{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.31088082901554404,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010362694300518135,
      "eval_loss": 3.650270462036133,
      "eval_runtime": 1.6107,
      "eval_samples_per_second": 25.456,
      "eval_steps_per_second": 13.038,
      "step": 1
    },
    {
      "epoch": 0.031088082901554404,
      "grad_norm": 3.7749135494232178,
      "learning_rate": 6e-05,
      "loss": 3.5551,
      "step": 3
    },
    {
      "epoch": 0.06217616580310881,
      "grad_norm": 3.140277624130249,
      "learning_rate": 0.00012,
      "loss": 3.4495,
      "step": 6
    },
    {
      "epoch": 0.08290155440414508,
      "eval_loss": 3.190791368484497,
      "eval_runtime": 0.5748,
      "eval_samples_per_second": 71.33,
      "eval_steps_per_second": 36.535,
      "step": 8
    },
    {
      "epoch": 0.09326424870466321,
      "grad_norm": 1.6338378190994263,
      "learning_rate": 0.00018,
      "loss": 3.1046,
      "step": 9
    },
    {
      "epoch": 0.12435233160621761,
      "grad_norm": 1.602424144744873,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.0697,
      "step": 12
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 1.1724361181259155,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.0577,
      "step": 15
    },
    {
      "epoch": 0.16580310880829016,
      "eval_loss": 2.8723623752593994,
      "eval_runtime": 0.6538,
      "eval_samples_per_second": 62.715,
      "eval_steps_per_second": 32.122,
      "step": 16
    },
    {
      "epoch": 0.18652849740932642,
      "grad_norm": 1.022718906402588,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.818,
      "step": 18
    },
    {
      "epoch": 0.21761658031088082,
      "grad_norm": 0.9972200393676758,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.7529,
      "step": 21
    },
    {
      "epoch": 0.24870466321243523,
      "grad_norm": 1.182674527168274,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.7646,
      "step": 24
    },
    {
      "epoch": 0.24870466321243523,
      "eval_loss": 2.7139012813568115,
      "eval_runtime": 0.6506,
      "eval_samples_per_second": 63.022,
      "eval_steps_per_second": 32.279,
      "step": 24
    },
    {
      "epoch": 0.27979274611398963,
      "grad_norm": 1.1637005805969238,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.6993,
      "step": 27
    },
    {
      "epoch": 0.31088082901554404,
      "grad_norm": 1.096183180809021,
      "learning_rate": 0.0,
      "loss": 2.681,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 208256379125760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}