{
  "best_metric": 0.17333222008850296,
  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-2127",
  "epoch": 9.988249118683902,
  "eval_steps": 500,
  "global_step": 4250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9988249118683902,
      "eval_accuracy": 0.7849561289082346,
      "eval_f1": 0.1613083366573594,
      "eval_loss": 0.6610585451126099,
      "eval_precision": 0.08832008386476806,
      "eval_recall": 0.9292279411764706,
      "eval_runtime": 14.7703,
      "eval_samples_per_second": 461.06,
      "eval_steps_per_second": 57.683,
      "step": 425
    },
    {
      "epoch": 1.1750881316098707,
      "grad_norm": 1.4406206607818604,
      "learning_rate": 4.411764705882353e-05,
      "loss": 0.3349,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7551182940392986,
      "eval_f1": 0.14506880733944952,
      "eval_loss": 0.9204075932502747,
      "eval_precision": 0.07866915422885572,
      "eval_recall": 0.9301470588235294,
      "eval_runtime": 14.7453,
      "eval_samples_per_second": 461.844,
      "eval_steps_per_second": 57.781,
      "step": 851
    },
    {
      "epoch": 2.3501762632197414,
      "grad_norm": 2.988006591796875,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 0.1788,
      "step": 1000
    },
    {
      "epoch": 2.99882491186839,
      "eval_accuracy": 0.7645035495077375,
      "eval_f1": 0.15487907225146869,
      "eval_loss": 0.9544711709022522,
      "eval_precision": 0.0844496214327315,
      "eval_recall": 0.9329044117647058,
      "eval_runtime": 14.8107,
      "eval_samples_per_second": 459.803,
      "eval_steps_per_second": 57.526,
      "step": 1276
    },
    {
      "epoch": 3.525264394829612,
      "grad_norm": 1.1645787954330444,
      "learning_rate": 3.235294117647059e-05,
      "loss": 0.1227,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7692064756203056,
      "eval_f1": 0.1618332674832082,
      "eval_loss": 1.0923608541488647,
      "eval_precision": 0.08852770813521224,
      "eval_recall": 0.9411764705882353,
      "eval_runtime": 14.8211,
      "eval_samples_per_second": 459.48,
      "eval_steps_per_second": 57.486,
      "step": 1702
    },
    {
      "epoch": 4.700352526439483,
      "grad_norm": 1.1214195489883423,
      "learning_rate": 2.647058823529412e-05,
      "loss": 0.0856,
      "step": 2000
    },
    {
      "epoch": 4.9988249118683905,
      "eval_accuracy": 0.7932840841995413,
      "eval_f1": 0.17333222008850296,
      "eval_loss": 1.0502684116363525,
      "eval_precision": 0.09532555790247038,
      "eval_recall": 0.9540441176470589,
      "eval_runtime": 14.797,
      "eval_samples_per_second": 460.229,
      "eval_steps_per_second": 57.579,
      "step": 2127
    },
    {
      "epoch": 5.875440658049354,
      "grad_norm": 1.1390776634216309,
      "learning_rate": 2.058823529411765e-05,
      "loss": 0.0597,
      "step": 2500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7787771018990209,
      "eval_f1": 0.16632958498503356,
      "eval_loss": 1.2641881704330444,
      "eval_precision": 0.0911913421449481,
      "eval_recall": 0.9448529411764706,
      "eval_runtime": 14.5753,
      "eval_samples_per_second": 467.228,
      "eval_steps_per_second": 58.455,
      "step": 2553
    },
    {
      "epoch": 6.9988249118683905,
      "eval_accuracy": 0.7828758564817994,
      "eval_f1": 0.16898640903880793,
      "eval_loss": 1.3261910676956177,
      "eval_precision": 0.09275570735214812,
      "eval_recall": 0.9485294117647058,
      "eval_runtime": 14.5617,
      "eval_samples_per_second": 467.665,
      "eval_steps_per_second": 58.51,
      "step": 2978
    },
    {
      "epoch": 7.050528789659224,
      "grad_norm": 0.5195357799530029,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 0.0458,
      "step": 3000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7848943386381424,
      "eval_f1": 0.1687846203975236,
      "eval_loss": 1.3697636127471924,
      "eval_precision": 0.09259921344297461,
      "eval_recall": 0.9522058823529411,
      "eval_runtime": 14.6608,
      "eval_samples_per_second": 464.504,
      "eval_steps_per_second": 58.114,
      "step": 3404
    },
    {
      "epoch": 8.225616921269095,
      "grad_norm": 0.8723571300506592,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.0343,
      "step": 3500
    },
    {
      "epoch": 8.99882491186839,
      "eval_accuracy": 0.782223625853049,
      "eval_f1": 0.165499476776946,
      "eval_loss": 1.4433350563049316,
      "eval_precision": 0.09069254521393913,
      "eval_recall": 0.9448529411764706,
      "eval_runtime": 15.0504,
      "eval_samples_per_second": 452.478,
      "eval_steps_per_second": 56.61,
      "step": 3829
    },
    {
      "epoch": 9.400705052878966,
      "grad_norm": 0.6075822710990906,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 0.0292,
      "step": 4000
    },
    {
      "epoch": 9.988249118683902,
      "eval_accuracy": 0.7820794485561674,
      "eval_f1": 0.16674769081186194,
      "eval_loss": 1.4861844778060913,
      "eval_precision": 0.0914341567442687,
      "eval_recall": 0.9457720588235294,
      "eval_runtime": 15.3988,
      "eval_samples_per_second": 442.243,
      "eval_steps_per_second": 55.329,
      "step": 4250
    },
    {
      "epoch": 9.988249118683902,
      "step": 4250,
      "total_flos": 1.2649810588547778e+16,
      "train_loss": 0.10639642311544979,
      "train_runtime": 1208.2019,
      "train_samples_per_second": 225.368,
      "train_steps_per_second": 3.518
    }
  ],
  "logging_steps": 500,
  "max_steps": 4250,
  "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": 1.2649810588547778e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}