{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00014832558950151478,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4832558950151478e-05,
      "grad_norm": 1032.5780029296875,
      "learning_rate": 2e-05,
      "loss": 95.6979,
      "step": 1
    },
    {
      "epoch": 1.4832558950151478e-05,
      "eval_loss": 23.534069061279297,
      "eval_runtime": 1979.9599,
      "eval_samples_per_second": 14.337,
      "eval_steps_per_second": 7.169,
      "step": 1
    },
    {
      "epoch": 2.9665117900302956e-05,
      "grad_norm": 1325.1285400390625,
      "learning_rate": 4e-05,
      "loss": 96.301,
      "step": 2
    },
    {
      "epoch": 4.449767685045443e-05,
      "grad_norm": 1420.2266845703125,
      "learning_rate": 6e-05,
      "loss": 95.2096,
      "step": 3
    },
    {
      "epoch": 4.449767685045443e-05,
      "eval_loss": 23.52667999267578,
      "eval_runtime": 1953.433,
      "eval_samples_per_second": 14.532,
      "eval_steps_per_second": 7.266,
      "step": 3
    },
    {
      "epoch": 5.933023580060591e-05,
      "grad_norm": 1357.5682373046875,
      "learning_rate": 8e-05,
      "loss": 93.3733,
      "step": 4
    },
    {
      "epoch": 7.416279475075739e-05,
      "grad_norm": 1045.089599609375,
      "learning_rate": 0.0001,
      "loss": 94.556,
      "step": 5
    },
    {
      "epoch": 8.899535370090886e-05,
      "grad_norm": 1248.4478759765625,
      "learning_rate": 0.00012,
      "loss": 94.1798,
      "step": 6
    },
    {
      "epoch": 8.899535370090886e-05,
      "eval_loss": 23.505847930908203,
      "eval_runtime": 2012.6089,
      "eval_samples_per_second": 14.105,
      "eval_steps_per_second": 7.053,
      "step": 6
    },
    {
      "epoch": 0.00010382791265106034,
      "grad_norm": 1596.7059326171875,
      "learning_rate": 0.00014,
      "loss": 92.502,
      "step": 7
    },
    {
      "epoch": 0.00011866047160121182,
      "grad_norm": 1535.9053955078125,
      "learning_rate": 0.00016,
      "loss": 93.105,
      "step": 8
    },
    {
      "epoch": 0.0001334930305513633,
      "grad_norm": 1895.4942626953125,
      "learning_rate": 0.00018,
      "loss": 94.8532,
      "step": 9
    },
    {
      "epoch": 0.0001334930305513633,
      "eval_loss": 23.469181060791016,
      "eval_runtime": 1915.8517,
      "eval_samples_per_second": 14.817,
      "eval_steps_per_second": 7.409,
      "step": 9
    },
    {
      "epoch": 0.00014832558950151478,
      "grad_norm": 1681.9525146484375,
      "learning_rate": 0.0002,
      "loss": 95.5572,
      "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": 89372900720640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}