{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011624527753560012,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011624527753560012,
      "grad_norm": 2.1026196479797363,
      "learning_rate": 2e-05,
      "loss": 7.6317,
      "step": 1
    },
    {
      "epoch": 0.0011624527753560012,
      "eval_loss": 1.7399663925170898,
      "eval_runtime": 5.3127,
      "eval_samples_per_second": 68.327,
      "eval_steps_per_second": 34.257,
      "step": 1
    },
    {
      "epoch": 0.0023249055507120024,
      "grad_norm": 2.210211753845215,
      "learning_rate": 4e-05,
      "loss": 6.4931,
      "step": 2
    },
    {
      "epoch": 0.0034873583260680036,
      "grad_norm": 2.009269952774048,
      "learning_rate": 6e-05,
      "loss": 6.6633,
      "step": 3
    },
    {
      "epoch": 0.0034873583260680036,
      "eval_loss": 1.7391419410705566,
      "eval_runtime": 5.3047,
      "eval_samples_per_second": 68.429,
      "eval_steps_per_second": 34.309,
      "step": 3
    },
    {
      "epoch": 0.004649811101424005,
      "grad_norm": 2.629911184310913,
      "learning_rate": 8e-05,
      "loss": 7.6159,
      "step": 4
    },
    {
      "epoch": 0.005812263876780006,
      "grad_norm": 2.106574535369873,
      "learning_rate": 0.0001,
      "loss": 7.1306,
      "step": 5
    },
    {
      "epoch": 0.006974716652136007,
      "grad_norm": 2.324009656906128,
      "learning_rate": 0.00012,
      "loss": 6.7403,
      "step": 6
    },
    {
      "epoch": 0.006974716652136007,
      "eval_loss": 1.7045127153396606,
      "eval_runtime": 5.4172,
      "eval_samples_per_second": 67.009,
      "eval_steps_per_second": 33.597,
      "step": 6
    },
    {
      "epoch": 0.008137169427492008,
      "grad_norm": 2.230163335800171,
      "learning_rate": 0.00014,
      "loss": 6.9837,
      "step": 7
    },
    {
      "epoch": 0.00929962220284801,
      "grad_norm": 2.328561544418335,
      "learning_rate": 0.00016,
      "loss": 6.8656,
      "step": 8
    },
    {
      "epoch": 0.010462074978204011,
      "grad_norm": 2.0170645713806152,
      "learning_rate": 0.00018,
      "loss": 6.773,
      "step": 9
    },
    {
      "epoch": 0.010462074978204011,
      "eval_loss": 1.6357529163360596,
      "eval_runtime": 5.6102,
      "eval_samples_per_second": 64.704,
      "eval_steps_per_second": 32.441,
      "step": 9
    },
    {
      "epoch": 0.011624527753560012,
      "grad_norm": 2.4245104789733887,
      "learning_rate": 0.0002,
      "loss": 6.607,
      "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": 105097514188800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}