{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014657383657017223,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014657383657017222,
      "grad_norm": 0.12143966555595398,
      "learning_rate": 2e-05,
      "loss": 0.7919,
      "step": 1
    },
    {
      "epoch": 0.0014657383657017222,
      "eval_loss": 0.8369418978691101,
      "eval_runtime": 16.8675,
      "eval_samples_per_second": 68.179,
      "eval_steps_per_second": 8.537,
      "step": 1
    },
    {
      "epoch": 0.0029314767314034445,
      "grad_norm": 0.12046486139297485,
      "learning_rate": 4e-05,
      "loss": 0.788,
      "step": 2
    },
    {
      "epoch": 0.004397215097105167,
      "grad_norm": 0.1069972962141037,
      "learning_rate": 6e-05,
      "loss": 0.7388,
      "step": 3
    },
    {
      "epoch": 0.004397215097105167,
      "eval_loss": 0.832497775554657,
      "eval_runtime": 15.0036,
      "eval_samples_per_second": 76.648,
      "eval_steps_per_second": 9.598,
      "step": 3
    },
    {
      "epoch": 0.005862953462806889,
      "grad_norm": 0.10991697758436203,
      "learning_rate": 8e-05,
      "loss": 0.8107,
      "step": 4
    },
    {
      "epoch": 0.007328691828508612,
      "grad_norm": 0.10991702228784561,
      "learning_rate": 0.0001,
      "loss": 0.7868,
      "step": 5
    },
    {
      "epoch": 0.008794430194210334,
      "grad_norm": 0.09949130564928055,
      "learning_rate": 0.00012,
      "loss": 0.7825,
      "step": 6
    },
    {
      "epoch": 0.008794430194210334,
      "eval_loss": 0.8176950216293335,
      "eval_runtime": 14.9845,
      "eval_samples_per_second": 76.746,
      "eval_steps_per_second": 9.61,
      "step": 6
    },
    {
      "epoch": 0.010260168559912056,
      "grad_norm": 0.09518777579069138,
      "learning_rate": 0.00014,
      "loss": 0.7771,
      "step": 7
    },
    {
      "epoch": 0.011725906925613778,
      "grad_norm": 0.10910291969776154,
      "learning_rate": 0.00016,
      "loss": 0.8689,
      "step": 8
    },
    {
      "epoch": 0.0131916452913155,
      "grad_norm": 0.10702081024646759,
      "learning_rate": 0.00018,
      "loss": 0.7665,
      "step": 9
    },
    {
      "epoch": 0.0131916452913155,
      "eval_loss": 0.8077729940414429,
      "eval_runtime": 14.9988,
      "eval_samples_per_second": 76.673,
      "eval_steps_per_second": 9.601,
      "step": 9
    },
    {
      "epoch": 0.014657383657017223,
      "grad_norm": 0.09443683177232742,
      "learning_rate": 0.0002,
      "loss": 0.7131,
      "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": 1.045015069458432e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}