{
  "best_global_step": 500,
  "best_metric": 6.749890599166974e-05,
  "best_model_checkpoint": null,
  "epoch": 150.0,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 25.0,
      "grad_norm": 0.8259572982788086,
      "learning_rate": 9.900000000000002e-06,
      "loss": 0.439,
      "step": 100
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.04174989461898804,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 0.005,
      "step": 200
    },
    {
      "epoch": 75.0,
      "grad_norm": 0.015752894803881645,
      "learning_rate": 2.9900000000000002e-05,
      "loss": 0.0009,
      "step": 300
    },
    {
      "epoch": 100.0,
      "grad_norm": 0.08130943775177002,
      "learning_rate": 3.99e-05,
      "loss": 0.0047,
      "step": 400
    },
    {
      "epoch": 125.0,
      "grad_norm": 0.02647593431174755,
      "learning_rate": 4.99e-05,
      "loss": 0.0004,
      "step": 500
    },
    {
      "epoch": 125.0,
      "eval_loss": 6.749890599166974e-05,
      "eval_runtime": 0.0206,
      "eval_samples_per_second": 48.489,
      "eval_steps_per_second": 48.489,
      "step": 500
    },
    {
      "epoch": 150.0,
      "grad_norm": 0.00916244089603424,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.0123,
      "step": 600
    }
  ],
  "logging_steps": 100,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 150,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 157627396915200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}