trainer_state.json

{
  "best_metric": 0.3051736056804657,
  "best_model_checkpoint": "hf-ner-sample_004-gbert-base.model/checkpoint-230",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 230,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_f1": 0.0979020979020979,
      "eval_loss": 1.2133915424346924,
      "eval_precision": 0.1590909090909091,
      "eval_recall": 0.0707070707070707,
      "eval_runtime": 0.4132,
      "eval_samples_per_second": 142.792,
      "eval_steps_per_second": 7.261,
      "step": 23
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.4466338259441708,
      "eval_loss": 0.741108775138855,
      "eval_precision": 0.4358974358974359,
      "eval_recall": 0.45791245791245794,
      "eval_runtime": 0.3079,
      "eval_samples_per_second": 191.613,
      "eval_steps_per_second": 9.743,
      "step": 46
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.637873754152824,
      "eval_loss": 0.5308826565742493,
      "eval_precision": 0.6295081967213115,
      "eval_recall": 0.6464646464646465,
      "eval_runtime": 0.3155,
      "eval_samples_per_second": 187.003,
      "eval_steps_per_second": 9.509,
      "step": 69
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.6928327645051194,
      "eval_loss": 0.4319136440753937,
      "eval_precision": 0.7024221453287197,
      "eval_recall": 0.6835016835016835,
      "eval_runtime": 0.3102,
      "eval_samples_per_second": 190.21,
      "eval_steps_per_second": 9.672,
      "step": 92
    },
    {
      "epoch": 5.0,
      "eval_f1": 0.7133550488599348,
      "eval_loss": 0.3702440857887268,
      "eval_precision": 0.6908517350157729,
      "eval_recall": 0.7373737373737373,
      "eval_runtime": 0.3081,
      "eval_samples_per_second": 191.509,
      "eval_steps_per_second": 9.738,
      "step": 115
    },
    {
      "epoch": 6.0,
      "eval_f1": 0.7408637873754154,
      "eval_loss": 0.33849552273750305,
      "eval_precision": 0.7311475409836066,
      "eval_recall": 0.7508417508417509,
      "eval_runtime": 0.306,
      "eval_samples_per_second": 192.832,
      "eval_steps_per_second": 9.805,
      "step": 138
    },
    {
      "epoch": 7.0,
      "eval_f1": 0.7397708674304418,
      "eval_loss": 0.3240445554256439,
      "eval_precision": 0.7197452229299363,
      "eval_recall": 0.7609427609427609,
      "eval_runtime": 0.309,
      "eval_samples_per_second": 190.938,
      "eval_steps_per_second": 9.709,
      "step": 161
    },
    {
      "epoch": 8.0,
      "eval_f1": 0.763157894736842,
      "eval_loss": 0.31296223402023315,
      "eval_precision": 0.7459807073954984,
      "eval_recall": 0.7811447811447811,
      "eval_runtime": 0.3151,
      "eval_samples_per_second": 187.228,
      "eval_steps_per_second": 9.52,
      "step": 184
    },
    {
      "epoch": 9.0,
      "eval_f1": 0.7560581583198708,
      "eval_loss": 0.30645591020584106,
      "eval_precision": 0.7267080745341615,
      "eval_recall": 0.7878787878787878,
      "eval_runtime": 0.3136,
      "eval_samples_per_second": 188.12,
      "eval_steps_per_second": 9.565,
      "step": 207
    },
    {
      "epoch": 10.0,
      "eval_f1": 0.7585089141004862,
      "eval_loss": 0.3051736056804657,
      "eval_precision": 0.73125,
      "eval_recall": 0.7878787878787878,
      "eval_runtime": 0.4257,
      "eval_samples_per_second": 138.601,
      "eval_steps_per_second": 7.048,
      "step": 230
    }
  ],
  "logging_steps": 500,
  "max_steps": 230,
  "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": 312424744893732.0,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": null
}