{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 345,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08714596949891068,
      "grad_norm": 5.177986166517991,
      "learning_rate": 2.571428571428571e-06,
      "loss": 0.6153196334838867,
      "step": 10
    },
    {
      "epoch": 0.17429193899782136,
      "grad_norm": 1.44175757217302,
      "learning_rate": 5.428571428571429e-06,
      "loss": 0.28919568061828616,
      "step": 20
    },
    {
      "epoch": 0.26143790849673204,
      "grad_norm": 0.9165793261415883,
      "learning_rate": 8.285714285714287e-06,
      "loss": 0.17522474527359008,
      "step": 30
    },
    {
      "epoch": 0.3485838779956427,
      "grad_norm": 0.6521905966085462,
      "learning_rate": 9.995892506564461e-06,
      "loss": 0.14669673442840575,
      "step": 40
    },
    {
      "epoch": 0.4357298474945534,
      "grad_norm": 0.607127669832236,
      "learning_rate": 9.949760673863846e-06,
      "loss": 0.12744725942611695,
      "step": 50
    },
    {
      "epoch": 0.5228758169934641,
      "grad_norm": 0.5498782876340255,
      "learning_rate": 9.85283759855301e-06,
      "loss": 0.11766195297241211,
      "step": 60
    },
    {
      "epoch": 0.6100217864923747,
      "grad_norm": 0.5918131618600547,
      "learning_rate": 9.706117842542517e-06,
      "loss": 0.10788841247558593,
      "step": 70
    },
    {
      "epoch": 0.6971677559912854,
      "grad_norm": 0.4439997345152047,
      "learning_rate": 9.511106949072588e-06,
      "loss": 0.09764145016670227,
      "step": 80
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.5075520825167553,
      "learning_rate": 9.26980599380213e-06,
      "loss": 0.10603783130645753,
      "step": 90
    },
    {
      "epoch": 0.8714596949891068,
      "grad_norm": 0.5140097183992045,
      "learning_rate": 8.984691051064576e-06,
      "loss": 0.09546730518341065,
      "step": 100
    },
    {
      "epoch": 0.9586056644880174,
      "grad_norm": 0.5703007918047962,
      "learning_rate": 8.658687785994579e-06,
      "loss": 0.092532217502594,
      "step": 110
    },
    {
      "epoch": 1.0435729847494553,
      "grad_norm": 0.5044506688179623,
      "learning_rate": 8.29514143324466e-06,
      "loss": 0.08056190013885497,
      "step": 120
    },
    {
      "epoch": 1.130718954248366,
      "grad_norm": 0.45897327652678604,
      "learning_rate": 7.89778247035085e-06,
      "loss": 0.07299971580505371,
      "step": 130
    },
    {
      "epoch": 1.2178649237472767,
      "grad_norm": 0.512980363314234,
      "learning_rate": 7.470688337985029e-06,
      "loss": 0.07079986333847046,
      "step": 140
    },
    {
      "epoch": 1.3050108932461875,
      "grad_norm": 0.47351565581785493,
      "learning_rate": 7.018241599895974e-06,
      "loss": 0.06660881042480468,
      "step": 150
    },
    {
      "epoch": 1.392156862745098,
      "grad_norm": 0.5370628072208776,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.0653923749923706,
      "step": 160
    },
    {
      "epoch": 1.4793028322440087,
      "grad_norm": 0.48059037186135045,
      "learning_rate": 6.056073681208038e-06,
      "loss": 0.06376279592514038,
      "step": 170
    },
    {
      "epoch": 1.5664488017429194,
      "grad_norm": 0.5064023315317826,
      "learning_rate": 5.556225645476119e-06,
      "loss": 0.06115278005599976,
      "step": 180
    },
    {
      "epoch": 1.65359477124183,
      "grad_norm": 0.42527473207127103,
      "learning_rate": 5.050669981928056e-06,
      "loss": 0.05721602439880371,
      "step": 190
    },
    {
      "epoch": 1.7407407407407407,
      "grad_norm": 0.6697126311013827,
      "learning_rate": 4.544594375797969e-06,
      "loss": 0.05891573429107666,
      "step": 200
    },
    {
      "epoch": 1.8278867102396514,
      "grad_norm": 0.5279032397256536,
      "learning_rate": 4.043191847634469e-06,
      "loss": 0.053774547576904294,
      "step": 210
    },
    {
      "epoch": 1.915032679738562,
      "grad_norm": 0.5503203177829016,
      "learning_rate": 3.55160746588254e-06,
      "loss": 0.05282905101776123,
      "step": 220
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5834909575577394,
      "learning_rate": 3.0748855515189104e-06,
      "loss": 0.04842503666877747,
      "step": 230
    },
    {
      "epoch": 2.0871459694989105,
      "grad_norm": 0.45637637277474224,
      "learning_rate": 2.617917916492776e-06,
      "loss": 0.030383211374282838,
      "step": 240
    },
    {
      "epoch": 2.1742919389978215,
      "grad_norm": 0.5460303567191565,
      "learning_rate": 2.185393667115513e-06,
      "loss": 0.027488625049591063,
      "step": 250
    },
    {
      "epoch": 2.261437908496732,
      "grad_norm": 0.5299369784489509,
      "learning_rate": 1.7817510874845585e-06,
      "loss": 0.02891799509525299,
      "step": 260
    },
    {
      "epoch": 2.348583877995643,
      "grad_norm": 0.47946594564717776,
      "learning_rate": 1.411132096682606e-06,
      "loss": 0.025755631923675536,
      "step": 270
    },
    {
      "epoch": 2.4357298474945535,
      "grad_norm": 0.5587855844190783,
      "learning_rate": 1.0773397470829145e-06,
      "loss": 0.02339869737625122,
      "step": 280
    },
    {
      "epoch": 2.522875816993464,
      "grad_norm": 0.5415169503522139,
      "learning_rate": 7.837991998855899e-07,
      "loss": 0.02193155437707901,
      "step": 290
    },
    {
      "epoch": 2.610021786492375,
      "grad_norm": 0.5047370934641092,
      "learning_rate": 5.335225783287051e-07,
      "loss": 0.022859147191047667,
      "step": 300
    },
    {
      "epoch": 2.6971677559912854,
      "grad_norm": 0.5339811061748208,
      "learning_rate": 3.290780592278148e-07,
      "loss": 0.022240425646305084,
      "step": 310
    },
    {
      "epoch": 2.784313725490196,
      "grad_norm": 0.5269387231320517,
      "learning_rate": 1.725635200065323e-07,
      "loss": 0.021587590873241424,
      "step": 320
    },
    {
      "epoch": 2.871459694989107,
      "grad_norm": 0.4475061358613248,
      "learning_rate": 6.558501163527964e-08,
      "loss": 0.020273779332637788,
      "step": 330
    },
    {
      "epoch": 2.9586056644880174,
      "grad_norm": 0.38102973450948285,
      "learning_rate": 9.240278374995637e-09,
      "loss": 0.019534435868263245,
      "step": 340
    },
    {
      "epoch": 3.0,
      "step": 345,
      "total_flos": 76776714797056.0,
      "train_loss": 0.08690919660139775,
      "train_runtime": 2313.134,
      "train_samples_per_second": 9.525,
      "train_steps_per_second": 0.149
    }
  ],
  "logging_steps": 10,
  "max_steps": 345,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 76776714797056.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}