{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011577424023154847,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011577424023154848,
      "grad_norm": 2.69914174079895,
      "learning_rate": 2e-05,
      "loss": 1.7536,
      "step": 1
    },
    {
      "epoch": 0.0011577424023154848,
      "eval_loss": 1.6031314134597778,
      "eval_runtime": 12.3053,
      "eval_samples_per_second": 29.581,
      "eval_steps_per_second": 14.79,
      "step": 1
    },
    {
      "epoch": 0.0023154848046309695,
      "grad_norm": 1.5747690200805664,
      "learning_rate": 4e-05,
      "loss": 1.6221,
      "step": 2
    },
    {
      "epoch": 0.0034732272069464545,
      "grad_norm": 2.0434021949768066,
      "learning_rate": 6e-05,
      "loss": 1.8146,
      "step": 3
    },
    {
      "epoch": 0.0034732272069464545,
      "eval_loss": 1.5877282619476318,
      "eval_runtime": 11.6663,
      "eval_samples_per_second": 31.201,
      "eval_steps_per_second": 15.601,
      "step": 3
    },
    {
      "epoch": 0.004630969609261939,
      "grad_norm": 2.013674259185791,
      "learning_rate": 8e-05,
      "loss": 1.5184,
      "step": 4
    },
    {
      "epoch": 0.005788712011577424,
      "grad_norm": 2.199882984161377,
      "learning_rate": 0.0001,
      "loss": 1.6555,
      "step": 5
    },
    {
      "epoch": 0.006946454413892909,
      "grad_norm": 2.254617929458618,
      "learning_rate": 0.00012,
      "loss": 1.6539,
      "step": 6
    },
    {
      "epoch": 0.006946454413892909,
      "eval_loss": 1.3257914781570435,
      "eval_runtime": 11.6694,
      "eval_samples_per_second": 31.193,
      "eval_steps_per_second": 15.596,
      "step": 6
    },
    {
      "epoch": 0.008104196816208394,
      "grad_norm": 1.7067660093307495,
      "learning_rate": 0.00014,
      "loss": 1.2289,
      "step": 7
    },
    {
      "epoch": 0.009261939218523878,
      "grad_norm": 1.4902814626693726,
      "learning_rate": 0.00016,
      "loss": 1.1926,
      "step": 8
    },
    {
      "epoch": 0.010419681620839363,
      "grad_norm": 1.5148963928222656,
      "learning_rate": 0.00018,
      "loss": 1.202,
      "step": 9
    },
    {
      "epoch": 0.010419681620839363,
      "eval_loss": 0.9547884464263916,
      "eval_runtime": 11.6062,
      "eval_samples_per_second": 31.363,
      "eval_steps_per_second": 15.681,
      "step": 9
    },
    {
      "epoch": 0.011577424023154847,
      "grad_norm": 1.4581676721572876,
      "learning_rate": 0.0002,
      "loss": 0.9752,
      "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": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}