wangrongsheng's picture
commit from root
2329af4
raw
history blame contribute delete
No virus
36.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.21234803843499495,
"global_step": 3000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998454568244e-05,
"loss": 1.3539,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 4.9999938182748876e-05,
"loss": 1.1833,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 4.9999870029288556e-05,
"loss": 1.173,
"step": 30
},
{
"epoch": 0.0,
"learning_rate": 4.999976494017406e-05,
"loss": 1.0772,
"step": 40
},
{
"epoch": 0.0,
"learning_rate": 4.999962894271507e-05,
"loss": 1.0715,
"step": 50
},
{
"epoch": 0.0,
"learning_rate": 4.9999462037079705e-05,
"loss": 1.0268,
"step": 60
},
{
"epoch": 0.0,
"learning_rate": 4.999926422347434e-05,
"loss": 0.9807,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 4.999903550214352e-05,
"loss": 0.9862,
"step": 80
},
{
"epoch": 0.01,
"learning_rate": 4.999877587337004e-05,
"loss": 0.9725,
"step": 90
},
{
"epoch": 0.01,
"learning_rate": 4.999848533747488e-05,
"loss": 0.9993,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 4.999816389481725e-05,
"loss": 0.9596,
"step": 110
},
{
"epoch": 0.01,
"learning_rate": 4.999781154579456e-05,
"loss": 0.979,
"step": 120
},
{
"epoch": 0.01,
"learning_rate": 4.9997428290842444e-05,
"loss": 0.9748,
"step": 130
},
{
"epoch": 0.01,
"learning_rate": 4.999701413043471e-05,
"loss": 0.9309,
"step": 140
},
{
"epoch": 0.01,
"learning_rate": 4.999656906508344e-05,
"loss": 0.9143,
"step": 150
},
{
"epoch": 0.01,
"learning_rate": 4.999609309533887e-05,
"loss": 0.9439,
"step": 160
},
{
"epoch": 0.01,
"learning_rate": 4.999558622178947e-05,
"loss": 0.9286,
"step": 170
},
{
"epoch": 0.01,
"learning_rate": 4.99950484450619e-05,
"loss": 0.9544,
"step": 180
},
{
"epoch": 0.01,
"learning_rate": 4.999447976582104e-05,
"loss": 0.9355,
"step": 190
},
{
"epoch": 0.01,
"learning_rate": 4.999388018476998e-05,
"loss": 0.9154,
"step": 200
},
{
"epoch": 0.01,
"learning_rate": 4.999324970265001e-05,
"loss": 0.9326,
"step": 210
},
{
"epoch": 0.02,
"learning_rate": 4.999258832024061e-05,
"loss": 0.9215,
"step": 220
},
{
"epoch": 0.02,
"learning_rate": 4.99918960383595e-05,
"loss": 0.9281,
"step": 230
},
{
"epoch": 0.02,
"learning_rate": 4.9991172857862555e-05,
"loss": 0.935,
"step": 240
},
{
"epoch": 0.02,
"learning_rate": 4.99904187796439e-05,
"loss": 0.941,
"step": 250
},
{
"epoch": 0.02,
"learning_rate": 4.9989633804635814e-05,
"loss": 0.9377,
"step": 260
},
{
"epoch": 0.02,
"learning_rate": 4.9988817933808814e-05,
"loss": 0.9014,
"step": 270
},
{
"epoch": 0.02,
"learning_rate": 4.9987971168171585e-05,
"loss": 0.9323,
"step": 280
},
{
"epoch": 0.02,
"learning_rate": 4.998709350877103e-05,
"loss": 0.8987,
"step": 290
},
{
"epoch": 0.02,
"learning_rate": 4.998618495669224e-05,
"loss": 0.8933,
"step": 300
},
{
"epoch": 0.02,
"learning_rate": 4.9985245513058495e-05,
"loss": 0.893,
"step": 310
},
{
"epoch": 0.02,
"learning_rate": 4.9984275179031276e-05,
"loss": 0.909,
"step": 320
},
{
"epoch": 0.02,
"learning_rate": 4.998327395581025e-05,
"loss": 0.9235,
"step": 330
},
{
"epoch": 0.02,
"learning_rate": 4.9982241844633265e-05,
"loss": 0.8945,
"step": 340
},
{
"epoch": 0.02,
"learning_rate": 4.998117884677638e-05,
"loss": 0.9095,
"step": 350
},
{
"epoch": 0.03,
"learning_rate": 4.998008496355382e-05,
"loss": 0.8919,
"step": 360
},
{
"epoch": 0.03,
"learning_rate": 4.9978960196318006e-05,
"loss": 0.9088,
"step": 370
},
{
"epoch": 0.03,
"learning_rate": 4.997780454645954e-05,
"loss": 0.8985,
"step": 380
},
{
"epoch": 0.03,
"learning_rate": 4.99766180154072e-05,
"loss": 0.8972,
"step": 390
},
{
"epoch": 0.03,
"learning_rate": 4.9975400604627957e-05,
"loss": 0.8983,
"step": 400
},
{
"epoch": 0.03,
"learning_rate": 4.9974152315626935e-05,
"loss": 0.9115,
"step": 410
},
{
"epoch": 0.03,
"learning_rate": 4.997287314994746e-05,
"loss": 0.8957,
"step": 420
},
{
"epoch": 0.03,
"learning_rate": 4.997156310917103e-05,
"loss": 0.8681,
"step": 430
},
{
"epoch": 0.03,
"learning_rate": 4.9970222194917296e-05,
"loss": 0.894,
"step": 440
},
{
"epoch": 0.03,
"learning_rate": 4.996885040884409e-05,
"loss": 0.8798,
"step": 450
},
{
"epoch": 0.03,
"learning_rate": 4.996744775264743e-05,
"loss": 0.9034,
"step": 460
},
{
"epoch": 0.03,
"learning_rate": 4.996601422806147e-05,
"loss": 0.9033,
"step": 470
},
{
"epoch": 0.03,
"learning_rate": 4.9964549836858536e-05,
"loss": 0.8841,
"step": 480
},
{
"epoch": 0.03,
"learning_rate": 4.9963054580849134e-05,
"loss": 0.8877,
"step": 490
},
{
"epoch": 0.04,
"learning_rate": 4.996152846188191e-05,
"loss": 0.8729,
"step": 500
},
{
"epoch": 0.04,
"learning_rate": 4.995997148184369e-05,
"loss": 0.8853,
"step": 510
},
{
"epoch": 0.04,
"learning_rate": 4.9958383642659414e-05,
"loss": 0.8837,
"step": 520
},
{
"epoch": 0.04,
"learning_rate": 4.995676494629221e-05,
"loss": 0.8833,
"step": 530
},
{
"epoch": 0.04,
"learning_rate": 4.9955115394743354e-05,
"loss": 0.8843,
"step": 540
},
{
"epoch": 0.04,
"learning_rate": 4.995343499005225e-05,
"loss": 0.892,
"step": 550
},
{
"epoch": 0.04,
"learning_rate": 4.995172373429646e-05,
"loss": 0.8575,
"step": 560
},
{
"epoch": 0.04,
"learning_rate": 4.9949981629591705e-05,
"loss": 0.8311,
"step": 570
},
{
"epoch": 0.04,
"learning_rate": 4.99482086780918e-05,
"loss": 0.8669,
"step": 580
},
{
"epoch": 0.04,
"learning_rate": 4.994640488198874e-05,
"loss": 0.8388,
"step": 590
},
{
"epoch": 0.04,
"learning_rate": 4.994457024351264e-05,
"loss": 0.8424,
"step": 600
},
{
"epoch": 0.04,
"learning_rate": 4.994270476493175e-05,
"loss": 0.8676,
"step": 610
},
{
"epoch": 0.04,
"learning_rate": 4.994080844855243e-05,
"loss": 0.8598,
"step": 620
},
{
"epoch": 0.04,
"learning_rate": 4.993888129671921e-05,
"loss": 0.824,
"step": 630
},
{
"epoch": 0.05,
"learning_rate": 4.993692331181469e-05,
"loss": 0.8652,
"step": 640
},
{
"epoch": 0.05,
"learning_rate": 4.993493449625963e-05,
"loss": 0.8533,
"step": 650
},
{
"epoch": 0.05,
"learning_rate": 4.993291485251288e-05,
"loss": 0.8677,
"step": 660
},
{
"epoch": 0.05,
"learning_rate": 4.993086438307143e-05,
"loss": 0.8459,
"step": 670
},
{
"epoch": 0.05,
"learning_rate": 4.9928783090470365e-05,
"loss": 0.8626,
"step": 680
},
{
"epoch": 0.05,
"learning_rate": 4.992667097728287e-05,
"loss": 0.8127,
"step": 690
},
{
"epoch": 0.05,
"learning_rate": 4.992452804612027e-05,
"loss": 0.8716,
"step": 700
},
{
"epoch": 0.05,
"learning_rate": 4.992235429963195e-05,
"loss": 0.8544,
"step": 710
},
{
"epoch": 0.05,
"learning_rate": 4.992014974050542e-05,
"loss": 0.8562,
"step": 720
},
{
"epoch": 0.05,
"learning_rate": 4.991791437146627e-05,
"loss": 0.871,
"step": 730
},
{
"epoch": 0.05,
"learning_rate": 4.9915648195278186e-05,
"loss": 0.8453,
"step": 740
},
{
"epoch": 0.05,
"learning_rate": 4.9913351214742945e-05,
"loss": 0.8524,
"step": 750
},
{
"epoch": 0.05,
"learning_rate": 4.991102343270042e-05,
"loss": 0.8581,
"step": 760
},
{
"epoch": 0.05,
"learning_rate": 4.9908664852028545e-05,
"loss": 0.8477,
"step": 770
},
{
"epoch": 0.06,
"learning_rate": 4.990627547564335e-05,
"loss": 0.8651,
"step": 780
},
{
"epoch": 0.06,
"learning_rate": 4.990385530649891e-05,
"loss": 0.8453,
"step": 790
},
{
"epoch": 0.06,
"learning_rate": 4.9901404347587404e-05,
"loss": 0.8586,
"step": 800
},
{
"epoch": 0.06,
"learning_rate": 4.9898922601939056e-05,
"loss": 0.8746,
"step": 810
},
{
"epoch": 0.06,
"learning_rate": 4.989641007262218e-05,
"loss": 0.8652,
"step": 820
},
{
"epoch": 0.06,
"learning_rate": 4.98938667627431e-05,
"loss": 0.8531,
"step": 830
},
{
"epoch": 0.06,
"learning_rate": 4.989129267544626e-05,
"loss": 0.8686,
"step": 840
},
{
"epoch": 0.06,
"learning_rate": 4.988868781391408e-05,
"loss": 0.8692,
"step": 850
},
{
"epoch": 0.06,
"learning_rate": 4.988605218136711e-05,
"loss": 0.8274,
"step": 860
},
{
"epoch": 0.06,
"learning_rate": 4.9883385781063876e-05,
"loss": 0.8502,
"step": 870
},
{
"epoch": 0.06,
"learning_rate": 4.9880688616300975e-05,
"loss": 0.8445,
"step": 880
},
{
"epoch": 0.06,
"learning_rate": 4.9877960690413035e-05,
"loss": 0.8475,
"step": 890
},
{
"epoch": 0.06,
"learning_rate": 4.987520200677271e-05,
"loss": 0.8215,
"step": 900
},
{
"epoch": 0.06,
"learning_rate": 4.987241256879071e-05,
"loss": 0.8389,
"step": 910
},
{
"epoch": 0.07,
"learning_rate": 4.986959237991571e-05,
"loss": 0.8422,
"step": 920
},
{
"epoch": 0.07,
"learning_rate": 4.9866741443634455e-05,
"loss": 0.8287,
"step": 930
},
{
"epoch": 0.07,
"learning_rate": 4.986385976347169e-05,
"loss": 0.8694,
"step": 940
},
{
"epoch": 0.07,
"learning_rate": 4.986094734299016e-05,
"loss": 0.847,
"step": 950
},
{
"epoch": 0.07,
"learning_rate": 4.985800418579063e-05,
"loss": 0.8191,
"step": 960
},
{
"epoch": 0.07,
"learning_rate": 4.985503029551184e-05,
"loss": 0.8419,
"step": 970
},
{
"epoch": 0.07,
"learning_rate": 4.985202567583057e-05,
"loss": 0.8517,
"step": 980
},
{
"epoch": 0.07,
"learning_rate": 4.984899033046155e-05,
"loss": 0.8653,
"step": 990
},
{
"epoch": 0.07,
"learning_rate": 4.9845924263157526e-05,
"loss": 0.8349,
"step": 1000
},
{
"epoch": 0.07,
"learning_rate": 4.984282747770922e-05,
"loss": 0.8536,
"step": 1010
},
{
"epoch": 0.07,
"learning_rate": 4.983969997794531e-05,
"loss": 0.8882,
"step": 1020
},
{
"epoch": 0.07,
"learning_rate": 4.983654176773248e-05,
"loss": 0.8285,
"step": 1030
},
{
"epoch": 0.07,
"learning_rate": 4.983335285097537e-05,
"loss": 0.8503,
"step": 1040
},
{
"epoch": 0.07,
"learning_rate": 4.983013323161657e-05,
"loss": 0.8171,
"step": 1050
},
{
"epoch": 0.08,
"learning_rate": 4.982688291363666e-05,
"loss": 0.8398,
"step": 1060
},
{
"epoch": 0.08,
"learning_rate": 4.982360190105414e-05,
"loss": 0.8222,
"step": 1070
},
{
"epoch": 0.08,
"learning_rate": 4.982029019792548e-05,
"loss": 0.8333,
"step": 1080
},
{
"epoch": 0.08,
"learning_rate": 4.981694780834508e-05,
"loss": 0.8437,
"step": 1090
},
{
"epoch": 0.08,
"learning_rate": 4.981357473644531e-05,
"loss": 0.827,
"step": 1100
},
{
"epoch": 0.08,
"learning_rate": 4.9810170986396434e-05,
"loss": 0.8216,
"step": 1110
},
{
"epoch": 0.08,
"learning_rate": 4.980673656240667e-05,
"loss": 0.8253,
"step": 1120
},
{
"epoch": 0.08,
"learning_rate": 4.9803271468722146e-05,
"loss": 0.8195,
"step": 1130
},
{
"epoch": 0.08,
"learning_rate": 4.9799775709626926e-05,
"loss": 0.8394,
"step": 1140
},
{
"epoch": 0.08,
"learning_rate": 4.9796249289442966e-05,
"loss": 0.8348,
"step": 1150
},
{
"epoch": 0.08,
"learning_rate": 4.9792692212530134e-05,
"loss": 0.859,
"step": 1160
},
{
"epoch": 0.08,
"learning_rate": 4.978910448328622e-05,
"loss": 0.8043,
"step": 1170
},
{
"epoch": 0.08,
"learning_rate": 4.97854861061469e-05,
"loss": 0.8433,
"step": 1180
},
{
"epoch": 0.08,
"learning_rate": 4.978183708558571e-05,
"loss": 0.8244,
"step": 1190
},
{
"epoch": 0.08,
"learning_rate": 4.977815742611413e-05,
"loss": 0.8379,
"step": 1200
},
{
"epoch": 0.09,
"learning_rate": 4.977444713228147e-05,
"loss": 0.8471,
"step": 1210
},
{
"epoch": 0.09,
"learning_rate": 4.9770706208674946e-05,
"loss": 0.808,
"step": 1220
},
{
"epoch": 0.09,
"learning_rate": 4.976693465991963e-05,
"loss": 0.8384,
"step": 1230
},
{
"epoch": 0.09,
"learning_rate": 4.9763132490678453e-05,
"loss": 0.856,
"step": 1240
},
{
"epoch": 0.09,
"learning_rate": 4.975929970565222e-05,
"loss": 0.8382,
"step": 1250
},
{
"epoch": 0.09,
"learning_rate": 4.975543630957957e-05,
"loss": 0.8219,
"step": 1260
},
{
"epoch": 0.09,
"learning_rate": 4.975154230723699e-05,
"loss": 0.8384,
"step": 1270
},
{
"epoch": 0.09,
"learning_rate": 4.9747617703438824e-05,
"loss": 0.8276,
"step": 1280
},
{
"epoch": 0.09,
"learning_rate": 4.974366250303723e-05,
"loss": 0.8604,
"step": 1290
},
{
"epoch": 0.09,
"learning_rate": 4.97396767109222e-05,
"loss": 0.8471,
"step": 1300
},
{
"epoch": 0.09,
"learning_rate": 4.973566033202156e-05,
"loss": 0.8199,
"step": 1310
},
{
"epoch": 0.09,
"learning_rate": 4.973161337130094e-05,
"loss": 0.8243,
"step": 1320
},
{
"epoch": 0.09,
"learning_rate": 4.972753583376376e-05,
"loss": 0.7936,
"step": 1330
},
{
"epoch": 0.09,
"learning_rate": 4.972342772445129e-05,
"loss": 0.8231,
"step": 1340
},
{
"epoch": 0.1,
"learning_rate": 4.9719289048442566e-05,
"loss": 0.8223,
"step": 1350
},
{
"epoch": 0.1,
"learning_rate": 4.971511981085441e-05,
"loss": 0.8174,
"step": 1360
},
{
"epoch": 0.1,
"learning_rate": 4.9710920016841455e-05,
"loss": 0.8088,
"step": 1370
},
{
"epoch": 0.1,
"learning_rate": 4.9706689671596086e-05,
"loss": 0.8149,
"step": 1380
},
{
"epoch": 0.1,
"learning_rate": 4.970242878034847e-05,
"loss": 0.8522,
"step": 1390
},
{
"epoch": 0.1,
"learning_rate": 4.969813734836656e-05,
"loss": 0.8404,
"step": 1400
},
{
"epoch": 0.1,
"learning_rate": 4.969381538095602e-05,
"loss": 0.8608,
"step": 1410
},
{
"epoch": 0.1,
"learning_rate": 4.968946288346031e-05,
"loss": 0.8232,
"step": 1420
},
{
"epoch": 0.1,
"learning_rate": 4.968507986126063e-05,
"loss": 0.8368,
"step": 1430
},
{
"epoch": 0.1,
"learning_rate": 4.9680666319775884e-05,
"loss": 0.8154,
"step": 1440
},
{
"epoch": 0.1,
"learning_rate": 4.967622226446276e-05,
"loss": 0.8379,
"step": 1450
},
{
"epoch": 0.1,
"learning_rate": 4.9671747700815615e-05,
"loss": 0.8333,
"step": 1460
},
{
"epoch": 0.1,
"learning_rate": 4.966724263436658e-05,
"loss": 0.8542,
"step": 1470
},
{
"epoch": 0.1,
"learning_rate": 4.9662707070685476e-05,
"loss": 0.8421,
"step": 1480
},
{
"epoch": 0.11,
"learning_rate": 4.9658141015379805e-05,
"loss": 0.7827,
"step": 1490
},
{
"epoch": 0.11,
"learning_rate": 4.9653544474094805e-05,
"loss": 0.8659,
"step": 1500
},
{
"epoch": 0.11,
"learning_rate": 4.9648917452513384e-05,
"loss": 0.8166,
"step": 1510
},
{
"epoch": 0.11,
"learning_rate": 4.964425995635613e-05,
"loss": 0.8221,
"step": 1520
},
{
"epoch": 0.11,
"learning_rate": 4.963957199138134e-05,
"loss": 0.8129,
"step": 1530
},
{
"epoch": 0.11,
"learning_rate": 4.963485356338493e-05,
"loss": 0.8171,
"step": 1540
},
{
"epoch": 0.11,
"learning_rate": 4.9630104678200526e-05,
"loss": 0.7984,
"step": 1550
},
{
"epoch": 0.11,
"learning_rate": 4.962532534169939e-05,
"loss": 0.8109,
"step": 1560
},
{
"epoch": 0.11,
"learning_rate": 4.962051555979042e-05,
"loss": 0.8164,
"step": 1570
},
{
"epoch": 0.11,
"learning_rate": 4.9615675338420174e-05,
"loss": 0.8063,
"step": 1580
},
{
"epoch": 0.11,
"learning_rate": 4.961080468357284e-05,
"loss": 0.8123,
"step": 1590
},
{
"epoch": 0.11,
"learning_rate": 4.9605903601270234e-05,
"loss": 0.8322,
"step": 1600
},
{
"epoch": 0.11,
"learning_rate": 4.960097209757178e-05,
"loss": 0.8256,
"step": 1610
},
{
"epoch": 0.11,
"learning_rate": 4.959601017857451e-05,
"loss": 0.8113,
"step": 1620
},
{
"epoch": 0.12,
"learning_rate": 4.959101785041309e-05,
"loss": 0.8323,
"step": 1630
},
{
"epoch": 0.12,
"learning_rate": 4.958599511925975e-05,
"loss": 0.7911,
"step": 1640
},
{
"epoch": 0.12,
"learning_rate": 4.958094199132432e-05,
"loss": 0.8175,
"step": 1650
},
{
"epoch": 0.12,
"learning_rate": 4.957585847285422e-05,
"loss": 0.8114,
"step": 1660
},
{
"epoch": 0.12,
"learning_rate": 4.957074457013442e-05,
"loss": 0.7619,
"step": 1670
},
{
"epoch": 0.12,
"learning_rate": 4.956560028948749e-05,
"loss": 0.7909,
"step": 1680
},
{
"epoch": 0.12,
"learning_rate": 4.956042563727352e-05,
"loss": 0.8274,
"step": 1690
},
{
"epoch": 0.12,
"learning_rate": 4.955522061989018e-05,
"loss": 0.8251,
"step": 1700
},
{
"epoch": 0.12,
"learning_rate": 4.9549985243772664e-05,
"loss": 0.8129,
"step": 1710
},
{
"epoch": 0.12,
"learning_rate": 4.95447195153937e-05,
"loss": 0.8211,
"step": 1720
},
{
"epoch": 0.12,
"learning_rate": 4.9539423441263554e-05,
"loss": 0.8131,
"step": 1730
},
{
"epoch": 0.12,
"learning_rate": 4.9534097027930006e-05,
"loss": 0.7954,
"step": 1740
},
{
"epoch": 0.12,
"learning_rate": 4.952874028197833e-05,
"loss": 0.829,
"step": 1750
},
{
"epoch": 0.12,
"learning_rate": 4.9523353210031325e-05,
"loss": 0.8021,
"step": 1760
},
{
"epoch": 0.13,
"learning_rate": 4.9517935818749275e-05,
"loss": 0.8026,
"step": 1770
},
{
"epoch": 0.13,
"learning_rate": 4.951248811482993e-05,
"loss": 0.8616,
"step": 1780
},
{
"epoch": 0.13,
"learning_rate": 4.950701010500856e-05,
"loss": 0.8444,
"step": 1790
},
{
"epoch": 0.13,
"learning_rate": 4.950150179605785e-05,
"loss": 0.8206,
"step": 1800
},
{
"epoch": 0.13,
"learning_rate": 4.9495963194787986e-05,
"loss": 0.7956,
"step": 1810
},
{
"epoch": 0.13,
"learning_rate": 4.94903943080466e-05,
"loss": 0.7983,
"step": 1820
},
{
"epoch": 0.13,
"learning_rate": 4.948479514271874e-05,
"loss": 0.8392,
"step": 1830
},
{
"epoch": 0.13,
"learning_rate": 4.947916570572693e-05,
"loss": 0.8538,
"step": 1840
},
{
"epoch": 0.13,
"learning_rate": 4.947350600403108e-05,
"loss": 0.7881,
"step": 1850
},
{
"epoch": 0.13,
"learning_rate": 4.946781604462854e-05,
"loss": 0.8101,
"step": 1860
},
{
"epoch": 0.13,
"learning_rate": 4.946209583455407e-05,
"loss": 0.8344,
"step": 1870
},
{
"epoch": 0.13,
"learning_rate": 4.945634538087983e-05,
"loss": 0.8239,
"step": 1880
},
{
"epoch": 0.13,
"learning_rate": 4.945056469071536e-05,
"loss": 0.8351,
"step": 1890
},
{
"epoch": 0.13,
"learning_rate": 4.94447537712076e-05,
"loss": 0.7967,
"step": 1900
},
{
"epoch": 0.14,
"learning_rate": 4.943891262954083e-05,
"loss": 0.797,
"step": 1910
},
{
"epoch": 0.14,
"learning_rate": 4.9433041272936734e-05,
"loss": 0.8146,
"step": 1920
},
{
"epoch": 0.14,
"learning_rate": 4.942713970865435e-05,
"loss": 0.8237,
"step": 1930
},
{
"epoch": 0.14,
"learning_rate": 4.942120794399002e-05,
"loss": 0.7953,
"step": 1940
},
{
"epoch": 0.14,
"learning_rate": 4.9415245986277483e-05,
"loss": 0.8066,
"step": 1950
},
{
"epoch": 0.14,
"learning_rate": 4.940925384288775e-05,
"loss": 0.8232,
"step": 1960
},
{
"epoch": 0.14,
"learning_rate": 4.940323152122921e-05,
"loss": 0.8156,
"step": 1970
},
{
"epoch": 0.14,
"learning_rate": 4.939717902874751e-05,
"loss": 0.8062,
"step": 1980
},
{
"epoch": 0.14,
"learning_rate": 4.9391096372925626e-05,
"loss": 0.7818,
"step": 1990
},
{
"epoch": 0.14,
"learning_rate": 4.9384983561283824e-05,
"loss": 0.8105,
"step": 2000
},
{
"epoch": 0.14,
"learning_rate": 4.937884060137966e-05,
"loss": 0.8112,
"step": 2010
},
{
"epoch": 0.14,
"learning_rate": 4.9372667500807944e-05,
"loss": 0.8102,
"step": 2020
},
{
"epoch": 0.14,
"learning_rate": 4.9366464267200755e-05,
"loss": 0.8369,
"step": 2030
},
{
"epoch": 0.14,
"learning_rate": 4.936023090822744e-05,
"loss": 0.7841,
"step": 2040
},
{
"epoch": 0.15,
"learning_rate": 4.935396743159459e-05,
"loss": 0.8299,
"step": 2050
},
{
"epoch": 0.15,
"learning_rate": 4.934767384504602e-05,
"loss": 0.8048,
"step": 2060
},
{
"epoch": 0.15,
"learning_rate": 4.934135015636276e-05,
"loss": 0.825,
"step": 2070
},
{
"epoch": 0.15,
"learning_rate": 4.93349963733631e-05,
"loss": 0.7928,
"step": 2080
},
{
"epoch": 0.15,
"learning_rate": 4.9328612503902496e-05,
"loss": 0.8016,
"step": 2090
},
{
"epoch": 0.15,
"learning_rate": 4.932219855587362e-05,
"loss": 0.8134,
"step": 2100
},
{
"epoch": 0.15,
"learning_rate": 4.931575453720633e-05,
"loss": 0.8109,
"step": 2110
},
{
"epoch": 0.15,
"learning_rate": 4.930928045586765e-05,
"loss": 0.7908,
"step": 2120
},
{
"epoch": 0.15,
"learning_rate": 4.9302776319861785e-05,
"loss": 0.7936,
"step": 2130
},
{
"epoch": 0.15,
"learning_rate": 4.92962421372301e-05,
"loss": 0.8008,
"step": 2140
},
{
"epoch": 0.15,
"learning_rate": 4.928967791605108e-05,
"loss": 0.8237,
"step": 2150
},
{
"epoch": 0.15,
"learning_rate": 4.92830836644404e-05,
"loss": 0.8127,
"step": 2160
},
{
"epoch": 0.15,
"learning_rate": 4.9276459390550815e-05,
"loss": 0.8168,
"step": 2170
},
{
"epoch": 0.15,
"learning_rate": 4.926980510257222e-05,
"loss": 0.805,
"step": 2180
},
{
"epoch": 0.16,
"learning_rate": 4.926312080873161e-05,
"loss": 0.8125,
"step": 2190
},
{
"epoch": 0.16,
"learning_rate": 4.9256406517293085e-05,
"loss": 0.8267,
"step": 2200
},
{
"epoch": 0.16,
"learning_rate": 4.924966223655782e-05,
"loss": 0.8405,
"step": 2210
},
{
"epoch": 0.16,
"learning_rate": 4.92428879748641e-05,
"loss": 0.7919,
"step": 2220
},
{
"epoch": 0.16,
"learning_rate": 4.923608374058721e-05,
"loss": 0.8398,
"step": 2230
},
{
"epoch": 0.16,
"learning_rate": 4.9229249542139576e-05,
"loss": 0.8179,
"step": 2240
},
{
"epoch": 0.16,
"learning_rate": 4.9222385387970604e-05,
"loss": 0.8156,
"step": 2250
},
{
"epoch": 0.16,
"learning_rate": 4.921549128656677e-05,
"loss": 0.8089,
"step": 2260
},
{
"epoch": 0.16,
"learning_rate": 4.920856724645155e-05,
"loss": 0.8244,
"step": 2270
},
{
"epoch": 0.16,
"learning_rate": 4.920161327618546e-05,
"loss": 0.8361,
"step": 2280
},
{
"epoch": 0.16,
"learning_rate": 4.919462938436602e-05,
"loss": 0.8159,
"step": 2290
},
{
"epoch": 0.16,
"learning_rate": 4.918761557962771e-05,
"loss": 0.8104,
"step": 2300
},
{
"epoch": 0.16,
"learning_rate": 4.9180571870642034e-05,
"loss": 0.7877,
"step": 2310
},
{
"epoch": 0.16,
"learning_rate": 4.917349826611744e-05,
"loss": 0.7967,
"step": 2320
},
{
"epoch": 0.16,
"learning_rate": 4.916639477479935e-05,
"loss": 0.7729,
"step": 2330
},
{
"epoch": 0.17,
"learning_rate": 4.915926140547013e-05,
"loss": 0.8578,
"step": 2340
},
{
"epoch": 0.17,
"learning_rate": 4.915209816694908e-05,
"loss": 0.8219,
"step": 2350
},
{
"epoch": 0.17,
"learning_rate": 4.914490506809245e-05,
"loss": 0.8145,
"step": 2360
},
{
"epoch": 0.17,
"learning_rate": 4.9137682117793395e-05,
"loss": 0.8132,
"step": 2370
},
{
"epoch": 0.17,
"learning_rate": 4.9130429324981963e-05,
"loss": 0.7872,
"step": 2380
},
{
"epoch": 0.17,
"learning_rate": 4.9123146698625134e-05,
"loss": 0.8177,
"step": 2390
},
{
"epoch": 0.17,
"learning_rate": 4.911583424772672e-05,
"loss": 0.8052,
"step": 2400
},
{
"epoch": 0.17,
"learning_rate": 4.910849198132747e-05,
"loss": 0.7646,
"step": 2410
},
{
"epoch": 0.17,
"learning_rate": 4.9101119908504935e-05,
"loss": 0.8199,
"step": 2420
},
{
"epoch": 0.17,
"learning_rate": 4.909371803837355e-05,
"loss": 0.7819,
"step": 2430
},
{
"epoch": 0.17,
"learning_rate": 4.908628638008458e-05,
"loss": 0.7957,
"step": 2440
},
{
"epoch": 0.17,
"learning_rate": 4.907882494282614e-05,
"loss": 0.8103,
"step": 2450
},
{
"epoch": 0.17,
"learning_rate": 4.907133373582312e-05,
"loss": 0.79,
"step": 2460
},
{
"epoch": 0.17,
"learning_rate": 4.9063812768337246e-05,
"loss": 0.8127,
"step": 2470
},
{
"epoch": 0.18,
"learning_rate": 4.905626204966705e-05,
"loss": 0.7915,
"step": 2480
},
{
"epoch": 0.18,
"learning_rate": 4.90486815891478e-05,
"loss": 0.8207,
"step": 2490
},
{
"epoch": 0.18,
"learning_rate": 4.9041071396151585e-05,
"loss": 0.8162,
"step": 2500
},
{
"epoch": 0.18,
"learning_rate": 4.903343148008722e-05,
"loss": 0.8055,
"step": 2510
},
{
"epoch": 0.18,
"learning_rate": 4.9025761850400283e-05,
"loss": 0.8019,
"step": 2520
},
{
"epoch": 0.18,
"learning_rate": 4.9018062516573086e-05,
"loss": 0.801,
"step": 2530
},
{
"epoch": 0.18,
"learning_rate": 4.901033348812467e-05,
"loss": 0.7831,
"step": 2540
},
{
"epoch": 0.18,
"learning_rate": 4.9002574774610776e-05,
"loss": 0.794,
"step": 2550
},
{
"epoch": 0.18,
"learning_rate": 4.899478638562386e-05,
"loss": 0.7902,
"step": 2560
},
{
"epoch": 0.18,
"learning_rate": 4.8986968330793054e-05,
"loss": 0.785,
"step": 2570
},
{
"epoch": 0.18,
"learning_rate": 4.897912061978418e-05,
"loss": 0.8006,
"step": 2580
},
{
"epoch": 0.18,
"learning_rate": 4.897124326229972e-05,
"loss": 0.8208,
"step": 2590
},
{
"epoch": 0.18,
"learning_rate": 4.896333626807881e-05,
"loss": 0.7793,
"step": 2600
},
{
"epoch": 0.18,
"learning_rate": 4.8955399646897215e-05,
"loss": 0.812,
"step": 2610
},
{
"epoch": 0.19,
"learning_rate": 4.894743340856735e-05,
"loss": 0.7948,
"step": 2620
},
{
"epoch": 0.19,
"learning_rate": 4.893943756293823e-05,
"loss": 0.7955,
"step": 2630
},
{
"epoch": 0.19,
"learning_rate": 4.893141211989549e-05,
"loss": 0.8363,
"step": 2640
},
{
"epoch": 0.19,
"learning_rate": 4.892335708936135e-05,
"loss": 0.7986,
"step": 2650
},
{
"epoch": 0.19,
"learning_rate": 4.89152724812946e-05,
"loss": 0.8249,
"step": 2660
},
{
"epoch": 0.19,
"learning_rate": 4.890715830569062e-05,
"loss": 0.7951,
"step": 2670
},
{
"epoch": 0.19,
"learning_rate": 4.889901457258133e-05,
"loss": 0.8098,
"step": 2680
},
{
"epoch": 0.19,
"learning_rate": 4.889084129203519e-05,
"loss": 0.7781,
"step": 2690
},
{
"epoch": 0.19,
"learning_rate": 4.888263847415721e-05,
"loss": 0.7817,
"step": 2700
},
{
"epoch": 0.19,
"learning_rate": 4.887440612908889e-05,
"loss": 0.7848,
"step": 2710
},
{
"epoch": 0.19,
"learning_rate": 4.886614426700826e-05,
"loss": 0.7965,
"step": 2720
},
{
"epoch": 0.19,
"learning_rate": 4.8857852898129844e-05,
"loss": 0.8067,
"step": 2730
},
{
"epoch": 0.19,
"learning_rate": 4.884953203270463e-05,
"loss": 0.7933,
"step": 2740
},
{
"epoch": 0.19,
"learning_rate": 4.884118168102008e-05,
"loss": 0.7918,
"step": 2750
},
{
"epoch": 0.2,
"learning_rate": 4.883280185340011e-05,
"loss": 0.7758,
"step": 2760
},
{
"epoch": 0.2,
"learning_rate": 4.8824392560205085e-05,
"loss": 0.7765,
"step": 2770
},
{
"epoch": 0.2,
"learning_rate": 4.88159538118318e-05,
"loss": 0.7848,
"step": 2780
},
{
"epoch": 0.2,
"learning_rate": 4.8807485618713463e-05,
"loss": 0.7852,
"step": 2790
},
{
"epoch": 0.2,
"learning_rate": 4.8798987991319686e-05,
"loss": 0.8201,
"step": 2800
},
{
"epoch": 0.2,
"learning_rate": 4.879046094015646e-05,
"loss": 0.8024,
"step": 2810
},
{
"epoch": 0.2,
"learning_rate": 4.8781904475766174e-05,
"loss": 0.7921,
"step": 2820
},
{
"epoch": 0.2,
"learning_rate": 4.877331860872758e-05,
"loss": 0.7541,
"step": 2830
},
{
"epoch": 0.2,
"learning_rate": 4.876470334965576e-05,
"loss": 0.7689,
"step": 2840
},
{
"epoch": 0.2,
"learning_rate": 4.875605870920217e-05,
"loss": 0.8107,
"step": 2850
},
{
"epoch": 0.2,
"learning_rate": 4.8747384698054546e-05,
"loss": 0.7784,
"step": 2860
},
{
"epoch": 0.2,
"learning_rate": 4.873868132693699e-05,
"loss": 0.7825,
"step": 2870
},
{
"epoch": 0.2,
"learning_rate": 4.872994860660985e-05,
"loss": 0.762,
"step": 2880
},
{
"epoch": 0.2,
"learning_rate": 4.872118654786979e-05,
"loss": 0.7719,
"step": 2890
},
{
"epoch": 0.21,
"learning_rate": 4.871239516154976e-05,
"loss": 0.8455,
"step": 2900
},
{
"epoch": 0.21,
"learning_rate": 4.870357445851893e-05,
"loss": 0.7819,
"step": 2910
},
{
"epoch": 0.21,
"learning_rate": 4.869472444968274e-05,
"loss": 0.7697,
"step": 2920
},
{
"epoch": 0.21,
"learning_rate": 4.8685845145982866e-05,
"loss": 0.7829,
"step": 2930
},
{
"epoch": 0.21,
"learning_rate": 4.867693655839719e-05,
"loss": 0.8084,
"step": 2940
},
{
"epoch": 0.21,
"learning_rate": 4.866799869793979e-05,
"loss": 0.8239,
"step": 2950
},
{
"epoch": 0.21,
"learning_rate": 4.8659031575660966e-05,
"loss": 0.7885,
"step": 2960
},
{
"epoch": 0.21,
"learning_rate": 4.865003520264717e-05,
"loss": 0.7958,
"step": 2970
},
{
"epoch": 0.21,
"learning_rate": 4.8641009590021035e-05,
"loss": 0.7812,
"step": 2980
},
{
"epoch": 0.21,
"learning_rate": 4.8631954748941327e-05,
"loss": 0.8139,
"step": 2990
},
{
"epoch": 0.21,
"learning_rate": 4.862287069060296e-05,
"loss": 0.7709,
"step": 3000
}
],
"max_steps": 28254,
"num_train_epochs": 2,
"total_flos": 7.302283371374182e+17,
"trial_name": null,
"trial_params": null
}