trainer_state.json

{
  "best_metric": 0.863960065934798,
  "best_model_checkpoint": "tmp_ner_fantastic-bale-09_44/run-61/checkpoint-675",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 675,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9783235867446394,
      "eval_loss": 0.06952951103448868,
      "eval_macro_f1": 0.6359234331864915,
      "eval_macro_precision": 0.8484880913225343,
      "eval_macro_recall": 0.621665816946364,
      "eval_runtime": 0.6216,
      "eval_samples_per_second": 160.873,
      "eval_steps_per_second": 20.913,
      "step": 75
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.983391812865497,
      "eval_loss": 0.056511040776968,
      "eval_macro_f1": 0.7614548378523822,
      "eval_macro_precision": 0.8731710257534685,
      "eval_macro_recall": 0.7203600182300229,
      "eval_runtime": 0.6015,
      "eval_samples_per_second": 166.249,
      "eval_steps_per_second": 21.612,
      "step": 150
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9857309941520468,
      "eval_loss": 0.05191269889473915,
      "eval_macro_f1": 0.8172545857097553,
      "eval_macro_precision": 0.8413749539052772,
      "eval_macro_recall": 0.7970101814719535,
      "eval_runtime": 0.6777,
      "eval_samples_per_second": 147.557,
      "eval_steps_per_second": 19.182,
      "step": 225
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9871734892787525,
      "eval_loss": 0.055695317685604095,
      "eval_macro_f1": 0.8405769067306196,
      "eval_macro_precision": 0.8557959065634769,
      "eval_macro_recall": 0.8269452880439045,
      "eval_runtime": 0.6377,
      "eval_samples_per_second": 156.826,
      "eval_steps_per_second": 20.387,
      "step": 300
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9875243664717349,
      "eval_loss": 0.055003080517053604,
      "eval_macro_f1": 0.8540405601187896,
      "eval_macro_precision": 0.8983484203175353,
      "eval_macro_recall": 0.8221656291922347,
      "eval_runtime": 0.6394,
      "eval_samples_per_second": 156.406,
      "eval_steps_per_second": 20.333,
      "step": 375
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9878362573099415,
      "eval_loss": 0.060502711683511734,
      "eval_macro_f1": 0.8610460620824656,
      "eval_macro_precision": 0.8865353357904526,
      "eval_macro_recall": 0.8387695106889209,
      "eval_runtime": 0.6171,
      "eval_samples_per_second": 162.056,
      "eval_steps_per_second": 21.067,
      "step": 450
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.02602095529437065,
      "learning_rate": 3.3881089787380476e-05,
      "loss": 0.08,
      "step": 500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9864327485380117,
      "eval_loss": 0.06403131783008575,
      "eval_macro_f1": 0.836324040811885,
      "eval_macro_precision": 0.8309543877948833,
      "eval_macro_recall": 0.8430665699031182,
      "eval_runtime": 0.6657,
      "eval_samples_per_second": 150.212,
      "eval_steps_per_second": 19.528,
      "step": 525
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9874463937621832,
      "eval_loss": 0.06809797883033752,
      "eval_macro_f1": 0.853127015308474,
      "eval_macro_precision": 0.871470843170948,
      "eval_macro_recall": 0.8370896203600997,
      "eval_runtime": 0.6629,
      "eval_samples_per_second": 150.862,
      "eval_steps_per_second": 19.612,
      "step": 600
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9883040935672515,
      "eval_loss": 0.06698578596115112,
      "eval_macro_f1": 0.863960065934798,
      "eval_macro_precision": 0.8939098518285944,
      "eval_macro_recall": 0.8388049073611367,
      "eval_runtime": 0.6334,
      "eval_samples_per_second": 157.89,
      "eval_steps_per_second": 20.526,
      "step": 675
    }
  ],
  "logging_steps": 500,
  "max_steps": 2400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 32,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 768333841626390.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.2369194386745274e-05,
    "per_device_train_batch_size": 8,
    "warmup_ratio": 0.009641097927077978,
    "weight_decay": 0.11095292966544487
  }
}