{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1423,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.035137034434293744,
      "grad_norm": 13.614160537719727,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.6868,
      "step": 50
    },
    {
      "epoch": 0.07027406886858749,
      "grad_norm": 7.1465582847595215,
      "learning_rate": 4.95e-06,
      "loss": 0.5593,
      "step": 100
    },
    {
      "epoch": 0.10541110330288124,
      "grad_norm": 0.4900398254394531,
      "learning_rate": 7.450000000000001e-06,
      "loss": 0.545,
      "step": 150
    },
    {
      "epoch": 0.14054813773717498,
      "grad_norm": 0.034149572253227234,
      "learning_rate": 9.950000000000001e-06,
      "loss": 0.2203,
      "step": 200
    },
    {
      "epoch": 0.17568517217146873,
      "grad_norm": 2.6971633434295654,
      "learning_rate": 9.814814814814815e-06,
      "loss": 0.1222,
      "step": 250
    },
    {
      "epoch": 0.21082220660576248,
      "grad_norm": 0.012744505889713764,
      "learning_rate": 9.625850340136055e-06,
      "loss": 0.0908,
      "step": 300
    },
    {
      "epoch": 0.24595924104005623,
      "grad_norm": 0.008385892026126385,
      "learning_rate": 9.436885865457295e-06,
      "loss": 0.0744,
      "step": 350
    },
    {
      "epoch": 0.28109627547434995,
      "grad_norm": 3.446326494216919,
      "learning_rate": 9.247921390778534e-06,
      "loss": 0.1984,
      "step": 400
    },
    {
      "epoch": 0.31623330990864373,
      "grad_norm": 5.261374473571777,
      "learning_rate": 9.058956916099774e-06,
      "loss": 0.0871,
      "step": 450
    },
    {
      "epoch": 0.35137034434293746,
      "grad_norm": 0.009863858111202717,
      "learning_rate": 8.869992441421013e-06,
      "loss": 0.0469,
      "step": 500
    },
    {
      "epoch": 0.3865073787772312,
      "grad_norm": 0.026721283793449402,
      "learning_rate": 8.681027966742253e-06,
      "loss": 0.0974,
      "step": 550
    },
    {
      "epoch": 0.42164441321152496,
      "grad_norm": 0.0059141730889678,
      "learning_rate": 8.492063492063492e-06,
      "loss": 0.1371,
      "step": 600
    },
    {
      "epoch": 0.4567814476458187,
      "grad_norm": 0.005736654158681631,
      "learning_rate": 8.303099017384732e-06,
      "loss": 0.1128,
      "step": 650
    },
    {
      "epoch": 0.49191848208011246,
      "grad_norm": 0.006507765036076307,
      "learning_rate": 8.114134542705972e-06,
      "loss": 0.1137,
      "step": 700
    },
    {
      "epoch": 0.5270555165144062,
      "grad_norm": 3.8664681911468506,
      "learning_rate": 7.925170068027211e-06,
      "loss": 0.1744,
      "step": 750
    },
    {
      "epoch": 0.5621925509486999,
      "grad_norm": 0.004181186202913523,
      "learning_rate": 7.73620559334845e-06,
      "loss": 0.1439,
      "step": 800
    },
    {
      "epoch": 0.5973295853829936,
      "grad_norm": 1.2505786418914795,
      "learning_rate": 7.54724111866969e-06,
      "loss": 0.2144,
      "step": 850
    },
    {
      "epoch": 0.6324666198172875,
      "grad_norm": 0.010104745626449585,
      "learning_rate": 7.358276643990931e-06,
      "loss": 0.1264,
      "step": 900
    },
    {
      "epoch": 0.6676036542515812,
      "grad_norm": 0.7443602085113525,
      "learning_rate": 7.16931216931217e-06,
      "loss": 0.152,
      "step": 950
    },
    {
      "epoch": 0.7027406886858749,
      "grad_norm": 0.005628188606351614,
      "learning_rate": 6.980347694633409e-06,
      "loss": 0.1059,
      "step": 1000
    },
    {
      "epoch": 0.7378777231201686,
      "grad_norm": 1.3959672451019287,
      "learning_rate": 6.7913832199546494e-06,
      "loss": 0.1033,
      "step": 1050
    },
    {
      "epoch": 0.7730147575544624,
      "grad_norm": 0.002598799532279372,
      "learning_rate": 6.602418745275889e-06,
      "loss": 0.102,
      "step": 1100
    },
    {
      "epoch": 0.8081517919887562,
      "grad_norm": 5.506197452545166,
      "learning_rate": 6.413454270597128e-06,
      "loss": 0.1057,
      "step": 1150
    },
    {
      "epoch": 0.8432888264230499,
      "grad_norm": 0.0023803438525646925,
      "learning_rate": 6.224489795918368e-06,
      "loss": 0.0908,
      "step": 1200
    },
    {
      "epoch": 0.8784258608573436,
      "grad_norm": 0.14706958830356598,
      "learning_rate": 6.035525321239607e-06,
      "loss": 0.0753,
      "step": 1250
    },
    {
      "epoch": 0.9135628952916374,
      "grad_norm": 0.003114320570603013,
      "learning_rate": 5.846560846560847e-06,
      "loss": 0.1046,
      "step": 1300
    },
    {
      "epoch": 0.9486999297259311,
      "grad_norm": 0.0024313139729201794,
      "learning_rate": 5.657596371882087e-06,
      "loss": 0.1181,
      "step": 1350
    },
    {
      "epoch": 0.9838369641602249,
      "grad_norm": 2.204352378845215,
      "learning_rate": 5.468631897203326e-06,
      "loss": 0.086,
      "step": 1400
    }
  ],
  "logging_steps": 50,
  "max_steps": 2846,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 371766674022912.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}