abhinavp's picture
Training in progress, epoch 0, checkpoint
1e684b6 verified
raw
history blame
No virus
56.1 kB
{
"best_metric": 3.9539332389831543,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/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": 11.0178,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8227,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.2018,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.991,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8204,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7126,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6098,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5458,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4575,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4132,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3638,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3233,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2691,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.223,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.179,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1459,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1159,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0987,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.98490857024181e-05,
"loss": 5.0575,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984069975490758e-05,
"loss": 5.0359,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983231380739706e-05,
"loss": 5.0237,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9769,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9529,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9361,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.928,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.8923,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8706,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8656,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.843,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8161,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8007,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740117521192533e-05,
"loss": 4.7962,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731731573682013e-05,
"loss": 4.783,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7802,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7556,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7412,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7429,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.707,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 4.7,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 4.6859,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6867,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6639,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6757,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6457,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6488,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6392,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6307,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6281,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.603,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5898,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.6045,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.5896,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5713,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5602,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5677,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5515,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5627,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.536,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5356,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5381,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949702331620985e-05,
"loss": 4.5188,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 4.5021,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5087,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4917,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4926,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5017,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.495,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 4.4803,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4683,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4622,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4741,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 4.4678,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4597,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4592,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4625,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4559,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4277,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4401,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4349,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4217,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4344,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4227,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4289,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.4187,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.3921,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.4026,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.4023,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.4021,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3947,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3876,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3896,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3783,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.371,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 4.3736,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3673,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3798,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3578,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3519,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3506,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3598,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3563,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3427,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3421,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3246,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3386,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3246,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3231,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3273,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3273,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3191,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3168,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3095,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3168,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3049,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3045,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3107,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.3071,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019237232558704e-05,
"loss": 4.3041,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010851285048184e-05,
"loss": 4.2971,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900246533753767e-05,
"loss": 4.3012,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899407939002715e-05,
"loss": 4.2966,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985693442516624e-05,
"loss": 4.2822,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2993,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.2849,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2913,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2746,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2683,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2681,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.2703,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2606,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2781,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2749,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2576,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2603,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.267,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.2625,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.2668,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.264,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2505,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2545,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2509,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2432,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2525,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.2403,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2296,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.252,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.2324,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2305,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2326,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875096880624072e-05,
"loss": 4.2255,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.19805908203125,
"eval_runtime": 317.5316,
"eval_samples_per_second": 1201.742,
"eval_steps_per_second": 37.555,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.209,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.2221,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2381,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2144,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.23,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2034,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2141,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.1993,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.2106,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.2068,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2115,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2093,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642017003818885e-05,
"loss": 4.1932,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633631056308365e-05,
"loss": 4.1863,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625245108797845e-05,
"loss": 4.1869,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616859161287324e-05,
"loss": 4.1893,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608473213776804e-05,
"loss": 4.1986,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860008726626628e-05,
"loss": 4.184,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591701318755764e-05,
"loss": 4.1919,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583315371245244e-05,
"loss": 4.2064,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.1819,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.1742,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.1802,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.1882,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.169,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853301606498585e-05,
"loss": 4.1727,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.1739,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.17,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850787460125802e-05,
"loss": 4.1528,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.84994886537475e-05,
"loss": 4.1601,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.1575,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.1678,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1753,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.1573,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845757529499864e-05,
"loss": 4.1535,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.1657,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.1408,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.1489,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.1392,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.1462,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.1374,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.1558,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.1394,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.1409,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.139,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836536262999038e-05,
"loss": 4.1428,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1354,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.1274,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834020478745882e-05,
"loss": 4.1192,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833183521875203e-05,
"loss": 4.1407,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.13,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831506332373099e-05,
"loss": 4.1183,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830667737622047e-05,
"loss": 4.1169,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829830780751368e-05,
"loss": 4.126,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828992186000316e-05,
"loss": 4.1152,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828153591249264e-05,
"loss": 4.132,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827314996498212e-05,
"loss": 4.1153,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.82647640174716e-05,
"loss": 4.117,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825637806996108e-05,
"loss": 4.1285,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824799212245056e-05,
"loss": 4.1038,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823960617494004e-05,
"loss": 4.1023,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823122022742952e-05,
"loss": 4.1105,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222834279919e-05,
"loss": 4.0951,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.1015,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820607876370169e-05,
"loss": 4.112,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819769281619117e-05,
"loss": 4.116,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818930686868065e-05,
"loss": 4.1034,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818092092117013e-05,
"loss": 4.0978,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817255135246334e-05,
"loss": 4.0885,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816416540495282e-05,
"loss": 4.1073,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155779457442305e-05,
"loss": 4.1047,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147393509931785e-05,
"loss": 4.1024,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.1037,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130637993714474e-05,
"loss": 4.106,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122252046203954e-05,
"loss": 4.1058,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113866098693434e-05,
"loss": 4.0836,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.0968,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809711058247612e-05,
"loss": 4.0966,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887246349656e-05,
"loss": 4.0813,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808033868745508e-05,
"loss": 4.1042,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807195273994456e-05,
"loss": 4.0952,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806358317123777e-05,
"loss": 4.1,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805519722372726e-05,
"loss": 4.0982,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804681127621674e-05,
"loss": 4.0732,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803842532870622e-05,
"loss": 4.0868,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803005575999943e-05,
"loss": 4.0855,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802166981248891e-05,
"loss": 4.0891,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801328386497839e-05,
"loss": 4.0852,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004914296271596e-05,
"loss": 4.0774,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996528348761076e-05,
"loss": 4.0869,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988142401250556e-05,
"loss": 4.0798,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979756453740036e-05,
"loss": 4.0666,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971370506229516e-05,
"loss": 4.0752,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7962984558718996e-05,
"loss": 4.0786,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795461499001221e-05,
"loss": 4.0877,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794622904250169e-05,
"loss": 4.0721,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793784309499117e-05,
"loss": 4.0577,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792945714748065e-05,
"loss": 4.0671,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792107119997013e-05,
"loss": 4.0757,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912685252459605e-05,
"loss": 4.0729,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904299304949085e-05,
"loss": 4.0673,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895913357438565e-05,
"loss": 4.0628,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887543788731774e-05,
"loss": 4.0517,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879157841221254e-05,
"loss": 4.0678,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870771893710734e-05,
"loss": 4.0519,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862385946200214e-05,
"loss": 4.0573,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785401637749343e-05,
"loss": 4.0599,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784563042998291e-05,
"loss": 4.0607,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783724448247239e-05,
"loss": 4.0567,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782885853496187e-05,
"loss": 4.0595,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782047258745135e-05,
"loss": 4.0506,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781208663994083e-05,
"loss": 4.0562,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780370069243031e-05,
"loss": 4.0485,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779531474491979e-05,
"loss": 4.0477,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786945176213e-05,
"loss": 4.0604,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777855922870248e-05,
"loss": 4.0574,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777018965999569e-05,
"loss": 4.0546,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776180371248517e-05,
"loss": 4.0494,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775341776497465e-05,
"loss": 4.0543,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7745031817464134e-05,
"loss": 4.0511,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736645869953614e-05,
"loss": 4.0405,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728259922443094e-05,
"loss": 4.0581,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719873974932574e-05,
"loss": 4.0445,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711488027422054e-05,
"loss": 4.0518,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770311845871526e-05,
"loss": 4.037,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769473251120474e-05,
"loss": 4.0374,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768634656369422e-05,
"loss": 4.0339,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76779606161837e-05,
"loss": 4.0342,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766959104747691e-05,
"loss": 4.0334,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766120509996639e-05,
"loss": 4.047,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765281915245587e-05,
"loss": 4.0504,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764443320494535e-05,
"loss": 4.0365,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763606363623857e-05,
"loss": 4.029,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762767768872805e-05,
"loss": 4.0417,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761929174121753e-05,
"loss": 4.0405,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761090579370701e-05,
"loss": 4.0481,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760253622500022e-05,
"loss": 4.0424,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941502774897e-05,
"loss": 4.0344,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758576432997918e-05,
"loss": 4.0289,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757737838246866e-05,
"loss": 4.0387,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569008813761866e-05,
"loss": 4.0287,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560622866251346e-05,
"loss": 4.0326,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552236918740826e-05,
"loss": 4.0296,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543850971230306e-05,
"loss": 4.0211,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753548140252352e-05,
"loss": 4.0428,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527095455013e-05,
"loss": 4.0248,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751870950750248e-05,
"loss": 4.0194,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751032355999196e-05,
"loss": 4.0238,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501937612481435e-05,
"loss": 4.0196,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.028687477111816,
"eval_runtime": 316.7625,
"eval_samples_per_second": 1204.659,
"eval_steps_per_second": 37.646,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493551664970914e-05,
"loss": 4.0026,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485165717460394e-05,
"loss": 4.0197,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476779769949874e-05,
"loss": 4.0343,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468393822439354e-05,
"loss": 4.0155,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460007874928834e-05,
"loss": 4.0303,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451621927418314e-05,
"loss": 4.0075,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443235979907794e-05,
"loss": 4.0202,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434850032397274e-05,
"loss": 4.0016,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742648046369049e-05,
"loss": 4.0181,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741809451617997e-05,
"loss": 4.0157,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740970856866945e-05,
"loss": 4.0133,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740132262115893e-05,
"loss": 4.0229,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739295305245214e-05,
"loss": 4.0027,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738456710494162e-05,
"loss": 3.999,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.73761811574311e-05,
"loss": 3.9968,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736779520992058e-05,
"loss": 4.0049,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735940926241006e-05,
"loss": 4.0108,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735102331489954e-05,
"loss": 4.003,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734263736738902e-05,
"loss": 4.0059,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.73342514198785e-05,
"loss": 4.0252,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732586547236797e-05,
"loss": 4.0018,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731747952485746e-05,
"loss": 3.9946,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730909357734694e-05,
"loss": 4.0034,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300724008640154e-05,
"loss": 4.0092,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729233806112963e-05,
"loss": 3.9923,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728395211361911e-05,
"loss": 3.9975,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727556616610859e-05,
"loss": 3.9983,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.72671965974018e-05,
"loss": 3.9958,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258810649891277e-05,
"loss": 3.9806,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250424702380757e-05,
"loss": 3.9881,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724205513367397e-05,
"loss": 3.9886,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233669186163446e-05,
"loss": 3.9948,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225283238652926e-05,
"loss": 4.009,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721689729114241e-05,
"loss": 3.9861,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720851134363189e-05,
"loss": 3.9868,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720012539612137e-05,
"loss": 3.9968,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719173944861085e-05,
"loss": 3.98,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718335350110033e-05,
"loss": 3.9807,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717498393239354e-05,
"loss": 3.9748,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716659798488302e-05,
"loss": 3.9847,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.71582120373725e-05,
"loss": 3.9734,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714982608986198e-05,
"loss": 3.9955,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714145652115519e-05,
"loss": 3.9755,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713307057364467e-05,
"loss": 3.9858,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712468462613415e-05,
"loss": 3.9816,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711629867862363e-05,
"loss": 3.9791,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107929109916846e-05,
"loss": 3.9808,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099543162406326e-05,
"loss": 3.9669,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091157214895806e-05,
"loss": 3.9627,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082787646189015e-05,
"loss": 3.9833,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074401698678495e-05,
"loss": 3.9771,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7066015751167975e-05,
"loss": 3.964,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057629803657455e-05,
"loss": 3.9665,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.7049260234950664e-05,
"loss": 3.9755,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040874287440144e-05,
"loss": 3.9563,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032488339929624e-05,
"loss": 3.9778,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024102392419104e-05,
"loss": 3.9652,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015716444908584e-05,
"loss": 3.9656,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007330497398064e-05,
"loss": 3.9822,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998944549887544e-05,
"loss": 3.9584,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699055860237703e-05,
"loss": 3.9537,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698218903367024e-05,
"loss": 3.9649,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697380308615972e-05,
"loss": 3.9497,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.69654171386492e-05,
"loss": 3.9542,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695703119113868e-05,
"loss": 3.9682,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694864524362816e-05,
"loss": 3.9698,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694025929611763e-05,
"loss": 3.9549,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693187334860711e-05,
"loss": 3.9553,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692352015870406e-05,
"loss": 3.9432,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691513421119354e-05,
"loss": 3.965,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690674826368302e-05,
"loss": 3.9591,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.68983623161725e-05,
"loss": 3.966,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6889976368661984e-05,
"loss": 3.9608,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688159042115146e-05,
"loss": 3.9639,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687320447364094e-05,
"loss": 3.9711,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686481852613042e-05,
"loss": 3.9452,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685644895742363e-05,
"loss": 3.9571,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848063009913106e-05,
"loss": 3.9611,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839677062402586e-05,
"loss": 3.9442,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831291114892066e-05,
"loss": 3.965,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822905167381546e-05,
"loss": 3.96,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814519219871026e-05,
"loss": 3.9638,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806133272360506e-05,
"loss": 3.9623,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797747324849986e-05,
"loss": 3.9405,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.67893777561432e-05,
"loss": 3.9523,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678100818743641e-05,
"loss": 3.9507,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677262223992589e-05,
"loss": 3.9584,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676423629241537e-05,
"loss": 3.9495,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675585034490485e-05,
"loss": 3.9466,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674748077619806e-05,
"loss": 3.9544,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673909482868754e-05,
"loss": 3.9495,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673070888117702e-05,
"loss": 3.9355,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.67223229336665e-05,
"loss": 3.9432,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671393698615598e-05,
"loss": 3.9496,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670556741744919e-05,
"loss": 3.9572,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697181469938675e-05,
"loss": 3.947,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688795522428155e-05,
"loss": 3.9273,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680409574917635e-05,
"loss": 3.9413,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6672023627407115e-05,
"loss": 3.9476,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663654058700324e-05,
"loss": 3.9447,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655268111189804e-05,
"loss": 3.9425,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.6646882163679284e-05,
"loss": 3.9384,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.6638496216168764e-05,
"loss": 3.9258,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.6630110268658244e-05,
"loss": 3.9469,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662174069995145e-05,
"loss": 3.9216,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661335475244093e-05,
"loss": 3.9356,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660496880493041e-05,
"loss": 3.9306,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659658285741989e-05,
"loss": 3.9442,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658821328871311e-05,
"loss": 3.9275,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657982734120259e-05,
"loss": 3.9399,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657144139369207e-05,
"loss": 3.9293,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656305544618155e-05,
"loss": 3.9298,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655466949867103e-05,
"loss": 3.9333,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654629992996424e-05,
"loss": 3.925,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653791398245372e-05,
"loss": 3.9418,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.65295280349432e-05,
"loss": 3.9386,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652114208743268e-05,
"loss": 3.9352,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651275613992216e-05,
"loss": 3.9295,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650437019241164e-05,
"loss": 3.9345,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649598424490112e-05,
"loss": 3.9369,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648761467619433e-05,
"loss": 3.9178,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647922872868381e-05,
"loss": 3.9402,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470842781173294e-05,
"loss": 3.9288,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646245683366277e-05,
"loss": 3.9349,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645407088615225e-05,
"loss": 3.9228,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644568493864173e-05,
"loss": 3.926,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437298991131207e-05,
"loss": 3.9137,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428913043620687e-05,
"loss": 3.9212,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420543474913896e-05,
"loss": 3.9176,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412157527403376e-05,
"loss": 3.9337,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640378795869659e-05,
"loss": 3.9375,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395402011186065e-05,
"loss": 3.9249,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387016063675545e-05,
"loss": 3.9167,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637863011616503e-05,
"loss": 3.9275,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637026054745824e-05,
"loss": 3.9288,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636187459994772e-05,
"loss": 3.9335,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.63534886524372e-05,
"loss": 3.9295,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634510270492668e-05,
"loss": 3.9196,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633673313621989e-05,
"loss": 3.9244,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632834718870937e-05,
"loss": 3.9295,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631996124119885e-05,
"loss": 3.9163,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631157529368833e-05,
"loss": 3.9222,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630318934617781e-05,
"loss": 3.9183,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629481977747102e-05,
"loss": 3.9106,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.62864338299605e-05,
"loss": 3.9329,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6278047882449985e-05,
"loss": 3.9173,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.6269661934939465e-05,
"loss": 3.9117,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.6261275987428945e-05,
"loss": 3.9142,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.6252906418722154e-05,
"loss": 3.9092,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9539332389831543,
"eval_runtime": 304.2645,
"eval_samples_per_second": 1254.142,
"eval_steps_per_second": 39.193,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.5869192680625357e+17,
"trial_name": null,
"trial_params": null
}