{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 320,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3125,
      "grad_norm": 3.6356492042541504,
      "learning_rate": 0.000125,
      "loss": 0.8272,
      "step": 10
    },
    {
      "epoch": 0.625,
      "grad_norm": 1.7680610418319702,
      "learning_rate": 0.0001999145758387301,
      "loss": 0.3108,
      "step": 20
    },
    {
      "epoch": 0.9375,
      "grad_norm": 1.0380995273590088,
      "learning_rate": 0.00019895522933272028,
      "loss": 0.1805,
      "step": 30
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.0853238105773926,
      "learning_rate": 0.00019694002659393305,
      "loss": 0.1284,
      "step": 40
    },
    {
      "epoch": 1.5625,
      "grad_norm": 1.007361888885498,
      "learning_rate": 0.00019389046991574298,
      "loss": 0.1185,
      "step": 50
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.5453008413314819,
      "learning_rate": 0.0001898390981891979,
      "loss": 0.1089,
      "step": 60
    },
    {
      "epoch": 2.1875,
      "grad_norm": 0.3457601070404053,
      "learning_rate": 0.00018482913971175737,
      "loss": 0.088,
      "step": 70
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.6399100422859192,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.0841,
      "step": 80
    },
    {
      "epoch": 2.8125,
      "grad_norm": 0.6185622811317444,
      "learning_rate": 0.0001721569461053062,
      "loss": 0.0755,
      "step": 90
    },
    {
      "epoch": 3.125,
      "grad_norm": 0.4300651550292969,
      "learning_rate": 0.00016462992378609407,
      "loss": 0.0696,
      "step": 100
    },
    {
      "epoch": 3.4375,
      "grad_norm": 0.5103808045387268,
      "learning_rate": 0.00015641329760952513,
      "loss": 0.0739,
      "step": 110
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.3218378722667694,
      "learning_rate": 0.00014759473930370736,
      "loss": 0.0666,
      "step": 120
    },
    {
      "epoch": 4.0625,
      "grad_norm": 0.3776991367340088,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0594,
      "step": 130
    },
    {
      "epoch": 4.375,
      "grad_norm": 0.4006097614765167,
      "learning_rate": 0.00012853362242491053,
      "loss": 0.0638,
      "step": 140
    },
    {
      "epoch": 4.6875,
      "grad_norm": 0.29042813181877136,
      "learning_rate": 0.00011849444672715586,
      "loss": 0.0589,
      "step": 150
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4325590133666992,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.0598,
      "step": 160
    },
    {
      "epoch": 5.3125,
      "grad_norm": 0.24041509628295898,
      "learning_rate": 9.793330987724459e-05,
      "loss": 0.0489,
      "step": 170
    },
    {
      "epoch": 5.625,
      "grad_norm": 0.22042500972747803,
      "learning_rate": 8.763073687306524e-05,
      "loss": 0.0463,
      "step": 180
    },
    {
      "epoch": 5.9375,
      "grad_norm": 0.20152679085731506,
      "learning_rate": 7.74601443984194e-05,
      "loss": 0.0467,
      "step": 190
    },
    {
      "epoch": 6.25,
      "grad_norm": 0.2634488344192505,
      "learning_rate": 6.753005307953167e-05,
      "loss": 0.0439,
      "step": 200
    },
    {
      "epoch": 6.5625,
      "grad_norm": 0.23869872093200684,
      "learning_rate": 5.794641738572925e-05,
      "loss": 0.0466,
      "step": 210
    },
    {
      "epoch": 6.875,
      "grad_norm": 0.23364406824111938,
      "learning_rate": 4.8811495091039926e-05,
      "loss": 0.0429,
      "step": 220
    },
    {
      "epoch": 7.1875,
      "grad_norm": 0.19756311178207397,
      "learning_rate": 4.022275617967591e-05,
      "loss": 0.0389,
      "step": 230
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.2429247349500656,
      "learning_rate": 3.227184283742591e-05,
      "loss": 0.044,
      "step": 240
    },
    {
      "epoch": 7.8125,
      "grad_norm": 0.2422388643026352,
      "learning_rate": 2.5043591625887407e-05,
      "loss": 0.039,
      "step": 250
    },
    {
      "epoch": 8.125,
      "grad_norm": 0.3408963978290558,
      "learning_rate": 1.861512827298051e-05,
      "loss": 0.0406,
      "step": 260
    },
    {
      "epoch": 8.4375,
      "grad_norm": 0.22210517525672913,
      "learning_rate": 1.305504473836331e-05,
      "loss": 0.037,
      "step": 270
    },
    {
      "epoch": 8.75,
      "grad_norm": 0.18523967266082764,
      "learning_rate": 8.422667334494249e-06,
      "loss": 0.0347,
      "step": 280
    },
    {
      "epoch": 9.0625,
      "grad_norm": 0.1788233369588852,
      "learning_rate": 4.767423712518559e-06,
      "loss": 0.0343,
      "step": 290
    },
    {
      "epoch": 9.375,
      "grad_norm": 0.2224978804588318,
      "learning_rate": 2.128315467264552e-06,
      "loss": 0.035,
      "step": 300
    },
    {
      "epoch": 9.6875,
      "grad_norm": 0.18424522876739502,
      "learning_rate": 5.335019886757442e-07,
      "loss": 0.0389,
      "step": 310
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.24724866449832916,
      "learning_rate": 0.0,
      "loss": 0.0303,
      "step": 320
    },
    {
      "epoch": 10.0,
      "step": 320,
      "total_flos": 4.354147443467232e+16,
      "train_loss": 0.0944320373237133,
      "train_runtime": 393.2592,
      "train_samples_per_second": 51.696,
      "train_steps_per_second": 0.814
    }
  ],
  "logging_steps": 10,
  "max_steps": 320,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 4.354147443467232e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}