{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00016389748212493086,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6389748212493087e-05,
      "grad_norm": 2.675468921661377,
      "learning_rate": 2e-05,
      "loss": 2.8366,
      "step": 1
    },
    {
      "epoch": 1.6389748212493087e-05,
      "eval_loss": 2.859771251678467,
      "eval_runtime": 1474.5123,
      "eval_samples_per_second": 17.423,
      "eval_steps_per_second": 8.711,
      "step": 1
    },
    {
      "epoch": 3.277949642498617e-05,
      "grad_norm": 1.655171513557434,
      "learning_rate": 4e-05,
      "loss": 2.8862,
      "step": 2
    },
    {
      "epoch": 4.9169244637479256e-05,
      "grad_norm": 1.9237943887710571,
      "learning_rate": 6e-05,
      "loss": 2.7132,
      "step": 3
    },
    {
      "epoch": 4.9169244637479256e-05,
      "eval_loss": 2.817953586578369,
      "eval_runtime": 1474.0421,
      "eval_samples_per_second": 17.428,
      "eval_steps_per_second": 8.714,
      "step": 3
    },
    {
      "epoch": 6.555899284997235e-05,
      "grad_norm": 2.498469352722168,
      "learning_rate": 8e-05,
      "loss": 2.5279,
      "step": 4
    },
    {
      "epoch": 8.194874106246543e-05,
      "grad_norm": 1.8479561805725098,
      "learning_rate": 0.0001,
      "loss": 2.6075,
      "step": 5
    },
    {
      "epoch": 9.833848927495851e-05,
      "grad_norm": 2.176384687423706,
      "learning_rate": 0.00012,
      "loss": 2.363,
      "step": 6
    },
    {
      "epoch": 9.833848927495851e-05,
      "eval_loss": 2.304943561553955,
      "eval_runtime": 1475.2692,
      "eval_samples_per_second": 17.414,
      "eval_steps_per_second": 8.707,
      "step": 6
    },
    {
      "epoch": 0.0001147282374874516,
      "grad_norm": 1.8790661096572876,
      "learning_rate": 0.00014,
      "loss": 2.5038,
      "step": 7
    },
    {
      "epoch": 0.0001311179856999447,
      "grad_norm": 2.056502342224121,
      "learning_rate": 0.00016,
      "loss": 2.1962,
      "step": 8
    },
    {
      "epoch": 0.00014750773391243778,
      "grad_norm": 1.2043896913528442,
      "learning_rate": 0.00018,
      "loss": 1.7013,
      "step": 9
    },
    {
      "epoch": 0.00014750773391243778,
      "eval_loss": 1.8729199171066284,
      "eval_runtime": 1474.8493,
      "eval_samples_per_second": 17.419,
      "eval_steps_per_second": 8.709,
      "step": 9
    },
    {
      "epoch": 0.00016389748212493086,
      "grad_norm": 1.626771092414856,
      "learning_rate": 0.0002,
      "loss": 1.9072,
      "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": 2668111702523904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}