{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008730193373783229,
  "eval_steps": 2,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.730193373783229e-05,
      "grad_norm": 1.6029466390609741,
      "learning_rate": 2e-05,
      "loss": 8.6163,
      "step": 1
    },
    {
      "epoch": 8.730193373783229e-05,
      "eval_loss": 8.479549407958984,
      "eval_runtime": 103.8322,
      "eval_samples_per_second": 46.45,
      "eval_steps_per_second": 23.23,
      "step": 1
    },
    {
      "epoch": 0.00017460386747566458,
      "grad_norm": 1.4574332237243652,
      "learning_rate": 4e-05,
      "loss": 8.5938,
      "step": 2
    },
    {
      "epoch": 0.00017460386747566458,
      "eval_loss": 8.479405403137207,
      "eval_runtime": 103.6916,
      "eval_samples_per_second": 46.513,
      "eval_steps_per_second": 23.261,
      "step": 2
    },
    {
      "epoch": 0.00026190580121349685,
      "grad_norm": 1.5145901441574097,
      "learning_rate": 6e-05,
      "loss": 8.2675,
      "step": 3
    },
    {
      "epoch": 0.00034920773495132916,
      "grad_norm": 2.280639410018921,
      "learning_rate": 8e-05,
      "loss": 8.7145,
      "step": 4
    },
    {
      "epoch": 0.00034920773495132916,
      "eval_loss": 8.475335121154785,
      "eval_runtime": 103.7528,
      "eval_samples_per_second": 46.485,
      "eval_steps_per_second": 23.248,
      "step": 4
    },
    {
      "epoch": 0.00043650966868916146,
      "grad_norm": 1.6258833408355713,
      "learning_rate": 0.0001,
      "loss": 8.7465,
      "step": 5
    },
    {
      "epoch": 0.0005238116024269937,
      "grad_norm": 1.7357032299041748,
      "learning_rate": 0.00012,
      "loss": 8.6569,
      "step": 6
    },
    {
      "epoch": 0.0005238116024269937,
      "eval_loss": 8.458909034729004,
      "eval_runtime": 103.6326,
      "eval_samples_per_second": 46.539,
      "eval_steps_per_second": 23.275,
      "step": 6
    },
    {
      "epoch": 0.000611113536164826,
      "grad_norm": 1.6086039543151855,
      "learning_rate": 0.00014,
      "loss": 8.5566,
      "step": 7
    },
    {
      "epoch": 0.0006984154699026583,
      "grad_norm": 1.5698775053024292,
      "learning_rate": 0.00016,
      "loss": 8.2834,
      "step": 8
    },
    {
      "epoch": 0.0006984154699026583,
      "eval_loss": 8.429530143737793,
      "eval_runtime": 103.6048,
      "eval_samples_per_second": 46.552,
      "eval_steps_per_second": 23.281,
      "step": 8
    },
    {
      "epoch": 0.0007857174036404906,
      "grad_norm": 1.3347610235214233,
      "learning_rate": 0.00018,
      "loss": 8.555,
      "step": 9
    },
    {
      "epoch": 0.0008730193373783229,
      "grad_norm": 1.6474040746688843,
      "learning_rate": 0.0002,
      "loss": 9.0077,
      "step": 10
    },
    {
      "epoch": 0.0008730193373783229,
      "eval_loss": 8.39326000213623,
      "eval_runtime": 103.6132,
      "eval_samples_per_second": 46.548,
      "eval_steps_per_second": 23.279,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2622341775360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}