{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9950445986124876,
  "eval_steps": 500,
  "global_step": 504,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19819150253932863,
      "grad_norm": 2.337883472442627,
      "learning_rate": 9.938184937771903e-06,
      "loss": 1.2991,
      "memory/device_mem_reserved(gib)": 74.87,
      "memory/max_mem_active(gib)": 64.54,
      "memory/max_mem_allocated(gib)": 64.54,
      "step": 50
    },
    {
      "epoch": 0.39638300507865726,
      "grad_norm": 0.3401966691017151,
      "learning_rate": 9.422581953373704e-06,
      "loss": 0.2659,
      "memory/device_mem_reserved(gib)": 74.87,
      "memory/max_mem_active(gib)": 64.54,
      "memory/max_mem_allocated(gib)": 64.54,
      "step": 100
    },
    {
      "epoch": 0.5945745076179859,
      "grad_norm": 0.3944408595561981,
      "learning_rate": 8.435622868637562e-06,
      "loss": 0.1302,
      "memory/device_mem_reserved(gib)": 74.87,
      "memory/max_mem_active(gib)": 64.54,
      "memory/max_mem_allocated(gib)": 64.54,
      "step": 150
    },
    {
      "epoch": 0.7927660101573145,
      "grad_norm": 0.375704288482666,
      "learning_rate": 7.0824971837873154e-06,
      "loss": 0.0999,
      "memory/device_mem_reserved(gib)": 74.87,
      "memory/max_mem_active(gib)": 64.54,
      "memory/max_mem_allocated(gib)": 64.54,
      "step": 200
    },
    {
      "epoch": 0.9909575126966431,
      "grad_norm": 0.3060258626937866,
      "learning_rate": 5.507420213044915e-06,
      "loss": 0.0799,
      "memory/device_mem_reserved(gib)": 74.87,
      "memory/max_mem_active(gib)": 64.54,
      "memory/max_mem_allocated(gib)": 64.54,
      "step": 250
    },
    {
      "epoch": 1.1863230921704657,
      "grad_norm": 0.22064049541950226,
      "learning_rate": 3.878262703971043e-06,
      "loss": 0.079,
      "memory/device_mem_reserved(gib)": 76.23,
      "memory/max_mem_active(gib)": 63.17,
      "memory/max_mem_allocated(gib)": 63.17,
      "step": 300
    },
    {
      "epoch": 1.3845391476709614,
      "grad_norm": 0.7604629993438721,
      "learning_rate": 2.3686592750779788e-06,
      "loss": 0.0724,
      "memory/device_mem_reserved(gib)": 76.23,
      "memory/max_mem_active(gib)": 63.17,
      "memory/max_mem_allocated(gib)": 63.17,
      "step": 350
    },
    {
      "epoch": 1.582755203171457,
      "grad_norm": 0.2681162655353546,
      "learning_rate": 1.1395025435747759e-06,
      "loss": 0.0755,
      "memory/device_mem_reserved(gib)": 76.23,
      "memory/max_mem_active(gib)": 63.17,
      "memory/max_mem_allocated(gib)": 63.17,
      "step": 400
    },
    {
      "epoch": 1.7809712586719524,
      "grad_norm": 0.23132048547267914,
      "learning_rate": 3.2179528787767313e-07,
      "loss": 0.0725,
      "memory/device_mem_reserved(gib)": 76.23,
      "memory/max_mem_active(gib)": 63.17,
      "memory/max_mem_allocated(gib)": 63.17,
      "step": 450
    },
    {
      "epoch": 1.979187314172448,
      "grad_norm": 0.2875792384147644,
      "learning_rate": 2.6882509976433604e-09,
      "loss": 0.0714,
      "memory/device_mem_reserved(gib)": 76.23,
      "memory/max_mem_active(gib)": 63.17,
      "memory/max_mem_allocated(gib)": 63.17,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 504,
  "num_input_tokens_seen": 0,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.517914304745308e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}