{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10802052389954091,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0054010261949770455,
      "grad_norm": 1.4275089502334595,
      "learning_rate": 0.00016,
      "loss": 3.4877567291259766,
      "step": 10
    },
    {
      "epoch": 0.010802052389954091,
      "grad_norm": 1.4062877893447876,
      "learning_rate": 0.00019971150378651282,
      "loss": 3.177476501464844,
      "step": 20
    },
    {
      "epoch": 0.016203078584931137,
      "grad_norm": 1.4894630908966064,
      "learning_rate": 0.0001993508835196538,
      "loss": 2.949508857727051,
      "step": 30
    },
    {
      "epoch": 0.021604104779908182,
      "grad_norm": 1.1637152433395386,
      "learning_rate": 0.00019899026325279482,
      "loss": 3.2568588256835938,
      "step": 40
    },
    {
      "epoch": 0.027005130974885227,
      "grad_norm": 1.0710796117782593,
      "learning_rate": 0.00019862964298593581,
      "loss": 3.033162307739258,
      "step": 50
    },
    {
      "epoch": 0.032406157169862275,
      "grad_norm": 1.036720633506775,
      "learning_rate": 0.0001982690227190768,
      "loss": 2.9209388732910155,
      "step": 60
    },
    {
      "epoch": 0.03780718336483932,
      "grad_norm": 1.5094584226608276,
      "learning_rate": 0.00019790840245221782,
      "loss": 3.199975776672363,
      "step": 70
    },
    {
      "epoch": 0.043208209559816364,
      "grad_norm": 1.25065016746521,
      "learning_rate": 0.00019754778218535884,
      "loss": 3.1586023330688477,
      "step": 80
    },
    {
      "epoch": 0.04860923575479341,
      "grad_norm": 1.093263864517212,
      "learning_rate": 0.00019718716191849983,
      "loss": 3.1673559188842773,
      "step": 90
    },
    {
      "epoch": 0.054010261949770454,
      "grad_norm": 1.7025214433670044,
      "learning_rate": 0.00019682654165164082,
      "loss": 3.0090349197387694,
      "step": 100
    },
    {
      "epoch": 0.059411288144747505,
      "grad_norm": 1.0379327535629272,
      "learning_rate": 0.00019646592138478184,
      "loss": 3.0862411499023437,
      "step": 110
    },
    {
      "epoch": 0.06481231433972455,
      "grad_norm": 1.0767595767974854,
      "learning_rate": 0.00019610530111792285,
      "loss": 2.9345855712890625,
      "step": 120
    },
    {
      "epoch": 0.07021334053470159,
      "grad_norm": 1.2473753690719604,
      "learning_rate": 0.00019574468085106384,
      "loss": 3.168864440917969,
      "step": 130
    },
    {
      "epoch": 0.07561436672967864,
      "grad_norm": 1.1580232381820679,
      "learning_rate": 0.00019538406058420483,
      "loss": 3.0444286346435545,
      "step": 140
    },
    {
      "epoch": 0.08101539292465569,
      "grad_norm": 1.1562517881393433,
      "learning_rate": 0.00019502344031734585,
      "loss": 3.0681676864624023,
      "step": 150
    },
    {
      "epoch": 0.08641641911963273,
      "grad_norm": 1.2069370746612549,
      "learning_rate": 0.00019466282005048684,
      "loss": 3.147779846191406,
      "step": 160
    },
    {
      "epoch": 0.09181744531460978,
      "grad_norm": 1.1520271301269531,
      "learning_rate": 0.00019430219978362786,
      "loss": 3.2159664154052736,
      "step": 170
    },
    {
      "epoch": 0.09721847150958682,
      "grad_norm": 1.3290963172912598,
      "learning_rate": 0.00019394157951676885,
      "loss": 3.17901668548584,
      "step": 180
    },
    {
      "epoch": 0.10261949770456387,
      "grad_norm": 1.4537458419799805,
      "learning_rate": 0.00019358095924990984,
      "loss": 3.076709747314453,
      "step": 190
    },
    {
      "epoch": 0.10802052389954091,
      "grad_norm": 1.6899892091751099,
      "learning_rate": 0.00019322033898305085,
      "loss": 2.9362957000732424,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 5556,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7070497480949760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}