{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 49.31506849315068,
  "eval_steps": 400,
  "global_step": 14400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.7123287671232876,
      "grad_norm": 2.024919271469116,
      "learning_rate": 5e-05,
      "loss": 3.8492,
      "step": 500
    },
    {
      "epoch": 3.4246575342465753,
      "grad_norm": 1.7762272357940674,
      "learning_rate": 4.6973365617433416e-05,
      "loss": 3.104,
      "step": 1000
    },
    {
      "epoch": 5.136986301369863,
      "grad_norm": 1.9453787803649902,
      "learning_rate": 4.394673123486683e-05,
      "loss": 2.7752,
      "step": 1500
    },
    {
      "epoch": 6.8493150684931505,
      "grad_norm": 1.9978324174880981,
      "learning_rate": 4.092009685230024e-05,
      "loss": 2.5478,
      "step": 2000
    },
    {
      "epoch": 8.561643835616438,
      "grad_norm": 1.8244125843048096,
      "learning_rate": 3.789346246973366e-05,
      "loss": 2.3579,
      "step": 2500
    },
    {
      "epoch": 10.273972602739725,
      "grad_norm": 2.0865862369537354,
      "learning_rate": 3.486682808716707e-05,
      "loss": 2.2151,
      "step": 3000
    },
    {
      "epoch": 11.986301369863014,
      "grad_norm": 2.022252321243286,
      "learning_rate": 3.184019370460048e-05,
      "loss": 2.0783,
      "step": 3500
    },
    {
      "epoch": 13.698630136986301,
      "grad_norm": 2.030592918395996,
      "learning_rate": 2.88135593220339e-05,
      "loss": 1.9546,
      "step": 4000
    },
    {
      "epoch": 15.41095890410959,
      "grad_norm": 2.101133346557617,
      "learning_rate": 2.5786924939467316e-05,
      "loss": 1.8636,
      "step": 4500
    },
    {
      "epoch": 17.123287671232877,
      "grad_norm": 2.0378260612487793,
      "learning_rate": 2.2760290556900726e-05,
      "loss": 1.7814,
      "step": 5000
    },
    {
      "epoch": 18.835616438356166,
      "grad_norm": 2.2219014167785645,
      "learning_rate": 1.9733656174334143e-05,
      "loss": 1.7052,
      "step": 5500
    },
    {
      "epoch": 20.54794520547945,
      "grad_norm": 2.211897373199463,
      "learning_rate": 1.6707021791767556e-05,
      "loss": 1.6337,
      "step": 6000
    },
    {
      "epoch": 22.26027397260274,
      "grad_norm": 2.0061228275299072,
      "learning_rate": 1.3680387409200971e-05,
      "loss": 1.5842,
      "step": 6500
    },
    {
      "epoch": 23.972602739726028,
      "grad_norm": 2.1824605464935303,
      "learning_rate": 1.0653753026634383e-05,
      "loss": 1.544,
      "step": 7000
    },
    {
      "epoch": 25.684931506849313,
      "grad_norm": 2.1209356784820557,
      "learning_rate": 7.627118644067798e-06,
      "loss": 1.5001,
      "step": 7500
    },
    {
      "epoch": 27.397260273972602,
      "grad_norm": 2.1307101249694824,
      "learning_rate": 4.600484261501211e-06,
      "loss": 1.4742,
      "step": 8000
    },
    {
      "epoch": 29.10958904109589,
      "grad_norm": 2.0766286849975586,
      "learning_rate": 1.5738498789346248e-06,
      "loss": 1.4553,
      "step": 8500
    },
    {
      "epoch": 30.82191780821918,
      "grad_norm": 2.4918978214263916,
      "learning_rate": 1.9858156028368796e-05,
      "loss": 1.6283,
      "step": 9000
    },
    {
      "epoch": 32.534246575342465,
      "grad_norm": 2.147444725036621,
      "learning_rate": 1.8085106382978724e-05,
      "loss": 1.5809,
      "step": 9500
    },
    {
      "epoch": 34.24657534246575,
      "grad_norm": 2.2365379333496094,
      "learning_rate": 1.6312056737588656e-05,
      "loss": 1.5219,
      "step": 10000
    },
    {
      "epoch": 35.95890410958904,
      "grad_norm": 2.2686374187469482,
      "learning_rate": 1.4539007092198581e-05,
      "loss": 1.4767,
      "step": 10500
    },
    {
      "epoch": 37.67123287671233,
      "grad_norm": 2.2740468978881836,
      "learning_rate": 1.2765957446808511e-05,
      "loss": 1.4248,
      "step": 11000
    },
    {
      "epoch": 39.38356164383562,
      "grad_norm": 2.060163736343384,
      "learning_rate": 1.0992907801418441e-05,
      "loss": 1.3853,
      "step": 11500
    },
    {
      "epoch": 41.0958904109589,
      "grad_norm": 2.2763679027557373,
      "learning_rate": 9.219858156028368e-06,
      "loss": 1.3555,
      "step": 12000
    },
    {
      "epoch": 42.80821917808219,
      "grad_norm": 2.2008297443389893,
      "learning_rate": 7.446808510638298e-06,
      "loss": 1.3242,
      "step": 12500
    },
    {
      "epoch": 44.52054794520548,
      "grad_norm": 2.5200419425964355,
      "learning_rate": 5.673758865248227e-06,
      "loss": 1.3008,
      "step": 13000
    },
    {
      "epoch": 46.23287671232877,
      "grad_norm": 2.2964625358581543,
      "learning_rate": 3.9007092198581565e-06,
      "loss": 1.2794,
      "step": 13500
    },
    {
      "epoch": 47.945205479452056,
      "grad_norm": 2.3451294898986816,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 1.2691,
      "step": 14000
    }
  ],
  "logging_steps": 500,
  "max_steps": 14600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "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": 3.0045885421584384e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}