{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0022637238256932655,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025152486952147396,
      "grad_norm": 0.2055659145116806,
      "learning_rate": 2e-05,
      "loss": 0.8211,
      "step": 1
    },
    {
      "epoch": 0.00025152486952147396,
      "eval_loss": NaN,
      "eval_runtime": 59.7379,
      "eval_samples_per_second": 28.039,
      "eval_steps_per_second": 14.028,
      "step": 1
    },
    {
      "epoch": 0.0005030497390429479,
      "grad_norm": 0.19586406648159027,
      "learning_rate": 4e-05,
      "loss": 0.6942,
      "step": 2
    },
    {
      "epoch": 0.0007545746085644218,
      "grad_norm": 0.22634905576705933,
      "learning_rate": 6e-05,
      "loss": 0.967,
      "step": 3
    },
    {
      "epoch": 0.0007545746085644218,
      "eval_loss": NaN,
      "eval_runtime": 58.4617,
      "eval_samples_per_second": 28.651,
      "eval_steps_per_second": 14.334,
      "step": 3
    },
    {
      "epoch": 0.0010060994780858958,
      "grad_norm": 0.239157572388649,
      "learning_rate": 8e-05,
      "loss": 0.8844,
      "step": 4
    },
    {
      "epoch": 0.0012576243476073697,
      "grad_norm": 0.19084791839122772,
      "learning_rate": 0.0001,
      "loss": 0.445,
      "step": 5
    },
    {
      "epoch": 0.0015091492171288435,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.7026,
      "step": 6
    },
    {
      "epoch": 0.0015091492171288435,
      "eval_loss": NaN,
      "eval_runtime": 58.4867,
      "eval_samples_per_second": 28.639,
      "eval_steps_per_second": 14.328,
      "step": 6
    },
    {
      "epoch": 0.0017606740866503176,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.8465,
      "step": 7
    },
    {
      "epoch": 0.0020121989561717917,
      "grad_norm": 0.24796241521835327,
      "learning_rate": 0.00016,
      "loss": 0.7513,
      "step": 8
    },
    {
      "epoch": 0.0022637238256932655,
      "grad_norm": 0.2246653288602829,
      "learning_rate": 0.00018,
      "loss": 0.5931,
      "step": 9
    },
    {
      "epoch": 0.0022637238256932655,
      "eval_loss": NaN,
      "eval_runtime": 58.4907,
      "eval_samples_per_second": 28.637,
      "eval_steps_per_second": 14.327,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1252301482229760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}