{
  "best_metric": 0.7058091506789402,
  "best_model_checkpoint": "/data/ephemeral/home/level2-nlp-datacentric-nlp-15/models/train_aug_filtered_data_8315.csv_20241107_223341/checkpoint-400",
  "epoch": 2.0,
  "eval_steps": 100,
  "global_step": 492,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04065040650406504,
      "grad_norm": 5.844911098480225,
      "learning_rate": 1.959349593495935e-05,
      "loss": 1.9107,
      "step": 10
    },
    {
      "epoch": 0.08130081300813008,
      "grad_norm": 4.806931495666504,
      "learning_rate": 1.91869918699187e-05,
      "loss": 1.793,
      "step": 20
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 5.768178939819336,
      "learning_rate": 1.878048780487805e-05,
      "loss": 1.6268,
      "step": 30
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 6.002701759338379,
      "learning_rate": 1.83739837398374e-05,
      "loss": 1.5186,
      "step": 40
    },
    {
      "epoch": 0.2032520325203252,
      "grad_norm": 5.8298115730285645,
      "learning_rate": 1.796747967479675e-05,
      "loss": 1.3802,
      "step": 50
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 5.422698020935059,
      "learning_rate": 1.75609756097561e-05,
      "loss": 1.3176,
      "step": 60
    },
    {
      "epoch": 0.2845528455284553,
      "grad_norm": 7.105832099914551,
      "learning_rate": 1.7154471544715447e-05,
      "loss": 1.1553,
      "step": 70
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 6.3010101318359375,
      "learning_rate": 1.6747967479674798e-05,
      "loss": 1.209,
      "step": 80
    },
    {
      "epoch": 0.36585365853658536,
      "grad_norm": 5.355374813079834,
      "learning_rate": 1.6341463414634145e-05,
      "loss": 1.1115,
      "step": 90
    },
    {
      "epoch": 0.4065040650406504,
      "grad_norm": 8.652898788452148,
      "learning_rate": 1.5934959349593496e-05,
      "loss": 1.2678,
      "step": 100
    },
    {
      "epoch": 0.4065040650406504,
      "eval_f1": 0.6317862490710497,
      "eval_loss": 1.1097809076309204,
      "eval_runtime": 30.8532,
      "eval_samples_per_second": 109.097,
      "eval_steps_per_second": 3.436,
      "step": 100
    },
    {
      "epoch": 0.44715447154471544,
      "grad_norm": 5.56029748916626,
      "learning_rate": 1.5528455284552847e-05,
      "loss": 1.2245,
      "step": 110
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 5.553459644317627,
      "learning_rate": 1.5121951219512196e-05,
      "loss": 1.0607,
      "step": 120
    },
    {
      "epoch": 0.5284552845528455,
      "grad_norm": 6.536402702331543,
      "learning_rate": 1.4715447154471545e-05,
      "loss": 1.1759,
      "step": 130
    },
    {
      "epoch": 0.5691056910569106,
      "grad_norm": 5.6078200340271,
      "learning_rate": 1.4308943089430896e-05,
      "loss": 1.0878,
      "step": 140
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 7.2565789222717285,
      "learning_rate": 1.3902439024390244e-05,
      "loss": 1.1789,
      "step": 150
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 6.567378520965576,
      "learning_rate": 1.3495934959349594e-05,
      "loss": 1.1621,
      "step": 160
    },
    {
      "epoch": 0.6910569105691057,
      "grad_norm": 6.680911064147949,
      "learning_rate": 1.3089430894308943e-05,
      "loss": 1.0317,
      "step": 170
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 5.503971576690674,
      "learning_rate": 1.2682926829268294e-05,
      "loss": 1.2348,
      "step": 180
    },
    {
      "epoch": 0.7723577235772358,
      "grad_norm": 5.242718696594238,
      "learning_rate": 1.2276422764227642e-05,
      "loss": 1.0482,
      "step": 190
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 5.709949016571045,
      "learning_rate": 1.1869918699186992e-05,
      "loss": 1.0018,
      "step": 200
    },
    {
      "epoch": 0.8130081300813008,
      "eval_f1": 0.6788360267939961,
      "eval_loss": 0.9953919649124146,
      "eval_runtime": 30.8775,
      "eval_samples_per_second": 109.011,
      "eval_steps_per_second": 3.433,
      "step": 200
    },
    {
      "epoch": 0.8536585365853658,
      "grad_norm": 6.952666759490967,
      "learning_rate": 1.1463414634146342e-05,
      "loss": 1.0277,
      "step": 210
    },
    {
      "epoch": 0.8943089430894309,
      "grad_norm": 8.080061912536621,
      "learning_rate": 1.1056910569105692e-05,
      "loss": 0.9702,
      "step": 220
    },
    {
      "epoch": 0.9349593495934959,
      "grad_norm": 6.3944549560546875,
      "learning_rate": 1.065040650406504e-05,
      "loss": 1.0117,
      "step": 230
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 6.3046488761901855,
      "learning_rate": 1.024390243902439e-05,
      "loss": 1.1426,
      "step": 240
    },
    {
      "epoch": 1.016260162601626,
      "grad_norm": 5.248263835906982,
      "learning_rate": 9.837398373983741e-06,
      "loss": 0.9627,
      "step": 250
    },
    {
      "epoch": 1.056910569105691,
      "grad_norm": 7.71372127532959,
      "learning_rate": 9.43089430894309e-06,
      "loss": 0.9348,
      "step": 260
    },
    {
      "epoch": 1.0975609756097562,
      "grad_norm": 9.51766586303711,
      "learning_rate": 9.02439024390244e-06,
      "loss": 0.9111,
      "step": 270
    },
    {
      "epoch": 1.1382113821138211,
      "grad_norm": 5.655633926391602,
      "learning_rate": 8.617886178861789e-06,
      "loss": 0.8609,
      "step": 280
    },
    {
      "epoch": 1.1788617886178863,
      "grad_norm": 7.609259128570557,
      "learning_rate": 8.21138211382114e-06,
      "loss": 0.8905,
      "step": 290
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": 5.490593433380127,
      "learning_rate": 7.804878048780489e-06,
      "loss": 0.7554,
      "step": 300
    },
    {
      "epoch": 1.2195121951219512,
      "eval_f1": 0.6839676640367311,
      "eval_loss": 0.9506719708442688,
      "eval_runtime": 30.8566,
      "eval_samples_per_second": 109.085,
      "eval_steps_per_second": 3.435,
      "step": 300
    },
    {
      "epoch": 1.2601626016260163,
      "grad_norm": 10.015968322753906,
      "learning_rate": 7.398373983739838e-06,
      "loss": 0.9043,
      "step": 310
    },
    {
      "epoch": 1.3008130081300813,
      "grad_norm": 7.634036064147949,
      "learning_rate": 6.991869918699188e-06,
      "loss": 0.8676,
      "step": 320
    },
    {
      "epoch": 1.3414634146341464,
      "grad_norm": 5.928556442260742,
      "learning_rate": 6.585365853658538e-06,
      "loss": 0.9127,
      "step": 330
    },
    {
      "epoch": 1.3821138211382114,
      "grad_norm": 6.368280410766602,
      "learning_rate": 6.178861788617887e-06,
      "loss": 0.9316,
      "step": 340
    },
    {
      "epoch": 1.4227642276422765,
      "grad_norm": 6.322418212890625,
      "learning_rate": 5.772357723577237e-06,
      "loss": 0.8273,
      "step": 350
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 7.215012550354004,
      "learning_rate": 5.365853658536586e-06,
      "loss": 0.8814,
      "step": 360
    },
    {
      "epoch": 1.5040650406504064,
      "grad_norm": 5.894520282745361,
      "learning_rate": 4.959349593495935e-06,
      "loss": 0.8295,
      "step": 370
    },
    {
      "epoch": 1.5447154471544715,
      "grad_norm": 6.685314178466797,
      "learning_rate": 4.552845528455285e-06,
      "loss": 0.8727,
      "step": 380
    },
    {
      "epoch": 1.5853658536585367,
      "grad_norm": 8.929649353027344,
      "learning_rate": 4.146341463414634e-06,
      "loss": 0.8012,
      "step": 390
    },
    {
      "epoch": 1.6260162601626016,
      "grad_norm": 8.644834518432617,
      "learning_rate": 3.7398373983739838e-06,
      "loss": 0.8151,
      "step": 400
    },
    {
      "epoch": 1.6260162601626016,
      "eval_f1": 0.7058091506789402,
      "eval_loss": 0.9088509678840637,
      "eval_runtime": 30.8562,
      "eval_samples_per_second": 109.087,
      "eval_steps_per_second": 3.435,
      "step": 400
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 7.286980628967285,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.8603,
      "step": 410
    },
    {
      "epoch": 1.7073170731707317,
      "grad_norm": 7.062027454376221,
      "learning_rate": 2.926829268292683e-06,
      "loss": 0.8243,
      "step": 420
    },
    {
      "epoch": 1.7479674796747968,
      "grad_norm": 6.453483581542969,
      "learning_rate": 2.5203252032520324e-06,
      "loss": 0.8328,
      "step": 430
    },
    {
      "epoch": 1.7886178861788617,
      "grad_norm": 6.350010395050049,
      "learning_rate": 2.1138211382113824e-06,
      "loss": 0.8307,
      "step": 440
    },
    {
      "epoch": 1.8292682926829267,
      "grad_norm": 11.967658042907715,
      "learning_rate": 1.707317073170732e-06,
      "loss": 0.8335,
      "step": 450
    },
    {
      "epoch": 1.8699186991869918,
      "grad_norm": 7.773582935333252,
      "learning_rate": 1.3008130081300815e-06,
      "loss": 0.7627,
      "step": 460
    },
    {
      "epoch": 1.910569105691057,
      "grad_norm": 8.230002403259277,
      "learning_rate": 8.94308943089431e-07,
      "loss": 0.7758,
      "step": 470
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 5.672370910644531,
      "learning_rate": 4.878048780487805e-07,
      "loss": 0.8621,
      "step": 480
    },
    {
      "epoch": 1.9918699186991868,
      "grad_norm": 9.773723602294922,
      "learning_rate": 8.130081300813009e-08,
      "loss": 0.8322,
      "step": 490
    }
  ],
  "logging_steps": 10,
  "max_steps": 492,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4131555260774400.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}