{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.444444444444445,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.20243267714977264,
      "learning_rate": 5e-05,
      "loss": 0.1508,
      "mean_token_accuracy": 0.9614167541265488,
      "num_tokens": 172590.0,
      "step": 50
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.22473949193954468,
      "learning_rate": 5e-05,
      "loss": 0.0762,
      "mean_token_accuracy": 0.974150316119194,
      "num_tokens": 346277.0,
      "step": 100
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.1306583136320114,
      "learning_rate": 5e-05,
      "loss": 0.059,
      "mean_token_accuracy": 0.9791698586940766,
      "num_tokens": 521548.0,
      "step": 150
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.2091003954410553,
      "learning_rate": 5e-05,
      "loss": 0.0511,
      "mean_token_accuracy": 0.9820115834474563,
      "num_tokens": 694583.0,
      "step": 200
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.18803296983242035,
      "learning_rate": 5e-05,
      "loss": 0.0443,
      "mean_token_accuracy": 0.9839017766714097,
      "num_tokens": 868203.0,
      "step": 250
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.19305875897407532,
      "learning_rate": 5e-05,
      "loss": 0.0484,
      "mean_token_accuracy": 0.9826253122091293,
      "num_tokens": 1044270.0,
      "step": 300
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.16429616510868073,
      "learning_rate": 5e-05,
      "loss": 0.0452,
      "mean_token_accuracy": 0.9832556092739105,
      "num_tokens": 1221728.0,
      "step": 350
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.17009682953357697,
      "learning_rate": 5e-05,
      "loss": 0.0419,
      "mean_token_accuracy": 0.9852031743526459,
      "num_tokens": 1395873.0,
      "step": 400
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.14838816225528717,
      "learning_rate": 5e-05,
      "loss": 0.0458,
      "mean_token_accuracy": 0.9842678928375244,
      "num_tokens": 1570780.0,
      "step": 450
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.20167161524295807,
      "learning_rate": 5e-05,
      "loss": 0.0335,
      "mean_token_accuracy": 0.9871636009216309,
      "num_tokens": 1746181.0,
      "step": 500
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.22028109431266785,
      "learning_rate": 5e-05,
      "loss": 0.0338,
      "mean_token_accuracy": 0.9862233906984329,
      "num_tokens": 1921414.0,
      "step": 550
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.12278841435909271,
      "learning_rate": 5e-05,
      "loss": 0.0299,
      "mean_token_accuracy": 0.9886959612369537,
      "num_tokens": 2095976.0,
      "step": 600
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.09097229689359665,
      "learning_rate": 5e-05,
      "loss": 0.0344,
      "mean_token_accuracy": 0.9869739925861358,
      "num_tokens": 2269976.0,
      "step": 650
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.149724543094635,
      "learning_rate": 5e-05,
      "loss": 0.0312,
      "mean_token_accuracy": 0.9881853342056275,
      "num_tokens": 2444238.0,
      "step": 700
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.1601683348417282,
      "learning_rate": 5e-05,
      "loss": 0.0375,
      "mean_token_accuracy": 0.9859996843338013,
      "num_tokens": 2618992.0,
      "step": 750
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.14399662613868713,
      "learning_rate": 5e-05,
      "loss": 0.0273,
      "mean_token_accuracy": 0.9900204366445542,
      "num_tokens": 2793057.0,
      "step": 800
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.1325361728668213,
      "learning_rate": 5e-05,
      "loss": 0.037,
      "mean_token_accuracy": 0.9859159809350967,
      "num_tokens": 2966769.0,
      "step": 850
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.12275587767362595,
      "learning_rate": 5e-05,
      "loss": 0.0359,
      "mean_token_accuracy": 0.9860490292310715,
      "num_tokens": 3141560.0,
      "step": 900
    },
    {
      "epoch": 2.111111111111111,
      "grad_norm": 0.14534829556941986,
      "learning_rate": 5e-05,
      "loss": 0.0238,
      "mean_token_accuracy": 0.9910678189992904,
      "num_tokens": 3315113.0,
      "step": 950
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.1087908148765564,
      "learning_rate": 5e-05,
      "loss": 0.0281,
      "mean_token_accuracy": 0.9884923130273819,
      "num_tokens": 3488791.0,
      "step": 1000
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.16228517889976501,
      "learning_rate": 5e-05,
      "loss": 0.0234,
      "mean_token_accuracy": 0.9911258590221405,
      "num_tokens": 3663372.0,
      "step": 1050
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.05340925231575966,
      "learning_rate": 5e-05,
      "loss": 0.0254,
      "mean_token_accuracy": 0.9899671649932862,
      "num_tokens": 3837397.0,
      "step": 1100
    },
    {
      "epoch": 2.5555555555555554,
      "grad_norm": 0.12148639559745789,
      "learning_rate": 5e-05,
      "loss": 0.0296,
      "mean_token_accuracy": 0.9886352431774139,
      "num_tokens": 4012362.0,
      "step": 1150
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.09275887161493301,
      "learning_rate": 5e-05,
      "loss": 0.0269,
      "mean_token_accuracy": 0.989583585858345,
      "num_tokens": 4188410.0,
      "step": 1200
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.17173512279987335,
      "learning_rate": 5e-05,
      "loss": 0.0275,
      "mean_token_accuracy": 0.9893661296367645,
      "num_tokens": 4364549.0,
      "step": 1250
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.18386530876159668,
      "learning_rate": 5e-05,
      "loss": 0.03,
      "mean_token_accuracy": 0.9877435737848281,
      "num_tokens": 4538708.0,
      "step": 1300
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.0737985298037529,
      "learning_rate": 5e-05,
      "loss": 0.0256,
      "mean_token_accuracy": 0.9906050026416778,
      "num_tokens": 4712340.0,
      "step": 1350
    },
    {
      "epoch": 3.111111111111111,
      "grad_norm": 0.10669398307800293,
      "learning_rate": 5e-05,
      "loss": 0.0231,
      "mean_token_accuracy": 0.9914622634649277,
      "num_tokens": 4887386.0,
      "step": 1400
    },
    {
      "epoch": 3.2222222222222223,
      "grad_norm": 0.09974446147680283,
      "learning_rate": 5e-05,
      "loss": 0.0212,
      "mean_token_accuracy": 0.9920986944437027,
      "num_tokens": 5059979.0,
      "step": 1450
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.18398422002792358,
      "learning_rate": 5e-05,
      "loss": 0.0229,
      "mean_token_accuracy": 0.9908855521678924,
      "num_tokens": 5233989.0,
      "step": 1500
    },
    {
      "epoch": 3.4444444444444446,
      "grad_norm": 0.10202126950025558,
      "learning_rate": 5e-05,
      "loss": 0.0236,
      "mean_token_accuracy": 0.9902925211191177,
      "num_tokens": 5410888.0,
      "step": 1550
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.1483769565820694,
      "learning_rate": 5e-05,
      "loss": 0.0244,
      "mean_token_accuracy": 0.9899595558643342,
      "num_tokens": 5584175.0,
      "step": 1600
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 0.07508880645036697,
      "learning_rate": 5e-05,
      "loss": 0.0226,
      "mean_token_accuracy": 0.9916278702020646,
      "num_tokens": 5759747.0,
      "step": 1650
    },
    {
      "epoch": 3.7777777777777777,
      "grad_norm": 0.08631623536348343,
      "learning_rate": 5e-05,
      "loss": 0.0252,
      "mean_token_accuracy": 0.9896138072013855,
      "num_tokens": 5933352.0,
      "step": 1700
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 0.12719225883483887,
      "learning_rate": 5e-05,
      "loss": 0.0213,
      "mean_token_accuracy": 0.9918474739789963,
      "num_tokens": 6108120.0,
      "step": 1750
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.07570526748895645,
      "learning_rate": 5e-05,
      "loss": 0.0243,
      "mean_token_accuracy": 0.990051948428154,
      "num_tokens": 6283120.0,
      "step": 1800
    },
    {
      "epoch": 4.111111111111111,
      "grad_norm": 0.7129213213920593,
      "learning_rate": 5e-05,
      "loss": 0.0181,
      "mean_token_accuracy": 0.9931919860839844,
      "num_tokens": 6456943.0,
      "step": 1850
    },
    {
      "epoch": 4.222222222222222,
      "grad_norm": 0.132768452167511,
      "learning_rate": 5e-05,
      "loss": 0.0202,
      "mean_token_accuracy": 0.9916618072986603,
      "num_tokens": 6632907.0,
      "step": 1900
    },
    {
      "epoch": 4.333333333333333,
      "grad_norm": 0.1010010689496994,
      "learning_rate": 5e-05,
      "loss": 0.0212,
      "mean_token_accuracy": 0.9916968619823456,
      "num_tokens": 6805656.0,
      "step": 1950
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.22385317087173462,
      "learning_rate": 5e-05,
      "loss": 0.0204,
      "mean_token_accuracy": 0.9914450365304946,
      "num_tokens": 6978299.0,
      "step": 2000
    }
  ],
  "logging_steps": 50,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 3.174835230239662e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}