{
  "best_global_step": 939,
  "best_metric": 0.8259977698326111,
  "best_model_checkpoint": "/content/drive/MyDrive/NLP Project/Model_Check_Points/checkpoint-939",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 2817,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10649627263045794,
      "grad_norm": 24.650606155395508,
      "learning_rate": 4.824281150159744e-05,
      "loss": 2.9361,
      "step": 100
    },
    {
      "epoch": 0.21299254526091588,
      "grad_norm": 16.183334350585938,
      "learning_rate": 4.646787362442315e-05,
      "loss": 1.5605,
      "step": 200
    },
    {
      "epoch": 0.3194888178913738,
      "grad_norm": 17.95966339111328,
      "learning_rate": 4.469293574724885e-05,
      "loss": 1.4362,
      "step": 300
    },
    {
      "epoch": 0.42598509052183176,
      "grad_norm": 6.452091217041016,
      "learning_rate": 4.291799787007455e-05,
      "loss": 1.1737,
      "step": 400
    },
    {
      "epoch": 0.5324813631522897,
      "grad_norm": 13.974135398864746,
      "learning_rate": 4.114305999290025e-05,
      "loss": 1.0572,
      "step": 500
    },
    {
      "epoch": 0.6389776357827476,
      "grad_norm": 8.441079139709473,
      "learning_rate": 3.936812211572595e-05,
      "loss": 1.0054,
      "step": 600
    },
    {
      "epoch": 0.7454739084132055,
      "grad_norm": 8.001397132873535,
      "learning_rate": 3.759318423855165e-05,
      "loss": 0.976,
      "step": 700
    },
    {
      "epoch": 0.8519701810436635,
      "grad_norm": 21.64325714111328,
      "learning_rate": 3.581824636137736e-05,
      "loss": 0.958,
      "step": 800
    },
    {
      "epoch": 0.9584664536741214,
      "grad_norm": 20.613216400146484,
      "learning_rate": 3.404330848420306e-05,
      "loss": 1.0714,
      "step": 900
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8259977698326111,
      "eval_runtime": 23.5113,
      "eval_samples_per_second": 35.515,
      "eval_steps_per_second": 4.466,
      "step": 939
    },
    {
      "epoch": 1.0649627263045793,
      "grad_norm": 5.86592435836792,
      "learning_rate": 3.226837060702875e-05,
      "loss": 0.7105,
      "step": 1000
    },
    {
      "epoch": 1.1714589989350372,
      "grad_norm": 6.007891654968262,
      "learning_rate": 3.0493432729854453e-05,
      "loss": 0.7573,
      "step": 1100
    },
    {
      "epoch": 1.2779552715654952,
      "grad_norm": 24.980873107910156,
      "learning_rate": 2.8718494852680156e-05,
      "loss": 0.6667,
      "step": 1200
    },
    {
      "epoch": 1.384451544195953,
      "grad_norm": 7.66667366027832,
      "learning_rate": 2.6943556975505857e-05,
      "loss": 0.686,
      "step": 1300
    },
    {
      "epoch": 1.4909478168264112,
      "grad_norm": 4.325304985046387,
      "learning_rate": 2.5168619098331557e-05,
      "loss": 0.6407,
      "step": 1400
    },
    {
      "epoch": 1.5974440894568689,
      "grad_norm": 15.46461296081543,
      "learning_rate": 2.339368122115726e-05,
      "loss": 0.7442,
      "step": 1500
    },
    {
      "epoch": 1.703940362087327,
      "grad_norm": 4.6854329109191895,
      "learning_rate": 2.161874334398296e-05,
      "loss": 0.614,
      "step": 1600
    },
    {
      "epoch": 1.810436634717785,
      "grad_norm": 11.84803581237793,
      "learning_rate": 1.984380546680866e-05,
      "loss": 0.5829,
      "step": 1700
    },
    {
      "epoch": 1.9169329073482428,
      "grad_norm": 6.407904148101807,
      "learning_rate": 1.8068867589634365e-05,
      "loss": 0.6597,
      "step": 1800
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8963555693626404,
      "eval_runtime": 23.6303,
      "eval_samples_per_second": 35.336,
      "eval_steps_per_second": 4.443,
      "step": 1878
    },
    {
      "epoch": 2.0234291799787005,
      "grad_norm": 3.6491150856018066,
      "learning_rate": 1.6293929712460065e-05,
      "loss": 0.5432,
      "step": 1900
    },
    {
      "epoch": 2.1299254526091587,
      "grad_norm": 8.647642135620117,
      "learning_rate": 1.4518991835285767e-05,
      "loss": 0.4277,
      "step": 2000
    },
    {
      "epoch": 2.236421725239617,
      "grad_norm": 12.06881046295166,
      "learning_rate": 1.2744053958111466e-05,
      "loss": 0.4552,
      "step": 2100
    },
    {
      "epoch": 2.3429179978700745,
      "grad_norm": 0.3559926450252533,
      "learning_rate": 1.0969116080937168e-05,
      "loss": 0.4722,
      "step": 2200
    },
    {
      "epoch": 2.4494142705005326,
      "grad_norm": 7.629179954528809,
      "learning_rate": 9.194178203762868e-06,
      "loss": 0.4412,
      "step": 2300
    },
    {
      "epoch": 2.5559105431309903,
      "grad_norm": 1.9225965738296509,
      "learning_rate": 7.419240326588569e-06,
      "loss": 0.4495,
      "step": 2400
    },
    {
      "epoch": 2.6624068157614484,
      "grad_norm": 42.623741149902344,
      "learning_rate": 5.644302449414271e-06,
      "loss": 0.4103,
      "step": 2500
    },
    {
      "epoch": 2.768903088391906,
      "grad_norm": 2.6453473567962646,
      "learning_rate": 3.869364572239972e-06,
      "loss": 0.4319,
      "step": 2600
    },
    {
      "epoch": 2.8753993610223643,
      "grad_norm": 11.74781322479248,
      "learning_rate": 2.0944266950656728e-06,
      "loss": 0.559,
      "step": 2700
    },
    {
      "epoch": 2.9818956336528224,
      "grad_norm": 8.635344505310059,
      "learning_rate": 3.194888178913738e-07,
      "loss": 0.4518,
      "step": 2800
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.9571546316146851,
      "eval_runtime": 23.3043,
      "eval_samples_per_second": 35.83,
      "eval_steps_per_second": 4.506,
      "step": 2817
    }
  ],
  "logging_steps": 100,
  "max_steps": 2817,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5883880368181248.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}