{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 2721,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11025358324145534,
      "grad_norm": 0.8042088747024536,
      "learning_rate": 4.816244027930908e-05,
      "loss": 5.8614,
      "step": 100
    },
    {
      "epoch": 0.2205071664829107,
      "grad_norm": 0.7716182470321655,
      "learning_rate": 4.6324880558618154e-05,
      "loss": 4.914,
      "step": 200
    },
    {
      "epoch": 0.33076074972436603,
      "grad_norm": 0.7360222935676575,
      "learning_rate": 4.448732083792723e-05,
      "loss": 4.8208,
      "step": 300
    },
    {
      "epoch": 0.4410143329658214,
      "grad_norm": 0.6253624558448792,
      "learning_rate": 4.264976111723631e-05,
      "loss": 4.7569,
      "step": 400
    },
    {
      "epoch": 0.5512679162072768,
      "grad_norm": 0.8106631636619568,
      "learning_rate": 4.081220139654539e-05,
      "loss": 4.7186,
      "step": 500
    },
    {
      "epoch": 0.6615214994487321,
      "grad_norm": 0.7546982765197754,
      "learning_rate": 3.897464167585447e-05,
      "loss": 4.7019,
      "step": 600
    },
    {
      "epoch": 0.7717750826901875,
      "grad_norm": 0.6954119205474854,
      "learning_rate": 3.713708195516354e-05,
      "loss": 4.6666,
      "step": 700
    },
    {
      "epoch": 0.8820286659316428,
      "grad_norm": 0.8203008770942688,
      "learning_rate": 3.529952223447262e-05,
      "loss": 4.6249,
      "step": 800
    },
    {
      "epoch": 0.9922822491730982,
      "grad_norm": 0.6401004791259766,
      "learning_rate": 3.34619625137817e-05,
      "loss": 4.6244,
      "step": 900
    },
    {
      "epoch": 1.1025358324145536,
      "grad_norm": 0.7980089783668518,
      "learning_rate": 3.162440279309078e-05,
      "loss": 4.5987,
      "step": 1000
    },
    {
      "epoch": 1.2127894156560088,
      "grad_norm": 0.6513141393661499,
      "learning_rate": 2.9786843072399855e-05,
      "loss": 4.5563,
      "step": 1100
    },
    {
      "epoch": 1.3230429988974641,
      "grad_norm": 0.7528166770935059,
      "learning_rate": 2.7949283351708934e-05,
      "loss": 4.5834,
      "step": 1200
    },
    {
      "epoch": 1.4332965821389196,
      "grad_norm": 0.8176023960113525,
      "learning_rate": 2.611172363101801e-05,
      "loss": 4.5594,
      "step": 1300
    },
    {
      "epoch": 1.543550165380375,
      "grad_norm": 0.6479560732841492,
      "learning_rate": 2.4274163910327085e-05,
      "loss": 4.5616,
      "step": 1400
    },
    {
      "epoch": 1.6538037486218302,
      "grad_norm": 0.6746203899383545,
      "learning_rate": 2.2436604189636164e-05,
      "loss": 4.5177,
      "step": 1500
    },
    {
      "epoch": 1.7640573318632855,
      "grad_norm": 0.6707162857055664,
      "learning_rate": 2.059904446894524e-05,
      "loss": 4.5275,
      "step": 1600
    },
    {
      "epoch": 1.8743109151047408,
      "grad_norm": 0.6458820700645447,
      "learning_rate": 1.876148474825432e-05,
      "loss": 4.5453,
      "step": 1700
    },
    {
      "epoch": 1.9845644983461963,
      "grad_norm": 0.6533669829368591,
      "learning_rate": 1.6923925027563398e-05,
      "loss": 4.5206,
      "step": 1800
    },
    {
      "epoch": 2.0948180815876514,
      "grad_norm": 0.7627405524253845,
      "learning_rate": 1.5086365306872474e-05,
      "loss": 4.5118,
      "step": 1900
    },
    {
      "epoch": 2.205071664829107,
      "grad_norm": 0.7460177540779114,
      "learning_rate": 1.3248805586181551e-05,
      "loss": 4.4961,
      "step": 2000
    },
    {
      "epoch": 2.3153252480705624,
      "grad_norm": 0.6778430938720703,
      "learning_rate": 1.1411245865490629e-05,
      "loss": 4.4962,
      "step": 2100
    },
    {
      "epoch": 2.4255788313120177,
      "grad_norm": 0.6369034647941589,
      "learning_rate": 9.573686144799706e-06,
      "loss": 4.4971,
      "step": 2200
    },
    {
      "epoch": 2.535832414553473,
      "grad_norm": 0.6314408779144287,
      "learning_rate": 7.736126424108783e-06,
      "loss": 4.5085,
      "step": 2300
    },
    {
      "epoch": 2.6460859977949283,
      "grad_norm": 0.6529719233512878,
      "learning_rate": 5.8985667034178614e-06,
      "loss": 4.4746,
      "step": 2400
    },
    {
      "epoch": 2.7563395810363835,
      "grad_norm": 0.6391235589981079,
      "learning_rate": 4.061006982726939e-06,
      "loss": 4.4794,
      "step": 2500
    },
    {
      "epoch": 2.8665931642778393,
      "grad_norm": 0.8441604971885681,
      "learning_rate": 2.223447262036016e-06,
      "loss": 4.4858,
      "step": 2600
    },
    {
      "epoch": 2.9768467475192946,
      "grad_norm": 0.644396960735321,
      "learning_rate": 3.858875413450937e-07,
      "loss": 4.5054,
      "step": 2700
    }
  ],
  "logging_steps": 100,
  "max_steps": 2721,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1472045103710208.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}