{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012578616352201259,
      "grad_norm": 9.856545448303223,
      "learning_rate": 6.25e-08,
      "loss": 0.1027,
      "num_input_tokens_seen": 16384,
      "step": 1
    },
    {
      "epoch": 0.06289308176100629,
      "grad_norm": 11.089835166931152,
      "learning_rate": 3.1249999999999997e-07,
      "loss": 0.1198,
      "num_input_tokens_seen": 76168,
      "step": 5
    },
    {
      "epoch": 0.12578616352201258,
      "grad_norm": 15.803651809692383,
      "learning_rate": 6.249999999999999e-07,
      "loss": 0.1383,
      "num_input_tokens_seen": 149912,
      "step": 10
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 22.760234832763672,
      "learning_rate": 9.374999999999999e-07,
      "loss": 0.248,
      "num_input_tokens_seen": 226896,
      "step": 15
    },
    {
      "epoch": 0.25157232704402516,
      "grad_norm": 19.20156478881836,
      "learning_rate": 9.980434110374724e-07,
      "loss": 0.1197,
      "num_input_tokens_seen": 300528,
      "step": 20
    },
    {
      "epoch": 0.31446540880503143,
      "grad_norm": 7.172516345977783,
      "learning_rate": 9.901210054809014e-07,
      "loss": 0.0924,
      "num_input_tokens_seen": 374912,
      "step": 25
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 25.888011932373047,
      "learning_rate": 9.762072666790656e-07,
      "loss": 0.1603,
      "num_input_tokens_seen": 453440,
      "step": 30
    },
    {
      "epoch": 0.44025157232704404,
      "grad_norm": 15.700849533081055,
      "learning_rate": 9.564722788456943e-07,
      "loss": 0.1709,
      "num_input_tokens_seen": 528608,
      "step": 35
    },
    {
      "epoch": 0.5031446540880503,
      "grad_norm": 5.688323497772217,
      "learning_rate": 9.311572862600138e-07,
      "loss": 0.0813,
      "num_input_tokens_seen": 602320,
      "step": 40
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 7.077651023864746,
      "learning_rate": 9.005717442503739e-07,
      "loss": 0.173,
      "num_input_tokens_seen": 677240,
      "step": 45
    },
    {
      "epoch": 0.6289308176100629,
      "grad_norm": 7.772736549377441,
      "learning_rate": 8.650895363529172e-07,
      "loss": 0.1132,
      "num_input_tokens_seen": 754944,
      "step": 50
    },
    {
      "epoch": 0.6918238993710691,
      "grad_norm": 10.398797035217285,
      "learning_rate": 8.251444038874685e-07,
      "loss": 0.1637,
      "num_input_tokens_seen": 832976,
      "step": 55
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 8.86781120300293,
      "learning_rate": 7.812246438203903e-07,
      "loss": 0.0767,
      "num_input_tokens_seen": 909744,
      "step": 60
    },
    {
      "epoch": 0.8176100628930818,
      "grad_norm": 7.527681827545166,
      "learning_rate": 7.338671397287408e-07,
      "loss": 0.1128,
      "num_input_tokens_seen": 986672,
      "step": 65
    },
    {
      "epoch": 0.8805031446540881,
      "grad_norm": 12.296772956848145,
      "learning_rate": 6.836507988323784e-07,
      "loss": 0.155,
      "num_input_tokens_seen": 1063256,
      "step": 70
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 5.3815460205078125,
      "learning_rate": 6.311894753209895e-07,
      "loss": 0.1218,
      "num_input_tokens_seen": 1139944,
      "step": 75
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.86342191696167,
      "learning_rate": 5.771244664826511e-07,
      "loss": 0.0685,
      "num_input_tokens_seen": 1209864,
      "step": 80
    }
  ],
  "logging_steps": 5,
  "max_steps": 158,
  "num_input_tokens_seen": 1209864,
  "num_train_epochs": 2,
  "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": 6516860485632.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}