{
  "best_global_step": 3800,
  "best_metric": 3.8959919379522034e-07,
  "best_model_checkpoint": "./code_corruptor_model_v2\\checkpoint-3800",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 3800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 0.10753314197063446,
      "learning_rate": 4.948464912280702e-05,
      "loss": 0.4466,
      "step": 50
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.006062635686248541,
      "learning_rate": 4.8936403508771935e-05,
      "loss": 0.0037,
      "step": 100
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 0.008465762250125408,
      "learning_rate": 4.838815789473685e-05,
      "loss": 0.001,
      "step": 150
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.01755240559577942,
      "learning_rate": 4.7839912280701754e-05,
      "loss": 0.0015,
      "step": 200
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 0.042610205709934235,
      "learning_rate": 4.7291666666666666e-05,
      "loss": 0.0009,
      "step": 250
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.05834781005978584,
      "learning_rate": 4.674342105263158e-05,
      "loss": 0.0006,
      "step": 300
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 0.0006559228058904409,
      "learning_rate": 4.619517543859649e-05,
      "loss": 0.0005,
      "step": 350
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6028698155423626e-05,
      "eval_runtime": 6.2183,
      "eval_samples_per_second": 24.444,
      "eval_steps_per_second": 12.222,
      "step": 380
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.055409740656614304,
      "learning_rate": 4.5646929824561405e-05,
      "loss": 0.0005,
      "step": 400
    },
    {
      "epoch": 1.1842105263157894,
      "grad_norm": 0.07685278356075287,
      "learning_rate": 4.509868421052632e-05,
      "loss": 0.0007,
      "step": 450
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 0.0034991835709661245,
      "learning_rate": 4.455043859649123e-05,
      "loss": 0.0004,
      "step": 500
    },
    {
      "epoch": 1.4473684210526316,
      "grad_norm": 0.0010067017283290625,
      "learning_rate": 4.400219298245614e-05,
      "loss": 0.0002,
      "step": 550
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 0.0004999448428861797,
      "learning_rate": 4.3453947368421056e-05,
      "loss": 0.0005,
      "step": 600
    },
    {
      "epoch": 1.7105263157894737,
      "grad_norm": 0.0048265825025737286,
      "learning_rate": 4.290570175438597e-05,
      "loss": 0.0001,
      "step": 650
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 0.0009590413537807763,
      "learning_rate": 4.235745614035088e-05,
      "loss": 0.0002,
      "step": 700
    },
    {
      "epoch": 1.973684210526316,
      "grad_norm": 0.0026596838142722845,
      "learning_rate": 4.180921052631579e-05,
      "loss": 0.0002,
      "step": 750
    },
    {
      "epoch": 2.0,
      "eval_loss": 9.181250788969919e-06,
      "eval_runtime": 6.0411,
      "eval_samples_per_second": 25.161,
      "eval_steps_per_second": 12.58,
      "step": 760
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.0004917697515338659,
      "learning_rate": 4.12609649122807e-05,
      "loss": 0.0003,
      "step": 800
    },
    {
      "epoch": 2.236842105263158,
      "grad_norm": 0.0010589464800432324,
      "learning_rate": 4.071271929824562e-05,
      "loss": 0.0005,
      "step": 850
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 0.001737129525281489,
      "learning_rate": 4.016447368421053e-05,
      "loss": 0.0004,
      "step": 900
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.00043353348155505955,
      "learning_rate": 3.9616228070175445e-05,
      "loss": 0.0002,
      "step": 950
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 0.000876229431014508,
      "learning_rate": 3.906798245614035e-05,
      "loss": 0.0001,
      "step": 1000
    },
    {
      "epoch": 2.763157894736842,
      "grad_norm": 0.006859931629151106,
      "learning_rate": 3.8519736842105264e-05,
      "loss": 0.0,
      "step": 1050
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 0.00029508452280424535,
      "learning_rate": 3.7971491228070176e-05,
      "loss": 0.0005,
      "step": 1100
    },
    {
      "epoch": 3.0,
      "eval_loss": 4.4037507905159146e-05,
      "eval_runtime": 6.0562,
      "eval_samples_per_second": 25.098,
      "eval_steps_per_second": 12.549,
      "step": 1140
    },
    {
      "epoch": 3.026315789473684,
      "grad_norm": 0.02006879821419716,
      "learning_rate": 3.742324561403509e-05,
      "loss": 0.001,
      "step": 1150
    },
    {
      "epoch": 3.1578947368421053,
      "grad_norm": 0.0015200282214209437,
      "learning_rate": 3.6875e-05,
      "loss": 0.0001,
      "step": 1200
    },
    {
      "epoch": 3.2894736842105265,
      "grad_norm": 0.0007221988635137677,
      "learning_rate": 3.6326754385964915e-05,
      "loss": 0.0,
      "step": 1250
    },
    {
      "epoch": 3.4210526315789473,
      "grad_norm": 0.0002022625703830272,
      "learning_rate": 3.577850877192983e-05,
      "loss": 0.0002,
      "step": 1300
    },
    {
      "epoch": 3.5526315789473686,
      "grad_norm": 0.2107187658548355,
      "learning_rate": 3.523026315789474e-05,
      "loss": 0.0009,
      "step": 1350
    },
    {
      "epoch": 3.6842105263157894,
      "grad_norm": 0.0004320333246141672,
      "learning_rate": 3.468201754385965e-05,
      "loss": 0.0009,
      "step": 1400
    },
    {
      "epoch": 3.8157894736842106,
      "grad_norm": 0.0014643239555880427,
      "learning_rate": 3.4133771929824566e-05,
      "loss": 0.0005,
      "step": 1450
    },
    {
      "epoch": 3.9473684210526314,
      "grad_norm": 0.0002134596143150702,
      "learning_rate": 3.358552631578947e-05,
      "loss": 0.0,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.688454176473897e-05,
      "eval_runtime": 6.1697,
      "eval_samples_per_second": 24.637,
      "eval_steps_per_second": 12.318,
      "step": 1520
    },
    {
      "epoch": 4.078947368421052,
      "grad_norm": 0.007211349904537201,
      "learning_rate": 3.3037280701754384e-05,
      "loss": 0.0002,
      "step": 1550
    },
    {
      "epoch": 4.2105263157894735,
      "grad_norm": 0.00045391780440695584,
      "learning_rate": 3.24890350877193e-05,
      "loss": 0.0003,
      "step": 1600
    },
    {
      "epoch": 4.342105263157895,
      "grad_norm": 0.00023115136718843132,
      "learning_rate": 3.194078947368421e-05,
      "loss": 0.0001,
      "step": 1650
    },
    {
      "epoch": 4.473684210526316,
      "grad_norm": 0.14033561944961548,
      "learning_rate": 3.139254385964913e-05,
      "loss": 0.0001,
      "step": 1700
    },
    {
      "epoch": 4.605263157894737,
      "grad_norm": 0.0017103628488257527,
      "learning_rate": 3.0844298245614035e-05,
      "loss": 0.0001,
      "step": 1750
    },
    {
      "epoch": 4.7368421052631575,
      "grad_norm": 0.0032462095841765404,
      "learning_rate": 3.0296052631578948e-05,
      "loss": 0.0,
      "step": 1800
    },
    {
      "epoch": 4.868421052631579,
      "grad_norm": 0.002826864365488291,
      "learning_rate": 2.974780701754386e-05,
      "loss": 0.0001,
      "step": 1850
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0006184170488268137,
      "learning_rate": 2.9199561403508774e-05,
      "loss": 0.0005,
      "step": 1900
    },
    {
      "epoch": 5.0,
      "eval_loss": 3.343406660860637e-06,
      "eval_runtime": 6.1148,
      "eval_samples_per_second": 24.858,
      "eval_steps_per_second": 12.429,
      "step": 1900
    },
    {
      "epoch": 5.131578947368421,
      "grad_norm": 0.0009092154796235263,
      "learning_rate": 2.8651315789473686e-05,
      "loss": 0.0,
      "step": 1950
    },
    {
      "epoch": 5.2631578947368425,
      "grad_norm": 0.0006162663921713829,
      "learning_rate": 2.81030701754386e-05,
      "loss": 0.0,
      "step": 2000
    },
    {
      "epoch": 5.394736842105263,
      "grad_norm": 0.0013979279901832342,
      "learning_rate": 2.755482456140351e-05,
      "loss": 0.0001,
      "step": 2050
    },
    {
      "epoch": 5.526315789473684,
      "grad_norm": 0.00045684297219850123,
      "learning_rate": 2.700657894736842e-05,
      "loss": 0.0,
      "step": 2100
    },
    {
      "epoch": 5.657894736842105,
      "grad_norm": 0.017059462144970894,
      "learning_rate": 2.6458333333333334e-05,
      "loss": 0.0,
      "step": 2150
    },
    {
      "epoch": 5.7894736842105265,
      "grad_norm": 9.451019286643714e-05,
      "learning_rate": 2.591008771929825e-05,
      "loss": 0.0001,
      "step": 2200
    },
    {
      "epoch": 5.921052631578947,
      "grad_norm": 0.0002531503851059824,
      "learning_rate": 2.5361842105263163e-05,
      "loss": 0.0002,
      "step": 2250
    },
    {
      "epoch": 6.0,
      "eval_loss": 8.532630317859002e-07,
      "eval_runtime": 6.1846,
      "eval_samples_per_second": 24.577,
      "eval_steps_per_second": 12.289,
      "step": 2280
    },
    {
      "epoch": 6.052631578947368,
      "grad_norm": 0.00012987718218937516,
      "learning_rate": 2.4813596491228072e-05,
      "loss": 0.0,
      "step": 2300
    },
    {
      "epoch": 6.184210526315789,
      "grad_norm": 8.179421274689957e-05,
      "learning_rate": 2.426535087719298e-05,
      "loss": 0.0,
      "step": 2350
    },
    {
      "epoch": 6.315789473684211,
      "grad_norm": 0.0004638760001398623,
      "learning_rate": 2.3717105263157898e-05,
      "loss": 0.0,
      "step": 2400
    },
    {
      "epoch": 6.447368421052632,
      "grad_norm": 0.0002866844297386706,
      "learning_rate": 2.316885964912281e-05,
      "loss": 0.0005,
      "step": 2450
    },
    {
      "epoch": 6.578947368421053,
      "grad_norm": 7.315115362871438e-05,
      "learning_rate": 2.262061403508772e-05,
      "loss": 0.0,
      "step": 2500
    },
    {
      "epoch": 6.7105263157894735,
      "grad_norm": 0.00015406313468702137,
      "learning_rate": 2.2072368421052632e-05,
      "loss": 0.0,
      "step": 2550
    },
    {
      "epoch": 6.842105263157895,
      "grad_norm": 8.98495563887991e-05,
      "learning_rate": 2.1524122807017545e-05,
      "loss": 0.0,
      "step": 2600
    },
    {
      "epoch": 6.973684210526316,
      "grad_norm": 0.00020581792341545224,
      "learning_rate": 2.0975877192982458e-05,
      "loss": 0.0,
      "step": 2650
    },
    {
      "epoch": 7.0,
      "eval_loss": 8.157680895237718e-07,
      "eval_runtime": 6.1011,
      "eval_samples_per_second": 24.914,
      "eval_steps_per_second": 12.457,
      "step": 2660
    },
    {
      "epoch": 7.105263157894737,
      "grad_norm": 0.00012650905409827828,
      "learning_rate": 2.042763157894737e-05,
      "loss": 0.0,
      "step": 2700
    },
    {
      "epoch": 7.2368421052631575,
      "grad_norm": 0.00016898708418011665,
      "learning_rate": 1.987938596491228e-05,
      "loss": 0.0,
      "step": 2750
    },
    {
      "epoch": 7.368421052631579,
      "grad_norm": 0.0003560652839951217,
      "learning_rate": 1.9331140350877193e-05,
      "loss": 0.0,
      "step": 2800
    },
    {
      "epoch": 7.5,
      "grad_norm": 8.456506475340575e-05,
      "learning_rate": 1.8782894736842105e-05,
      "loss": 0.0,
      "step": 2850
    },
    {
      "epoch": 7.631578947368421,
      "grad_norm": 0.00023642393352929503,
      "learning_rate": 1.8234649122807018e-05,
      "loss": 0.0,
      "step": 2900
    },
    {
      "epoch": 7.7631578947368425,
      "grad_norm": 8.907222945708781e-05,
      "learning_rate": 1.768640350877193e-05,
      "loss": 0.0,
      "step": 2950
    },
    {
      "epoch": 7.894736842105263,
      "grad_norm": 6.318661326076835e-05,
      "learning_rate": 1.7138157894736844e-05,
      "loss": 0.0,
      "step": 3000
    },
    {
      "epoch": 8.0,
      "eval_loss": 5.999586392135825e-07,
      "eval_runtime": 6.1117,
      "eval_samples_per_second": 24.87,
      "eval_steps_per_second": 12.435,
      "step": 3040
    },
    {
      "epoch": 8.026315789473685,
      "grad_norm": 0.04527832567691803,
      "learning_rate": 1.6589912280701756e-05,
      "loss": 0.0002,
      "step": 3050
    },
    {
      "epoch": 8.157894736842104,
      "grad_norm": 0.0002466822334099561,
      "learning_rate": 1.604166666666667e-05,
      "loss": 0.0,
      "step": 3100
    },
    {
      "epoch": 8.289473684210526,
      "grad_norm": 0.00023732382396701723,
      "learning_rate": 1.549342105263158e-05,
      "loss": 0.0,
      "step": 3150
    },
    {
      "epoch": 8.421052631578947,
      "grad_norm": 8.941477426560596e-05,
      "learning_rate": 1.4945175438596493e-05,
      "loss": 0.0001,
      "step": 3200
    },
    {
      "epoch": 8.552631578947368,
      "grad_norm": 0.00011901962716365233,
      "learning_rate": 1.4396929824561402e-05,
      "loss": 0.0,
      "step": 3250
    },
    {
      "epoch": 8.68421052631579,
      "grad_norm": 9.798636165214702e-05,
      "learning_rate": 1.3848684210526317e-05,
      "loss": 0.0,
      "step": 3300
    },
    {
      "epoch": 8.81578947368421,
      "grad_norm": 3.7345100281527266e-05,
      "learning_rate": 1.330043859649123e-05,
      "loss": 0.0,
      "step": 3350
    },
    {
      "epoch": 8.947368421052632,
      "grad_norm": 2.8350032152957283e-05,
      "learning_rate": 1.275219298245614e-05,
      "loss": 0.0,
      "step": 3400
    },
    {
      "epoch": 9.0,
      "eval_loss": 4.4665341647487367e-07,
      "eval_runtime": 6.1054,
      "eval_samples_per_second": 24.896,
      "eval_steps_per_second": 12.448,
      "step": 3420
    },
    {
      "epoch": 9.078947368421053,
      "grad_norm": 8.318301843246445e-05,
      "learning_rate": 1.2203947368421053e-05,
      "loss": 0.0,
      "step": 3450
    },
    {
      "epoch": 9.210526315789474,
      "grad_norm": 4.566019197227433e-05,
      "learning_rate": 1.1655701754385966e-05,
      "loss": 0.0,
      "step": 3500
    },
    {
      "epoch": 9.342105263157896,
      "grad_norm": 0.03128642588853836,
      "learning_rate": 1.1107456140350877e-05,
      "loss": 0.0,
      "step": 3550
    },
    {
      "epoch": 9.473684210526315,
      "grad_norm": 4.535232073976658e-05,
      "learning_rate": 1.055921052631579e-05,
      "loss": 0.0,
      "step": 3600
    },
    {
      "epoch": 9.605263157894736,
      "grad_norm": 7.957038906170055e-05,
      "learning_rate": 1.0010964912280703e-05,
      "loss": 0.0,
      "step": 3650
    },
    {
      "epoch": 9.736842105263158,
      "grad_norm": 5.397196946432814e-05,
      "learning_rate": 9.462719298245615e-06,
      "loss": 0.0,
      "step": 3700
    },
    {
      "epoch": 9.868421052631579,
      "grad_norm": 0.00015735568013042212,
      "learning_rate": 8.914473684210526e-06,
      "loss": 0.0,
      "step": 3750
    },
    {
      "epoch": 10.0,
      "grad_norm": 3.112037666141987e-05,
      "learning_rate": 8.36622807017544e-06,
      "loss": 0.0,
      "step": 3800
    },
    {
      "epoch": 10.0,
      "eval_loss": 3.8959919379522034e-07,
      "eval_runtime": 6.0027,
      "eval_samples_per_second": 25.322,
      "eval_steps_per_second": 12.661,
      "step": 3800
    }
  ],
  "logging_steps": 50,
  "max_steps": 4560,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "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": 4621990389350400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}