{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 29864,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01674256630056255,
      "grad_norm": 0.26318585872650146,
      "learning_rate": 1.6538332775359894e-06,
      "loss": 0.1468,
      "step": 500
    },
    {
      "epoch": 0.0334851326011251,
      "grad_norm": 40.848941802978516,
      "learning_rate": 3.3244057582859056e-06,
      "loss": 0.1348,
      "step": 1000
    },
    {
      "epoch": 0.05022769890168765,
      "grad_norm": 0.3210512399673462,
      "learning_rate": 4.9983260796786076e-06,
      "loss": 0.1292,
      "step": 1500
    },
    {
      "epoch": 0.0669702652022502,
      "grad_norm": 51.398277282714844,
      "learning_rate": 6.6722464010713095e-06,
      "loss": 0.1246,
      "step": 2000
    },
    {
      "epoch": 0.08371283150281275,
      "grad_norm": 1.8654736280441284,
      "learning_rate": 8.346166722464011e-06,
      "loss": 0.073,
      "step": 2500
    },
    {
      "epoch": 0.1004553978033753,
      "grad_norm": 2.204322338104248,
      "learning_rate": 9.997767607991965e-06,
      "loss": 0.0861,
      "step": 3000
    },
    {
      "epoch": 0.11719796410393785,
      "grad_norm": 0.029873741790652275,
      "learning_rate": 9.81173494065558e-06,
      "loss": 0.0626,
      "step": 3500
    },
    {
      "epoch": 0.1339405304045004,
      "grad_norm": 2.218162775039673,
      "learning_rate": 9.626074338653869e-06,
      "loss": 0.0731,
      "step": 4000
    },
    {
      "epoch": 0.15068309670506294,
      "grad_norm": 6.862820625305176,
      "learning_rate": 9.440041671317484e-06,
      "loss": 0.0756,
      "step": 4500
    },
    {
      "epoch": 0.1674256630056255,
      "grad_norm": 1.0643534660339355,
      "learning_rate": 9.2540090039811e-06,
      "loss": 0.0702,
      "step": 5000
    },
    {
      "epoch": 0.18416822930618806,
      "grad_norm": 0.14988207817077637,
      "learning_rate": 9.067976336644717e-06,
      "loss": 0.0675,
      "step": 5500
    },
    {
      "epoch": 0.2009107956067506,
      "grad_norm": 0.25116392970085144,
      "learning_rate": 8.882315734643004e-06,
      "loss": 0.0604,
      "step": 6000
    },
    {
      "epoch": 0.21765336190731316,
      "grad_norm": 0.3021365702152252,
      "learning_rate": 8.69628306730662e-06,
      "loss": 0.0515,
      "step": 6500
    },
    {
      "epoch": 0.2343959282078757,
      "grad_norm": 22.51474952697754,
      "learning_rate": 8.510250399970235e-06,
      "loss": 0.0643,
      "step": 7000
    },
    {
      "epoch": 0.2511384945084382,
      "grad_norm": 2.37544584274292,
      "learning_rate": 8.324217732633852e-06,
      "loss": 0.07,
      "step": 7500
    },
    {
      "epoch": 0.2678810608090008,
      "grad_norm": 57.23020553588867,
      "learning_rate": 8.138185065297467e-06,
      "loss": 0.0557,
      "step": 8000
    },
    {
      "epoch": 0.28462362710956335,
      "grad_norm": 0.0032292637042701244,
      "learning_rate": 7.952152397961083e-06,
      "loss": 0.0614,
      "step": 8500
    },
    {
      "epoch": 0.3013661934101259,
      "grad_norm": 5.582527160644531,
      "learning_rate": 7.766119730624698e-06,
      "loss": 0.0577,
      "step": 9000
    },
    {
      "epoch": 0.31810875971068847,
      "grad_norm": 0.04729452729225159,
      "learning_rate": 7.580087063288314e-06,
      "loss": 0.0582,
      "step": 9500
    },
    {
      "epoch": 0.334851326011251,
      "grad_norm": 2.683903217315674,
      "learning_rate": 7.394426461286602e-06,
      "loss": 0.0549,
      "step": 10000
    },
    {
      "epoch": 0.35159389231181354,
      "grad_norm": 0.9779844880104065,
      "learning_rate": 7.208393793950218e-06,
      "loss": 0.0615,
      "step": 10500
    },
    {
      "epoch": 0.3683364586123761,
      "grad_norm": 79.76528930664062,
      "learning_rate": 7.0223611266138335e-06,
      "loss": 0.0519,
      "step": 11000
    },
    {
      "epoch": 0.38507902491293866,
      "grad_norm": 0.3208529055118561,
      "learning_rate": 6.836328459277449e-06,
      "loss": 0.0591,
      "step": 11500
    },
    {
      "epoch": 0.4018215912135012,
      "grad_norm": 23.068653106689453,
      "learning_rate": 6.650295791941065e-06,
      "loss": 0.0539,
      "step": 12000
    },
    {
      "epoch": 0.41856415751406373,
      "grad_norm": 0.6496044993400574,
      "learning_rate": 6.464635189939353e-06,
      "loss": 0.0549,
      "step": 12500
    },
    {
      "epoch": 0.4353067238146263,
      "grad_norm": 38.81090545654297,
      "learning_rate": 6.2786025226029705e-06,
      "loss": 0.0543,
      "step": 13000
    },
    {
      "epoch": 0.45204929011518885,
      "grad_norm": 2.4993317127227783,
      "learning_rate": 6.092569855266585e-06,
      "loss": 0.0614,
      "step": 13500
    },
    {
      "epoch": 0.4687918564157514,
      "grad_norm": 0.5560814738273621,
      "learning_rate": 5.906537187930201e-06,
      "loss": 0.048,
      "step": 14000
    },
    {
      "epoch": 0.485534422716314,
      "grad_norm": 1.5382946729660034,
      "learning_rate": 5.720504520593817e-06,
      "loss": 0.0558,
      "step": 14500
    },
    {
      "epoch": 0.5022769890168765,
      "grad_norm": 0.026120496913790703,
      "learning_rate": 5.534471853257432e-06,
      "loss": 0.0492,
      "step": 15000
    },
    {
      "epoch": 0.519019555317439,
      "grad_norm": 1.6323872804641724,
      "learning_rate": 5.348439185921048e-06,
      "loss": 0.0633,
      "step": 15500
    },
    {
      "epoch": 0.5357621216180016,
      "grad_norm": 0.012650725431740284,
      "learning_rate": 5.162406518584664e-06,
      "loss": 0.0447,
      "step": 16000
    },
    {
      "epoch": 0.5525046879185641,
      "grad_norm": 8.42776107788086,
      "learning_rate": 4.976745916582952e-06,
      "loss": 0.043,
      "step": 16500
    },
    {
      "epoch": 0.5692472542191267,
      "grad_norm": 2.717674732208252,
      "learning_rate": 4.790713249246568e-06,
      "loss": 0.0517,
      "step": 17000
    },
    {
      "epoch": 0.5859898205196893,
      "grad_norm": 0.01320638321340084,
      "learning_rate": 4.604680581910183e-06,
      "loss": 0.0768,
      "step": 17500
    },
    {
      "epoch": 0.6027323868202518,
      "grad_norm": 68.84772491455078,
      "learning_rate": 4.418647914573799e-06,
      "loss": 0.0578,
      "step": 18000
    },
    {
      "epoch": 0.6194749531208144,
      "grad_norm": 0.05758577585220337,
      "learning_rate": 4.232987312572088e-06,
      "loss": 0.0575,
      "step": 18500
    },
    {
      "epoch": 0.6362175194213769,
      "grad_norm": 0.02908864989876747,
      "learning_rate": 4.046954645235704e-06,
      "loss": 0.0527,
      "step": 19000
    },
    {
      "epoch": 0.6529600857219394,
      "grad_norm": 5.406867027282715,
      "learning_rate": 3.86092197789932e-06,
      "loss": 0.0556,
      "step": 19500
    },
    {
      "epoch": 0.669702652022502,
      "grad_norm": 0.1083500012755394,
      "learning_rate": 3.6748893105629353e-06,
      "loss": 0.0607,
      "step": 20000
    },
    {
      "epoch": 0.6864452183230646,
      "grad_norm": 13.136815071105957,
      "learning_rate": 3.488856643226551e-06,
      "loss": 0.0608,
      "step": 20500
    },
    {
      "epoch": 0.7031877846236271,
      "grad_norm": 0.7505860328674316,
      "learning_rate": 3.3028239758901666e-06,
      "loss": 0.0691,
      "step": 21000
    },
    {
      "epoch": 0.7199303509241897,
      "grad_norm": 56.34339141845703,
      "learning_rate": 3.1167913085537823e-06,
      "loss": 0.0563,
      "step": 21500
    },
    {
      "epoch": 0.7366729172247523,
      "grad_norm": 0.267652302980423,
      "learning_rate": 2.9307586412173984e-06,
      "loss": 0.0688,
      "step": 22000
    },
    {
      "epoch": 0.7534154835253147,
      "grad_norm": 4.030105113983154,
      "learning_rate": 2.7450980392156867e-06,
      "loss": 0.0637,
      "step": 22500
    },
    {
      "epoch": 0.7701580498258773,
      "grad_norm": 1.6611367464065552,
      "learning_rate": 2.5590653718793024e-06,
      "loss": 0.0724,
      "step": 23000
    },
    {
      "epoch": 0.7869006161264399,
      "grad_norm": 65.19082641601562,
      "learning_rate": 2.3734047698775908e-06,
      "loss": 0.0759,
      "step": 23500
    },
    {
      "epoch": 0.8036431824270024,
      "grad_norm": 2.824739694595337,
      "learning_rate": 2.1873721025412064e-06,
      "loss": 0.0675,
      "step": 24000
    },
    {
      "epoch": 0.820385748727565,
      "grad_norm": 1.6871856451034546,
      "learning_rate": 2.001339435204822e-06,
      "loss": 0.1016,
      "step": 24500
    },
    {
      "epoch": 0.8371283150281275,
      "grad_norm": 73.87975311279297,
      "learning_rate": 1.8156788332031105e-06,
      "loss": 0.0995,
      "step": 25000
    },
    {
      "epoch": 0.85387088132869,
      "grad_norm": 1.2010084390640259,
      "learning_rate": 1.6296461658667261e-06,
      "loss": 0.0871,
      "step": 25500
    },
    {
      "epoch": 0.8706134476292526,
      "grad_norm": 8.91370964050293,
      "learning_rate": 1.443613498530342e-06,
      "loss": 0.0936,
      "step": 26000
    },
    {
      "epoch": 0.8873560139298151,
      "grad_norm": 8.569842338562012,
      "learning_rate": 1.2575808311939577e-06,
      "loss": 0.0927,
      "step": 26500
    },
    {
      "epoch": 0.9040985802303777,
      "grad_norm": 0.14943744242191315,
      "learning_rate": 1.0715481638575736e-06,
      "loss": 0.1108,
      "step": 27000
    },
    {
      "epoch": 0.9208411465309403,
      "grad_norm": 48.06157684326172,
      "learning_rate": 8.855154965211891e-07,
      "loss": 0.1141,
      "step": 27500
    },
    {
      "epoch": 0.9375837128315028,
      "grad_norm": 46.07848358154297,
      "learning_rate": 6.994828291848049e-07,
      "loss": 0.118,
      "step": 28000
    },
    {
      "epoch": 0.9543262791320654,
      "grad_norm": 1.0916130542755127,
      "learning_rate": 5.134501618484206e-07,
      "loss": 0.138,
      "step": 28500
    },
    {
      "epoch": 0.971068845432628,
      "grad_norm": 0.2534860074520111,
      "learning_rate": 3.277895598467091e-07,
      "loss": 0.1425,
      "step": 29000
    },
    {
      "epoch": 0.9878114117331904,
      "grad_norm": 0.08512990921735764,
      "learning_rate": 1.421289578449976e-07,
      "loss": 0.1432,
      "step": 29500
    }
  ],
  "logging_steps": 500,
  "max_steps": 29864,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}