{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03017832647462277,
  "eval_steps": 500,
  "global_step": 11,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 1.902702808380127,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.0959,
      "step": 1
    },
    {
      "epoch": 0.0054869684499314125,
      "grad_norm": 1.8936893939971924,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.099,
      "step": 2
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 1.9235605001449585,
      "learning_rate": 6e-06,
      "loss": 2.1045,
      "step": 3
    },
    {
      "epoch": 0.010973936899862825,
      "grad_norm": 1.7873843908309937,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.0144,
      "step": 4
    },
    {
      "epoch": 0.013717421124828532,
      "grad_norm": 1.8321126699447632,
      "learning_rate": 1e-05,
      "loss": 2.0872,
      "step": 5
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 2.0333194732666016,
      "learning_rate": 1.2e-05,
      "loss": 2.1146,
      "step": 6
    },
    {
      "epoch": 0.019204389574759947,
      "grad_norm": 1.763102650642395,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.036,
      "step": 7
    },
    {
      "epoch": 0.02194787379972565,
      "grad_norm": 1.5287824869155884,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.984,
      "step": 8
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 1.2035481929779053,
      "learning_rate": 1.8e-05,
      "loss": 1.928,
      "step": 9
    },
    {
      "epoch": 0.027434842249657063,
      "grad_norm": 1.0602883100509644,
      "learning_rate": 2e-05,
      "loss": 1.9322,
      "step": 10
    },
    {
      "epoch": 0.03017832647462277,
      "grad_norm": 0.9456723928451538,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.9257,
      "step": 11
    }
  ],
  "logging_steps": 1,
  "max_steps": 364,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.367494067331072e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}