{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 158,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12779552715654952,
      "grad_norm": 18.5,
      "learning_rate": 9.999529497453782e-06,
      "loss": 3.7181739807128906,
      "mean_token_accuracy": 0.4391625240445137,
      "num_tokens": 21235.0,
      "step": 10
    },
    {
      "epoch": 0.25559105431309903,
      "grad_norm": 7.21875,
      "learning_rate": 9.943176257655567e-06,
      "loss": 1.891798973083496,
      "mean_token_accuracy": 0.6172753922641278,
      "num_tokens": 43208.0,
      "step": 20
    },
    {
      "epoch": 0.38338658146964855,
      "grad_norm": 7.65625,
      "learning_rate": 9.793936295756292e-06,
      "loss": 1.6918453216552733,
      "mean_token_accuracy": 0.6530756063759326,
      "num_tokens": 64501.0,
      "step": 30
    },
    {
      "epoch": 0.5111821086261981,
      "grad_norm": 8.25,
      "learning_rate": 9.554613964695189e-06,
      "loss": 1.5507073402404785,
      "mean_token_accuracy": 0.67677718475461,
      "num_tokens": 85419.0,
      "step": 40
    },
    {
      "epoch": 0.6389776357827476,
      "grad_norm": 5.90625,
      "learning_rate": 9.229706346044749e-06,
      "loss": 1.5302507400512695,
      "mean_token_accuracy": 0.6773553751409054,
      "num_tokens": 105883.0,
      "step": 50
    },
    {
      "epoch": 0.7667731629392971,
      "grad_norm": 5.71875,
      "learning_rate": 8.82531874580844e-06,
      "loss": 1.494858455657959,
      "mean_token_accuracy": 0.6708411455154419,
      "num_tokens": 127613.0,
      "step": 60
    },
    {
      "epoch": 0.8945686900958466,
      "grad_norm": 6.3125,
      "learning_rate": 8.349049970236822e-06,
      "loss": 1.5066747665405273,
      "mean_token_accuracy": 0.669723616540432,
      "num_tokens": 149072.0,
      "step": 70
    },
    {
      "epoch": 1.012779552715655,
      "grad_norm": 5.625,
      "learning_rate": 7.809849537432432e-06,
      "loss": 1.4628400802612305,
      "mean_token_accuracy": 0.6772601225891629,
      "num_tokens": 169145.0,
      "step": 80
    },
    {
      "epoch": 1.1405750798722045,
      "grad_norm": 5.0625,
      "learning_rate": 7.217849507865724e-06,
      "loss": 1.376960563659668,
      "mean_token_accuracy": 0.6908419519662857,
      "num_tokens": 190389.0,
      "step": 90
    },
    {
      "epoch": 1.268370607028754,
      "grad_norm": 5.15625,
      "learning_rate": 6.584174093857676e-06,
      "loss": 1.36422758102417,
      "mean_token_accuracy": 0.6926982000470161,
      "num_tokens": 212740.0,
      "step": 100
    },
    {
      "epoch": 1.3961661341853036,
      "grad_norm": 5.78125,
      "learning_rate": 5.920730625637934e-06,
      "loss": 1.4209732055664062,
      "mean_token_accuracy": 0.6916342236101627,
      "num_tokens": 234029.0,
      "step": 110
    },
    {
      "epoch": 1.5239616613418532,
      "grad_norm": 5.1875,
      "learning_rate": 5.2399858019140005e-06,
      "loss": 1.343826675415039,
      "mean_token_accuracy": 0.6992332696914673,
      "num_tokens": 255213.0,
      "step": 120
    },
    {
      "epoch": 1.6517571884984026,
      "grad_norm": 5.625,
      "learning_rate": 4.554731429404293e-06,
      "loss": 1.3290119171142578,
      "mean_token_accuracy": 0.7052423760294915,
      "num_tokens": 275442.0,
      "step": 130
    },
    {
      "epoch": 1.779552715654952,
      "grad_norm": 5.625,
      "learning_rate": 3.87784405329962e-06,
      "loss": 1.3492921829223632,
      "mean_token_accuracy": 0.6974035024642944,
      "num_tokens": 296810.0,
      "step": 140
    },
    {
      "epoch": 1.9073482428115016,
      "grad_norm": 5.71875,
      "learning_rate": 3.222042995412669e-06,
      "loss": 1.365804100036621,
      "mean_token_accuracy": 0.6936390474438667,
      "num_tokens": 317830.0,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 237,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4999952478812160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}