{
  "best_metric": 0.9335180055401663,
  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-4056",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 5070,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9861932938856016,
      "grad_norm": 0.16175590455532074,
      "learning_rate": 4.5069033530571994e-05,
      "loss": 0.0183,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9985418469009014,
      "eval_f1": 0.9170464904284412,
      "eval_loss": 0.005470008589327335,
      "eval_precision": 0.8974130240856378,
      "eval_recall": 0.9375582479030755,
      "eval_runtime": 15.2218,
      "eval_samples_per_second": 456.319,
      "eval_steps_per_second": 57.089,
      "step": 507
    },
    {
      "epoch": 1.972386587771203,
      "grad_norm": 0.13494741916656494,
      "learning_rate": 4.0138067061143986e-05,
      "loss": 0.0043,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9985976613735942,
      "eval_f1": 0.9208103130755064,
      "eval_loss": 0.005941031500697136,
      "eval_precision": 0.9099181073703366,
      "eval_recall": 0.9319664492078286,
      "eval_runtime": 15.129,
      "eval_samples_per_second": 459.117,
      "eval_steps_per_second": 57.439,
      "step": 1014
    },
    {
      "epoch": 2.9585798816568047,
      "grad_norm": 0.14869354665279388,
      "learning_rate": 3.520710059171598e-05,
      "loss": 0.0022,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.998513939664555,
      "eval_f1": 0.9155963302752294,
      "eval_loss": 0.005716267507523298,
      "eval_precision": 0.9015356820234869,
      "eval_recall": 0.9301025163094129,
      "eval_runtime": 15.1542,
      "eval_samples_per_second": 458.356,
      "eval_steps_per_second": 57.344,
      "step": 1521
    },
    {
      "epoch": 3.9447731755424065,
      "grad_norm": 0.15148845314979553,
      "learning_rate": 3.027613412228797e-05,
      "loss": 0.0018,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9985767309463344,
      "eval_f1": 0.9227166276346604,
      "eval_loss": 0.0072021945379674435,
      "eval_precision": 0.9274952919020716,
      "eval_recall": 0.9179869524697111,
      "eval_runtime": 15.3453,
      "eval_samples_per_second": 452.646,
      "eval_steps_per_second": 56.63,
      "step": 2028
    },
    {
      "epoch": 4.930966469428008,
      "grad_norm": 0.17791983485221863,
      "learning_rate": 2.5345167652859964e-05,
      "loss": 0.0009,
      "step": 2500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9986604526553735,
      "eval_f1": 0.9215236346948141,
      "eval_loss": 0.0063728527165949345,
      "eval_precision": 0.9077757685352622,
      "eval_recall": 0.9356943150046598,
      "eval_runtime": 15.1945,
      "eval_samples_per_second": 457.14,
      "eval_steps_per_second": 57.192,
      "step": 2535
    },
    {
      "epoch": 5.9171597633136095,
      "grad_norm": 0.027111981064081192,
      "learning_rate": 2.0414201183431952e-05,
      "loss": 0.0007,
      "step": 3000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9987302207462395,
      "eval_f1": 0.9274826789838336,
      "eval_loss": 0.006401057820767164,
      "eval_precision": 0.9194139194139194,
      "eval_recall": 0.9356943150046598,
      "eval_runtime": 15.0971,
      "eval_samples_per_second": 460.088,
      "eval_steps_per_second": 57.561,
      "step": 3042
    },
    {
      "epoch": 6.903353057199211,
      "grad_norm": 0.0044996230863034725,
      "learning_rate": 1.5483234714003947e-05,
      "loss": 0.0004,
      "step": 3500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9987651047916725,
      "eval_f1": 0.9332096474953618,
      "eval_loss": 0.00720419455319643,
      "eval_precision": 0.9289012003693444,
      "eval_recall": 0.9375582479030755,
      "eval_runtime": 15.1686,
      "eval_samples_per_second": 457.919,
      "eval_steps_per_second": 57.289,
      "step": 3549
    },
    {
      "epoch": 7.889546351084813,
      "grad_norm": 0.0005134351667948067,
      "learning_rate": 1.0552268244575937e-05,
      "loss": 0.0004,
      "step": 4000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.998772081600759,
      "eval_f1": 0.9335180055401663,
      "eval_loss": 0.007628325838595629,
      "eval_precision": 0.9249771271729186,
      "eval_recall": 0.9422180801491147,
      "eval_runtime": 15.1289,
      "eval_samples_per_second": 459.122,
      "eval_steps_per_second": 57.44,
      "step": 4056
    },
    {
      "epoch": 8.875739644970414,
      "grad_norm": 0.0011633747490122914,
      "learning_rate": 5.621301775147929e-06,
      "loss": 0.0003,
      "step": 4500
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9987162671280663,
      "eval_f1": 0.9262672811059908,
      "eval_loss": 0.00773056922480464,
      "eval_precision": 0.9161349134001823,
      "eval_recall": 0.9366262814538676,
      "eval_runtime": 15.3347,
      "eval_samples_per_second": 452.96,
      "eval_steps_per_second": 56.669,
      "step": 4563
    },
    {
      "epoch": 9.861932938856016,
      "grad_norm": 0.001042825635522604,
      "learning_rate": 6.903353057199211e-07,
      "loss": 0.0002,
      "step": 5000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9987511511734993,
      "eval_f1": 0.92797783933518,
      "eval_loss": 0.00769586768001318,
      "eval_precision": 0.9194876486733761,
      "eval_recall": 0.9366262814538676,
      "eval_runtime": 15.2047,
      "eval_samples_per_second": 456.832,
      "eval_steps_per_second": 57.153,
      "step": 5070
    },
    {
      "epoch": 10.0,
      "step": 5070,
      "total_flos": 1.394810359803495e+16,
      "train_loss": 0.0028968164414402532,
      "train_runtime": 2196.5741,
      "train_samples_per_second": 147.716,
      "train_steps_per_second": 2.308
    }
  ],
  "logging_steps": 500,
  "max_steps": 5070,
  "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": 1.394810359803495e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}