{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013628620102214651,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00045428733674048835,
      "eval_loss": 3.4793825149536133,
      "eval_runtime": 35.5072,
      "eval_samples_per_second": 26.107,
      "eval_steps_per_second": 13.068,
      "step": 1
    },
    {
      "epoch": 0.001362862010221465,
      "grad_norm": 5.045869827270508,
      "learning_rate": 3e-05,
      "loss": 3.3263,
      "step": 3
    },
    {
      "epoch": 0.002271436683702442,
      "eval_loss": 2.745880365371704,
      "eval_runtime": 35.5125,
      "eval_samples_per_second": 26.103,
      "eval_steps_per_second": 13.066,
      "step": 5
    },
    {
      "epoch": 0.00272572402044293,
      "grad_norm": 3.6982457637786865,
      "learning_rate": 6e-05,
      "loss": 3.0068,
      "step": 6
    },
    {
      "epoch": 0.0040885860306643955,
      "grad_norm": 4.1545586585998535,
      "learning_rate": 9e-05,
      "loss": 2.3262,
      "step": 9
    },
    {
      "epoch": 0.004542873367404884,
      "eval_loss": 1.500496745109558,
      "eval_runtime": 35.5043,
      "eval_samples_per_second": 26.11,
      "eval_steps_per_second": 13.069,
      "step": 10
    },
    {
      "epoch": 0.00545144804088586,
      "grad_norm": 3.069416046142578,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.6011,
      "step": 12
    },
    {
      "epoch": 0.0068143100511073255,
      "grad_norm": 2.1913928985595703,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.9641,
      "step": 15
    },
    {
      "epoch": 0.0068143100511073255,
      "eval_loss": 0.766928493976593,
      "eval_runtime": 35.5756,
      "eval_samples_per_second": 26.057,
      "eval_steps_per_second": 13.043,
      "step": 15
    },
    {
      "epoch": 0.008177172061328791,
      "grad_norm": 3.124316930770874,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5871,
      "step": 18
    },
    {
      "epoch": 0.009085746734809767,
      "eval_loss": 0.5429315567016602,
      "eval_runtime": 35.5067,
      "eval_samples_per_second": 26.108,
      "eval_steps_per_second": 13.068,
      "step": 20
    },
    {
      "epoch": 0.009540034071550256,
      "grad_norm": 2.8077774047851562,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.6029,
      "step": 21
    },
    {
      "epoch": 0.01090289608177172,
      "grad_norm": 1.9062230587005615,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.4214,
      "step": 24
    },
    {
      "epoch": 0.011357183418512209,
      "eval_loss": 0.44642192125320435,
      "eval_runtime": 35.5591,
      "eval_samples_per_second": 26.069,
      "eval_steps_per_second": 13.049,
      "step": 25
    },
    {
      "epoch": 0.012265758091993186,
      "grad_norm": 2.084507703781128,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.3852,
      "step": 27
    },
    {
      "epoch": 0.013628620102214651,
      "grad_norm": 2.0485944747924805,
      "learning_rate": 0.0,
      "loss": 0.3978,
      "step": 30
    },
    {
      "epoch": 0.013628620102214651,
      "eval_loss": 0.4265938103199005,
      "eval_runtime": 35.5332,
      "eval_samples_per_second": 26.088,
      "eval_steps_per_second": 13.058,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3015894871572480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}