abhinavp's picture
Training in progress, epoch 1, checkpoint
e130169 verified
{
"best_metric": 4.030747413635254,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/transformer/1/checkpoints/checkpoint-152640",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 152640,
"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": 10.9931,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8206,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.2067,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.0045,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8356,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7277,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6144,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5429,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4633,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4028,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.364,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.316,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.269,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 5.2209,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 5.1951,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 5.1482,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1226,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0968,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.064,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0333,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0177,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.986,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9694,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9416,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9363,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.901,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8872,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8597,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8517,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8274,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8213,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.8086,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7926,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.7812,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 4.7671,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970659010995419e-05,
"loss": 4.7526,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969820416244367e-05,
"loss": 4.7505,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7196,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7092,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6879,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6908,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6757,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6789,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 4.6558,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6507,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6451,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6392,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6264,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6105,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.6,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.6196,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.6088,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.5851,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5728,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5805,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5585,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5683,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5391,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 4.5604,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5444,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5224,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5168,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 4.53,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 4.4904,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.5044,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5108,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.495,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 4.4886,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.471,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.4701,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4657,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.483,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.458,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.468,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.4616,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4608,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4439,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4426,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4391,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.435,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4266,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4196,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 4.4218,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 4.4218,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.4004,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.4067,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 4.4066,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 4.4098,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3933,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3914,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3841,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3783,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3791,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 4.3816,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3752,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3825,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3724,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3567,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3554,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3648,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3604,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3596,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3484,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3395,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3523,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3292,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3351,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3313,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3313,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.321,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3209,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.315,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.322,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3163,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3067,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3196,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.323,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.3104,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.2994,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.2952,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2948,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.3004,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.2969,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2846,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2939,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2869,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2863,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2799,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2802,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2728,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.2827,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2813,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2799,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2573,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.2724,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.2666,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.2693,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.2594,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2672,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2572,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2737,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2439,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2614,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.2468,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.2432,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2471,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.2341,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.2379,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.2444,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.2329,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.200936317443848,
"eval_runtime": 303.3774,
"eval_samples_per_second": 1257.81,
"eval_steps_per_second": 39.307,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.2284,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.2245,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2383,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.2284,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.2377,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.2149,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2172,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.2077,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2168,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.2138,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.2097,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.2144,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.1946,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.2068,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.1924,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.193,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.1975,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.1908,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.1948,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.2094,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.1843,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.1883,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.1875,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.1935,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.1843,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.1848,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.1704,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.1762,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.1656,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.175,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.1702,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.1736,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.1779,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.1655,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.1719,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.1682,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.1574,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.1509,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.1432,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.1506,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.1483,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.1594,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.1446,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.1449,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.1496,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.1418,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.1443,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.1306,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.1282,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.152,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.1481,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.131,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.1331,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.1391,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.1196,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.1384,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.1138,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.1401,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.1346,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.1165,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823958979613631e-05,
"loss": 4.1145,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823120384862579e-05,
"loss": 4.1289,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822281790111527e-05,
"loss": 4.0973,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821443195360475e-05,
"loss": 4.1129,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.1245,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.1161,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.1088,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.0975,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817255135246334e-05,
"loss": 4.1041,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816416540495282e-05,
"loss": 4.1054,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155779457442305e-05,
"loss": 4.1117,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147393509931785e-05,
"loss": 4.1015,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.1116,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.1126,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122235667400224e-05,
"loss": 4.1107,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.0946,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.1032,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097094203672393e-05,
"loss": 4.1025,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.8088708256161873e-05,
"loss": 4.0981,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.0955,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.0918,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806356679243404e-05,
"loss": 4.1002,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805518084492352e-05,
"loss": 4.095,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046794897413e-05,
"loss": 4.0801,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803840894990248e-05,
"loss": 4.0878,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.80300393811957e-05,
"loss": 4.0892,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802165343368518e-05,
"loss": 4.0959,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.0873,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800488153866413e-05,
"loss": 4.0824,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799649559115361e-05,
"loss": 4.0816,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798812602244683e-05,
"loss": 4.0728,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.79797400749363e-05,
"loss": 4.0769,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.0861,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796296817991526e-05,
"loss": 4.0831,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954598611208476e-05,
"loss": 4.0915,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946212663697956e-05,
"loss": 4.081,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937826716187436e-05,
"loss": 4.0724,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929440768676916e-05,
"loss": 4.071,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921054821166396e-05,
"loss": 4.0783,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912685252459605e-05,
"loss": 4.0827,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904299304949085e-05,
"loss": 4.082,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895913357438565e-05,
"loss": 4.0721,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887527409928045e-05,
"loss": 4.0617,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879157841221254e-05,
"loss": 4.0815,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870771893710734e-05,
"loss": 4.0601,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786240232500395e-05,
"loss": 4.0673,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785401637749343e-05,
"loss": 4.0671,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784563042998291e-05,
"loss": 4.0657,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783724448247239e-05,
"loss": 4.0545,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782885853496187e-05,
"loss": 4.0638,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782047258745135e-05,
"loss": 4.0539,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781208663994083e-05,
"loss": 4.0633,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780370069243031e-05,
"loss": 4.0609,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779531474491979e-05,
"loss": 4.0529,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786945176213e-05,
"loss": 4.0737,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777855922870248e-05,
"loss": 4.072,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777017328119196e-05,
"loss": 4.064,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776178733368144e-05,
"loss": 4.0552,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775340138617092e-05,
"loss": 4.0483,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7745031817464134e-05,
"loss": 4.0548,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736645869953614e-05,
"loss": 4.0513,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728259922443094e-05,
"loss": 4.061,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719873974932574e-05,
"loss": 4.043,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771150440622578e-05,
"loss": 4.0527,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770311845871526e-05,
"loss": 4.0543,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769473251120474e-05,
"loss": 4.0552,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768634656369422e-05,
"loss": 4.0429,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767797699498743e-05,
"loss": 4.0489,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766959104747691e-05,
"loss": 4.0479,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766120509996639e-05,
"loss": 4.0496,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765281915245587e-05,
"loss": 4.0541,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764444958374909e-05,
"loss": 4.0545,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763606363623857e-05,
"loss": 4.0322,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762767768872805e-05,
"loss": 4.0452,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761930812002126e-05,
"loss": 4.0486,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761092217251074e-05,
"loss": 4.0459,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760253622500022e-05,
"loss": 4.0417,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941502774897e-05,
"loss": 4.0482,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758576432997918e-05,
"loss": 4.0414,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757737838246866e-05,
"loss": 4.0585,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7568992434958137e-05,
"loss": 4.0316,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560622866251346e-05,
"loss": 4.0462,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552236918740826e-05,
"loss": 4.0367,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543850971230306e-05,
"loss": 4.0306,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753548140252352e-05,
"loss": 4.0378,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527095455013e-05,
"loss": 4.0289,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751870950750248e-05,
"loss": 4.0302,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751032355999196e-05,
"loss": 4.0317,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501937612481435e-05,
"loss": 4.0289,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.030747413635254,
"eval_runtime": 317.6174,
"eval_samples_per_second": 1201.417,
"eval_steps_per_second": 37.545,
"step": 152640
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.0423436420559053e+17,
"trial_name": null,
"trial_params": null
}