{
  "best_metric": 0.4000471532344818,
  "best_model_checkpoint": "realFake-food/checkpoint-100",
  "epoch": 4.0,
  "eval_steps": 100,
  "global_step": 208,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 3.332577705383301,
      "learning_rate": 0.00019038461538461538,
      "loss": 0.5794,
      "step": 10
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 9.896267890930176,
      "learning_rate": 0.00018076923076923077,
      "loss": 0.7166,
      "step": 20
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 2.1554434299468994,
      "learning_rate": 0.00017115384615384616,
      "loss": 0.6577,
      "step": 30
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.039557695388794,
      "learning_rate": 0.00016153846153846155,
      "loss": 0.5564,
      "step": 40
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 1.7540931701660156,
      "learning_rate": 0.00015192307692307692,
      "loss": 0.5091,
      "step": 50
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 3.100355386734009,
      "learning_rate": 0.0001423076923076923,
      "loss": 0.4778,
      "step": 60
    },
    {
      "epoch": 1.3461538461538463,
      "grad_norm": 2.988347053527832,
      "learning_rate": 0.0001326923076923077,
      "loss": 0.4587,
      "step": 70
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 1.9209961891174316,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.4119,
      "step": 80
    },
    {
      "epoch": 1.7307692307692308,
      "grad_norm": 1.357641339302063,
      "learning_rate": 0.00011346153846153846,
      "loss": 0.3792,
      "step": 90
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 1.6307432651519775,
      "learning_rate": 0.00010384615384615386,
      "loss": 0.3207,
      "step": 100
    },
    {
      "epoch": 1.9230769230769231,
      "eval_accuracy": 0.821917808219178,
      "eval_loss": 0.4000471532344818,
      "eval_runtime": 107.5888,
      "eval_samples_per_second": 1.357,
      "eval_steps_per_second": 0.177,
      "step": 100
    },
    {
      "epoch": 2.1153846153846154,
      "grad_norm": 2.9391109943389893,
      "learning_rate": 9.423076923076924e-05,
      "loss": 0.333,
      "step": 110
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 2.208177089691162,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2452,
      "step": 120
    },
    {
      "epoch": 2.5,
      "grad_norm": 2.402629852294922,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2187,
      "step": 130
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.8266276121139526,
      "learning_rate": 6.538461538461539e-05,
      "loss": 0.2606,
      "step": 140
    },
    {
      "epoch": 2.8846153846153846,
      "grad_norm": 4.629295825958252,
      "learning_rate": 5.576923076923077e-05,
      "loss": 0.3003,
      "step": 150
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.8120359778404236,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3157,
      "step": 160
    },
    {
      "epoch": 3.269230769230769,
      "grad_norm": 0.8266440629959106,
      "learning_rate": 3.653846153846154e-05,
      "loss": 0.1906,
      "step": 170
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 2.106200933456421,
      "learning_rate": 2.6923076923076923e-05,
      "loss": 0.2095,
      "step": 180
    },
    {
      "epoch": 3.6538461538461537,
      "grad_norm": 4.685356140136719,
      "learning_rate": 1.730769230769231e-05,
      "loss": 0.1751,
      "step": 190
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.821261465549469,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.1926,
      "step": 200
    },
    {
      "epoch": 3.8461538461538463,
      "eval_accuracy": 0.8082191780821918,
      "eval_loss": 0.4611532688140869,
      "eval_runtime": 107.6459,
      "eval_samples_per_second": 1.356,
      "eval_steps_per_second": 0.177,
      "step": 200
    },
    {
      "epoch": 4.0,
      "step": 208,
      "total_flos": 2.585132773542789e+17,
      "train_loss": 0.36694453771297747,
      "train_runtime": 7749.7539,
      "train_samples_per_second": 0.426,
      "train_steps_per_second": 0.027
    }
  ],
  "logging_steps": 10,
  "max_steps": 208,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 2.585132773542789e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}