{
  "best_metric": 0.621301775147929,
  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/MY DATA/Timesformer_WLASL_100_200_epochs_p20_SR_16/checkpoint-3785",
  "epoch": 40.005,
  "eval_steps": 500,
  "global_step": 7390,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002777777777777778,
      "grad_norm": 50.3983268737793,
      "learning_rate": 1.3194444444444444e-06,
      "loss": 19.1155,
      "step": 100
    },
    {
      "epoch": 0.005,
      "eval_accuracy": 0.008875739644970414,
      "eval_f1": 0.010524091293322064,
      "eval_loss": 4.692718029022217,
      "eval_precision": 0.015532544378698224,
      "eval_recall": 0.008875739644970414,
      "eval_runtime": 11.6929,
      "eval_samples_per_second": 28.906,
      "eval_steps_per_second": 14.453,
      "eval_top_10_accuracy": 0.08875739644970414,
      "eval_top_1_accuracy": 0.008875739644970414,
      "eval_top_5_accuracy": 0.04142011834319527,
      "step": 180
    },
    {
      "epoch": 1.000548611111111,
      "grad_norm": 49.16985321044922,
      "learning_rate": 2.6944444444444444e-06,
      "loss": 18.7026,
      "step": 200
    },
    {
      "epoch": 1.0033263888888888,
      "grad_norm": 54.74333572387695,
      "learning_rate": 4.083333333333334e-06,
      "loss": 18.5538,
      "step": 300
    },
    {
      "epoch": 1.0049930555555555,
      "eval_accuracy": 0.026627218934911243,
      "eval_f1": 0.01160748704902843,
      "eval_loss": 4.582146644592285,
      "eval_precision": 0.013707884027829569,
      "eval_recall": 0.026627218934911243,
      "eval_runtime": 11.4919,
      "eval_samples_per_second": 29.412,
      "eval_steps_per_second": 14.706,
      "eval_top_10_accuracy": 0.1301775147928994,
      "eval_top_1_accuracy": 0.026627218934911243,
      "eval_top_5_accuracy": 0.07692307692307693,
      "step": 360
    },
    {
      "epoch": 2.001097222222222,
      "grad_norm": 49.70963668823242,
      "learning_rate": 5.472222222222223e-06,
      "loss": 18.0616,
      "step": 400
    },
    {
      "epoch": 2.003875,
      "grad_norm": 52.42399978637695,
      "learning_rate": 6.861111111111111e-06,
      "loss": 17.5848,
      "step": 500
    },
    {
      "epoch": 2.004986111111111,
      "eval_accuracy": 0.05621301775147929,
      "eval_f1": 0.03896742883758426,
      "eval_loss": 4.3987812995910645,
      "eval_precision": 0.04859307359307359,
      "eval_recall": 0.05621301775147929,
      "eval_runtime": 12.0994,
      "eval_samples_per_second": 27.935,
      "eval_steps_per_second": 13.968,
      "eval_top_10_accuracy": 0.26331360946745563,
      "eval_top_1_accuracy": 0.05621301775147929,
      "eval_top_5_accuracy": 0.14497041420118342,
      "step": 540
    },
    {
      "epoch": 3.0016458333333333,
      "grad_norm": 54.07436752319336,
      "learning_rate": 8.25e-06,
      "loss": 16.7062,
      "step": 600
    },
    {
      "epoch": 3.004423611111111,
      "grad_norm": 57.311805725097656,
      "learning_rate": 9.625e-06,
      "loss": 15.8283,
      "step": 700
    },
    {
      "epoch": 3.0050069444444443,
      "eval_accuracy": 0.1301775147928994,
      "eval_f1": 0.09761319747359186,
      "eval_loss": 4.051616191864014,
      "eval_precision": 0.10124132555089023,
      "eval_recall": 0.1301775147928994,
      "eval_runtime": 12.2039,
      "eval_samples_per_second": 27.696,
      "eval_steps_per_second": 13.848,
      "eval_top_10_accuracy": 0.46449704142011833,
      "eval_top_1_accuracy": 0.1301775147928994,
      "eval_top_5_accuracy": 0.2958579881656805,
      "step": 721
    },
    {
      "epoch": 4.002194444444444,
      "grad_norm": 55.184627532958984,
      "learning_rate": 1.1013888888888889e-05,
      "loss": 14.1811,
      "step": 800
    },
    {
      "epoch": 4.004972222222222,
      "grad_norm": 62.36821746826172,
      "learning_rate": 1.2402777777777778e-05,
      "loss": 13.3102,
      "step": 900
    },
    {
      "epoch": 4.005,
      "eval_accuracy": 0.22485207100591717,
      "eval_f1": 0.17408013159057364,
      "eval_loss": 3.615004062652588,
      "eval_precision": 0.17807893898652688,
      "eval_recall": 0.22485207100591717,
      "eval_runtime": 12.3307,
      "eval_samples_per_second": 27.411,
      "eval_steps_per_second": 13.706,
      "eval_top_10_accuracy": 0.6153846153846154,
      "eval_top_1_accuracy": 0.22485207100591717,
      "eval_top_5_accuracy": 0.47041420118343197,
      "step": 901
    },
    {
      "epoch": 5.002743055555555,
      "grad_norm": 59.29837417602539,
      "learning_rate": 1.3791666666666667e-05,
      "loss": 11.2113,
      "step": 1000
    },
    {
      "epoch": 5.0049930555555555,
      "eval_accuracy": 0.2603550295857988,
      "eval_f1": 0.2214583903933016,
      "eval_loss": 3.238880157470703,
      "eval_precision": 0.24217353159660848,
      "eval_recall": 0.2603550295857988,
      "eval_runtime": 11.9439,
      "eval_samples_per_second": 28.299,
      "eval_steps_per_second": 14.149,
      "eval_top_10_accuracy": 0.7366863905325444,
      "eval_top_1_accuracy": 0.2603550295857988,
      "eval_top_5_accuracy": 0.606508875739645,
      "step": 1081
    },
    {
      "epoch": 6.0005138888888885,
      "grad_norm": 55.69058609008789,
      "learning_rate": 1.5180555555555556e-05,
      "loss": 10.4522,
      "step": 1100
    },
    {
      "epoch": 6.003291666666667,
      "grad_norm": 61.44662094116211,
      "learning_rate": 1.6569444444444447e-05,
      "loss": 8.898,
      "step": 1200
    },
    {
      "epoch": 6.004986111111111,
      "eval_accuracy": 0.3757396449704142,
      "eval_f1": 0.33238789867749136,
      "eval_loss": 2.8713691234588623,
      "eval_precision": 0.358355869968296,
      "eval_recall": 0.3757396449704142,
      "eval_runtime": 11.7736,
      "eval_samples_per_second": 28.708,
      "eval_steps_per_second": 14.354,
      "eval_top_10_accuracy": 0.8165680473372781,
      "eval_top_1_accuracy": 0.3757396449704142,
      "eval_top_5_accuracy": 0.6775147928994083,
      "step": 1261
    },
    {
      "epoch": 7.0010625,
      "grad_norm": 52.68465042114258,
      "learning_rate": 1.7958333333333334e-05,
      "loss": 7.9604,
      "step": 1300
    },
    {
      "epoch": 7.003840277777778,
      "grad_norm": 47.81911849975586,
      "learning_rate": 1.934722222222222e-05,
      "loss": 6.715,
      "step": 1400
    },
    {
      "epoch": 7.005006944444444,
      "eval_accuracy": 0.4230769230769231,
      "eval_f1": 0.372985971950469,
      "eval_loss": 2.6518218517303467,
      "eval_precision": 0.3827507962123347,
      "eval_recall": 0.4230769230769231,
      "eval_runtime": 11.7923,
      "eval_samples_per_second": 28.663,
      "eval_steps_per_second": 14.331,
      "eval_top_10_accuracy": 0.8402366863905325,
      "eval_top_1_accuracy": 0.4230769230769231,
      "eval_top_5_accuracy": 0.7248520710059172,
      "step": 1442
    },
    {
      "epoch": 8.001611111111112,
      "grad_norm": 57.77692413330078,
      "learning_rate": 2.0736111111111112e-05,
      "loss": 5.661,
      "step": 1500
    },
    {
      "epoch": 8.004388888888888,
      "grad_norm": 46.77447509765625,
      "learning_rate": 2.2125000000000002e-05,
      "loss": 4.8442,
      "step": 1600
    },
    {
      "epoch": 8.005,
      "eval_accuracy": 0.46449704142011833,
      "eval_f1": 0.4376789876789876,
      "eval_loss": 2.329350471496582,
      "eval_precision": 0.5076618893926585,
      "eval_recall": 0.46449704142011833,
      "eval_runtime": 11.6897,
      "eval_samples_per_second": 28.914,
      "eval_steps_per_second": 14.457,
      "eval_top_10_accuracy": 0.8875739644970414,
      "eval_top_1_accuracy": 0.46449704142011833,
      "eval_top_5_accuracy": 0.7928994082840237,
      "step": 1622
    },
    {
      "epoch": 9.002159722222222,
      "grad_norm": 37.64653396606445,
      "learning_rate": 2.351388888888889e-05,
      "loss": 3.5341,
      "step": 1700
    },
    {
      "epoch": 9.0049375,
      "grad_norm": 37.44438171386719,
      "learning_rate": 2.4902777777777777e-05,
      "loss": 3.3825,
      "step": 1800
    },
    {
      "epoch": 9.004993055555556,
      "eval_accuracy": 0.4911242603550296,
      "eval_f1": 0.46539428684399103,
      "eval_loss": 2.174729347229004,
      "eval_precision": 0.5436003099464638,
      "eval_recall": 0.4911242603550296,
      "eval_runtime": 11.6633,
      "eval_samples_per_second": 28.98,
      "eval_steps_per_second": 14.49,
      "eval_top_10_accuracy": 0.8964497041420119,
      "eval_top_1_accuracy": 0.4911242603550296,
      "eval_top_5_accuracy": 0.7899408284023669,
      "step": 1802
    },
    {
      "epoch": 10.002708333333333,
      "grad_norm": 41.797882080078125,
      "learning_rate": 2.629166666666667e-05,
      "loss": 2.0471,
      "step": 1900
    },
    {
      "epoch": 10.00498611111111,
      "eval_accuracy": 0.5177514792899408,
      "eval_f1": 0.5056634660885672,
      "eval_loss": 1.9989553689956665,
      "eval_precision": 0.5871284164553396,
      "eval_recall": 0.5177514792899408,
      "eval_runtime": 11.7241,
      "eval_samples_per_second": 28.83,
      "eval_steps_per_second": 14.415,
      "eval_top_10_accuracy": 0.9053254437869822,
      "eval_top_1_accuracy": 0.514792899408284,
      "eval_top_5_accuracy": 0.8106508875739645,
      "step": 1982
    },
    {
      "epoch": 11.000479166666667,
      "grad_norm": 35.05084228515625,
      "learning_rate": 2.7680555555555558e-05,
      "loss": 2.1684,
      "step": 2000
    },
    {
      "epoch": 11.003256944444445,
      "grad_norm": 32.317020416259766,
      "learning_rate": 2.9069444444444442e-05,
      "loss": 1.3242,
      "step": 2100
    },
    {
      "epoch": 11.005006944444444,
      "eval_accuracy": 0.5473372781065089,
      "eval_f1": 0.5199061622138544,
      "eval_loss": 1.896411418914795,
      "eval_precision": 0.582156945618484,
      "eval_recall": 0.5473372781065089,
      "eval_runtime": 11.653,
      "eval_samples_per_second": 29.005,
      "eval_steps_per_second": 14.503,
      "eval_top_10_accuracy": 0.893491124260355,
      "eval_top_1_accuracy": 0.5473372781065089,
      "eval_top_5_accuracy": 0.8165680473372781,
      "step": 2163
    },
    {
      "epoch": 12.001027777777777,
      "grad_norm": 20.89638900756836,
      "learning_rate": 3.0458333333333333e-05,
      "loss": 1.244,
      "step": 2200
    },
    {
      "epoch": 12.003805555555555,
      "grad_norm": 25.03165054321289,
      "learning_rate": 3.184722222222222e-05,
      "loss": 0.8746,
      "step": 2300
    },
    {
      "epoch": 12.005,
      "eval_accuracy": 0.5562130177514792,
      "eval_f1": 0.531996208919286,
      "eval_loss": 1.8221518993377686,
      "eval_precision": 0.5796251825097979,
      "eval_recall": 0.5562130177514792,
      "eval_runtime": 11.5373,
      "eval_samples_per_second": 29.296,
      "eval_steps_per_second": 14.648,
      "eval_top_10_accuracy": 0.908284023668639,
      "eval_top_1_accuracy": 0.5562130177514792,
      "eval_top_5_accuracy": 0.8254437869822485,
      "step": 2343
    },
    {
      "epoch": 13.00157638888889,
      "grad_norm": 30.899749755859375,
      "learning_rate": 3.3236111111111114e-05,
      "loss": 0.6561,
      "step": 2400
    },
    {
      "epoch": 13.004354166666667,
      "grad_norm": 9.373037338256836,
      "learning_rate": 3.4625e-05,
      "loss": 0.5537,
      "step": 2500
    },
    {
      "epoch": 13.004993055555556,
      "eval_accuracy": 0.5769230769230769,
      "eval_f1": 0.5467897487128257,
      "eval_loss": 1.7525219917297363,
      "eval_precision": 0.5813186813186813,
      "eval_recall": 0.5769230769230769,
      "eval_runtime": 11.5774,
      "eval_samples_per_second": 29.195,
      "eval_steps_per_second": 14.597,
      "eval_top_10_accuracy": 0.9142011834319527,
      "eval_top_1_accuracy": 0.5769230769230769,
      "eval_top_5_accuracy": 0.834319526627219,
      "step": 2523
    },
    {
      "epoch": 14.002125,
      "grad_norm": 4.441218376159668,
      "learning_rate": 3.601388888888889e-05,
      "loss": 0.3664,
      "step": 2600
    },
    {
      "epoch": 14.004902777777778,
      "grad_norm": 39.638824462890625,
      "learning_rate": 3.740277777777778e-05,
      "loss": 0.4081,
      "step": 2700
    },
    {
      "epoch": 14.00498611111111,
      "eval_accuracy": 0.5946745562130178,
      "eval_f1": 0.5833541540642132,
      "eval_loss": 1.7350622415542603,
      "eval_precision": 0.6683572837418991,
      "eval_recall": 0.5946745562130178,
      "eval_runtime": 12.1445,
      "eval_samples_per_second": 27.831,
      "eval_steps_per_second": 13.916,
      "eval_top_10_accuracy": 0.8964497041420119,
      "eval_top_1_accuracy": 0.5946745562130178,
      "eval_top_5_accuracy": 0.8136094674556213,
      "step": 2703
    },
    {
      "epoch": 15.002673611111112,
      "grad_norm": 7.7865376472473145,
      "learning_rate": 3.879166666666667e-05,
      "loss": 0.17,
      "step": 2800
    },
    {
      "epoch": 15.005006944444444,
      "eval_accuracy": 0.5591715976331361,
      "eval_f1": 0.5341941753184356,
      "eval_loss": 1.6997803449630737,
      "eval_precision": 0.5763416071108378,
      "eval_recall": 0.5591715976331361,
      "eval_runtime": 12.1127,
      "eval_samples_per_second": 27.905,
      "eval_steps_per_second": 13.952,
      "eval_top_10_accuracy": 0.908284023668639,
      "eval_top_1_accuracy": 0.5591715976331361,
      "eval_top_5_accuracy": 0.8224852071005917,
      "step": 2884
    },
    {
      "epoch": 16.000444444444444,
      "grad_norm": 7.096034049987793,
      "learning_rate": 4.018055555555556e-05,
      "loss": 0.3333,
      "step": 2900
    },
    {
      "epoch": 16.003222222222224,
      "grad_norm": 8.13654613494873,
      "learning_rate": 4.1569444444444444e-05,
      "loss": 0.2053,
      "step": 3000
    },
    {
      "epoch": 16.005,
      "eval_accuracy": 0.5650887573964497,
      "eval_f1": 0.5390417275032658,
      "eval_loss": 1.7339895963668823,
      "eval_precision": 0.6214919695688926,
      "eval_recall": 0.5650887573964497,
      "eval_runtime": 12.1867,
      "eval_samples_per_second": 27.735,
      "eval_steps_per_second": 13.868,
      "eval_top_10_accuracy": 0.908284023668639,
      "eval_top_1_accuracy": 0.5650887573964497,
      "eval_top_5_accuracy": 0.834319526627219,
      "step": 3064
    },
    {
      "epoch": 17.000993055555554,
      "grad_norm": 2.6876680850982666,
      "learning_rate": 4.295833333333333e-05,
      "loss": 0.1874,
      "step": 3100
    },
    {
      "epoch": 17.003770833333334,
      "grad_norm": 29.59245491027832,
      "learning_rate": 4.4347222222222226e-05,
      "loss": 0.1434,
      "step": 3200
    },
    {
      "epoch": 17.004993055555556,
      "eval_accuracy": 0.6005917159763313,
      "eval_f1": 0.5806121557600847,
      "eval_loss": 1.7350496053695679,
      "eval_precision": 0.6346953096213452,
      "eval_recall": 0.6005917159763313,
      "eval_runtime": 12.2719,
      "eval_samples_per_second": 27.543,
      "eval_steps_per_second": 13.771,
      "eval_top_10_accuracy": 0.9142011834319527,
      "eval_top_1_accuracy": 0.6005917159763313,
      "eval_top_5_accuracy": 0.8431952662721893,
      "step": 3244
    },
    {
      "epoch": 18.001541666666668,
      "grad_norm": 0.8009536266326904,
      "learning_rate": 4.573611111111111e-05,
      "loss": 0.0921,
      "step": 3300
    },
    {
      "epoch": 18.004319444444445,
      "grad_norm": 2.7831170558929443,
      "learning_rate": 4.7125e-05,
      "loss": 0.1957,
      "step": 3400
    },
    {
      "epoch": 18.004986111111112,
      "eval_accuracy": 0.5621301775147929,
      "eval_f1": 0.5349809460756207,
      "eval_loss": 1.8179223537445068,
      "eval_precision": 0.6059920848382387,
      "eval_recall": 0.5621301775147929,
      "eval_runtime": 12.0029,
      "eval_samples_per_second": 28.16,
      "eval_steps_per_second": 14.08,
      "eval_top_10_accuracy": 0.9142011834319527,
      "eval_top_1_accuracy": 0.5621301775147929,
      "eval_top_5_accuracy": 0.8372781065088757,
      "step": 3424
    },
    {
      "epoch": 19.00209027777778,
      "grad_norm": 0.349692165851593,
      "learning_rate": 4.8513888888888894e-05,
      "loss": 0.1161,
      "step": 3500
    },
    {
      "epoch": 19.004868055555555,
      "grad_norm": 86.96188354492188,
      "learning_rate": 4.990277777777778e-05,
      "loss": 0.1636,
      "step": 3600
    },
    {
      "epoch": 19.005006944444446,
      "eval_accuracy": 0.6153846153846154,
      "eval_f1": 0.5916679966975824,
      "eval_loss": 1.7831283807754517,
      "eval_precision": 0.6401178949255872,
      "eval_recall": 0.6153846153846154,
      "eval_runtime": 11.9167,
      "eval_samples_per_second": 28.364,
      "eval_steps_per_second": 14.182,
      "eval_top_10_accuracy": 0.8905325443786982,
      "eval_top_1_accuracy": 0.6153846153846154,
      "eval_top_5_accuracy": 0.8224852071005917,
      "step": 3605
    },
    {
      "epoch": 20.00263888888889,
      "grad_norm": 0.18171709775924683,
      "learning_rate": 4.985648148148148e-05,
      "loss": 0.0908,
      "step": 3700
    },
    {
      "epoch": 20.005,
      "eval_accuracy": 0.621301775147929,
      "eval_f1": 0.6014277142975367,
      "eval_loss": 1.7552212476730347,
      "eval_precision": 0.6504156100309946,
      "eval_recall": 0.621301775147929,
      "eval_runtime": 11.9034,
      "eval_samples_per_second": 28.395,
      "eval_steps_per_second": 14.198,
      "eval_top_10_accuracy": 0.9053254437869822,
      "eval_top_1_accuracy": 0.621301775147929,
      "eval_top_5_accuracy": 0.8402366863905325,
      "step": 3785
    },
    {
      "epoch": 21.000409722222223,
      "grad_norm": 32.656211853027344,
      "learning_rate": 4.970216049382716e-05,
      "loss": 0.1217,
      "step": 3800
    },
    {
      "epoch": 21.0031875,
      "grad_norm": 0.07043986022472382,
      "learning_rate": 4.954783950617284e-05,
      "loss": 0.058,
      "step": 3900
    },
    {
      "epoch": 21.004993055555556,
      "eval_accuracy": 0.621301775147929,
      "eval_f1": 0.5961879507737495,
      "eval_loss": 1.8422198295593262,
      "eval_precision": 0.6392187940264863,
      "eval_recall": 0.621301775147929,
      "eval_runtime": 11.7783,
      "eval_samples_per_second": 28.697,
      "eval_steps_per_second": 14.348,
      "eval_top_10_accuracy": 0.9112426035502958,
      "eval_top_1_accuracy": 0.6242603550295858,
      "eval_top_5_accuracy": 0.8254437869822485,
      "step": 3965
    },
    {
      "epoch": 22.000958333333333,
      "grad_norm": 0.16647548973560333,
      "learning_rate": 4.939351851851852e-05,
      "loss": 0.1357,
      "step": 4000
    },
    {
      "epoch": 22.00373611111111,
      "grad_norm": 0.13775382936000824,
      "learning_rate": 4.92391975308642e-05,
      "loss": 0.0924,
      "step": 4100
    },
    {
      "epoch": 22.004986111111112,
      "eval_accuracy": 0.6005917159763313,
      "eval_f1": 0.5735153735153736,
      "eval_loss": 1.834716796875,
      "eval_precision": 0.6217596506058044,
      "eval_recall": 0.6005917159763313,
      "eval_runtime": 11.8787,
      "eval_samples_per_second": 28.454,
      "eval_steps_per_second": 14.227,
      "eval_top_10_accuracy": 0.9201183431952663,
      "eval_top_1_accuracy": 0.6005917159763313,
      "eval_top_5_accuracy": 0.8224852071005917,
      "step": 4145
    },
    {
      "epoch": 23.001506944444444,
      "grad_norm": 1.0737590789794922,
      "learning_rate": 4.908487654320988e-05,
      "loss": 0.102,
      "step": 4200
    },
    {
      "epoch": 23.004284722222224,
      "grad_norm": 3.3763539791107178,
      "learning_rate": 4.893055555555556e-05,
      "loss": 0.0799,
      "step": 4300
    },
    {
      "epoch": 23.005006944444446,
      "eval_accuracy": 0.6035502958579881,
      "eval_f1": 0.572392564700257,
      "eval_loss": 1.9649921655654907,
      "eval_precision": 0.6182439355516278,
      "eval_recall": 0.6035502958579881,
      "eval_runtime": 12.1311,
      "eval_samples_per_second": 27.862,
      "eval_steps_per_second": 13.931,
      "eval_top_10_accuracy": 0.8846153846153846,
      "eval_top_1_accuracy": 0.6035502958579881,
      "eval_top_5_accuracy": 0.8106508875739645,
      "step": 4326
    },
    {
      "epoch": 24.002055555555554,
      "grad_norm": 116.17411804199219,
      "learning_rate": 4.877623456790124e-05,
      "loss": 0.1349,
      "step": 4400
    },
    {
      "epoch": 24.004833333333334,
      "grad_norm": 47.67039108276367,
      "learning_rate": 4.8621913580246915e-05,
      "loss": 0.176,
      "step": 4500
    },
    {
      "epoch": 24.005,
      "eval_accuracy": 0.5857988165680473,
      "eval_f1": 0.5670846247769326,
      "eval_loss": 1.9325687885284424,
      "eval_precision": 0.6240464663541586,
      "eval_recall": 0.5857988165680473,
      "eval_runtime": 12.1023,
      "eval_samples_per_second": 27.929,
      "eval_steps_per_second": 13.964,
      "eval_top_10_accuracy": 0.9142011834319527,
      "eval_top_1_accuracy": 0.5857988165680473,
      "eval_top_5_accuracy": 0.8402366863905325,
      "step": 4506
    },
    {
      "epoch": 25.002604166666668,
      "grad_norm": 0.11518964916467667,
      "learning_rate": 4.846759259259259e-05,
      "loss": 0.0786,
      "step": 4600
    },
    {
      "epoch": 25.004993055555556,
      "eval_accuracy": 0.6124260355029586,
      "eval_f1": 0.599836816700722,
      "eval_loss": 1.775345802307129,
      "eval_precision": 0.660682586644125,
      "eval_recall": 0.6124260355029586,
      "eval_runtime": 11.4818,
      "eval_samples_per_second": 29.438,
      "eval_steps_per_second": 14.719,
      "eval_top_10_accuracy": 0.9142011834319527,
      "eval_top_1_accuracy": 0.6124260355029586,
      "eval_top_5_accuracy": 0.849112426035503,
      "step": 4686
    },
    {
      "epoch": 26.000375,
      "grad_norm": 0.5315603017807007,
      "learning_rate": 4.831327160493828e-05,
      "loss": 0.2613,
      "step": 4700
    },
    {
      "epoch": 26.00315277777778,
      "grad_norm": 0.860506534576416,
      "learning_rate": 4.81604938271605e-05,
      "loss": 0.242,
      "step": 4800
    },
    {
      "epoch": 26.004986111111112,
      "eval_accuracy": 0.5769230769230769,
      "eval_f1": 0.5552139674920741,
      "eval_loss": 2.021881580352783,
      "eval_precision": 0.6336890673429134,
      "eval_recall": 0.5769230769230769,
      "eval_runtime": 11.9203,
      "eval_samples_per_second": 28.355,
      "eval_steps_per_second": 14.177,
      "eval_top_10_accuracy": 0.8875739644970414,
      "eval_top_1_accuracy": 0.5769230769230769,
      "eval_top_5_accuracy": 0.772189349112426,
      "step": 4866
    },
    {
      "epoch": 27.000923611111112,
      "grad_norm": 5.388744354248047,
      "learning_rate": 4.8006172839506177e-05,
      "loss": 0.1656,
      "step": 4900
    },
    {
      "epoch": 27.00370138888889,
      "grad_norm": 2.032120704650879,
      "learning_rate": 4.7851851851851854e-05,
      "loss": 0.1767,
      "step": 5000
    },
    {
      "epoch": 27.005006944444446,
      "eval_accuracy": 0.5828402366863905,
      "eval_f1": 0.5721016163323855,
      "eval_loss": 1.9743586778640747,
      "eval_precision": 0.6330223031406463,
      "eval_recall": 0.5828402366863905,
      "eval_runtime": 11.9635,
      "eval_samples_per_second": 28.253,
      "eval_steps_per_second": 14.126,
      "eval_top_10_accuracy": 0.9023668639053254,
      "eval_top_1_accuracy": 0.5828402366863905,
      "eval_top_5_accuracy": 0.8165680473372781,
      "step": 5047
    },
    {
      "epoch": 28.001472222222223,
      "grad_norm": 1.4519288539886475,
      "learning_rate": 4.769753086419753e-05,
      "loss": 0.19,
      "step": 5100
    },
    {
      "epoch": 28.00425,
      "grad_norm": 7.525012016296387,
      "learning_rate": 4.754320987654321e-05,
      "loss": 0.14,
      "step": 5200
    },
    {
      "epoch": 28.005,
      "eval_accuracy": 0.5769230769230769,
      "eval_f1": 0.5429622288219573,
      "eval_loss": 2.1995532512664795,
      "eval_precision": 0.5982988165680473,
      "eval_recall": 0.5769230769230769,
      "eval_runtime": 11.6103,
      "eval_samples_per_second": 29.112,
      "eval_steps_per_second": 14.556,
      "eval_top_10_accuracy": 0.8609467455621301,
      "eval_top_1_accuracy": 0.5769230769230769,
      "eval_top_5_accuracy": 0.7810650887573964,
      "step": 5227
    },
    {
      "epoch": 29.002020833333333,
      "grad_norm": 0.7301017045974731,
      "learning_rate": 4.7388888888888894e-05,
      "loss": 0.2472,
      "step": 5300
    },
    {
      "epoch": 29.00479861111111,
      "grad_norm": 0.6413145065307617,
      "learning_rate": 4.723456790123457e-05,
      "loss": 0.104,
      "step": 5400
    },
    {
      "epoch": 29.004993055555556,
      "eval_accuracy": 0.5769230769230769,
      "eval_f1": 0.5640588044434198,
      "eval_loss": 2.0880820751190186,
      "eval_precision": 0.6145991828684136,
      "eval_recall": 0.5769230769230769,
      "eval_runtime": 11.4084,
      "eval_samples_per_second": 29.627,
      "eval_steps_per_second": 14.814,
      "eval_top_10_accuracy": 0.8875739644970414,
      "eval_top_1_accuracy": 0.5769230769230769,
      "eval_top_5_accuracy": 0.8165680473372781,
      "step": 5407
    },
    {
      "epoch": 30.002569444444443,
      "grad_norm": 0.333312064409256,
      "learning_rate": 4.708024691358025e-05,
      "loss": 0.1454,
      "step": 5500
    },
    {
      "epoch": 30.004986111111112,
      "eval_accuracy": 0.5621301775147929,
      "eval_f1": 0.5447567389875081,
      "eval_loss": 2.33941388130188,
      "eval_precision": 0.628030303030303,
      "eval_recall": 0.5621301775147929,
      "eval_runtime": 12.0785,
      "eval_samples_per_second": 27.984,
      "eval_steps_per_second": 13.992,
      "eval_top_10_accuracy": 0.8905325443786982,
      "eval_top_1_accuracy": 0.5621301775147929,
      "eval_top_5_accuracy": 0.7958579881656804,
      "step": 5587
    },
    {
      "epoch": 31.000340277777777,
      "grad_norm": 0.10098100453615189,
      "learning_rate": 4.692592592592593e-05,
      "loss": 0.1388,
      "step": 5600
    },
    {
      "epoch": 31.003118055555557,
      "grad_norm": 0.03804658353328705,
      "learning_rate": 4.6771604938271605e-05,
      "loss": 0.2221,
      "step": 5700
    },
    {
      "epoch": 31.005006944444446,
      "eval_accuracy": 0.5946745562130178,
      "eval_f1": 0.5881447119612799,
      "eval_loss": 1.9360294342041016,
      "eval_precision": 0.6606297548605241,
      "eval_recall": 0.5946745562130178,
      "eval_runtime": 11.5488,
      "eval_samples_per_second": 29.267,
      "eval_steps_per_second": 14.634,
      "eval_top_10_accuracy": 0.9023668639053254,
      "eval_top_1_accuracy": 0.5946745562130178,
      "eval_top_5_accuracy": 0.8224852071005917,
      "step": 5768
    },
    {
      "epoch": 32.00088888888889,
      "grad_norm": 0.024992674589157104,
      "learning_rate": 4.661728395061728e-05,
      "loss": 0.1003,
      "step": 5800
    },
    {
      "epoch": 32.00366666666667,
      "grad_norm": 0.2089391052722931,
      "learning_rate": 4.646296296296297e-05,
      "loss": 0.1026,
      "step": 5900
    },
    {
      "epoch": 32.005,
      "eval_accuracy": 0.6035502958579881,
      "eval_f1": 0.5831550927704774,
      "eval_loss": 2.092036485671997,
      "eval_precision": 0.6375950972104818,
      "eval_recall": 0.6035502958579881,
      "eval_runtime": 11.4387,
      "eval_samples_per_second": 29.549,
      "eval_steps_per_second": 14.774,
      "eval_top_10_accuracy": 0.893491124260355,
      "eval_top_1_accuracy": 0.6035502958579881,
      "eval_top_5_accuracy": 0.8106508875739645,
      "step": 5948
    },
    {
      "epoch": 33.0014375,
      "grad_norm": 0.051621366292238235,
      "learning_rate": 4.6308641975308645e-05,
      "loss": 0.0709,
      "step": 6000
    },
    {
      "epoch": 33.004215277777774,
      "grad_norm": 0.05871783196926117,
      "learning_rate": 4.615432098765433e-05,
      "loss": 0.0968,
      "step": 6100
    },
    {
      "epoch": 33.00499305555556,
      "eval_accuracy": 0.5739644970414202,
      "eval_f1": 0.5541961818589037,
      "eval_loss": 2.2745707035064697,
      "eval_precision": 0.6308041317656701,
      "eval_recall": 0.5739644970414202,
      "eval_runtime": 11.2862,
      "eval_samples_per_second": 29.948,
      "eval_steps_per_second": 14.974,
      "eval_top_10_accuracy": 0.8846153846153846,
      "eval_top_1_accuracy": 0.5739644970414202,
      "eval_top_5_accuracy": 0.8047337278106509,
      "step": 6128
    },
    {
      "epoch": 34.00198611111111,
      "grad_norm": 0.23713918030261993,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.2097,
      "step": 6200
    },
    {
      "epoch": 34.00476388888889,
      "grad_norm": 0.9631951451301575,
      "learning_rate": 4.5845679012345684e-05,
      "loss": 0.1864,
      "step": 6300
    },
    {
      "epoch": 34.00498611111111,
      "eval_accuracy": 0.5887573964497042,
      "eval_f1": 0.5704292684109307,
      "eval_loss": 2.208103656768799,
      "eval_precision": 0.639407621471231,
      "eval_recall": 0.5887573964497042,
      "eval_runtime": 11.7319,
      "eval_samples_per_second": 28.81,
      "eval_steps_per_second": 14.405,
      "eval_top_10_accuracy": 0.8698224852071006,
      "eval_top_1_accuracy": 0.5887573964497042,
      "eval_top_5_accuracy": 0.8047337278106509,
      "step": 6308
    },
    {
      "epoch": 35.00253472222222,
      "grad_norm": 0.04889826104044914,
      "learning_rate": 4.569135802469136e-05,
      "loss": 0.1353,
      "step": 6400
    },
    {
      "epoch": 35.005006944444446,
      "eval_accuracy": 0.5798816568047337,
      "eval_f1": 0.5635964955491581,
      "eval_loss": 2.1853461265563965,
      "eval_precision": 0.6133398652629422,
      "eval_recall": 0.5798816568047337,
      "eval_runtime": 11.3905,
      "eval_samples_per_second": 29.674,
      "eval_steps_per_second": 14.837,
      "eval_top_10_accuracy": 0.893491124260355,
      "eval_top_1_accuracy": 0.5798816568047337,
      "eval_top_5_accuracy": 0.8254437869822485,
      "step": 6489
    },
    {
      "epoch": 36.000305555555556,
      "grad_norm": 0.8964897394180298,
      "learning_rate": 4.553703703703704e-05,
      "loss": 0.1746,
      "step": 6500
    },
    {
      "epoch": 36.003083333333336,
      "grad_norm": 0.05014768987894058,
      "learning_rate": 4.538271604938272e-05,
      "loss": 0.1618,
      "step": 6600
    },
    {
      "epoch": 36.005,
      "eval_accuracy": 0.5710059171597633,
      "eval_f1": 0.5514817365409082,
      "eval_loss": 2.266056537628174,
      "eval_precision": 0.624323753169907,
      "eval_recall": 0.5710059171597633,
      "eval_runtime": 11.0844,
      "eval_samples_per_second": 30.493,
      "eval_steps_per_second": 15.247,
      "eval_top_10_accuracy": 0.8698224852071006,
      "eval_top_1_accuracy": 0.5710059171597633,
      "eval_top_5_accuracy": 0.7958579881656804,
      "step": 6669
    },
    {
      "epoch": 37.00085416666667,
      "grad_norm": 0.18619082868099213,
      "learning_rate": 4.5228395061728395e-05,
      "loss": 0.3118,
      "step": 6700
    },
    {
      "epoch": 37.00363194444444,
      "grad_norm": 0.18089838325977325,
      "learning_rate": 4.507407407407407e-05,
      "loss": 0.259,
      "step": 6800
    },
    {
      "epoch": 37.00499305555556,
      "eval_accuracy": 0.5739644970414202,
      "eval_f1": 0.5459162632239556,
      "eval_loss": 2.3162882328033447,
      "eval_precision": 0.6088229078613694,
      "eval_recall": 0.5739644970414202,
      "eval_runtime": 11.492,
      "eval_samples_per_second": 29.412,
      "eval_steps_per_second": 14.706,
      "eval_top_10_accuracy": 0.8579881656804734,
      "eval_top_1_accuracy": 0.5739644970414202,
      "eval_top_5_accuracy": 0.7869822485207101,
      "step": 6849
    },
    {
      "epoch": 38.00140277777778,
      "grad_norm": 0.049058422446250916,
      "learning_rate": 4.49212962962963e-05,
      "loss": 0.3374,
      "step": 6900
    },
    {
      "epoch": 38.00418055555556,
      "grad_norm": 0.4456841051578522,
      "learning_rate": 4.476697530864198e-05,
      "loss": 0.3394,
      "step": 7000
    },
    {
      "epoch": 38.00498611111111,
      "eval_accuracy": 0.5769230769230769,
      "eval_f1": 0.5614232086125578,
      "eval_loss": 2.0984292030334473,
      "eval_precision": 0.6154339250493096,
      "eval_recall": 0.5769230769230769,
      "eval_runtime": 11.997,
      "eval_samples_per_second": 28.174,
      "eval_steps_per_second": 14.087,
      "eval_top_10_accuracy": 0.8905325443786982,
      "eval_top_1_accuracy": 0.5769230769230769,
      "eval_top_5_accuracy": 0.7988165680473372,
      "step": 7029
    },
    {
      "epoch": 39.00195138888889,
      "grad_norm": 0.010750464163720608,
      "learning_rate": 4.4612654320987657e-05,
      "loss": 0.1193,
      "step": 7100
    },
    {
      "epoch": 39.004729166666664,
      "grad_norm": 0.22571489214897156,
      "learning_rate": 4.4458333333333334e-05,
      "loss": 0.0833,
      "step": 7200
    },
    {
      "epoch": 39.005006944444446,
      "eval_accuracy": 0.5532544378698225,
      "eval_f1": 0.5328080203819848,
      "eval_loss": 2.281132936477661,
      "eval_precision": 0.6051346089807629,
      "eval_recall": 0.5532544378698225,
      "eval_runtime": 11.8037,
      "eval_samples_per_second": 28.635,
      "eval_steps_per_second": 14.317,
      "eval_top_10_accuracy": 0.8698224852071006,
      "eval_top_1_accuracy": 0.5532544378698225,
      "eval_top_5_accuracy": 0.8047337278106509,
      "step": 7210
    },
    {
      "epoch": 40.0025,
      "grad_norm": 1.91786789894104,
      "learning_rate": 4.430401234567901e-05,
      "loss": 0.1259,
      "step": 7300
    },
    {
      "epoch": 40.005,
      "eval_accuracy": 0.5828402366863905,
      "eval_f1": 0.551048433814706,
      "eval_loss": 2.2599146366119385,
      "eval_precision": 0.5806347252353169,
      "eval_recall": 0.5828402366863905,
      "eval_runtime": 11.6047,
      "eval_samples_per_second": 29.126,
      "eval_steps_per_second": 14.563,
      "eval_top_10_accuracy": 0.8698224852071006,
      "eval_top_1_accuracy": 0.5828402366863905,
      "eval_top_5_accuracy": 0.7899408284023669,
      "step": 7390
    },
    {
      "epoch": 40.005,
      "step": 7390,
      "total_flos": 5.1831774087363035e+19,
      "train_loss": 3.1396320400444515,
      "train_runtime": 4689.7449,
      "train_samples_per_second": 61.411,
      "train_steps_per_second": 7.676
    }
  ],
  "logging_steps": 100,
  "max_steps": 36000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 20,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 20
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.1831774087363035e+19,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}