{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.982857142857143,
  "eval_steps": 500,
  "global_step": 215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.14607588946819305,
      "learning_rate": 2.272727272727273e-05,
      "loss": 0.0505,
      "step": 10
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.1369447410106659,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.0136,
      "step": 20
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.11242067813873291,
      "learning_rate": 4.9788329024834144e-05,
      "loss": 0.0118,
      "step": 30
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.05123613774776459,
      "learning_rate": 4.893455513052003e-05,
      "loss": 0.0094,
      "step": 40
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.06896992027759552,
      "learning_rate": 4.7448003278586086e-05,
      "loss": 0.0071,
      "step": 50
    },
    {
      "epoch": 1.3885714285714286,
      "grad_norm": 0.46913379430770874,
      "learning_rate": 4.536797469020116e-05,
      "loss": 0.0061,
      "step": 60
    },
    {
      "epoch": 1.617142857142857,
      "grad_norm": 0.10468105971813202,
      "learning_rate": 4.274946082999753e-05,
      "loss": 0.0064,
      "step": 70
    },
    {
      "epoch": 1.8457142857142856,
      "grad_norm": 0.06397916376590729,
      "learning_rate": 3.9661689550484805e-05,
      "loss": 0.0065,
      "step": 80
    },
    {
      "epoch": 2.0914285714285716,
      "grad_norm": 0.0648517832159996,
      "learning_rate": 3.6186294857107936e-05,
      "loss": 0.0061,
      "step": 90
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.07107104361057281,
      "learning_rate": 3.241515868140921e-05,
      "loss": 0.0039,
      "step": 100
    },
    {
      "epoch": 2.5485714285714285,
      "grad_norm": 0.21339790523052216,
      "learning_rate": 2.844798172115185e-05,
      "loss": 0.0032,
      "step": 110
    },
    {
      "epoch": 2.777142857142857,
      "grad_norm": 0.05857868865132332,
      "learning_rate": 2.438964756914712e-05,
      "loss": 0.0033,
      "step": 120
    },
    {
      "epoch": 3.0228571428571427,
      "grad_norm": 0.1693907380104065,
      "learning_rate": 2.034744981752741e-05,
      "loss": 0.004,
      "step": 130
    },
    {
      "epoch": 3.2514285714285713,
      "grad_norm": 0.020911961793899536,
      "learning_rate": 1.642825544684101e-05,
      "loss": 0.0015,
      "step": 140
    },
    {
      "epoch": 3.48,
      "grad_norm": 0.04083988070487976,
      "learning_rate": 1.2735679493836009e-05,
      "loss": 0.0009,
      "step": 150
    },
    {
      "epoch": 3.7085714285714286,
      "grad_norm": 0.026034992188215256,
      "learning_rate": 9.367345693616624e-06,
      "loss": 0.001,
      "step": 160
    },
    {
      "epoch": 3.9371428571428573,
      "grad_norm": 0.07884740084409714,
      "learning_rate": 6.412305518878342e-06,
      "loss": 0.0008,
      "step": 170
    },
    {
      "epoch": 4.182857142857143,
      "grad_norm": 0.015410957857966423,
      "learning_rate": 3.948683851251878e-06,
      "loss": 0.0005,
      "step": 180
    },
    {
      "epoch": 4.411428571428571,
      "grad_norm": 0.01501483004540205,
      "learning_rate": 2.041613528121822e-06,
      "loss": 0.0002,
      "step": 190
    },
    {
      "epoch": 4.64,
      "grad_norm": 0.13119111955165863,
      "learning_rate": 7.415133710424793e-07,
      "loss": 0.0002,
      "step": 200
    },
    {
      "epoch": 4.868571428571428,
      "grad_norm": 0.01860298588871956,
      "learning_rate": 8.275522096146405e-08,
      "loss": 0.0002,
      "step": 210
    },
    {
      "epoch": 4.982857142857143,
      "step": 215,
      "total_flos": 9.788115420905472e+16,
      "train_loss": 0.006386435382761234,
      "train_runtime": 2535.9671,
      "train_samples_per_second": 0.69,
      "train_steps_per_second": 0.085
    }
  ],
  "logging_steps": 10,
  "max_steps": 215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.788115420905472e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}