{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 4,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04819277108433735,
      "grad_norm": 0.2415952831506729,
      "learning_rate": 0.0,
      "loss": 1.3147,
      "step": 1
    },
    {
      "epoch": 0.0963855421686747,
      "grad_norm": 0.22961878776550293,
      "learning_rate": 5e-05,
      "loss": 1.2904,
      "step": 2
    },
    {
      "epoch": 0.14457831325301204,
      "grad_norm": 0.24637073278427124,
      "learning_rate": 0.0001,
      "loss": 1.2993,
      "step": 3
    },
    {
      "epoch": 0.1927710843373494,
      "grad_norm": 0.296914279460907,
      "learning_rate": 9.938625865312251e-05,
      "loss": 1.2838,
      "step": 4
    },
    {
      "epoch": 0.24096385542168675,
      "grad_norm": 0.5144539475440979,
      "learning_rate": 9.756177587652856e-05,
      "loss": 1.3135,
      "step": 5
    },
    {
      "epoch": 0.24096385542168675,
      "eval_loss": 1.201416015625,
      "eval_runtime": 0.7986,
      "eval_samples_per_second": 2.504,
      "eval_steps_per_second": 1.252,
      "step": 5
    },
    {
      "epoch": 0.2891566265060241,
      "grad_norm": 0.39435362815856934,
      "learning_rate": 9.4576318804292e-05,
      "loss": 1.2159,
      "step": 6
    },
    {
      "epoch": 0.3373493975903614,
      "grad_norm": 0.5370274782180786,
      "learning_rate": 9.051132292283771e-05,
      "loss": 1.1807,
      "step": 7
    },
    {
      "epoch": 0.3855421686746988,
      "grad_norm": 0.4366680383682251,
      "learning_rate": 8.547767072315835e-05,
      "loss": 1.1483,
      "step": 8
    },
    {
      "epoch": 0.43373493975903615,
      "grad_norm": 0.39267539978027344,
      "learning_rate": 7.961266711550922e-05,
      "loss": 1.1533,
      "step": 9
    },
    {
      "epoch": 0.43373493975903615,
      "eval_loss": 1.095703125,
      "eval_runtime": 0.768,
      "eval_samples_per_second": 2.604,
      "eval_steps_per_second": 1.302,
      "step": 9
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 0.4050292670726776,
      "learning_rate": 7.307629410938363e-05,
      "loss": 1.1178,
      "step": 10
    },
    {
      "epoch": 0.5301204819277109,
      "grad_norm": 0.3959778845310211,
      "learning_rate": 6.604684692133597e-05,
      "loss": 1.0914,
      "step": 11
    },
    {
      "epoch": 0.5783132530120482,
      "grad_norm": 0.399052232503891,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 1.0811,
      "step": 12
    },
    {
      "epoch": 0.6265060240963856,
      "grad_norm": 0.37912508845329285,
      "learning_rate": 5.128392945374505e-05,
      "loss": 1.0525,
      "step": 13
    },
    {
      "epoch": 0.6265060240963856,
      "eval_loss": 1.0302734375,
      "eval_runtime": 0.7707,
      "eval_samples_per_second": 2.595,
      "eval_steps_per_second": 1.298,
      "step": 13
    },
    {
      "epoch": 0.6746987951807228,
      "grad_norm": 0.3741072416305542,
      "learning_rate": 4.395315307866405e-05,
      "loss": 1.0322,
      "step": 14
    },
    {
      "epoch": 0.7228915662650602,
      "grad_norm": 0.37119606137275696,
      "learning_rate": 3.692370589061639e-05,
      "loss": 1.0183,
      "step": 15
    },
    {
      "epoch": 0.7710843373493976,
      "grad_norm": 0.3511562645435333,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 1.0051,
      "step": 16
    },
    {
      "epoch": 0.8192771084337349,
      "grad_norm": 0.3403362035751343,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 1.0125,
      "step": 17
    },
    {
      "epoch": 0.8192771084337349,
      "eval_loss": 0.99462890625,
      "eval_runtime": 0.7715,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 1.296,
      "step": 17
    },
    {
      "epoch": 0.8674698795180723,
      "grad_norm": 0.32571786642074585,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 0.9865,
      "step": 18
    },
    {
      "epoch": 0.9156626506024096,
      "grad_norm": 0.31077131628990173,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 0.9647,
      "step": 19
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 0.327077716588974,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 0.9882,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3131638765335083,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 0.9779,
      "step": 21
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.981689453125,
      "eval_runtime": 0.7686,
      "eval_samples_per_second": 2.602,
      "eval_steps_per_second": 1.301,
      "step": 21
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 21,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.825118173154771e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}