{
  "best_global_step": 4000,
  "best_metric": 0.6931638121604919,
  "best_model_checkpoint": "/content/drive/MyDrive/PolyGuard/model_final/checkpoint-4000",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 8000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025,
      "grad_norm": 4.840836524963379,
      "learning_rate": 2.4750000000000002e-05,
      "loss": 0.6476753997802734,
      "step": 100
    },
    {
      "epoch": 0.05,
      "grad_norm": 3.3573901653289795,
      "learning_rate": 4.975e-05,
      "loss": 0.6003963470458984,
      "step": 200
    },
    {
      "epoch": 0.075,
      "grad_norm": 5.3957953453063965,
      "learning_rate": 4.96867088607595e-05,
      "loss": 0.5752050399780273,
      "step": 300
    },
    {
      "epoch": 0.1,
      "grad_norm": 6.348972797393799,
      "learning_rate": 4.937025316455696e-05,
      "loss": 0.5668778610229492,
      "step": 400
    },
    {
      "epoch": 0.125,
      "grad_norm": 3.777247428894043,
      "learning_rate": 4.905379746835443e-05,
      "loss": 0.6448370361328125,
      "step": 500
    },
    {
      "epoch": 0.15,
      "grad_norm": 5.974273204803467,
      "learning_rate": 4.87373417721519e-05,
      "loss": 0.5914559173583984,
      "step": 600
    },
    {
      "epoch": 0.175,
      "grad_norm": 5.3988165855407715,
      "learning_rate": 4.842088607594937e-05,
      "loss": 0.6363700103759765,
      "step": 700
    },
    {
      "epoch": 0.2,
      "grad_norm": 2.299058675765991,
      "learning_rate": 4.810443037974684e-05,
      "loss": 0.5667419815063477,
      "step": 800
    },
    {
      "epoch": 0.225,
      "grad_norm": 3.1783978939056396,
      "learning_rate": 4.7787974683544305e-05,
      "loss": 0.5284980392456055,
      "step": 900
    },
    {
      "epoch": 0.25,
      "grad_norm": 3.9692907333374023,
      "learning_rate": 4.747151898734177e-05,
      "loss": 0.56060546875,
      "step": 1000
    },
    {
      "epoch": 0.275,
      "grad_norm": 2.46657657623291,
      "learning_rate": 4.715506329113925e-05,
      "loss": 0.5778974151611328,
      "step": 1100
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.4161385297775269,
      "learning_rate": 4.683860759493671e-05,
      "loss": 0.5550444412231446,
      "step": 1200
    },
    {
      "epoch": 0.325,
      "grad_norm": 6.127955436706543,
      "learning_rate": 4.652215189873418e-05,
      "loss": 0.638050308227539,
      "step": 1300
    },
    {
      "epoch": 0.35,
      "grad_norm": 2.9411966800689697,
      "learning_rate": 4.620569620253164e-05,
      "loss": 0.5464860153198242,
      "step": 1400
    },
    {
      "epoch": 0.375,
      "grad_norm": 5.668337345123291,
      "learning_rate": 4.588924050632912e-05,
      "loss": 0.6324460220336914,
      "step": 1500
    },
    {
      "epoch": 0.4,
      "grad_norm": 5.304285049438477,
      "learning_rate": 4.5572784810126585e-05,
      "loss": 0.5795536041259766,
      "step": 1600
    },
    {
      "epoch": 0.425,
      "grad_norm": 1.6371102333068848,
      "learning_rate": 4.525632911392405e-05,
      "loss": 0.5774750137329101,
      "step": 1700
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.4340555667877197,
      "learning_rate": 4.493987341772152e-05,
      "loss": 0.6004017257690429,
      "step": 1800
    },
    {
      "epoch": 0.475,
      "grad_norm": 2.997642755508423,
      "learning_rate": 4.462341772151899e-05,
      "loss": 0.6037093734741211,
      "step": 1900
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.124809741973877,
      "learning_rate": 4.430696202531646e-05,
      "loss": 0.5478248596191406,
      "step": 2000
    },
    {
      "epoch": 0.525,
      "grad_norm": 1.4012881517410278,
      "learning_rate": 4.399050632911393e-05,
      "loss": 0.5746703720092774,
      "step": 2100
    },
    {
      "epoch": 0.55,
      "grad_norm": 2.774062395095825,
      "learning_rate": 4.367405063291139e-05,
      "loss": 0.5518299865722657,
      "step": 2200
    },
    {
      "epoch": 0.575,
      "grad_norm": 0.9460004568099976,
      "learning_rate": 4.3357594936708864e-05,
      "loss": 0.5653076553344727,
      "step": 2300
    },
    {
      "epoch": 0.6,
      "grad_norm": 4.564599514007568,
      "learning_rate": 4.304113924050633e-05,
      "loss": 0.626568832397461,
      "step": 2400
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.9103949666023254,
      "learning_rate": 4.27246835443038e-05,
      "loss": 0.5939551544189453,
      "step": 2500
    },
    {
      "epoch": 0.65,
      "grad_norm": 3.449150800704956,
      "learning_rate": 4.2408227848101265e-05,
      "loss": 0.5971554946899414,
      "step": 2600
    },
    {
      "epoch": 0.675,
      "grad_norm": 3.5549769401550293,
      "learning_rate": 4.2091772151898736e-05,
      "loss": 0.5751391983032227,
      "step": 2700
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.6542292833328247,
      "learning_rate": 4.177531645569621e-05,
      "loss": 0.5986330032348632,
      "step": 2800
    },
    {
      "epoch": 0.725,
      "grad_norm": 1.3074430227279663,
      "learning_rate": 4.145886075949367e-05,
      "loss": 0.5717515182495118,
      "step": 2900
    },
    {
      "epoch": 0.75,
      "grad_norm": 3.095973014831543,
      "learning_rate": 4.114240506329114e-05,
      "loss": 0.5813043594360352,
      "step": 3000
    },
    {
      "epoch": 0.775,
      "grad_norm": 2.611328363418579,
      "learning_rate": 4.0825949367088615e-05,
      "loss": 0.6051469039916992,
      "step": 3100
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.4239795207977295,
      "learning_rate": 4.050949367088608e-05,
      "loss": 0.5933720779418945,
      "step": 3200
    },
    {
      "epoch": 0.825,
      "grad_norm": 1.3653069734573364,
      "learning_rate": 4.0193037974683544e-05,
      "loss": 0.5751293182373047,
      "step": 3300
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.4362722635269165,
      "learning_rate": 3.9876582278481015e-05,
      "loss": 0.5673767852783204,
      "step": 3400
    },
    {
      "epoch": 0.875,
      "grad_norm": 1.1265358924865723,
      "learning_rate": 3.956012658227849e-05,
      "loss": 0.6048561477661133,
      "step": 3500
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.3712810277938843,
      "learning_rate": 3.924367088607595e-05,
      "loss": 0.6653845977783203,
      "step": 3600
    },
    {
      "epoch": 0.925,
      "grad_norm": 1.213412880897522,
      "learning_rate": 3.8927215189873416e-05,
      "loss": 0.6943452453613281,
      "step": 3700
    },
    {
      "epoch": 0.95,
      "grad_norm": 2.019483804702759,
      "learning_rate": 3.861075949367089e-05,
      "loss": 0.6974296569824219,
      "step": 3800
    },
    {
      "epoch": 0.975,
      "grad_norm": 1.273471713066101,
      "learning_rate": 3.829430379746836e-05,
      "loss": 0.706220474243164,
      "step": 3900
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.3656868934631348,
      "learning_rate": 3.7977848101265823e-05,
      "loss": 0.702726058959961,
      "step": 4000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6931638121604919,
      "eval_runtime": 166.9577,
      "eval_samples_per_second": 47.916,
      "eval_steps_per_second": 5.99,
      "step": 4000
    },
    {
      "epoch": 1.025,
      "grad_norm": 1.4108144044876099,
      "learning_rate": 3.7661392405063295e-05,
      "loss": 0.6999430847167969,
      "step": 4100
    },
    {
      "epoch": 1.05,
      "grad_norm": 2.259119987487793,
      "learning_rate": 3.734493670886076e-05,
      "loss": 0.7005876922607421,
      "step": 4200
    },
    {
      "epoch": 1.075,
      "grad_norm": 0.8190616965293884,
      "learning_rate": 3.702848101265823e-05,
      "loss": 0.6983786010742188,
      "step": 4300
    },
    {
      "epoch": 1.1,
      "grad_norm": 1.3949053287506104,
      "learning_rate": 3.67120253164557e-05,
      "loss": 0.6970309448242188,
      "step": 4400
    },
    {
      "epoch": 1.125,
      "grad_norm": 1.9007196426391602,
      "learning_rate": 3.639556962025317e-05,
      "loss": 0.7024803161621094,
      "step": 4500
    },
    {
      "epoch": 1.15,
      "grad_norm": 3.2963850498199463,
      "learning_rate": 3.607911392405063e-05,
      "loss": 0.6969153594970703,
      "step": 4600
    },
    {
      "epoch": 1.175,
      "grad_norm": 2.8197951316833496,
      "learning_rate": 3.57626582278481e-05,
      "loss": 0.6913418579101562,
      "step": 4700
    },
    {
      "epoch": 1.2,
      "grad_norm": 3.7260422706604004,
      "learning_rate": 3.5446202531645574e-05,
      "loss": 0.6954251098632812,
      "step": 4800
    },
    {
      "epoch": 1.225,
      "grad_norm": 2.538835048675537,
      "learning_rate": 3.512974683544304e-05,
      "loss": 0.7016423797607422,
      "step": 4900
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.9548262357711792,
      "learning_rate": 3.48132911392405e-05,
      "loss": 0.6976743316650391,
      "step": 5000
    },
    {
      "epoch": 1.275,
      "grad_norm": 4.0937180519104,
      "learning_rate": 3.4496835443037975e-05,
      "loss": 0.700084228515625,
      "step": 5100
    },
    {
      "epoch": 1.3,
      "grad_norm": 2.521569013595581,
      "learning_rate": 3.4180379746835446e-05,
      "loss": 0.6976382446289062,
      "step": 5200
    },
    {
      "epoch": 1.325,
      "grad_norm": 4.047502517700195,
      "learning_rate": 3.386392405063291e-05,
      "loss": 0.6967656707763672,
      "step": 5300
    },
    {
      "epoch": 1.35,
      "grad_norm": 3.4342639446258545,
      "learning_rate": 3.354746835443038e-05,
      "loss": 0.6955546569824219,
      "step": 5400
    },
    {
      "epoch": 1.375,
      "grad_norm": 1.5393496751785278,
      "learning_rate": 3.3231012658227854e-05,
      "loss": 0.6965518951416015,
      "step": 5500
    },
    {
      "epoch": 1.4,
      "grad_norm": 4.321380138397217,
      "learning_rate": 3.291455696202532e-05,
      "loss": 0.6958496856689453,
      "step": 5600
    },
    {
      "epoch": 1.425,
      "grad_norm": 1.1191785335540771,
      "learning_rate": 3.259810126582279e-05,
      "loss": 0.6999098968505859,
      "step": 5700
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.8614036440849304,
      "learning_rate": 3.2281645569620254e-05,
      "loss": 0.6959712219238281,
      "step": 5800
    },
    {
      "epoch": 1.475,
      "grad_norm": 0.9664958715438843,
      "learning_rate": 3.1965189873417725e-05,
      "loss": 0.6925695037841797,
      "step": 5900
    },
    {
      "epoch": 1.5,
      "grad_norm": 2.1453211307525635,
      "learning_rate": 3.164873417721519e-05,
      "loss": 0.698175048828125,
      "step": 6000
    },
    {
      "epoch": 1.525,
      "grad_norm": 2.1440930366516113,
      "learning_rate": 3.133227848101266e-05,
      "loss": 0.682925796508789,
      "step": 6100
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.8990124464035034,
      "learning_rate": 3.1015822784810126e-05,
      "loss": 0.6517456817626953,
      "step": 6200
    },
    {
      "epoch": 1.575,
      "grad_norm": 1.3929342031478882,
      "learning_rate": 3.06993670886076e-05,
      "loss": 0.7006549835205078,
      "step": 6300
    },
    {
      "epoch": 1.6,
      "grad_norm": 2.1912875175476074,
      "learning_rate": 3.0382911392405065e-05,
      "loss": 0.6975661468505859,
      "step": 6400
    },
    {
      "epoch": 1.625,
      "grad_norm": 1.1694247722625732,
      "learning_rate": 3.0066455696202533e-05,
      "loss": 0.6955360412597656,
      "step": 6500
    },
    {
      "epoch": 1.65,
      "grad_norm": 3.340589761734009,
      "learning_rate": 2.975e-05,
      "loss": 0.7008393859863281,
      "step": 6600
    },
    {
      "epoch": 1.675,
      "grad_norm": 2.42465877532959,
      "learning_rate": 2.9433544303797473e-05,
      "loss": 0.6998232269287109,
      "step": 6700
    },
    {
      "epoch": 1.7,
      "grad_norm": 1.9139105081558228,
      "learning_rate": 2.9117088607594937e-05,
      "loss": 0.6989698028564453,
      "step": 6800
    },
    {
      "epoch": 1.725,
      "grad_norm": 0.7264005541801453,
      "learning_rate": 2.8800632911392405e-05,
      "loss": 0.6944959259033203,
      "step": 6900
    },
    {
      "epoch": 1.75,
      "grad_norm": 1.1322827339172363,
      "learning_rate": 2.8484177215189873e-05,
      "loss": 0.7098442840576172,
      "step": 7000
    },
    {
      "epoch": 1.775,
      "grad_norm": 2.150141477584839,
      "learning_rate": 2.8167721518987345e-05,
      "loss": 0.6946941375732422,
      "step": 7100
    },
    {
      "epoch": 1.8,
      "grad_norm": 1.850095510482788,
      "learning_rate": 2.785126582278481e-05,
      "loss": 0.6941130065917969,
      "step": 7200
    },
    {
      "epoch": 1.825,
      "grad_norm": 1.994320273399353,
      "learning_rate": 2.7534810126582277e-05,
      "loss": 0.6933687591552734,
      "step": 7300
    },
    {
      "epoch": 1.85,
      "grad_norm": 1.1272798776626587,
      "learning_rate": 2.721835443037975e-05,
      "loss": 0.7010916900634766,
      "step": 7400
    },
    {
      "epoch": 1.875,
      "grad_norm": 2.2662463188171387,
      "learning_rate": 2.6901898734177217e-05,
      "loss": 0.6951226806640625,
      "step": 7500
    },
    {
      "epoch": 1.9,
      "grad_norm": 2.8019468784332275,
      "learning_rate": 2.6585443037974685e-05,
      "loss": 0.6966998291015625,
      "step": 7600
    },
    {
      "epoch": 1.925,
      "grad_norm": 2.3949637413024902,
      "learning_rate": 2.6268987341772156e-05,
      "loss": 0.6956380462646484,
      "step": 7700
    },
    {
      "epoch": 1.95,
      "grad_norm": 2.5100715160369873,
      "learning_rate": 2.595253164556962e-05,
      "loss": 0.6968719482421875,
      "step": 7800
    },
    {
      "epoch": 1.975,
      "grad_norm": 6.460758209228516,
      "learning_rate": 2.563607594936709e-05,
      "loss": 0.692848892211914,
      "step": 7900
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.2004637718200684,
      "learning_rate": 2.5319620253164557e-05,
      "loss": 0.6972612762451171,
      "step": 8000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6932027339935303,
      "eval_runtime": 166.3088,
      "eval_samples_per_second": 48.103,
      "eval_steps_per_second": 6.013,
      "step": 8000
    }
  ],
  "logging_steps": 100,
  "max_steps": 16000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 8419553771520000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}