{
  "best_metric": 0.9230769230769231,
  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-4850",
  "epoch": 9.989701338825952,
  "eval_steps": 500,
  "global_step": 4850,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9989701338825953,
      "eval_accuracy": 0.9984030122046221,
      "eval_f1": 0.9132331555986428,
      "eval_loss": 0.004271956626325846,
      "eval_precision": 0.9145631067961165,
      "eval_recall": 0.9119070667957405,
      "eval_runtime": 17.5218,
      "eval_samples_per_second": 387.973,
      "eval_steps_per_second": 48.511,
      "step": 485
    },
    {
      "epoch": 1.0298661174047374,
      "grad_norm": 0.35554030537605286,
      "learning_rate": 4.484536082474227e-05,
      "loss": 0.0127,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9984679304076863,
      "eval_f1": 0.9130645944633317,
      "eval_loss": 0.005422212183475494,
      "eval_precision": 0.9161793372319688,
      "eval_recall": 0.9099709583736689,
      "eval_runtime": 17.524,
      "eval_samples_per_second": 387.925,
      "eval_steps_per_second": 48.505,
      "step": 971
    },
    {
      "epoch": 2.059732234809475,
      "grad_norm": 0.2354772835969925,
      "learning_rate": 3.9690721649484535e-05,
      "loss": 0.0033,
      "step": 1000
    },
    {
      "epoch": 2.998970133882595,
      "eval_accuracy": 0.9985912749935082,
      "eval_f1": 0.9173955296404277,
      "eval_loss": 0.0059292372316122055,
      "eval_precision": 0.9209756097560976,
      "eval_recall": 0.9138431752178122,
      "eval_runtime": 17.4807,
      "eval_samples_per_second": 388.886,
      "eval_steps_per_second": 48.625,
      "step": 1456
    },
    {
      "epoch": 3.089598352214212,
      "grad_norm": 0.026833873242139816,
      "learning_rate": 3.4536082474226805e-05,
      "loss": 0.0016,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9985523240716697,
      "eval_f1": 0.9135212613473483,
      "eval_loss": 0.006239830516278744,
      "eval_precision": 0.9018867924528302,
      "eval_recall": 0.925459825750242,
      "eval_runtime": 17.8043,
      "eval_samples_per_second": 381.818,
      "eval_steps_per_second": 47.741,
      "step": 1942
    },
    {
      "epoch": 4.11946446961895,
      "grad_norm": 0.1513855904340744,
      "learning_rate": 2.9381443298969075e-05,
      "loss": 0.001,
      "step": 2000
    },
    {
      "epoch": 4.998970133882596,
      "eval_accuracy": 0.9986042586341211,
      "eval_f1": 0.920328343795268,
      "eval_loss": 0.006359434220939875,
      "eval_precision": 0.918111753371869,
      "eval_recall": 0.9225556631171346,
      "eval_runtime": 17.4628,
      "eval_samples_per_second": 389.284,
      "eval_steps_per_second": 48.675,
      "step": 2427
    },
    {
      "epoch": 5.1493305870236865,
      "grad_norm": 0.007741741370409727,
      "learning_rate": 2.422680412371134e-05,
      "loss": 0.0006,
      "step": 2500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9985523240716697,
      "eval_f1": 0.9180009704027171,
      "eval_loss": 0.00812861043959856,
      "eval_precision": 0.9202334630350194,
      "eval_recall": 0.9157792836398838,
      "eval_runtime": 17.5273,
      "eval_samples_per_second": 387.852,
      "eval_steps_per_second": 48.496,
      "step": 2913
    },
    {
      "epoch": 6.179196704428424,
      "grad_norm": 0.06708419322967529,
      "learning_rate": 1.9072164948453608e-05,
      "loss": 0.0004,
      "step": 3000
    },
    {
      "epoch": 6.998970133882596,
      "eval_accuracy": 0.9985653077122826,
      "eval_f1": 0.920328343795268,
      "eval_loss": 0.008457792922854424,
      "eval_precision": 0.918111753371869,
      "eval_recall": 0.9225556631171346,
      "eval_runtime": 17.4726,
      "eval_samples_per_second": 389.067,
      "eval_steps_per_second": 48.648,
      "step": 3398
    },
    {
      "epoch": 7.209062821833162,
      "grad_norm": 0.0032746351789683104,
      "learning_rate": 1.3917525773195878e-05,
      "loss": 0.0003,
      "step": 3500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9985847831732018,
      "eval_f1": 0.9210653753026635,
      "eval_loss": 0.00870645884424448,
      "eval_precision": 0.9215116279069767,
      "eval_recall": 0.920619554695063,
      "eval_runtime": 17.5192,
      "eval_samples_per_second": 388.031,
      "eval_steps_per_second": 48.518,
      "step": 3884
    },
    {
      "epoch": 8.2389289392379,
      "grad_norm": 0.0013693332439288497,
      "learning_rate": 8.762886597938144e-06,
      "loss": 0.0002,
      "step": 4000
    },
    {
      "epoch": 8.998970133882596,
      "eval_accuracy": 0.9985198649701377,
      "eval_f1": 0.9206500956022945,
      "eval_loss": 0.008967469446361065,
      "eval_precision": 0.9093484419263456,
      "eval_recall": 0.9322362052274927,
      "eval_runtime": 17.7573,
      "eval_samples_per_second": 382.828,
      "eval_steps_per_second": 47.868,
      "step": 4369
    },
    {
      "epoch": 9.268795056642636,
      "grad_norm": 0.0005869244341738522,
      "learning_rate": 3.608247422680412e-06,
      "loss": 0.0001,
      "step": 4500
    },
    {
      "epoch": 9.989701338825952,
      "eval_accuracy": 0.9986302259153467,
      "eval_f1": 0.9230769230769231,
      "eval_loss": 0.009366312995553017,
      "eval_precision": 0.9169054441260746,
      "eval_recall": 0.9293320425943853,
      "eval_runtime": 17.4762,
      "eval_samples_per_second": 388.987,
      "eval_steps_per_second": 48.638,
      "step": 4850
    },
    {
      "epoch": 9.989701338825952,
      "step": 4850,
      "total_flos": 1.7736053837017554e+16,
      "train_loss": 0.002068036902580679,
      "train_runtime": 2701.3395,
      "train_samples_per_second": 114.954,
      "train_steps_per_second": 1.795
    }
  ],
  "logging_steps": 500,
  "max_steps": 4850,
  "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": 1.7736053837017554e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}