{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005685856432125089,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005685856432125089,
      "grad_norm": 0.027778511866927147,
      "learning_rate": 2e-05,
      "loss": 10.3767,
      "step": 1
    },
    {
      "epoch": 0.0005685856432125089,
      "eval_loss": 10.37804126739502,
      "eval_runtime": 2.07,
      "eval_samples_per_second": 357.967,
      "eval_steps_per_second": 179.225,
      "step": 1
    },
    {
      "epoch": 0.0011371712864250178,
      "grad_norm": 0.025175217539072037,
      "learning_rate": 4e-05,
      "loss": 10.3764,
      "step": 2
    },
    {
      "epoch": 0.0017057569296375266,
      "grad_norm": 0.029762376099824905,
      "learning_rate": 6e-05,
      "loss": 10.3729,
      "step": 3
    },
    {
      "epoch": 0.0017057569296375266,
      "eval_loss": 10.378033638000488,
      "eval_runtime": 1.9993,
      "eval_samples_per_second": 370.631,
      "eval_steps_per_second": 185.566,
      "step": 3
    },
    {
      "epoch": 0.0022743425728500356,
      "grad_norm": 0.021651335060596466,
      "learning_rate": 8e-05,
      "loss": 10.3822,
      "step": 4
    },
    {
      "epoch": 0.0028429282160625444,
      "grad_norm": 0.022406775504350662,
      "learning_rate": 0.0001,
      "loss": 10.379,
      "step": 5
    },
    {
      "epoch": 0.003411513859275053,
      "grad_norm": 0.022688135504722595,
      "learning_rate": 0.00012,
      "loss": 10.38,
      "step": 6
    },
    {
      "epoch": 0.003411513859275053,
      "eval_loss": 10.377971649169922,
      "eval_runtime": 2.0968,
      "eval_samples_per_second": 353.395,
      "eval_steps_per_second": 176.936,
      "step": 6
    },
    {
      "epoch": 0.003980099502487562,
      "grad_norm": 0.02032436616718769,
      "learning_rate": 0.00014,
      "loss": 10.3819,
      "step": 7
    },
    {
      "epoch": 0.004548685145700071,
      "grad_norm": 0.03226882219314575,
      "learning_rate": 0.00016,
      "loss": 10.3762,
      "step": 8
    },
    {
      "epoch": 0.00511727078891258,
      "grad_norm": 0.029927022755146027,
      "learning_rate": 0.00018,
      "loss": 10.3753,
      "step": 9
    },
    {
      "epoch": 0.00511727078891258,
      "eval_loss": 10.377878189086914,
      "eval_runtime": 2.0184,
      "eval_samples_per_second": 367.126,
      "eval_steps_per_second": 183.811,
      "step": 9
    },
    {
      "epoch": 0.005685856432125089,
      "grad_norm": 0.024643944576382637,
      "learning_rate": 0.0002,
      "loss": 10.3809,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 164869079040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}