{
  "best_metric": 0.8040201005025126,
  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-3996",
  "epoch": 9.98998998998999,
  "eval_steps": 500,
  "global_step": 4990,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.998998998998999,
      "eval_accuracy": 0.9730869045820918,
      "eval_f1": 0.75963794837412,
      "eval_loss": 0.07385822385549545,
      "eval_precision": 0.7270588235294118,
      "eval_recall": 0.7952737482452036,
      "eval_runtime": 14.2023,
      "eval_samples_per_second": 479.501,
      "eval_steps_per_second": 59.99,
      "step": 499
    },
    {
      "epoch": 1.001001001001001,
      "grad_norm": 0.8427119851112366,
      "learning_rate": 4.4989979959919844e-05,
      "loss": 0.105,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.972949592870776,
      "eval_f1": 0.7655806561471223,
      "eval_loss": 0.09075114130973816,
      "eval_precision": 0.7435501653803749,
      "eval_recall": 0.7889564810481984,
      "eval_runtime": 14.1492,
      "eval_samples_per_second": 481.299,
      "eval_steps_per_second": 60.215,
      "step": 999
    },
    {
      "epoch": 2.002002002002002,
      "grad_norm": 0.9121108651161194,
      "learning_rate": 3.997995991983968e-05,
      "loss": 0.0448,
      "step": 1000
    },
    {
      "epoch": 2.998998998998999,
      "eval_accuracy": 0.9743913658395924,
      "eval_f1": 0.7829875042989798,
      "eval_loss": 0.09297410398721695,
      "eval_precision": 0.7675882220723759,
      "eval_recall": 0.7990173139915769,
      "eval_runtime": 14.1376,
      "eval_samples_per_second": 481.693,
      "eval_steps_per_second": 60.265,
      "step": 1498
    },
    {
      "epoch": 3.003003003003003,
      "grad_norm": 0.5380845069885254,
      "learning_rate": 3.496993987975952e-05,
      "loss": 0.0255,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9757438861960537,
      "eval_f1": 0.789358010410642,
      "eval_loss": 0.10520397126674652,
      "eval_precision": 0.7805994051704416,
      "eval_recall": 0.798315395414132,
      "eval_runtime": 14.3621,
      "eval_samples_per_second": 474.163,
      "eval_steps_per_second": 59.323,
      "step": 1998
    },
    {
      "epoch": 4.004004004004004,
      "grad_norm": 0.2705754339694977,
      "learning_rate": 2.9959919839679363e-05,
      "loss": 0.0164,
      "step": 2000
    },
    {
      "epoch": 4.998998998998999,
      "eval_accuracy": 0.9750435964683428,
      "eval_f1": 0.7879346074142298,
      "eval_loss": 0.10997848957777023,
      "eval_precision": 0.7756119673617408,
      "eval_recall": 0.8006551240056153,
      "eval_runtime": 14.2341,
      "eval_samples_per_second": 478.428,
      "eval_steps_per_second": 59.856,
      "step": 2497
    },
    {
      "epoch": 5.005005005005005,
      "grad_norm": 0.27666428685188293,
      "learning_rate": 2.49498997995992e-05,
      "loss": 0.0112,
      "step": 2500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9768011863731858,
      "eval_f1": 0.799447386599125,
      "eval_loss": 0.12663568556308746,
      "eval_precision": 0.7869446962828649,
      "eval_recall": 0.8123537669630323,
      "eval_runtime": 14.5018,
      "eval_samples_per_second": 469.597,
      "eval_steps_per_second": 58.751,
      "step": 2997
    },
    {
      "epoch": 6.006006006006006,
      "grad_norm": 0.24552026391029358,
      "learning_rate": 1.993987975951904e-05,
      "loss": 0.0073,
      "step": 3000
    },
    {
      "epoch": 6.998998998998999,
      "eval_accuracy": 0.976293133041317,
      "eval_f1": 0.7968804562914678,
      "eval_loss": 0.12882493436336517,
      "eval_precision": 0.792911744266852,
      "eval_recall": 0.8008890968647637,
      "eval_runtime": 14.3476,
      "eval_samples_per_second": 474.643,
      "eval_steps_per_second": 59.383,
      "step": 3496
    },
    {
      "epoch": 7.007007007007007,
      "grad_norm": 0.2008085697889328,
      "learning_rate": 1.492985971943888e-05,
      "loss": 0.0054,
      "step": 3500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9764853694371592,
      "eval_f1": 0.8040201005025126,
      "eval_loss": 0.14244574308395386,
      "eval_precision": 0.803175344384777,
      "eval_recall": 0.8048666354702855,
      "eval_runtime": 14.514,
      "eval_samples_per_second": 469.202,
      "eval_steps_per_second": 58.702,
      "step": 3996
    },
    {
      "epoch": 8.008008008008009,
      "grad_norm": 0.12597906589508057,
      "learning_rate": 9.919839679358718e-06,
      "loss": 0.0038,
      "step": 4000
    },
    {
      "epoch": 8.998998998999,
      "eval_accuracy": 0.9765059661938567,
      "eval_f1": 0.7970779220779219,
      "eval_loss": 0.14552859961986542,
      "eval_precision": 0.7901149425287356,
      "eval_recall": 0.8041647168928404,
      "eval_runtime": 14.2396,
      "eval_samples_per_second": 478.242,
      "eval_steps_per_second": 59.833,
      "step": 4495
    },
    {
      "epoch": 9.00900900900901,
      "grad_norm": 0.2577208876609802,
      "learning_rate": 4.9098196392785576e-06,
      "loss": 0.0028,
      "step": 4500
    },
    {
      "epoch": 9.98998998998999,
      "eval_accuracy": 0.9768286487154489,
      "eval_f1": 0.7984262902105993,
      "eval_loss": 0.14972682297229767,
      "eval_precision": 0.7898351648351648,
      "eval_recall": 0.8072063640617688,
      "eval_runtime": 14.3927,
      "eval_samples_per_second": 473.158,
      "eval_steps_per_second": 59.197,
      "step": 4990
    },
    {
      "epoch": 9.98998998998999,
      "step": 4990,
      "total_flos": 1.5071241212671032e+16,
      "train_loss": 0.022475468706272407,
      "train_runtime": 1385.1143,
      "train_samples_per_second": 230.645,
      "train_steps_per_second": 3.603
    }
  ],
  "logging_steps": 500,
  "max_steps": 4990,
  "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": 1.5071241212671032e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}