{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 16.0,
  "eval_steps": 500,
  "global_step": 208,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 1.4849790334701538,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.4899,
      "step": 10
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 1.4494893550872803,
      "learning_rate": 9.523809523809524e-05,
      "loss": 1.4047,
      "step": 20
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 1.1887791156768799,
      "learning_rate": 9.94295546780682e-05,
      "loss": 1.1335,
      "step": 30
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 2.6606452465057373,
      "learning_rate": 9.747435008912438e-05,
      "loss": 0.758,
      "step": 40
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 2.238654136657715,
      "learning_rate": 9.418238419956484e-05,
      "loss": 0.6976,
      "step": 50
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 2.202763080596924,
      "learning_rate": 8.964635069757802e-05,
      "loss": 0.5176,
      "step": 60
    },
    {
      "epoch": 5.384615384615385,
      "grad_norm": 1.5672999620437622,
      "learning_rate": 8.399397316510596e-05,
      "loss": 0.5374,
      "step": 70
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 1.7563928365707397,
      "learning_rate": 7.738440869493018e-05,
      "loss": 0.4344,
      "step": 80
    },
    {
      "epoch": 6.923076923076923,
      "grad_norm": 1.8594719171524048,
      "learning_rate": 7.000376641716133e-05,
      "loss": 0.3991,
      "step": 90
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 1.8146908283233643,
      "learning_rate": 6.205986712243875e-05,
      "loss": 0.3497,
      "step": 100
    },
    {
      "epoch": 8.461538461538462,
      "grad_norm": 1.8267848491668701,
      "learning_rate": 5.377639153800229e-05,
      "loss": 0.3176,
      "step": 110
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 1.6012214422225952,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 0.2394,
      "step": 120
    },
    {
      "epoch": 10.0,
      "grad_norm": 2.043828010559082,
      "learning_rate": 3.712667505458622e-05,
      "loss": 0.2328,
      "step": 130
    },
    {
      "epoch": 10.76923076923077,
      "grad_norm": 2.1970419883728027,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 0.1849,
      "step": 140
    },
    {
      "epoch": 11.538461538461538,
      "grad_norm": 1.2817729711532593,
      "learning_rate": 2.1916677057681785e-05,
      "loss": 0.1416,
      "step": 150
    },
    {
      "epoch": 12.307692307692308,
      "grad_norm": 1.8149962425231934,
      "learning_rate": 1.5394862284655264e-05,
      "loss": 0.1323,
      "step": 160
    },
    {
      "epoch": 13.076923076923077,
      "grad_norm": 2.4009556770324707,
      "learning_rate": 9.847443344610297e-06,
      "loss": 0.1315,
      "step": 170
    },
    {
      "epoch": 13.846153846153847,
      "grad_norm": 1.9544780254364014,
      "learning_rate": 5.430621953703785e-06,
      "loss": 0.1065,
      "step": 180
    },
    {
      "epoch": 14.615384615384615,
      "grad_norm": 1.0407898426055908,
      "learning_rate": 2.268764973114684e-06,
      "loss": 0.1174,
      "step": 190
    },
    {
      "epoch": 15.384615384615385,
      "grad_norm": 3.4905996322631836,
      "learning_rate": 4.5090254315662826e-07,
      "loss": 0.0959,
      "step": 200
    },
    {
      "epoch": 16.0,
      "step": 208,
      "total_flos": 3.485945501879501e+16,
      "train_loss": 0.457215073876656,
      "train_runtime": 4064.4346,
      "train_samples_per_second": 1.638,
      "train_steps_per_second": 0.051
    }
  ],
  "logging_steps": 10,
  "max_steps": 208,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 16,
  "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": 3.485945501879501e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}