{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0029331964508322946,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00029331964508322946,
      "grad_norm": 0.3954114317893982,
      "learning_rate": 2e-05,
      "loss": 1.3667,
      "step": 1
    },
    {
      "epoch": 0.00029331964508322946,
      "eval_loss": 1.2396342754364014,
      "eval_runtime": 26.413,
      "eval_samples_per_second": 54.367,
      "eval_steps_per_second": 27.184,
      "step": 1
    },
    {
      "epoch": 0.0005866392901664589,
      "grad_norm": 0.3591647148132324,
      "learning_rate": 4e-05,
      "loss": 1.2968,
      "step": 2
    },
    {
      "epoch": 0.0008799589352496884,
      "grad_norm": 0.34322068095207214,
      "learning_rate": 6e-05,
      "loss": 1.1401,
      "step": 3
    },
    {
      "epoch": 0.0008799589352496884,
      "eval_loss": 1.239241361618042,
      "eval_runtime": 25.4795,
      "eval_samples_per_second": 56.359,
      "eval_steps_per_second": 28.179,
      "step": 3
    },
    {
      "epoch": 0.0011732785803329178,
      "grad_norm": 0.46506813168525696,
      "learning_rate": 8e-05,
      "loss": 1.2674,
      "step": 4
    },
    {
      "epoch": 0.0014665982254161473,
      "grad_norm": 0.3876882493495941,
      "learning_rate": 0.0001,
      "loss": 1.1952,
      "step": 5
    },
    {
      "epoch": 0.0017599178704993767,
      "grad_norm": 0.3271230459213257,
      "learning_rate": 0.00012,
      "loss": 1.2299,
      "step": 6
    },
    {
      "epoch": 0.0017599178704993767,
      "eval_loss": 1.2357220649719238,
      "eval_runtime": 25.7722,
      "eval_samples_per_second": 55.719,
      "eval_steps_per_second": 27.859,
      "step": 6
    },
    {
      "epoch": 0.002053237515582606,
      "grad_norm": 0.4138140082359314,
      "learning_rate": 0.00014,
      "loss": 1.3228,
      "step": 7
    },
    {
      "epoch": 0.0023465571606658357,
      "grad_norm": 0.5157594084739685,
      "learning_rate": 0.00016,
      "loss": 1.336,
      "step": 8
    },
    {
      "epoch": 0.002639876805749065,
      "grad_norm": 0.40979161858558655,
      "learning_rate": 0.00018,
      "loss": 1.2117,
      "step": 9
    },
    {
      "epoch": 0.002639876805749065,
      "eval_loss": 1.2226723432540894,
      "eval_runtime": 25.6186,
      "eval_samples_per_second": 56.053,
      "eval_steps_per_second": 28.026,
      "step": 9
    },
    {
      "epoch": 0.0029331964508322946,
      "grad_norm": 0.39748358726501465,
      "learning_rate": 0.0002,
      "loss": 1.3094,
      "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": 274976376619008.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}