abhinavp's picture
Training in progress, epoch 0, checkpoint
0fae97a verified
{
"best_metric": 3.9593703746795654,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/transformer/3/checkpoints/checkpoint-228960",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 228960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.9751,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8389,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1964,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9913,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.831,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.729,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6181,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5466,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4708,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4107,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3693,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3226,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2769,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 5.2265,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 5.2016,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 5.1534,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 5.1278,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.1024,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0704,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0395,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.024,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9922,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9741,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9492,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9421,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.9073,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 4.8925,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8648,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8574,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.835,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 4.8275,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740117521192533e-05,
"loss": 4.8153,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731731573682013e-05,
"loss": 4.7978,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7871,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7747,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7605,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969820416244367e-05,
"loss": 4.7562,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7263,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7161,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6945,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6983,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6842,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6841,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6636,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.658,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6533,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6467,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6345,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6175,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.607,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.626,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.6135,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.594,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.58,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5894,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5654,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5763,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5455,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5663,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5519,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5308,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5254,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5371,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4981,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.5097,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5177,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.5039,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4962,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4801,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4776,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4747,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4897,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4655,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.477,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4706,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4679,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.451,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4509,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4463,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4422,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4351,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4272,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4292,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.429,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.4078,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.4161,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.4141,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.4159,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.4003,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3988,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.389,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3841,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922878764749932e-05,
"loss": 4.386,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3884,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3837,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3889,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3802,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3615,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.363,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3707,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3667,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.365,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.355,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3449,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3576,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3364,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3404,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3355,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.3354,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.327,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.3271,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.3205,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.3286,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3227,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3148,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3247,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.3281,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.3174,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.3046,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.3016,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.3007,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.3064,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.3021,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2912,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.3,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2918,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2915,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.2856,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2863,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2782,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.2889,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2873,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2855,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2637,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.2777,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.2728,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.2745,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2644,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2725,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2626,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2801,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2486,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2673,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.2524,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2501,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2526,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.2388,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2436,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2508,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.238,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.206758975982666,
"eval_runtime": 303.3129,
"eval_samples_per_second": 1258.077,
"eval_steps_per_second": 39.316,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.2339,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.2289,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2439,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2338,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.2424,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.2215,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.2239,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.2119,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.2221,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.2176,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2141,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2205,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.1997,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.2117,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.197,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.1969,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.2043,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860008726626628e-05,
"loss": 4.1963,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591701318755764e-05,
"loss": 4.198,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583315371245244e-05,
"loss": 4.2132,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.1907,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856655985502793e-05,
"loss": 4.1932,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855817390751741e-05,
"loss": 4.1915,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854978796000689e-05,
"loss": 4.1981,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.1901,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853303244378958e-05,
"loss": 4.1893,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852464649627906e-05,
"loss": 4.1739,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851626054876854e-05,
"loss": 4.1814,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850787460125802e-05,
"loss": 4.1703,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.84994886537475e-05,
"loss": 4.1817,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849111908504072e-05,
"loss": 4.1757,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482749516333934e-05,
"loss": 4.1788,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847436356882341e-05,
"loss": 4.1832,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846597762131289e-05,
"loss": 4.1711,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845759167380237e-05,
"loss": 4.1762,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844920572629185e-05,
"loss": 4.172,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844081977878133e-05,
"loss": 4.1624,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843243383127081e-05,
"loss": 4.1557,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.8424064262564016e-05,
"loss": 4.1473,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.8415678315053496e-05,
"loss": 4.1549,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.8407292367542976e-05,
"loss": 4.1553,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398906420032456e-05,
"loss": 4.1624,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839053685132567e-05,
"loss": 4.1507,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838215090381515e-05,
"loss": 4.1486,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837376495630463e-05,
"loss": 4.1542,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836537900879411e-05,
"loss": 4.1477,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835700944008732e-05,
"loss": 4.1483,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.83486234925768e-05,
"loss": 4.1356,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834023754506628e-05,
"loss": 4.1328,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833185159755576e-05,
"loss": 4.1569,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832346565004524e-05,
"loss": 4.1533,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831509608133845e-05,
"loss": 4.137,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830671013382793e-05,
"loss": 4.1392,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829834056512114e-05,
"loss": 4.1433,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289954617610625e-05,
"loss": 4.1246,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281568670100105e-05,
"loss": 4.1434,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273182722589585e-05,
"loss": 4.1177,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264796775079065e-05,
"loss": 4.1445,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256410827568545e-05,
"loss": 4.1392,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248024880058025e-05,
"loss": 4.121,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239655311351234e-05,
"loss": 4.1194,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231269363840714e-05,
"loss": 4.1344,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222883416330194e-05,
"loss": 4.1004,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214497468819674e-05,
"loss": 4.1178,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820612790011288e-05,
"loss": 4.1285,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819774195260236e-05,
"loss": 4.1218,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818935600509184e-05,
"loss": 4.1126,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818097005758132e-05,
"loss": 4.1008,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817260048887454e-05,
"loss": 4.1089,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816421454136402e-05,
"loss": 4.1099,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.81558285938535e-05,
"loss": 4.1186,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814744264634298e-05,
"loss": 4.1073,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813907307763619e-05,
"loss": 4.1162,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813068713012567e-05,
"loss": 4.1182,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812230118261515e-05,
"loss": 4.1164,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811391523510463e-05,
"loss": 4.1007,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810554566639784e-05,
"loss": 4.1078,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809715971888732e-05,
"loss": 4.1074,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887737713768e-05,
"loss": 4.1014,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808038782386628e-05,
"loss": 4.1036,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807201825515949e-05,
"loss": 4.0974,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806363230764897e-05,
"loss": 4.1048,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805524636013845e-05,
"loss": 4.1024,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804686041262793e-05,
"loss": 4.0836,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803849084392114e-05,
"loss": 4.0912,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803010489641062e-05,
"loss": 4.0954,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.80217189489001e-05,
"loss": 4.1019,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801333300138958e-05,
"loss": 4.0921,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800496343268279e-05,
"loss": 4.0892,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799657748517227e-05,
"loss": 4.0846,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798819153766175e-05,
"loss": 4.0763,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797980559015123e-05,
"loss": 4.0809,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971436021444446e-05,
"loss": 4.0893,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7963050073933926e-05,
"loss": 4.0859,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954664126423406e-05,
"loss": 4.0948,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946278178912886e-05,
"loss": 4.0854,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937908610206095e-05,
"loss": 4.0774,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929522662695575e-05,
"loss": 4.0753,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921136715185055e-05,
"loss": 4.0832,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912750767674535e-05,
"loss": 4.0869,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904381198967744e-05,
"loss": 4.0845,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895995251457224e-05,
"loss": 4.0764,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887609303946704e-05,
"loss": 4.0669,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879223356436184e-05,
"loss": 4.0843,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.78708537877294e-05,
"loss": 4.064,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786246784021888e-05,
"loss": 4.0713,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785408189270836e-05,
"loss": 4.0704,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784569594519783e-05,
"loss": 4.069,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783734275529478e-05,
"loss": 4.0601,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782895680778426e-05,
"loss": 4.0697,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782057086027374e-05,
"loss": 4.0576,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781218491276322e-05,
"loss": 4.0676,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.78037989652527e-05,
"loss": 4.0658,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779541301774218e-05,
"loss": 4.0582,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778702707023166e-05,
"loss": 4.0777,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777864112272114e-05,
"loss": 4.0754,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770271554014354e-05,
"loss": 4.0677,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761885606503834e-05,
"loss": 4.058,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775349965899331e-05,
"loss": 4.0522,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774511371148279e-05,
"loss": 4.0587,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773672776397227e-05,
"loss": 4.0553,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728341816461747e-05,
"loss": 4.0645,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719955868951227e-05,
"loss": 4.046,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711569921440707e-05,
"loss": 4.0568,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703200352733916e-05,
"loss": 4.0583,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694814405223396e-05,
"loss": 4.06,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686428457712876e-05,
"loss": 4.0453,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767805888900609e-05,
"loss": 4.0531,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766967294149557e-05,
"loss": 4.0514,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766128699398505e-05,
"loss": 4.0542,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765290104647453e-05,
"loss": 4.0592,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764453147776774e-05,
"loss": 4.0587,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763614553025722e-05,
"loss": 4.0364,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.76277595827467e-05,
"loss": 4.0494,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761939001403991e-05,
"loss": 4.0513,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761100406652939e-05,
"loss": 4.05,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760261811901887e-05,
"loss": 4.047,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759423217150835e-05,
"loss": 4.0517,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758584622399783e-05,
"loss": 4.0453,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757746027648731e-05,
"loss": 4.0607,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569090707780525e-05,
"loss": 4.0361,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560704760270005e-05,
"loss": 4.0509,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552318812759485e-05,
"loss": 4.0399,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543932865248965e-05,
"loss": 4.0374,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535563296542174e-05,
"loss": 4.0418,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527177349031654e-05,
"loss": 4.0319,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518791401521134e-05,
"loss": 4.0351,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510405454010614e-05,
"loss": 4.0369,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7502019506500094e-05,
"loss": 4.0326,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.035162925720215,
"eval_runtime": 303.1156,
"eval_samples_per_second": 1258.896,
"eval_steps_per_second": 39.341,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493633558989574e-05,
"loss": 4.0293,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485247611479054e-05,
"loss": 4.0246,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476861663968534e-05,
"loss": 4.041,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468475716458014e-05,
"loss": 4.0305,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460089768947494e-05,
"loss": 4.048,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451703821436974e-05,
"loss": 4.0216,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443317873926453e-05,
"loss": 4.0286,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434931926415933e-05,
"loss": 4.0127,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426545978905413e-05,
"loss": 4.0294,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741816003139489e-05,
"loss": 4.0244,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740977408388437e-05,
"loss": 4.0201,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740140451517758e-05,
"loss": 4.0309,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739303494647079e-05,
"loss": 4.008,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738464899896027e-05,
"loss": 4.0249,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737626305144975e-05,
"loss": 4.0077,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736787710393923e-05,
"loss": 4.0097,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735949115642871e-05,
"loss": 4.0099,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.73511052089182e-05,
"loss": 4.0181,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734271926140768e-05,
"loss": 4.0111,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733433331389716e-05,
"loss": 4.0303,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325980123994096e-05,
"loss": 4.0102,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317594176483576e-05,
"loss": 4.0132,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7309208228973056e-05,
"loss": 4.0122,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300822281462536e-05,
"loss": 4.0211,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292436333952016e-05,
"loss": 4.0076,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7284050386441496e-05,
"loss": 4.0136,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275664438930976e-05,
"loss": 3.9999,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267278491420456e-05,
"loss": 4.0062,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258908922713665e-05,
"loss": 3.9943,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725052297520315e-05,
"loss": 4.009,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724213702769263e-05,
"loss": 4.0067,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723376745898584e-05,
"loss": 4.0094,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722538151147532e-05,
"loss": 4.0147,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.72169955639648e-05,
"loss": 4.0008,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720860961645428e-05,
"loss": 4.0003,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720022366894376e-05,
"loss": 4.0055,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719183772143324e-05,
"loss": 3.9971,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718345177392272e-05,
"loss": 3.9903,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717508220521593e-05,
"loss": 3.9818,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716671263650914e-05,
"loss": 3.9915,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715832668899862e-05,
"loss": 3.9904,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149940741488105e-05,
"loss": 4.0001,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141554793977585e-05,
"loss": 3.9924,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133168846467065e-05,
"loss": 3.984,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124799277760274e-05,
"loss": 3.9977,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116413330249754e-05,
"loss": 3.9897,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7108027382739234e-05,
"loss": 3.9858,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099641435228714e-05,
"loss": 3.9811,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091255487718194e-05,
"loss": 3.9748,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082869540207674e-05,
"loss": 3.9998,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074483592697154e-05,
"loss": 3.9977,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706609764518663e-05,
"loss": 3.9833,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705772807647984e-05,
"loss": 3.9833,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704934212896932e-05,
"loss": 3.9917,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.70409561814588e-05,
"loss": 3.968,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703257023394828e-05,
"loss": 3.9898,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702418428643776e-05,
"loss": 3.968,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701579833892724e-05,
"loss": 3.9903,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700741239141672e-05,
"loss": 3.9943,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.69990264439062e-05,
"loss": 3.9756,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699067325400315e-05,
"loss": 3.9667,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698228730649263e-05,
"loss": 3.9871,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.69739013589821e-05,
"loss": 3.9568,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696551541147158e-05,
"loss": 3.9719,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695712946396106e-05,
"loss": 3.9813,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694874351645054e-05,
"loss": 3.9793,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694035756894003e-05,
"loss": 3.9692,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693197162142951e-05,
"loss": 3.9583,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692361843152645e-05,
"loss": 3.9626,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915232484015926e-05,
"loss": 3.9651,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906846536505406e-05,
"loss": 3.9758,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898460588994886e-05,
"loss": 3.9646,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890074641484366e-05,
"loss": 3.9762,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881688693973846e-05,
"loss": 3.9784,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873319125267055e-05,
"loss": 3.978,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864933177756535e-05,
"loss": 3.9581,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856547230246015e-05,
"loss": 3.9692,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848161282735495e-05,
"loss": 3.9716,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683977533522498e-05,
"loss": 3.9626,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683140576651819e-05,
"loss": 3.9665,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682301981900767e-05,
"loss": 3.9638,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681463387149715e-05,
"loss": 3.9646,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680624792398663e-05,
"loss": 3.9694,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679786197647611e-05,
"loss": 3.9479,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678947602896559e-05,
"loss": 3.9603,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.67811064602588e-05,
"loss": 3.9578,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677272051274828e-05,
"loss": 3.9692,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676433456523776e-05,
"loss": 3.958,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675594861772724e-05,
"loss": 3.9579,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674756267021672e-05,
"loss": 3.9531,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739193101509935e-05,
"loss": 3.9471,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730807153999415e-05,
"loss": 3.9469,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722421206488895e-05,
"loss": 3.9571,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6714035258978375e-05,
"loss": 3.9653,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705665690271584e-05,
"loss": 3.9628,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697279742761064e-05,
"loss": 3.9553,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688893795250544e-05,
"loss": 3.9491,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680507847740024e-05,
"loss": 3.9497,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667213827903323e-05,
"loss": 3.9537,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666375233152271e-05,
"loss": 3.9605,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665536638401219e-05,
"loss": 3.9576,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664698043650167e-05,
"loss": 3.9503,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663859448899115e-05,
"loss": 3.9415,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663022492028437e-05,
"loss": 3.9625,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662183897277385e-05,
"loss": 3.9389,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661345302526333e-05,
"loss": 3.9486,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660506707775281e-05,
"loss": 3.9421,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659668113024229e-05,
"loss": 3.9482,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.65883115615355e-05,
"loss": 3.9386,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657992561402498e-05,
"loss": 3.948,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657153966651446e-05,
"loss": 3.9395,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656315371900393e-05,
"loss": 3.9403,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655476777149341e-05,
"loss": 3.9496,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546398202786626e-05,
"loss": 3.9345,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6538012255276106e-05,
"loss": 3.9567,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.6529626307765586e-05,
"loss": 3.9549,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521240360255066e-05,
"loss": 3.9486,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512854412744546e-05,
"loss": 3.9397,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650448484403776e-05,
"loss": 3.9356,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6496098896527235e-05,
"loss": 3.9368,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487712949016715e-05,
"loss": 3.9377,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479327001506195e-05,
"loss": 3.9462,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470941053995675e-05,
"loss": 3.9279,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462555106485155e-05,
"loss": 3.9419,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454169158974635e-05,
"loss": 3.9439,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445783211464115e-05,
"loss": 3.9414,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437413642757324e-05,
"loss": 3.9315,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429027695246804e-05,
"loss": 3.9368,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642064174773629e-05,
"loss": 3.9391,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641225580022577e-05,
"loss": 3.9395,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640386985271525e-05,
"loss": 3.9414,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639548390520473e-05,
"loss": 3.9466,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638711433649794e-05,
"loss": 3.9217,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637872838898742e-05,
"loss": 3.9372,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.63703424414769e-05,
"loss": 3.9392,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636195649396638e-05,
"loss": 3.9344,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635358692525959e-05,
"loss": 3.9331,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634520097774907e-05,
"loss": 3.9433,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633681503023855e-05,
"loss": 3.9355,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632842908272803e-05,
"loss": 3.9488,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632004313521751e-05,
"loss": 3.9256,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631165718770699e-05,
"loss": 3.9364,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303271240196475e-05,
"loss": 3.9325,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294901671489684e-05,
"loss": 3.9283,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286515723979164e-05,
"loss": 3.9312,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6278129776468644e-05,
"loss": 3.9253,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626974382895812e-05,
"loss": 3.9216,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626137426025133e-05,
"loss": 3.9274,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625298831274081e-05,
"loss": 3.9254,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9593703746795654,
"eval_runtime": 320.1607,
"eval_samples_per_second": 1191.873,
"eval_steps_per_second": 37.247,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.563515463083858e+17,
"trial_name": null,
"trial_params": null
}