mrigankraman-4090 / trainer_state.json
Vicki Boykis
remove old checkpoints
2791d7b
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.007712082262211,
"eval_steps": 15000,
"global_step": 2340,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 3.1914893617021277e-06,
"loss": 0.8544,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 6.3829787234042555e-06,
"loss": 0.8342,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 9.574468085106385e-06,
"loss": 0.8016,
"step": 30
},
{
"epoch": 0.05,
"learning_rate": 1.2765957446808511e-05,
"loss": 0.7802,
"step": 40
},
{
"epoch": 0.06,
"learning_rate": 1.5957446808510637e-05,
"loss": 0.7127,
"step": 50
},
{
"epoch": 0.08,
"learning_rate": 1.914893617021277e-05,
"loss": 0.6504,
"step": 60
},
{
"epoch": 0.09,
"learning_rate": 2.2340425531914894e-05,
"loss": 0.6011,
"step": 70
},
{
"epoch": 0.1,
"learning_rate": 2.5531914893617022e-05,
"loss": 0.6859,
"step": 80
},
{
"epoch": 0.12,
"learning_rate": 2.872340425531915e-05,
"loss": 0.5766,
"step": 90
},
{
"epoch": 0.13,
"learning_rate": 2.9999474091752356e-05,
"loss": 0.6617,
"step": 100
},
{
"epoch": 0.14,
"learning_rate": 2.9996260341563078e-05,
"loss": 0.6804,
"step": 110
},
{
"epoch": 0.15,
"learning_rate": 2.999012563764485e-05,
"loss": 0.5635,
"step": 120
},
{
"epoch": 0.17,
"learning_rate": 2.9981071174907998e-05,
"loss": 0.5021,
"step": 130
},
{
"epoch": 0.18,
"learning_rate": 2.9969098716969983e-05,
"loss": 0.575,
"step": 140
},
{
"epoch": 0.19,
"learning_rate": 2.995421059581191e-05,
"loss": 0.6085,
"step": 150
},
{
"epoch": 0.21,
"learning_rate": 2.993640971132428e-05,
"loss": 0.6241,
"step": 160
},
{
"epoch": 0.22,
"learning_rate": 2.991569953074218e-05,
"loss": 0.6405,
"step": 170
},
{
"epoch": 0.23,
"learning_rate": 2.9892084087969912e-05,
"loss": 0.6318,
"step": 180
},
{
"epoch": 0.24,
"learning_rate": 2.98655679827953e-05,
"loss": 0.5592,
"step": 190
},
{
"epoch": 0.26,
"learning_rate": 2.9836156379993726e-05,
"loss": 0.5625,
"step": 200
},
{
"epoch": 0.27,
"learning_rate": 2.980385500832215e-05,
"loss": 0.5857,
"step": 210
},
{
"epoch": 0.28,
"learning_rate": 2.9768670159403283e-05,
"loss": 0.6439,
"step": 220
},
{
"epoch": 0.3,
"learning_rate": 2.9730608686500093e-05,
"loss": 0.4829,
"step": 230
},
{
"epoch": 0.31,
"learning_rate": 2.9689678003180932e-05,
"loss": 0.5554,
"step": 240
},
{
"epoch": 0.32,
"learning_rate": 2.964588608187556e-05,
"loss": 0.5177,
"step": 250
},
{
"epoch": 0.33,
"learning_rate": 2.9599241452322243e-05,
"loss": 0.5375,
"step": 260
},
{
"epoch": 0.35,
"learning_rate": 2.9549753199906383e-05,
"loss": 0.5527,
"step": 270
},
{
"epoch": 0.36,
"learning_rate": 2.9497430963890838e-05,
"loss": 0.5166,
"step": 280
},
{
"epoch": 0.37,
"learning_rate": 2.9442284935538424e-05,
"loss": 0.5353,
"step": 290
},
{
"epoch": 0.39,
"learning_rate": 2.9384325856126867e-05,
"loss": 0.531,
"step": 300
},
{
"epoch": 0.4,
"learning_rate": 2.932356501485663e-05,
"loss": 0.5583,
"step": 310
},
{
"epoch": 0.41,
"learning_rate": 2.9260014246652e-05,
"loss": 0.5355,
"step": 320
},
{
"epoch": 0.42,
"learning_rate": 2.919368592985593e-05,
"loss": 0.5351,
"step": 330
},
{
"epoch": 0.44,
"learning_rate": 2.9124592983818963e-05,
"loss": 0.5349,
"step": 340
},
{
"epoch": 0.45,
"learning_rate": 2.9052748866382848e-05,
"loss": 0.5094,
"step": 350
},
{
"epoch": 0.46,
"learning_rate": 2.8978167571259202e-05,
"loss": 0.538,
"step": 360
},
{
"epoch": 0.48,
"learning_rate": 2.8900863625303867e-05,
"loss": 0.5041,
"step": 370
},
{
"epoch": 0.49,
"learning_rate": 2.8820852085687373e-05,
"loss": 0.4906,
"step": 380
},
{
"epoch": 0.5,
"learning_rate": 2.873814853696211e-05,
"loss": 0.5246,
"step": 390
},
{
"epoch": 0.51,
"learning_rate": 2.8652769088026798e-05,
"loss": 0.5484,
"step": 400
},
{
"epoch": 0.53,
"learning_rate": 2.856473036898882e-05,
"loss": 0.4325,
"step": 410
},
{
"epoch": 0.54,
"learning_rate": 2.847404952792501e-05,
"loss": 0.4965,
"step": 420
},
{
"epoch": 0.55,
"learning_rate": 2.8380744227541592e-05,
"loss": 0.509,
"step": 430
},
{
"epoch": 0.57,
"learning_rate": 2.8284832641733857e-05,
"loss": 0.5052,
"step": 440
},
{
"epoch": 0.58,
"learning_rate": 2.8186333452046256e-05,
"loss": 0.5119,
"step": 450
},
{
"epoch": 0.59,
"learning_rate": 2.808526584403364e-05,
"loss": 0.4206,
"step": 460
},
{
"epoch": 0.6,
"learning_rate": 2.7981649503524323e-05,
"loss": 0.5834,
"step": 470
},
{
"epoch": 0.62,
"learning_rate": 2.7875504612785717e-05,
"loss": 0.4789,
"step": 480
},
{
"epoch": 0.63,
"learning_rate": 2.7766851846593215e-05,
"loss": 0.4196,
"step": 490
},
{
"epoch": 0.64,
"learning_rate": 2.7655712368203213e-05,
"loss": 0.4959,
"step": 500
},
{
"epoch": 0.66,
"learning_rate": 2.7542107825230944e-05,
"loss": 0.4784,
"step": 510
},
{
"epoch": 0.67,
"learning_rate": 2.7426060345433984e-05,
"loss": 0.52,
"step": 520
},
{
"epoch": 0.68,
"learning_rate": 2.7307592532402248e-05,
"loss": 0.517,
"step": 530
},
{
"epoch": 0.69,
"learning_rate": 2.7186727461155252e-05,
"loss": 0.4751,
"step": 540
},
{
"epoch": 0.71,
"learning_rate": 2.706348867364763e-05,
"loss": 0.4711,
"step": 550
},
{
"epoch": 0.72,
"learning_rate": 2.6937900174183637e-05,
"loss": 0.4961,
"step": 560
},
{
"epoch": 0.73,
"learning_rate": 2.6809986424741623e-05,
"loss": 0.5276,
"step": 570
},
{
"epoch": 0.75,
"learning_rate": 2.6679772340209362e-05,
"loss": 0.5341,
"step": 580
},
{
"epoch": 0.76,
"learning_rate": 2.6547283283531153e-05,
"loss": 0.5208,
"step": 590
},
{
"epoch": 0.77,
"learning_rate": 2.6412545060767663e-05,
"loss": 0.4345,
"step": 600
},
{
"epoch": 0.78,
"learning_rate": 2.6275583916069456e-05,
"loss": 0.4814,
"step": 610
},
{
"epoch": 0.8,
"learning_rate": 2.6136426526565168e-05,
"loss": 0.4222,
"step": 620
},
{
"epoch": 0.81,
"learning_rate": 2.5995099997165395e-05,
"loss": 0.5428,
"step": 630
},
{
"epoch": 0.82,
"learning_rate": 2.585163185528322e-05,
"loss": 0.4636,
"step": 640
},
{
"epoch": 0.84,
"learning_rate": 2.5706050045472446e-05,
"loss": 0.4903,
"step": 650
},
{
"epoch": 0.85,
"learning_rate": 2.55583829239846e-05,
"loss": 0.4702,
"step": 660
},
{
"epoch": 0.86,
"learning_rate": 2.540865925324574e-05,
"loss": 0.5231,
"step": 670
},
{
"epoch": 0.87,
"learning_rate": 2.5256908196254126e-05,
"loss": 0.5089,
"step": 680
},
{
"epoch": 0.89,
"learning_rate": 2.510315931089991e-05,
"loss": 0.4572,
"step": 690
},
{
"epoch": 0.9,
"learning_rate": 2.494744254420787e-05,
"loss": 0.471,
"step": 700
},
{
"epoch": 0.91,
"learning_rate": 2.478978822650436e-05,
"loss": 0.3929,
"step": 710
},
{
"epoch": 0.93,
"learning_rate": 2.4630227065509627e-05,
"loss": 0.476,
"step": 720
},
{
"epoch": 0.94,
"learning_rate": 2.446879014035656e-05,
"loss": 0.5348,
"step": 730
},
{
"epoch": 0.95,
"learning_rate": 2.4305508895537186e-05,
"loss": 0.4399,
"step": 740
},
{
"epoch": 0.96,
"learning_rate": 2.4140415134777895e-05,
"loss": 0.4443,
"step": 750
},
{
"epoch": 0.98,
"learning_rate": 2.3973541014844783e-05,
"loss": 0.5046,
"step": 760
},
{
"epoch": 0.99,
"learning_rate": 2.380491903928019e-05,
"loss": 0.4318,
"step": 770
},
{
"epoch": 1.0,
"learning_rate": 2.3634582052071682e-05,
"loss": 0.5244,
"step": 780
},
{
"epoch": 1.02,
"learning_rate": 2.3462563231254764e-05,
"loss": 0.5364,
"step": 790
},
{
"epoch": 1.03,
"learning_rate": 2.328889608245048e-05,
"loss": 0.5278,
"step": 800
},
{
"epoch": 1.04,
"learning_rate": 2.3113614432339247e-05,
"loss": 0.5021,
"step": 810
},
{
"epoch": 1.05,
"learning_rate": 2.2936752422072105e-05,
"loss": 0.4363,
"step": 820
},
{
"epoch": 1.07,
"learning_rate": 2.275834450062077e-05,
"loss": 0.4657,
"step": 830
},
{
"epoch": 1.08,
"learning_rate": 2.2578425418067713e-05,
"loss": 0.4355,
"step": 840
},
{
"epoch": 1.09,
"learning_rate": 2.239703021883754e-05,
"loss": 0.402,
"step": 850
},
{
"epoch": 1.11,
"learning_rate": 2.221419423487113e-05,
"loss": 0.5007,
"step": 860
},
{
"epoch": 1.12,
"learning_rate": 2.202995307874367e-05,
"loss": 0.4388,
"step": 870
},
{
"epoch": 1.13,
"learning_rate": 2.1844342636728133e-05,
"loss": 0.5182,
"step": 880
},
{
"epoch": 1.14,
"learning_rate": 2.165739906180535e-05,
"loss": 0.5118,
"step": 890
},
{
"epoch": 1.16,
"learning_rate": 2.1469158766622195e-05,
"loss": 0.3888,
"step": 900
},
{
"epoch": 1.17,
"learning_rate": 2.127965841639918e-05,
"loss": 0.3978,
"step": 910
},
{
"epoch": 1.18,
"learning_rate": 2.1088934921788813e-05,
"loss": 0.5071,
"step": 920
},
{
"epoch": 1.2,
"learning_rate": 2.0897025431686234e-05,
"loss": 0.4999,
"step": 930
},
{
"epoch": 1.21,
"learning_rate": 2.0703967325993373e-05,
"loss": 0.4734,
"step": 940
},
{
"epoch": 1.22,
"learning_rate": 2.0509798208338107e-05,
"loss": 0.5421,
"step": 950
},
{
"epoch": 1.23,
"learning_rate": 2.0314555898749934e-05,
"loss": 0.4867,
"step": 960
},
{
"epoch": 1.25,
"learning_rate": 2.0118278426293376e-05,
"loss": 0.4662,
"step": 970
},
{
"epoch": 1.26,
"learning_rate": 1.9921004021660762e-05,
"loss": 0.4709,
"step": 980
},
{
"epoch": 1.27,
"learning_rate": 1.972277110972567e-05,
"loss": 0.5178,
"step": 990
},
{
"epoch": 1.29,
"learning_rate": 1.952361830205859e-05,
"loss": 0.5188,
"step": 1000
},
{
"epoch": 1.3,
"learning_rate": 1.932358438940622e-05,
"loss": 0.412,
"step": 1010
},
{
"epoch": 1.31,
"learning_rate": 1.9122708334135816e-05,
"loss": 0.4236,
"step": 1020
},
{
"epoch": 1.32,
"learning_rate": 1.8921029262646187e-05,
"loss": 0.4594,
"step": 1030
},
{
"epoch": 1.34,
"learning_rate": 1.8718586457746694e-05,
"loss": 0.4521,
"step": 1040
},
{
"epoch": 1.35,
"learning_rate": 1.8515419351005745e-05,
"loss": 0.4427,
"step": 1050
},
{
"epoch": 1.36,
"learning_rate": 1.8311567515070438e-05,
"loss": 0.4509,
"step": 1060
},
{
"epoch": 1.38,
"learning_rate": 1.8107070655958584e-05,
"loss": 0.4548,
"step": 1070
},
{
"epoch": 1.39,
"learning_rate": 1.7901968605324847e-05,
"loss": 0.479,
"step": 1080
},
{
"epoch": 1.4,
"learning_rate": 1.7696301312702383e-05,
"loss": 0.4867,
"step": 1090
},
{
"epoch": 1.41,
"learning_rate": 1.7490108837721493e-05,
"loss": 0.4894,
"step": 1100
},
{
"epoch": 1.43,
"learning_rate": 1.7283431342306884e-05,
"loss": 0.4646,
"step": 1110
},
{
"epoch": 1.44,
"learning_rate": 1.7076309082854963e-05,
"loss": 0.4802,
"step": 1120
},
{
"epoch": 1.45,
"learning_rate": 1.686878240239274e-05,
"loss": 0.4287,
"step": 1130
},
{
"epoch": 1.47,
"learning_rate": 1.666089172271988e-05,
"loss": 0.4808,
"step": 1140
},
{
"epoch": 1.48,
"learning_rate": 1.6452677536535375e-05,
"loss": 0.4639,
"step": 1150
},
{
"epoch": 1.49,
"learning_rate": 1.624418039955042e-05,
"loss": 0.4263,
"step": 1160
},
{
"epoch": 1.5,
"learning_rate": 1.6035440922589054e-05,
"loss": 0.492,
"step": 1170
},
{
"epoch": 1.52,
"learning_rate": 1.5826499763677982e-05,
"loss": 0.487,
"step": 1180
},
{
"epoch": 1.53,
"learning_rate": 1.561739762012729e-05,
"loss": 0.3992,
"step": 1190
},
{
"epoch": 1.54,
"learning_rate": 1.5408175220603464e-05,
"loss": 0.4221,
"step": 1200
},
{
"epoch": 1.56,
"learning_rate": 1.5198873317196304e-05,
"loss": 0.4954,
"step": 1210
},
{
"epoch": 1.57,
"learning_rate": 1.4989532677481273e-05,
"loss": 0.4486,
"step": 1220
},
{
"epoch": 1.58,
"learning_rate": 1.4780194076578861e-05,
"loss": 0.4657,
"step": 1230
},
{
"epoch": 1.59,
"learning_rate": 1.4570898289212423e-05,
"loss": 0.3984,
"step": 1240
},
{
"epoch": 1.61,
"learning_rate": 1.4361686081766154e-05,
"loss": 0.512,
"step": 1250
},
{
"epoch": 1.62,
"learning_rate": 1.4152598204344656e-05,
"loss": 0.4178,
"step": 1260
},
{
"epoch": 1.63,
"learning_rate": 1.3943675382835672e-05,
"loss": 0.3971,
"step": 1270
},
{
"epoch": 1.65,
"learning_rate": 1.3734958310977542e-05,
"loss": 0.4343,
"step": 1280
},
{
"epoch": 1.66,
"learning_rate": 1.3526487642432953e-05,
"loss": 0.4675,
"step": 1290
},
{
"epoch": 1.67,
"learning_rate": 1.331830398287044e-05,
"loss": 0.469,
"step": 1300
},
{
"epoch": 1.68,
"learning_rate": 1.3110447882055255e-05,
"loss": 0.4457,
"step": 1310
},
{
"epoch": 1.7,
"learning_rate": 1.290295982595117e-05,
"loss": 0.4495,
"step": 1320
},
{
"epoch": 1.71,
"learning_rate": 1.2695880228834631e-05,
"loss": 0.4329,
"step": 1330
},
{
"epoch": 1.72,
"learning_rate": 1.2489249425422943e-05,
"loss": 0.4681,
"step": 1340
},
{
"epoch": 1.74,
"learning_rate": 1.2283107663017894e-05,
"loss": 0.4718,
"step": 1350
},
{
"epoch": 1.75,
"learning_rate": 1.207749509366645e-05,
"loss": 0.5212,
"step": 1360
},
{
"epoch": 1.76,
"learning_rate": 1.1872451766340002e-05,
"loss": 0.4652,
"step": 1370
},
{
"epoch": 1.77,
"learning_rate": 1.1668017619133619e-05,
"loss": 0.3881,
"step": 1380
},
{
"epoch": 1.79,
"learning_rate": 1.1464232471487033e-05,
"loss": 0.4384,
"step": 1390
},
{
"epoch": 1.8,
"learning_rate": 1.126113601642859e-05,
"loss": 0.4238,
"step": 1400
},
{
"epoch": 1.81,
"learning_rate": 1.1058767812843915e-05,
"loss": 0.4394,
"step": 1410
},
{
"epoch": 1.83,
"learning_rate": 1.0857167277770699e-05,
"loss": 0.4405,
"step": 1420
},
{
"epoch": 1.84,
"learning_rate": 1.0656373678721051e-05,
"loss": 0.4231,
"step": 1430
},
{
"epoch": 1.85,
"learning_rate": 1.0456426126033047e-05,
"loss": 0.4997,
"step": 1440
},
{
"epoch": 1.86,
"learning_rate": 1.0257363565252867e-05,
"loss": 0.4339,
"step": 1450
},
{
"epoch": 1.88,
"learning_rate": 1.0059224769549022e-05,
"loss": 0.4579,
"step": 1460
},
{
"epoch": 1.89,
"learning_rate": 9.862048332160156e-06,
"loss": 0.491,
"step": 1470
},
{
"epoch": 1.9,
"learning_rate": 9.665872658877904e-06,
"loss": 0.4215,
"step": 1480
},
{
"epoch": 1.92,
"learning_rate": 9.470735960566274e-06,
"loss": 0.3476,
"step": 1490
},
{
"epoch": 1.93,
"learning_rate": 9.276676245718955e-06,
"loss": 0.4651,
"step": 1500
},
{
"epoch": 1.94,
"learning_rate": 9.083731313056076e-06,
"loss": 0.4833,
"step": 1510
},
{
"epoch": 1.95,
"learning_rate": 8.891938744161832e-06,
"loss": 0.3936,
"step": 1520
},
{
"epoch": 1.97,
"learning_rate": 8.701335896164365e-06,
"loss": 0.4424,
"step": 1530
},
{
"epoch": 1.98,
"learning_rate": 8.511959894459403e-06,
"loss": 0.4624,
"step": 1540
},
{
"epoch": 1.99,
"learning_rate": 8.32384762547901e-06,
"loss": 0.3945,
"step": 1550
},
{
"epoch": 2.01,
"learning_rate": 8.13703572950691e-06,
"loss": 0.5025,
"step": 1560
},
{
"epoch": 2.02,
"learning_rate": 7.951560593541705e-06,
"loss": 0.5045,
"step": 1570
},
{
"epoch": 2.03,
"learning_rate": 7.767458344209473e-06,
"loss": 0.5225,
"step": 1580
},
{
"epoch": 2.04,
"learning_rate": 7.584764840727073e-06,
"loss": 0.4701,
"step": 1590
},
{
"epoch": 2.06,
"learning_rate": 7.403515667917537e-06,
"loss": 0.3575,
"step": 1600
},
{
"epoch": 2.07,
"learning_rate": 7.223746129278879e-06,
"loss": 0.447,
"step": 1610
},
{
"epoch": 2.08,
"learning_rate": 7.045491240107726e-06,
"loss": 0.4191,
"step": 1620
},
{
"epoch": 2.1,
"learning_rate": 6.868785720679093e-06,
"loss": 0.3947,
"step": 1630
},
{
"epoch": 2.11,
"learning_rate": 6.6936639894836e-06,
"loss": 0.4557,
"step": 1640
},
{
"epoch": 2.12,
"learning_rate": 6.520160156523481e-06,
"loss": 0.404,
"step": 1650
},
{
"epoch": 2.13,
"learning_rate": 6.348308016668679e-06,
"loss": 0.4951,
"step": 1660
},
{
"epoch": 2.15,
"learning_rate": 6.178141043074322e-06,
"loss": 0.4677,
"step": 1670
},
{
"epoch": 2.16,
"learning_rate": 6.0096923806608595e-06,
"loss": 0.3628,
"step": 1680
},
{
"epoch": 2.17,
"learning_rate": 5.842994839658134e-06,
"loss": 0.4757,
"step": 1690
},
{
"epoch": 2.19,
"learning_rate": 5.6780808892146444e-06,
"loss": 0.387,
"step": 1700
},
{
"epoch": 2.2,
"learning_rate": 5.514982651073259e-06,
"loss": 0.4685,
"step": 1710
},
{
"epoch": 2.21,
"learning_rate": 5.3537318933145445e-06,
"loss": 0.4819,
"step": 1720
},
{
"epoch": 2.22,
"learning_rate": 5.19436002416905e-06,
"loss": 0.4856,
"step": 1730
},
{
"epoch": 2.24,
"learning_rate": 5.036898085899639e-06,
"loss": 0.4924,
"step": 1740
},
{
"epoch": 2.25,
"learning_rate": 4.881376748755111e-06,
"loss": 0.4058,
"step": 1750
},
{
"epoch": 2.26,
"learning_rate": 4.727826304996294e-06,
"loss": 0.4738,
"step": 1760
},
{
"epoch": 2.28,
"learning_rate": 4.576276662995751e-06,
"loss": 0.519,
"step": 1770
},
{
"epoch": 2.29,
"learning_rate": 4.426757341412246e-06,
"loss": 0.4648,
"step": 1780
},
{
"epoch": 2.3,
"learning_rate": 4.279297463441161e-06,
"loss": 0.3798,
"step": 1790
},
{
"epoch": 2.31,
"learning_rate": 4.133925751141913e-06,
"loss": 0.4013,
"step": 1800
},
{
"epoch": 2.33,
"learning_rate": 3.990670519843484e-06,
"loss": 0.4445,
"step": 1810
},
{
"epoch": 2.34,
"learning_rate": 3.849559672629211e-06,
"loss": 0.4292,
"step": 1820
},
{
"epoch": 2.35,
"learning_rate": 3.7106206949018525e-06,
"loss": 0.4329,
"step": 1830
},
{
"epoch": 2.37,
"learning_rate": 3.5738806490300157e-06,
"loss": 0.4456,
"step": 1840
},
{
"epoch": 2.38,
"learning_rate": 3.439366169076979e-06,
"loss": 0.4048,
"step": 1850
},
{
"epoch": 2.39,
"learning_rate": 3.307103455612942e-06,
"loss": 0.4805,
"step": 1860
},
{
"epoch": 2.4,
"learning_rate": 3.1771182706117107e-06,
"loss": 0.4863,
"step": 1870
},
{
"epoch": 2.42,
"learning_rate": 3.049435932432809e-06,
"loss": 0.4468,
"step": 1880
},
{
"epoch": 2.43,
"learning_rate": 2.9240813108900007e-06,
"loss": 0.4431,
"step": 1890
},
{
"epoch": 2.44,
"learning_rate": 2.801078822407166e-06,
"loss": 0.4527,
"step": 1900
},
{
"epoch": 2.46,
"learning_rate": 2.68045242526253e-06,
"loss": 0.4331,
"step": 1910
},
{
"epoch": 2.47,
"learning_rate": 2.562225614922054e-06,
"loss": 0.4499,
"step": 1920
},
{
"epoch": 2.48,
"learning_rate": 2.446421419463053e-06,
"loss": 0.4549,
"step": 1930
},
{
"epoch": 2.49,
"learning_rate": 2.333062395088795e-06,
"loss": 0.4125,
"step": 1940
},
{
"epoch": 2.51,
"learning_rate": 2.222170621735036e-06,
"loss": 0.4973,
"step": 1950
},
{
"epoch": 2.52,
"learning_rate": 2.1137676987693256e-06,
"loss": 0.4298,
"step": 1960
},
{
"epoch": 2.53,
"learning_rate": 2.0078747407838893e-06,
"loss": 0.4095,
"step": 1970
},
{
"epoch": 2.54,
"learning_rate": 1.90451237348297e-06,
"loss": 0.3815,
"step": 1980
},
{
"epoch": 2.56,
"learning_rate": 1.8037007296653558e-06,
"loss": 0.4799,
"step": 1990
},
{
"epoch": 2.57,
"learning_rate": 1.7054594453029748e-06,
"loss": 0.4514,
"step": 2000
},
{
"epoch": 2.58,
"learning_rate": 1.6098076557161873e-06,
"loss": 0.4336,
"step": 2010
},
{
"epoch": 2.6,
"learning_rate": 1.5167639918466492e-06,
"loss": 0.433,
"step": 2020
},
{
"epoch": 2.61,
"learning_rate": 1.426346576628394e-06,
"loss": 0.4462,
"step": 2030
},
{
"epoch": 2.62,
"learning_rate": 1.3385730214578711e-06,
"loss": 0.4031,
"step": 2040
},
{
"epoch": 2.63,
"learning_rate": 1.253460422763622e-06,
"loss": 0.4046,
"step": 2050
},
{
"epoch": 2.65,
"learning_rate": 1.1710253586762516e-06,
"loss": 0.4105,
"step": 2060
},
{
"epoch": 2.66,
"learning_rate": 1.0912838857993612e-06,
"loss": 0.4747,
"step": 2070
},
{
"epoch": 2.67,
"learning_rate": 1.0142515360820698e-06,
"loss": 0.4577,
"step": 2080
},
{
"epoch": 2.69,
"learning_rate": 9.399433137937074e-07,
"loss": 0.4083,
"step": 2090
},
{
"epoch": 2.7,
"learning_rate": 8.683736926013108e-07,
"loss": 0.4248,
"step": 2100
},
{
"epoch": 2.71,
"learning_rate": 7.995566127504644e-07,
"loss": 0.4173,
"step": 2110
},
{
"epoch": 2.72,
"learning_rate": 7.335054783500128e-07,
"loss": 0.4909,
"step": 2120
},
{
"epoch": 2.74,
"learning_rate": 6.702331547612523e-07,
"loss": 0.4548,
"step": 2130
},
{
"epoch": 2.75,
"learning_rate": 6.097519660920137e-07,
"loss": 0.486,
"step": 2140
},
{
"epoch": 2.76,
"learning_rate": 5.520736927961911e-07,
"loss": 0.4523,
"step": 2150
},
{
"epoch": 2.78,
"learning_rate": 4.972095693791673e-07,
"loss": 0.3658,
"step": 2160
},
{
"epoch": 2.79,
"learning_rate": 4.451702822095588e-07,
"loss": 0.4309,
"step": 2170
},
{
"epoch": 2.8,
"learning_rate": 3.959659674377414e-07,
"loss": 0.407,
"step": 2180
},
{
"epoch": 2.81,
"learning_rate": 3.496062090215424e-07,
"loss": 0.4581,
"step": 2190
},
{
"epoch": 2.83,
"learning_rate": 3.0610003685949073e-07,
"loss": 0.4145,
"step": 2200
},
{
"epoch": 2.84,
"learning_rate": 2.6545592503199046e-07,
"loss": 0.44,
"step": 2210
},
{
"epoch": 2.85,
"learning_rate": 2.2768179015073443e-07,
"loss": 0.4814,
"step": 2220
},
{
"epoch": 2.87,
"learning_rate": 1.9278498981672444e-07,
"loss": 0.4276,
"step": 2230
},
{
"epoch": 2.88,
"learning_rate": 1.607723211871709e-07,
"loss": 0.4293,
"step": 2240
},
{
"epoch": 2.89,
"learning_rate": 1.3165001965153854e-07,
"loss": 0.4662,
"step": 2250
},
{
"epoch": 2.9,
"learning_rate": 1.054237576170397e-07,
"loss": 0.4045,
"step": 2260
},
{
"epoch": 2.92,
"learning_rate": 8.209864340375795e-08,
"loss": 0.4039,
"step": 2270
},
{
"epoch": 2.93,
"learning_rate": 6.167922024965744e-08,
"loss": 0.4408,
"step": 2280
},
{
"epoch": 2.94,
"learning_rate": 4.416946542566247e-08,
"loss": 0.4574,
"step": 2290
},
{
"epoch": 2.96,
"learning_rate": 2.9572789460963756e-08,
"loss": 0.4278,
"step": 2300
},
{
"epoch": 2.97,
"learning_rate": 1.789203547871987e-08,
"loss": 0.4004,
"step": 2310
},
{
"epoch": 2.98,
"learning_rate": 9.129478642283528e-09,
"loss": 0.4565,
"step": 2320
},
{
"epoch": 2.99,
"learning_rate": 3.2868257120344247e-09,
"loss": 0.4554,
"step": 2330
},
{
"epoch": 3.01,
"learning_rate": 3.65214712955142e-10,
"loss": 0.4397,
"step": 2340
}
],
"logging_steps": 10,
"max_steps": 2345,
"num_train_epochs": 4,
"save_steps": 260,
"total_flos": 1.340869517825833e+18,
"trial_name": null,
"trial_params": null
}