{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.998298355076574,
  "eval_steps": 6,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05445263754963131,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.2318,
      "step": 6
    },
    {
      "epoch": 0.10890527509926262,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.221,
      "step": 12
    },
    {
      "epoch": 0.16335791264889393,
      "grad_norm": 0.4241572618484497,
      "learning_rate": 0.0016329931618554523,
      "loss": 1.276,
      "step": 18
    },
    {
      "epoch": 0.21781055019852524,
      "grad_norm": 0.8251659274101257,
      "learning_rate": 0.0010690449676496977,
      "loss": 1.3199,
      "step": 24
    },
    {
      "epoch": 0.27226318774815655,
      "grad_norm": 0.5137020945549011,
      "learning_rate": 0.0007844645405527362,
      "loss": 0.9029,
      "step": 30
    },
    {
      "epoch": 0.32671582529778787,
      "grad_norm": 0.36745768785476685,
      "learning_rate": 0.0006488856845230502,
      "loss": 0.8627,
      "step": 36
    },
    {
      "epoch": 0.3811684628474192,
      "grad_norm": 0.2598075270652771,
      "learning_rate": 0.000565685424949238,
      "loss": 0.8395,
      "step": 42
    },
    {
      "epoch": 0.4356211003970505,
      "grad_norm": 0.2544526159763336,
      "learning_rate": 0.000508000508000762,
      "loss": 0.8215,
      "step": 48
    },
    {
      "epoch": 0.4900737379466818,
      "grad_norm": 0.24817149341106415,
      "learning_rate": 0.00046499055497527714,
      "loss": 0.8061,
      "step": 54
    },
    {
      "epoch": 0.5445263754963131,
      "grad_norm": 0.2519798278808594,
      "learning_rate": 0.00043133109281375367,
      "loss": 0.7974,
      "step": 60
    },
    {
      "epoch": 0.5989790130459444,
      "grad_norm": 0.2303462028503418,
      "learning_rate": 0.0004040610178208843,
      "loss": 0.7873,
      "step": 66
    },
    {
      "epoch": 0.6534316505955757,
      "grad_norm": 0.2645089030265808,
      "learning_rate": 0.00038138503569823694,
      "loss": 0.7853,
      "step": 72
    },
    {
      "epoch": 0.707884288145207,
      "grad_norm": 0.26605910062789917,
      "learning_rate": 0.00036214298417007413,
      "loss": 0.7686,
      "step": 78
    },
    {
      "epoch": 0.7623369256948384,
      "grad_norm": 0.22281917929649353,
      "learning_rate": 0.0003455473702325441,
      "loss": 0.7476,
      "step": 84
    },
    {
      "epoch": 0.8167895632444696,
      "grad_norm": 0.2260071039199829,
      "learning_rate": 0.00033104235544094716,
      "loss": 0.7326,
      "step": 90
    },
    {
      "epoch": 0.871242200794101,
      "grad_norm": 0.2315952628850937,
      "learning_rate": 0.000318222913670292,
      "loss": 0.7728,
      "step": 96
    },
    {
      "epoch": 0.9256948383437322,
      "grad_norm": 0.22036141157150269,
      "learning_rate": 0.00030678599553894816,
      "loss": 0.7623,
      "step": 102
    },
    {
      "epoch": 0.9801474758933636,
      "grad_norm": 0.22690173983573914,
      "learning_rate": 0.00029649972666444046,
      "loss": 0.7514,
      "step": 108
    },
    {
      "epoch": 0.998298355076574,
      "step": 110,
      "total_flos": 1.1172110162041242e+18,
      "train_loss": 0.8966737844727256,
      "train_runtime": 979.7853,
      "train_samples_per_second": 14.389,
      "train_steps_per_second": 0.112
    }
  ],
  "logging_steps": 6,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1172110162041242e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}