{
  "best_metric": 0.019755465909838676,
  "best_model_checkpoint": "influence-longformer/checkpoint-1995",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1995,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03759398496240601,
      "grad_norm": 1.6022701263427734,
      "learning_rate": 4.229323308270677e-06,
      "loss": 0.1482,
      "step": 25
    },
    {
      "epoch": 0.07518796992481203,
      "grad_norm": 2.4601035118103027,
      "learning_rate": 8.458646616541353e-06,
      "loss": 0.0555,
      "step": 50
    },
    {
      "epoch": 0.11278195488721804,
      "grad_norm": 0.42991551756858826,
      "learning_rate": 1.2687969924812032e-05,
      "loss": 0.038,
      "step": 75
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 1.5615288019180298,
      "learning_rate": 1.6917293233082707e-05,
      "loss": 0.0332,
      "step": 100
    },
    {
      "epoch": 0.18796992481203006,
      "grad_norm": 1.0025038719177246,
      "learning_rate": 2.1146616541353385e-05,
      "loss": 0.0334,
      "step": 125
    },
    {
      "epoch": 0.22556390977443608,
      "grad_norm": 0.8407266736030579,
      "learning_rate": 2.5375939849624064e-05,
      "loss": 0.0291,
      "step": 150
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 2.030592441558838,
      "learning_rate": 2.9605263157894742e-05,
      "loss": 0.031,
      "step": 175
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.8694236278533936,
      "learning_rate": 3.3834586466165414e-05,
      "loss": 0.0312,
      "step": 200
    },
    {
      "epoch": 0.3383458646616541,
      "grad_norm": 0.6539453268051147,
      "learning_rate": 3.806390977443609e-05,
      "loss": 0.0282,
      "step": 225
    },
    {
      "epoch": 0.37593984962406013,
      "grad_norm": 1.2007642984390259,
      "learning_rate": 4.229323308270677e-05,
      "loss": 0.0281,
      "step": 250
    },
    {
      "epoch": 0.41353383458646614,
      "grad_norm": 0.33443132042884827,
      "learning_rate": 4.4830827067669176e-05,
      "loss": 0.0295,
      "step": 275
    },
    {
      "epoch": 0.45112781954887216,
      "grad_norm": 1.085522174835205,
      "learning_rate": 4.43609022556391e-05,
      "loss": 0.027,
      "step": 300
    },
    {
      "epoch": 0.48872180451127817,
      "grad_norm": 0.7158887982368469,
      "learning_rate": 4.3890977443609024e-05,
      "loss": 0.0264,
      "step": 325
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.23328174650669098,
      "learning_rate": 4.342105263157895e-05,
      "loss": 0.0259,
      "step": 350
    },
    {
      "epoch": 0.5639097744360902,
      "grad_norm": 0.4180866777896881,
      "learning_rate": 4.295112781954887e-05,
      "loss": 0.0265,
      "step": 375
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 0.2783370018005371,
      "learning_rate": 4.24812030075188e-05,
      "loss": 0.0264,
      "step": 400
    },
    {
      "epoch": 0.6390977443609023,
      "grad_norm": 1.226720929145813,
      "learning_rate": 4.201127819548873e-05,
      "loss": 0.0252,
      "step": 425
    },
    {
      "epoch": 0.6766917293233082,
      "grad_norm": 0.7401314973831177,
      "learning_rate": 4.154135338345865e-05,
      "loss": 0.0275,
      "step": 450
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.986824631690979,
      "learning_rate": 4.107142857142857e-05,
      "loss": 0.0279,
      "step": 475
    },
    {
      "epoch": 0.7518796992481203,
      "grad_norm": 0.8208933472633362,
      "learning_rate": 4.0601503759398494e-05,
      "loss": 0.0268,
      "step": 500
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.4981847405433655,
      "learning_rate": 4.0131578947368425e-05,
      "loss": 0.025,
      "step": 525
    },
    {
      "epoch": 0.8270676691729323,
      "grad_norm": 0.2331264764070511,
      "learning_rate": 3.966165413533835e-05,
      "loss": 0.0245,
      "step": 550
    },
    {
      "epoch": 0.8646616541353384,
      "grad_norm": 0.8994643092155457,
      "learning_rate": 3.9191729323308274e-05,
      "loss": 0.0258,
      "step": 575
    },
    {
      "epoch": 0.9022556390977443,
      "grad_norm": 0.1817372441291809,
      "learning_rate": 3.87218045112782e-05,
      "loss": 0.0251,
      "step": 600
    },
    {
      "epoch": 0.9398496240601504,
      "grad_norm": 0.5260267853736877,
      "learning_rate": 3.825187969924812e-05,
      "loss": 0.0251,
      "step": 625
    },
    {
      "epoch": 0.9774436090225563,
      "grad_norm": 0.4542248547077179,
      "learning_rate": 3.780075187969925e-05,
      "loss": 0.0239,
      "step": 650
    },
    {
      "epoch": 1.0,
      "eval_explained_variance": 0.28540539741516113,
      "eval_loss": 0.02087027207016945,
      "eval_mae": 0.11132633686065674,
      "eval_mse": 0.020866233855485916,
      "eval_r2": 0.2827957272529602,
      "eval_rmse": 0.14445149308846175,
      "eval_runtime": 333.1624,
      "eval_samples_per_second": 63.858,
      "eval_steps_per_second": 1.0,
      "step": 665
    },
    {
      "epoch": 1.0150375939849625,
      "grad_norm": 0.3731153607368469,
      "learning_rate": 3.7330827067669176e-05,
      "loss": 0.0238,
      "step": 675
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.5566776990890503,
      "learning_rate": 3.68609022556391e-05,
      "loss": 0.0237,
      "step": 700
    },
    {
      "epoch": 1.0902255639097744,
      "grad_norm": 0.7956374287605286,
      "learning_rate": 3.6390977443609025e-05,
      "loss": 0.0231,
      "step": 725
    },
    {
      "epoch": 1.1278195488721805,
      "grad_norm": 0.40257030725479126,
      "learning_rate": 3.592105263157895e-05,
      "loss": 0.0231,
      "step": 750
    },
    {
      "epoch": 1.1654135338345863,
      "grad_norm": 0.20914725959300995,
      "learning_rate": 3.5451127819548873e-05,
      "loss": 0.0245,
      "step": 775
    },
    {
      "epoch": 1.2030075187969924,
      "grad_norm": 0.20414456725120544,
      "learning_rate": 3.49812030075188e-05,
      "loss": 0.0235,
      "step": 800
    },
    {
      "epoch": 1.2406015037593985,
      "grad_norm": 0.5779170393943787,
      "learning_rate": 3.451127819548872e-05,
      "loss": 0.0238,
      "step": 825
    },
    {
      "epoch": 1.2781954887218046,
      "grad_norm": 0.9034671783447266,
      "learning_rate": 3.404135338345865e-05,
      "loss": 0.0237,
      "step": 850
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 0.2771829068660736,
      "learning_rate": 3.357142857142858e-05,
      "loss": 0.0225,
      "step": 875
    },
    {
      "epoch": 1.3533834586466165,
      "grad_norm": 0.5990172028541565,
      "learning_rate": 3.3101503759398495e-05,
      "loss": 0.024,
      "step": 900
    },
    {
      "epoch": 1.3909774436090225,
      "grad_norm": 0.6648531556129456,
      "learning_rate": 3.263157894736842e-05,
      "loss": 0.0229,
      "step": 925
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.2648594379425049,
      "learning_rate": 3.216165413533835e-05,
      "loss": 0.0224,
      "step": 950
    },
    {
      "epoch": 1.4661654135338344,
      "grad_norm": 0.26627054810523987,
      "learning_rate": 3.1691729323308274e-05,
      "loss": 0.0242,
      "step": 975
    },
    {
      "epoch": 1.5037593984962405,
      "grad_norm": 0.5062589645385742,
      "learning_rate": 3.12218045112782e-05,
      "loss": 0.0223,
      "step": 1000
    },
    {
      "epoch": 1.5413533834586466,
      "grad_norm": 0.21417106688022614,
      "learning_rate": 3.075187969924812e-05,
      "loss": 0.0218,
      "step": 1025
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 0.9766432046890259,
      "learning_rate": 3.028195488721805e-05,
      "loss": 0.023,
      "step": 1050
    },
    {
      "epoch": 1.6165413533834587,
      "grad_norm": 0.17392820119857788,
      "learning_rate": 2.981203007518797e-05,
      "loss": 0.023,
      "step": 1075
    },
    {
      "epoch": 1.6541353383458648,
      "grad_norm": 0.23946884274482727,
      "learning_rate": 2.9342105263157895e-05,
      "loss": 0.0218,
      "step": 1100
    },
    {
      "epoch": 1.6917293233082706,
      "grad_norm": 0.3760274648666382,
      "learning_rate": 2.887218045112782e-05,
      "loss": 0.0226,
      "step": 1125
    },
    {
      "epoch": 1.7293233082706767,
      "grad_norm": 0.3618028461933136,
      "learning_rate": 2.8402255639097747e-05,
      "loss": 0.0215,
      "step": 1150
    },
    {
      "epoch": 1.7669172932330826,
      "grad_norm": 0.24896082282066345,
      "learning_rate": 2.793233082706767e-05,
      "loss": 0.0218,
      "step": 1175
    },
    {
      "epoch": 1.8045112781954886,
      "grad_norm": 0.9801834225654602,
      "learning_rate": 2.7462406015037596e-05,
      "loss": 0.0222,
      "step": 1200
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 0.2100023478269577,
      "learning_rate": 2.699248120300752e-05,
      "loss": 0.024,
      "step": 1225
    },
    {
      "epoch": 1.8796992481203008,
      "grad_norm": 0.4694213569164276,
      "learning_rate": 2.6522556390977448e-05,
      "loss": 0.0221,
      "step": 1250
    },
    {
      "epoch": 1.9172932330827068,
      "grad_norm": 0.5287728309631348,
      "learning_rate": 2.6052631578947372e-05,
      "loss": 0.0223,
      "step": 1275
    },
    {
      "epoch": 1.954887218045113,
      "grad_norm": 1.2186554670333862,
      "learning_rate": 2.5582706766917296e-05,
      "loss": 0.0221,
      "step": 1300
    },
    {
      "epoch": 1.9924812030075187,
      "grad_norm": 0.18354646861553192,
      "learning_rate": 2.5112781954887217e-05,
      "loss": 0.0222,
      "step": 1325
    },
    {
      "epoch": 2.0,
      "eval_explained_variance": 0.3022691607475281,
      "eval_loss": 0.02030428871512413,
      "eval_mae": 0.11059005558490753,
      "eval_mse": 0.020300239324569702,
      "eval_r2": 0.3022497892379761,
      "eval_rmse": 0.14247890834986665,
      "eval_runtime": 332.2379,
      "eval_samples_per_second": 64.035,
      "eval_steps_per_second": 1.002,
      "step": 1330
    },
    {
      "epoch": 2.030075187969925,
      "grad_norm": 0.13428334891796112,
      "learning_rate": 2.4642857142857148e-05,
      "loss": 0.0212,
      "step": 1350
    },
    {
      "epoch": 2.0676691729323307,
      "grad_norm": 0.31226059794425964,
      "learning_rate": 2.417293233082707e-05,
      "loss": 0.0211,
      "step": 1375
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.3287919759750366,
      "learning_rate": 2.3703007518796993e-05,
      "loss": 0.022,
      "step": 1400
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.43540850281715393,
      "learning_rate": 2.3233082706766917e-05,
      "loss": 0.0213,
      "step": 1425
    },
    {
      "epoch": 2.180451127819549,
      "grad_norm": 0.25581884384155273,
      "learning_rate": 2.2763157894736845e-05,
      "loss": 0.0205,
      "step": 1450
    },
    {
      "epoch": 2.218045112781955,
      "grad_norm": 0.45723602175712585,
      "learning_rate": 2.2293233082706766e-05,
      "loss": 0.021,
      "step": 1475
    },
    {
      "epoch": 2.255639097744361,
      "grad_norm": 0.5476940274238586,
      "learning_rate": 2.1823308270676693e-05,
      "loss": 0.0212,
      "step": 1500
    },
    {
      "epoch": 2.293233082706767,
      "grad_norm": 0.1626814901828766,
      "learning_rate": 2.1353383458646618e-05,
      "loss": 0.021,
      "step": 1525
    },
    {
      "epoch": 2.3308270676691727,
      "grad_norm": 0.29517662525177,
      "learning_rate": 2.0883458646616542e-05,
      "loss": 0.0204,
      "step": 1550
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 0.6911824345588684,
      "learning_rate": 2.0413533834586466e-05,
      "loss": 0.0203,
      "step": 1575
    },
    {
      "epoch": 2.406015037593985,
      "grad_norm": 0.42551133036613464,
      "learning_rate": 1.9943609022556394e-05,
      "loss": 0.02,
      "step": 1600
    },
    {
      "epoch": 2.443609022556391,
      "grad_norm": 0.44191497564315796,
      "learning_rate": 1.9473684210526315e-05,
      "loss": 0.0206,
      "step": 1625
    },
    {
      "epoch": 2.481203007518797,
      "grad_norm": 0.853766143321991,
      "learning_rate": 1.9003759398496242e-05,
      "loss": 0.0209,
      "step": 1650
    },
    {
      "epoch": 2.518796992481203,
      "grad_norm": 1.0731028318405151,
      "learning_rate": 1.8533834586466166e-05,
      "loss": 0.0212,
      "step": 1675
    },
    {
      "epoch": 2.556390977443609,
      "grad_norm": 0.3144964575767517,
      "learning_rate": 1.806390977443609e-05,
      "loss": 0.021,
      "step": 1700
    },
    {
      "epoch": 2.593984962406015,
      "grad_norm": 0.3022163212299347,
      "learning_rate": 1.7593984962406015e-05,
      "loss": 0.0216,
      "step": 1725
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 0.45970025658607483,
      "learning_rate": 1.7124060150375943e-05,
      "loss": 0.0204,
      "step": 1750
    },
    {
      "epoch": 2.6691729323308273,
      "grad_norm": 0.2722722291946411,
      "learning_rate": 1.6654135338345863e-05,
      "loss": 0.021,
      "step": 1775
    },
    {
      "epoch": 2.706766917293233,
      "grad_norm": 0.24549676477909088,
      "learning_rate": 1.618421052631579e-05,
      "loss": 0.0207,
      "step": 1800
    },
    {
      "epoch": 2.744360902255639,
      "grad_norm": 0.28373944759368896,
      "learning_rate": 1.5714285714285715e-05,
      "loss": 0.0204,
      "step": 1825
    },
    {
      "epoch": 2.781954887218045,
      "grad_norm": 0.47003814578056335,
      "learning_rate": 1.5244360902255641e-05,
      "loss": 0.0207,
      "step": 1850
    },
    {
      "epoch": 2.819548872180451,
      "grad_norm": 0.967040479183197,
      "learning_rate": 1.4774436090225564e-05,
      "loss": 0.0215,
      "step": 1875
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.46782004833221436,
      "learning_rate": 1.430451127819549e-05,
      "loss": 0.0217,
      "step": 1900
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 0.5362545251846313,
      "learning_rate": 1.3834586466165414e-05,
      "loss": 0.0211,
      "step": 1925
    },
    {
      "epoch": 2.932330827067669,
      "grad_norm": 0.25926506519317627,
      "learning_rate": 1.336466165413534e-05,
      "loss": 0.0204,
      "step": 1950
    },
    {
      "epoch": 2.969924812030075,
      "grad_norm": 0.44383227825164795,
      "learning_rate": 1.2894736842105262e-05,
      "loss": 0.0204,
      "step": 1975
    },
    {
      "epoch": 3.0,
      "eval_explained_variance": 0.32502323389053345,
      "eval_loss": 0.019755465909838676,
      "eval_mae": 0.11072802543640137,
      "eval_mse": 0.019751867279410362,
      "eval_r2": 0.3210982084274292,
      "eval_rmse": 0.14054133655053364,
      "eval_runtime": 333.2303,
      "eval_samples_per_second": 63.845,
      "eval_steps_per_second": 0.999,
      "step": 1995
    }
  ],
  "logging_steps": 25,
  "max_steps": 2660,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.709296778916659e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}