{
  "best_metric": 0.8721568627450981,
  "best_model_checkpoint": "./results/checkpoint-444",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 592,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 2.898142099380493,
      "learning_rate": 1.4898648648648649e-05,
      "loss": 1.2162,
      "step": 10
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 0.9556340575218201,
      "learning_rate": 1.4797297297297299e-05,
      "loss": 0.7314,
      "step": 20
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 1.6656218767166138,
      "learning_rate": 1.4695945945945946e-05,
      "loss": 0.596,
      "step": 30
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 0.9088318347930908,
      "learning_rate": 1.4594594594594596e-05,
      "loss": 0.4541,
      "step": 40
    },
    {
      "epoch": 0.33783783783783783,
      "grad_norm": 1.9701541662216187,
      "learning_rate": 1.4493243243243244e-05,
      "loss": 0.3396,
      "step": 50
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 2.7924790382385254,
      "learning_rate": 1.4391891891891892e-05,
      "loss": 0.2765,
      "step": 60
    },
    {
      "epoch": 0.47297297297297297,
      "grad_norm": 3.7695441246032715,
      "learning_rate": 1.429054054054054e-05,
      "loss": 0.2233,
      "step": 70
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 2.107003927230835,
      "learning_rate": 1.4189189189189189e-05,
      "loss": 0.1853,
      "step": 80
    },
    {
      "epoch": 0.6081081081081081,
      "grad_norm": 2.121389865875244,
      "learning_rate": 1.4087837837837838e-05,
      "loss": 0.1754,
      "step": 90
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 1.2353276014328003,
      "learning_rate": 1.3986486486486488e-05,
      "loss": 0.1681,
      "step": 100
    },
    {
      "epoch": 0.7432432432432432,
      "grad_norm": 1.7530581951141357,
      "learning_rate": 1.3885135135135136e-05,
      "loss": 0.1448,
      "step": 110
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 2.630220651626587,
      "learning_rate": 1.3783783783783784e-05,
      "loss": 0.1487,
      "step": 120
    },
    {
      "epoch": 0.8783783783783784,
      "grad_norm": 2.1581919193267822,
      "learning_rate": 1.3682432432432433e-05,
      "loss": 0.1203,
      "step": 130
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 1.465224027633667,
      "learning_rate": 1.3581081081081081e-05,
      "loss": 0.1196,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.8060747663551402,
      "eval_loss": 0.1058039739727974,
      "eval_precision": 0.7864741641337386,
      "eval_recall": 0.8266773162939297,
      "eval_runtime": 1.8909,
      "eval_samples_per_second": 311.49,
      "eval_steps_per_second": 19.567,
      "step": 148
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 1.859381914138794,
      "learning_rate": 1.3479729729729731e-05,
      "loss": 0.1077,
      "step": 150
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 1.1303757429122925,
      "learning_rate": 1.3378378378378378e-05,
      "loss": 0.0834,
      "step": 160
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 2.2320058345794678,
      "learning_rate": 1.3277027027027026e-05,
      "loss": 0.0806,
      "step": 170
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 2.2659084796905518,
      "learning_rate": 1.3175675675675676e-05,
      "loss": 0.1037,
      "step": 180
    },
    {
      "epoch": 1.2837837837837838,
      "grad_norm": 1.503485918045044,
      "learning_rate": 1.3074324324324325e-05,
      "loss": 0.0795,
      "step": 190
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 2.4358086585998535,
      "learning_rate": 1.2972972972972975e-05,
      "loss": 0.0843,
      "step": 200
    },
    {
      "epoch": 1.4189189189189189,
      "grad_norm": 2.3112075328826904,
      "learning_rate": 1.2871621621621622e-05,
      "loss": 0.0919,
      "step": 210
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 2.4183337688446045,
      "learning_rate": 1.277027027027027e-05,
      "loss": 0.1095,
      "step": 220
    },
    {
      "epoch": 1.554054054054054,
      "grad_norm": 2.2701897621154785,
      "learning_rate": 1.266891891891892e-05,
      "loss": 0.0814,
      "step": 230
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 1.8825066089630127,
      "learning_rate": 1.2567567567567568e-05,
      "loss": 0.0767,
      "step": 240
    },
    {
      "epoch": 1.689189189189189,
      "grad_norm": 1.3128814697265625,
      "learning_rate": 1.2466216216216215e-05,
      "loss": 0.0757,
      "step": 250
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 1.7098441123962402,
      "learning_rate": 1.2364864864864865e-05,
      "loss": 0.0628,
      "step": 260
    },
    {
      "epoch": 1.8243243243243243,
      "grad_norm": 2.450141191482544,
      "learning_rate": 1.2263513513513513e-05,
      "loss": 0.0714,
      "step": 270
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 0.9712327718734741,
      "learning_rate": 1.2162162162162164e-05,
      "loss": 0.065,
      "step": 280
    },
    {
      "epoch": 1.9594594594594594,
      "grad_norm": 1.2407033443450928,
      "learning_rate": 1.2060810810810812e-05,
      "loss": 0.0644,
      "step": 290
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.8542713567839195,
      "eval_loss": 0.09045273810625076,
      "eval_precision": 0.8277153558052435,
      "eval_recall": 0.8825878594249201,
      "eval_runtime": 1.8851,
      "eval_samples_per_second": 312.457,
      "eval_steps_per_second": 19.628,
      "step": 296
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 1.290103554725647,
      "learning_rate": 1.1959459459459459e-05,
      "loss": 0.0531,
      "step": 300
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 0.7347075343132019,
      "learning_rate": 1.1858108108108109e-05,
      "loss": 0.0342,
      "step": 310
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 1.7486129999160767,
      "learning_rate": 1.1756756756756757e-05,
      "loss": 0.0581,
      "step": 320
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 1.5185946226119995,
      "learning_rate": 1.1655405405405405e-05,
      "loss": 0.0442,
      "step": 330
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 0.46719256043434143,
      "learning_rate": 1.1554054054054054e-05,
      "loss": 0.0453,
      "step": 340
    },
    {
      "epoch": 2.364864864864865,
      "grad_norm": 1.4159014225006104,
      "learning_rate": 1.1452702702702702e-05,
      "loss": 0.0357,
      "step": 350
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 1.519043207168579,
      "learning_rate": 1.1351351351351352e-05,
      "loss": 0.0519,
      "step": 360
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.9069762825965881,
      "learning_rate": 1.125e-05,
      "loss": 0.0475,
      "step": 370
    },
    {
      "epoch": 2.5675675675675675,
      "grad_norm": 1.1645039319992065,
      "learning_rate": 1.1148648648648649e-05,
      "loss": 0.0523,
      "step": 380
    },
    {
      "epoch": 2.635135135135135,
      "grad_norm": 0.3658510744571686,
      "learning_rate": 1.1047297297297297e-05,
      "loss": 0.0421,
      "step": 390
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 2.1059019565582275,
      "learning_rate": 1.0945945945945946e-05,
      "loss": 0.0428,
      "step": 400
    },
    {
      "epoch": 2.77027027027027,
      "grad_norm": 1.0494921207427979,
      "learning_rate": 1.0844594594594596e-05,
      "loss": 0.0422,
      "step": 410
    },
    {
      "epoch": 2.8378378378378377,
      "grad_norm": 1.9335922002792358,
      "learning_rate": 1.0743243243243244e-05,
      "loss": 0.0525,
      "step": 420
    },
    {
      "epoch": 2.9054054054054053,
      "grad_norm": 2.4838504791259766,
      "learning_rate": 1.0641891891891891e-05,
      "loss": 0.054,
      "step": 430
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 0.15148599445819855,
      "learning_rate": 1.0540540540540541e-05,
      "loss": 0.0333,
      "step": 440
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.8721568627450981,
      "eval_loss": 0.08150659501552582,
      "eval_precision": 0.8567026194144838,
      "eval_recall": 0.8881789137380192,
      "eval_runtime": 1.8956,
      "eval_samples_per_second": 310.712,
      "eval_steps_per_second": 19.518,
      "step": 444
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 0.2796086370944977,
      "learning_rate": 1.043918918918919e-05,
      "loss": 0.0256,
      "step": 450
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 0.33986714482307434,
      "learning_rate": 1.0337837837837838e-05,
      "loss": 0.0217,
      "step": 460
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 0.7989048361778259,
      "learning_rate": 1.0236486486486488e-05,
      "loss": 0.027,
      "step": 470
    },
    {
      "epoch": 3.2432432432432434,
      "grad_norm": 0.6396713256835938,
      "learning_rate": 1.0135135135135135e-05,
      "loss": 0.0376,
      "step": 480
    },
    {
      "epoch": 3.310810810810811,
      "grad_norm": 0.6923012137413025,
      "learning_rate": 1.0033783783783785e-05,
      "loss": 0.0242,
      "step": 490
    },
    {
      "epoch": 3.3783783783783785,
      "grad_norm": 1.0020307302474976,
      "learning_rate": 9.932432432432433e-06,
      "loss": 0.0246,
      "step": 500
    },
    {
      "epoch": 3.445945945945946,
      "grad_norm": 1.2554748058319092,
      "learning_rate": 9.831081081081081e-06,
      "loss": 0.0355,
      "step": 510
    },
    {
      "epoch": 3.5135135135135136,
      "grad_norm": 0.999401330947876,
      "learning_rate": 9.72972972972973e-06,
      "loss": 0.0207,
      "step": 520
    },
    {
      "epoch": 3.581081081081081,
      "grad_norm": 1.5477733612060547,
      "learning_rate": 9.628378378378378e-06,
      "loss": 0.0305,
      "step": 530
    },
    {
      "epoch": 3.6486486486486487,
      "grad_norm": 1.2256771326065063,
      "learning_rate": 9.527027027027027e-06,
      "loss": 0.0321,
      "step": 540
    },
    {
      "epoch": 3.7162162162162162,
      "grad_norm": 0.9079200625419617,
      "learning_rate": 9.425675675675677e-06,
      "loss": 0.0216,
      "step": 550
    },
    {
      "epoch": 3.7837837837837838,
      "grad_norm": 0.6151091456413269,
      "learning_rate": 9.324324324324325e-06,
      "loss": 0.0245,
      "step": 560
    },
    {
      "epoch": 3.8513513513513513,
      "grad_norm": 0.9502114653587341,
      "learning_rate": 9.222972972972973e-06,
      "loss": 0.0244,
      "step": 570
    },
    {
      "epoch": 3.918918918918919,
      "grad_norm": 1.7815593481063843,
      "learning_rate": 9.121621621621622e-06,
      "loss": 0.0272,
      "step": 580
    },
    {
      "epoch": 3.9864864864864864,
      "grad_norm": 0.6826658248901367,
      "learning_rate": 9.02027027027027e-06,
      "loss": 0.0249,
      "step": 590
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.8645953202915228,
      "eval_loss": 0.09485752880573273,
      "eval_precision": 0.8317343173431734,
      "eval_recall": 0.9001597444089456,
      "eval_runtime": 1.8853,
      "eval_samples_per_second": 312.416,
      "eval_steps_per_second": 19.625,
      "step": 592
    }
  ],
  "logging_steps": 10,
  "max_steps": 1480,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 436344245873250.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}