{
  "best_metric": 0.897123396396637,
  "best_model_checkpoint": "./cocoa_outputs_resnet/checkpoint-980",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 980,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05102040816326531,
      "grad_norm": 9.393156051635742,
      "learning_rate": 1.979591836734694e-05,
      "loss": 1.8572,
      "step": 10
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 6.8461503982543945,
      "learning_rate": 1.9591836734693877e-05,
      "loss": 1.8224,
      "step": 20
    },
    {
      "epoch": 0.15306122448979592,
      "grad_norm": 8.049448013305664,
      "learning_rate": 1.9387755102040817e-05,
      "loss": 1.7955,
      "step": 30
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 6.181807041168213,
      "learning_rate": 1.9183673469387756e-05,
      "loss": 1.7641,
      "step": 40
    },
    {
      "epoch": 0.25510204081632654,
      "grad_norm": 6.991772651672363,
      "learning_rate": 1.8979591836734696e-05,
      "loss": 1.7421,
      "step": 50
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 6.233796119689941,
      "learning_rate": 1.8775510204081636e-05,
      "loss": 1.7018,
      "step": 60
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 7.064742088317871,
      "learning_rate": 1.8571428571428575e-05,
      "loss": 1.6763,
      "step": 70
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 7.047808647155762,
      "learning_rate": 1.836734693877551e-05,
      "loss": 1.654,
      "step": 80
    },
    {
      "epoch": 0.45918367346938777,
      "grad_norm": 8.950271606445312,
      "learning_rate": 1.816326530612245e-05,
      "loss": 1.6461,
      "step": 90
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 7.686429023742676,
      "learning_rate": 1.795918367346939e-05,
      "loss": 1.6049,
      "step": 100
    },
    {
      "epoch": 0.5612244897959183,
      "grad_norm": 6.434399127960205,
      "learning_rate": 1.7755102040816327e-05,
      "loss": 1.5926,
      "step": 110
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 6.048853397369385,
      "learning_rate": 1.7551020408163266e-05,
      "loss": 1.5614,
      "step": 120
    },
    {
      "epoch": 0.6632653061224489,
      "grad_norm": 12.146856307983398,
      "learning_rate": 1.7346938775510206e-05,
      "loss": 1.5344,
      "step": 130
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 8.939432144165039,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 1.4892,
      "step": 140
    },
    {
      "epoch": 0.7653061224489796,
      "grad_norm": 16.924053192138672,
      "learning_rate": 1.6938775510204085e-05,
      "loss": 1.4829,
      "step": 150
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 10.929306983947754,
      "learning_rate": 1.673469387755102e-05,
      "loss": 1.5136,
      "step": 160
    },
    {
      "epoch": 0.8673469387755102,
      "grad_norm": 12.943446159362793,
      "learning_rate": 1.653061224489796e-05,
      "loss": 1.4316,
      "step": 170
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": 6.890258312225342,
      "learning_rate": 1.63265306122449e-05,
      "loss": 1.4373,
      "step": 180
    },
    {
      "epoch": 0.9693877551020408,
      "grad_norm": 9.790729522705078,
      "learning_rate": 1.612244897959184e-05,
      "loss": 1.4094,
      "step": 190
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8592057761732852,
      "eval_loss": 1.4767718315124512,
      "eval_runtime": 14.5787,
      "eval_samples_per_second": 19.0,
      "eval_steps_per_second": 2.401,
      "step": 196
    },
    {
      "epoch": 1.0204081632653061,
      "grad_norm": 20.24932861328125,
      "learning_rate": 1.5918367346938776e-05,
      "loss": 1.4063,
      "step": 200
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 14.811591148376465,
      "learning_rate": 1.5714285714285715e-05,
      "loss": 1.3551,
      "step": 210
    },
    {
      "epoch": 1.1224489795918366,
      "grad_norm": 18.894763946533203,
      "learning_rate": 1.5510204081632655e-05,
      "loss": 1.3314,
      "step": 220
    },
    {
      "epoch": 1.1734693877551021,
      "grad_norm": 13.06529426574707,
      "learning_rate": 1.530612244897959e-05,
      "loss": 1.3112,
      "step": 230
    },
    {
      "epoch": 1.2244897959183674,
      "grad_norm": 16.423351287841797,
      "learning_rate": 1.510204081632653e-05,
      "loss": 1.2519,
      "step": 240
    },
    {
      "epoch": 1.2755102040816326,
      "grad_norm": 11.016277313232422,
      "learning_rate": 1.4897959183673472e-05,
      "loss": 1.3565,
      "step": 250
    },
    {
      "epoch": 1.3265306122448979,
      "grad_norm": 7.271716594696045,
      "learning_rate": 1.469387755102041e-05,
      "loss": 1.2681,
      "step": 260
    },
    {
      "epoch": 1.3775510204081631,
      "grad_norm": 8.437969207763672,
      "learning_rate": 1.448979591836735e-05,
      "loss": 1.2675,
      "step": 270
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 6.352739334106445,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 1.1948,
      "step": 280
    },
    {
      "epoch": 1.4795918367346939,
      "grad_norm": 17.921051025390625,
      "learning_rate": 1.4081632653061225e-05,
      "loss": 1.3366,
      "step": 290
    },
    {
      "epoch": 1.5306122448979593,
      "grad_norm": 22.707721710205078,
      "learning_rate": 1.3877551020408165e-05,
      "loss": 1.2684,
      "step": 300
    },
    {
      "epoch": 1.5816326530612246,
      "grad_norm": 8.037663459777832,
      "learning_rate": 1.3673469387755102e-05,
      "loss": 1.2322,
      "step": 310
    },
    {
      "epoch": 1.6326530612244898,
      "grad_norm": 9.421684265136719,
      "learning_rate": 1.3469387755102042e-05,
      "loss": 1.1945,
      "step": 320
    },
    {
      "epoch": 1.683673469387755,
      "grad_norm": 27.85601043701172,
      "learning_rate": 1.326530612244898e-05,
      "loss": 1.2519,
      "step": 330
    },
    {
      "epoch": 1.7346938775510203,
      "grad_norm": 15.291147232055664,
      "learning_rate": 1.3061224489795918e-05,
      "loss": 1.1934,
      "step": 340
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 10.985498428344727,
      "learning_rate": 1.2857142857142859e-05,
      "loss": 1.123,
      "step": 350
    },
    {
      "epoch": 1.836734693877551,
      "grad_norm": 9.827385902404785,
      "learning_rate": 1.2653061224489798e-05,
      "loss": 1.1677,
      "step": 360
    },
    {
      "epoch": 1.8877551020408163,
      "grad_norm": 16.994632720947266,
      "learning_rate": 1.2448979591836736e-05,
      "loss": 1.171,
      "step": 370
    },
    {
      "epoch": 1.9387755102040818,
      "grad_norm": 16.16167449951172,
      "learning_rate": 1.2244897959183674e-05,
      "loss": 1.1488,
      "step": 380
    },
    {
      "epoch": 1.989795918367347,
      "grad_norm": 12.466065406799316,
      "learning_rate": 1.2040816326530614e-05,
      "loss": 1.0664,
      "step": 390
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8628158844765343,
      "eval_loss": 1.2089825868606567,
      "eval_runtime": 17.1021,
      "eval_samples_per_second": 16.197,
      "eval_steps_per_second": 2.047,
      "step": 392
    },
    {
      "epoch": 2.0408163265306123,
      "grad_norm": 14.415572166442871,
      "learning_rate": 1.1836734693877552e-05,
      "loss": 1.1081,
      "step": 400
    },
    {
      "epoch": 2.0918367346938775,
      "grad_norm": 16.120677947998047,
      "learning_rate": 1.1632653061224491e-05,
      "loss": 1.1347,
      "step": 410
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 9.960640907287598,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 1.0755,
      "step": 420
    },
    {
      "epoch": 2.193877551020408,
      "grad_norm": 14.734106063842773,
      "learning_rate": 1.1224489795918367e-05,
      "loss": 1.0976,
      "step": 430
    },
    {
      "epoch": 2.2448979591836733,
      "grad_norm": 12.98324203491211,
      "learning_rate": 1.1020408163265306e-05,
      "loss": 0.9844,
      "step": 440
    },
    {
      "epoch": 2.295918367346939,
      "grad_norm": 8.834336280822754,
      "learning_rate": 1.0816326530612246e-05,
      "loss": 1.0923,
      "step": 450
    },
    {
      "epoch": 2.3469387755102042,
      "grad_norm": 10.948126792907715,
      "learning_rate": 1.0612244897959186e-05,
      "loss": 0.9711,
      "step": 460
    },
    {
      "epoch": 2.3979591836734695,
      "grad_norm": 13.707374572753906,
      "learning_rate": 1.0408163265306123e-05,
      "loss": 1.0786,
      "step": 470
    },
    {
      "epoch": 2.4489795918367347,
      "grad_norm": 18.081064224243164,
      "learning_rate": 1.0204081632653063e-05,
      "loss": 1.0399,
      "step": 480
    },
    {
      "epoch": 2.5,
      "grad_norm": 12.470099449157715,
      "learning_rate": 1e-05,
      "loss": 0.9344,
      "step": 490
    },
    {
      "epoch": 2.5510204081632653,
      "grad_norm": 10.96716022491455,
      "learning_rate": 9.795918367346939e-06,
      "loss": 1.043,
      "step": 500
    },
    {
      "epoch": 2.6020408163265305,
      "grad_norm": 7.244050025939941,
      "learning_rate": 9.591836734693878e-06,
      "loss": 0.9058,
      "step": 510
    },
    {
      "epoch": 2.6530612244897958,
      "grad_norm": 10.213088035583496,
      "learning_rate": 9.387755102040818e-06,
      "loss": 0.9683,
      "step": 520
    },
    {
      "epoch": 2.704081632653061,
      "grad_norm": 30.410015106201172,
      "learning_rate": 9.183673469387756e-06,
      "loss": 1.0396,
      "step": 530
    },
    {
      "epoch": 2.7551020408163263,
      "grad_norm": 10.457310676574707,
      "learning_rate": 8.979591836734695e-06,
      "loss": 1.0215,
      "step": 540
    },
    {
      "epoch": 2.806122448979592,
      "grad_norm": 12.294684410095215,
      "learning_rate": 8.775510204081633e-06,
      "loss": 0.9301,
      "step": 550
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 10.194703102111816,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.9541,
      "step": 560
    },
    {
      "epoch": 2.9081632653061225,
      "grad_norm": 17.80396842956543,
      "learning_rate": 8.36734693877551e-06,
      "loss": 0.964,
      "step": 570
    },
    {
      "epoch": 2.9591836734693877,
      "grad_norm": 12.601577758789062,
      "learning_rate": 8.16326530612245e-06,
      "loss": 1.0295,
      "step": 580
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8628158844765343,
      "eval_loss": 0.9923866987228394,
      "eval_runtime": 14.8495,
      "eval_samples_per_second": 18.654,
      "eval_steps_per_second": 2.357,
      "step": 588
    },
    {
      "epoch": 3.010204081632653,
      "grad_norm": 12.689225196838379,
      "learning_rate": 7.959183673469388e-06,
      "loss": 0.9564,
      "step": 590
    },
    {
      "epoch": 3.061224489795918,
      "grad_norm": 13.568258285522461,
      "learning_rate": 7.755102040816327e-06,
      "loss": 1.0031,
      "step": 600
    },
    {
      "epoch": 3.1122448979591835,
      "grad_norm": 15.86646842956543,
      "learning_rate": 7.551020408163265e-06,
      "loss": 0.9434,
      "step": 610
    },
    {
      "epoch": 3.163265306122449,
      "grad_norm": 16.88734245300293,
      "learning_rate": 7.346938775510205e-06,
      "loss": 0.9468,
      "step": 620
    },
    {
      "epoch": 3.2142857142857144,
      "grad_norm": 14.894389152526855,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.9284,
      "step": 630
    },
    {
      "epoch": 3.2653061224489797,
      "grad_norm": 13.203142166137695,
      "learning_rate": 6.938775510204082e-06,
      "loss": 0.9288,
      "step": 640
    },
    {
      "epoch": 3.316326530612245,
      "grad_norm": 13.70313835144043,
      "learning_rate": 6.734693877551021e-06,
      "loss": 0.8879,
      "step": 650
    },
    {
      "epoch": 3.36734693877551,
      "grad_norm": 22.619674682617188,
      "learning_rate": 6.530612244897959e-06,
      "loss": 0.9367,
      "step": 660
    },
    {
      "epoch": 3.4183673469387754,
      "grad_norm": 17.59436798095703,
      "learning_rate": 6.326530612244899e-06,
      "loss": 0.9176,
      "step": 670
    },
    {
      "epoch": 3.4693877551020407,
      "grad_norm": 12.488346099853516,
      "learning_rate": 6.122448979591837e-06,
      "loss": 0.9448,
      "step": 680
    },
    {
      "epoch": 3.520408163265306,
      "grad_norm": 7.665136337280273,
      "learning_rate": 5.918367346938776e-06,
      "loss": 0.8446,
      "step": 690
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 7.547515392303467,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 0.8465,
      "step": 700
    },
    {
      "epoch": 3.622448979591837,
      "grad_norm": 5.4680304527282715,
      "learning_rate": 5.510204081632653e-06,
      "loss": 0.8302,
      "step": 710
    },
    {
      "epoch": 3.673469387755102,
      "grad_norm": 22.36733055114746,
      "learning_rate": 5.306122448979593e-06,
      "loss": 0.9601,
      "step": 720
    },
    {
      "epoch": 3.7244897959183674,
      "grad_norm": 12.001816749572754,
      "learning_rate": 5.1020408163265315e-06,
      "loss": 0.8835,
      "step": 730
    },
    {
      "epoch": 3.7755102040816326,
      "grad_norm": 23.104984283447266,
      "learning_rate": 4.897959183673469e-06,
      "loss": 0.8024,
      "step": 740
    },
    {
      "epoch": 3.826530612244898,
      "grad_norm": 13.406716346740723,
      "learning_rate": 4.693877551020409e-06,
      "loss": 1.0554,
      "step": 750
    },
    {
      "epoch": 3.877551020408163,
      "grad_norm": 9.763223648071289,
      "learning_rate": 4.489795918367348e-06,
      "loss": 0.79,
      "step": 760
    },
    {
      "epoch": 3.928571428571429,
      "grad_norm": 10.93140983581543,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 0.8532,
      "step": 770
    },
    {
      "epoch": 3.979591836734694,
      "grad_norm": 10.841426849365234,
      "learning_rate": 4.081632653061225e-06,
      "loss": 0.8401,
      "step": 780
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8628158844765343,
      "eval_loss": 0.9142875075340271,
      "eval_runtime": 14.5094,
      "eval_samples_per_second": 19.091,
      "eval_steps_per_second": 2.412,
      "step": 784
    },
    {
      "epoch": 4.030612244897959,
      "grad_norm": 11.179267883300781,
      "learning_rate": 3.877551020408164e-06,
      "loss": 0.8061,
      "step": 790
    },
    {
      "epoch": 4.081632653061225,
      "grad_norm": 6.5305585861206055,
      "learning_rate": 3.6734693877551024e-06,
      "loss": 0.8525,
      "step": 800
    },
    {
      "epoch": 4.13265306122449,
      "grad_norm": 7.101966857910156,
      "learning_rate": 3.469387755102041e-06,
      "loss": 0.7967,
      "step": 810
    },
    {
      "epoch": 4.183673469387755,
      "grad_norm": 9.439040184020996,
      "learning_rate": 3.2653061224489794e-06,
      "loss": 0.8487,
      "step": 820
    },
    {
      "epoch": 4.23469387755102,
      "grad_norm": 16.658971786499023,
      "learning_rate": 3.0612244897959185e-06,
      "loss": 0.8698,
      "step": 830
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 14.88980484008789,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 0.7877,
      "step": 840
    },
    {
      "epoch": 4.336734693877551,
      "grad_norm": 10.878366470336914,
      "learning_rate": 2.6530612244897964e-06,
      "loss": 0.7731,
      "step": 850
    },
    {
      "epoch": 4.387755102040816,
      "grad_norm": 11.978877067565918,
      "learning_rate": 2.4489795918367347e-06,
      "loss": 0.8627,
      "step": 860
    },
    {
      "epoch": 4.438775510204081,
      "grad_norm": 20.543222427368164,
      "learning_rate": 2.244897959183674e-06,
      "loss": 0.8106,
      "step": 870
    },
    {
      "epoch": 4.489795918367347,
      "grad_norm": 5.99076509475708,
      "learning_rate": 2.0408163265306125e-06,
      "loss": 0.8779,
      "step": 880
    },
    {
      "epoch": 4.540816326530612,
      "grad_norm": 13.510481834411621,
      "learning_rate": 1.8367346938775512e-06,
      "loss": 0.8535,
      "step": 890
    },
    {
      "epoch": 4.591836734693878,
      "grad_norm": 14.781784057617188,
      "learning_rate": 1.6326530612244897e-06,
      "loss": 0.8972,
      "step": 900
    },
    {
      "epoch": 4.642857142857143,
      "grad_norm": 14.63200855255127,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 0.9312,
      "step": 910
    },
    {
      "epoch": 4.6938775510204085,
      "grad_norm": 19.910818099975586,
      "learning_rate": 1.2244897959183673e-06,
      "loss": 0.8134,
      "step": 920
    },
    {
      "epoch": 4.744897959183674,
      "grad_norm": 16.637697219848633,
      "learning_rate": 1.0204081632653063e-06,
      "loss": 0.8341,
      "step": 930
    },
    {
      "epoch": 4.795918367346939,
      "grad_norm": 5.32245397567749,
      "learning_rate": 8.163265306122449e-07,
      "loss": 0.7553,
      "step": 940
    },
    {
      "epoch": 4.846938775510204,
      "grad_norm": 13.930354118347168,
      "learning_rate": 6.122448979591837e-07,
      "loss": 0.8303,
      "step": 950
    },
    {
      "epoch": 4.8979591836734695,
      "grad_norm": 18.44146728515625,
      "learning_rate": 4.0816326530612243e-07,
      "loss": 0.8247,
      "step": 960
    },
    {
      "epoch": 4.948979591836735,
      "grad_norm": 15.450093269348145,
      "learning_rate": 2.0408163265306121e-07,
      "loss": 0.9838,
      "step": 970
    },
    {
      "epoch": 5.0,
      "grad_norm": 38.064430236816406,
      "learning_rate": 0.0,
      "loss": 0.8213,
      "step": 980
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8628158844765343,
      "eval_loss": 0.897123396396637,
      "eval_runtime": 14.3653,
      "eval_samples_per_second": 19.283,
      "eval_steps_per_second": 2.436,
      "step": 980
    },
    {
      "epoch": 5.0,
      "step": 980,
      "total_flos": 1.6633116935737344e+17,
      "train_loss": 1.1215976812401596,
      "train_runtime": 1562.8364,
      "train_samples_per_second": 5.01,
      "train_steps_per_second": 0.627
    }
  ],
  "logging_steps": 10,
  "max_steps": 980,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6633116935737344e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}