{
  "best_metric": 0.0019312179647386074,
  "best_model_checkpoint": "./vision_transformer_model_progress/checkpoint-200",
  "epoch": 9.0,
  "eval_steps": 100,
  "global_step": 297,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.12155108898878098,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0158,
      "step": 10
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.0541080236434937,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0479,
      "step": 20
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.03966180980205536,
      "learning_rate": 6e-06,
      "loss": 0.0047,
      "step": 30
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.06989104300737381,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0045,
      "step": 40
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 0.0959181860089302,
      "learning_rate": 1e-05,
      "loss": 0.0027,
      "step": 50
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.05803044140338898,
      "learning_rate": 1.2e-05,
      "loss": 0.0281,
      "step": 60
    },
    {
      "epoch": 2.121212121212121,
      "grad_norm": 0.24542172253131866,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.0049,
      "step": 70
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.0824781134724617,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0018,
      "step": 80
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.05576428771018982,
      "learning_rate": 1.8e-05,
      "loss": 0.0015,
      "step": 90
    },
    {
      "epoch": 3.0303030303030303,
      "grad_norm": 0.02234538644552231,
      "learning_rate": 2e-05,
      "loss": 0.0018,
      "step": 100
    },
    {
      "epoch": 3.0303030303030303,
      "eval_loss": 0.0030471435748040676,
      "eval_runtime": 12.9149,
      "eval_samples_per_second": 10.066,
      "eval_steps_per_second": 0.697,
      "step": 100
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.014021256007254124,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.001,
      "step": 110
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.03260282799601555,
      "learning_rate": 2.4e-05,
      "loss": 0.0011,
      "step": 120
    },
    {
      "epoch": 3.9393939393939394,
      "grad_norm": 0.020618194714188576,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.0012,
      "step": 130
    },
    {
      "epoch": 4.242424242424242,
      "grad_norm": 0.021722646430134773,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.0009,
      "step": 140
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.015248863026499748,
      "learning_rate": 3e-05,
      "loss": 0.0007,
      "step": 150
    },
    {
      "epoch": 4.848484848484849,
      "grad_norm": 0.00668317498639226,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.0007,
      "step": 160
    },
    {
      "epoch": 5.151515151515151,
      "grad_norm": 0.009767434559762478,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.0006,
      "step": 170
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.0070835500955581665,
      "learning_rate": 3.6e-05,
      "loss": 0.0005,
      "step": 180
    },
    {
      "epoch": 5.757575757575758,
      "grad_norm": 0.005514961667358875,
      "learning_rate": 3.8e-05,
      "loss": 0.0005,
      "step": 190
    },
    {
      "epoch": 6.0606060606060606,
      "grad_norm": 0.007456360850483179,
      "learning_rate": 4e-05,
      "loss": 0.0005,
      "step": 200
    },
    {
      "epoch": 6.0606060606060606,
      "eval_loss": 0.0019312179647386074,
      "eval_runtime": 13.4333,
      "eval_samples_per_second": 9.677,
      "eval_steps_per_second": 0.67,
      "step": 200
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 0.0049119917675852776,
      "learning_rate": 4.2e-05,
      "loss": 0.0004,
      "step": 210
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.0046443757601082325,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.0004,
      "step": 220
    },
    {
      "epoch": 6.96969696969697,
      "grad_norm": 0.006061806809157133,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.0004,
      "step": 230
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 0.004031210206449032,
      "learning_rate": 4.8e-05,
      "loss": 0.0004,
      "step": 240
    },
    {
      "epoch": 7.575757575757576,
      "grad_norm": 0.004312009084969759,
      "learning_rate": 5e-05,
      "loss": 0.0003,
      "step": 250
    },
    {
      "epoch": 7.878787878787879,
      "grad_norm": 0.004320390522480011,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.0003,
      "step": 260
    },
    {
      "epoch": 8.181818181818182,
      "grad_norm": 0.0036691236309707165,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.0003,
      "step": 270
    },
    {
      "epoch": 8.484848484848484,
      "grad_norm": 0.0040830825455486774,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.0003,
      "step": 280
    },
    {
      "epoch": 8.787878787878787,
      "grad_norm": 0.003878690768033266,
      "learning_rate": 5.8e-05,
      "loss": 0.0002,
      "step": 290
    }
  ],
  "logging_steps": 10,
  "max_steps": 297,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.62740521701376e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}