{
  "best_global_step": 150,
  "best_metric": 0.9915354168771638,
  "best_model_checkpoint": "/content/drive/MyDrive/model/Roberta_Squad/roberta_Squad/checkpoint-150",
  "epoch": 0.450112528132033,
  "eval_steps": 150,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007501875468867217,
      "grad_norm": 27.303098678588867,
      "learning_rate": 0.0,
      "loss": 1.1906,
      "step": 1
    },
    {
      "epoch": 0.037509377344336084,
      "grad_norm": 17.193105697631836,
      "learning_rate": 8.997188378631678e-07,
      "loss": 1.0245,
      "step": 50
    },
    {
      "epoch": 0.07501875468867217,
      "grad_norm": 0.9530491232872009,
      "learning_rate": 1.8369259606373011e-06,
      "loss": 0.2468,
      "step": 100
    },
    {
      "epoch": 0.11252813203300825,
      "grad_norm": 0.649541974067688,
      "learning_rate": 2.7741330834114345e-06,
      "loss": 0.0702,
      "step": 150
    },
    {
      "epoch": 0.11252813203300825,
      "eval_accuracy": 0.9943516121440339,
      "eval_f1_macro": 0.24929195185272598,
      "eval_f1_min": 0.0,
      "eval_f1_std": 0.4317863265269357,
      "eval_f1_weighted": 0.9915354168771638,
      "eval_loss": 0.038926418870687485,
      "eval_runtime": 35.4512,
      "eval_samples_per_second": 119.855,
      "eval_steps_per_second": 3.752,
      "step": 150
    },
    {
      "epoch": 0.15003750937734434,
      "grad_norm": 0.23891082406044006,
      "learning_rate": 3.7113402061855674e-06,
      "loss": 0.0472,
      "step": 200
    },
    {
      "epoch": 0.18754688672168043,
      "grad_norm": 1.910960078239441,
      "learning_rate": 4.6485473289597e-06,
      "loss": 0.0478,
      "step": 250
    },
    {
      "epoch": 0.2250562640660165,
      "grad_norm": 0.1880768984556198,
      "learning_rate": 5.585754451733834e-06,
      "loss": 0.0412,
      "step": 300
    },
    {
      "epoch": 0.2250562640660165,
      "eval_accuracy": 0.9943516121440339,
      "eval_f1_macro": 0.24929195185272598,
      "eval_f1_min": 0.0,
      "eval_f1_std": 0.4317863265269357,
      "eval_f1_weighted": 0.9915354168771638,
      "eval_loss": 0.040430303663015366,
      "eval_runtime": 34.879,
      "eval_samples_per_second": 121.821,
      "eval_steps_per_second": 3.813,
      "step": 300
    },
    {
      "epoch": 0.2625656414103526,
      "grad_norm": 0.09085190296173096,
      "learning_rate": 6.522961574507966e-06,
      "loss": 0.04,
      "step": 350
    },
    {
      "epoch": 0.30007501875468867,
      "grad_norm": 0.05724379047751427,
      "learning_rate": 7.4601686972821e-06,
      "loss": 0.0287,
      "step": 400
    },
    {
      "epoch": 0.33758439609902474,
      "grad_norm": 0.2768031358718872,
      "learning_rate": 8.397375820056232e-06,
      "loss": 0.0374,
      "step": 450
    },
    {
      "epoch": 0.33758439609902474,
      "eval_accuracy": 0.9943516121440339,
      "eval_f1_macro": 0.24929195185272598,
      "eval_f1_min": 0.0,
      "eval_f1_std": 0.4317863265269357,
      "eval_f1_weighted": 0.9915354168771638,
      "eval_loss": 0.033962853252887726,
      "eval_runtime": 34.8673,
      "eval_samples_per_second": 121.862,
      "eval_steps_per_second": 3.814,
      "step": 450
    },
    {
      "epoch": 0.37509377344336087,
      "grad_norm": 1.1712861061096191,
      "learning_rate": 9.334582942830366e-06,
      "loss": 0.0351,
      "step": 500
    },
    {
      "epoch": 0.41260315078769694,
      "grad_norm": 0.24754193425178528,
      "learning_rate": 1.0271790065604499e-05,
      "loss": 0.042,
      "step": 550
    },
    {
      "epoch": 0.450112528132033,
      "grad_norm": 1.4196994304656982,
      "learning_rate": 1.1208997188378632e-05,
      "loss": 0.0544,
      "step": 600
    },
    {
      "epoch": 0.450112528132033,
      "eval_accuracy": 0.9943516121440339,
      "eval_f1_macro": 0.24929195185272598,
      "eval_f1_min": 0.0,
      "eval_f1_std": 0.4317863265269357,
      "eval_f1_weighted": 0.9915354168771638,
      "eval_loss": 0.03701222687959671,
      "eval_runtime": 35.0215,
      "eval_samples_per_second": 121.325,
      "eval_steps_per_second": 3.798,
      "step": 600
    }
  ],
  "logging_steps": 50,
  "max_steps": 10664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 150,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0005
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.01037366706176e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}