{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7912484717522958,
  "eval_steps": 7000,
  "global_step": 63000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19902760797247732,
      "grad_norm": 0.012659882195293903,
      "learning_rate": 9.94314143567875e-06,
      "loss": 0.0072,
      "step": 7000
    },
    {
      "epoch": 0.19902760797247732,
      "eval_loss": 0.0020498675294220448,
      "eval_runtime": 428.2581,
      "eval_samples_per_second": 164.249,
      "eval_steps_per_second": 20.532,
      "step": 7000
    },
    {
      "epoch": 0.39805521594495463,
      "grad_norm": 0.000786342192441225,
      "learning_rate": 8.900911431595243e-06,
      "loss": 0.0019,
      "step": 14000
    },
    {
      "epoch": 0.39805521594495463,
      "eval_loss": 0.0020361661445349455,
      "eval_runtime": 426.3268,
      "eval_samples_per_second": 164.993,
      "eval_steps_per_second": 20.625,
      "step": 14000
    },
    {
      "epoch": 0.597082823917432,
      "grad_norm": 0.7821819186210632,
      "learning_rate": 7.795978327831047e-06,
      "loss": 0.0034,
      "step": 21000
    },
    {
      "epoch": 0.597082823917432,
      "eval_loss": 0.0016205289866775274,
      "eval_runtime": 427.1096,
      "eval_samples_per_second": 164.691,
      "eval_steps_per_second": 20.587,
      "step": 21000
    },
    {
      "epoch": 0.7961104318899093,
      "grad_norm": 0.000917082536034286,
      "learning_rate": 6.69025542199125e-06,
      "loss": 0.001,
      "step": 28000
    },
    {
      "epoch": 0.7961104318899093,
      "eval_loss": 0.0012641858775168657,
      "eval_runtime": 431.2051,
      "eval_samples_per_second": 163.127,
      "eval_steps_per_second": 20.392,
      "step": 28000
    },
    {
      "epoch": 0.9951380398623866,
      "grad_norm": 0.00031811260851100087,
      "learning_rate": 5.585006397396813e-06,
      "loss": 0.0012,
      "step": 35000
    },
    {
      "epoch": 0.9951380398623866,
      "eval_loss": 0.001008204068057239,
      "eval_runtime": 429.1103,
      "eval_samples_per_second": 163.923,
      "eval_steps_per_second": 20.491,
      "step": 35000
    },
    {
      "epoch": 1.194165647834864,
      "grad_norm": 0.0007407604134641588,
      "learning_rate": 4.479441451972137e-06,
      "loss": 0.0009,
      "step": 42000
    },
    {
      "epoch": 1.194165647834864,
      "eval_loss": 0.0008274485589936376,
      "eval_runtime": 430.5634,
      "eval_samples_per_second": 163.37,
      "eval_steps_per_second": 20.422,
      "step": 42000
    },
    {
      "epoch": 1.3931932558073412,
      "grad_norm": 0.001614529057405889,
      "learning_rate": 3.3740344669625798e-06,
      "loss": 0.0005,
      "step": 49000
    },
    {
      "epoch": 1.3931932558073412,
      "eval_loss": 0.0008763344376347959,
      "eval_runtime": 432.4373,
      "eval_samples_per_second": 162.662,
      "eval_steps_per_second": 20.334,
      "step": 49000
    },
    {
      "epoch": 1.5922208637798185,
      "grad_norm": 0.00013046746607869864,
      "learning_rate": 2.2687854423681427e-06,
      "loss": 0.0004,
      "step": 56000
    },
    {
      "epoch": 1.5922208637798185,
      "eval_loss": 0.0007292362279258668,
      "eval_runtime": 427.6302,
      "eval_samples_per_second": 164.49,
      "eval_steps_per_second": 20.562,
      "step": 56000
    },
    {
      "epoch": 1.7912484717522958,
      "grad_norm": 0.00014433814794756472,
      "learning_rate": 1.163536417773706e-06,
      "loss": 0.0003,
      "step": 63000
    },
    {
      "epoch": 1.7912484717522958,
      "eval_loss": 0.0007480237982235849,
      "eval_runtime": 429.05,
      "eval_samples_per_second": 163.946,
      "eval_steps_per_second": 20.494,
      "step": 63000
    }
  ],
  "logging_steps": 7000,
  "max_steps": 70342,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 7000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}