{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 9307,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05372300419039433,
      "grad_norm": 2.991044759750366,
      "learning_rate": 4.7313849790480286e-05,
      "loss": 1.8861,
      "step": 500
    },
    {
      "epoch": 0.10744600838078866,
      "grad_norm": 5.196695804595947,
      "learning_rate": 4.462769958096057e-05,
      "loss": 1.7948,
      "step": 1000
    },
    {
      "epoch": 0.161169012571183,
      "grad_norm": 3.814988136291504,
      "learning_rate": 4.194154937144085e-05,
      "loss": 1.7804,
      "step": 1500
    },
    {
      "epoch": 0.21489201676157732,
      "grad_norm": 2.7339048385620117,
      "learning_rate": 3.9255399161921137e-05,
      "loss": 1.747,
      "step": 2000
    },
    {
      "epoch": 0.26861502095197165,
      "grad_norm": 3.035710096359253,
      "learning_rate": 3.656924895240142e-05,
      "loss": 1.721,
      "step": 2500
    },
    {
      "epoch": 0.322338025142366,
      "grad_norm": 2.720536708831787,
      "learning_rate": 3.3883098742881704e-05,
      "loss": 1.7191,
      "step": 3000
    },
    {
      "epoch": 0.3760610293327603,
      "grad_norm": 3.523932695388794,
      "learning_rate": 3.119694853336199e-05,
      "loss": 1.7057,
      "step": 3500
    },
    {
      "epoch": 0.42978403352315464,
      "grad_norm": 2.8171215057373047,
      "learning_rate": 2.851079832384227e-05,
      "loss": 1.7023,
      "step": 4000
    },
    {
      "epoch": 0.4835070377135489,
      "grad_norm": 3.2410666942596436,
      "learning_rate": 2.5824648114322554e-05,
      "loss": 1.6839,
      "step": 4500
    },
    {
      "epoch": 0.5372300419039433,
      "grad_norm": 2.8419201374053955,
      "learning_rate": 2.3138497904802838e-05,
      "loss": 1.6678,
      "step": 5000
    },
    {
      "epoch": 0.5909530460943376,
      "grad_norm": 3.81278657913208,
      "learning_rate": 2.045234769528312e-05,
      "loss": 1.6508,
      "step": 5500
    },
    {
      "epoch": 0.644676050284732,
      "grad_norm": 3.6869781017303467,
      "learning_rate": 1.7766197485763405e-05,
      "loss": 1.6397,
      "step": 6000
    },
    {
      "epoch": 0.6983990544751263,
      "grad_norm": 3.0194380283355713,
      "learning_rate": 1.5080047276243688e-05,
      "loss": 1.6355,
      "step": 6500
    },
    {
      "epoch": 0.7521220586655206,
      "grad_norm": 3.7461318969726562,
      "learning_rate": 1.2393897066723972e-05,
      "loss": 1.6324,
      "step": 7000
    },
    {
      "epoch": 0.805845062855915,
      "grad_norm": 2.7630088329315186,
      "learning_rate": 9.707746857204256e-06,
      "loss": 1.6115,
      "step": 7500
    },
    {
      "epoch": 0.8595680670463093,
      "grad_norm": 3.0207743644714355,
      "learning_rate": 7.021596647684539e-06,
      "loss": 1.6415,
      "step": 8000
    },
    {
      "epoch": 0.9132910712367036,
      "grad_norm": 2.8768997192382812,
      "learning_rate": 4.335446438164823e-06,
      "loss": 1.6103,
      "step": 8500
    },
    {
      "epoch": 0.9670140754270978,
      "grad_norm": 2.9209845066070557,
      "learning_rate": 1.6492962286451057e-06,
      "loss": 1.6273,
      "step": 9000
    }
  ],
  "logging_steps": 500,
  "max_steps": 9307,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5047449588596736.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}