SWIN-AI-Image-Detector / trainer_state.json
mmanikanta's picture
End of training
5079e6c
raw history blame
No virus
88.1 kB
{
"best_metric": 0.9874,
"best_model_checkpoint": "SWIN-AI-Image-Detector/checkpoint-6329",
"epoch": 9.996445076430856,
"global_step": 7030,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 7.112375533428166e-07,
"loss": 0.7628,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 1.4224751066856332e-06,
"loss": 0.7346,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 2.1337126600284495e-06,
"loss": 0.7017,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 2.8449502133712664e-06,
"loss": 0.6932,
"step": 40
},
{
"epoch": 0.07,
"learning_rate": 3.556187766714083e-06,
"loss": 0.6677,
"step": 50
},
{
"epoch": 0.09,
"learning_rate": 4.267425320056899e-06,
"loss": 0.648,
"step": 60
},
{
"epoch": 0.1,
"learning_rate": 4.9786628733997155e-06,
"loss": 0.6154,
"step": 70
},
{
"epoch": 0.11,
"learning_rate": 5.689900426742533e-06,
"loss": 0.5817,
"step": 80
},
{
"epoch": 0.13,
"learning_rate": 6.401137980085349e-06,
"loss": 0.5484,
"step": 90
},
{
"epoch": 0.14,
"learning_rate": 7.112375533428166e-06,
"loss": 0.5137,
"step": 100
},
{
"epoch": 0.16,
"learning_rate": 7.823613086770983e-06,
"loss": 0.4486,
"step": 110
},
{
"epoch": 0.17,
"learning_rate": 8.534850640113798e-06,
"loss": 0.4474,
"step": 120
},
{
"epoch": 0.18,
"learning_rate": 9.246088193456614e-06,
"loss": 0.4034,
"step": 130
},
{
"epoch": 0.2,
"learning_rate": 9.957325746799431e-06,
"loss": 0.4124,
"step": 140
},
{
"epoch": 0.21,
"learning_rate": 1.0668563300142247e-05,
"loss": 0.373,
"step": 150
},
{
"epoch": 0.23,
"learning_rate": 1.1379800853485066e-05,
"loss": 0.3743,
"step": 160
},
{
"epoch": 0.24,
"learning_rate": 1.2091038406827882e-05,
"loss": 0.3942,
"step": 170
},
{
"epoch": 0.26,
"learning_rate": 1.2802275960170699e-05,
"loss": 0.3733,
"step": 180
},
{
"epoch": 0.27,
"learning_rate": 1.3513513513513515e-05,
"loss": 0.335,
"step": 190
},
{
"epoch": 0.28,
"learning_rate": 1.4224751066856332e-05,
"loss": 0.335,
"step": 200
},
{
"epoch": 0.3,
"learning_rate": 1.4935988620199148e-05,
"loss": 0.3517,
"step": 210
},
{
"epoch": 0.31,
"learning_rate": 1.5647226173541966e-05,
"loss": 0.3076,
"step": 220
},
{
"epoch": 0.33,
"learning_rate": 1.6358463726884778e-05,
"loss": 0.3263,
"step": 230
},
{
"epoch": 0.34,
"learning_rate": 1.7069701280227596e-05,
"loss": 0.3275,
"step": 240
},
{
"epoch": 0.36,
"learning_rate": 1.7780938833570414e-05,
"loss": 0.2999,
"step": 250
},
{
"epoch": 0.37,
"learning_rate": 1.849217638691323e-05,
"loss": 0.29,
"step": 260
},
{
"epoch": 0.38,
"learning_rate": 1.9203413940256047e-05,
"loss": 0.3474,
"step": 270
},
{
"epoch": 0.4,
"learning_rate": 1.9914651493598862e-05,
"loss": 0.3244,
"step": 280
},
{
"epoch": 0.41,
"learning_rate": 2.062588904694168e-05,
"loss": 0.3155,
"step": 290
},
{
"epoch": 0.43,
"learning_rate": 2.1337126600284495e-05,
"loss": 0.2766,
"step": 300
},
{
"epoch": 0.44,
"learning_rate": 2.2048364153627313e-05,
"loss": 0.2595,
"step": 310
},
{
"epoch": 0.46,
"learning_rate": 2.275960170697013e-05,
"loss": 0.3204,
"step": 320
},
{
"epoch": 0.47,
"learning_rate": 2.3470839260312946e-05,
"loss": 0.269,
"step": 330
},
{
"epoch": 0.48,
"learning_rate": 2.4182076813655764e-05,
"loss": 0.2864,
"step": 340
},
{
"epoch": 0.5,
"learning_rate": 2.489331436699858e-05,
"loss": 0.2387,
"step": 350
},
{
"epoch": 0.51,
"learning_rate": 2.5604551920341397e-05,
"loss": 0.2619,
"step": 360
},
{
"epoch": 0.53,
"learning_rate": 2.6315789473684212e-05,
"loss": 0.3276,
"step": 370
},
{
"epoch": 0.54,
"learning_rate": 2.702702702702703e-05,
"loss": 0.2843,
"step": 380
},
{
"epoch": 0.55,
"learning_rate": 2.7738264580369845e-05,
"loss": 0.2991,
"step": 390
},
{
"epoch": 0.57,
"learning_rate": 2.8449502133712663e-05,
"loss": 0.2723,
"step": 400
},
{
"epoch": 0.58,
"learning_rate": 2.9160739687055478e-05,
"loss": 0.2446,
"step": 410
},
{
"epoch": 0.6,
"learning_rate": 2.9871977240398296e-05,
"loss": 0.25,
"step": 420
},
{
"epoch": 0.61,
"learning_rate": 3.058321479374111e-05,
"loss": 0.2601,
"step": 430
},
{
"epoch": 0.63,
"learning_rate": 3.129445234708393e-05,
"loss": 0.2581,
"step": 440
},
{
"epoch": 0.64,
"learning_rate": 3.200568990042675e-05,
"loss": 0.2473,
"step": 450
},
{
"epoch": 0.65,
"learning_rate": 3.2716927453769555e-05,
"loss": 0.278,
"step": 460
},
{
"epoch": 0.67,
"learning_rate": 3.342816500711238e-05,
"loss": 0.289,
"step": 470
},
{
"epoch": 0.68,
"learning_rate": 3.413940256045519e-05,
"loss": 0.2493,
"step": 480
},
{
"epoch": 0.7,
"learning_rate": 3.485064011379801e-05,
"loss": 0.3039,
"step": 490
},
{
"epoch": 0.71,
"learning_rate": 3.556187766714083e-05,
"loss": 0.2833,
"step": 500
},
{
"epoch": 0.73,
"learning_rate": 3.627311522048364e-05,
"loss": 0.2366,
"step": 510
},
{
"epoch": 0.74,
"learning_rate": 3.698435277382646e-05,
"loss": 0.2751,
"step": 520
},
{
"epoch": 0.75,
"learning_rate": 3.769559032716928e-05,
"loss": 0.2569,
"step": 530
},
{
"epoch": 0.77,
"learning_rate": 3.8406827880512094e-05,
"loss": 0.2947,
"step": 540
},
{
"epoch": 0.78,
"learning_rate": 3.911806543385491e-05,
"loss": 0.2916,
"step": 550
},
{
"epoch": 0.8,
"learning_rate": 3.9829302987197724e-05,
"loss": 0.2456,
"step": 560
},
{
"epoch": 0.81,
"learning_rate": 4.0540540540540545e-05,
"loss": 0.2592,
"step": 570
},
{
"epoch": 0.82,
"learning_rate": 4.125177809388336e-05,
"loss": 0.2402,
"step": 580
},
{
"epoch": 0.84,
"learning_rate": 4.1963015647226175e-05,
"loss": 0.2126,
"step": 590
},
{
"epoch": 0.85,
"learning_rate": 4.267425320056899e-05,
"loss": 0.2507,
"step": 600
},
{
"epoch": 0.87,
"learning_rate": 4.3385490753911804e-05,
"loss": 0.2062,
"step": 610
},
{
"epoch": 0.88,
"learning_rate": 4.4096728307254626e-05,
"loss": 0.2415,
"step": 620
},
{
"epoch": 0.9,
"learning_rate": 4.480796586059744e-05,
"loss": 0.2459,
"step": 630
},
{
"epoch": 0.91,
"learning_rate": 4.551920341394026e-05,
"loss": 0.2641,
"step": 640
},
{
"epoch": 0.92,
"learning_rate": 4.623044096728307e-05,
"loss": 0.2334,
"step": 650
},
{
"epoch": 0.94,
"learning_rate": 4.694167852062589e-05,
"loss": 0.255,
"step": 660
},
{
"epoch": 0.95,
"learning_rate": 4.765291607396871e-05,
"loss": 0.2355,
"step": 670
},
{
"epoch": 0.97,
"learning_rate": 4.836415362731153e-05,
"loss": 0.2416,
"step": 680
},
{
"epoch": 0.98,
"learning_rate": 4.907539118065434e-05,
"loss": 0.2322,
"step": 690
},
{
"epoch": 1.0,
"learning_rate": 4.978662873399716e-05,
"loss": 0.2432,
"step": 700
},
{
"epoch": 1.0,
"eval_accuracy": 0.9267,
"eval_loss": 0.1859399676322937,
"eval_runtime": 59.5879,
"eval_samples_per_second": 167.819,
"eval_steps_per_second": 5.253,
"step": 703
},
{
"epoch": 1.01,
"learning_rate": 4.9944681523628895e-05,
"loss": 0.2492,
"step": 710
},
{
"epoch": 1.02,
"learning_rate": 4.9865655128813026e-05,
"loss": 0.2235,
"step": 720
},
{
"epoch": 1.04,
"learning_rate": 4.978662873399716e-05,
"loss": 0.2463,
"step": 730
},
{
"epoch": 1.05,
"learning_rate": 4.970760233918128e-05,
"loss": 0.231,
"step": 740
},
{
"epoch": 1.07,
"learning_rate": 4.962857594436542e-05,
"loss": 0.2507,
"step": 750
},
{
"epoch": 1.08,
"learning_rate": 4.954954954954955e-05,
"loss": 0.228,
"step": 760
},
{
"epoch": 1.09,
"learning_rate": 4.9470523154733685e-05,
"loss": 0.2438,
"step": 770
},
{
"epoch": 1.11,
"learning_rate": 4.9391496759917816e-05,
"loss": 0.2249,
"step": 780
},
{
"epoch": 1.12,
"learning_rate": 4.931247036510195e-05,
"loss": 0.2223,
"step": 790
},
{
"epoch": 1.14,
"learning_rate": 4.923344397028608e-05,
"loss": 0.2163,
"step": 800
},
{
"epoch": 1.15,
"learning_rate": 4.9154417575470205e-05,
"loss": 0.2265,
"step": 810
},
{
"epoch": 1.17,
"learning_rate": 4.907539118065434e-05,
"loss": 0.2032,
"step": 820
},
{
"epoch": 1.18,
"learning_rate": 4.8996364785838475e-05,
"loss": 0.1977,
"step": 830
},
{
"epoch": 1.19,
"learning_rate": 4.8917338391022607e-05,
"loss": 0.2326,
"step": 840
},
{
"epoch": 1.21,
"learning_rate": 4.883831199620674e-05,
"loss": 0.1894,
"step": 850
},
{
"epoch": 1.22,
"learning_rate": 4.875928560139087e-05,
"loss": 0.2655,
"step": 860
},
{
"epoch": 1.24,
"learning_rate": 4.8680259206574995e-05,
"loss": 0.2196,
"step": 870
},
{
"epoch": 1.25,
"learning_rate": 4.8601232811759127e-05,
"loss": 0.1939,
"step": 880
},
{
"epoch": 1.27,
"learning_rate": 4.852220641694326e-05,
"loss": 0.2548,
"step": 890
},
{
"epoch": 1.28,
"learning_rate": 4.84431800221274e-05,
"loss": 0.1991,
"step": 900
},
{
"epoch": 1.29,
"learning_rate": 4.836415362731153e-05,
"loss": 0.1932,
"step": 910
},
{
"epoch": 1.31,
"learning_rate": 4.828512723249566e-05,
"loss": 0.2012,
"step": 920
},
{
"epoch": 1.32,
"learning_rate": 4.8206100837679785e-05,
"loss": 0.2109,
"step": 930
},
{
"epoch": 1.34,
"learning_rate": 4.812707444286392e-05,
"loss": 0.199,
"step": 940
},
{
"epoch": 1.35,
"learning_rate": 4.804804804804805e-05,
"loss": 0.2195,
"step": 950
},
{
"epoch": 1.37,
"learning_rate": 4.796902165323218e-05,
"loss": 0.2223,
"step": 960
},
{
"epoch": 1.38,
"learning_rate": 4.788999525841631e-05,
"loss": 0.1989,
"step": 970
},
{
"epoch": 1.39,
"learning_rate": 4.781096886360045e-05,
"loss": 0.1844,
"step": 980
},
{
"epoch": 1.41,
"learning_rate": 4.7731942468784575e-05,
"loss": 0.1992,
"step": 990
},
{
"epoch": 1.42,
"learning_rate": 4.765291607396871e-05,
"loss": 0.1832,
"step": 1000
},
{
"epoch": 1.44,
"learning_rate": 4.757388967915284e-05,
"loss": 0.207,
"step": 1010
},
{
"epoch": 1.45,
"learning_rate": 4.749486328433697e-05,
"loss": 0.2247,
"step": 1020
},
{
"epoch": 1.46,
"learning_rate": 4.74158368895211e-05,
"loss": 0.2278,
"step": 1030
},
{
"epoch": 1.48,
"learning_rate": 4.7336810494705234e-05,
"loss": 0.2058,
"step": 1040
},
{
"epoch": 1.49,
"learning_rate": 4.7257784099889365e-05,
"loss": 0.1964,
"step": 1050
},
{
"epoch": 1.51,
"learning_rate": 4.71787577050735e-05,
"loss": 0.186,
"step": 1060
},
{
"epoch": 1.52,
"learning_rate": 4.709973131025763e-05,
"loss": 0.2042,
"step": 1070
},
{
"epoch": 1.54,
"learning_rate": 4.702070491544176e-05,
"loss": 0.1665,
"step": 1080
},
{
"epoch": 1.55,
"learning_rate": 4.694167852062589e-05,
"loss": 0.2434,
"step": 1090
},
{
"epoch": 1.56,
"learning_rate": 4.6862652125810024e-05,
"loss": 0.2005,
"step": 1100
},
{
"epoch": 1.58,
"learning_rate": 4.678362573099415e-05,
"loss": 0.2025,
"step": 1110
},
{
"epoch": 1.59,
"learning_rate": 4.670459933617829e-05,
"loss": 0.189,
"step": 1120
},
{
"epoch": 1.61,
"learning_rate": 4.662557294136242e-05,
"loss": 0.1944,
"step": 1130
},
{
"epoch": 1.62,
"learning_rate": 4.654654654654655e-05,
"loss": 0.1941,
"step": 1140
},
{
"epoch": 1.64,
"learning_rate": 4.646752015173068e-05,
"loss": 0.1969,
"step": 1150
},
{
"epoch": 1.65,
"learning_rate": 4.6388493756914814e-05,
"loss": 0.1794,
"step": 1160
},
{
"epoch": 1.66,
"learning_rate": 4.630946736209894e-05,
"loss": 0.1907,
"step": 1170
},
{
"epoch": 1.68,
"learning_rate": 4.623044096728307e-05,
"loss": 0.1809,
"step": 1180
},
{
"epoch": 1.69,
"learning_rate": 4.61514145724672e-05,
"loss": 0.1937,
"step": 1190
},
{
"epoch": 1.71,
"learning_rate": 4.607238817765134e-05,
"loss": 0.1916,
"step": 1200
},
{
"epoch": 1.72,
"learning_rate": 4.599336178283547e-05,
"loss": 0.2069,
"step": 1210
},
{
"epoch": 1.73,
"learning_rate": 4.5914335388019604e-05,
"loss": 0.1825,
"step": 1220
},
{
"epoch": 1.75,
"learning_rate": 4.5835308993203736e-05,
"loss": 0.1821,
"step": 1230
},
{
"epoch": 1.76,
"learning_rate": 4.575628259838786e-05,
"loss": 0.1858,
"step": 1240
},
{
"epoch": 1.78,
"learning_rate": 4.567725620357199e-05,
"loss": 0.174,
"step": 1250
},
{
"epoch": 1.79,
"learning_rate": 4.5598229808756124e-05,
"loss": 0.1953,
"step": 1260
},
{
"epoch": 1.81,
"learning_rate": 4.551920341394026e-05,
"loss": 0.1653,
"step": 1270
},
{
"epoch": 1.82,
"learning_rate": 4.5440177019124394e-05,
"loss": 0.2142,
"step": 1280
},
{
"epoch": 1.83,
"learning_rate": 4.5361150624308526e-05,
"loss": 0.194,
"step": 1290
},
{
"epoch": 1.85,
"learning_rate": 4.528212422949265e-05,
"loss": 0.2183,
"step": 1300
},
{
"epoch": 1.86,
"learning_rate": 4.520309783467678e-05,
"loss": 0.1974,
"step": 1310
},
{
"epoch": 1.88,
"learning_rate": 4.5124071439860914e-05,
"loss": 0.171,
"step": 1320
},
{
"epoch": 1.89,
"learning_rate": 4.5045045045045046e-05,
"loss": 0.158,
"step": 1330
},
{
"epoch": 1.91,
"learning_rate": 4.496601865022918e-05,
"loss": 0.1823,
"step": 1340
},
{
"epoch": 1.92,
"learning_rate": 4.4886992255413316e-05,
"loss": 0.1649,
"step": 1350
},
{
"epoch": 1.93,
"learning_rate": 4.480796586059744e-05,
"loss": 0.1724,
"step": 1360
},
{
"epoch": 1.95,
"learning_rate": 4.472893946578157e-05,
"loss": 0.1832,
"step": 1370
},
{
"epoch": 1.96,
"learning_rate": 4.4649913070965704e-05,
"loss": 0.1657,
"step": 1380
},
{
"epoch": 1.98,
"learning_rate": 4.4570886676149836e-05,
"loss": 0.1956,
"step": 1390
},
{
"epoch": 1.99,
"learning_rate": 4.449186028133397e-05,
"loss": 0.1665,
"step": 1400
},
{
"epoch": 2.0,
"eval_accuracy": 0.9514,
"eval_loss": 0.1229332983493805,
"eval_runtime": 59.6111,
"eval_samples_per_second": 167.754,
"eval_steps_per_second": 5.251,
"step": 1406
},
{
"epoch": 2.0,
"learning_rate": 4.44128338865181e-05,
"loss": 0.1707,
"step": 1410
},
{
"epoch": 2.02,
"learning_rate": 4.433380749170223e-05,
"loss": 0.1837,
"step": 1420
},
{
"epoch": 2.03,
"learning_rate": 4.425478109688636e-05,
"loss": 0.1625,
"step": 1430
},
{
"epoch": 2.05,
"learning_rate": 4.4175754702070494e-05,
"loss": 0.1683,
"step": 1440
},
{
"epoch": 2.06,
"learning_rate": 4.4096728307254626e-05,
"loss": 0.1493,
"step": 1450
},
{
"epoch": 2.08,
"learning_rate": 4.401770191243876e-05,
"loss": 0.1613,
"step": 1460
},
{
"epoch": 2.09,
"learning_rate": 4.393867551762289e-05,
"loss": 0.1741,
"step": 1470
},
{
"epoch": 2.1,
"learning_rate": 4.3859649122807014e-05,
"loss": 0.1384,
"step": 1480
},
{
"epoch": 2.12,
"learning_rate": 4.378062272799115e-05,
"loss": 0.2032,
"step": 1490
},
{
"epoch": 2.13,
"learning_rate": 4.3701596333175284e-05,
"loss": 0.1721,
"step": 1500
},
{
"epoch": 2.15,
"learning_rate": 4.3622569938359416e-05,
"loss": 0.1664,
"step": 1510
},
{
"epoch": 2.16,
"learning_rate": 4.354354354354355e-05,
"loss": 0.1784,
"step": 1520
},
{
"epoch": 2.18,
"learning_rate": 4.346451714872768e-05,
"loss": 0.184,
"step": 1530
},
{
"epoch": 2.19,
"learning_rate": 4.3385490753911804e-05,
"loss": 0.1558,
"step": 1540
},
{
"epoch": 2.2,
"learning_rate": 4.3306464359095936e-05,
"loss": 0.1746,
"step": 1550
},
{
"epoch": 2.22,
"learning_rate": 4.322743796428007e-05,
"loss": 0.1595,
"step": 1560
},
{
"epoch": 2.23,
"learning_rate": 4.3148411569464206e-05,
"loss": 0.1764,
"step": 1570
},
{
"epoch": 2.25,
"learning_rate": 4.306938517464834e-05,
"loss": 0.1575,
"step": 1580
},
{
"epoch": 2.26,
"learning_rate": 4.299035877983247e-05,
"loss": 0.173,
"step": 1590
},
{
"epoch": 2.28,
"learning_rate": 4.2911332385016595e-05,
"loss": 0.1879,
"step": 1600
},
{
"epoch": 2.29,
"learning_rate": 4.2832305990200726e-05,
"loss": 0.1879,
"step": 1610
},
{
"epoch": 2.3,
"learning_rate": 4.275327959538486e-05,
"loss": 0.1313,
"step": 1620
},
{
"epoch": 2.32,
"learning_rate": 4.267425320056899e-05,
"loss": 0.1741,
"step": 1630
},
{
"epoch": 2.33,
"learning_rate": 4.259522680575312e-05,
"loss": 0.1393,
"step": 1640
},
{
"epoch": 2.35,
"learning_rate": 4.251620041093726e-05,
"loss": 0.164,
"step": 1650
},
{
"epoch": 2.36,
"learning_rate": 4.243717401612139e-05,
"loss": 0.1709,
"step": 1660
},
{
"epoch": 2.37,
"learning_rate": 4.2358147621305516e-05,
"loss": 0.1686,
"step": 1670
},
{
"epoch": 2.39,
"learning_rate": 4.227912122648965e-05,
"loss": 0.1595,
"step": 1680
},
{
"epoch": 2.4,
"learning_rate": 4.220009483167378e-05,
"loss": 0.1552,
"step": 1690
},
{
"epoch": 2.42,
"learning_rate": 4.212106843685791e-05,
"loss": 0.1657,
"step": 1700
},
{
"epoch": 2.43,
"learning_rate": 4.204204204204204e-05,
"loss": 0.1696,
"step": 1710
},
{
"epoch": 2.45,
"learning_rate": 4.1963015647226175e-05,
"loss": 0.1567,
"step": 1720
},
{
"epoch": 2.46,
"learning_rate": 4.1883989252410307e-05,
"loss": 0.1518,
"step": 1730
},
{
"epoch": 2.47,
"learning_rate": 4.180496285759444e-05,
"loss": 0.1744,
"step": 1740
},
{
"epoch": 2.49,
"learning_rate": 4.172593646277857e-05,
"loss": 0.1696,
"step": 1750
},
{
"epoch": 2.5,
"learning_rate": 4.16469100679627e-05,
"loss": 0.1637,
"step": 1760
},
{
"epoch": 2.52,
"learning_rate": 4.156788367314683e-05,
"loss": 0.147,
"step": 1770
},
{
"epoch": 2.53,
"learning_rate": 4.1488857278330965e-05,
"loss": 0.1602,
"step": 1780
},
{
"epoch": 2.55,
"learning_rate": 4.14098308835151e-05,
"loss": 0.1275,
"step": 1790
},
{
"epoch": 2.56,
"learning_rate": 4.133080448869923e-05,
"loss": 0.1472,
"step": 1800
},
{
"epoch": 2.57,
"learning_rate": 4.125177809388336e-05,
"loss": 0.1812,
"step": 1810
},
{
"epoch": 2.59,
"learning_rate": 4.117275169906749e-05,
"loss": 0.1632,
"step": 1820
},
{
"epoch": 2.6,
"learning_rate": 4.1093725304251623e-05,
"loss": 0.169,
"step": 1830
},
{
"epoch": 2.62,
"learning_rate": 4.1014698909435755e-05,
"loss": 0.1457,
"step": 1840
},
{
"epoch": 2.63,
"learning_rate": 4.093567251461988e-05,
"loss": 0.1599,
"step": 1850
},
{
"epoch": 2.64,
"learning_rate": 4.085664611980402e-05,
"loss": 0.1672,
"step": 1860
},
{
"epoch": 2.66,
"learning_rate": 4.077761972498815e-05,
"loss": 0.1473,
"step": 1870
},
{
"epoch": 2.67,
"learning_rate": 4.069859333017228e-05,
"loss": 0.1584,
"step": 1880
},
{
"epoch": 2.69,
"learning_rate": 4.0619566935356414e-05,
"loss": 0.1474,
"step": 1890
},
{
"epoch": 2.7,
"learning_rate": 4.0540540540540545e-05,
"loss": 0.1658,
"step": 1900
},
{
"epoch": 2.72,
"learning_rate": 4.046151414572467e-05,
"loss": 0.156,
"step": 1910
},
{
"epoch": 2.73,
"learning_rate": 4.03824877509088e-05,
"loss": 0.1563,
"step": 1920
},
{
"epoch": 2.74,
"learning_rate": 4.0303461356092934e-05,
"loss": 0.1382,
"step": 1930
},
{
"epoch": 2.76,
"learning_rate": 4.022443496127707e-05,
"loss": 0.1536,
"step": 1940
},
{
"epoch": 2.77,
"learning_rate": 4.0145408566461204e-05,
"loss": 0.1579,
"step": 1950
},
{
"epoch": 2.79,
"learning_rate": 4.0066382171645335e-05,
"loss": 0.1245,
"step": 1960
},
{
"epoch": 2.8,
"learning_rate": 3.998735577682946e-05,
"loss": 0.1648,
"step": 1970
},
{
"epoch": 2.82,
"learning_rate": 3.990832938201359e-05,
"loss": 0.1703,
"step": 1980
},
{
"epoch": 2.83,
"learning_rate": 3.9829302987197724e-05,
"loss": 0.1521,
"step": 1990
},
{
"epoch": 2.84,
"learning_rate": 3.9750276592381855e-05,
"loss": 0.1543,
"step": 2000
},
{
"epoch": 2.86,
"learning_rate": 3.967125019756599e-05,
"loss": 0.1588,
"step": 2010
},
{
"epoch": 2.87,
"learning_rate": 3.9592223802750125e-05,
"loss": 0.1234,
"step": 2020
},
{
"epoch": 2.89,
"learning_rate": 3.951319740793425e-05,
"loss": 0.1407,
"step": 2030
},
{
"epoch": 2.9,
"learning_rate": 3.943417101311838e-05,
"loss": 0.1547,
"step": 2040
},
{
"epoch": 2.92,
"learning_rate": 3.9355144618302514e-05,
"loss": 0.1271,
"step": 2050
},
{
"epoch": 2.93,
"learning_rate": 3.9276118223486645e-05,
"loss": 0.1231,
"step": 2060
},
{
"epoch": 2.94,
"learning_rate": 3.919709182867078e-05,
"loss": 0.1596,
"step": 2070
},
{
"epoch": 2.96,
"learning_rate": 3.911806543385491e-05,
"loss": 0.1723,
"step": 2080
},
{
"epoch": 2.97,
"learning_rate": 3.903903903903904e-05,
"loss": 0.1504,
"step": 2090
},
{
"epoch": 2.99,
"learning_rate": 3.896001264422317e-05,
"loss": 0.1427,
"step": 2100
},
{
"epoch": 3.0,
"eval_accuracy": 0.9761,
"eval_loss": 0.06038949638605118,
"eval_runtime": 59.8642,
"eval_samples_per_second": 167.045,
"eval_steps_per_second": 5.229,
"step": 2109
},
{
"epoch": 3.0,
"learning_rate": 3.8880986249407304e-05,
"loss": 0.1521,
"step": 2110
},
{
"epoch": 3.01,
"learning_rate": 3.8801959854591436e-05,
"loss": 0.1344,
"step": 2120
},
{
"epoch": 3.03,
"learning_rate": 3.872293345977557e-05,
"loss": 0.133,
"step": 2130
},
{
"epoch": 3.04,
"learning_rate": 3.86439070649597e-05,
"loss": 0.141,
"step": 2140
},
{
"epoch": 3.06,
"learning_rate": 3.856488067014383e-05,
"loss": 0.1306,
"step": 2150
},
{
"epoch": 3.07,
"learning_rate": 3.848585427532796e-05,
"loss": 0.1694,
"step": 2160
},
{
"epoch": 3.09,
"learning_rate": 3.8406827880512094e-05,
"loss": 0.1679,
"step": 2170
},
{
"epoch": 3.1,
"learning_rate": 3.8327801485696226e-05,
"loss": 0.1388,
"step": 2180
},
{
"epoch": 3.11,
"learning_rate": 3.824877509088036e-05,
"loss": 0.1369,
"step": 2190
},
{
"epoch": 3.13,
"learning_rate": 3.816974869606449e-05,
"loss": 0.1535,
"step": 2200
},
{
"epoch": 3.14,
"learning_rate": 3.809072230124862e-05,
"loss": 0.1499,
"step": 2210
},
{
"epoch": 3.16,
"learning_rate": 3.8011695906432746e-05,
"loss": 0.1609,
"step": 2220
},
{
"epoch": 3.17,
"learning_rate": 3.793266951161688e-05,
"loss": 0.1402,
"step": 2230
},
{
"epoch": 3.19,
"learning_rate": 3.7853643116801016e-05,
"loss": 0.1305,
"step": 2240
},
{
"epoch": 3.2,
"learning_rate": 3.777461672198515e-05,
"loss": 0.1483,
"step": 2250
},
{
"epoch": 3.21,
"learning_rate": 3.769559032716928e-05,
"loss": 0.1322,
"step": 2260
},
{
"epoch": 3.23,
"learning_rate": 3.761656393235341e-05,
"loss": 0.134,
"step": 2270
},
{
"epoch": 3.24,
"learning_rate": 3.7537537537537536e-05,
"loss": 0.1399,
"step": 2280
},
{
"epoch": 3.26,
"learning_rate": 3.745851114272167e-05,
"loss": 0.1505,
"step": 2290
},
{
"epoch": 3.27,
"learning_rate": 3.73794847479058e-05,
"loss": 0.1433,
"step": 2300
},
{
"epoch": 3.28,
"learning_rate": 3.730045835308993e-05,
"loss": 0.1272,
"step": 2310
},
{
"epoch": 3.3,
"learning_rate": 3.722143195827407e-05,
"loss": 0.1498,
"step": 2320
},
{
"epoch": 3.31,
"learning_rate": 3.71424055634582e-05,
"loss": 0.1288,
"step": 2330
},
{
"epoch": 3.33,
"learning_rate": 3.7063379168642326e-05,
"loss": 0.1553,
"step": 2340
},
{
"epoch": 3.34,
"learning_rate": 3.698435277382646e-05,
"loss": 0.1656,
"step": 2350
},
{
"epoch": 3.36,
"learning_rate": 3.690532637901059e-05,
"loss": 0.1336,
"step": 2360
},
{
"epoch": 3.37,
"learning_rate": 3.682629998419472e-05,
"loss": 0.1469,
"step": 2370
},
{
"epoch": 3.38,
"learning_rate": 3.674727358937885e-05,
"loss": 0.1254,
"step": 2380
},
{
"epoch": 3.4,
"learning_rate": 3.666824719456299e-05,
"loss": 0.1366,
"step": 2390
},
{
"epoch": 3.41,
"learning_rate": 3.6589220799747116e-05,
"loss": 0.1333,
"step": 2400
},
{
"epoch": 3.43,
"learning_rate": 3.651019440493125e-05,
"loss": 0.1435,
"step": 2410
},
{
"epoch": 3.44,
"learning_rate": 3.643116801011538e-05,
"loss": 0.1488,
"step": 2420
},
{
"epoch": 3.46,
"learning_rate": 3.635214161529951e-05,
"loss": 0.1422,
"step": 2430
},
{
"epoch": 3.47,
"learning_rate": 3.627311522048364e-05,
"loss": 0.1267,
"step": 2440
},
{
"epoch": 3.48,
"learning_rate": 3.6194088825667775e-05,
"loss": 0.1257,
"step": 2450
},
{
"epoch": 3.5,
"learning_rate": 3.6115062430851906e-05,
"loss": 0.1362,
"step": 2460
},
{
"epoch": 3.51,
"learning_rate": 3.603603603603604e-05,
"loss": 0.1263,
"step": 2470
},
{
"epoch": 3.53,
"learning_rate": 3.595700964122017e-05,
"loss": 0.1317,
"step": 2480
},
{
"epoch": 3.54,
"learning_rate": 3.58779832464043e-05,
"loss": 0.1268,
"step": 2490
},
{
"epoch": 3.55,
"learning_rate": 3.579895685158843e-05,
"loss": 0.156,
"step": 2500
},
{
"epoch": 3.57,
"learning_rate": 3.5719930456772565e-05,
"loss": 0.1366,
"step": 2510
},
{
"epoch": 3.58,
"learning_rate": 3.564090406195669e-05,
"loss": 0.1442,
"step": 2520
},
{
"epoch": 3.6,
"learning_rate": 3.556187766714083e-05,
"loss": 0.1228,
"step": 2530
},
{
"epoch": 3.61,
"learning_rate": 3.548285127232496e-05,
"loss": 0.1321,
"step": 2540
},
{
"epoch": 3.63,
"learning_rate": 3.540382487750909e-05,
"loss": 0.1358,
"step": 2550
},
{
"epoch": 3.64,
"learning_rate": 3.532479848269322e-05,
"loss": 0.1415,
"step": 2560
},
{
"epoch": 3.65,
"learning_rate": 3.5245772087877355e-05,
"loss": 0.1324,
"step": 2570
},
{
"epoch": 3.67,
"learning_rate": 3.5166745693061487e-05,
"loss": 0.1299,
"step": 2580
},
{
"epoch": 3.68,
"learning_rate": 3.508771929824561e-05,
"loss": 0.1263,
"step": 2590
},
{
"epoch": 3.7,
"learning_rate": 3.500869290342974e-05,
"loss": 0.1134,
"step": 2600
},
{
"epoch": 3.71,
"learning_rate": 3.492966650861388e-05,
"loss": 0.1313,
"step": 2610
},
{
"epoch": 3.73,
"learning_rate": 3.485064011379801e-05,
"loss": 0.1138,
"step": 2620
},
{
"epoch": 3.74,
"learning_rate": 3.4771613718982145e-05,
"loss": 0.174,
"step": 2630
},
{
"epoch": 3.75,
"learning_rate": 3.469258732416628e-05,
"loss": 0.1235,
"step": 2640
},
{
"epoch": 3.77,
"learning_rate": 3.46135609293504e-05,
"loss": 0.1267,
"step": 2650
},
{
"epoch": 3.78,
"learning_rate": 3.453453453453453e-05,
"loss": 0.1578,
"step": 2660
},
{
"epoch": 3.8,
"learning_rate": 3.4455508139718665e-05,
"loss": 0.1508,
"step": 2670
},
{
"epoch": 3.81,
"learning_rate": 3.43764817449028e-05,
"loss": 0.1189,
"step": 2680
},
{
"epoch": 3.83,
"learning_rate": 3.4297455350086935e-05,
"loss": 0.1456,
"step": 2690
},
{
"epoch": 3.84,
"learning_rate": 3.421842895527107e-05,
"loss": 0.1214,
"step": 2700
},
{
"epoch": 3.85,
"learning_rate": 3.413940256045519e-05,
"loss": 0.1493,
"step": 2710
},
{
"epoch": 3.87,
"learning_rate": 3.4060376165639323e-05,
"loss": 0.1317,
"step": 2720
},
{
"epoch": 3.88,
"learning_rate": 3.3981349770823455e-05,
"loss": 0.133,
"step": 2730
},
{
"epoch": 3.9,
"learning_rate": 3.390232337600759e-05,
"loss": 0.1219,
"step": 2740
},
{
"epoch": 3.91,
"learning_rate": 3.382329698119172e-05,
"loss": 0.1372,
"step": 2750
},
{
"epoch": 3.92,
"learning_rate": 3.374427058637585e-05,
"loss": 0.1372,
"step": 2760
},
{
"epoch": 3.94,
"learning_rate": 3.366524419155998e-05,
"loss": 0.1458,
"step": 2770
},
{
"epoch": 3.95,
"learning_rate": 3.3586217796744114e-05,
"loss": 0.1455,
"step": 2780
},
{
"epoch": 3.97,
"learning_rate": 3.3507191401928245e-05,
"loss": 0.1508,
"step": 2790
},
{
"epoch": 3.98,
"learning_rate": 3.342816500711238e-05,
"loss": 0.1458,
"step": 2800
},
{
"epoch": 4.0,
"learning_rate": 3.334913861229651e-05,
"loss": 0.143,
"step": 2810
},
{
"epoch": 4.0,
"eval_accuracy": 0.97,
"eval_loss": 0.08071798086166382,
"eval_runtime": 59.8831,
"eval_samples_per_second": 166.992,
"eval_steps_per_second": 5.227,
"step": 2813
},
{
"epoch": 4.01,
"learning_rate": 3.327011221748064e-05,
"loss": 0.1265,
"step": 2820
},
{
"epoch": 4.02,
"learning_rate": 3.319108582266477e-05,
"loss": 0.129,
"step": 2830
},
{
"epoch": 4.04,
"learning_rate": 3.3112059427848904e-05,
"loss": 0.1364,
"step": 2840
},
{
"epoch": 4.05,
"learning_rate": 3.3033033033033035e-05,
"loss": 0.1148,
"step": 2850
},
{
"epoch": 4.07,
"learning_rate": 3.295400663821717e-05,
"loss": 0.1114,
"step": 2860
},
{
"epoch": 4.08,
"learning_rate": 3.28749802434013e-05,
"loss": 0.1081,
"step": 2870
},
{
"epoch": 4.1,
"learning_rate": 3.279595384858543e-05,
"loss": 0.138,
"step": 2880
},
{
"epoch": 4.11,
"learning_rate": 3.2716927453769555e-05,
"loss": 0.1163,
"step": 2890
},
{
"epoch": 4.12,
"learning_rate": 3.2637901058953694e-05,
"loss": 0.1348,
"step": 2900
},
{
"epoch": 4.14,
"learning_rate": 3.2558874664137825e-05,
"loss": 0.1249,
"step": 2910
},
{
"epoch": 4.15,
"learning_rate": 3.247984826932196e-05,
"loss": 0.1094,
"step": 2920
},
{
"epoch": 4.17,
"learning_rate": 3.240082187450609e-05,
"loss": 0.1124,
"step": 2930
},
{
"epoch": 4.18,
"learning_rate": 3.232179547969022e-05,
"loss": 0.1181,
"step": 2940
},
{
"epoch": 4.19,
"learning_rate": 3.2242769084874345e-05,
"loss": 0.1161,
"step": 2950
},
{
"epoch": 4.21,
"learning_rate": 3.216374269005848e-05,
"loss": 0.1365,
"step": 2960
},
{
"epoch": 4.22,
"learning_rate": 3.208471629524261e-05,
"loss": 0.1183,
"step": 2970
},
{
"epoch": 4.24,
"learning_rate": 3.200568990042675e-05,
"loss": 0.1288,
"step": 2980
},
{
"epoch": 4.25,
"learning_rate": 3.192666350561088e-05,
"loss": 0.1042,
"step": 2990
},
{
"epoch": 4.27,
"learning_rate": 3.184763711079501e-05,
"loss": 0.1182,
"step": 3000
},
{
"epoch": 4.28,
"learning_rate": 3.176861071597914e-05,
"loss": 0.133,
"step": 3010
},
{
"epoch": 4.29,
"learning_rate": 3.168958432116327e-05,
"loss": 0.143,
"step": 3020
},
{
"epoch": 4.31,
"learning_rate": 3.16105579263474e-05,
"loss": 0.1564,
"step": 3030
},
{
"epoch": 4.32,
"learning_rate": 3.153153153153153e-05,
"loss": 0.1307,
"step": 3040
},
{
"epoch": 4.34,
"learning_rate": 3.145250513671566e-05,
"loss": 0.1084,
"step": 3050
},
{
"epoch": 4.35,
"learning_rate": 3.13734787418998e-05,
"loss": 0.1435,
"step": 3060
},
{
"epoch": 4.37,
"learning_rate": 3.129445234708393e-05,
"loss": 0.1394,
"step": 3070
},
{
"epoch": 4.38,
"learning_rate": 3.121542595226806e-05,
"loss": 0.1206,
"step": 3080
},
{
"epoch": 4.39,
"learning_rate": 3.113639955745219e-05,
"loss": 0.1361,
"step": 3090
},
{
"epoch": 4.41,
"learning_rate": 3.105737316263632e-05,
"loss": 0.109,
"step": 3100
},
{
"epoch": 4.42,
"learning_rate": 3.097834676782045e-05,
"loss": 0.0935,
"step": 3110
},
{
"epoch": 4.44,
"learning_rate": 3.0899320373004584e-05,
"loss": 0.1217,
"step": 3120
},
{
"epoch": 4.45,
"learning_rate": 3.0820293978188716e-05,
"loss": 0.1139,
"step": 3130
},
{
"epoch": 4.46,
"learning_rate": 3.074126758337285e-05,
"loss": 0.1201,
"step": 3140
},
{
"epoch": 4.48,
"learning_rate": 3.066224118855698e-05,
"loss": 0.1222,
"step": 3150
},
{
"epoch": 4.49,
"learning_rate": 3.058321479374111e-05,
"loss": 0.1296,
"step": 3160
},
{
"epoch": 4.51,
"learning_rate": 3.0504188398925243e-05,
"loss": 0.1308,
"step": 3170
},
{
"epoch": 4.52,
"learning_rate": 3.0425162004109374e-05,
"loss": 0.0969,
"step": 3180
},
{
"epoch": 4.54,
"learning_rate": 3.034613560929351e-05,
"loss": 0.1037,
"step": 3190
},
{
"epoch": 4.55,
"learning_rate": 3.0267109214477634e-05,
"loss": 0.1152,
"step": 3200
},
{
"epoch": 4.56,
"learning_rate": 3.0188082819661766e-05,
"loss": 0.1205,
"step": 3210
},
{
"epoch": 4.58,
"learning_rate": 3.01090564248459e-05,
"loss": 0.115,
"step": 3220
},
{
"epoch": 4.59,
"learning_rate": 3.0030030030030033e-05,
"loss": 0.1311,
"step": 3230
},
{
"epoch": 4.61,
"learning_rate": 2.9951003635214164e-05,
"loss": 0.1366,
"step": 3240
},
{
"epoch": 4.62,
"learning_rate": 2.9871977240398296e-05,
"loss": 0.1323,
"step": 3250
},
{
"epoch": 4.64,
"learning_rate": 2.9792950845582424e-05,
"loss": 0.1266,
"step": 3260
},
{
"epoch": 4.65,
"learning_rate": 2.9713924450766556e-05,
"loss": 0.1274,
"step": 3270
},
{
"epoch": 4.66,
"learning_rate": 2.9634898055950688e-05,
"loss": 0.1481,
"step": 3280
},
{
"epoch": 4.68,
"learning_rate": 2.955587166113482e-05,
"loss": 0.1298,
"step": 3290
},
{
"epoch": 4.69,
"learning_rate": 2.9476845266318955e-05,
"loss": 0.1301,
"step": 3300
},
{
"epoch": 4.71,
"learning_rate": 2.9397818871503086e-05,
"loss": 0.1176,
"step": 3310
},
{
"epoch": 4.72,
"learning_rate": 2.931879247668721e-05,
"loss": 0.1169,
"step": 3320
},
{
"epoch": 4.74,
"learning_rate": 2.9239766081871346e-05,
"loss": 0.1274,
"step": 3330
},
{
"epoch": 4.75,
"learning_rate": 2.9160739687055478e-05,
"loss": 0.1128,
"step": 3340
},
{
"epoch": 4.76,
"learning_rate": 2.908171329223961e-05,
"loss": 0.1389,
"step": 3350
},
{
"epoch": 4.78,
"learning_rate": 2.900268689742374e-05,
"loss": 0.1013,
"step": 3360
},
{
"epoch": 4.79,
"learning_rate": 2.8923660502607873e-05,
"loss": 0.0948,
"step": 3370
},
{
"epoch": 4.81,
"learning_rate": 2.8844634107792e-05,
"loss": 0.1191,
"step": 3380
},
{
"epoch": 4.82,
"learning_rate": 2.8765607712976133e-05,
"loss": 0.1014,
"step": 3390
},
{
"epoch": 4.83,
"learning_rate": 2.8686581318160265e-05,
"loss": 0.1237,
"step": 3400
},
{
"epoch": 4.85,
"learning_rate": 2.86075549233444e-05,
"loss": 0.1355,
"step": 3410
},
{
"epoch": 4.86,
"learning_rate": 2.852852852852853e-05,
"loss": 0.1327,
"step": 3420
},
{
"epoch": 4.88,
"learning_rate": 2.8449502133712663e-05,
"loss": 0.112,
"step": 3430
},
{
"epoch": 4.89,
"learning_rate": 2.837047573889679e-05,
"loss": 0.1231,
"step": 3440
},
{
"epoch": 4.91,
"learning_rate": 2.8291449344080923e-05,
"loss": 0.1291,
"step": 3450
},
{
"epoch": 4.92,
"learning_rate": 2.8212422949265055e-05,
"loss": 0.1121,
"step": 3460
},
{
"epoch": 4.93,
"learning_rate": 2.8133396554449187e-05,
"loss": 0.1234,
"step": 3470
},
{
"epoch": 4.95,
"learning_rate": 2.8054370159633318e-05,
"loss": 0.0887,
"step": 3480
},
{
"epoch": 4.96,
"learning_rate": 2.7975343764817453e-05,
"loss": 0.1136,
"step": 3490
},
{
"epoch": 4.98,
"learning_rate": 2.7896317370001585e-05,
"loss": 0.1393,
"step": 3500
},
{
"epoch": 4.99,
"learning_rate": 2.781729097518571e-05,
"loss": 0.1008,
"step": 3510
},
{
"epoch": 5.0,
"eval_accuracy": 0.9824,
"eval_loss": 0.0443880558013916,
"eval_runtime": 59.6491,
"eval_samples_per_second": 167.647,
"eval_steps_per_second": 5.247,
"step": 3516
},
{
"epoch": 5.01,
"learning_rate": 2.7738264580369845e-05,
"loss": 0.1171,
"step": 3520
},
{
"epoch": 5.02,
"learning_rate": 2.7659238185553977e-05,
"loss": 0.1185,
"step": 3530
},
{
"epoch": 5.03,
"learning_rate": 2.758021179073811e-05,
"loss": 0.1209,
"step": 3540
},
{
"epoch": 5.05,
"learning_rate": 2.750118539592224e-05,
"loss": 0.1207,
"step": 3550
},
{
"epoch": 5.06,
"learning_rate": 2.7422159001106372e-05,
"loss": 0.1079,
"step": 3560
},
{
"epoch": 5.08,
"learning_rate": 2.73431326062905e-05,
"loss": 0.1204,
"step": 3570
},
{
"epoch": 5.09,
"learning_rate": 2.7264106211474632e-05,
"loss": 0.112,
"step": 3580
},
{
"epoch": 5.1,
"learning_rate": 2.7185079816658763e-05,
"loss": 0.1139,
"step": 3590
},
{
"epoch": 5.12,
"learning_rate": 2.71060534218429e-05,
"loss": 0.1126,
"step": 3600
},
{
"epoch": 5.13,
"learning_rate": 2.702702702702703e-05,
"loss": 0.1355,
"step": 3610
},
{
"epoch": 5.15,
"learning_rate": 2.6948000632211162e-05,
"loss": 0.1107,
"step": 3620
},
{
"epoch": 5.16,
"learning_rate": 2.686897423739529e-05,
"loss": 0.0918,
"step": 3630
},
{
"epoch": 5.18,
"learning_rate": 2.6789947842579422e-05,
"loss": 0.1175,
"step": 3640
},
{
"epoch": 5.19,
"learning_rate": 2.6710921447763554e-05,
"loss": 0.1131,
"step": 3650
},
{
"epoch": 5.2,
"learning_rate": 2.6631895052947685e-05,
"loss": 0.1271,
"step": 3660
},
{
"epoch": 5.22,
"learning_rate": 2.655286865813182e-05,
"loss": 0.1262,
"step": 3670
},
{
"epoch": 5.23,
"learning_rate": 2.6473842263315952e-05,
"loss": 0.1034,
"step": 3680
},
{
"epoch": 5.25,
"learning_rate": 2.6394815868500077e-05,
"loss": 0.1266,
"step": 3690
},
{
"epoch": 5.26,
"learning_rate": 2.6315789473684212e-05,
"loss": 0.1149,
"step": 3700
},
{
"epoch": 5.28,
"learning_rate": 2.6236763078868344e-05,
"loss": 0.1187,
"step": 3710
},
{
"epoch": 5.29,
"learning_rate": 2.6157736684052475e-05,
"loss": 0.1143,
"step": 3720
},
{
"epoch": 5.3,
"learning_rate": 2.6078710289236607e-05,
"loss": 0.1066,
"step": 3730
},
{
"epoch": 5.32,
"learning_rate": 2.599968389442074e-05,
"loss": 0.0993,
"step": 3740
},
{
"epoch": 5.33,
"learning_rate": 2.5920657499604867e-05,
"loss": 0.1201,
"step": 3750
},
{
"epoch": 5.35,
"learning_rate": 2.5841631104789e-05,
"loss": 0.0983,
"step": 3760
},
{
"epoch": 5.36,
"learning_rate": 2.576260470997313e-05,
"loss": 0.1202,
"step": 3770
},
{
"epoch": 5.38,
"learning_rate": 2.5683578315157265e-05,
"loss": 0.0995,
"step": 3780
},
{
"epoch": 5.39,
"learning_rate": 2.5604551920341397e-05,
"loss": 0.1016,
"step": 3790
},
{
"epoch": 5.4,
"learning_rate": 2.552552552552553e-05,
"loss": 0.1155,
"step": 3800
},
{
"epoch": 5.42,
"learning_rate": 2.5446499130709657e-05,
"loss": 0.129,
"step": 3810
},
{
"epoch": 5.43,
"learning_rate": 2.536747273589379e-05,
"loss": 0.1278,
"step": 3820
},
{
"epoch": 5.45,
"learning_rate": 2.528844634107792e-05,
"loss": 0.1111,
"step": 3830
},
{
"epoch": 5.46,
"learning_rate": 2.5209419946262052e-05,
"loss": 0.1067,
"step": 3840
},
{
"epoch": 5.47,
"learning_rate": 2.5130393551446184e-05,
"loss": 0.1085,
"step": 3850
},
{
"epoch": 5.49,
"learning_rate": 2.505136715663032e-05,
"loss": 0.1171,
"step": 3860
},
{
"epoch": 5.5,
"learning_rate": 2.4972340761814447e-05,
"loss": 0.1067,
"step": 3870
},
{
"epoch": 5.52,
"learning_rate": 2.489331436699858e-05,
"loss": 0.1027,
"step": 3880
},
{
"epoch": 5.53,
"learning_rate": 2.481428797218271e-05,
"loss": 0.1487,
"step": 3890
},
{
"epoch": 5.55,
"learning_rate": 2.4735261577366842e-05,
"loss": 0.1243,
"step": 3900
},
{
"epoch": 5.56,
"learning_rate": 2.4656235182550974e-05,
"loss": 0.0905,
"step": 3910
},
{
"epoch": 5.57,
"learning_rate": 2.4577208787735102e-05,
"loss": 0.1274,
"step": 3920
},
{
"epoch": 5.59,
"learning_rate": 2.4498182392919237e-05,
"loss": 0.1185,
"step": 3930
},
{
"epoch": 5.6,
"learning_rate": 2.441915599810337e-05,
"loss": 0.1153,
"step": 3940
},
{
"epoch": 5.62,
"learning_rate": 2.4340129603287497e-05,
"loss": 0.1153,
"step": 3950
},
{
"epoch": 5.63,
"learning_rate": 2.426110320847163e-05,
"loss": 0.1229,
"step": 3960
},
{
"epoch": 5.65,
"learning_rate": 2.4182076813655764e-05,
"loss": 0.1115,
"step": 3970
},
{
"epoch": 5.66,
"learning_rate": 2.4103050418839892e-05,
"loss": 0.1222,
"step": 3980
},
{
"epoch": 5.67,
"learning_rate": 2.4024024024024024e-05,
"loss": 0.1335,
"step": 3990
},
{
"epoch": 5.69,
"learning_rate": 2.3944997629208156e-05,
"loss": 0.1141,
"step": 4000
},
{
"epoch": 5.7,
"learning_rate": 2.3865971234392288e-05,
"loss": 0.111,
"step": 4010
},
{
"epoch": 5.72,
"learning_rate": 2.378694483957642e-05,
"loss": 0.1009,
"step": 4020
},
{
"epoch": 5.73,
"learning_rate": 2.370791844476055e-05,
"loss": 0.1076,
"step": 4030
},
{
"epoch": 5.74,
"learning_rate": 2.3628892049944683e-05,
"loss": 0.0905,
"step": 4040
},
{
"epoch": 5.76,
"learning_rate": 2.3549865655128814e-05,
"loss": 0.1196,
"step": 4050
},
{
"epoch": 5.77,
"learning_rate": 2.3470839260312946e-05,
"loss": 0.1057,
"step": 4060
},
{
"epoch": 5.79,
"learning_rate": 2.3391812865497074e-05,
"loss": 0.1076,
"step": 4070
},
{
"epoch": 5.8,
"learning_rate": 2.331278647068121e-05,
"loss": 0.1077,
"step": 4080
},
{
"epoch": 5.82,
"learning_rate": 2.323376007586534e-05,
"loss": 0.1057,
"step": 4090
},
{
"epoch": 5.83,
"learning_rate": 2.315473368104947e-05,
"loss": 0.1254,
"step": 4100
},
{
"epoch": 5.84,
"learning_rate": 2.30757072862336e-05,
"loss": 0.1015,
"step": 4110
},
{
"epoch": 5.86,
"learning_rate": 2.2996680891417736e-05,
"loss": 0.1059,
"step": 4120
},
{
"epoch": 5.87,
"learning_rate": 2.2917654496601868e-05,
"loss": 0.1103,
"step": 4130
},
{
"epoch": 5.89,
"learning_rate": 2.2838628101785996e-05,
"loss": 0.1141,
"step": 4140
},
{
"epoch": 5.9,
"learning_rate": 2.275960170697013e-05,
"loss": 0.1046,
"step": 4150
},
{
"epoch": 5.92,
"learning_rate": 2.2680575312154263e-05,
"loss": 0.1228,
"step": 4160
},
{
"epoch": 5.93,
"learning_rate": 2.260154891733839e-05,
"loss": 0.099,
"step": 4170
},
{
"epoch": 5.94,
"learning_rate": 2.2522522522522523e-05,
"loss": 0.1156,
"step": 4180
},
{
"epoch": 5.96,
"learning_rate": 2.2443496127706658e-05,
"loss": 0.0834,
"step": 4190
},
{
"epoch": 5.97,
"learning_rate": 2.2364469732890786e-05,
"loss": 0.0929,
"step": 4200
},
{
"epoch": 5.99,
"learning_rate": 2.2285443338074918e-05,
"loss": 0.1189,
"step": 4210
},
{
"epoch": 6.0,
"eval_accuracy": 0.977,
"eval_loss": 0.06354519724845886,
"eval_runtime": 59.4966,
"eval_samples_per_second": 168.077,
"eval_steps_per_second": 5.261,
"step": 4219
},
{
"epoch": 6.0,
"learning_rate": 2.220641694325905e-05,
"loss": 0.0914,
"step": 4220
},
{
"epoch": 6.01,
"learning_rate": 2.212739054844318e-05,
"loss": 0.113,
"step": 4230
},
{
"epoch": 6.03,
"learning_rate": 2.2048364153627313e-05,
"loss": 0.1103,
"step": 4240
},
{
"epoch": 6.04,
"learning_rate": 2.1969337758811445e-05,
"loss": 0.1226,
"step": 4250
},
{
"epoch": 6.06,
"learning_rate": 2.1890311363995576e-05,
"loss": 0.1094,
"step": 4260
},
{
"epoch": 6.07,
"learning_rate": 2.1811284969179708e-05,
"loss": 0.119,
"step": 4270
},
{
"epoch": 6.09,
"learning_rate": 2.173225857436384e-05,
"loss": 0.113,
"step": 4280
},
{
"epoch": 6.1,
"learning_rate": 2.1653232179547968e-05,
"loss": 0.1079,
"step": 4290
},
{
"epoch": 6.11,
"learning_rate": 2.1574205784732103e-05,
"loss": 0.1015,
"step": 4300
},
{
"epoch": 6.13,
"learning_rate": 2.1495179389916235e-05,
"loss": 0.108,
"step": 4310
},
{
"epoch": 6.14,
"learning_rate": 2.1416152995100363e-05,
"loss": 0.0954,
"step": 4320
},
{
"epoch": 6.16,
"learning_rate": 2.1337126600284495e-05,
"loss": 0.093,
"step": 4330
},
{
"epoch": 6.17,
"learning_rate": 2.125810020546863e-05,
"loss": 0.0899,
"step": 4340
},
{
"epoch": 6.19,
"learning_rate": 2.1179073810652758e-05,
"loss": 0.1142,
"step": 4350
},
{
"epoch": 6.2,
"learning_rate": 2.110004741583689e-05,
"loss": 0.1046,
"step": 4360
},
{
"epoch": 6.21,
"learning_rate": 2.102102102102102e-05,
"loss": 0.1051,
"step": 4370
},
{
"epoch": 6.23,
"learning_rate": 2.0941994626205153e-05,
"loss": 0.1096,
"step": 4380
},
{
"epoch": 6.24,
"learning_rate": 2.0862968231389285e-05,
"loss": 0.1282,
"step": 4390
},
{
"epoch": 6.26,
"learning_rate": 2.0783941836573417e-05,
"loss": 0.1124,
"step": 4400
},
{
"epoch": 6.27,
"learning_rate": 2.070491544175755e-05,
"loss": 0.0819,
"step": 4410
},
{
"epoch": 6.29,
"learning_rate": 2.062588904694168e-05,
"loss": 0.0963,
"step": 4420
},
{
"epoch": 6.3,
"learning_rate": 2.0546862652125812e-05,
"loss": 0.1037,
"step": 4430
},
{
"epoch": 6.31,
"learning_rate": 2.046783625730994e-05,
"loss": 0.0856,
"step": 4440
},
{
"epoch": 6.33,
"learning_rate": 2.0388809862494075e-05,
"loss": 0.1141,
"step": 4450
},
{
"epoch": 6.34,
"learning_rate": 2.0309783467678207e-05,
"loss": 0.112,
"step": 4460
},
{
"epoch": 6.36,
"learning_rate": 2.0230757072862335e-05,
"loss": 0.1134,
"step": 4470
},
{
"epoch": 6.37,
"learning_rate": 2.0151730678046467e-05,
"loss": 0.0848,
"step": 4480
},
{
"epoch": 6.38,
"learning_rate": 2.0072704283230602e-05,
"loss": 0.1022,
"step": 4490
},
{
"epoch": 6.4,
"learning_rate": 1.999367788841473e-05,
"loss": 0.091,
"step": 4500
},
{
"epoch": 6.41,
"learning_rate": 1.9914651493598862e-05,
"loss": 0.0989,
"step": 4510
},
{
"epoch": 6.43,
"learning_rate": 1.9835625098782994e-05,
"loss": 0.1159,
"step": 4520
},
{
"epoch": 6.44,
"learning_rate": 1.9756598703967125e-05,
"loss": 0.1183,
"step": 4530
},
{
"epoch": 6.46,
"learning_rate": 1.9677572309151257e-05,
"loss": 0.0916,
"step": 4540
},
{
"epoch": 6.47,
"learning_rate": 1.959854591433539e-05,
"loss": 0.1234,
"step": 4550
},
{
"epoch": 6.48,
"learning_rate": 1.951951951951952e-05,
"loss": 0.1049,
"step": 4560
},
{
"epoch": 6.5,
"learning_rate": 1.9440493124703652e-05,
"loss": 0.1282,
"step": 4570
},
{
"epoch": 6.51,
"learning_rate": 1.9361466729887784e-05,
"loss": 0.0907,
"step": 4580
},
{
"epoch": 6.53,
"learning_rate": 1.9282440335071915e-05,
"loss": 0.0939,
"step": 4590
},
{
"epoch": 6.54,
"learning_rate": 1.9203413940256047e-05,
"loss": 0.1022,
"step": 4600
},
{
"epoch": 6.56,
"learning_rate": 1.912438754544018e-05,
"loss": 0.1305,
"step": 4610
},
{
"epoch": 6.57,
"learning_rate": 1.904536115062431e-05,
"loss": 0.0918,
"step": 4620
},
{
"epoch": 6.58,
"learning_rate": 1.896633475580844e-05,
"loss": 0.0948,
"step": 4630
},
{
"epoch": 6.6,
"learning_rate": 1.8887308360992574e-05,
"loss": 0.0913,
"step": 4640
},
{
"epoch": 6.61,
"learning_rate": 1.8808281966176705e-05,
"loss": 0.0961,
"step": 4650
},
{
"epoch": 6.63,
"learning_rate": 1.8729255571360834e-05,
"loss": 0.119,
"step": 4660
},
{
"epoch": 6.64,
"learning_rate": 1.8650229176544965e-05,
"loss": 0.119,
"step": 4670
},
{
"epoch": 6.65,
"learning_rate": 1.85712027817291e-05,
"loss": 0.1092,
"step": 4680
},
{
"epoch": 6.67,
"learning_rate": 1.849217638691323e-05,
"loss": 0.1111,
"step": 4690
},
{
"epoch": 6.68,
"learning_rate": 1.841314999209736e-05,
"loss": 0.0882,
"step": 4700
},
{
"epoch": 6.7,
"learning_rate": 1.8334123597281496e-05,
"loss": 0.0968,
"step": 4710
},
{
"epoch": 6.71,
"learning_rate": 1.8255097202465624e-05,
"loss": 0.1249,
"step": 4720
},
{
"epoch": 6.73,
"learning_rate": 1.8176070807649756e-05,
"loss": 0.125,
"step": 4730
},
{
"epoch": 6.74,
"learning_rate": 1.8097044412833887e-05,
"loss": 0.0981,
"step": 4740
},
{
"epoch": 6.75,
"learning_rate": 1.801801801801802e-05,
"loss": 0.1078,
"step": 4750
},
{
"epoch": 6.77,
"learning_rate": 1.793899162320215e-05,
"loss": 0.0949,
"step": 4760
},
{
"epoch": 6.78,
"learning_rate": 1.7859965228386282e-05,
"loss": 0.0952,
"step": 4770
},
{
"epoch": 6.8,
"learning_rate": 1.7780938833570414e-05,
"loss": 0.0863,
"step": 4780
},
{
"epoch": 6.81,
"learning_rate": 1.7701912438754546e-05,
"loss": 0.0878,
"step": 4790
},
{
"epoch": 6.83,
"learning_rate": 1.7622886043938677e-05,
"loss": 0.0944,
"step": 4800
},
{
"epoch": 6.84,
"learning_rate": 1.7543859649122806e-05,
"loss": 0.0911,
"step": 4810
},
{
"epoch": 6.85,
"learning_rate": 1.746483325430694e-05,
"loss": 0.0844,
"step": 4820
},
{
"epoch": 6.87,
"learning_rate": 1.7385806859491072e-05,
"loss": 0.1032,
"step": 4830
},
{
"epoch": 6.88,
"learning_rate": 1.73067804646752e-05,
"loss": 0.1096,
"step": 4840
},
{
"epoch": 6.9,
"learning_rate": 1.7227754069859332e-05,
"loss": 0.0933,
"step": 4850
},
{
"epoch": 6.91,
"learning_rate": 1.7148727675043468e-05,
"loss": 0.1098,
"step": 4860
},
{
"epoch": 6.92,
"learning_rate": 1.7069701280227596e-05,
"loss": 0.0994,
"step": 4870
},
{
"epoch": 6.94,
"learning_rate": 1.6990674885411728e-05,
"loss": 0.0983,
"step": 4880
},
{
"epoch": 6.95,
"learning_rate": 1.691164849059586e-05,
"loss": 0.1076,
"step": 4890
},
{
"epoch": 6.97,
"learning_rate": 1.683262209577999e-05,
"loss": 0.0996,
"step": 4900
},
{
"epoch": 6.98,
"learning_rate": 1.6753595700964123e-05,
"loss": 0.0863,
"step": 4910
},
{
"epoch": 7.0,
"learning_rate": 1.6674569306148254e-05,
"loss": 0.0936,
"step": 4920
},
{
"epoch": 7.0,
"eval_accuracy": 0.9789,
"eval_loss": 0.0534820482134819,
"eval_runtime": 59.7551,
"eval_samples_per_second": 167.35,
"eval_steps_per_second": 5.238,
"step": 4922
},
{
"epoch": 7.01,
"learning_rate": 1.6595542911332386e-05,
"loss": 0.1044,
"step": 4930
},
{
"epoch": 7.02,
"learning_rate": 1.6516516516516518e-05,
"loss": 0.0981,
"step": 4940
},
{
"epoch": 7.04,
"learning_rate": 1.643749012170065e-05,
"loss": 0.0757,
"step": 4950
},
{
"epoch": 7.05,
"learning_rate": 1.6358463726884778e-05,
"loss": 0.0857,
"step": 4960
},
{
"epoch": 7.07,
"learning_rate": 1.6279437332068913e-05,
"loss": 0.1061,
"step": 4970
},
{
"epoch": 7.08,
"learning_rate": 1.6200410937253044e-05,
"loss": 0.0842,
"step": 4980
},
{
"epoch": 7.1,
"learning_rate": 1.6121384542437173e-05,
"loss": 0.0854,
"step": 4990
},
{
"epoch": 7.11,
"learning_rate": 1.6042358147621304e-05,
"loss": 0.0872,
"step": 5000
},
{
"epoch": 7.12,
"learning_rate": 1.596333175280544e-05,
"loss": 0.1066,
"step": 5010
},
{
"epoch": 7.14,
"learning_rate": 1.588430535798957e-05,
"loss": 0.0951,
"step": 5020
},
{
"epoch": 7.15,
"learning_rate": 1.58052789631737e-05,
"loss": 0.0889,
"step": 5030
},
{
"epoch": 7.17,
"learning_rate": 1.572625256835783e-05,
"loss": 0.0975,
"step": 5040
},
{
"epoch": 7.18,
"learning_rate": 1.5647226173541966e-05,
"loss": 0.0858,
"step": 5050
},
{
"epoch": 7.2,
"learning_rate": 1.5568199778726095e-05,
"loss": 0.0917,
"step": 5060
},
{
"epoch": 7.21,
"learning_rate": 1.5489173383910226e-05,
"loss": 0.079,
"step": 5070
},
{
"epoch": 7.22,
"learning_rate": 1.5410146989094358e-05,
"loss": 0.0853,
"step": 5080
},
{
"epoch": 7.24,
"learning_rate": 1.533112059427849e-05,
"loss": 0.1045,
"step": 5090
},
{
"epoch": 7.25,
"learning_rate": 1.5252094199462621e-05,
"loss": 0.0895,
"step": 5100
},
{
"epoch": 7.27,
"learning_rate": 1.5173067804646755e-05,
"loss": 0.0892,
"step": 5110
},
{
"epoch": 7.28,
"learning_rate": 1.5094041409830883e-05,
"loss": 0.1013,
"step": 5120
},
{
"epoch": 7.29,
"learning_rate": 1.5015015015015016e-05,
"loss": 0.0946,
"step": 5130
},
{
"epoch": 7.31,
"learning_rate": 1.4935988620199148e-05,
"loss": 0.0878,
"step": 5140
},
{
"epoch": 7.32,
"learning_rate": 1.4856962225383278e-05,
"loss": 0.1028,
"step": 5150
},
{
"epoch": 7.34,
"learning_rate": 1.477793583056741e-05,
"loss": 0.0851,
"step": 5160
},
{
"epoch": 7.35,
"learning_rate": 1.4698909435751543e-05,
"loss": 0.0942,
"step": 5170
},
{
"epoch": 7.37,
"learning_rate": 1.4619883040935673e-05,
"loss": 0.0883,
"step": 5180
},
{
"epoch": 7.38,
"learning_rate": 1.4540856646119805e-05,
"loss": 0.079,
"step": 5190
},
{
"epoch": 7.39,
"learning_rate": 1.4461830251303937e-05,
"loss": 0.0804,
"step": 5200
},
{
"epoch": 7.41,
"learning_rate": 1.4382803856488066e-05,
"loss": 0.0976,
"step": 5210
},
{
"epoch": 7.42,
"learning_rate": 1.43037774616722e-05,
"loss": 0.1087,
"step": 5220
},
{
"epoch": 7.44,
"learning_rate": 1.4224751066856332e-05,
"loss": 0.0889,
"step": 5230
},
{
"epoch": 7.45,
"learning_rate": 1.4145724672040462e-05,
"loss": 0.0915,
"step": 5240
},
{
"epoch": 7.47,
"learning_rate": 1.4066698277224593e-05,
"loss": 0.0933,
"step": 5250
},
{
"epoch": 7.48,
"learning_rate": 1.3987671882408727e-05,
"loss": 0.1267,
"step": 5260
},
{
"epoch": 7.49,
"learning_rate": 1.3908645487592855e-05,
"loss": 0.0947,
"step": 5270
},
{
"epoch": 7.51,
"learning_rate": 1.3829619092776988e-05,
"loss": 0.0952,
"step": 5280
},
{
"epoch": 7.52,
"learning_rate": 1.375059269796112e-05,
"loss": 0.0761,
"step": 5290
},
{
"epoch": 7.54,
"learning_rate": 1.367156630314525e-05,
"loss": 0.0965,
"step": 5300
},
{
"epoch": 7.55,
"learning_rate": 1.3592539908329382e-05,
"loss": 0.1109,
"step": 5310
},
{
"epoch": 7.56,
"learning_rate": 1.3513513513513515e-05,
"loss": 0.0994,
"step": 5320
},
{
"epoch": 7.58,
"learning_rate": 1.3434487118697645e-05,
"loss": 0.0951,
"step": 5330
},
{
"epoch": 7.59,
"learning_rate": 1.3355460723881777e-05,
"loss": 0.1052,
"step": 5340
},
{
"epoch": 7.61,
"learning_rate": 1.327643432906591e-05,
"loss": 0.0902,
"step": 5350
},
{
"epoch": 7.62,
"learning_rate": 1.3197407934250038e-05,
"loss": 0.0858,
"step": 5360
},
{
"epoch": 7.64,
"learning_rate": 1.3118381539434172e-05,
"loss": 0.0908,
"step": 5370
},
{
"epoch": 7.65,
"learning_rate": 1.3039355144618304e-05,
"loss": 0.0952,
"step": 5380
},
{
"epoch": 7.66,
"learning_rate": 1.2960328749802434e-05,
"loss": 0.099,
"step": 5390
},
{
"epoch": 7.68,
"learning_rate": 1.2881302354986565e-05,
"loss": 0.0982,
"step": 5400
},
{
"epoch": 7.69,
"learning_rate": 1.2802275960170699e-05,
"loss": 0.0886,
"step": 5410
},
{
"epoch": 7.71,
"learning_rate": 1.2723249565354829e-05,
"loss": 0.0873,
"step": 5420
},
{
"epoch": 7.72,
"learning_rate": 1.264422317053896e-05,
"loss": 0.1065,
"step": 5430
},
{
"epoch": 7.74,
"learning_rate": 1.2565196775723092e-05,
"loss": 0.0807,
"step": 5440
},
{
"epoch": 7.75,
"learning_rate": 1.2486170380907224e-05,
"loss": 0.0742,
"step": 5450
},
{
"epoch": 7.76,
"learning_rate": 1.2407143986091355e-05,
"loss": 0.0856,
"step": 5460
},
{
"epoch": 7.78,
"learning_rate": 1.2328117591275487e-05,
"loss": 0.1036,
"step": 5470
},
{
"epoch": 7.79,
"learning_rate": 1.2249091196459619e-05,
"loss": 0.0879,
"step": 5480
},
{
"epoch": 7.81,
"learning_rate": 1.2170064801643749e-05,
"loss": 0.1094,
"step": 5490
},
{
"epoch": 7.82,
"learning_rate": 1.2091038406827882e-05,
"loss": 0.0821,
"step": 5500
},
{
"epoch": 7.84,
"learning_rate": 1.2012012012012012e-05,
"loss": 0.0852,
"step": 5510
},
{
"epoch": 7.85,
"learning_rate": 1.1932985617196144e-05,
"loss": 0.105,
"step": 5520
},
{
"epoch": 7.86,
"learning_rate": 1.1853959222380275e-05,
"loss": 0.1152,
"step": 5530
},
{
"epoch": 7.88,
"learning_rate": 1.1774932827564407e-05,
"loss": 0.0926,
"step": 5540
},
{
"epoch": 7.89,
"learning_rate": 1.1695906432748537e-05,
"loss": 0.0987,
"step": 5550
},
{
"epoch": 7.91,
"learning_rate": 1.161688003793267e-05,
"loss": 0.0982,
"step": 5560
},
{
"epoch": 7.92,
"learning_rate": 1.15378536431168e-05,
"loss": 0.0934,
"step": 5570
},
{
"epoch": 7.93,
"learning_rate": 1.1458827248300934e-05,
"loss": 0.0865,
"step": 5580
},
{
"epoch": 7.95,
"learning_rate": 1.1379800853485066e-05,
"loss": 0.1016,
"step": 5590
},
{
"epoch": 7.96,
"learning_rate": 1.1300774458669196e-05,
"loss": 0.0936,
"step": 5600
},
{
"epoch": 7.98,
"learning_rate": 1.1221748063853329e-05,
"loss": 0.0917,
"step": 5610
},
{
"epoch": 7.99,
"learning_rate": 1.1142721669037459e-05,
"loss": 0.1201,
"step": 5620
},
{
"epoch": 8.0,
"eval_accuracy": 0.9854,
"eval_loss": 0.03756237030029297,
"eval_runtime": 59.7644,
"eval_samples_per_second": 167.324,
"eval_steps_per_second": 5.237,
"step": 5626
},
{
"epoch": 8.01,
"learning_rate": 1.106369527422159e-05,
"loss": 0.0872,
"step": 5630
},
{
"epoch": 8.02,
"learning_rate": 1.0984668879405722e-05,
"loss": 0.0914,
"step": 5640
},
{
"epoch": 8.03,
"learning_rate": 1.0905642484589854e-05,
"loss": 0.0965,
"step": 5650
},
{
"epoch": 8.05,
"learning_rate": 1.0826616089773984e-05,
"loss": 0.0961,
"step": 5660
},
{
"epoch": 8.06,
"learning_rate": 1.0747589694958117e-05,
"loss": 0.0823,
"step": 5670
},
{
"epoch": 8.08,
"learning_rate": 1.0668563300142247e-05,
"loss": 0.093,
"step": 5680
},
{
"epoch": 8.09,
"learning_rate": 1.0589536905326379e-05,
"loss": 0.1008,
"step": 5690
},
{
"epoch": 8.11,
"learning_rate": 1.051051051051051e-05,
"loss": 0.0933,
"step": 5700
},
{
"epoch": 8.12,
"learning_rate": 1.0431484115694642e-05,
"loss": 0.0933,
"step": 5710
},
{
"epoch": 8.13,
"learning_rate": 1.0352457720878774e-05,
"loss": 0.0759,
"step": 5720
},
{
"epoch": 8.15,
"learning_rate": 1.0273431326062906e-05,
"loss": 0.0911,
"step": 5730
},
{
"epoch": 8.16,
"learning_rate": 1.0194404931247038e-05,
"loss": 0.0893,
"step": 5740
},
{
"epoch": 8.18,
"learning_rate": 1.0115378536431168e-05,
"loss": 0.0979,
"step": 5750
},
{
"epoch": 8.19,
"learning_rate": 1.0036352141615301e-05,
"loss": 0.0835,
"step": 5760
},
{
"epoch": 8.2,
"learning_rate": 9.957325746799431e-06,
"loss": 0.08,
"step": 5770
},
{
"epoch": 8.22,
"learning_rate": 9.878299351983563e-06,
"loss": 0.0963,
"step": 5780
},
{
"epoch": 8.23,
"learning_rate": 9.799272957167694e-06,
"loss": 0.07,
"step": 5790
},
{
"epoch": 8.25,
"learning_rate": 9.720246562351826e-06,
"loss": 0.098,
"step": 5800
},
{
"epoch": 8.26,
"learning_rate": 9.641220167535958e-06,
"loss": 0.0849,
"step": 5810
},
{
"epoch": 8.28,
"learning_rate": 9.56219377272009e-06,
"loss": 0.0709,
"step": 5820
},
{
"epoch": 8.29,
"learning_rate": 9.48316737790422e-06,
"loss": 0.0807,
"step": 5830
},
{
"epoch": 8.3,
"learning_rate": 9.404140983088353e-06,
"loss": 0.0914,
"step": 5840
},
{
"epoch": 8.32,
"learning_rate": 9.325114588272483e-06,
"loss": 0.0841,
"step": 5850
},
{
"epoch": 8.33,
"learning_rate": 9.246088193456614e-06,
"loss": 0.072,
"step": 5860
},
{
"epoch": 8.35,
"learning_rate": 9.167061798640748e-06,
"loss": 0.0941,
"step": 5870
},
{
"epoch": 8.36,
"learning_rate": 9.088035403824878e-06,
"loss": 0.0721,
"step": 5880
},
{
"epoch": 8.38,
"learning_rate": 9.00900900900901e-06,
"loss": 0.0897,
"step": 5890
},
{
"epoch": 8.39,
"learning_rate": 8.929982614193141e-06,
"loss": 0.0899,
"step": 5900
},
{
"epoch": 8.4,
"learning_rate": 8.850956219377273e-06,
"loss": 0.0901,
"step": 5910
},
{
"epoch": 8.42,
"learning_rate": 8.771929824561403e-06,
"loss": 0.0844,
"step": 5920
},
{
"epoch": 8.43,
"learning_rate": 8.692903429745536e-06,
"loss": 0.0801,
"step": 5930
},
{
"epoch": 8.45,
"learning_rate": 8.613877034929666e-06,
"loss": 0.0799,
"step": 5940
},
{
"epoch": 8.46,
"learning_rate": 8.534850640113798e-06,
"loss": 0.0898,
"step": 5950
},
{
"epoch": 8.47,
"learning_rate": 8.45582424529793e-06,
"loss": 0.0725,
"step": 5960
},
{
"epoch": 8.49,
"learning_rate": 8.376797850482061e-06,
"loss": 0.0835,
"step": 5970
},
{
"epoch": 8.5,
"learning_rate": 8.297771455666193e-06,
"loss": 0.1063,
"step": 5980
},
{
"epoch": 8.52,
"learning_rate": 8.218745060850325e-06,
"loss": 0.0807,
"step": 5990
},
{
"epoch": 8.53,
"learning_rate": 8.139718666034456e-06,
"loss": 0.0726,
"step": 6000
},
{
"epoch": 8.55,
"learning_rate": 8.060692271218586e-06,
"loss": 0.0816,
"step": 6010
},
{
"epoch": 8.56,
"learning_rate": 7.98166587640272e-06,
"loss": 0.0838,
"step": 6020
},
{
"epoch": 8.57,
"learning_rate": 7.90263948158685e-06,
"loss": 0.0752,
"step": 6030
},
{
"epoch": 8.59,
"learning_rate": 7.823613086770983e-06,
"loss": 0.09,
"step": 6040
},
{
"epoch": 8.6,
"learning_rate": 7.744586691955113e-06,
"loss": 0.1017,
"step": 6050
},
{
"epoch": 8.62,
"learning_rate": 7.665560297139245e-06,
"loss": 0.1002,
"step": 6060
},
{
"epoch": 8.63,
"learning_rate": 7.586533902323377e-06,
"loss": 0.0853,
"step": 6070
},
{
"epoch": 8.65,
"learning_rate": 7.507507507507508e-06,
"loss": 0.0848,
"step": 6080
},
{
"epoch": 8.66,
"learning_rate": 7.428481112691639e-06,
"loss": 0.0735,
"step": 6090
},
{
"epoch": 8.67,
"learning_rate": 7.3494547178757716e-06,
"loss": 0.0849,
"step": 6100
},
{
"epoch": 8.69,
"learning_rate": 7.270428323059902e-06,
"loss": 0.0916,
"step": 6110
},
{
"epoch": 8.7,
"learning_rate": 7.191401928244033e-06,
"loss": 0.0903,
"step": 6120
},
{
"epoch": 8.72,
"learning_rate": 7.112375533428166e-06,
"loss": 0.0874,
"step": 6130
},
{
"epoch": 8.73,
"learning_rate": 7.033349138612297e-06,
"loss": 0.0937,
"step": 6140
},
{
"epoch": 8.75,
"learning_rate": 6.9543227437964275e-06,
"loss": 0.089,
"step": 6150
},
{
"epoch": 8.76,
"learning_rate": 6.87529634898056e-06,
"loss": 0.0874,
"step": 6160
},
{
"epoch": 8.77,
"learning_rate": 6.796269954164691e-06,
"loss": 0.1022,
"step": 6170
},
{
"epoch": 8.79,
"learning_rate": 6.7172435593488225e-06,
"loss": 0.0915,
"step": 6180
},
{
"epoch": 8.8,
"learning_rate": 6.638217164532955e-06,
"loss": 0.0867,
"step": 6190
},
{
"epoch": 8.82,
"learning_rate": 6.559190769717086e-06,
"loss": 0.0794,
"step": 6200
},
{
"epoch": 8.83,
"learning_rate": 6.480164374901217e-06,
"loss": 0.0746,
"step": 6210
},
{
"epoch": 8.84,
"learning_rate": 6.401137980085349e-06,
"loss": 0.0803,
"step": 6220
},
{
"epoch": 8.86,
"learning_rate": 6.32211158526948e-06,
"loss": 0.0726,
"step": 6230
},
{
"epoch": 8.87,
"learning_rate": 6.243085190453612e-06,
"loss": 0.0884,
"step": 6240
},
{
"epoch": 8.89,
"learning_rate": 6.1640587956377435e-06,
"loss": 0.0933,
"step": 6250
},
{
"epoch": 8.9,
"learning_rate": 6.085032400821874e-06,
"loss": 0.0945,
"step": 6260
},
{
"epoch": 8.92,
"learning_rate": 6.006006006006006e-06,
"loss": 0.0665,
"step": 6270
},
{
"epoch": 8.93,
"learning_rate": 5.926979611190138e-06,
"loss": 0.0775,
"step": 6280
},
{
"epoch": 8.94,
"learning_rate": 5.8479532163742686e-06,
"loss": 0.0835,
"step": 6290
},
{
"epoch": 8.96,
"learning_rate": 5.7689268215584e-06,
"loss": 0.0954,
"step": 6300
},
{
"epoch": 8.97,
"learning_rate": 5.689900426742533e-06,
"loss": 0.0762,
"step": 6310
},
{
"epoch": 8.99,
"learning_rate": 5.6108740319266645e-06,
"loss": 0.076,
"step": 6320
},
{
"epoch": 9.0,
"eval_accuracy": 0.9874,
"eval_loss": 0.034222181886434555,
"eval_runtime": 59.85,
"eval_samples_per_second": 167.084,
"eval_steps_per_second": 5.23,
"step": 6329
},
{
"epoch": 9.0,
"learning_rate": 5.531847637110795e-06,
"loss": 0.066,
"step": 6330
},
{
"epoch": 9.02,
"learning_rate": 5.452821242294927e-06,
"loss": 0.0833,
"step": 6340
},
{
"epoch": 9.03,
"learning_rate": 5.373794847479059e-06,
"loss": 0.0711,
"step": 6350
},
{
"epoch": 9.04,
"learning_rate": 5.2947684526631895e-06,
"loss": 0.0953,
"step": 6360
},
{
"epoch": 9.06,
"learning_rate": 5.215742057847321e-06,
"loss": 0.0773,
"step": 6370
},
{
"epoch": 9.07,
"learning_rate": 5.136715663031453e-06,
"loss": 0.0961,
"step": 6380
},
{
"epoch": 9.09,
"learning_rate": 5.057689268215584e-06,
"loss": 0.0954,
"step": 6390
},
{
"epoch": 9.1,
"learning_rate": 4.9786628733997155e-06,
"loss": 0.0827,
"step": 6400
},
{
"epoch": 9.11,
"learning_rate": 4.899636478583847e-06,
"loss": 0.0778,
"step": 6410
},
{
"epoch": 9.13,
"learning_rate": 4.820610083767979e-06,
"loss": 0.0818,
"step": 6420
},
{
"epoch": 9.14,
"learning_rate": 4.74158368895211e-06,
"loss": 0.0815,
"step": 6430
},
{
"epoch": 9.16,
"learning_rate": 4.662557294136241e-06,
"loss": 0.0817,
"step": 6440
},
{
"epoch": 9.17,
"learning_rate": 4.583530899320374e-06,
"loss": 0.0855,
"step": 6450
},
{
"epoch": 9.19,
"learning_rate": 4.504504504504505e-06,
"loss": 0.0608,
"step": 6460
},
{
"epoch": 9.2,
"learning_rate": 4.4254781096886364e-06,
"loss": 0.0625,
"step": 6470
},
{
"epoch": 9.21,
"learning_rate": 4.346451714872768e-06,
"loss": 0.0829,
"step": 6480
},
{
"epoch": 9.23,
"learning_rate": 4.267425320056899e-06,
"loss": 0.0712,
"step": 6490
},
{
"epoch": 9.24,
"learning_rate": 4.188398925241031e-06,
"loss": 0.0912,
"step": 6500
},
{
"epoch": 9.26,
"learning_rate": 4.109372530425162e-06,
"loss": 0.0813,
"step": 6510
},
{
"epoch": 9.27,
"learning_rate": 4.030346135609293e-06,
"loss": 0.0733,
"step": 6520
},
{
"epoch": 9.29,
"learning_rate": 3.951319740793425e-06,
"loss": 0.0747,
"step": 6530
},
{
"epoch": 9.3,
"learning_rate": 3.8722933459775566e-06,
"loss": 0.0722,
"step": 6540
},
{
"epoch": 9.31,
"learning_rate": 3.7932669511616887e-06,
"loss": 0.0972,
"step": 6550
},
{
"epoch": 9.33,
"learning_rate": 3.7142405563458195e-06,
"loss": 0.0794,
"step": 6560
},
{
"epoch": 9.34,
"learning_rate": 3.635214161529951e-06,
"loss": 0.0795,
"step": 6570
},
{
"epoch": 9.36,
"learning_rate": 3.556187766714083e-06,
"loss": 0.0743,
"step": 6580
},
{
"epoch": 9.37,
"learning_rate": 3.4771613718982137e-06,
"loss": 0.0903,
"step": 6590
},
{
"epoch": 9.38,
"learning_rate": 3.3981349770823454e-06,
"loss": 0.0802,
"step": 6600
},
{
"epoch": 9.4,
"learning_rate": 3.3191085822664775e-06,
"loss": 0.0869,
"step": 6610
},
{
"epoch": 9.41,
"learning_rate": 3.2400821874506084e-06,
"loss": 0.0905,
"step": 6620
},
{
"epoch": 9.43,
"learning_rate": 3.16105579263474e-06,
"loss": 0.0796,
"step": 6630
},
{
"epoch": 9.44,
"learning_rate": 3.0820293978188718e-06,
"loss": 0.0849,
"step": 6640
},
{
"epoch": 9.46,
"learning_rate": 3.003003003003003e-06,
"loss": 0.0999,
"step": 6650
},
{
"epoch": 9.47,
"learning_rate": 2.9239766081871343e-06,
"loss": 0.085,
"step": 6660
},
{
"epoch": 9.48,
"learning_rate": 2.8449502133712664e-06,
"loss": 0.0716,
"step": 6670
},
{
"epoch": 9.5,
"learning_rate": 2.7659238185553977e-06,
"loss": 0.083,
"step": 6680
},
{
"epoch": 9.51,
"learning_rate": 2.6868974237395294e-06,
"loss": 0.0889,
"step": 6690
},
{
"epoch": 9.53,
"learning_rate": 2.6078710289236606e-06,
"loss": 0.0897,
"step": 6700
},
{
"epoch": 9.54,
"learning_rate": 2.528844634107792e-06,
"loss": 0.0854,
"step": 6710
},
{
"epoch": 9.56,
"learning_rate": 2.4498182392919236e-06,
"loss": 0.0946,
"step": 6720
},
{
"epoch": 9.57,
"learning_rate": 2.370791844476055e-06,
"loss": 0.0767,
"step": 6730
},
{
"epoch": 9.58,
"learning_rate": 2.291765449660187e-06,
"loss": 0.0822,
"step": 6740
},
{
"epoch": 9.6,
"learning_rate": 2.2127390548443182e-06,
"loss": 0.0847,
"step": 6750
},
{
"epoch": 9.61,
"learning_rate": 2.1337126600284495e-06,
"loss": 0.085,
"step": 6760
},
{
"epoch": 9.63,
"learning_rate": 2.054686265212581e-06,
"loss": 0.0721,
"step": 6770
},
{
"epoch": 9.64,
"learning_rate": 1.9756598703967124e-06,
"loss": 0.0767,
"step": 6780
},
{
"epoch": 9.66,
"learning_rate": 1.8966334755808443e-06,
"loss": 0.0771,
"step": 6790
},
{
"epoch": 9.67,
"learning_rate": 1.8176070807649756e-06,
"loss": 0.0869,
"step": 6800
},
{
"epoch": 9.68,
"learning_rate": 1.7385806859491069e-06,
"loss": 0.0791,
"step": 6810
},
{
"epoch": 9.7,
"learning_rate": 1.6595542911332388e-06,
"loss": 0.0707,
"step": 6820
},
{
"epoch": 9.71,
"learning_rate": 1.58052789631737e-06,
"loss": 0.0617,
"step": 6830
},
{
"epoch": 9.73,
"learning_rate": 1.5015015015015015e-06,
"loss": 0.0894,
"step": 6840
},
{
"epoch": 9.74,
"learning_rate": 1.4224751066856332e-06,
"loss": 0.0786,
"step": 6850
},
{
"epoch": 9.75,
"learning_rate": 1.3434487118697647e-06,
"loss": 0.0733,
"step": 6860
},
{
"epoch": 9.77,
"learning_rate": 1.264422317053896e-06,
"loss": 0.0771,
"step": 6870
},
{
"epoch": 9.78,
"learning_rate": 1.1853959222380274e-06,
"loss": 0.0838,
"step": 6880
},
{
"epoch": 9.8,
"learning_rate": 1.1063695274221591e-06,
"loss": 0.0855,
"step": 6890
},
{
"epoch": 9.81,
"learning_rate": 1.0273431326062906e-06,
"loss": 0.0696,
"step": 6900
},
{
"epoch": 9.83,
"learning_rate": 9.483167377904222e-07,
"loss": 0.0867,
"step": 6910
},
{
"epoch": 9.84,
"learning_rate": 8.692903429745534e-07,
"loss": 0.0822,
"step": 6920
},
{
"epoch": 9.85,
"learning_rate": 7.90263948158685e-07,
"loss": 0.0768,
"step": 6930
},
{
"epoch": 9.87,
"learning_rate": 7.112375533428166e-07,
"loss": 0.0716,
"step": 6940
},
{
"epoch": 9.88,
"learning_rate": 6.32211158526948e-07,
"loss": 0.0722,
"step": 6950
},
{
"epoch": 9.9,
"learning_rate": 5.531847637110796e-07,
"loss": 0.0594,
"step": 6960
},
{
"epoch": 9.91,
"learning_rate": 4.741583688952111e-07,
"loss": 0.0749,
"step": 6970
},
{
"epoch": 9.93,
"learning_rate": 3.951319740793425e-07,
"loss": 0.0972,
"step": 6980
},
{
"epoch": 9.94,
"learning_rate": 3.16105579263474e-07,
"loss": 0.0951,
"step": 6990
},
{
"epoch": 9.95,
"learning_rate": 2.3707918444760554e-07,
"loss": 0.0805,
"step": 7000
},
{
"epoch": 9.97,
"learning_rate": 1.58052789631737e-07,
"loss": 0.08,
"step": 7010
},
{
"epoch": 9.98,
"learning_rate": 7.90263948158685e-08,
"loss": 0.0925,
"step": 7020
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 0.0887,
"step": 7030
},
{
"epoch": 10.0,
"eval_accuracy": 0.9844,
"eval_loss": 0.0412600003182888,
"eval_runtime": 59.4728,
"eval_samples_per_second": 168.144,
"eval_steps_per_second": 5.263,
"step": 7030
},
{
"epoch": 10.0,
"step": 7030,
"total_flos": 2.23628338666187e+19,
"train_loss": 0.1441501469903786,
"train_runtime": 13283.8875,
"train_samples_per_second": 67.751,
"train_steps_per_second": 0.529
}
],
"max_steps": 7030,
"num_train_epochs": 10,
"total_flos": 2.23628338666187e+19,
"trial_name": null,
"trial_params": null
}