{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016448315281307312,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.2896630562614627e-05,
      "eval_loss": 2.757455348968506,
      "eval_runtime": 409.7731,
      "eval_samples_per_second": 31.237,
      "eval_steps_per_second": 15.618,
      "step": 1
    },
    {
      "epoch": 0.0001644831528130731,
      "grad_norm": 1.5864917039871216,
      "learning_rate": 5e-05,
      "loss": 2.8875,
      "step": 5
    },
    {
      "epoch": 0.0003289663056261462,
      "grad_norm": 1.2908947467803955,
      "learning_rate": 0.0001,
      "loss": 2.7408,
      "step": 10
    },
    {
      "epoch": 0.0003289663056261462,
      "eval_loss": 2.6381289958953857,
      "eval_runtime": 418.9016,
      "eval_samples_per_second": 30.556,
      "eval_steps_per_second": 15.278,
      "step": 10
    },
    {
      "epoch": 0.0004934494584392194,
      "grad_norm": 1.0580534934997559,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.6184,
      "step": 15
    },
    {
      "epoch": 0.0006579326112522924,
      "grad_norm": 0.9917417764663696,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.6363,
      "step": 20
    },
    {
      "epoch": 0.0006579326112522924,
      "eval_loss": 2.5264508724212646,
      "eval_runtime": 418.3664,
      "eval_samples_per_second": 30.595,
      "eval_steps_per_second": 15.298,
      "step": 20
    },
    {
      "epoch": 0.0008224157640653656,
      "grad_norm": 0.8751965761184692,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.5034,
      "step": 25
    },
    {
      "epoch": 0.0009868989168784388,
      "grad_norm": 0.8939478993415833,
      "learning_rate": 5e-05,
      "loss": 2.5836,
      "step": 30
    },
    {
      "epoch": 0.0009868989168784388,
      "eval_loss": 2.4934544563293457,
      "eval_runtime": 412.0983,
      "eval_samples_per_second": 31.061,
      "eval_steps_per_second": 15.53,
      "step": 30
    },
    {
      "epoch": 0.001151382069691512,
      "grad_norm": 0.9748537540435791,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.5254,
      "step": 35
    },
    {
      "epoch": 0.001315865222504585,
      "grad_norm": 1.0387564897537231,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.588,
      "step": 40
    },
    {
      "epoch": 0.001315865222504585,
      "eval_loss": 2.4847793579101562,
      "eval_runtime": 412.2008,
      "eval_samples_per_second": 31.053,
      "eval_steps_per_second": 15.526,
      "step": 40
    },
    {
      "epoch": 0.001480348375317658,
      "grad_norm": 0.9422990083694458,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.5758,
      "step": 45
    },
    {
      "epoch": 0.0016448315281307312,
      "grad_norm": 0.8218869566917419,
      "learning_rate": 0.0,
      "loss": 2.5283,
      "step": 50
    },
    {
      "epoch": 0.0016448315281307312,
      "eval_loss": 2.4830634593963623,
      "eval_runtime": 411.1322,
      "eval_samples_per_second": 31.134,
      "eval_steps_per_second": 15.567,
      "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": 383619013017600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}