{
  "best_metric": 0.4011619985103607,
  "best_model_checkpoint": "realFake-food/checkpoint-200",
  "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": 2.2526018619537354,
      "learning_rate": 0.00019038461538461538,
      "loss": 0.8691,
      "step": 10
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 3.1683309078216553,
      "learning_rate": 0.00018076923076923077,
      "loss": 0.6246,
      "step": 20
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 1.3931829929351807,
      "learning_rate": 0.00017115384615384616,
      "loss": 0.6948,
      "step": 30
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 1.4135185480117798,
      "learning_rate": 0.00016153846153846155,
      "loss": 0.6189,
      "step": 40
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 1.1267380714416504,
      "learning_rate": 0.00015192307692307692,
      "loss": 0.5385,
      "step": 50
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 2.51800799369812,
      "learning_rate": 0.0001423076923076923,
      "loss": 0.5534,
      "step": 60
    },
    {
      "epoch": 1.3461538461538463,
      "grad_norm": 2.433380365371704,
      "learning_rate": 0.0001326923076923077,
      "loss": 0.4538,
      "step": 70
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 2.7342333793640137,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.4093,
      "step": 80
    },
    {
      "epoch": 1.7307692307692308,
      "grad_norm": 2.5821759700775146,
      "learning_rate": 0.00011346153846153846,
      "loss": 0.4234,
      "step": 90
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 1.005037546157837,
      "learning_rate": 0.00010384615384615386,
      "loss": 0.398,
      "step": 100
    },
    {
      "epoch": 1.9230769230769231,
      "eval_accuracy": 0.773972602739726,
      "eval_loss": 0.5322885513305664,
      "eval_runtime": 5.4109,
      "eval_samples_per_second": 26.983,
      "eval_steps_per_second": 3.511,
      "step": 100
    },
    {
      "epoch": 2.1153846153846154,
      "grad_norm": 1.1994967460632324,
      "learning_rate": 9.423076923076924e-05,
      "loss": 0.3894,
      "step": 110
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 3.602186679840088,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2986,
      "step": 120
    },
    {
      "epoch": 2.5,
      "grad_norm": 3.0683720111846924,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3787,
      "step": 130
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 1.893823504447937,
      "learning_rate": 6.538461538461539e-05,
      "loss": 0.253,
      "step": 140
    },
    {
      "epoch": 2.8846153846153846,
      "grad_norm": 4.061652183532715,
      "learning_rate": 5.576923076923077e-05,
      "loss": 0.2849,
      "step": 150
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 1.501720666885376,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.203,
      "step": 160
    },
    {
      "epoch": 3.269230769230769,
      "grad_norm": 1.777280330657959,
      "learning_rate": 3.653846153846154e-05,
      "loss": 0.2886,
      "step": 170
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 3.2315940856933594,
      "learning_rate": 2.6923076923076923e-05,
      "loss": 0.2468,
      "step": 180
    },
    {
      "epoch": 3.6538461538461537,
      "grad_norm": 3.8452298641204834,
      "learning_rate": 1.730769230769231e-05,
      "loss": 0.1768,
      "step": 190
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 1.731667399406433,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.2281,
      "step": 200
    },
    {
      "epoch": 3.8461538461538463,
      "eval_accuracy": 0.863013698630137,
      "eval_loss": 0.4011619985103607,
      "eval_runtime": 6.6761,
      "eval_samples_per_second": 21.869,
      "eval_steps_per_second": 2.846,
      "step": 200
    },
    {
      "epoch": 4.0,
      "step": 208,
      "total_flos": 2.5603353368661197e+17,
      "train_loss": 0.40654734350167787,
      "train_runtime": 177.3408,
      "train_samples_per_second": 18.631,
      "train_steps_per_second": 1.173
    }
  ],
  "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": 2.5603353368661197e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}