{
  "best_metric": 0.9706230241510936,
  "best_model_checkpoint": "/home/ddo37/Security-Project/scripts/finetune/output/checkpoints/checkpoint-1856",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 2320,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 11.954014778137207,
      "learning_rate": 3.5344827586206898e-06,
      "loss": 1.8299,
      "step": 100
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 2.8888251781463623,
      "learning_rate": 7.844827586206897e-06,
      "loss": 0.7131,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8713592233009708,
      "eval_f1": 0.8631315005994362,
      "eval_loss": 0.3847014009952545,
      "eval_runtime": 1.2398,
      "eval_samples_per_second": 664.646,
      "eval_steps_per_second": 20.972,
      "step": 232
    },
    {
      "epoch": 1.293103448275862,
      "grad_norm": 2.661858558654785,
      "learning_rate": 9.760536398467434e-06,
      "loss": 0.3837,
      "step": 300
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 2.5226521492004395,
      "learning_rate": 9.281609195402299e-06,
      "loss": 0.2957,
      "step": 400
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9344660194174758,
      "eval_f1": 0.9309781897227271,
      "eval_loss": 0.22864548861980438,
      "eval_runtime": 1.2773,
      "eval_samples_per_second": 645.087,
      "eval_steps_per_second": 20.355,
      "step": 464
    },
    {
      "epoch": 2.1551724137931036,
      "grad_norm": 5.212111473083496,
      "learning_rate": 8.802681992337166e-06,
      "loss": 0.2293,
      "step": 500
    },
    {
      "epoch": 2.586206896551724,
      "grad_norm": 3.2719788551330566,
      "learning_rate": 8.323754789272031e-06,
      "loss": 0.2061,
      "step": 600
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9453883495145631,
      "eval_f1": 0.9428782627566964,
      "eval_loss": 0.17873604595661163,
      "eval_runtime": 1.2824,
      "eval_samples_per_second": 642.533,
      "eval_steps_per_second": 20.274,
      "step": 696
    },
    {
      "epoch": 3.0172413793103448,
      "grad_norm": 3.8508994579315186,
      "learning_rate": 7.844827586206897e-06,
      "loss": 0.2151,
      "step": 700
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 1.9576607942581177,
      "learning_rate": 7.365900383141763e-06,
      "loss": 0.1763,
      "step": 800
    },
    {
      "epoch": 3.8793103448275863,
      "grad_norm": 9.453478813171387,
      "learning_rate": 6.886973180076629e-06,
      "loss": 0.1558,
      "step": 900
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9538834951456311,
      "eval_f1": 0.9512711549345356,
      "eval_loss": 0.14712262153625488,
      "eval_runtime": 1.2772,
      "eval_samples_per_second": 645.171,
      "eval_steps_per_second": 20.357,
      "step": 928
    },
    {
      "epoch": 4.310344827586207,
      "grad_norm": 1.4285823106765747,
      "learning_rate": 6.408045977011495e-06,
      "loss": 0.1631,
      "step": 1000
    },
    {
      "epoch": 4.741379310344827,
      "grad_norm": 5.883343696594238,
      "learning_rate": 5.933908045977011e-06,
      "loss": 0.1504,
      "step": 1100
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9611650485436893,
      "eval_f1": 0.9599362299707782,
      "eval_loss": 0.12942931056022644,
      "eval_runtime": 1.2731,
      "eval_samples_per_second": 647.238,
      "eval_steps_per_second": 20.423,
      "step": 1160
    },
    {
      "epoch": 5.172413793103448,
      "grad_norm": 3.6885058879852295,
      "learning_rate": 5.454980842911878e-06,
      "loss": 0.125,
      "step": 1200
    },
    {
      "epoch": 5.603448275862069,
      "grad_norm": 2.8290116786956787,
      "learning_rate": 4.976053639846744e-06,
      "loss": 0.125,
      "step": 1300
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9635922330097088,
      "eval_f1": 0.9621841535418691,
      "eval_loss": 0.11738289892673492,
      "eval_runtime": 1.2789,
      "eval_samples_per_second": 644.281,
      "eval_steps_per_second": 20.329,
      "step": 1392
    },
    {
      "epoch": 6.0344827586206895,
      "grad_norm": 0.3815958499908447,
      "learning_rate": 4.49712643678161e-06,
      "loss": 0.1202,
      "step": 1400
    },
    {
      "epoch": 6.4655172413793105,
      "grad_norm": 3.272099018096924,
      "learning_rate": 4.0181992337164755e-06,
      "loss": 0.1118,
      "step": 1500
    },
    {
      "epoch": 6.896551724137931,
      "grad_norm": 4.3483662605285645,
      "learning_rate": 3.5392720306513413e-06,
      "loss": 0.1184,
      "step": 1600
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9660194174757282,
      "eval_f1": 0.9665106319184217,
      "eval_loss": 0.10380454361438751,
      "eval_runtime": 1.2789,
      "eval_samples_per_second": 644.297,
      "eval_steps_per_second": 20.33,
      "step": 1624
    },
    {
      "epoch": 7.327586206896552,
      "grad_norm": 0.32656994462013245,
      "learning_rate": 3.0603448275862068e-06,
      "loss": 0.1011,
      "step": 1700
    },
    {
      "epoch": 7.758620689655173,
      "grad_norm": 6.692719459533691,
      "learning_rate": 2.581417624521073e-06,
      "loss": 0.0889,
      "step": 1800
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.970873786407767,
      "eval_f1": 0.9706230241510936,
      "eval_loss": 0.09331130981445312,
      "eval_runtime": 1.2861,
      "eval_samples_per_second": 640.719,
      "eval_steps_per_second": 20.217,
      "step": 1856
    },
    {
      "epoch": 8.189655172413794,
      "grad_norm": 5.316383361816406,
      "learning_rate": 2.102490421455939e-06,
      "loss": 0.0904,
      "step": 1900
    },
    {
      "epoch": 8.620689655172415,
      "grad_norm": 1.0274827480316162,
      "learning_rate": 1.623563218390805e-06,
      "loss": 0.1022,
      "step": 2000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.970873786407767,
      "eval_f1": 0.9700692044603826,
      "eval_loss": 0.09119965136051178,
      "eval_runtime": 1.2882,
      "eval_samples_per_second": 639.669,
      "eval_steps_per_second": 20.184,
      "step": 2088
    },
    {
      "epoch": 9.051724137931034,
      "grad_norm": 4.100451946258545,
      "learning_rate": 1.1494252873563219e-06,
      "loss": 0.0927,
      "step": 2100
    },
    {
      "epoch": 9.482758620689655,
      "grad_norm": 3.5858731269836426,
      "learning_rate": 6.752873563218392e-07,
      "loss": 0.0757,
      "step": 2200
    },
    {
      "epoch": 9.913793103448276,
      "grad_norm": 4.313425064086914,
      "learning_rate": 1.96360153256705e-07,
      "loss": 0.0988,
      "step": 2300
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9696601941747572,
      "eval_f1": 0.9687676005765485,
      "eval_loss": 0.08939822018146515,
      "eval_runtime": 1.2896,
      "eval_samples_per_second": 638.946,
      "eval_steps_per_second": 20.161,
      "step": 2320
    }
  ],
  "logging_steps": 100,
  "max_steps": 2320,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 9835957818753024.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}