{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016300582745833164,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016300582745833165,
      "grad_norm": 1.6866501498136166e+17,
      "learning_rate": 2e-05,
      "loss": 8.6994,
      "step": 1
    },
    {
      "epoch": 0.00016300582745833165,
      "eval_loss": 9.382376670837402,
      "eval_runtime": 901.7037,
      "eval_samples_per_second": 2.865,
      "eval_steps_per_second": 1.433,
      "step": 1
    },
    {
      "epoch": 0.0003260116549166633,
      "grad_norm": Infinity,
      "learning_rate": 4e-05,
      "loss": 10.0716,
      "step": 2
    },
    {
      "epoch": 0.0004890174823749949,
      "grad_norm": 4.4766390525016146e+18,
      "learning_rate": 6e-05,
      "loss": 8.8761,
      "step": 3
    },
    {
      "epoch": 0.0004890174823749949,
      "eval_loss": 9.339409828186035,
      "eval_runtime": 903.9163,
      "eval_samples_per_second": 2.858,
      "eval_steps_per_second": 1.429,
      "step": 3
    },
    {
      "epoch": 0.0006520233098333266,
      "grad_norm": Infinity,
      "learning_rate": 8e-05,
      "loss": 7.1275,
      "step": 4
    },
    {
      "epoch": 0.0008150291372916582,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 10.6433,
      "step": 5
    },
    {
      "epoch": 0.0009780349647499898,
      "grad_norm": 1.913991874121564e+17,
      "learning_rate": 0.00012,
      "loss": 10.064,
      "step": 6
    },
    {
      "epoch": 0.0009780349647499898,
      "eval_loss": 9.447994232177734,
      "eval_runtime": 903.8354,
      "eval_samples_per_second": 2.858,
      "eval_steps_per_second": 1.429,
      "step": 6
    },
    {
      "epoch": 0.0011410407922083214,
      "grad_norm": 1.7332163570355405e+17,
      "learning_rate": 0.00014,
      "loss": 8.4746,
      "step": 7
    },
    {
      "epoch": 0.0013040466196666532,
      "grad_norm": Infinity,
      "learning_rate": 0.00016,
      "loss": 9.2175,
      "step": 8
    },
    {
      "epoch": 0.0014670524471249848,
      "grad_norm": Infinity,
      "learning_rate": 0.00018,
      "loss": 9.5814,
      "step": 9
    },
    {
      "epoch": 0.0014670524471249848,
      "eval_loss": 9.504780769348145,
      "eval_runtime": 904.1481,
      "eval_samples_per_second": 2.857,
      "eval_steps_per_second": 1.429,
      "step": 9
    },
    {
      "epoch": 0.0016300582745833164,
      "grad_norm": Infinity,
      "learning_rate": 0.0002,
      "loss": 9.763,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7377643162828800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}