{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016936521915859358,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.774608766343743e-05,
      "grad_norm": 0.8233054280281067,
      "learning_rate": 1e-05,
      "loss": 0.1314,
      "step": 1
    },
    {
      "epoch": 6.774608766343743e-05,
      "eval_loss": 0.2796812355518341,
      "eval_runtime": 665.8955,
      "eval_samples_per_second": 9.335,
      "eval_steps_per_second": 4.667,
      "step": 1
    },
    {
      "epoch": 0.00013549217532687487,
      "grad_norm": 0.8228352069854736,
      "learning_rate": 2e-05,
      "loss": 0.1639,
      "step": 2
    },
    {
      "epoch": 0.00020323826299031232,
      "grad_norm": 0.874422550201416,
      "learning_rate": 3e-05,
      "loss": 0.3309,
      "step": 3
    },
    {
      "epoch": 0.00027098435065374974,
      "grad_norm": 0.7818086743354797,
      "learning_rate": 4e-05,
      "loss": 0.2912,
      "step": 4
    },
    {
      "epoch": 0.00033873043831718716,
      "grad_norm": 1.3595991134643555,
      "learning_rate": 5e-05,
      "loss": 0.2264,
      "step": 5
    },
    {
      "epoch": 0.00033873043831718716,
      "eval_loss": 0.2366383820772171,
      "eval_runtime": 666.6637,
      "eval_samples_per_second": 9.324,
      "eval_steps_per_second": 4.662,
      "step": 5
    },
    {
      "epoch": 0.00040647652598062463,
      "grad_norm": 0.7172532677650452,
      "learning_rate": 6e-05,
      "loss": 0.2212,
      "step": 6
    },
    {
      "epoch": 0.00047422261364406205,
      "grad_norm": 0.5402056574821472,
      "learning_rate": 7e-05,
      "loss": 0.1591,
      "step": 7
    },
    {
      "epoch": 0.0005419687013074995,
      "grad_norm": 0.36438921093940735,
      "learning_rate": 8e-05,
      "loss": 0.1035,
      "step": 8
    },
    {
      "epoch": 0.0006097147889709369,
      "grad_norm": 0.3213193416595459,
      "learning_rate": 9e-05,
      "loss": 0.0886,
      "step": 9
    },
    {
      "epoch": 0.0006774608766343743,
      "grad_norm": 0.20761890709400177,
      "learning_rate": 0.0001,
      "loss": 0.0519,
      "step": 10
    },
    {
      "epoch": 0.0006774608766343743,
      "eval_loss": 0.07342575490474701,
      "eval_runtime": 665.7454,
      "eval_samples_per_second": 9.337,
      "eval_steps_per_second": 4.668,
      "step": 10
    },
    {
      "epoch": 0.0007452069642978118,
      "grad_norm": 0.24599295854568481,
      "learning_rate": 9.98458666866564e-05,
      "loss": 0.0342,
      "step": 11
    },
    {
      "epoch": 0.0008129530519612493,
      "grad_norm": 0.7074724435806274,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0683,
      "step": 12
    },
    {
      "epoch": 0.0008806991396246867,
      "grad_norm": 0.38543498516082764,
      "learning_rate": 9.861849601988383e-05,
      "loss": 0.043,
      "step": 13
    },
    {
      "epoch": 0.0009484452272881241,
      "grad_norm": 1.034214973449707,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.046,
      "step": 14
    },
    {
      "epoch": 0.0010161913149515616,
      "grad_norm": 0.3483338952064514,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0148,
      "step": 15
    },
    {
      "epoch": 0.0010161913149515616,
      "eval_loss": 0.023688077926635742,
      "eval_runtime": 666.0576,
      "eval_samples_per_second": 9.333,
      "eval_steps_per_second": 4.666,
      "step": 15
    },
    {
      "epoch": 0.001083937402614999,
      "grad_norm": 0.6300506591796875,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.021,
      "step": 16
    },
    {
      "epoch": 0.0011516834902784365,
      "grad_norm": 0.17888888716697693,
      "learning_rate": 9.263200821770461e-05,
      "loss": 0.014,
      "step": 17
    },
    {
      "epoch": 0.0012194295779418738,
      "grad_norm": 0.2301134169101715,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0147,
      "step": 18
    },
    {
      "epoch": 0.0012871756656053113,
      "grad_norm": 0.09758873283863068,
      "learning_rate": 8.802029828000156e-05,
      "loss": 0.0031,
      "step": 19
    },
    {
      "epoch": 0.0013549217532687486,
      "grad_norm": 0.2426326721906662,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0061,
      "step": 20
    },
    {
      "epoch": 0.0013549217532687486,
      "eval_loss": 0.012212304398417473,
      "eval_runtime": 665.6147,
      "eval_samples_per_second": 9.339,
      "eval_steps_per_second": 4.669,
      "step": 20
    },
    {
      "epoch": 0.0014226678409321862,
      "grad_norm": 0.05613824352622032,
      "learning_rate": 8.247240241650918e-05,
      "loss": 0.0015,
      "step": 21
    },
    {
      "epoch": 0.0014904139285956237,
      "grad_norm": 0.4901060163974762,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0078,
      "step": 22
    },
    {
      "epoch": 0.001558160016259061,
      "grad_norm": 0.13020113110542297,
      "learning_rate": 7.612492823579745e-05,
      "loss": 0.0012,
      "step": 23
    },
    {
      "epoch": 0.0016259061039224985,
      "grad_norm": 0.11555192619562149,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0016,
      "step": 24
    },
    {
      "epoch": 0.0016936521915859358,
      "grad_norm": 0.016919150948524475,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0008,
      "step": 25
    },
    {
      "epoch": 0.0016936521915859358,
      "eval_loss": 0.011942427605390549,
      "eval_runtime": 665.8139,
      "eval_samples_per_second": 9.336,
      "eval_steps_per_second": 4.668,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.86502613041152e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}