{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 2880.0,
      "learning_rate": 7.999999999999999e-05,
      "loss": 3.1943845748901367,
      "step": 5
    },
    {
      "epoch": 0.02,
      "grad_norm": 111104.0,
      "learning_rate": 0.00017999999999999998,
      "loss": 3.2289222717285155,
      "step": 10
    },
    {
      "epoch": 0.03,
      "grad_norm": 7776.0,
      "learning_rate": 0.00028,
      "loss": 3.2137096405029295,
      "step": 15
    },
    {
      "epoch": 0.04,
      "grad_norm": 13952.0,
      "learning_rate": 0.0003,
      "loss": 3.192697525024414,
      "step": 20
    },
    {
      "epoch": 0.05,
      "grad_norm": 34304.0,
      "learning_rate": 0.0003,
      "loss": 3.1834150314331056,
      "step": 25
    },
    {
      "epoch": 0.06,
      "grad_norm": 3296.0,
      "learning_rate": 0.0003,
      "loss": 3.2362594604492188,
      "step": 30
    },
    {
      "epoch": 0.07,
      "grad_norm": 33024.0,
      "learning_rate": 0.0003,
      "loss": 3.2107208251953123,
      "step": 35
    },
    {
      "epoch": 0.08,
      "grad_norm": 45312.0,
      "learning_rate": 0.0003,
      "loss": 3.219687652587891,
      "step": 40
    },
    {
      "epoch": 0.09,
      "grad_norm": 2112.0,
      "learning_rate": 0.0003,
      "loss": 3.2011333465576173,
      "step": 45
    },
    {
      "epoch": 0.1,
      "grad_norm": 3584.0,
      "learning_rate": 0.0003,
      "loss": 3.2285308837890625,
      "step": 50
    },
    {
      "epoch": 0.1,
      "eval_loss": 3.5073623657226562,
      "eval_runtime": 9.0594,
      "eval_samples_per_second": 1.987,
      "eval_steps_per_second": 1.987,
      "step": 50
    },
    {
      "epoch": 0.11,
      "grad_norm": 828.0,
      "learning_rate": 0.0003,
      "loss": 3.205875778198242,
      "step": 55
    },
    {
      "epoch": 0.12,
      "grad_norm": 8096.0,
      "learning_rate": 0.0003,
      "loss": 3.2160839080810546,
      "step": 60
    },
    {
      "epoch": 0.13,
      "grad_norm": 9728.0,
      "learning_rate": 0.0003,
      "loss": 3.2235694885253907,
      "step": 65
    },
    {
      "epoch": 0.14,
      "grad_norm": 35584.0,
      "learning_rate": 0.0003,
      "loss": 3.271558380126953,
      "step": 70
    },
    {
      "epoch": 0.15,
      "grad_norm": 2672.0,
      "learning_rate": 0.0003,
      "loss": 3.263863372802734,
      "step": 75
    },
    {
      "epoch": 0.16,
      "grad_norm": 5504.0,
      "learning_rate": 0.0003,
      "loss": 3.264923858642578,
      "step": 80
    },
    {
      "epoch": 0.17,
      "grad_norm": 296960.0,
      "learning_rate": 0.0003,
      "loss": 3.2530628204345704,
      "step": 85
    },
    {
      "epoch": 0.18,
      "grad_norm": 2608.0,
      "learning_rate": 0.0003,
      "loss": 3.279144287109375,
      "step": 90
    },
    {
      "epoch": 0.19,
      "grad_norm": 1736.0,
      "learning_rate": 0.0003,
      "loss": 3.2283939361572265,
      "step": 95
    },
    {
      "epoch": 0.2,
      "grad_norm": 2928.0,
      "learning_rate": 0.0003,
      "loss": 3.276975631713867,
      "step": 100
    },
    {
      "epoch": 0.2,
      "eval_loss": 3.581308126449585,
      "eval_runtime": 9.0248,
      "eval_samples_per_second": 1.995,
      "eval_steps_per_second": 1.995,
      "step": 100
    },
    {
      "epoch": 0.21,
      "grad_norm": 2384.0,
      "learning_rate": 0.0003,
      "loss": 3.2437297821044924,
      "step": 105
    },
    {
      "epoch": 0.22,
      "grad_norm": 13440.0,
      "learning_rate": 0.0003,
      "loss": 3.1839040756225585,
      "step": 110
    },
    {
      "epoch": 0.23,
      "grad_norm": 744.0,
      "learning_rate": 0.0003,
      "loss": 3.157756805419922,
      "step": 115
    },
    {
      "epoch": 0.24,
      "grad_norm": 207.0,
      "learning_rate": 0.0003,
      "loss": 3.179922676086426,
      "step": 120
    },
    {
      "epoch": 0.25,
      "grad_norm": 660.0,
      "learning_rate": 0.0003,
      "loss": 3.1574981689453123,
      "step": 125
    },
    {
      "epoch": 0.26,
      "grad_norm": 99.0,
      "learning_rate": 0.0003,
      "loss": 3.1093936920166017,
      "step": 130
    },
    {
      "epoch": 0.27,
      "grad_norm": 936.0,
      "learning_rate": 0.0003,
      "loss": 3.068846893310547,
      "step": 135
    },
    {
      "epoch": 0.28,
      "grad_norm": 1296.0,
      "learning_rate": 0.0003,
      "loss": 3.043972206115723,
      "step": 140
    },
    {
      "epoch": 0.29,
      "grad_norm": 152.0,
      "learning_rate": 0.0003,
      "loss": 3.063678741455078,
      "step": 145
    },
    {
      "epoch": 0.3,
      "grad_norm": 50.0,
      "learning_rate": 0.0003,
      "loss": 3.0807422637939452,
      "step": 150
    },
    {
      "epoch": 0.3,
      "eval_loss": 3.381226062774658,
      "eval_runtime": 8.9995,
      "eval_samples_per_second": 2.0,
      "eval_steps_per_second": 2.0,
      "step": 150
    },
    {
      "epoch": 0.31,
      "grad_norm": 652.0,
      "learning_rate": 0.0003,
      "loss": 3.050394821166992,
      "step": 155
    },
    {
      "epoch": 0.32,
      "grad_norm": 187.0,
      "learning_rate": 0.0003,
      "loss": 3.1013137817382814,
      "step": 160
    },
    {
      "epoch": 0.33,
      "grad_norm": 430.0,
      "learning_rate": 0.0003,
      "loss": 3.052425003051758,
      "step": 165
    },
    {
      "epoch": 0.34,
      "grad_norm": 147.0,
      "learning_rate": 0.0003,
      "loss": 3.0121395111083986,
      "step": 170
    },
    {
      "epoch": 0.35,
      "grad_norm": 382.0,
      "learning_rate": 0.0003,
      "loss": 3.015604591369629,
      "step": 175
    },
    {
      "epoch": 0.36,
      "grad_norm": 368.0,
      "learning_rate": 0.0003,
      "loss": 3.006996726989746,
      "step": 180
    },
    {
      "epoch": 0.37,
      "grad_norm": 14.5625,
      "learning_rate": 0.0003,
      "loss": 3.026082992553711,
      "step": 185
    },
    {
      "epoch": 0.38,
      "grad_norm": 158.0,
      "learning_rate": 0.0003,
      "loss": 3.029666709899902,
      "step": 190
    },
    {
      "epoch": 0.39,
      "grad_norm": 62.25,
      "learning_rate": 0.0003,
      "loss": 2.9676319122314454,
      "step": 195
    },
    {
      "epoch": 0.4,
      "grad_norm": 1496.0,
      "learning_rate": 0.0003,
      "loss": 3.016917419433594,
      "step": 200
    },
    {
      "epoch": 0.4,
      "eval_loss": 3.3380279541015625,
      "eval_runtime": 9.0151,
      "eval_samples_per_second": 1.997,
      "eval_steps_per_second": 1.997,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.79830248636416e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}