{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14272970561998216,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007136485280999108,
      "eval_loss": 0.6165480017662048,
      "eval_runtime": 55.534,
      "eval_samples_per_second": 10.624,
      "eval_steps_per_second": 5.312,
      "step": 1
    },
    {
      "epoch": 0.007136485280999108,
      "grad_norm": 0.39041173458099365,
      "learning_rate": 0.00019967573081342103,
      "loss": 0.4714,
      "step": 10
    },
    {
      "epoch": 0.014272970561998216,
      "grad_norm": 0.35318252444267273,
      "learning_rate": 0.0001970941817426052,
      "loss": 0.3333,
      "step": 20
    },
    {
      "epoch": 0.021409455842997322,
      "grad_norm": 0.22868792712688446,
      "learning_rate": 0.00019199794436588243,
      "loss": 0.3151,
      "step": 30
    },
    {
      "epoch": 0.028545941123996433,
      "grad_norm": 0.2561885714530945,
      "learning_rate": 0.0001845190085543795,
      "loss": 0.3316,
      "step": 40
    },
    {
      "epoch": 0.03568242640499554,
      "grad_norm": 0.27606117725372314,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.2918,
      "step": 50
    },
    {
      "epoch": 0.03568242640499554,
      "eval_loss": 0.3071356415748596,
      "eval_runtime": 55.5552,
      "eval_samples_per_second": 10.62,
      "eval_steps_per_second": 5.31,
      "step": 50
    },
    {
      "epoch": 0.042818911685994644,
      "grad_norm": 0.22240565717220306,
      "learning_rate": 0.00016324453755953773,
      "loss": 0.3401,
      "step": 60
    },
    {
      "epoch": 0.049955396966993755,
      "grad_norm": 0.25228607654571533,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.3181,
      "step": 70
    },
    {
      "epoch": 0.057091882247992866,
      "grad_norm": 0.25924035906791687,
      "learning_rate": 0.00013546048870425356,
      "loss": 0.3091,
      "step": 80
    },
    {
      "epoch": 0.06422836752899197,
      "grad_norm": 0.22803744673728943,
      "learning_rate": 0.00012000256937760445,
      "loss": 0.3028,
      "step": 90
    },
    {
      "epoch": 0.07136485280999108,
      "grad_norm": 0.2437671571969986,
      "learning_rate": 0.00010402659401094152,
      "loss": 0.2869,
      "step": 100
    },
    {
      "epoch": 0.07136485280999108,
      "eval_loss": 0.2971809506416321,
      "eval_runtime": 55.5199,
      "eval_samples_per_second": 10.627,
      "eval_steps_per_second": 5.313,
      "step": 100
    },
    {
      "epoch": 0.07850133809099019,
      "grad_norm": 0.26714345812797546,
      "learning_rate": 8.79463319744677e-05,
      "loss": 0.3431,
      "step": 110
    },
    {
      "epoch": 0.08563782337198929,
      "grad_norm": 0.21566510200500488,
      "learning_rate": 7.217825360835473e-05,
      "loss": 0.2721,
      "step": 120
    },
    {
      "epoch": 0.0927743086529884,
      "grad_norm": 0.25159725546836853,
      "learning_rate": 5.713074385969457e-05,
      "loss": 0.3095,
      "step": 130
    },
    {
      "epoch": 0.09991079393398751,
      "grad_norm": 0.2559829652309418,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 0.3015,
      "step": 140
    },
    {
      "epoch": 0.10704727921498662,
      "grad_norm": 0.22735165059566498,
      "learning_rate": 3.072756464904006e-05,
      "loss": 0.2623,
      "step": 150
    },
    {
      "epoch": 0.10704727921498662,
      "eval_loss": 0.2916809618473053,
      "eval_runtime": 55.5435,
      "eval_samples_per_second": 10.622,
      "eval_steps_per_second": 5.311,
      "step": 150
    },
    {
      "epoch": 0.11418376449598573,
      "grad_norm": 0.24490103125572205,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 0.3098,
      "step": 160
    },
    {
      "epoch": 0.12132024977698483,
      "grad_norm": 0.21790523827075958,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 0.2828,
      "step": 170
    },
    {
      "epoch": 0.12845673505798394,
      "grad_norm": 0.24194355309009552,
      "learning_rate": 5.146355805285452e-06,
      "loss": 0.2992,
      "step": 180
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 0.29640981554985046,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 0.3089,
      "step": 190
    },
    {
      "epoch": 0.14272970561998216,
      "grad_norm": 0.4439384341239929,
      "learning_rate": 0.0,
      "loss": 0.3361,
      "step": 200
    },
    {
      "epoch": 0.14272970561998216,
      "eval_loss": 0.2901231050491333,
      "eval_runtime": 55.6242,
      "eval_samples_per_second": 10.607,
      "eval_steps_per_second": 5.303,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.168526596957798e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}