
"loss": 3.9065,
"step": 1559040
},
{
"epoch": 1.01,
"learning_rate": 2.4465526876634197e-05,
"loss": 3.9105,
"step": 1559552
},
{
"epoch": 1.01,
"learning_rate": 2.4457140929123677e-05,
"loss": 3.9087,
"step": 1560064
},
{
"epoch": 1.01,
"learning_rate": 2.4448754981613157e-05,
"loss": 3.8996,
"step": 1560576
},
{
"epoch": 1.01,
"learning_rate": 2.4440369034102637e-05,
"loss": 3.9005,
"step": 1561088
},
{
"epoch": 1.01,
"learning_rate": 2.4431983086592117e-05,
"loss": 3.8962,
"step": 1561600
},
{
"epoch": 1.01,
"learning_rate": 2.4423597139081597e-05,
"loss": 3.8993,
"step": 1562112
},
{
"epoch": 1.01,
"learning_rate": 2.441522757037481e-05,
"loss": 3.914,
"step": 1562624
},
{
"epoch": 1.01,
"learning_rate": 2.440684162286429e-05,
"loss": 3.9088,
"step": 1563136
},
{
"epoch": 1.01,
"learning_rate": 2.439845567535377e-05,
"loss": 3.9157,
"step": 1563648
},
{
"epoch": 1.01,
"learning_rate": 2.4390069727843245e-05,
"loss": 3.9162,
"step": 1564160
},
{
"epoch": 1.01,
"learning_rate": 2.4381700159136458e-05,
"loss": 3.9185,
"step": 1564672
},
{
"epoch": 1.01,
"learning_rate": 2.4373314211625938e-05,
"loss": 3.8968,
"step": 1565184
},
{
"epoch": 1.01,
"learning_rate": 2.4364928264115418e-05,
"loss": 3.9068,
"step": 1565696
},
{
"epoch": 1.01,
"learning_rate": 2.4356542316604898e-05,
"loss": 3.9183,
"step": 1566208
},
{
"epoch": 1.01,
"learning_rate": 2.4348156369094378e-05,
"loss": 3.9025,
"step": 1566720
},
{
"epoch": 1.01,
"learning_rate": 2.4339770421583858e-05,
"loss": 3.9065,
"step": 1567232
},
{
"epoch": 1.01,
"learning_rate": 2.433140085287707e-05,
"loss": 3.9078,
"step": 1567744
},
{
"epoch": 1.01,
"learning_rate": 2.4323014905366547e-05,
"loss": 3.9243,
"step": 1568256
},
{
"epoch": 1.01,
"learning_rate": 2.4314628957856027e-05,
"loss": 3.9071,
"step": 1568768
},
{
"epoch": 1.01,
"learning_rate": 2.430624301034551e-05,
"loss": 3.8925,
"step": 1569280
},
{
"epoch": 1.01,
"learning_rate": 2.429785706283499e-05,
"loss": 3.9037,
"step": 1569792
},
{
"epoch": 1.01,
"learning_rate": 2.428947111532447e-05,
"loss": 3.9058,
"step": 1570304
},
{
"epoch": 1.01,
"learning_rate": 2.428108516781395e-05,
"loss": 3.912,
"step": 1570816
},
{
"epoch": 1.01,
"learning_rate": 2.4272699220303427e-05,
"loss": 3.914,
"step": 1571328
},
{
"epoch": 1.01,
"learning_rate": 2.426432965159664e-05,
"loss": 3.9021,
"step": 1571840
},
{
"epoch": 1.02,
"learning_rate": 2.425594370408612e-05,
"loss": 3.904,
"step": 1572352
},
{
"epoch": 1.02,
"learning_rate": 2.4247557756575602e-05,
"loss": 3.904,
"step": 1572864
},
{
"epoch": 1.02,
"learning_rate": 2.423917180906508e-05,
"loss": 3.8948,
"step": 1573376
},
{
"epoch": 1.02,
"learning_rate": 2.423080224035829e-05,
"loss": 3.9057,
"step": 1573888
},
{
"epoch": 1.02,
"learning_rate": 2.422241629284777e-05,
"loss": 3.9117,
"step": 1574400
},
{
"epoch": 1.02,
"learning_rate": 2.421403034533725e-05,
"loss": 3.9257,
"step": 1574912
},
{
"epoch": 1.02,
"learning_rate": 2.4205644397826728e-05,
"loss": 3.912,
"step": 1575424
},
{
"epoch": 1.02,
"learning_rate": 2.419725845031621e-05,
"loss": 3.8956,
"step": 1575936
},
{
"epoch": 1.02,
"learning_rate": 2.4188888881609424e-05,
"loss": 3.9057,
"step": 1576448
},
{
"epoch": 1.02,
"learning_rate": 2.41805029340989e-05,
"loss": 3.9018,
"step": 1576960
},
{
"epoch": 1.02,
"learning_rate": 2.417211698658838e-05,
"loss": 3.9146,
"step": 1577472
},
{
"epoch": 1.02,
"learning_rate": 2.416373103907786e-05,
"loss": 3.9123,
"step": 1577984
},
{
"epoch": 1.02,
"learning_rate": 2.415534509156734e-05,
"loss": 3.9092,
"step": 1578496
},
{
"epoch": 1.02,
"learning_rate": 2.414695914405682e-05,
"loss": 3.9017,
"step": 1579008
},
{
"epoch": 1.02,
"learning_rate": 2.4138573196546303e-05,
"loss": 3.9129,
"step": 1579520
},
{
"epoch": 1.02,
"learning_rate": 2.4130187249035783e-05,
"loss": 3.8929,
"step": 1580032
},
{
"epoch": 1.02,
"learning_rate": 2.4121817680328992e-05,
"loss": 3.9041,
"step": 1580544
},
{
"epoch": 1.02,
"learning_rate": 2.41134481116222e-05,
"loss": 3.8934,
"step": 1581056
},
{
"epoch": 1.02,
"learning_rate": 2.410506216411168e-05,
"loss": 3.9125,
"step": 1581568
},
{
"epoch": 1.02,
"learning_rate": 2.4096676216601165e-05,
"loss": 3.902,
"step": 1582080
},
{
"epoch": 1.02,
"learning_rate": 2.4088290269090645e-05,
"loss": 3.9034,
"step": 1582592
},
{
"epoch": 1.02,
"learning_rate": 2.4079904321580125e-05,
"loss": 3.898,
"step": 1583104
},
{
"epoch": 1.02,
"learning_rate": 2.4071518374069605e-05,
"loss": 3.9044,
"step": 1583616
},
{
"epoch": 1.02,
"learning_rate": 2.4063148805362814e-05,
"loss": 3.9044,
"step": 1584128
},
{
"epoch": 1.02,
"learning_rate": 2.4054762857852294e-05,
"loss": 3.9042,
"step": 1584640
},
{
"epoch": 1.02,
"learning_rate": 2.4046376910341774e-05,
"loss": 3.9157,
"step": 1585152
},
{
"epoch": 1.02,
"learning_rate": 2.4037990962831257e-05,
"loss": 3.917,
"step": 1585664
},
{
"epoch": 1.02,
"learning_rate": 2.4029621394124466e-05,
"loss": 3.9108,
"step": 1586176
},
{
"epoch": 1.02,
"learning_rate": 2.4021251825417675e-05,
"loss": 3.9031,
"step": 1586688
},
{
"epoch": 1.02,
"learning_rate": 2.4012865877907155e-05,
"loss": 3.9034,
"step": 1587200
},
{
"epoch": 1.02,
"learning_rate": 2.4004479930396635e-05,
"loss": 3.9135,
"step": 1587712
},
{
"epoch": 1.02,
"learning_rate": 2.399609398288612e-05,
"loss": 3.8948,
"step": 1588224
},
{
"epoch": 1.02,
"learning_rate": 2.39877080353756e-05,
"loss": 3.9107,
"step": 1588736
},
{
"epoch": 1.02,
"learning_rate": 2.397932208786508e-05,
"loss": 3.8973,
"step": 1589248
},
{
"epoch": 1.02,
"learning_rate": 2.3970952519158288e-05,
"loss": 3.9043,
"step": 1589760
},
{
"epoch": 1.02,
"learning_rate": 2.3962566571647767e-05,
"loss": 3.901,
"step": 1590272
},
{
"epoch": 1.02,
"learning_rate": 2.3954180624137247e-05,
"loss": 3.9007,
"step": 1590784
},
{
"epoch": 1.02,
"learning_rate": 2.3945794676626727e-05,
"loss": 3.8937,
"step": 1591296
},
{
"epoch": 1.02,
"learning_rate": 2.3937408729116207e-05,
"loss": 3.9103,
"step": 1591808
},
{
"epoch": 1.02,
"learning_rate": 2.3929022781605687e-05,
"loss": 3.892,
"step": 1592320
},
{
"epoch": 1.02,
"learning_rate": 2.3920636834095167e-05,
"loss": 3.9189,
"step": 1592832
},
{
"epoch": 1.02,
"learning_rate": 2.3912250886584647e-05,
"loss": 3.9111,
"step": 1593344
},
{
"epoch": 1.02,
"learning_rate": 2.3903881317877856e-05,
"loss": 3.921,
"step": 1593856
},
{
"epoch": 1.02,
"learning_rate": 2.3895495370367336e-05,
"loss": 3.8897,
"step": 1594368
},
{
"epoch": 1.02,
"learning_rate": 2.388710942285682e-05,
"loss": 3.9124,
"step": 1594880
},
{
"epoch": 1.02,
"learning_rate": 2.38787234753463e-05,
"loss": 3.9111,
"step": 1595392
},
{
"epoch": 1.02,
"learning_rate": 2.387033752783578e-05,
"loss": 3.9108,
"step": 1595904
},
{
"epoch": 1.02,
"learning_rate": 2.386196795912899e-05,
"loss": 3.9082,
"step": 1596416
},
{
"epoch": 1.02,
"learning_rate": 2.385358201161847e-05,
"loss": 3.9107,
"step": 1596928
},
{
"epoch": 1.02,
"learning_rate": 2.384519606410795e-05,
"loss": 3.9057,
"step": 1597440
},
{
"epoch": 1.02,
"learning_rate": 2.383681011659743e-05,
"loss": 3.9114,
"step": 1597952
},
{
"epoch": 1.02,
"learning_rate": 2.3828424169086912e-05,
"loss": 3.8994,
"step": 1598464
},
{
"epoch": 1.02,
"learning_rate": 2.382003822157639e-05,
"loss": 3.9113,
"step": 1598976
},
{
"epoch": 1.02,
"learning_rate": 2.381165227406587e-05,
"loss": 3.9045,
"step": 1599488
},
{
"epoch": 1.02,
"learning_rate": 2.380326632655535e-05,
"loss": 3.9024,
"step": 1600000
},
{
"epoch": 1.02,
"learning_rate": 2.3794896757848557e-05,
"loss": 3.906,
"step": 1600512
},
{
"epoch": 1.02,
"learning_rate": 2.378651081033804e-05,
"loss": 3.9145,
"step": 1601024
},
{
"epoch": 1.02,
"learning_rate": 2.3778141241631253e-05,
"loss": 3.9061,
"step": 1601536
},
{
"epoch": 1.02,
"learning_rate": 2.3769755294120733e-05,
"loss": 3.8959,
"step": 1602048
},
{
"epoch": 1.02,
"learning_rate": 2.376136934661021e-05,
"loss": 3.9013,
"step": 1602560
},
{
"epoch": 1.03,
"eval_loss": 3.99383282661438,
"eval_runtime": 309.9904,
"eval_samples_per_second": 1230.977,
"eval_steps_per_second": 38.469,
"step": 1602720
},
{
"epoch": 0.0,
"learning_rate": 2.375298339909969e-05,
"loss": 3.9047,
"step": 1603072
},
{
"epoch": 0.0,
"learning_rate": 2.374459745158917e-05,
"loss": 3.8959,
"step": 1603584
},
{
"epoch": 0.0,
"learning_rate": 2.373621150407865e-05,
"loss": 3.9058,
"step": 1604096
},
{
"epoch": 0.0,
"learning_rate": 2.372782555656813e-05,
"loss": 3.9078,
"step": 1604608
},
{
"epoch": 0.0,
"learning_rate": 2.3719439609057613e-05,
"loss": 3.9126,
"step": 1605120
},
{
"epoch": 0.0,
"learning_rate": 2.3711053661547093e-05,
"loss": 3.9026,
"step": 1605632
},
{
"epoch": 0.0,
"learning_rate": 2.370266771403657e-05,
"loss": 3.8986,
"step": 1606144
},
{
"epoch": 0.0,
"learning_rate": 2.369428176652605e-05,
"loss": 3.89,
"step": 1606656
},
{
"epoch": 0.0,
"learning_rate": 2.368589581901553e-05,
"loss": 3.9066,
"step": 1607168
},
{
"epoch": 0.0,
"learning_rate": 2.367750987150501e-05,
"loss": 3.9126,
"step": 1607680
},
{
"epoch": 0.0,
"learning_rate": 2.366912392399449e-05,
"loss": 3.9069,
"step": 1608192
},
{
"epoch": 0.0,
"learning_rate": 2.3660737976483973e-05,
"loss": 3.91,
"step": 1608704
},
{
"epoch": 0.0,
"learning_rate": 2.365235202897345e-05,
"loss": 3.8956,
"step": 1609216
},
{
"epoch": 0.0,
"learning_rate": 2.364396608146293e-05,
"loss": 3.9063,
"step": 1609728
},
{
"epoch": 0.0,
"learning_rate": 2.363558013395241e-05,
"loss": 3.8994,
"step": 1610240
},
{
"epoch": 0.0,
"learning_rate": 2.362719418644189e-05,
"loss": 3.9018,
"step": 1610752
},
{
"epoch": 0.0,
"learning_rate": 2.361880823893137e-05,
"loss": 3.8955,
"step": 1611264
},
{
"epoch": 0.0,
"learning_rate": 2.361043867022458e-05,
"loss": 3.9017,
"step": 1611776
},
{
"epoch": 0.0,
"learning_rate": 2.360205272271406e-05,
"loss": 3.898,
"step": 1612288
},
{
"epoch": 0.0,
"learning_rate": 2.359366677520354e-05,
"loss": 3.9175,
"step": 1612800
},
{
"epoch": 0.0,
"learning_rate": 2.358528082769302e-05,
"loss": 3.9045,
"step": 1613312
},
{
"epoch": 0.0,
"learning_rate": 2.35768948801825e-05,
"loss": 3.9152,
"step": 1613824
},
{
"epoch": 0.0,
"learning_rate": 2.356850893267198e-05,
"loss": 3.9009,
"step": 1614336
},
{
"epoch": 0.0,
"learning_rate": 2.3560122985161458e-05,
"loss": 3.9101,
"step": 1614848
},
{
"epoch": 0.0,
"learning_rate": 2.3551737037650938e-05,
"loss": 3.8976,
"step": 1615360
},
{
"epoch": 0.0,
"learning_rate": 2.354335109014042e-05,
"loss": 3.9083,
"step": 1615872
},
{
"epoch": 0.0,
"learning_rate": 2.353498152143363e-05,
"loss": 3.9043,
"step": 1616384
},
{
"epoch": 0.0,
"learning_rate": 2.3526611952726843e-05,
"loss": 3.8935,
"step": 1616896
},
{
"epoch": 0.0,
"learning_rate": 2.3518226005216323e-05,
"loss": 3.8921,
"step": 1617408
},
{
"epoch": 0.0,
"learning_rate": 2.3509840057705803e-05,
"loss": 3.8992,
"step": 1617920
},
{
"epoch": 0.01,
"learning_rate": 2.3501454110195283e-05,
"loss": 3.9042,
"step": 1618432
},
{
"epoch": 0.01,
"learning_rate": 2.3493068162684763e-05,
"loss": 3.9059,
"step": 1618944
},
{
"epoch": 0.01,
"learning_rate": 2.3484682215174242e-05,
"loss": 3.9077,
"step": 1619456
},
{
"epoch": 0.01,
"learning_rate": 2.3476296267663722e-05,
"loss": 3.9125,
"step": 1619968
},
{
"epoch": 0.01,
"learning_rate": 2.346792669895693e-05,
"loss": 3.9031,
"step": 1620480
},
{
"epoch": 0.01,
"learning_rate": 2.345954075144641e-05,
"loss": 3.9067,
"step": 1620992
},
{
"epoch": 0.01,
"learning_rate": 2.345115480393589e-05,
"loss": 3.9005,
"step": 1621504
},
{
"epoch": 0.01,
"learning_rate": 2.3442768856425375e-05,
"loss": 3.8999,
"step": 1622016
},
{
"epoch": 0.01,
"learning_rate": 2.3434382908914855e-05,
"loss": 3.8861,
"step": 1622528
},
{
"epoch": 0.01,
"learning_rate": 2.3425996961404335e-05,
"loss": 3.9043,
"step": 1623040
},
{
"epoch": 0.01,
"learning_rate": 2.3417627392697544e-05,
"loss": 3.8964,
"step": 1623552
},
{
"epoch": 0.01,
"learning_rate": 2.3409241445187024e-05,
"loss": 3.9069,
"step": 1624064
},
{
"epoch": 0.01,
"learning_rate": 2.3400871876480236e-05,
"loss": 3.9011,
"step": 1624576
},
{
"epoch": 0.01,
"learning_rate": 2.3392485928969716e-05,
"loss": 3.8941,
"step": 1625088
},
{
"epoch": 0.01,
"learning_rate": 2.3384099981459196e-05,
"loss": 3.9109,
"step": 1625600
},
{
"epoch": 0.01,
"learning_rate": 2.3375714033948676e-05,
"loss": 3.8988,
"step": 1626112
},
{
"epoch": 0.01,
"learning_rate": 2.3367328086438156e-05,
"loss": 3.9003,
"step": 1626624
},
{
"epoch": 0.01,
"learning_rate": 2.3358942138927633e-05,
"loss": 3.8892,
"step": 1627136
},
{
"epoch": 0.01,
"learning_rate": 2.3350556191417113e-05,
"loss": 3.8857,
"step": 1627648
},
{
"epoch": 0.01,
"learning_rate": 2.3342170243906593e-05,
"loss": 3.9041,
"step": 1628160
},
{
"epoch": 0.01,
"learning_rate": 2.3333784296396076e-05,
"loss": 3.9021,
"step": 1628672
},
{
"epoch": 0.01,
"learning_rate": 2.3325398348885556e-05,
"loss": 3.8953,
"step": 1629184
},
{
"epoch": 0.01,
"learning_rate": 2.3317012401375036e-05,
"loss": 3.8921,
"step": 1629696
},
{
"epoch": 0.01,
"learning_rate": 2.3308626453864516e-05,
"loss": 3.9024,
"step": 1630208
},
{
"epoch": 0.01,
"learning_rate": 2.3300256885157725e-05,
"loss": 3.8837,
"step": 1630720
},
{
"epoch": 0.01,
"learning_rate": 2.3291887316450937e-05,
"loss": 3.9042,
"step": 1631232
},
{
"epoch": 0.01,
"learning_rate": 2.3283501368940417e-05,
"loss": 3.8911,
"step": 1631744
},
{
"epoch": 0.01,
"learning_rate": 2.3275115421429897e-05,
"loss": 3.9021,
"step": 1632256
},
{
"epoch": 0.01,
"learning_rate": 2.3266745852723106e-05,
"loss": 3.8955,
"step": 1632768
},
{
"epoch": 0.01,
"learning_rate": 2.3258359905212586e-05,
"loss": 3.8983,
"step": 1633280
},
{
"epoch": 0.01,
"learning_rate": 2.3249973957702066e-05,
"loss": 3.8906,
"step": 1633792
},
{
"epoch": 0.01,
"learning_rate": 2.3241588010191546e-05,
"loss": 3.8993,
"step": 1634304
},
{
"epoch": 0.01,
"learning_rate": 2.323320206268103e-05,
"loss": 3.8926,
"step": 1634816
},
{
"epoch": 0.01,
"learning_rate": 2.322481611517051e-05,
"loss": 3.8947,
"step": 1635328
},
{
"epoch": 0.01,
"learning_rate": 2.321643016765999e-05,
"loss": 3.9019,
"step": 1635840
},
{
"epoch": 0.01,
"learning_rate": 2.3208044220149466e-05,
"loss": 3.9017,
"step": 1636352
},
{
"epoch": 0.01,
"learning_rate": 2.3199658272638946e-05,
"loss": 3.8883,
"step": 1636864
},
{
"epoch": 0.01,
"learning_rate": 2.3191272325128426e-05,
"loss": 3.9007,
"step": 1637376
},
{
"epoch": 0.01,
"learning_rate": 2.318290275642164e-05,
"loss": 3.8852,
"step": 1637888
},
{
"epoch": 0.01,
"learning_rate": 2.317451680891112e-05,
"loss": 3.8926,
"step": 1638400
},
{
"epoch": 0.01,
"learning_rate": 2.31661308614006e-05,
"loss": 3.9073,
"step": 1638912
},
{
"epoch": 0.01,
"learning_rate": 2.3157744913890078e-05,
"loss": 3.9031,
"step": 1639424
},
{
"epoch": 0.01,
"learning_rate": 2.3149358966379558e-05,
"loss": 3.9053,
"step": 1639936
},
{
"epoch": 0.01,
"learning_rate": 2.3140973018869038e-05,
"loss": 3.9058,
"step": 1640448
},
{
"epoch": 0.01,
"learning_rate": 2.313260345016225e-05,
"loss": 3.9173,
"step": 1640960
},
{
"epoch": 0.01,
"learning_rate": 2.312421750265173e-05,
"loss": 3.8949,
"step": 1641472
},
{
"epoch": 0.01,
"learning_rate": 2.311583155514121e-05,
"loss": 3.8991,
"step": 1641984
},
{
"epoch": 0.01,
"learning_rate": 2.310744560763069e-05,
"loss": 3.9119,
"step": 1642496
},
{
"epoch": 0.01,
"learning_rate": 2.309905966012017e-05,
"loss": 3.8931,
"step": 1643008
},
{
"epoch": 0.01,
"learning_rate": 2.3090673712609647e-05,
"loss": 3.9025,
"step": 1643520
},
{
"epoch": 0.01,
"learning_rate": 2.3082287765099127e-05,
"loss": 3.9039,
"step": 1644032
},
{
"epoch": 0.01,
"learning_rate": 2.3073901817588607e-05,
"loss": 3.9097,
"step": 1644544
},
{
"epoch": 0.01,
"learning_rate": 2.3065532248881823e-05,
"loss": 3.9024,
"step": 1645056
},
{
"epoch": 0.01,
"learning_rate": 2.30571463013713e-05,
"loss": 3.8892,
"step": 1645568
},
{
"epoch": 0.01,
"learning_rate": 2.3048776732664512e-05,
"loss": 3.8963,
"step": 1646080
},
{
"epoch": 0.01,
"learning_rate": 2.3040390785153992e-05,
"loss": 3.8987,
"step": 1646592
},
{
"epoch": 0.01,
"learning_rate": 2.303200483764347e-05,
"loss": 3.9049,
"step": 1647104
},
{
"epoch": 0.01,
"learning_rate": 2.3023618890132952e-05,
"loss": 3.904,
"step": 1647616
},
{
"epoch": 0.01,
"learning_rate": 2.3015232942622432e-05,
"loss": 3.8965,
"step": 1648128
},
{
"epoch": 0.02,
"learning_rate": 2.3006863373915644e-05,
"loss": 3.899,
"step": 1648640
},
{
"epoch": 0.02,
"learning_rate": 2.299847742640512e-05,
"loss": 3.8924,
"step": 1649152
},
{
"epoch": 0.02,
"learning_rate": 2.29900914788946e-05,
"loss": 3.8895,
"step": 1649664
},
{
"epoch": 0.02,
"learning_rate": 2.298170553138408e-05,
"loss": 3.8958,
"step": 1650176
},
{
"epoch": 0.02,
"learning_rate": 2.2973335962677293e-05,
"loss": 3.9073,
"step": 1650688
},
{
"epoch": 0.02,
"learning_rate": 2.2964950015166773e-05,
"loss": 3.9181,
"step": 1651200
},
{
"epoch": 0.02,
"learning_rate": 2.2956564067656253e-05,
"loss": 3.9074,
"step": 1651712
},
{
"epoch": 0.02,
"learning_rate": 2.2948178120145733e-05,
"loss": 3.886,
"step": 1652224
},
{
"epoch": 0.02,
"learning_rate": 2.2939792172635213e-05,
"loss": 3.9019,
"step": 1652736
},
{
"epoch": 0.02,
"learning_rate": 2.2931406225124693e-05,
"loss": 3.8961,
"step": 1653248
},
{
"epoch": 0.02,
"learning_rate": 2.2923020277614173e-05,
"loss": 3.9071,
"step": 1653760
},
{
"epoch": 0.02,
"learning_rate": 2.2914634330103653e-05,
"loss": 3.9015,
"step": 1654272
},
{
"epoch": 0.02,
"learning_rate": 2.2906281140200595e-05,
"loss": 3.9013,
"step": 1654784
},
{
"epoch": 0.02,
"learning_rate": 2.2897895192690074e-05,
"loss": 3.8967,
"step": 1655296
},
{
"epoch": 0.02,
"learning_rate": 2.2889509245179554e-05,
"loss": 3.9,
"step": 1655808
},
{
"epoch": 0.02,
"learning_rate": 2.2881123297669034e-05,
"loss": 3.89,
"step": 1656320
},
{
"epoch": 0.02,
"learning_rate": 2.2872737350158514e-05,
"loss": 3.8977,
"step": 1656832
},
{
"epoch": 0.02,
"learning_rate": 2.2864351402647998e-05,
"loss": 3.8874,
"step": 1657344
},
{
"epoch": 0.02,
"learning_rate": 2.2855981833941207e-05,
"loss": 3.9095,
"step": 1657856
},
{
"epoch": 0.02,
"learning_rate": 2.2847595886430687e-05,
"loss": 3.8946,
"step": 1658368
},
{
"epoch": 0.02,
"learning_rate": 2.2839209938920167e-05,
"loss": 3.8961,
"step": 1658880
},
{
"epoch": 0.02,
"learning_rate": 2.2830823991409647e-05,
"loss": 3.8859,
"step": 1659392
},
{
"epoch": 0.02,
"learning_rate": 2.2822438043899123e-05,
"loss": 3.8991,
"step": 1659904
},
{
"epoch": 0.02,
"learning_rate": 2.2814052096388607e-05,
"loss": 3.8963,
"step": 1660416
},
{
"epoch": 0.02,
"learning_rate": 2.2805666148878086e-05,
"loss": 3.8973,
"step": 1660928
},
{
"epoch": 0.02,
"learning_rate": 2.2797280201367566e-05,
"loss": 3.9071,
"step": 1661440
},
{
"epoch": 0.02,
"learning_rate": 2.2788894253857046e-05,
"loss": 3.9103,
"step": 1661952
},
{
"epoch": 0.02,
"learning_rate": 2.2780541063953988e-05,
"loss": 3.9038,
"step": 1662464
},
{
"epoch": 0.02,
"learning_rate": 2.2772155116443468e-05,
"loss": 3.8987,
"step": 1662976
},
{
"epoch": 0.02,
"learning_rate": 2.2763769168932948e-05,
"loss": 3.8938,
"step": 1663488
},
{
"epoch": 0.02,
"learning_rate": 2.2755383221422428e-05,
"loss": 3.9079,
"step": 1664000
},
{
"epoch": 0.02,
"learning_rate": 2.2746997273911908e-05,
"loss": 3.8907,
"step": 1664512
},
{
"epoch": 0.02,
"learning_rate": 2.2738611326401388e-05,
"loss": 3.9025,
"step": 1665024
},
{
"epoch": 0.02,
"learning_rate": 2.2730225378890868e-05,
"loss": 3.8897,
"step": 1665536
},
{
"epoch": 0.02,
"learning_rate": 2.2721839431380348e-05,
"loss": 3.9,
"step": 1666048
},
{
"epoch": 0.02,
"learning_rate": 2.271346986267356e-05,
"loss": 3.8887,
"step": 1666560
},
{
"epoch": 0.02,
"learning_rate": 2.2705100293966773e-05,
"loss": 3.896,
"step": 1667072
},
{
"epoch": 0.02,
"learning_rate": 2.269671434645625e-05,
"loss": 3.8935,
"step": 1667584
},
{
"epoch": 0.02,
"learning_rate": 2.268832839894573e-05,
"loss": 3.8962,
"step": 1668096
},
{
"epoch": 0.02,
"learning_rate": 2.267994245143521e-05,
"loss": 3.8901,
"step": 1668608
},
{
"epoch": 0.02,
"learning_rate": 2.267155650392469e-05,
"loss": 3.91,
"step": 1669120
},
{
"epoch": 0.02,
"learning_rate": 2.26631869352179e-05,
"loss": 3.9079,
"step": 1669632
},
{
"epoch": 0.02,
"learning_rate": 2.265480098770738e-05,
"loss": 3.9097,
"step": 1670144
},
{
"epoch": 0.02,
"learning_rate": 2.264641504019686e-05,
"loss": 3.8854,
"step": 1670656
},
{
"epoch": 0.02,
"learning_rate": 2.263802909268634e-05,
"loss": 3.9066,
"step": 1671168
},
{
"epoch": 0.02,
"learning_rate": 2.262964314517582e-05,
"loss": 3.9059,
"step": 1671680
},
{
"epoch": 0.02,
"learning_rate": 2.26212571976653e-05,
"loss": 3.9051,
"step": 1672192
},
{
"epoch": 0.02,
"learning_rate": 2.2612871250154778e-05,
"loss": 3.8988,
"step": 1672704
},
{
"epoch": 0.02,
"learning_rate": 2.260448530264426e-05,
"loss": 3.9034,
"step": 1673216
},
{
"epoch": 0.02,
"learning_rate": 2.2596115733937474e-05,
"loss": 3.9008,
"step": 1673728
},
{
"epoch": 0.02,
"learning_rate": 2.2587746165230683e-05,
"loss": 3.9073,
"step": 1674240
},
{
"epoch": 0.02,
"learning_rate": 2.2579360217720163e-05,
"loss": 3.8908,
"step": 1674752
},
{
"epoch": 0.02,
"learning_rate": 2.2570974270209643e-05,
"loss": 3.9064,
"step": 1675264
},
{
"epoch": 0.02,
"learning_rate": 2.2562588322699123e-05,
"loss": 3.8956,
"step": 1675776
},
{
"epoch": 0.02,
"learning_rate": 2.2554202375188603e-05,
"loss": 3.8965,
"step": 1676288
},
{
"epoch": 0.02,
"learning_rate": 2.2545832806481815e-05,
"loss": 3.8996,
"step": 1676800
},
{
"epoch": 0.02,
"learning_rate": 2.2537446858971295e-05,
"loss": 3.8998,
"step": 1677312
},
{
"epoch": 0.02,
"learning_rate": 2.2529060911460775e-05,
"loss": 3.904,
"step": 1677824
},
{
"epoch": 0.02,
"learning_rate": 2.252067496395025e-05,
"loss": 3.8863,
"step": 1678336
},
{
"epoch": 0.02,
"learning_rate": 2.251228901643973e-05,
"loss": 3.8963,
"step": 1678848
},
{
"epoch": 0.03,
"eval_loss": 3.9906888008117676,
"eval_runtime": 293.3761,
"eval_samples_per_second": 1300.689,
"eval_steps_per_second": 40.647,
"step": 1679040
},
{
"epoch": 1.0,
"learning_rate": 2.2503903068929215e-05,
"loss": 3.9017,
"step": 1679360
},
{
"epoch": 1.0,
"learning_rate": 2.2495517121418695e-05,
"loss": 3.8884,
"step": 1679872
},
{
"epoch": 1.0,
"learning_rate": 2.2487131173908175e-05,
"loss": 3.9008,
"step": 1680384
},
{
"epoch": 1.0,
"learning_rate": 2.2478761605201384e-05,
"loss": 3.9024,
"step": 1680896
},
{
"epoch": 1.0,
"learning_rate": 2.2470375657690864e-05,
"loss": 3.9075,
"step": 1681408
},
{
"epoch": 1.0,
"learning_rate": 2.2461989710180344e-05,
"loss": 3.8944,
"step": 1681920
},
{
"epoch": 1.0,
"learning_rate": 2.2453603762669824e-05,
"loss": 3.8893,
"step": 1682432
},
{
"epoch": 1.0,
"learning_rate": 2.244525057276677e-05,
"loss": 3.8887,
"step": 1682944
},
{
"epoch": 1.0,
"learning_rate": 2.243686462525625e-05,
"loss": 3.8966,
"step": 1683456
},
{
"epoch": 1.0,
"learning_rate": 2.2428478677745725e-05,
"loss": 3.9069,
"step": 1683968
},
{
"epoch": 1.0,
"learning_rate": 2.2420092730235205e-05,
"loss": 3.9005,
"step": 1684480
},
{
"epoch": 1.0,
"learning_rate": 2.241172316152842e-05,
"loss": 3.9026,
"step": 1684992
},
{
"epoch": 1.0,
"learning_rate": 2.24033372140179e-05,
"loss": 3.894,
"step": 1685504
},
{
"epoch": 1.0,
"learning_rate": 2.2394951266507378e-05,
"loss": 3.8929,
"step": 1686016
},
{
"epoch": 1.0,
"learning_rate": 2.2386565318996858e-05,
"loss": 3.8928,
"step": 1686528
},
{
"epoch": 1.0,
"learning_rate": 2.2378179371486338e-05,
"loss": 3.8932,
"step": 1687040
},
{
"epoch": 1.0,
"learning_rate": 2.2369793423975818e-05,
"loss": 3.8898,
"step": 1687552
},
{
"epoch": 1.0,
"learning_rate": 2.2361407476465298e-05,
"loss": 3.8919,
"step": 1688064
},
{
"epoch": 1.0,
"learning_rate": 2.2353021528954778e-05,
"loss": 3.8944,
"step": 1688576
},
{
"epoch": 1.0,
"learning_rate": 2.234465196024799e-05,
"loss": 3.9079,
"step": 1689088
},
{
"epoch": 1.0,
"learning_rate": 2.233626601273747e-05,
"loss": 3.9007,
"step": 1689600
},
{
"epoch": 1.0,
"learning_rate": 2.232789644403068e-05,
"loss": 3.9086,
"step": 1690112
},
{
"epoch": 1.0,
"learning_rate": 2.231951049652016e-05,
"loss": 3.8914,
"step": 1690624
},
{
"epoch": 1.0,
"learning_rate": 2.231112454900964e-05,
"loss": 3.9061,
"step": 1691136
},
{
"epoch": 1.0,
"learning_rate": 2.2302738601499122e-05,
"loss": 3.89,
"step": 1691648
},
{
"epoch": 1.0,
"learning_rate": 2.2294352653988602e-05,
"loss": 3.9041,
"step": 1692160
},
{
"epoch": 1.0,
"learning_rate": 2.2285966706478082e-05,
"loss": 3.8937,
"step": 1692672
},
{
"epoch": 1.0,
"learning_rate": 2.227758075896756e-05,
"loss": 3.8844,
"step": 1693184
},
{
"epoch": 1.0,
"learning_rate": 2.226919481145704e-05,
"loss": 3.8917,
"step": 1693696
},
{
"epoch": 1.0,
"learning_rate": 2.226082524275025e-05,
"loss": 3.8921,
"step": 1694208
},
{
"epoch": 1.01,
"learning_rate": 2.225243929523973e-05,
"loss": 3.8964,
"step": 1694720
},
{
"epoch": 1.01,
"learning_rate": 2.224405334772921e-05,
"loss": 3.8994,
"step": 1695232
},
{
"epoch": 1.01,
"learning_rate": 2.2235683779022424e-05,
"loss": 3.9001,
"step": 1695744
},
{
"epoch": 1.01,
"learning_rate": 2.2227297831511904e-05,
"loss": 3.9097,
"step": 1696256
},
{
"epoch": 1.01,
"learning_rate": 2.221891188400138e-05,
"loss": 3.8902,
"step": 1696768
},
{
"epoch": 1.01,
"learning_rate": 2.221052593649086e-05,
"loss": 3.9036,
"step": 1697280
},
{
"epoch": 1.01,
"learning_rate": 2.2202156367784076e-05,
"loss": 3.8981,
"step": 1697792
},
{
"epoch": 1.01,
"learning_rate": 2.2193770420273553e-05,
"loss": 3.8867,
"step": 1698304
},
{
"epoch": 1.01,
"learning_rate": 2.2185384472763032e-05,
"loss": 3.8816,
"step": 1698816
},
{
"epoch": 1.01,
"learning_rate": 2.2176998525252512e-05,
"loss": 3.8918,
"step": 1699328
},
{
"epoch": 1.01,
"learning_rate": 2.2168612577741992e-05,
"loss": 3.8949,
"step": 1699840
},
{
"epoch": 1.01,
"learning_rate": 2.2160226630231472e-05,
"loss": 3.8985,
"step": 1700352
},
{
"epoch": 1.01,
"learning_rate": 2.2151840682720952e-05,
"loss": 3.8918,
"step": 1700864
},
{
"epoch": 1.01,
"learning_rate": 2.2143454735210432e-05,
"loss": 3.8877,
"step": 1701376
},
{
"epoch": 1.01,
"learning_rate": 2.2135068787699912e-05,
"loss": 3.9071,
"step": 1701888
},
{
"epoch": 1.01,
"learning_rate": 2.2126699218993125e-05,
"loss": 3.8916,
"step": 1702400
},
{
"epoch": 1.01,
"learning_rate": 2.2118313271482605e-05,
"loss": 3.8924,
"step": 1702912
},
{
"epoch": 1.01,
"learning_rate": 2.2109927323972085e-05,
"loss": 3.884,
"step": 1703424
},
{
"epoch": 1.01,
"learning_rate": 2.2101557755265294e-05,
"loss": 3.8781,
"step": 1703936
},
{
"epoch": 1.01,
"learning_rate": 2.2093171807754777e-05,
"loss": 3.8981,
"step": 1704448
},
{
"epoch": 1.01,
"learning_rate": 2.2084785860244257e-05,
"loss": 3.8957,
"step": 1704960
},
{
"epoch": 1.01,
"learning_rate": 2.2076399912733734e-05,
"loss": 3.8898,
"step": 1705472
},
{
"epoch": 1.01,
"learning_rate": 2.2068013965223214e-05,
"loss": 3.8845,
"step": 1705984
},
{
"epoch": 1.01,
"learning_rate": 2.2059628017712693e-05,
"loss": 3.8992,
"step": 1706496
},
{
"epoch": 1.01,
"learning_rate": 2.2051242070202173e-05,
"loss": 3.8745,
"step": 1707008
},
{
"epoch": 1.01,
"learning_rate": 2.2042872501495386e-05,
"loss": 3.8997,
"step": 1707520
},
{
"epoch": 1.01,
"learning_rate": 2.2034486553984866e-05,
"loss": 3.8851,
"step": 1708032
},
{
"epoch": 1.01,
"learning_rate": 2.2026100606474346e-05,
"loss": 3.8912,
"step": 1708544
},
{
"epoch": 1.01,
"learning_rate": 2.2017714658963826e-05,
"loss": 3.8941,
"step": 1709056
},
{
"epoch": 1.01,
"learning_rate": 2.2009328711453306e-05,
"loss": 3.8875,
"step": 1709568
},
{
"epoch": 1.01,
"learning_rate": 2.2000959142746515e-05,
"loss": 3.8857,
"step": 1710080
},
{
"epoch": 1.01,
"learning_rate": 2.1992573195235995e-05,
"loss": 3.8977,
"step": 1710592
},
{
"epoch": 1.01,
"learning_rate": 2.1984187247725478e-05,
"loss": 3.8825,
"step": 1711104
},
{
"epoch": 1.01,
"learning_rate": 2.1975801300214958e-05,
"loss": 3.8881,
"step": 1711616
},
{
"epoch": 1.01,
"learning_rate": 2.1967431731508167e-05,
"loss": 3.8965,
"step": 1712128
},
{
"epoch": 1.01,
"learning_rate": 2.1959045783997647e-05,
"loss": 3.8962,
"step": 1712640
},
{
"epoch": 1.01,
"learning_rate": 2.1950659836487127e-05,
"loss": 3.8854,
"step": 1713152
},
{
"epoch": 1.01,
"learning_rate": 2.1942273888976607e-05,
"loss": 3.8935,
"step": 1713664
},
{
"epoch": 1.01,
"learning_rate": 2.1933887941466087e-05,
"loss": 3.8773,
"step": 1714176
},
{
"epoch": 1.01,
"learning_rate": 2.1925501993955567e-05,
"loss": 3.8876,
"step": 1714688
},
{
"epoch": 1.01,
"learning_rate": 2.1917116046445047e-05,
"loss": 3.8977,
"step": 1715200
},
{
"epoch": 1.01,
"learning_rate": 2.1908730098934527e-05,
"loss": 3.8975,
"step": 1715712
},
{
"epoch": 1.01,
"learning_rate": 2.1900344151424007e-05,
"loss": 3.9036,
"step": 1716224
},
{
"epoch": 1.01,
"learning_rate": 2.1891974582717216e-05,
"loss": 3.8959,
"step": 1716736
},
{
"epoch": 1.01,
"learning_rate": 2.18835886352067e-05,
"loss": 3.9121,
"step": 1717248
},
{
"epoch": 1.01,
"learning_rate": 2.187520268769618e-05,
"loss": 3.8855,
"step": 1717760
},
{
"epoch": 1.01,
"learning_rate": 2.186681674018566e-05,
"loss": 3.8973,
"step": 1718272
},
{
"epoch": 1.01,
"learning_rate": 2.185843079267514e-05,
"loss": 3.9038,
"step": 1718784
},
{
"epoch": 1.01,
"learning_rate": 2.185004484516462e-05,
"loss": 3.8834,
"step": 1719296
},
{
"epoch": 1.01,
"learning_rate": 2.1841658897654096e-05,
"loss": 3.8962,
"step": 1719808
},
{
"epoch": 1.01,
"learning_rate": 2.1833289328947308e-05,
"loss": 3.8977,
"step": 1720320
},
{
"epoch": 1.01,
"learning_rate": 2.1824903381436788e-05,
"loss": 3.906,
"step": 1720832
},
{
"epoch": 1.01,
"learning_rate": 2.1816550191533733e-05,
"loss": 3.8942,
"step": 1721344
},
{
"epoch": 1.01,
"learning_rate": 2.1808164244023213e-05,
"loss": 3.884,
"step": 1721856
},
{
"epoch": 1.01,
"learning_rate": 2.179977829651269e-05,
"loss": 3.8882,
"step": 1722368
},
{
"epoch": 1.01,
"learning_rate": 2.179139234900217e-05,
"loss": 3.8919,
"step": 1722880
},
{
"epoch": 1.01,
"learning_rate": 2.1783006401491653e-05,
"loss": 3.8981,
"step": 1723392
},
{
"epoch": 1.01,
"learning_rate": 2.1774620453981133e-05,
"loss": 3.8991,
"step": 1723904
},
{
"epoch": 1.01,
"learning_rate": 2.1766234506470613e-05,
"loss": 3.8949,
"step": 1724416
},
{
"epoch": 1.02,
"learning_rate": 2.1757848558960093e-05,
"loss": 3.8844,
"step": 1724928
},
{
"epoch": 1.02,
"learning_rate": 2.1749478990253302e-05,
"loss": 3.8893,
"step": 1725440
},
{
"epoch": 1.02,
"learning_rate": 2.1741093042742782e-05,
"loss": 3.8848,
"step": 1725952
},
{
"epoch": 1.02,
"learning_rate": 2.1732707095232262e-05,
"loss": 3.8889,
"step": 1726464
},
{
"epoch": 1.02,
"learning_rate": 2.1724321147721742e-05,
"loss": 3.9047,
"step": 1726976
},
{
"epoch": 1.02,
"learning_rate": 2.1715935200211222e-05,
"loss": 3.9068,
"step": 1727488
},
{
"epoch": 1.02,
"learning_rate": 2.1707549252700702e-05,
"loss": 3.9023,
"step": 1728000
},
{
"epoch": 1.02,
"learning_rate": 2.1699179683993914e-05,
"loss": 3.8818,
"step": 1728512
},
{
"epoch": 1.02,
"learning_rate": 2.1690793736483394e-05,
"loss": 3.8911,
"step": 1729024
},
{
"epoch": 1.02,
"learning_rate": 2.168240778897287e-05,
"loss": 3.8895,
"step": 1729536
},
{
"epoch": 1.02,
"learning_rate": 2.1674021841462354e-05,
"loss": 3.8995,
"step": 1730048
},
{
"epoch": 1.02,
"learning_rate": 2.1665635893951834e-05,
"loss": 3.8944,
"step": 1730560
},
{
"epoch": 1.02,
"learning_rate": 2.1657249946441314e-05,
"loss": 3.8994,
"step": 1731072
},
{
"epoch": 1.02,
"learning_rate": 2.1648880377734523e-05,
"loss": 3.8928,
"step": 1731584
},
{
"epoch": 1.02,
"learning_rate": 2.1640494430224003e-05,
"loss": 3.8874,
"step": 1732096
},
{
"epoch": 1.02,
"learning_rate": 2.1632108482713483e-05,
"loss": 3.8882,
"step": 1732608
},
{
"epoch": 1.02,
"learning_rate": 2.1623722535202963e-05,
"loss": 3.8901,
"step": 1733120
},
{
"epoch": 1.02,
"learning_rate": 2.1615336587692446e-05,
"loss": 3.8826,
"step": 1733632
},
{
"epoch": 1.02,
"learning_rate": 2.1606967018985655e-05,
"loss": 3.9017,
"step": 1734144
},
{
"epoch": 1.02,
"learning_rate": 2.1598581071475135e-05,
"loss": 3.8889,
"step": 1734656
},
{
"epoch": 1.02,
"learning_rate": 2.1590195123964615e-05,
"loss": 3.8876,
"step": 1735168
},
{
"epoch": 1.02,
"learning_rate": 2.1581809176454095e-05,
"loss": 3.8836,
"step": 1735680
},
{
"epoch": 1.02,
"learning_rate": 2.1573423228943572e-05,
"loss": 3.891,
"step": 1736192
},
{
"epoch": 1.02,
"learning_rate": 2.1565053660236788e-05,
"loss": 3.894,
"step": 1736704
},
{
"epoch": 1.02,
"learning_rate": 2.1556667712726268e-05,
"loss": 3.889,
"step": 1737216
},
{
"epoch": 1.02,
"learning_rate": 2.1548281765215748e-05,
"loss": 3.9045,
"step": 1737728
},
{
"epoch": 1.02,
"learning_rate": 2.1539895817705224e-05,
"loss": 3.9006,
"step": 1738240
},
{
"epoch": 1.02,
"learning_rate": 2.1531526248998437e-05,
"loss": 3.897,
"step": 1738752
},
{
"epoch": 1.02,
"learning_rate": 2.1523140301487917e-05,
"loss": 3.8968,
"step": 1739264
},
{
"epoch": 1.02,
"learning_rate": 2.15147543539774e-05,
"loss": 3.8821,
"step": 1739776
},
{
"epoch": 1.02,
"learning_rate": 2.1506368406466877e-05,
"loss": 3.9039,
"step": 1740288
},
{
"epoch": 1.02,
"learning_rate": 2.1497982458956356e-05,
"loss": 3.8888,
"step": 1740800
},
{
"epoch": 1.02,
"learning_rate": 2.1489596511445836e-05,
"loss": 3.8951,
"step": 1741312
},
{
"epoch": 1.02,
"learning_rate": 2.1481210563935316e-05,
"loss": 3.8816,
"step": 1741824
},
{
"epoch": 1.02,
"learning_rate": 2.1472840995228525e-05,
"loss": 3.8936,
"step": 1742336
},
{
"epoch": 1.02,
"learning_rate": 2.146445504771801e-05,
"loss": 3.8828,
"step": 1742848
},
{
"epoch": 1.02,
"learning_rate": 2.145606910020749e-05,
"loss": 3.8903,
"step": 1743360
},
{
"epoch": 1.02,
"learning_rate": 2.144768315269697e-05,
"loss": 3.885,
"step": 1743872
},
{
"epoch": 1.02,
"learning_rate": 2.143929720518645e-05,
"loss": 3.895,
"step": 1744384
},
{
"epoch": 1.02,
"learning_rate": 2.1430927636479658e-05,
"loss": 3.8826,
"step": 1744896
},
{
"epoch": 1.02,
"learning_rate": 2.1422541688969138e-05,
"loss": 3.9026,
"step": 1745408
},
{
"epoch": 1.02,
"learning_rate": 2.1414155741458618e-05,
"loss": 3.8961,
"step": 1745920
},
{
"epoch": 1.02,
"learning_rate": 2.14057697939481e-05,
"loss": 3.9032,
"step": 1746432
},
{
"epoch": 1.02,
"learning_rate": 2.139738384643758e-05,
"loss": 3.8814,
"step": 1746944
},
{
"epoch": 1.02,
"learning_rate": 2.1388997898927058e-05,
"loss": 3.9004,
"step": 1747456
},
{
"epoch": 1.02,
"learning_rate": 2.1380611951416538e-05,
"loss": 3.8983,
"step": 1747968
},
{
"epoch": 1.02,
"learning_rate": 2.1372226003906017e-05,
"loss": 3.8968,
"step": 1748480
},
{
"epoch": 1.02,
"learning_rate": 2.1363872814002962e-05,
"loss": 3.8965,
"step": 1748992
},
{
"epoch": 1.02,
"learning_rate": 2.1355486866492442e-05,
"loss": 3.8966,
"step": 1749504
},
{
"epoch": 1.02,
"learning_rate": 2.1347100918981922e-05,
"loss": 3.8903,
"step": 1750016
},
{
"epoch": 1.02,
"learning_rate": 2.1338714971471402e-05,
"loss": 3.9083,
"step": 1750528
},
{
"epoch": 1.02,
"learning_rate": 2.133032902396088e-05,
"loss": 3.8818,
"step": 1751040
},
{
"epoch": 1.02,
"learning_rate": 2.132194307645036e-05,
"loss": 3.9013,
"step": 1751552
},
{
"epoch": 1.02,
"learning_rate": 2.131355712893984e-05,
"loss": 3.8911,
"step": 1752064
},
{
"epoch": 1.02,
"learning_rate": 2.130517118142932e-05,
"loss": 3.8941,
"step": 1752576
},
{
"epoch": 1.02,
"learning_rate": 2.129680161272253e-05,
"loss": 3.894,
"step": 1753088
},
{
"epoch": 1.02,
"learning_rate": 2.128841566521201e-05,
"loss": 3.8931,
"step": 1753600
},
{
"epoch": 1.02,
"learning_rate": 2.128002971770149e-05,
"loss": 3.8993,
"step": 1754112
},
{
"epoch": 1.02,
"learning_rate": 2.127164377019097e-05,
"loss": 3.8775,
"step": 1754624
},
{
"epoch": 1.02,
"learning_rate": 2.126325782268045e-05,
"loss": 3.8925,
"step": 1755136
},
{
"epoch": 1.03,
"eval_loss": 3.988659620285034,
"eval_runtime": 292.259,
"eval_samples_per_second": 1305.66,
"eval_steps_per_second": 40.803,
"step": 1755360
},
{
"epoch": 0.0,
"learning_rate": 2.125487187516993e-05,
"loss": 3.8949,
"step": 1755648
},
{
"epoch": 0.0,
"learning_rate": 2.124648592765941e-05,
"loss": 3.884,
"step": 1756160
},
{
"epoch": 0.0,
"learning_rate": 2.123809998014889e-05,
"loss": 3.8943,
"step": 1756672
},
{
"epoch": 0.0,
"learning_rate": 2.122971403263837e-05,
"loss": 3.8924,
"step": 1757184
},
{
"epoch": 0.0,
"learning_rate": 2.122132808512785e-05,
"loss": 3.9009,
"step": 1757696
},
{
"epoch": 0.0,
"learning_rate": 2.121294213761733e-05,
"loss": 3.8913,
"step": 1758208
},
{
"epoch": 0.0,
"learning_rate": 2.120455619010681e-05,
"loss": 3.8852,
"step": 1758720
},
{
"epoch": 0.0,
"learning_rate": 2.119617024259629e-05,
"loss": 3.8837,
"step": 1759232
},
{
"epoch": 0.0,
"learning_rate": 2.118778429508577e-05,
"loss": 3.8924,
"step": 1759744
},
{
"epoch": 0.0,
"learning_rate": 2.117939834757525e-05,
"loss": 3.8985,
"step": 1760256
},
{
"epoch": 0.0,
"learning_rate": 2.117101240006473e-05,
"loss": 3.8948,
"step": 1760768
},
{
"epoch": 0.0,
"learning_rate": 2.116262645255421e-05,
"loss": 3.8966,
"step": 1761280
},
{
"epoch": 0.0,
"learning_rate": 2.115424050504369e-05,
"loss": 3.8893,
"step": 1761792
},
{
"epoch": 0.0,
"learning_rate": 2.114585455753317e-05,
"loss": 3.8891,
"step": 1762304
},
{
"epoch": 0.0,
"learning_rate": 2.113746861002265e-05,
"loss": 3.8852,
"step": 1762816
},
{
"epoch": 0.0,
"learning_rate": 2.1129082662512127e-05,
"loss": 3.8846,
"step": 1763328
},
{
"epoch": 0.0,
"learning_rate": 2.112069671500161e-05,
"loss": 3.8869,
"step": 1763840
},
{
"epoch": 0.0,
"learning_rate": 2.111231076749109e-05,
"loss": 3.8845,
"step": 1764352
},
{
"epoch": 0.0,
"learning_rate": 2.11039411987843e-05,
"loss": 3.8903,
"step": 1764864
},
{
"epoch": 0.0,
"learning_rate": 2.109555525127378e-05,
"loss": 3.8988,
"step": 1765376
},
{
"epoch": 0.0,
"learning_rate": 2.108716930376326e-05,
"loss": 3.8983,
"step": 1765888
},
{
"epoch": 0.0,
"learning_rate": 2.107878335625274e-05,
"loss": 3.9001,
"step": 1766400
},
{
"epoch": 0.0,
"learning_rate": 2.107039740874222e-05,
"loss": 3.8875,
"step": 1766912
},
{
"epoch": 0.0,
"learning_rate": 2.106202784003543e-05,
"loss": 3.8966,
"step": 1767424
},
{
"epoch": 0.0,
"learning_rate": 2.105364189252491e-05,
"loss": 3.8829,
"step": 1767936
},
{
"epoch": 0.0,
"learning_rate": 2.104525594501439e-05,
"loss": 3.9026,
"step": 1768448
},
{
"epoch": 0.0,
"learning_rate": 2.103686999750387e-05,
"loss": 3.8849,
"step": 1768960
},
{
"epoch": 0.0,
"learning_rate": 2.102848404999335e-05,
"loss": 3.8823,
"step": 1769472
},
{
"epoch": 0.0,
"learning_rate": 2.1020098102482828e-05,
"loss": 3.8844,
"step": 1769984
},
{
"epoch": 0.0,
"learning_rate": 2.101171215497231e-05,
"loss": 3.8878,
"step": 1770496
},
{
"epoch": 0.01,
"learning_rate": 2.1003342586265524e-05,
"loss": 3.8881,
"step": 1771008
},
{
"epoch": 0.01,
"learning_rate": 2.0994956638755004e-05,
"loss": 3.8942,
"step": 1771520
},
{
"epoch": 0.01,
"learning_rate": 2.098657069124448e-05,
"loss": 3.8977,
"step": 1772032
},
{
"epoch": 0.01,
"learning_rate": 2.097818474373396e-05,
"loss": 3.8968,
"step": 1772544
},
{
"epoch": 0.01,
"learning_rate": 2.096979879622344e-05,
"loss": 3.8889,
"step": 1773056
},
{
"epoch": 0.01,
"learning_rate": 2.096141284871292e-05,
"loss": 3.8974,
"step": 1773568
},
{
"epoch": 0.01,
"learning_rate": 2.0953026901202404e-05,
"loss": 3.8935,
"step": 1774080
},
{
"epoch": 0.01,
"learning_rate": 2.0944657332495613e-05,
"loss": 3.879,
"step": 1774592
},
{
"epoch": 0.01,
"learning_rate": 2.0936271384985093e-05,
"loss": 3.8807,
"step": 1775104
},
{
"epoch": 0.01,
"learning_rate": 2.0927885437474573e-05,
"loss": 3.8838,
"step": 1775616
},
{
"epoch": 0.01,
"learning_rate": 2.0919515868767782e-05,
"loss": 3.8874,
"step": 1776128
},
{
"epoch": 0.01,
"learning_rate": 2.0911129921257265e-05,
"loss": 3.8933,
"step": 1776640
},
{
"epoch": 0.01,
"learning_rate": 2.0902743973746745e-05,
"loss": 3.887,
"step": 1777152
},
{
"epoch": 0.01,
"learning_rate": 2.0894358026236225e-05,
"loss": 3.8813,
"step": 1777664
},
{
"epoch": 0.01,
"learning_rate": 2.0885988457529434e-05,
"loss": 3.8981,
"step": 1778176
},
{
"epoch": 0.01,
"learning_rate": 2.0877602510018914e-05,
"loss": 3.8882,
"step": 1778688
},
{
"epoch": 0.01,
"learning_rate": 2.0869216562508394e-05,
"loss": 3.8908,
"step": 1779200
},
{
"epoch": 0.01,
"learning_rate": 2.0860830614997874e-05,
"loss": 3.8733,
"step": 1779712
},
{
"epoch": 0.01,
"learning_rate": 2.0852461046291086e-05,
"loss": 3.8688,
"step": 1780224
},
{
"epoch": 0.01,
"learning_rate": 2.0844075098780566e-05,
"loss": 3.8976,
"step": 1780736
},
{
"epoch": 0.01,
"learning_rate": 2.0835689151270046e-05,
"loss": 3.8843,
"step": 1781248
},
{
"epoch": 0.01,
"learning_rate": 2.0827303203759526e-05,
"loss": 3.8875,
"step": 1781760
},
{
"epoch": 0.01,
"learning_rate": 2.0818917256249006e-05,
"loss": 3.8797,
"step": 1782272
},
{
"epoch": 0.01,
"learning_rate": 2.0810531308738486e-05,
"loss": 3.8854,
"step": 1782784
},
{
"epoch": 0.01,
"learning_rate": 2.0802145361227966e-05,
"loss": 3.8711,
"step": 1783296
},
{
"epoch": 0.01,
"learning_rate": 2.079377579252118e-05,
"loss": 3.8881,
"step": 1783808
},
{
"epoch": 0.01,
"learning_rate": 2.078538984501066e-05,
"loss": 3.8813,
"step": 1784320
},
{
"epoch": 0.01,
"learning_rate": 2.0777003897500135e-05,
"loss": 3.8833,
"step": 1784832
},
{
"epoch": 0.01,
"learning_rate": 2.0768617949989615e-05,
"loss": 3.8918,
"step": 1785344
},
{
"epoch": 0.01,
"learning_rate": 2.0760232002479095e-05,
"loss": 3.8829,
"step": 1785856
},
{
"epoch": 0.01,
"learning_rate": 2.0751846054968575e-05,
"loss": 3.8775,
"step": 1786368
},
{
"epoch": 0.01,
"learning_rate": 2.074346010745806e-05,
"loss": 3.892,
"step": 1786880
},
{
"epoch": 0.01,
"learning_rate": 2.073507415994754e-05,
"loss": 3.8784,
"step": 1787392
},
{
"epoch": 0.01,
"learning_rate": 2.0726704591240747e-05,
"loss": 3.8786,
"step": 1787904
},
{
"epoch": 0.01,
"learning_rate": 2.0718318643730227e-05,
"loss": 3.8923,
"step": 1788416
},
{
"epoch": 0.01,
"learning_rate": 2.0709932696219707e-05,
"loss": 3.8882,
"step": 1788928
},
{
"epoch": 0.01,
"learning_rate": 2.0701546748709187e-05,
"loss": 3.8762,
"step": 1789440
},
{
"epoch": 0.01,
"learning_rate": 2.06931771800024e-05,
"loss": 3.8903,
"step": 1789952
},
{
"epoch": 0.01,
"learning_rate": 2.068479123249188e-05,
"loss": 3.8731,
"step": 1790464
},
{
"epoch": 0.01,
"learning_rate": 2.067642166378509e-05,
"loss": 3.8808,
"step": 1790976
},
{
"epoch": 0.01,
"learning_rate": 2.066803571627457e-05,
"loss": 3.8932,
"step": 1791488
},
{
"epoch": 0.01,
"learning_rate": 2.065964976876405e-05,
"loss": 3.8912,
"step": 1792000
},
{
"epoch": 0.01,
"learning_rate": 2.065126382125353e-05,
"loss": 3.891,
"step": 1792512
},
{
"epoch": 0.01,
"learning_rate": 2.0642877873743012e-05,
"loss": 3.8899,
"step": 1793024
},
{
"epoch": 0.01,
"learning_rate": 2.063450830503622e-05,
"loss": 3.908,
"step": 1793536
},
{
"epoch": 0.01,
"learning_rate": 2.06261223575257e-05,
"loss": 3.8807,
"step": 1794048
},
{
"epoch": 0.01,
"learning_rate": 2.061773641001518e-05,
"loss": 3.8902,
"step": 1794560
},
{
"epoch": 0.01,
"learning_rate": 2.060935046250466e-05,
"loss": 3.8989,
"step": 1795072
},
{
"epoch": 0.01,
"learning_rate": 2.060096451499414e-05,
"loss": 3.8788,
"step": 1795584
},
{
"epoch": 0.01,
"learning_rate": 2.0592594946287353e-05,
"loss": 3.888,
"step": 1796096
},
{
"epoch": 0.01,
"learning_rate": 2.0584225377580563e-05,
"loss": 3.8948,
"step": 1796608
},
{
"epoch": 0.01,
"learning_rate": 2.0575839430070043e-05,
"loss": 3.8971,
"step": 1797120
},
{
"epoch": 0.01,
"learning_rate": 2.0567453482559522e-05,
"loss": 3.8918,
"step": 1797632
},
{
"epoch": 0.01,
"learning_rate": 2.0559067535049002e-05,
"loss": 3.8798,
"step": 1798144
},
{
"epoch": 0.01,
"learning_rate": 2.0550681587538482e-05,
"loss": 3.8759,
"step": 1798656
},
{
"epoch": 0.01,
"learning_rate": 2.0542312018831695e-05,
"loss": 3.8885,
"step": 1799168
},
{
"epoch": 0.01,
"learning_rate": 2.0533926071321175e-05,
"loss": 3.8946,
"step": 1799680
},
{
"epoch": 0.01,
"learning_rate": 2.0525540123810655e-05,
"loss": 3.8935,
"step": 1800192
},
{
"epoch": 0.01,
"learning_rate": 2.0517154176300135e-05,
"loss": 3.8903,
"step": 1800704
},
{
"epoch": 0.02,
"learning_rate": 2.050876822878961e-05,
"loss": 3.8738,
"step": 1801216
},
{
"epoch": 0.02,
"learning_rate": 2.0500398660082827e-05,
"loss": 3.8849,
"step": 1801728
},
{
"epoch": 0.02,
"learning_rate": 2.0492012712572307e-05,
"loss": 3.881,
"step": 1802240
},
{
"epoch": 0.02,
"learning_rate": 2.0483626765061787e-05,
"loss": 3.8856,
"step": 1802752
},
{
"epoch": 0.02,
"learning_rate": 2.0475240817551264e-05,
"loss": 3.8944,
"step": 1803264
},
{
"epoch": 0.02,
"learning_rate": 2.0466854870040744e-05,
"loss": 3.9048,
"step": 1803776
},
{
"epoch": 0.02,
"learning_rate": 2.0458468922530224e-05,
"loss": 3.8942,
"step": 1804288
},
{
"epoch": 0.02,
"learning_rate": 2.0450082975019704e-05,
"loss": 3.8801,
"step": 1804800
},
{
"epoch": 0.02,
"learning_rate": 2.0441697027509183e-05,
"loss": 3.8835,
"step": 1805312
},
{
"epoch": 0.02,
"learning_rate": 2.0433311079998667e-05,
"loss": 3.8842,
"step": 1805824
},
{
"epoch": 0.02,
"learning_rate": 2.0424925132488143e-05,
"loss": 3.8933,
"step": 1806336
},
{
"epoch": 0.02,
"learning_rate": 2.0416539184977623e-05,
"loss": 3.8885,
"step": 1806848
},
{
"epoch": 0.02,
"learning_rate": 2.0408169616270836e-05,
"loss": 3.8968,
"step": 1807360
},
{
"epoch": 0.02,
"learning_rate": 2.0399783668760316e-05,
"loss": 3.8897,
"step": 1807872
},
{
"epoch": 0.02,
"learning_rate": 2.0391397721249796e-05,
"loss": 3.8737,
"step": 1808384
},
{
"epoch": 0.02,
"learning_rate": 2.0383011773739276e-05,
"loss": 3.8866,
"step": 1808896
},
{
"epoch": 0.02,
"learning_rate": 2.0374658583836217e-05,
"loss": 3.8787,
"step": 1809408
},
{
"epoch": 0.02,
"learning_rate": 2.0366272636325697e-05,
"loss": 3.8805,
"step": 1809920
},
{
"epoch": 0.02,
"learning_rate": 2.0357886688815177e-05,
"loss": 3.8899,
"step": 1810432
},
{
"epoch": 0.02,
"learning_rate": 2.0349500741304657e-05,
"loss": 3.8854,
"step": 1810944
},
{
"epoch": 0.02,
"learning_rate": 2.0341114793794137e-05,
"loss": 3.8794,
"step": 1811456
},
{
"epoch": 0.02,
"learning_rate": 2.0332728846283617e-05,
"loss": 3.8814,
"step": 1811968
},
{
"epoch": 0.02,
"learning_rate": 2.0324342898773097e-05,
"loss": 3.8806,
"step": 1812480
},
{
"epoch": 0.02,
"learning_rate": 2.0315956951262577e-05,
"loss": 3.8878,
"step": 1812992
},
{
"epoch": 0.02,
"learning_rate": 2.0307571003752057e-05,
"loss": 3.8812,
"step": 1813504
},
{
"epoch": 0.02,
"learning_rate": 2.0299185056241537e-05,
"loss": 3.9012,
"step": 1814016
},
{
"epoch": 0.02,
"learning_rate": 2.029081548753475e-05,
"loss": 3.8954,
"step": 1814528
},
{
"epoch": 0.02,
"learning_rate": 2.028242954002423e-05,
"loss": 3.8919,
"step": 1815040
},
{
"epoch": 0.02,
"learning_rate": 2.027404359251371e-05,
"loss": 3.8902,
"step": 1815552
},
{
"epoch": 0.02,
"learning_rate": 2.026565764500319e-05,
"loss": 3.8769,
"step": 1816064
},
{
"epoch": 0.02,
"learning_rate": 2.025727169749267e-05,
"loss": 3.8906,
"step": 1816576
},
{
"epoch": 0.02,
"learning_rate": 2.024888574998215e-05,
"loss": 3.8893,
"step": 1817088
},
{
"epoch": 0.02,
"learning_rate": 2.0240499802471626e-05,
"loss": 3.8848,
"step": 1817600
},
{
"epoch": 0.02,
"learning_rate": 2.0232113854961106e-05,
"loss": 3.8774,
"step": 1818112
},
{
"epoch": 0.02,
"learning_rate": 2.022376066505805e-05,
"loss": 3.8895,
"step": 1818624
},
{
"epoch": 0.02,
"learning_rate": 2.021537471754753e-05,
"loss": 3.8768,
"step": 1819136
},
{
"epoch": 0.02,
"learning_rate": 2.020698877003701e-05,
"loss": 3.8845,
"step": 1819648
},
{
"epoch": 0.02,
"learning_rate": 2.019861920133022e-05,
"loss": 3.8763,
"step": 1820160
},
{
"epoch": 0.02,
"learning_rate": 2.0190233253819703e-05,
"loss": 3.8899,
"step": 1820672
},
{
"epoch": 0.02,
"learning_rate": 2.0181847306309183e-05,
"loss": 3.8749,
"step": 1821184
},
{
"epoch": 0.02,
"learning_rate": 2.0173461358798663e-05,
"loss": 3.8989,
"step": 1821696
},
{
"epoch": 0.02,
"learning_rate": 2.0165075411288143e-05,
"loss": 3.8878,
"step": 1822208
},
{
"epoch": 0.02,
"learning_rate": 2.0156689463777623e-05,
"loss": 3.8968,
"step": 1822720
},
{
"epoch": 0.02,
"learning_rate": 2.01483035162671e-05,
"loss": 3.8761,
"step": 1823232
},
{
"epoch": 0.02,
"learning_rate": 2.013991756875658e-05,
"loss": 3.8958,
"step": 1823744
},
{
"epoch": 0.02,
"learning_rate": 2.013153162124606e-05,
"loss": 3.891,
"step": 1824256
},
{
"epoch": 0.02,
"learning_rate": 2.0123162052539272e-05,
"loss": 3.8941,
"step": 1824768
},
{
"epoch": 0.02,
"learning_rate": 2.0114776105028752e-05,
"loss": 3.8894,
"step": 1825280
},
{
"epoch": 0.02,
"learning_rate": 2.0106390157518232e-05,
"loss": 3.8882,
"step": 1825792
},
{
"epoch": 0.02,
"learning_rate": 2.0098004210007712e-05,
"loss": 3.8885,
"step": 1826304
},
{
"epoch": 0.02,
"learning_rate": 2.008961826249719e-05,
"loss": 3.9013,
"step": 1826816
},
{
"epoch": 0.02,
"learning_rate": 2.008123231498667e-05,
"loss": 3.8768,
"step": 1827328
},
{
"epoch": 0.02,
"learning_rate": 2.0072862746279884e-05,
"loss": 3.8942,
"step": 1827840
},
{
"epoch": 0.02,
"learning_rate": 2.0064476798769364e-05,
"loss": 3.888,
"step": 1828352
},
{
"epoch": 0.02,
"learning_rate": 2.0056090851258844e-05,
"loss": 3.8861,
"step": 1828864
},
{
"epoch": 0.02,
"learning_rate": 2.0047704903748324e-05,
"loss": 3.888,
"step": 1829376
},
{
"epoch": 0.02,
"learning_rate": 2.0039351713845266e-05,
"loss": 3.8828,
"step": 1829888
},
{
"epoch": 0.02,
"learning_rate": 2.0030965766334746e-05,
"loss": 3.895,
"step": 1830400
},
{
"epoch": 0.02,
"learning_rate": 2.0022579818824226e-05,
"loss": 3.8702,
"step": 1830912
},
{
"epoch": 0.02,
"learning_rate": 2.0014193871313705e-05,
"loss": 3.8896,
"step": 1831424
},
{
"epoch": 0.03,
"eval_loss": 3.9860286712646484,
"eval_runtime": 295.0616,
"eval_samples_per_second": 1293.259,
"eval_steps_per_second": 40.415,
"step": 1831680
},
{
"epoch": 1.0,
"learning_rate": 2.0005807923803185e-05,
"loss": 3.8857,
"step": 1831936
},
{
"epoch": 1.0,
"learning_rate": 1.9997421976292665e-05,
"loss": 3.8797,
"step": 1832448
},
{
"epoch": 1.0,
"learning_rate": 1.9989036028782145e-05,
"loss": 3.8844,
"step": 1832960
},
{
"epoch": 1.0,
"learning_rate": 1.9980650081271625e-05,
"loss": 3.8867,
"step": 1833472
},
{
"epoch": 1.0,
"learning_rate": 1.9972264133761105e-05,
"loss": 3.8976,
"step": 1833984
},
{
"epoch": 1.0,
"learning_rate": 1.9963878186250585e-05,
"loss": 3.883,
"step": 1834496
},
{
"epoch": 1.0,
"learning_rate": 1.9955508617543798e-05,
"loss": 3.885,
"step": 1835008
},
{
"epoch": 1.0,
"learning_rate": 1.9947122670033278e-05,
"loss": 3.8794,
"step": 1835520
},
{
"epoch": 1.0,
"learning_rate": 1.9938736722522754e-05,
"loss": 3.8807,
"step": 1836032
},
{
"epoch": 1.0,
"learning_rate": 1.9930350775012234e-05,
"loss": 3.8954,
"step": 1836544
},
{
"epoch": 1.0,
"learning_rate": 1.9921964827501714e-05,
"loss": 3.885,
"step": 1837056
},
{
"epoch": 1.0,
"learning_rate": 1.9913595258794927e-05,
"loss": 3.8927,
"step": 1837568
},
{
"epoch": 1.0,
"learning_rate": 1.9905209311284407e-05,
"loss": 3.8812,
"step": 1838080
},
{
"epoch": 1.0,
"learning_rate": 1.9896823363773887e-05,
"loss": 3.8819,
"step": 1838592
},
{
"epoch": 1.0,
"learning_rate": 1.98884537950671e-05,
"loss": 3.8824,
"step": 1839104
},
{
"epoch": 1.0,
"learning_rate": 1.9880067847556576e-05,
"loss": 3.8799,
"step": 1839616
},
{
"epoch": 1.0,
"learning_rate": 1.987168190004606e-05,
"loss": 3.8806,
"step": 1840128
},
{
"epoch": 1.0,
"learning_rate": 1.986329595253554e-05,
"loss": 3.8815,
"step": 1840640
},
{
"epoch": 1.0,
"learning_rate": 1.985491000502502e-05,
"loss": 3.8852,
"step": 1841152
},
{
"epoch": 1.0,
"learning_rate": 1.98465240575145e-05,
"loss": 3.8892,
"step": 1841664
},
{
"epoch": 1.0,
"learning_rate": 1.983813811000398e-05,
"loss": 3.8936,
"step": 1842176
},
{
"epoch": 1.0,
"learning_rate": 1.9829752162493455e-05,
"loss": 3.8955,
"step": 1842688
},
{
"epoch": 1.0,
"learning_rate": 1.9821366214982935e-05,
"loss": 3.8801,
"step": 1843200
},
{
"epoch": 1.0,
"learning_rate": 1.9812980267472415e-05,
"loss": 3.8897,
"step": 1843712
},
{
"epoch": 1.0,
"learning_rate": 1.98045943199619e-05,
"loss": 3.8822,
"step": 1844224
},
{
"epoch": 1.0,
"learning_rate": 1.979620837245138e-05,
"loss": 3.8927,
"step": 1844736
},
{
"epoch": 1.0,
"learning_rate": 1.9787838803744588e-05,
"loss": 3.8814,
"step": 1845248
},
{
"epoch": 1.0,
"learning_rate": 1.9779452856234068e-05,
"loss": 3.8796,
"step": 1845760
},
{
"epoch": 1.0,
"learning_rate": 1.977108328752728e-05,
"loss": 3.881,
"step": 1846272
},
{
"epoch": 1.0,
"learning_rate": 1.976269734001676e-05,
"loss": 3.8791,
"step": 1846784
},
{
"epoch": 1.01,
"learning_rate": 1.9754327771309973e-05,
"loss": 3.8799,
"step": 1847296
},
{
"epoch": 1.01,
"learning_rate": 1.9745941823799452e-05,
"loss": 3.8918,
"step": 1847808
},
{
"epoch": 1.01,
"learning_rate": 1.973755587628893e-05,
"loss": 3.8852,
"step": 1848320
},
{
"epoch": 1.01,
"learning_rate": 1.972916992877841e-05,
"loss": 3.8932,
"step": 1848832
},
{
"epoch": 1.01,
"learning_rate": 1.972078398126789e-05,
"loss": 3.8852,
"step": 1849344
},
{
"epoch": 1.01,
"learning_rate": 1.971239803375737e-05,
"loss": 3.8926,
"step": 1849856
},
{
"epoch": 1.01,
"learning_rate": 1.9704012086246852e-05,
"loss": 3.8871,
"step": 1850368
},
{
"epoch": 1.01,
"learning_rate": 1.9695626138736332e-05,
"loss": 3.8724,
"step": 1850880
},
{
"epoch": 1.01,
"learning_rate": 1.9687240191225812e-05,
"loss": 3.8772,
"step": 1851392
},
{
"epoch": 1.01,
"learning_rate": 1.967885424371529e-05,
"loss": 3.8774,
"step": 1851904
},
{
"epoch": 1.01,
"learning_rate": 1.967046829620477e-05,
"loss": 3.8802,
"step": 1852416
},
{
"epoch": 1.01,
"learning_rate": 1.966208234869425e-05,
"loss": 3.8874,
"step": 1852928
},
{
"epoch": 1.01,
"learning_rate": 1.965371277998746e-05,
"loss": 3.8819,
"step": 1853440
},
{
"epoch": 1.01,
"learning_rate": 1.9645343211280674e-05,
"loss": 3.8771,
"step": 1853952
},
{
"epoch": 1.01,
"learning_rate": 1.9636973642573883e-05,
"loss": 3.8913,
"step": 1854464
},
{
"epoch": 1.01,
"learning_rate": 1.9628587695063363e-05,
"loss": 3.8798,
"step": 1854976
},
{
"epoch": 1.01,
"learning_rate": 1.9620201747552843e-05,
"loss": 3.8856,
"step": 1855488
},
{
"epoch": 1.01,
"learning_rate": 1.9611815800042323e-05,
"loss": 3.8694,
"step": 1856000
},
{
"epoch": 1.01,
"learning_rate": 1.9603429852531806e-05,
"loss": 3.858,
"step": 1856512
},
{
"epoch": 1.01,
"learning_rate": 1.9595043905021286e-05,
"loss": 3.895,
"step": 1857024
},
{
"epoch": 1.01,
"learning_rate": 1.9586657957510762e-05,
"loss": 3.8796,
"step": 1857536
},
{
"epoch": 1.01,
"learning_rate": 1.9578272010000242e-05,
"loss": 3.886,
"step": 1858048
},
{
"epoch": 1.01,
"learning_rate": 1.9569886062489722e-05,
"loss": 3.8761,
"step": 1858560
},
{
"epoch": 1.01,
"learning_rate": 1.9561500114979202e-05,
"loss": 3.8749,
"step": 1859072
},
{
"epoch": 1.01,
"learning_rate": 1.9553114167468682e-05,
"loss": 3.8728,
"step": 1859584
},
{
"epoch": 1.01,
"learning_rate": 1.9544744598761895e-05,
"loss": 3.8833,
"step": 1860096
},
{
"epoch": 1.01,
"learning_rate": 1.9536358651251375e-05,
"loss": 3.8734,
"step": 1860608
},
{
"epoch": 1.01,
"learning_rate": 1.9527972703740855e-05,
"loss": 3.8797,
"step": 1861120
},
{
"epoch": 1.01,
"learning_rate": 1.9519586756230335e-05,
"loss": 3.8901,
"step": 1861632
},
{
"epoch": 1.01,
"learning_rate": 1.9511217187523544e-05,
"loss": 3.8742,
"step": 1862144
},
{
"epoch": 1.01,
"learning_rate": 1.9502831240013024e-05,
"loss": 3.8712,
"step": 1862656
},
{
"epoch": 1.01,
"learning_rate": 1.9494445292502507e-05,
"loss": 3.8895,
"step": 1863168
},
{
"epoch": 1.01,
"learning_rate": 1.9486059344991987e-05,
"loss": 3.8713,
"step": 1863680
},
{
"epoch": 1.01,
"learning_rate": 1.9477673397481467e-05,
"loss": 3.8709,
"step": 1864192
},
{
"epoch": 1.01,
"learning_rate": 1.9469287449970943e-05,
"loss": 3.8888,
"step": 1864704
},
{
"epoch": 1.01,
"learning_rate": 1.9460917881264156e-05,
"loss": 3.8785,
"step": 1865216
},
{
"epoch": 1.01,
"learning_rate": 1.9452531933753636e-05,
"loss": 3.872,
"step": 1865728
},
{
"epoch": 1.01,
"learning_rate": 1.9444145986243116e-05,
"loss": 3.8852,
"step": 1866240
},
{
"epoch": 1.01,
"learning_rate": 1.9435760038732596e-05,
"loss": 3.87,
"step": 1866752
},
{
"epoch": 1.01,
"learning_rate": 1.9427374091222076e-05,
"loss": 3.8725,
"step": 1867264
},
{
"epoch": 1.01,
"learning_rate": 1.9418988143711556e-05,
"loss": 3.8897,
"step": 1867776
},
{
"epoch": 1.01,
"learning_rate": 1.9410602196201036e-05,
"loss": 3.8848,
"step": 1868288
},
{
"epoch": 1.01,
"learning_rate": 1.9402216248690516e-05,
"loss": 3.883,
"step": 1868800
},
{
"epoch": 1.01,
"learning_rate": 1.9393830301179996e-05,
"loss": 3.8849,
"step": 1869312
},
{
"epoch": 1.01,
"learning_rate": 1.9385460732473208e-05,
"loss": 3.9019,
"step": 1869824
},
{
"epoch": 1.01,
"learning_rate": 1.9377074784962688e-05,
"loss": 3.8755,
"step": 1870336
},
{
"epoch": 1.01,
"learning_rate": 1.9368688837452168e-05,
"loss": 3.8867,
"step": 1870848
},
{
"epoch": 1.01,
"learning_rate": 1.9360302889941648e-05,
"loss": 3.8888,
"step": 1871360
},
{
"epoch": 1.01,
"learning_rate": 1.9351916942431125e-05,
"loss": 3.8769,
"step": 1871872
},
{
"epoch": 1.01,
"learning_rate": 1.9343530994920604e-05,
"loss": 3.8779,
"step": 1872384
},
{
"epoch": 1.01,
"learning_rate": 1.9335145047410084e-05,
"loss": 3.8922,
"step": 1872896
},
{
"epoch": 1.01,
"learning_rate": 1.93267754787033e-05,
"loss": 3.8901,
"step": 1873408
},
{
"epoch": 1.01,
"learning_rate": 1.931840590999651e-05,
"loss": 3.8911,
"step": 1873920
},
{
"epoch": 1.01,
"learning_rate": 1.931001996248599e-05,
"loss": 3.8711,
"step": 1874432
},
{
"epoch": 1.01,
"learning_rate": 1.930163401497547e-05,
"loss": 3.8695,
"step": 1874944
},
{
"epoch": 1.01,
"learning_rate": 1.9293248067464946e-05,
"loss": 3.8839,
"step": 1875456
},
{
"epoch": 1.01,
"learning_rate": 1.928486211995443e-05,
"loss": 3.889,
"step": 1875968
},
{
"epoch": 1.01,
"learning_rate": 1.927647617244391e-05,
"loss": 3.8863,
"step": 1876480
},
{
"epoch": 1.01,
"learning_rate": 1.926810660373712e-05,
"loss": 3.884,
"step": 1876992
},
{
"epoch": 1.02,
"learning_rate": 1.9259720656226598e-05,
"loss": 3.8698,
"step": 1877504
},
{
"epoch": 1.02,
"learning_rate": 1.9251334708716078e-05,
"loss": 3.8813,
"step": 1878016
},
{
"epoch": 1.02,
"learning_rate": 1.9242948761205558e-05,
"loss": 3.876,
"step": 1878528
},
{
"epoch": 1.02,
"learning_rate": 1.9234562813695038e-05,
"loss": 3.8773,
"step": 1879040
},
{
"epoch": 1.02,
"learning_rate": 1.922617686618452e-05,
"loss": 3.8912,
"step": 1879552
},
{
"epoch": 1.02,
"learning_rate": 1.9217790918674e-05,
"loss": 3.8939,
"step": 1880064
},
{
"epoch": 1.02,
"learning_rate": 1.9209404971163478e-05,
"loss": 3.8893,
"step": 1880576
},
{
"epoch": 1.02,
"learning_rate": 1.9201019023652958e-05,
"loss": 3.8785,
"step": 1881088
},
{
"epoch": 1.02,
"learning_rate": 1.9192633076142438e-05,
"loss": 3.8742,
"step": 1881600
},
{
"epoch": 1.02,
"learning_rate": 1.9184247128631918e-05,
"loss": 3.8799,
"step": 1882112
},
{
"epoch": 1.02,
"learning_rate": 1.9175861181121398e-05,
"loss": 3.8885,
"step": 1882624
},
{
"epoch": 1.02,
"learning_rate": 1.916749161241461e-05,
"loss": 3.8828,
"step": 1883136
},
{
"epoch": 1.02,
"learning_rate": 1.9159122043707823e-05,
"loss": 3.8903,
"step": 1883648
},
{
"epoch": 1.02,
"learning_rate": 1.9150736096197303e-05,
"loss": 3.8836,
"step": 1884160
},
{
"epoch": 1.02,
"learning_rate": 1.914235014868678e-05,
"loss": 3.8729,
"step": 1884672
},
{
"epoch": 1.02,
"learning_rate": 1.913396420117626e-05,
"loss": 3.8815,
"step": 1885184
},
{
"epoch": 1.02,
"learning_rate": 1.9125594632469475e-05,
"loss": 3.8728,
"step": 1885696
},
{
"epoch": 1.02,
"learning_rate": 1.911720868495895e-05,
"loss": 3.8752,
"step": 1886208
},
{
"epoch": 1.02,
"learning_rate": 1.910882273744843e-05,
"loss": 3.8842,
"step": 1886720
},
{
"epoch": 1.02,
"learning_rate": 1.910043678993791e-05,
"loss": 3.8831,
"step": 1887232
},
{
"epoch": 1.02,
"learning_rate": 1.9092067221231124e-05,
"loss": 3.8766,
"step": 1887744
},
{
"epoch": 1.02,
"learning_rate": 1.90836812737206e-05,
"loss": 3.8721,
"step": 1888256
},
{
"epoch": 1.02,
"learning_rate": 1.9075295326210084e-05,
"loss": 3.8733,
"step": 1888768
},
{
"epoch": 1.02,
"learning_rate": 1.9066909378699564e-05,
"loss": 3.8843,
"step": 1889280
},
{
"epoch": 1.02,
"learning_rate": 1.9058523431189044e-05,
"loss": 3.875,
"step": 1889792
},
{
"epoch": 1.02,
"learning_rate": 1.9050137483678524e-05,
"loss": 3.8959,
"step": 1890304
},
{
"epoch": 1.02,
"learning_rate": 1.9041751536168004e-05,
"loss": 3.8931,
"step": 1890816
},
{
"epoch": 1.02,
"learning_rate": 1.9033365588657484e-05,
"loss": 3.888,
"step": 1891328
},
{
"epoch": 1.02,
"learning_rate": 1.9024996019950693e-05,
"loss": 3.8825,
"step": 1891840
},
{
"epoch": 1.02,
"learning_rate": 1.9016610072440176e-05,
"loss": 3.8741,
"step": 1892352
},
{
"epoch": 1.02,
"learning_rate": 1.9008224124929656e-05,
"loss": 3.8837,
"step": 1892864
},
{
"epoch": 1.02,
"learning_rate": 1.8999838177419133e-05,
"loss": 3.8825,
"step": 1893376
},
{
"epoch": 1.02,
"learning_rate": 1.8991452229908613e-05,
"loss": 3.878,
"step": 1893888
},
{
"epoch": 1.02,
"learning_rate": 1.8983066282398093e-05,
"loss": 3.8744,
"step": 1894400
},
{
"epoch": 1.02,
"learning_rate": 1.8974680334887573e-05,
"loss": 3.8855,
"step": 1894912
},
{
"epoch": 1.02,
"learning_rate": 1.8966310766180785e-05,
"loss": 3.8726,
"step": 1895424
},
{
"epoch": 1.02,
"learning_rate": 1.8957941197473998e-05,
"loss": 3.8778,
"step": 1895936
},
{
"epoch": 1.02,
"learning_rate": 1.8949555249963478e-05,
"loss": 3.8682,
"step": 1896448
},
{
"epoch": 1.02,
"learning_rate": 1.8941169302452957e-05,
"loss": 3.8873,
"step": 1896960
},
{
"epoch": 1.02,
"learning_rate": 1.8932783354942434e-05,
"loss": 3.8719,
"step": 1897472
},
{
"epoch": 1.02,
"learning_rate": 1.8924397407431914e-05,
"loss": 3.8905,
"step": 1897984
},
{
"epoch": 1.02,
"learning_rate": 1.8916011459921394e-05,
"loss": 3.8855,
"step": 1898496
},
{
"epoch": 1.02,
"learning_rate": 1.8907625512410877e-05,
"loss": 3.8916,
"step": 1899008
},
{
"epoch": 1.02,
"learning_rate": 1.8899239564900357e-05,
"loss": 3.8728,
"step": 1899520
},
{
"epoch": 1.02,
"learning_rate": 1.8890853617389837e-05,
"loss": 3.8923,
"step": 1900032
},
{
"epoch": 1.02,
"learning_rate": 1.8882484048683046e-05,
"loss": 3.882,
"step": 1900544
},
{
"epoch": 1.02,
"learning_rate": 1.8874098101172526e-05,
"loss": 3.8894,
"step": 1901056
},
{
"epoch": 1.02,
"learning_rate": 1.8865712153662006e-05,
"loss": 3.8879,
"step": 1901568
},
{
"epoch": 1.02,
"learning_rate": 1.8857326206151486e-05,
"loss": 3.8786,
"step": 1902080
},
{
"epoch": 1.02,
"learning_rate": 1.8848940258640966e-05,
"loss": 3.8851,
"step": 1902592
},
{
"epoch": 1.02,
"learning_rate": 1.884057068993418e-05,
"loss": 3.8944,
"step": 1903104
},
{
"epoch": 1.02,
"learning_rate": 1.883218474242366e-05,
"loss": 3.87,
"step": 1903616
},
{
"epoch": 1.02,
"learning_rate": 1.882379879491314e-05,
"loss": 3.8865,
"step": 1904128
},
{
"epoch": 1.02,
"learning_rate": 1.8815412847402615e-05,
"loss": 3.8875,
"step": 1904640
},
{
"epoch": 1.02,
"learning_rate": 1.88070268998921e-05,
"loss": 3.8845,
"step": 1905152
},
{
"epoch": 1.02,
"learning_rate": 1.879865733118531e-05,
"loss": 3.8758,
"step": 1905664
},
{
"epoch": 1.02,
"learning_rate": 1.8790271383674787e-05,
"loss": 3.8805,
"step": 1906176
},
{
"epoch": 1.02,
"learning_rate": 1.8781885436164267e-05,
"loss": 3.8894,
"step": 1906688
},
{
"epoch": 1.02,
"learning_rate": 1.8773499488653747e-05,
"loss": 3.8707,
"step": 1907200
},
{
"epoch": 1.02,
"learning_rate": 1.876512991994696e-05,
"loss": 3.8836,
"step": 1907712
},
{
"epoch": 1.03,
"eval_loss": 3.9842660427093506,
"eval_runtime": 294.9931,
"eval_samples_per_second": 1293.559,
"eval_steps_per_second": 40.425,
"step": 1908000
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 7.898115180620832e+17,
"trial_name": null,
"trial_params": null
}