abhinavp's picture
Training in progress, epoch 1, checkpoint
505579e verified
raw
history blame
No virus
112 kB
{
"best_metric": 3.876544713973999,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/transformer/0/checkpoints/checkpoint-457920",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 457920,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.9798,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8315,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.2085,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.0029,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8364,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7323,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6185,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5452,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4657,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4052,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3625,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3164,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2673,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 5.2177,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 5.1919,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 5.1458,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1187,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0946,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.062,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0318,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0174,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 4.9839,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9684,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9416,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9354,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.9031,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8876,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8579,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.851,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8285,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 4.8212,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.811,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7942,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.7832,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 4.7702,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7545,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969820416244367e-05,
"loss": 4.7525,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7217,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7116,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6904,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.693,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6795,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6804,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6593,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6529,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6492,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6431,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6303,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6123,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.604,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.6218,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.6102,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5907,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5766,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5847,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5632,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5721,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5424,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5625,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5485,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5277,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5207,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5342,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4944,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.5079,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5149,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4988,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4924,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4754,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4751,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4699,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4867,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.461,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4739,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4674,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4658,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4485,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4464,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.443,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4395,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4323,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4245,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4269,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.4248,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.405,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.4122,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.4112,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.4133,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 4.3986,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 4.3952,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.92455267849129e-05,
"loss": 4.3888,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 4.3822,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 4.3827,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 4.3874,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921198299487081e-05,
"loss": 4.3792,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920359704736029e-05,
"loss": 4.3861,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 4.3766,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 4.3595,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.3597,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 4.3693,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3653,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3627,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.3532,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.3426,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3571,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3341,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3392,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3341,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.3342,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.324,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.3249,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.3196,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.325,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3209,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3114,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3225,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.328,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.316,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.3028,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.3008,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.2988,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.3051,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.3013,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.289,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.299,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2885,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2886,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.2837,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.2848,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.2769,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.286,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890181758860769e-05,
"loss": 4.2858,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.2845,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.2602,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.2759,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.2696,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2747,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.2633,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884314871364151e-05,
"loss": 4.2722,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883476276613099e-05,
"loss": 4.2612,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2783,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.2473,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.2663,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.2505,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2497,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.2518,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2365,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.2413,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.2486,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2377,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.202905178070068,
"eval_runtime": 309.1099,
"eval_samples_per_second": 1234.483,
"eval_steps_per_second": 38.579,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.2312,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.2274,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.2408,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2327,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2405,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2188,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2217,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.2097,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2204,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.2159,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.2127,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.218,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.198,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.2114,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.1947,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.1952,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.2004,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.1946,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.1972,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.2123,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.1869,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.1916,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.1892,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.1947,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.1891,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.1874,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.1726,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.1793,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.1705,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.1797,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.1734,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.1754,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1806,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.1686,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.1738,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.1721,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.1595,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.1544,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.1453,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.1524,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.1536,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.1615,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.1482,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382134525011416e-05,
"loss": 4.1471,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83737485775009e-05,
"loss": 4.1524,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836536262999038e-05,
"loss": 4.1457,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1489,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834860711377307e-05,
"loss": 4.1337,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834022116626255e-05,
"loss": 4.132,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833183521875203e-05,
"loss": 4.1555,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.1515,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831507970253472e-05,
"loss": 4.1349,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.83066937550242e-05,
"loss": 4.1362,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829832418631741e-05,
"loss": 4.1414,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828993823880689e-05,
"loss": 4.1242,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828155229129637e-05,
"loss": 4.1421,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273166343785856e-05,
"loss": 4.1159,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264780396275336e-05,
"loss": 4.1424,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256394448764816e-05,
"loss": 4.137,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248008501254296e-05,
"loss": 4.1192,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239638932547505e-05,
"loss": 4.1172,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231252985036985e-05,
"loss": 4.1309,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222867037526465e-05,
"loss": 4.0984,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214481090015945e-05,
"loss": 4.1139,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206111521309154e-05,
"loss": 4.1268,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197725573798634e-05,
"loss": 4.1186,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189339626288114e-05,
"loss": 4.112,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180953678777594e-05,
"loss": 4.1011,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817260048887454e-05,
"loss": 4.1062,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816421454136402e-05,
"loss": 4.1071,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.81558285938535e-05,
"loss": 4.115,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814744264634298e-05,
"loss": 4.1046,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813905669883246e-05,
"loss": 4.1143,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813067075132194e-05,
"loss": 4.1168,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812228480381141e-05,
"loss": 4.113,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811389885630089e-05,
"loss": 4.0988,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810552928759411e-05,
"loss": 4.1054,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809714334008359e-05,
"loss": 4.1047,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808875739257306e-05,
"loss": 4.1025,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808037144506255e-05,
"loss": 4.1008,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807200187635576e-05,
"loss": 4.0943,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063615928845243e-05,
"loss": 4.1026,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055229981334717e-05,
"loss": 4.0997,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046844033824197e-05,
"loss": 4.0836,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803847446511741e-05,
"loss": 4.0898,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8030088517606886e-05,
"loss": 4.0925,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.8021702570096366e-05,
"loss": 4.0992,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013316622585846e-05,
"loss": 4.0898,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800494705387906e-05,
"loss": 4.0844,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996561106368535e-05,
"loss": 4.0847,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988175158858015e-05,
"loss": 4.0772,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979789211347494e-05,
"loss": 4.0782,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797140326383698e-05,
"loss": 4.0899,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796301731632646e-05,
"loss": 4.0839,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795463136881594e-05,
"loss": 4.0936,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794624542130542e-05,
"loss": 4.0834,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793787585259863e-05,
"loss": 4.0736,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792948990508811e-05,
"loss": 4.0739,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792110395757759e-05,
"loss": 4.0809,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791271801006707e-05,
"loss": 4.0849,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790434844136028e-05,
"loss": 4.0827,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789596249384976e-05,
"loss": 4.0757,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788757654633924e-05,
"loss": 4.0656,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787920697763245e-05,
"loss": 4.0827,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870821030121935e-05,
"loss": 4.0614,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862451461415144e-05,
"loss": 4.0701,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854065513904624e-05,
"loss": 4.0689,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845679566394104e-05,
"loss": 4.0688,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837293618883584e-05,
"loss": 4.057,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828907671373064e-05,
"loss": 4.0678,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820521723862544e-05,
"loss": 4.0582,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812135776352024e-05,
"loss": 4.0658,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803749828841504e-05,
"loss": 4.064,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779538026013471e-05,
"loss": 4.0543,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778699431262419e-05,
"loss": 4.0753,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777860836511367e-05,
"loss": 4.0753,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777023879640689e-05,
"loss": 4.066,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776185284889637e-05,
"loss": 4.0556,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775346690138585e-05,
"loss": 4.0512,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774508095387533e-05,
"loss": 4.0562,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773669500636481e-05,
"loss": 4.0545,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772830905885429e-05,
"loss": 4.0651,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771992311134377e-05,
"loss": 4.0455,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771155354263698e-05,
"loss": 4.0551,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770316759512646e-05,
"loss": 4.0575,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769478164761594e-05,
"loss": 4.0561,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.0434,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76780097525949e-05,
"loss": 4.0517,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766962380508437e-05,
"loss": 4.0484,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766123785757386e-05,
"loss": 4.0522,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765285191006334e-05,
"loss": 4.0566,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764448234135655e-05,
"loss": 4.0562,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.7636096393846026e-05,
"loss": 4.0365,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.7627710446335506e-05,
"loss": 4.0505,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.7619324498824986e-05,
"loss": 4.0494,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610954930118195e-05,
"loss": 4.049,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602568982607675e-05,
"loss": 4.0444,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594183035097155e-05,
"loss": 4.052,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.7585797087586635e-05,
"loss": 4.044,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757744389768358e-05,
"loss": 4.0618,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756905795017306e-05,
"loss": 4.0364,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756067200266254e-05,
"loss": 4.0487,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755228605515202e-05,
"loss": 4.039,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.75439001076415e-05,
"loss": 4.0348,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753551416013098e-05,
"loss": 4.0387,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752712821262046e-05,
"loss": 4.0297,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751875864391367e-05,
"loss": 4.0317,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751037269640315e-05,
"loss": 4.0364,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750198674889263e-05,
"loss": 4.0318,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.0336785316467285,
"eval_runtime": 301.7288,
"eval_samples_per_second": 1264.682,
"eval_steps_per_second": 39.522,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749360080138211e-05,
"loss": 4.0274,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748521485387159e-05,
"loss": 4.022,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747682890636107e-05,
"loss": 4.0399,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746844295885055e-05,
"loss": 4.0288,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.746005701134003e-05,
"loss": 4.0442,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745167106382951e-05,
"loss": 4.0203,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744328511631899e-05,
"loss": 4.0278,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434899168808475e-05,
"loss": 4.0115,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426513221297955e-05,
"loss": 4.0269,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418127273787435e-05,
"loss": 4.0224,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740974132627691e-05,
"loss": 4.018,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401371757570124e-05,
"loss": 4.0306,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739300218886333e-05,
"loss": 4.0066,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738461624135281e-05,
"loss": 4.0237,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737623029384229e-05,
"loss": 4.0052,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736784434633177e-05,
"loss": 4.0077,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735945839882125e-05,
"loss": 4.007,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735107245131073e-05,
"loss": 4.0163,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734268650380021e-05,
"loss": 4.0097,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733430055628969e-05,
"loss": 4.0282,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732593098758291e-05,
"loss": 4.0078,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731756141887612e-05,
"loss": 4.0134,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73091754713656e-05,
"loss": 4.0083,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730078952385508e-05,
"loss": 4.0177,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729240357634456e-05,
"loss": 4.0046,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728401762883403e-05,
"loss": 4.0113,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727563168132351e-05,
"loss": 3.9999,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726724573381299e-05,
"loss": 4.0039,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725885978630247e-05,
"loss": 3.993,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725049021759568e-05,
"loss": 4.0076,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724210427008517e-05,
"loss": 4.0051,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233718322574647e-05,
"loss": 4.0056,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225332375064127e-05,
"loss": 4.0123,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216962806357336e-05,
"loss": 4.0008,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208576858846816e-05,
"loss": 3.9987,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200190911336296e-05,
"loss": 4.006,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191804963825775e-05,
"loss": 3.9977,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183435395118985e-05,
"loss": 3.9881,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.71750658264122e-05,
"loss": 3.9802,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716667987890168e-05,
"loss": 3.9882,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158293931391154e-05,
"loss": 3.9905,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149907983880634e-05,
"loss": 3.9987,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714152203637012e-05,
"loss": 3.9905,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71331360888596e-05,
"loss": 3.9813,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712475014134908e-05,
"loss": 3.9977,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711636419383856e-05,
"loss": 3.9876,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710799462513177e-05,
"loss": 3.9842,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709962505642498e-05,
"loss": 3.9792,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709123910891446e-05,
"loss": 3.9724,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708285316140394e-05,
"loss": 3.999,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707446721389342e-05,
"loss": 3.9959,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.70660812663829e-05,
"loss": 3.981,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705769531887238e-05,
"loss": 3.981,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704932575016559e-05,
"loss": 3.9901,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040939802655074e-05,
"loss": 3.9669,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032553855144554e-05,
"loss": 3.9885,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024167907634034e-05,
"loss": 3.9658,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015781960123514e-05,
"loss": 3.9864,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007396012612994e-05,
"loss": 3.9937,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6999010065102474e-05,
"loss": 3.9731,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699064049639568e-05,
"loss": 3.9649,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698225454888516e-05,
"loss": 3.9838,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697386860137464e-05,
"loss": 3.9553,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696548265386412e-05,
"loss": 3.9686,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69570967063536e-05,
"loss": 3.9791,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694871075884308e-05,
"loss": 3.9762,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694032481133256e-05,
"loss": 3.9706,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693195524262577e-05,
"loss": 3.9563,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692356929511526e-05,
"loss": 3.9606,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691518334760474e-05,
"loss": 3.9617,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690679740009422e-05,
"loss": 3.9747,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689841145258369e-05,
"loss": 3.9621,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689002550507317e-05,
"loss": 3.9744,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688165593636639e-05,
"loss": 3.9747,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687326998885587e-05,
"loss": 3.9735,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686488404134534e-05,
"loss": 3.9582,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685649809383482e-05,
"loss": 3.9677,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.68481121463243e-05,
"loss": 3.9682,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683974257761751e-05,
"loss": 3.9617,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831356630106996e-05,
"loss": 3.9657,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822970682596476e-05,
"loss": 3.9612,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814584735085956e-05,
"loss": 3.9618,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806198787575436e-05,
"loss": 3.9674,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797812840064916e-05,
"loss": 3.9478,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789426892554396e-05,
"loss": 3.9587,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.6781040945043876e-05,
"loss": 3.9551,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772671376337085e-05,
"loss": 3.9666,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764285428826565e-05,
"loss": 3.956,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755915860119774e-05,
"loss": 3.9541,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747529912609254e-05,
"loss": 3.953,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739143965098734e-05,
"loss": 3.9475,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730758017588214e-05,
"loss": 3.9442,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672238844888143e-05,
"loss": 3.9555,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671400250137091e-05,
"loss": 3.9654,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670561655386039e-05,
"loss": 3.9604,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669723060634987e-05,
"loss": 3.9526,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668884465883935e-05,
"loss": 3.9462,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668045871132883e-05,
"loss": 3.947,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667207276381831e-05,
"loss": 3.9506,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666370319511152e-05,
"loss": 3.9587,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655317247601e-05,
"loss": 3.9559,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664693130009048e-05,
"loss": 3.9493,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663854535257996e-05,
"loss": 3.9394,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663017578387317e-05,
"loss": 3.9608,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662178983636265e-05,
"loss": 3.9363,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661340388885213e-05,
"loss": 3.9482,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6605017941341614e-05,
"loss": 3.9415,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596631993831094e-05,
"loss": 3.9471,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.65882624251243e-05,
"loss": 3.9364,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657987647761378e-05,
"loss": 3.9473,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657149053010326e-05,
"loss": 3.9381,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656310458259274e-05,
"loss": 3.937,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655471863508222e-05,
"loss": 3.9501,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654634906637543e-05,
"loss": 3.9308,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653796311886491e-05,
"loss": 3.9554,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652957717135439e-05,
"loss": 3.9547,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652119122384387e-05,
"loss": 3.9471,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651280527633335e-05,
"loss": 3.937,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650443570762657e-05,
"loss": 3.9355,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649604976011605e-05,
"loss": 3.9361,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648766381260553e-05,
"loss": 3.9369,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479277865095e-05,
"loss": 3.9455,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647089191758448e-05,
"loss": 3.9268,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.64625223488777e-05,
"loss": 3.9386,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645413640136718e-05,
"loss": 3.9424,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644575045385665e-05,
"loss": 3.9396,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643736450634613e-05,
"loss": 3.9309,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428994937639346e-05,
"loss": 3.9357,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642060899012882e-05,
"loss": 3.9358,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412223042618306e-05,
"loss": 3.9384,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403837095107786e-05,
"loss": 3.9389,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395451147597266e-05,
"loss": 3.9436,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387065200086746e-05,
"loss": 3.9228,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378679252576226e-05,
"loss": 3.9368,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370309683869435e-05,
"loss": 3.938,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6361923736358915e-05,
"loss": 3.935,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353537788848395e-05,
"loss": 3.932,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345151841337874e-05,
"loss": 3.9418,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336782272631084e-05,
"loss": 3.9323,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328396325120564e-05,
"loss": 3.9482,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320010377610043e-05,
"loss": 3.9258,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311624430099523e-05,
"loss": 3.9342,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303238482589003e-05,
"loss": 3.9316,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629486891388222e-05,
"loss": 3.9261,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.62864829663717e-05,
"loss": 3.9291,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627809701886118e-05,
"loss": 3.9241,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626971107135066e-05,
"loss": 3.9218,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626134150264387e-05,
"loss": 3.9273,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625295555513335e-05,
"loss": 3.9251,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9582722187042236,
"eval_runtime": 302.7231,
"eval_samples_per_second": 1260.528,
"eval_steps_per_second": 39.392,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624456960762283e-05,
"loss": 3.9238,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623618366011231e-05,
"loss": 3.9151,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622779771260179e-05,
"loss": 3.9305,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219428143895e-05,
"loss": 3.9215,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621104219638448e-05,
"loss": 3.9412,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620265624887396e-05,
"loss": 3.9158,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619427030136344e-05,
"loss": 3.922,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618590073265665e-05,
"loss": 3.9064,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617751478514613e-05,
"loss": 3.9244,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616912883763561e-05,
"loss": 3.9198,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616074289012509e-05,
"loss": 3.9129,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.61523733214183e-05,
"loss": 3.9219,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614398737390778e-05,
"loss": 3.9066,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613560142639726e-05,
"loss": 3.9201,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612721547888674e-05,
"loss": 3.9042,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611884591017995e-05,
"loss": 3.9035,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611045996266943e-05,
"loss": 3.9065,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610207401515891e-05,
"loss": 3.9132,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609368806764839e-05,
"loss": 3.9089,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608530212013788e-05,
"loss": 3.9262,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076932551431087e-05,
"loss": 3.9094,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068546603920566e-05,
"loss": 3.9171,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6060160656410046e-05,
"loss": 3.9079,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051774708899526e-05,
"loss": 3.9143,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.6043405140192735e-05,
"loss": 3.9056,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.6035019192682215e-05,
"loss": 3.9135,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.6026633245171695e-05,
"loss": 3.9048,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018247297661175e-05,
"loss": 3.9017,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009877728954384e-05,
"loss": 3.8994,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001491781443864e-05,
"loss": 3.9074,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.5993105833933344e-05,
"loss": 3.9107,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598471988642283e-05,
"loss": 3.9075,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597633393891231e-05,
"loss": 3.9179,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596796437020552e-05,
"loss": 3.9051,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.5959578422695e-05,
"loss": 3.9009,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595119247518448e-05,
"loss": 3.9079,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594280652767395e-05,
"loss": 3.9086,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593443695896717e-05,
"loss": 3.8895,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592605101145665e-05,
"loss": 3.8849,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591766506394613e-05,
"loss": 3.8913,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.59092791164356e-05,
"loss": 3.9001,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590090954772882e-05,
"loss": 3.9027,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.58925236002183e-05,
"loss": 3.8996,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5884137652707785e-05,
"loss": 3.8872,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587575170519726e-05,
"loss": 3.9024,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586736575768674e-05,
"loss": 3.8974,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858996188979954e-05,
"loss": 3.8931,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585061024146943e-05,
"loss": 3.8863,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584222429395891e-05,
"loss": 3.8743,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583383834644839e-05,
"loss": 3.9151,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582545239893787e-05,
"loss": 3.9014,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581706645142735e-05,
"loss": 3.8927,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580868050391683e-05,
"loss": 3.8933,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800310935210036e-05,
"loss": 3.8932,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579192498769952e-05,
"loss": 3.8783,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783539040189e-05,
"loss": 3.8969,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577515309267848e-05,
"loss": 3.8801,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576678352397169e-05,
"loss": 3.8916,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575839757646117e-05,
"loss": 3.9073,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.575001162895065e-05,
"loss": 3.8851,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574162568144013e-05,
"loss": 3.8726,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573325611273334e-05,
"loss": 3.8985,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572487016522282e-05,
"loss": 3.8672,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.57164842177123e-05,
"loss": 3.8744,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570809827020178e-05,
"loss": 3.8947,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569972870149499e-05,
"loss": 3.8883,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.5691342753984476e-05,
"loss": 3.8816,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5682956806473956e-05,
"loss": 3.8747,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.5674570858963436e-05,
"loss": 3.8687,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.5666201290256645e-05,
"loss": 3.8754,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.5657815342746125e-05,
"loss": 3.8889,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.5649429395235605e-05,
"loss": 3.8743,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.5641043447725085e-05,
"loss": 3.8908,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.5632673879018294e-05,
"loss": 3.8843,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624287931507774e-05,
"loss": 3.8926,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615901983997254e-05,
"loss": 3.877,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.5607516036486734e-05,
"loss": 3.8786,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559914646777994e-05,
"loss": 3.8844,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559076052026943e-05,
"loss": 3.875,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558237457275891e-05,
"loss": 3.8875,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557398862524839e-05,
"loss": 3.8751,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.55656190565416e-05,
"loss": 3.8768,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555723310903108e-05,
"loss": 3.881,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554884716152056e-05,
"loss": 3.8657,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554046121401004e-05,
"loss": 3.8723,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553209164530325e-05,
"loss": 3.8759,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552370569779273e-05,
"loss": 3.8814,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551531975028221e-05,
"loss": 3.8718,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550693380277169e-05,
"loss": 3.8731,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549854785526117e-05,
"loss": 3.8671,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.5490178286554384e-05,
"loss": 3.8657,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.5481792339043864e-05,
"loss": 3.8636,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.5473406391533343e-05,
"loss": 3.8722,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.5465020444022823e-05,
"loss": 3.8828,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545665087531603e-05,
"loss": 3.8827,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544826492780551e-05,
"loss": 3.872,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543987898029499e-05,
"loss": 3.8635,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543149303278447e-05,
"loss": 3.8677,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542312346407768e-05,
"loss": 3.8715,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541473751656716e-05,
"loss": 3.8771,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540635156905664e-05,
"loss": 3.8764,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539796562154612e-05,
"loss": 3.8712,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538959605283933e-05,
"loss": 3.8593,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538121010532882e-05,
"loss": 3.8834,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.53728241578183e-05,
"loss": 3.853,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536443821030778e-05,
"loss": 3.8716,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5356068641600986e-05,
"loss": 3.8611,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347682694090466e-05,
"loss": 3.8684,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339296746579946e-05,
"loss": 3.8585,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330910799069426e-05,
"loss": 3.8681,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322541230362635e-05,
"loss": 3.8607,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314155282852115e-05,
"loss": 3.8597,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.5305769335341595e-05,
"loss": 3.8688,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297383387831075e-05,
"loss": 3.8563,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.5289013819124284e-05,
"loss": 3.8758,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528062787161377e-05,
"loss": 3.8778,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527224192410325e-05,
"loss": 3.8709,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526385597659273e-05,
"loss": 3.8602,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525548640788594e-05,
"loss": 3.8606,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524710046037542e-05,
"loss": 3.8578,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.52387145128649e-05,
"loss": 3.861,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523032856535438e-05,
"loss": 3.8696,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522195899664759e-05,
"loss": 3.8465,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521357304913707e-05,
"loss": 3.8626,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520518710162655e-05,
"loss": 3.8634,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519680115411603e-05,
"loss": 3.8675,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518843158540924e-05,
"loss": 3.8554,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5180045637898725e-05,
"loss": 3.8623,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171659690388204e-05,
"loss": 3.8544,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163273742877684e-05,
"loss": 3.8696,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.5154904174170894e-05,
"loss": 3.8614,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146518226660373e-05,
"loss": 3.8706,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5138132279149853e-05,
"loss": 3.8463,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.5129746331639333e-05,
"loss": 3.8627,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512137676293254e-05,
"loss": 3.8646,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511299081542202e-05,
"loss": 3.8557,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.51046048679115e-05,
"loss": 3.8578,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5096218920400976e-05,
"loss": 3.868,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508784935169419e-05,
"loss": 3.8603,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507946340418368e-05,
"loss": 3.8755,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507107745667316e-05,
"loss": 3.8504,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506269150916263e-05,
"loss": 3.8634,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505432194045585e-05,
"loss": 3.8537,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504593599294533e-05,
"loss": 3.8549,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.50375500454348e-05,
"loss": 3.8565,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502916409792428e-05,
"loss": 3.8505,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020810908021225e-05,
"loss": 3.8494,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012424960510705e-05,
"loss": 3.8507,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.5004039013000185e-05,
"loss": 3.8539,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.9172236919403076,
"eval_runtime": 302.6065,
"eval_samples_per_second": 1261.014,
"eval_steps_per_second": 39.408,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.4995653065489665e-05,
"loss": 3.8498,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987267117979145e-05,
"loss": 3.843,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497888117046863e-05,
"loss": 3.861,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970495222958105e-05,
"loss": 3.8513,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4962109275447585e-05,
"loss": 3.8671,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953723327937065e-05,
"loss": 3.8502,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945337380426545e-05,
"loss": 3.8499,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936951432916025e-05,
"loss": 3.8365,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928581864209234e-05,
"loss": 3.8509,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4920195916698714e-05,
"loss": 3.8471,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911809969188194e-05,
"loss": 3.8472,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903424021677674e-05,
"loss": 3.849,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489505445297088e-05,
"loss": 3.8364,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488666850546037e-05,
"loss": 3.8514,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487828255794985e-05,
"loss": 3.8345,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486989661043933e-05,
"loss": 3.8346,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486152704173254e-05,
"loss": 3.8361,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485314109422202e-05,
"loss": 3.8468,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.48447551467115e-05,
"loss": 3.8373,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483636919920098e-05,
"loss": 3.856,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482799963049419e-05,
"loss": 3.8422,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481961368298367e-05,
"loss": 3.8497,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481122773547315e-05,
"loss": 3.8416,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480284178796263e-05,
"loss": 3.8441,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.4794472219255837e-05,
"loss": 3.8375,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478608627174532e-05,
"loss": 3.8477,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.47777003242348e-05,
"loss": 3.8355,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476931437672428e-05,
"loss": 3.8378,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476094480801749e-05,
"loss": 3.83,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475255886050697e-05,
"loss": 3.839,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474417291299645e-05,
"loss": 3.8433,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473578696548593e-05,
"loss": 3.8415,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472741739677914e-05,
"loss": 3.8473,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471903144926862e-05,
"loss": 3.8365,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.47106455017581e-05,
"loss": 3.8354,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470225955424758e-05,
"loss": 3.8452,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469388998554079e-05,
"loss": 3.8436,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468550403803028e-05,
"loss": 3.82,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467711809051976e-05,
"loss": 3.8255,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466873214300924e-05,
"loss": 3.8248,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660362574302446e-05,
"loss": 3.8293,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651976626791926e-05,
"loss": 3.841,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.4643590679281406e-05,
"loss": 3.8321,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4635204731770886e-05,
"loss": 3.8274,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626835163064095e-05,
"loss": 3.8358,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618449215553575e-05,
"loss": 3.8281,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4610063268043055e-05,
"loss": 3.8301,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601677320532535e-05,
"loss": 3.8245,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4593307751825744e-05,
"loss": 3.8052,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584921804315224e-05,
"loss": 3.8513,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457653585680471e-05,
"loss": 3.8373,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456814990929419e-05,
"loss": 3.832,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.45597803405874e-05,
"loss": 3.8269,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455141077188061e-05,
"loss": 3.8261,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454302482437009e-05,
"loss": 3.816,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453463887685957e-05,
"loss": 3.8302,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452625292934905e-05,
"loss": 3.8212,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451786698183853e-05,
"loss": 3.8263,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450948103432801e-05,
"loss": 3.844,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450109508681749e-05,
"loss": 3.8199,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449270913930697e-05,
"loss": 3.8138,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448433957060018e-05,
"loss": 3.8356,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.4475953623089664e-05,
"loss": 3.8065,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.4467567675579144e-05,
"loss": 3.8151,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.4459181728068624e-05,
"loss": 3.8293,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445081215936183e-05,
"loss": 3.8253,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444242621185131e-05,
"loss": 3.8197,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443404026434079e-05,
"loss": 3.815,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.4425670695634e-05,
"loss": 3.8044,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441728474812348e-05,
"loss": 3.8143,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440889880061296e-05,
"loss": 3.8259,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440051285310244e-05,
"loss": 3.8156,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439214328439565e-05,
"loss": 3.8248,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438375733688513e-05,
"loss": 3.8254,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437537138937462e-05,
"loss": 3.8328,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.43669854418641e-05,
"loss": 3.8148,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435861587315731e-05,
"loss": 3.8146,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435022992564679e-05,
"loss": 3.8242,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434184397813627e-05,
"loss": 3.8105,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433345803062575e-05,
"loss": 3.8296,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4325088461918956e-05,
"loss": 3.8156,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316702514408436e-05,
"loss": 3.8161,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4308316566897916e-05,
"loss": 3.8226,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299930619387396e-05,
"loss": 3.804,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291561050680605e-05,
"loss": 3.8101,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4283175103170085e-05,
"loss": 3.8145,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427478915565957e-05,
"loss": 3.8229,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426640320814905e-05,
"loss": 3.8069,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425803363944226e-05,
"loss": 3.8156,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424964769193174e-05,
"loss": 3.8086,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424126174442122e-05,
"loss": 3.8114,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.42328757969107e-05,
"loss": 3.8017,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422450622820391e-05,
"loss": 3.8147,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421612028069339e-05,
"loss": 3.8226,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420773433318287e-05,
"loss": 3.8213,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419934838567235e-05,
"loss": 3.8188,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419097881696556e-05,
"loss": 3.8031,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418259286945504e-05,
"loss": 3.8065,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4174206921944525e-05,
"loss": 3.81,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.4165820974434005e-05,
"loss": 3.8196,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157451405727214e-05,
"loss": 3.8169,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.4149065458216694e-05,
"loss": 3.8118,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.4140679510706174e-05,
"loss": 3.8052,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4132293563195654e-05,
"loss": 3.8233,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412392399448886e-05,
"loss": 3.7972,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411553804697834e-05,
"loss": 3.8123,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410715209946782e-05,
"loss": 3.8038,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098766151957296e-05,
"loss": 3.8121,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409039658325051e-05,
"loss": 3.799,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408201063573999e-05,
"loss": 3.8115,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407362468822948e-05,
"loss": 3.8011,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406523874071895e-05,
"loss": 3.8063,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405686917201217e-05,
"loss": 3.8102,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404848322450165e-05,
"loss": 3.803,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.404009727699113e-05,
"loss": 3.8156,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.40317113294806e-05,
"loss": 3.8216,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402334176077382e-05,
"loss": 3.8095,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.40149558132633e-05,
"loss": 3.8082,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400656986575277e-05,
"loss": 3.8005,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399818391824225e-05,
"loss": 3.8045,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.3989814349535466e-05,
"loss": 3.8022,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.3981428402024946e-05,
"loss": 3.8173,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.3973042454514426e-05,
"loss": 3.7872,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.3964656507003906e-05,
"loss": 3.8055,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395628693829712e-05,
"loss": 3.8049,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.39479009907866e-05,
"loss": 3.8108,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939515043276075e-05,
"loss": 3.8,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3931129095765555e-05,
"loss": 3.8049,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392275952705877e-05,
"loss": 3.7972,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3914373579548244e-05,
"loss": 3.8118,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905987632037724e-05,
"loss": 3.8088,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897601684527204e-05,
"loss": 3.8114,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388923211582042e-05,
"loss": 3.7943,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.38808461683099e-05,
"loss": 3.807,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387246022079938e-05,
"loss": 3.8102,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386407427328886e-05,
"loss": 3.8009,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855704704582075e-05,
"loss": 3.8029,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384731875707155e-05,
"loss": 3.8103,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383893280956103e-05,
"loss": 3.8023,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383054686205051e-05,
"loss": 3.8239,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382217729334372e-05,
"loss": 3.796,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.38137913458332e-05,
"loss": 3.8061,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380540539832268e-05,
"loss": 3.7984,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379701945081216e-05,
"loss": 3.8009,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378864988210537e-05,
"loss": 3.8046,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.378026393459485e-05,
"loss": 3.7967,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377189436588807e-05,
"loss": 3.7996,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376350841837754e-05,
"loss": 3.7876,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375512247086702e-05,
"loss": 3.8033,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.8930797576904297,
"eval_runtime": 305.8231,
"eval_samples_per_second": 1247.751,
"eval_steps_per_second": 38.993,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.37467365233565e-05,
"loss": 3.8019,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.373835057584598e-05,
"loss": 3.7899,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.372996462833546e-05,
"loss": 3.8041,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.372157868082494e-05,
"loss": 3.8021,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.371319273331442e-05,
"loss": 3.8094,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.370482316460763e-05,
"loss": 3.7951,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.369645359590085e-05,
"loss": 3.7964,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368806764839033e-05,
"loss": 3.7857,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367968170087981e-05,
"loss": 3.7983,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367129575336929e-05,
"loss": 3.7953,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366290980585877e-05,
"loss": 3.7972,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.365452385834825e-05,
"loss": 3.791,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.364613791083773e-05,
"loss": 3.7895,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.363775196332721e-05,
"loss": 3.7919,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.3629382394620416e-05,
"loss": 3.7846,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.3620996447109896e-05,
"loss": 3.7798,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.3612610499599376e-05,
"loss": 3.7845,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.3604224552088856e-05,
"loss": 3.7926,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.3595854983382065e-05,
"loss": 3.7859,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.3587469035871545e-05,
"loss": 3.8036,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.3579083088361025e-05,
"loss": 3.7929,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.357069714085051e-05,
"loss": 3.7991,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.356232757214372e-05,
"loss": 3.7868,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.35539416246332e-05,
"loss": 3.7888,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.354555567712268e-05,
"loss": 3.7865,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.353716972961216e-05,
"loss": 3.7987,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.352880016090537e-05,
"loss": 3.7867,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.352041421339485e-05,
"loss": 3.7848,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.351202826588433e-05,
"loss": 3.7799,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.350364231837381e-05,
"loss": 3.7889,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.349527274966702e-05,
"loss": 3.7901,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.34868868021565e-05,
"loss": 3.7929,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.347850085464598e-05,
"loss": 3.7948,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.3470114907135465e-05,
"loss": 3.7906,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.3461745338428674e-05,
"loss": 3.785,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.3453359390918154e-05,
"loss": 3.7957,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.3444973443407634e-05,
"loss": 3.7918,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.343660387470084e-05,
"loss": 3.7738,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.342821792719032e-05,
"loss": 3.7748,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.34198319796798e-05,
"loss": 3.7717,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.341144603216928e-05,
"loss": 3.7779,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.340307646346249e-05,
"loss": 3.7903,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.339469051595197e-05,
"loss": 3.7846,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338630456844145e-05,
"loss": 3.7773,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337791862093093e-05,
"loss": 3.7859,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.336954905222415e-05,
"loss": 3.7776,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.336116310471363e-05,
"loss": 3.7811,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.335277715720311e-05,
"loss": 3.7718,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334439120969259e-05,
"loss": 3.7547,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.33360216409858e-05,
"loss": 3.803,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.332763569347528e-05,
"loss": 3.7848,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.331924974596476e-05,
"loss": 3.7888,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331086379845424e-05,
"loss": 3.7746,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.3302494229747446e-05,
"loss": 3.7829,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.3294108282236926e-05,
"loss": 3.7665,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.3285722334726406e-05,
"loss": 3.7778,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.3277336387215886e-05,
"loss": 3.7771,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326895043970537e-05,
"loss": 3.7747,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326056449219485e-05,
"loss": 3.7974,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.3252178544684325e-05,
"loss": 3.77,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.3243792597173805e-05,
"loss": 3.7629,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.323542302846702e-05,
"loss": 3.7898,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.32270370809565e-05,
"loss": 3.757,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.3218651133445974e-05,
"loss": 3.7648,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.3210265185935454e-05,
"loss": 3.7826,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.320189561722867e-05,
"loss": 3.7802,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.319350966971815e-05,
"loss": 3.7665,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.3185123722207623e-05,
"loss": 3.7736,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.317675415350084e-05,
"loss": 3.7545,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.3168368205990326e-05,
"loss": 3.7694,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.31599822584798e-05,
"loss": 3.778,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.315159631096928e-05,
"loss": 3.7646,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.3143226742262495e-05,
"loss": 3.7795,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.3134840794751975e-05,
"loss": 3.7771,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.312645484724145e-05,
"loss": 3.7883,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311806889973093e-05,
"loss": 3.766,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.3109699331024144e-05,
"loss": 3.773,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310131338351362e-05,
"loss": 3.7764,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.30929274360031e-05,
"loss": 3.762,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308454148849258e-05,
"loss": 3.7781,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.307617191978579e-05,
"loss": 3.7721,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.306778597227527e-05,
"loss": 3.7685,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.305940002476475e-05,
"loss": 3.778,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.305101407725423e-05,
"loss": 3.7586,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.304264450854745e-05,
"loss": 3.7582,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.303425856103692e-05,
"loss": 3.7691,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.30258726135264e-05,
"loss": 3.7754,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.301748666601588e-05,
"loss": 3.7642,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.300911709730909e-05,
"loss": 3.7688,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.300073114979857e-05,
"loss": 3.7561,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.299234520228805e-05,
"loss": 3.7659,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.298395925477753e-05,
"loss": 3.7578,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.297558968607075e-05,
"loss": 3.7652,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.2967203738560227e-05,
"loss": 3.779,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.2958817791049707e-05,
"loss": 3.772,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.2950431843539186e-05,
"loss": 3.7704,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.2942062274832396e-05,
"loss": 3.7587,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.2933676327321876e-05,
"loss": 3.7602,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.2925290379811355e-05,
"loss": 3.7634,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.2916904432300835e-05,
"loss": 3.7764,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.2908534863594045e-05,
"loss": 3.7673,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.2900148916083525e-05,
"loss": 3.7728,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.2891762968573004e-05,
"loss": 3.7575,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.2883377021062484e-05,
"loss": 3.7758,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.28750074523557e-05,
"loss": 3.7536,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286662150484518e-05,
"loss": 3.7676,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.285823555733466e-05,
"loss": 3.7554,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.284984960982414e-05,
"loss": 3.7698,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.2841496419921085e-05,
"loss": 3.7544,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.2833110472410565e-05,
"loss": 3.7623,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.282472452490004e-05,
"loss": 3.7594,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281633857738952e-05,
"loss": 3.761,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.2807952629879e-05,
"loss": 3.7618,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.279956668236848e-05,
"loss": 3.7592,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.279118073485796e-05,
"loss": 3.7694,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.278279478734744e-05,
"loss": 3.7745,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.2774425218640654e-05,
"loss": 3.7668,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.2766039271130134e-05,
"loss": 3.7676,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.2757653323619614e-05,
"loss": 3.7534,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.2749267376109094e-05,
"loss": 3.758,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.27408978074023e-05,
"loss": 3.7615,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273251185989178e-05,
"loss": 3.769,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.272412591238126e-05,
"loss": 3.7442,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.271573996487074e-05,
"loss": 3.7603,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.270737039616395e-05,
"loss": 3.7651,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.269898444865343e-05,
"loss": 3.7624,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.269059850114291e-05,
"loss": 3.7569,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.268221255363239e-05,
"loss": 3.7625,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.267384298492561e-05,
"loss": 3.7554,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.266545703741509e-05,
"loss": 3.7684,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.265707108990457e-05,
"loss": 3.764,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.264868514239405e-05,
"loss": 3.7677,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.2640315573687257e-05,
"loss": 3.749,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.2631929626176737e-05,
"loss": 3.7628,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.2623543678666216e-05,
"loss": 3.7678,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.2615157731155696e-05,
"loss": 3.7573,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.2606788162448906e-05,
"loss": 3.76,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.2598402214938386e-05,
"loss": 3.7652,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.2590016267427865e-05,
"loss": 3.7613,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.2581630319917345e-05,
"loss": 3.7757,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.257326075121056e-05,
"loss": 3.7562,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256487480370004e-05,
"loss": 3.7611,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255648885618952e-05,
"loss": 3.7573,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.2548102908679e-05,
"loss": 3.7578,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253973333997221e-05,
"loss": 3.7553,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253136377126542e-05,
"loss": 3.7531,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.25229778237549e-05,
"loss": 3.7604,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251459187624438e-05,
"loss": 3.7434,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250620592873386e-05,
"loss": 3.7625,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 3.876544713973999,
"eval_runtime": 303.1442,
"eval_samples_per_second": 1258.777,
"eval_steps_per_second": 39.338,
"step": 457920
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.127030926167716e+17,
"trial_name": null,
"trial_params": null
}