{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006520286240565961,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.520286240565961e-05,
      "grad_norm": 2.612797498703003,
      "learning_rate": 2e-05,
      "loss": 12.7637,
      "step": 1
    },
    {
      "epoch": 6.520286240565961e-05,
      "eval_loss": 3.082449197769165,
      "eval_runtime": 180.7875,
      "eval_samples_per_second": 35.721,
      "eval_steps_per_second": 17.861,
      "step": 1
    },
    {
      "epoch": 0.00013040572481131922,
      "grad_norm": 2.143118143081665,
      "learning_rate": 4e-05,
      "loss": 12.7267,
      "step": 2
    },
    {
      "epoch": 0.00019560858721697882,
      "grad_norm": 2.1318533420562744,
      "learning_rate": 6e-05,
      "loss": 13.1611,
      "step": 3
    },
    {
      "epoch": 0.00019560858721697882,
      "eval_loss": 3.081737995147705,
      "eval_runtime": 180.3593,
      "eval_samples_per_second": 35.806,
      "eval_steps_per_second": 17.903,
      "step": 3
    },
    {
      "epoch": 0.00026081144962263844,
      "grad_norm": 2.989206075668335,
      "learning_rate": 8e-05,
      "loss": 12.9235,
      "step": 4
    },
    {
      "epoch": 0.00032601431202829807,
      "grad_norm": 2.6654365062713623,
      "learning_rate": 0.0001,
      "loss": 11.8837,
      "step": 5
    },
    {
      "epoch": 0.00039121717443395764,
      "grad_norm": 3.009270429611206,
      "learning_rate": 0.00012,
      "loss": 12.3513,
      "step": 6
    },
    {
      "epoch": 0.00039121717443395764,
      "eval_loss": 3.029892921447754,
      "eval_runtime": 180.8393,
      "eval_samples_per_second": 35.711,
      "eval_steps_per_second": 17.856,
      "step": 6
    },
    {
      "epoch": 0.00045642003683961726,
      "grad_norm": 4.376823902130127,
      "learning_rate": 0.00014,
      "loss": 12.742,
      "step": 7
    },
    {
      "epoch": 0.0005216228992452769,
      "grad_norm": 5.373292446136475,
      "learning_rate": 0.00016,
      "loss": 12.2543,
      "step": 8
    },
    {
      "epoch": 0.0005868257616509365,
      "grad_norm": 6.618515968322754,
      "learning_rate": 0.00018,
      "loss": 11.7093,
      "step": 9
    },
    {
      "epoch": 0.0005868257616509365,
      "eval_loss": 2.806042194366455,
      "eval_runtime": 180.8621,
      "eval_samples_per_second": 35.707,
      "eval_steps_per_second": 17.853,
      "step": 9
    },
    {
      "epoch": 0.0006520286240565961,
      "grad_norm": 9.779359817504883,
      "learning_rate": 0.0002,
      "loss": 11.859,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1632478030725120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}