{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025,
      "grad_norm": 5.632253646850586,
      "learning_rate": 1.25e-08,
      "loss": 0.0817,
      "num_input_tokens_seen": 30616,
      "step": 1
    },
    {
      "epoch": 0.25,
      "grad_norm": 10.799251556396484,
      "learning_rate": 9.980973490458727e-08,
      "loss": 0.1641,
      "num_input_tokens_seen": 301784,
      "step": 10
    },
    {
      "epoch": 0.5,
      "grad_norm": 6.7454352378845215,
      "learning_rate": 9.330127018922194e-08,
      "loss": 0.1429,
      "num_input_tokens_seen": 605040,
      "step": 20
    },
    {
      "epoch": 0.75,
      "grad_norm": 8.523561477661133,
      "learning_rate": 7.86788218175523e-08,
      "loss": 0.1787,
      "num_input_tokens_seen": 913096,
      "step": 30
    },
    {
      "epoch": 1.0,
      "grad_norm": 13.516364097595215,
      "learning_rate": 5.868240888334653e-08,
      "loss": 0.1711,
      "num_input_tokens_seen": 1221704,
      "step": 40
    },
    {
      "epoch": 1.25,
      "grad_norm": 9.197039604187012,
      "learning_rate": 3.705904774487396e-08,
      "loss": 0.1756,
      "num_input_tokens_seen": 1529696,
      "step": 50
    },
    {
      "epoch": 1.5,
      "grad_norm": 17.770536422729492,
      "learning_rate": 1.786061951567303e-08,
      "loss": 0.1114,
      "num_input_tokens_seen": 1834848,
      "step": 60
    },
    {
      "epoch": 1.75,
      "grad_norm": 7.028417587280273,
      "learning_rate": 4.684610648167503e-09,
      "loss": 0.1535,
      "num_input_tokens_seen": 2134968,
      "step": 70
    },
    {
      "epoch": 2.0,
      "grad_norm": 32.19283676147461,
      "learning_rate": 0.0,
      "loss": 0.1963,
      "num_input_tokens_seen": 2441952,
      "step": 80
    },
    {
      "epoch": 2.0,
      "num_input_tokens_seen": 2441952,
      "step": 80,
      "total_flos": 13198335098880.0,
      "train_loss": 0.16065627336502075,
      "train_runtime": 1774.0756,
      "train_samples_per_second": 0.358,
      "train_steps_per_second": 0.045
    }
  ],
  "logging_steps": 10,
  "max_steps": 80,
  "num_input_tokens_seen": 2441952,
  "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": 13198335098880.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}