{
  "best_metric": 0.983640081799591,
  "best_model_checkpoint": "/home/user/Desktop/ViT/microsoft/vit_finetuned/checkpoint-4405",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 4405,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "grad_norm": 7.11489200592041,
      "learning_rate": 1.9772985244040862e-05,
      "loss": 1.3281,
      "step": 50
    },
    {
      "epoch": 0.11,
      "grad_norm": 7.982043266296387,
      "learning_rate": 1.9545970488081726e-05,
      "loss": 0.855,
      "step": 100
    },
    {
      "epoch": 0.17,
      "grad_norm": 10.429923057556152,
      "learning_rate": 1.9318955732122587e-05,
      "loss": 0.5551,
      "step": 150
    },
    {
      "epoch": 0.23,
      "grad_norm": 8.25513744354248,
      "learning_rate": 1.909194097616345e-05,
      "loss": 0.4069,
      "step": 200
    },
    {
      "epoch": 0.28,
      "grad_norm": 8.956159591674805,
      "learning_rate": 1.8864926220204315e-05,
      "loss": 0.3274,
      "step": 250
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.4499558210372925,
      "learning_rate": 1.863791146424518e-05,
      "loss": 0.2836,
      "step": 300
    },
    {
      "epoch": 0.4,
      "grad_norm": 8.211179733276367,
      "learning_rate": 1.841089670828604e-05,
      "loss": 0.2992,
      "step": 350
    },
    {
      "epoch": 0.45,
      "grad_norm": 8.798752784729004,
      "learning_rate": 1.8183881952326903e-05,
      "loss": 0.2276,
      "step": 400
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.3845123052597046,
      "learning_rate": 1.7956867196367764e-05,
      "loss": 0.2877,
      "step": 450
    },
    {
      "epoch": 0.57,
      "grad_norm": 15.287618637084961,
      "learning_rate": 1.7729852440408628e-05,
      "loss": 0.3295,
      "step": 500
    },
    {
      "epoch": 0.62,
      "grad_norm": 19.116310119628906,
      "learning_rate": 1.750283768444949e-05,
      "loss": 0.2301,
      "step": 550
    },
    {
      "epoch": 0.68,
      "grad_norm": 8.03623104095459,
      "learning_rate": 1.7275822928490352e-05,
      "loss": 0.1888,
      "step": 600
    },
    {
      "epoch": 0.74,
      "grad_norm": 6.62972354888916,
      "learning_rate": 1.7048808172531216e-05,
      "loss": 0.2183,
      "step": 650
    },
    {
      "epoch": 0.79,
      "grad_norm": 2.2878506183624268,
      "learning_rate": 1.6821793416572077e-05,
      "loss": 0.1921,
      "step": 700
    },
    {
      "epoch": 0.85,
      "grad_norm": 11.028101921081543,
      "learning_rate": 1.659477866061294e-05,
      "loss": 0.2508,
      "step": 750
    },
    {
      "epoch": 0.91,
      "grad_norm": 19.02913475036621,
      "learning_rate": 1.6367763904653805e-05,
      "loss": 0.2718,
      "step": 800
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.5358214378356934,
      "learning_rate": 1.6140749148694666e-05,
      "loss": 0.1693,
      "step": 850
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9611451942740287,
      "eval_loss": 0.14811581373214722,
      "eval_runtime": 75.4555,
      "eval_samples_per_second": 12.961,
      "eval_steps_per_second": 3.247,
      "step": 881
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.04142925515770912,
      "learning_rate": 1.591373439273553e-05,
      "loss": 0.0968,
      "step": 900
    },
    {
      "epoch": 1.08,
      "grad_norm": 12.202880859375,
      "learning_rate": 1.568671963677639e-05,
      "loss": 0.1501,
      "step": 950
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.7614470720291138,
      "learning_rate": 1.5459704880817254e-05,
      "loss": 0.1543,
      "step": 1000
    },
    {
      "epoch": 1.19,
      "grad_norm": 13.012730598449707,
      "learning_rate": 1.5232690124858116e-05,
      "loss": 0.2138,
      "step": 1050
    },
    {
      "epoch": 1.25,
      "grad_norm": 25.198537826538086,
      "learning_rate": 1.500567536889898e-05,
      "loss": 0.1441,
      "step": 1100
    },
    {
      "epoch": 1.31,
      "grad_norm": 10.802690505981445,
      "learning_rate": 1.4778660612939841e-05,
      "loss": 0.1082,
      "step": 1150
    },
    {
      "epoch": 1.36,
      "grad_norm": 32.39842224121094,
      "learning_rate": 1.4551645856980705e-05,
      "loss": 0.1193,
      "step": 1200
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.05127358064055443,
      "learning_rate": 1.4324631101021567e-05,
      "loss": 0.1431,
      "step": 1250
    },
    {
      "epoch": 1.48,
      "grad_norm": 15.374510765075684,
      "learning_rate": 1.409761634506243e-05,
      "loss": 0.1306,
      "step": 1300
    },
    {
      "epoch": 1.53,
      "grad_norm": 22.718175888061523,
      "learning_rate": 1.3870601589103292e-05,
      "loss": 0.1379,
      "step": 1350
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.05202079191803932,
      "learning_rate": 1.3643586833144156e-05,
      "loss": 0.1174,
      "step": 1400
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.06224975362420082,
      "learning_rate": 1.3416572077185016e-05,
      "loss": 0.1303,
      "step": 1450
    },
    {
      "epoch": 1.7,
      "grad_norm": 11.104813575744629,
      "learning_rate": 1.318955732122588e-05,
      "loss": 0.1536,
      "step": 1500
    },
    {
      "epoch": 1.76,
      "grad_norm": 9.409710884094238,
      "learning_rate": 1.2962542565266743e-05,
      "loss": 0.1594,
      "step": 1550
    },
    {
      "epoch": 1.82,
      "grad_norm": 1.2388224601745605,
      "learning_rate": 1.2735527809307607e-05,
      "loss": 0.0914,
      "step": 1600
    },
    {
      "epoch": 1.87,
      "grad_norm": 12.70537281036377,
      "learning_rate": 1.2508513053348467e-05,
      "loss": 0.1253,
      "step": 1650
    },
    {
      "epoch": 1.93,
      "grad_norm": 19.78186798095703,
      "learning_rate": 1.2281498297389331e-05,
      "loss": 0.12,
      "step": 1700
    },
    {
      "epoch": 1.99,
      "grad_norm": 1.3154646158218384,
      "learning_rate": 1.2054483541430193e-05,
      "loss": 0.1244,
      "step": 1750
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9693251533742331,
      "eval_loss": 0.11500896513462067,
      "eval_runtime": 73.5646,
      "eval_samples_per_second": 13.294,
      "eval_steps_per_second": 3.33,
      "step": 1762
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.14741405844688416,
      "learning_rate": 1.1827468785471057e-05,
      "loss": 0.0995,
      "step": 1800
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.8733153939247131,
      "learning_rate": 1.1600454029511918e-05,
      "loss": 0.041,
      "step": 1850
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.20158135890960693,
      "learning_rate": 1.1373439273552782e-05,
      "loss": 0.025,
      "step": 1900
    },
    {
      "epoch": 2.21,
      "grad_norm": 0.3511994779109955,
      "learning_rate": 1.1146424517593644e-05,
      "loss": 0.1116,
      "step": 1950
    },
    {
      "epoch": 2.27,
      "grad_norm": 0.01977057382464409,
      "learning_rate": 1.0919409761634507e-05,
      "loss": 0.0746,
      "step": 2000
    },
    {
      "epoch": 2.33,
      "grad_norm": 0.0061535644344985485,
      "learning_rate": 1.0692395005675369e-05,
      "loss": 0.0586,
      "step": 2050
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.009720620699226856,
      "learning_rate": 1.0465380249716233e-05,
      "loss": 0.0499,
      "step": 2100
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.07518770545721054,
      "learning_rate": 1.0238365493757093e-05,
      "loss": 0.0497,
      "step": 2150
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.17679017782211304,
      "learning_rate": 1.0011350737797957e-05,
      "loss": 0.1088,
      "step": 2200
    },
    {
      "epoch": 2.55,
      "grad_norm": 0.010072373785078526,
      "learning_rate": 9.784335981838821e-06,
      "loss": 0.0475,
      "step": 2250
    },
    {
      "epoch": 2.61,
      "grad_norm": 13.180130004882812,
      "learning_rate": 9.557321225879684e-06,
      "loss": 0.0702,
      "step": 2300
    },
    {
      "epoch": 2.67,
      "grad_norm": 10.65009880065918,
      "learning_rate": 9.330306469920546e-06,
      "loss": 0.0956,
      "step": 2350
    },
    {
      "epoch": 2.72,
      "grad_norm": 0.06876125931739807,
      "learning_rate": 9.103291713961408e-06,
      "loss": 0.1123,
      "step": 2400
    },
    {
      "epoch": 2.78,
      "grad_norm": 0.03692874684929848,
      "learning_rate": 8.87627695800227e-06,
      "loss": 0.0345,
      "step": 2450
    },
    {
      "epoch": 2.84,
      "grad_norm": 30.104206085205078,
      "learning_rate": 8.649262202043135e-06,
      "loss": 0.0515,
      "step": 2500
    },
    {
      "epoch": 2.89,
      "grad_norm": 3.871462345123291,
      "learning_rate": 8.422247446083997e-06,
      "loss": 0.0661,
      "step": 2550
    },
    {
      "epoch": 2.95,
      "grad_norm": 0.03757273405790329,
      "learning_rate": 8.195232690124859e-06,
      "loss": 0.0692,
      "step": 2600
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9785276073619632,
      "eval_loss": 0.11215907335281372,
      "eval_runtime": 73.8279,
      "eval_samples_per_second": 13.247,
      "eval_steps_per_second": 3.319,
      "step": 2643
    },
    {
      "epoch": 3.01,
      "grad_norm": 0.36702996492385864,
      "learning_rate": 7.968217934165721e-06,
      "loss": 0.0561,
      "step": 2650
    },
    {
      "epoch": 3.06,
      "grad_norm": 0.0126617681235075,
      "learning_rate": 7.741203178206584e-06,
      "loss": 0.039,
      "step": 2700
    },
    {
      "epoch": 3.12,
      "grad_norm": 0.009421919472515583,
      "learning_rate": 7.514188422247447e-06,
      "loss": 0.0243,
      "step": 2750
    },
    {
      "epoch": 3.18,
      "grad_norm": 0.09766176342964172,
      "learning_rate": 7.28717366628831e-06,
      "loss": 0.0299,
      "step": 2800
    },
    {
      "epoch": 3.23,
      "grad_norm": 0.0054335640743374825,
      "learning_rate": 7.060158910329172e-06,
      "loss": 0.0066,
      "step": 2850
    },
    {
      "epoch": 3.29,
      "grad_norm": 0.046133432537317276,
      "learning_rate": 6.833144154370035e-06,
      "loss": 0.0275,
      "step": 2900
    },
    {
      "epoch": 3.35,
      "grad_norm": 0.003417497966438532,
      "learning_rate": 6.606129398410898e-06,
      "loss": 0.0139,
      "step": 2950
    },
    {
      "epoch": 3.41,
      "grad_norm": 0.009167753159999847,
      "learning_rate": 6.37911464245176e-06,
      "loss": 0.0553,
      "step": 3000
    },
    {
      "epoch": 3.46,
      "grad_norm": 0.03221438080072403,
      "learning_rate": 6.152099886492623e-06,
      "loss": 0.0601,
      "step": 3050
    },
    {
      "epoch": 3.52,
      "grad_norm": 15.037586212158203,
      "learning_rate": 5.925085130533485e-06,
      "loss": 0.0343,
      "step": 3100
    },
    {
      "epoch": 3.58,
      "grad_norm": 0.18505249917507172,
      "learning_rate": 5.6980703745743485e-06,
      "loss": 0.0539,
      "step": 3150
    },
    {
      "epoch": 3.63,
      "grad_norm": 24.898054122924805,
      "learning_rate": 5.471055618615211e-06,
      "loss": 0.0455,
      "step": 3200
    },
    {
      "epoch": 3.69,
      "grad_norm": 7.430636882781982,
      "learning_rate": 5.244040862656073e-06,
      "loss": 0.0502,
      "step": 3250
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.005094760097563267,
      "learning_rate": 5.017026106696936e-06,
      "loss": 0.0114,
      "step": 3300
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.03962313383817673,
      "learning_rate": 4.7900113507377985e-06,
      "loss": 0.0173,
      "step": 3350
    },
    {
      "epoch": 3.86,
      "grad_norm": 0.7573426961898804,
      "learning_rate": 4.562996594778661e-06,
      "loss": 0.0185,
      "step": 3400
    },
    {
      "epoch": 3.92,
      "grad_norm": 0.03129027783870697,
      "learning_rate": 4.335981838819524e-06,
      "loss": 0.0262,
      "step": 3450
    },
    {
      "epoch": 3.97,
      "grad_norm": 0.18763615190982819,
      "learning_rate": 4.108967082860386e-06,
      "loss": 0.0326,
      "step": 3500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9775051124744376,
      "eval_loss": 0.09212471544742584,
      "eval_runtime": 73.5389,
      "eval_samples_per_second": 13.299,
      "eval_steps_per_second": 3.332,
      "step": 3524
    },
    {
      "epoch": 4.03,
      "grad_norm": 0.052001625299453735,
      "learning_rate": 3.8819523269012485e-06,
      "loss": 0.0174,
      "step": 3550
    },
    {
      "epoch": 4.09,
      "grad_norm": 0.017523808404803276,
      "learning_rate": 3.6549375709421116e-06,
      "loss": 0.0081,
      "step": 3600
    },
    {
      "epoch": 4.14,
      "grad_norm": 0.007012099493294954,
      "learning_rate": 3.427922814982974e-06,
      "loss": 0.0152,
      "step": 3650
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.01468530111014843,
      "learning_rate": 3.2009080590238366e-06,
      "loss": 0.0098,
      "step": 3700
    },
    {
      "epoch": 4.26,
      "grad_norm": 0.160551518201828,
      "learning_rate": 2.9738933030646993e-06,
      "loss": 0.01,
      "step": 3750
    },
    {
      "epoch": 4.31,
      "grad_norm": 0.006342815700918436,
      "learning_rate": 2.746878547105562e-06,
      "loss": 0.001,
      "step": 3800
    },
    {
      "epoch": 4.37,
      "grad_norm": 0.011349351145327091,
      "learning_rate": 2.5198637911464247e-06,
      "loss": 0.0135,
      "step": 3850
    },
    {
      "epoch": 4.43,
      "grad_norm": 0.004315485712140799,
      "learning_rate": 2.2928490351872874e-06,
      "loss": 0.0061,
      "step": 3900
    },
    {
      "epoch": 4.48,
      "grad_norm": 0.25492075085639954,
      "learning_rate": 2.06583427922815e-06,
      "loss": 0.0122,
      "step": 3950
    },
    {
      "epoch": 4.54,
      "grad_norm": 0.00799469742923975,
      "learning_rate": 1.8388195232690126e-06,
      "loss": 0.0036,
      "step": 4000
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.12055113166570663,
      "learning_rate": 1.6118047673098751e-06,
      "loss": 0.004,
      "step": 4050
    },
    {
      "epoch": 4.65,
      "grad_norm": 0.014251478016376495,
      "learning_rate": 1.3847900113507379e-06,
      "loss": 0.0191,
      "step": 4100
    },
    {
      "epoch": 4.71,
      "grad_norm": 0.007032675202935934,
      "learning_rate": 1.1577752553916006e-06,
      "loss": 0.0106,
      "step": 4150
    },
    {
      "epoch": 4.77,
      "grad_norm": 0.007455560844391584,
      "learning_rate": 9.307604994324632e-07,
      "loss": 0.0081,
      "step": 4200
    },
    {
      "epoch": 4.82,
      "grad_norm": 0.06628051400184631,
      "learning_rate": 7.037457434733258e-07,
      "loss": 0.0038,
      "step": 4250
    },
    {
      "epoch": 4.88,
      "grad_norm": 0.004159100819379091,
      "learning_rate": 4.7673098751418843e-07,
      "loss": 0.0134,
      "step": 4300
    },
    {
      "epoch": 4.94,
      "grad_norm": 0.0036380901001393795,
      "learning_rate": 2.497162315550511e-07,
      "loss": 0.0211,
      "step": 4350
    },
    {
      "epoch": 4.99,
      "grad_norm": 0.0037857021670788527,
      "learning_rate": 2.2701475595913736e-08,
      "loss": 0.0235,
      "step": 4400
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.983640081799591,
      "eval_loss": 0.09139783680438995,
      "eval_runtime": 73.8525,
      "eval_samples_per_second": 13.243,
      "eval_steps_per_second": 3.317,
      "step": 4405
    }
  ],
  "logging_steps": 50,
  "max_steps": 4405,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 3.4106364287028634e+18,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}