{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0405926527298559,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008118530545971179,
      "eval_loss": 3.347118854522705,
      "eval_runtime": 10.23,
      "eval_samples_per_second": 202.835,
      "eval_steps_per_second": 25.416,
      "step": 1
    },
    {
      "epoch": 0.004059265272985589,
      "grad_norm": 1.7521936893463135,
      "learning_rate": 5e-05,
      "loss": 3.2952,
      "step": 5
    },
    {
      "epoch": 0.008118530545971179,
      "grad_norm": 1.8896790742874146,
      "learning_rate": 0.0001,
      "loss": 3.0832,
      "step": 10
    },
    {
      "epoch": 0.008118530545971179,
      "eval_loss": 2.856214761734009,
      "eval_runtime": 10.1919,
      "eval_samples_per_second": 203.593,
      "eval_steps_per_second": 25.51,
      "step": 10
    },
    {
      "epoch": 0.012177795818956769,
      "grad_norm": 1.7719788551330566,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.5535,
      "step": 15
    },
    {
      "epoch": 0.016237061091942357,
      "grad_norm": 1.603336215019226,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9786,
      "step": 20
    },
    {
      "epoch": 0.016237061091942357,
      "eval_loss": 1.7487651109695435,
      "eval_runtime": 10.1456,
      "eval_samples_per_second": 204.522,
      "eval_steps_per_second": 25.627,
      "step": 20
    },
    {
      "epoch": 0.02029632636492795,
      "grad_norm": 1.4670517444610596,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6016,
      "step": 25
    },
    {
      "epoch": 0.024355591637913537,
      "grad_norm": 1.3406275510787964,
      "learning_rate": 5e-05,
      "loss": 1.3608,
      "step": 30
    },
    {
      "epoch": 0.024355591637913537,
      "eval_loss": 1.2690577507019043,
      "eval_runtime": 10.1814,
      "eval_samples_per_second": 203.803,
      "eval_steps_per_second": 25.537,
      "step": 30
    },
    {
      "epoch": 0.028414856910899126,
      "grad_norm": 1.1591341495513916,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.2299,
      "step": 35
    },
    {
      "epoch": 0.032474122183884714,
      "grad_norm": 1.445990800857544,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.1991,
      "step": 40
    },
    {
      "epoch": 0.032474122183884714,
      "eval_loss": 1.141239047050476,
      "eval_runtime": 10.1908,
      "eval_samples_per_second": 203.615,
      "eval_steps_per_second": 25.513,
      "step": 40
    },
    {
      "epoch": 0.036533387456870306,
      "grad_norm": 1.2058775424957275,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.1088,
      "step": 45
    },
    {
      "epoch": 0.0405926527298559,
      "grad_norm": 1.1205410957336426,
      "learning_rate": 0.0,
      "loss": 1.1277,
      "step": 50
    },
    {
      "epoch": 0.0405926527298559,
      "eval_loss": 1.120613932609558,
      "eval_runtime": 10.1316,
      "eval_samples_per_second": 204.806,
      "eval_steps_per_second": 25.662,
      "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": 5115839565004800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}