{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 1000,
  "global_step": 1158,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17271157167530224,
      "grad_norm": 2.183316946029663,
      "learning_rate": 1e-05,
      "loss": 1.8532,
      "step": 100
    },
    {
      "epoch": 0.3454231433506045,
      "grad_norm": 2.597714424133301,
      "learning_rate": 2e-05,
      "loss": 1.7855,
      "step": 200
    },
    {
      "epoch": 0.5181347150259067,
      "grad_norm": 2.9139578342437744,
      "learning_rate": 3e-05,
      "loss": 1.594,
      "step": 300
    },
    {
      "epoch": 0.690846286701209,
      "grad_norm": 3.019888162612915,
      "learning_rate": 4e-05,
      "loss": 1.5054,
      "step": 400
    },
    {
      "epoch": 0.8635578583765112,
      "grad_norm": 2.9077558517456055,
      "learning_rate": 5e-05,
      "loss": 1.4328,
      "step": 500
    },
    {
      "epoch": 1.0362694300518134,
      "grad_norm": 2.961933135986328,
      "learning_rate": 4.2401215805471125e-05,
      "loss": 1.3829,
      "step": 600
    },
    {
      "epoch": 1.2089810017271156,
      "grad_norm": 2.7607100009918213,
      "learning_rate": 3.480243161094225e-05,
      "loss": 1.339,
      "step": 700
    },
    {
      "epoch": 1.381692573402418,
      "grad_norm": 3.11777400970459,
      "learning_rate": 2.7203647416413374e-05,
      "loss": 1.3353,
      "step": 800
    },
    {
      "epoch": 1.5544041450777202,
      "grad_norm": 3.1563587188720703,
      "learning_rate": 1.96048632218845e-05,
      "loss": 1.3264,
      "step": 900
    },
    {
      "epoch": 1.7271157167530224,
      "grad_norm": 3.3616676330566406,
      "learning_rate": 1.2006079027355625e-05,
      "loss": 1.3414,
      "step": 1000
    },
    {
      "epoch": 1.7271157167530224,
      "eval_runtime": 1213.4576,
      "eval_samples_per_second": 1.907,
      "eval_steps_per_second": 0.239,
      "step": 1000
    },
    {
      "epoch": 1.8998272884283247,
      "grad_norm": 2.7425153255462646,
      "learning_rate": 4.407294832826748e-06,
      "loss": 1.3114,
      "step": 1100
    }
  ],
  "logging_steps": 100,
  "max_steps": 1158,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.866988058745242e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}