{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.042417815482502653,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0042417815482502655,
      "grad_norm": 26.52564811706543,
      "learning_rate": 2e-05,
      "loss": 13.1837,
      "step": 1
    },
    {
      "epoch": 0.0042417815482502655,
      "eval_loss": 2.862527370452881,
      "eval_runtime": 7.3126,
      "eval_samples_per_second": 13.675,
      "eval_steps_per_second": 6.837,
      "step": 1
    },
    {
      "epoch": 0.008483563096500531,
      "grad_norm": 25.08441734313965,
      "learning_rate": 4e-05,
      "loss": 12.6117,
      "step": 2
    },
    {
      "epoch": 0.012725344644750796,
      "grad_norm": 24.540241241455078,
      "learning_rate": 6e-05,
      "loss": 12.313,
      "step": 3
    },
    {
      "epoch": 0.012725344644750796,
      "eval_loss": 2.8124911785125732,
      "eval_runtime": 7.3197,
      "eval_samples_per_second": 13.662,
      "eval_steps_per_second": 6.831,
      "step": 3
    },
    {
      "epoch": 0.016967126193001062,
      "grad_norm": 25.230684280395508,
      "learning_rate": 8e-05,
      "loss": 11.8793,
      "step": 4
    },
    {
      "epoch": 0.021208907741251327,
      "grad_norm": 27.78314971923828,
      "learning_rate": 0.0001,
      "loss": 11.4658,
      "step": 5
    },
    {
      "epoch": 0.02545068928950159,
      "grad_norm": 25.26974868774414,
      "learning_rate": 0.00012,
      "loss": 8.6117,
      "step": 6
    },
    {
      "epoch": 0.02545068928950159,
      "eval_loss": 2.2034640312194824,
      "eval_runtime": 7.2958,
      "eval_samples_per_second": 13.707,
      "eval_steps_per_second": 6.853,
      "step": 6
    },
    {
      "epoch": 0.029692470837751856,
      "grad_norm": 31.234804153442383,
      "learning_rate": 0.00014,
      "loss": 7.8261,
      "step": 7
    },
    {
      "epoch": 0.033934252386002124,
      "grad_norm": 18.909399032592773,
      "learning_rate": 0.00016,
      "loss": 4.5187,
      "step": 8
    },
    {
      "epoch": 0.03817603393425239,
      "grad_norm": 29.047086715698242,
      "learning_rate": 0.00018,
      "loss": 6.0829,
      "step": 9
    },
    {
      "epoch": 0.03817603393425239,
      "eval_loss": 1.4232113361358643,
      "eval_runtime": 7.33,
      "eval_samples_per_second": 13.643,
      "eval_steps_per_second": 6.821,
      "step": 9
    },
    {
      "epoch": 0.042417815482502653,
      "grad_norm": 17.52285385131836,
      "learning_rate": 0.0002,
      "loss": 4.6828,
      "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": 1796486530596864.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}