checkpoint-597/trainer_state.json

{
  "best_metric": 0.9897435897435898,
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341",
  "epoch": 6.992679355783309,
  "eval_steps": 500,
  "global_step": 597,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9956076134699854,
      "eval_accuracy": 0.9538461538461539,
      "eval_f1": 0.953235199825453,
      "eval_loss": 0.13410410284996033,
      "eval_precision": 0.9543176332312968,
      "eval_recall": 0.9538461538461539,
      "eval_runtime": 5.9191,
      "eval_samples_per_second": 230.61,
      "eval_steps_per_second": 28.89,
      "step": 85
    },
    {
      "epoch": 1.9912152269399708,
      "eval_accuracy": 0.96996336996337,
      "eval_f1": 0.970275727358029,
      "eval_loss": 0.08308757096529007,
      "eval_precision": 0.9720059808561178,
      "eval_recall": 0.96996336996337,
      "eval_runtime": 5.9321,
      "eval_samples_per_second": 230.105,
      "eval_steps_per_second": 28.826,
      "step": 170
    },
    {
      "epoch": 2.998535871156662,
      "eval_accuracy": 0.9846153846153847,
      "eval_f1": 0.9845587007434289,
      "eval_loss": 0.05695493519306183,
      "eval_precision": 0.984652882646444,
      "eval_recall": 0.9846153846153847,
      "eval_runtime": 5.924,
      "eval_samples_per_second": 230.421,
      "eval_steps_per_second": 28.866,
      "step": 256
    },
    {
      "epoch": 3.994143484626647,
      "eval_accuracy": 0.9897435897435898,
      "eval_f1": 0.9897502348272303,
      "eval_loss": 0.03400224819779396,
      "eval_precision": 0.9897618176566864,
      "eval_recall": 0.9897435897435898,
      "eval_runtime": 5.9234,
      "eval_samples_per_second": 230.441,
      "eval_steps_per_second": 28.868,
      "step": 341
    },
    {
      "epoch": 4.989751098096632,
      "eval_accuracy": 0.9875457875457876,
      "eval_f1": 0.9876042969414931,
      "eval_loss": 0.04599935933947563,
      "eval_precision": 0.9879353582239604,
      "eval_recall": 0.9875457875457876,
      "eval_runtime": 5.9141,
      "eval_samples_per_second": 230.803,
      "eval_steps_per_second": 28.914,
      "step": 426
    },
    {
      "epoch": 5.856515373352855,
      "grad_norm": 0.020362911745905876,
      "learning_rate": 1.819507083000514e-05,
      "loss": 0.0707,
      "step": 500
    },
    {
      "epoch": 5.997071742313324,
      "eval_accuracy": 0.9897435897435898,
      "eval_f1": 0.9897761336599745,
      "eval_loss": 0.04312068223953247,
      "eval_precision": 0.9899308989239506,
      "eval_recall": 0.9897435897435898,
      "eval_runtime": 5.5776,
      "eval_samples_per_second": 244.727,
      "eval_steps_per_second": 30.658,
      "step": 512
    },
    {
      "epoch": 6.992679355783309,
      "eval_accuracy": 0.9882783882783883,
      "eval_f1": 0.9882934987415589,
      "eval_loss": 0.035927049815654755,
      "eval_precision": 0.9883282714000319,
      "eval_recall": 0.9882783882783883,
      "eval_runtime": 5.5806,
      "eval_samples_per_second": 244.596,
      "eval_steps_per_second": 30.642,
      "step": 597
    }
  ],
  "logging_steps": 500,
  "max_steps": 850,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.691905319552e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}