{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005064124476179625,
  "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,
      "eval_loss": 3.332756996154785,
      "eval_runtime": 1255.489,
      "eval_samples_per_second": 6.623,
      "eval_steps_per_second": 3.312,
      "step": 0
    },
    {
      "epoch": 5.0641244761796245e-05,
      "grad_norm": 0.7450602054595947,
      "learning_rate": 0.0,
      "loss": 3.0601,
      "step": 1
    },
    {
      "epoch": 0.00010128248952359249,
      "grad_norm": 0.7262908816337585,
      "learning_rate": 2e-05,
      "loss": 3.0686,
      "step": 2
    },
    {
      "epoch": 0.00015192373428538875,
      "grad_norm": 0.6945377588272095,
      "learning_rate": 4e-05,
      "loss": 3.4784,
      "step": 3
    },
    {
      "epoch": 0.00015192373428538875,
      "eval_loss": 3.3230936527252197,
      "eval_runtime": 1245.743,
      "eval_samples_per_second": 6.675,
      "eval_steps_per_second": 3.338,
      "step": 3
    },
    {
      "epoch": 0.00020256497904718498,
      "grad_norm": 0.7639620304107666,
      "learning_rate": 6e-05,
      "loss": 3.3284,
      "step": 4
    },
    {
      "epoch": 0.00025320622380898124,
      "grad_norm": 0.7831843495368958,
      "learning_rate": 8e-05,
      "loss": 3.0446,
      "step": 5
    },
    {
      "epoch": 0.0003038474685707775,
      "grad_norm": 0.9005393981933594,
      "learning_rate": 0.0001,
      "loss": 3.03,
      "step": 6
    },
    {
      "epoch": 0.0003038474685707775,
      "eval_loss": 3.2163121700286865,
      "eval_runtime": 1246.0826,
      "eval_samples_per_second": 6.673,
      "eval_steps_per_second": 3.337,
      "step": 6
    },
    {
      "epoch": 0.0003544887133325737,
      "grad_norm": 0.8589541912078857,
      "learning_rate": 0.00012,
      "loss": 3.0754,
      "step": 7
    },
    {
      "epoch": 0.00040512995809436996,
      "grad_norm": 0.904832661151886,
      "learning_rate": 0.00014,
      "loss": 3.3662,
      "step": 8
    },
    {
      "epoch": 0.0004557712028561662,
      "grad_norm": 0.8699621558189392,
      "learning_rate": 0.00016,
      "loss": 2.9704,
      "step": 9
    },
    {
      "epoch": 0.0004557712028561662,
      "eval_loss": 2.990236520767212,
      "eval_runtime": 1246.2607,
      "eval_samples_per_second": 6.672,
      "eval_steps_per_second": 3.336,
      "step": 9
    },
    {
      "epoch": 0.0005064124476179625,
      "grad_norm": 0.7870314717292786,
      "learning_rate": 0.00018,
      "loss": 3.0758,
      "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": 2852805358387200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}