{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.022714366837024418,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00045428733674048835,
      "eval_loss": 2.3526980876922607,
      "eval_runtime": 48.7648,
      "eval_samples_per_second": 19.01,
      "eval_steps_per_second": 9.515,
      "step": 1
    },
    {
      "epoch": 0.002271436683702442,
      "grad_norm": 6.649918079376221,
      "learning_rate": 5e-05,
      "loss": 2.2383,
      "step": 5
    },
    {
      "epoch": 0.004542873367404884,
      "grad_norm": 3.9040491580963135,
      "learning_rate": 0.0001,
      "loss": 1.5065,
      "step": 10
    },
    {
      "epoch": 0.004542873367404884,
      "eval_loss": 0.6507410407066345,
      "eval_runtime": 48.9057,
      "eval_samples_per_second": 18.955,
      "eval_steps_per_second": 9.488,
      "step": 10
    },
    {
      "epoch": 0.0068143100511073255,
      "grad_norm": 1.8648144006729126,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.3623,
      "step": 15
    },
    {
      "epoch": 0.009085746734809767,
      "grad_norm": 1.6206068992614746,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.158,
      "step": 20
    },
    {
      "epoch": 0.009085746734809767,
      "eval_loss": 0.06087474152445793,
      "eval_runtime": 48.8725,
      "eval_samples_per_second": 18.968,
      "eval_steps_per_second": 9.494,
      "step": 20
    },
    {
      "epoch": 0.011357183418512209,
      "grad_norm": 0.552495002746582,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0247,
      "step": 25
    },
    {
      "epoch": 0.013628620102214651,
      "grad_norm": 2.7146968841552734,
      "learning_rate": 5e-05,
      "loss": 0.0146,
      "step": 30
    },
    {
      "epoch": 0.013628620102214651,
      "eval_loss": 0.00583901721984148,
      "eval_runtime": 49.0134,
      "eval_samples_per_second": 18.913,
      "eval_steps_per_second": 9.467,
      "step": 30
    },
    {
      "epoch": 0.01590005678591709,
      "grad_norm": 0.5495128631591797,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0018,
      "step": 35
    },
    {
      "epoch": 0.018171493469619535,
      "grad_norm": 0.01361869927495718,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0004,
      "step": 40
    },
    {
      "epoch": 0.018171493469619535,
      "eval_loss": 0.0021691254805773497,
      "eval_runtime": 49.1642,
      "eval_samples_per_second": 18.855,
      "eval_steps_per_second": 9.438,
      "step": 40
    },
    {
      "epoch": 0.020442930153321975,
      "grad_norm": 0.020270636305212975,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.001,
      "step": 45
    },
    {
      "epoch": 0.022714366837024418,
      "grad_norm": 0.010211742483079433,
      "learning_rate": 0.0,
      "loss": 0.0019,
      "step": 50
    },
    {
      "epoch": 0.022714366837024418,
      "eval_loss": 0.001980047207325697,
      "eval_runtime": 49.0112,
      "eval_samples_per_second": 18.914,
      "eval_steps_per_second": 9.467,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2500486653542400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}