{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 820,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024390243902439025,
      "grad_norm": 0.527539849281311,
      "learning_rate": 0.00019631901840490797,
      "loss": 2.5938,
      "step": 20
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 0.44933316111564636,
      "learning_rate": 0.0001914110429447853,
      "loss": 2.3199,
      "step": 40
    },
    {
      "epoch": 0.07317073170731707,
      "grad_norm": 0.4288434088230133,
      "learning_rate": 0.00018650306748466258,
      "loss": 2.3258,
      "step": 60
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.45298221707344055,
      "learning_rate": 0.00018159509202453987,
      "loss": 2.2702,
      "step": 80
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 0.43396779894828796,
      "learning_rate": 0.0001766871165644172,
      "loss": 2.2431,
      "step": 100
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 0.49523407220840454,
      "learning_rate": 0.0001717791411042945,
      "loss": 2.1976,
      "step": 120
    },
    {
      "epoch": 0.17073170731707318,
      "grad_norm": 0.5997231602668762,
      "learning_rate": 0.00016687116564417177,
      "loss": 2.2976,
      "step": 140
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.41708627343177795,
      "learning_rate": 0.00016196319018404909,
      "loss": 2.1886,
      "step": 160
    },
    {
      "epoch": 0.21951219512195122,
      "grad_norm": 0.6412221789360046,
      "learning_rate": 0.0001570552147239264,
      "loss": 2.191,
      "step": 180
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.47484350204467773,
      "learning_rate": 0.0001521472392638037,
      "loss": 2.2481,
      "step": 200
    },
    {
      "epoch": 0.2682926829268293,
      "grad_norm": 0.4611384868621826,
      "learning_rate": 0.00014723926380368098,
      "loss": 2.2095,
      "step": 220
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.40287452936172485,
      "learning_rate": 0.00014233128834355828,
      "loss": 2.1993,
      "step": 240
    },
    {
      "epoch": 0.3170731707317073,
      "grad_norm": 0.49002254009246826,
      "learning_rate": 0.0001374233128834356,
      "loss": 2.179,
      "step": 260
    },
    {
      "epoch": 0.34146341463414637,
      "grad_norm": 0.4154254198074341,
      "learning_rate": 0.00013251533742331288,
      "loss": 2.1647,
      "step": 280
    },
    {
      "epoch": 0.36585365853658536,
      "grad_norm": 0.43139123916625977,
      "learning_rate": 0.00012760736196319017,
      "loss": 2.1829,
      "step": 300
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.4743005335330963,
      "learning_rate": 0.0001226993865030675,
      "loss": 2.1758,
      "step": 320
    },
    {
      "epoch": 0.4146341463414634,
      "grad_norm": 0.4346872568130493,
      "learning_rate": 0.0001177914110429448,
      "loss": 2.2358,
      "step": 340
    },
    {
      "epoch": 0.43902439024390244,
      "grad_norm": 0.42171671986579895,
      "learning_rate": 0.00011288343558282209,
      "loss": 2.1037,
      "step": 360
    },
    {
      "epoch": 0.4634146341463415,
      "grad_norm": 0.4054619073867798,
      "learning_rate": 0.00010797546012269939,
      "loss": 2.2304,
      "step": 380
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.5276986956596375,
      "learning_rate": 0.0001030674846625767,
      "loss": 2.2531,
      "step": 400
    },
    {
      "epoch": 0.5121951219512195,
      "grad_norm": 0.49335718154907227,
      "learning_rate": 9.815950920245399e-05,
      "loss": 2.2101,
      "step": 420
    },
    {
      "epoch": 0.5365853658536586,
      "grad_norm": 0.48215413093566895,
      "learning_rate": 9.325153374233129e-05,
      "loss": 2.1688,
      "step": 440
    },
    {
      "epoch": 0.5609756097560976,
      "grad_norm": 0.4506737291812897,
      "learning_rate": 8.83435582822086e-05,
      "loss": 2.2078,
      "step": 460
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 0.5203718543052673,
      "learning_rate": 8.343558282208588e-05,
      "loss": 2.1614,
      "step": 480
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 0.38517746329307556,
      "learning_rate": 7.85276073619632e-05,
      "loss": 2.1959,
      "step": 500
    },
    {
      "epoch": 0.6341463414634146,
      "grad_norm": 0.49157264828681946,
      "learning_rate": 7.361963190184049e-05,
      "loss": 2.1381,
      "step": 520
    },
    {
      "epoch": 0.6585365853658537,
      "grad_norm": 0.5212781429290771,
      "learning_rate": 6.87116564417178e-05,
      "loss": 2.153,
      "step": 540
    },
    {
      "epoch": 0.6829268292682927,
      "grad_norm": 0.47320759296417236,
      "learning_rate": 6.380368098159509e-05,
      "loss": 2.1742,
      "step": 560
    },
    {
      "epoch": 0.7073170731707317,
      "grad_norm": 0.44908636808395386,
      "learning_rate": 5.88957055214724e-05,
      "loss": 2.1698,
      "step": 580
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 0.49904754757881165,
      "learning_rate": 5.3987730061349695e-05,
      "loss": 2.1669,
      "step": 600
    },
    {
      "epoch": 0.7560975609756098,
      "grad_norm": 0.3902740180492401,
      "learning_rate": 4.907975460122699e-05,
      "loss": 2.2217,
      "step": 620
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 0.6002075672149658,
      "learning_rate": 4.41717791411043e-05,
      "loss": 2.1774,
      "step": 640
    },
    {
      "epoch": 0.8048780487804879,
      "grad_norm": 0.4561316668987274,
      "learning_rate": 3.92638036809816e-05,
      "loss": 2.1768,
      "step": 660
    },
    {
      "epoch": 0.8292682926829268,
      "grad_norm": 0.4364475905895233,
      "learning_rate": 3.43558282208589e-05,
      "loss": 2.1112,
      "step": 680
    },
    {
      "epoch": 0.8536585365853658,
      "grad_norm": 0.4561122953891754,
      "learning_rate": 2.94478527607362e-05,
      "loss": 2.2019,
      "step": 700
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 0.5945191383361816,
      "learning_rate": 2.4539877300613496e-05,
      "loss": 2.1516,
      "step": 720
    },
    {
      "epoch": 0.9024390243902439,
      "grad_norm": 0.4705474376678467,
      "learning_rate": 1.96319018404908e-05,
      "loss": 2.2102,
      "step": 740
    },
    {
      "epoch": 0.926829268292683,
      "grad_norm": 0.5758923888206482,
      "learning_rate": 1.47239263803681e-05,
      "loss": 2.1795,
      "step": 760
    },
    {
      "epoch": 0.9512195121951219,
      "grad_norm": 0.43113359808921814,
      "learning_rate": 9.8159509202454e-06,
      "loss": 2.176,
      "step": 780
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.5037071704864502,
      "learning_rate": 4.9079754601227e-06,
      "loss": 2.1368,
      "step": 800
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5516627430915833,
      "learning_rate": 0.0,
      "loss": 2.1066,
      "step": 820
    }
  ],
  "logging_steps": 20,
  "max_steps": 820,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9629279858946867e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}