checkpoint-1890/trainer_state.json

{
  "best_global_step": 1890,
  "best_metric": 0.8640991774392113,
  "best_model_checkpoint": "outputs/runs/mbert/checkpoint-1890",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1890,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9968253968253968,
      "grad_norm": 2.8764171600341797,
      "learning_rate": 4.999432333543028e-06,
      "loss": 0.3922,
      "step": 314
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8576303179904168,
      "eval_f1": 0.8463278723071122,
      "eval_loss": 0.34177419543266296,
      "eval_precision": 0.8663865734795833,
      "eval_recall": 0.8368564126768949,
      "eval_runtime": 1.539,
      "eval_samples_per_second": 845.341,
      "eval_steps_per_second": 26.64,
      "step": 315
    },
    {
      "epoch": 1.9936507936507937,
      "grad_norm": 3.1037893295288086,
      "learning_rate": 4.996525669931999e-06,
      "loss": 0.2939,
      "step": 628
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.862621605924205,
      "eval_f1": 0.8567911162439183,
      "eval_loss": 0.30715054273605347,
      "eval_precision": 0.8570806369874044,
      "eval_recall": 0.8565085419444378,
      "eval_runtime": 1.5519,
      "eval_samples_per_second": 838.327,
      "eval_steps_per_second": 26.419,
      "step": 630
    },
    {
      "epoch": 2.9904761904761905,
      "grad_norm": 2.2518210411071777,
      "learning_rate": 4.991155236893945e-06,
      "loss": 0.2786,
      "step": 942
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8685930013068099,
      "eval_f1": 0.8614307154654214,
      "eval_loss": 0.3059610426425934,
      "eval_precision": 0.8669559804904288,
      "eval_recall": 0.8574043561902019,
      "eval_runtime": 1.5527,
      "eval_samples_per_second": 837.903,
      "eval_steps_per_second": 26.406,
      "step": 945
    },
    {
      "epoch": 3.9873015873015873,
      "grad_norm": 5.058016777038574,
      "learning_rate": 4.983326334397891e-06,
      "loss": 0.2663,
      "step": 1256
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8673224916509366,
      "eval_f1": 0.8565473676548805,
      "eval_loss": 0.3232356607913971,
      "eval_precision": 0.8784162677513533,
      "eval_recall": 0.8463548582123183,
      "eval_runtime": 1.5544,
      "eval_samples_per_second": 836.995,
      "eval_steps_per_second": 26.377,
      "step": 1260
    },
    {
      "epoch": 4.984126984126984,
      "grad_norm": 7.031896591186523,
      "learning_rate": 4.97304668862541e-06,
      "loss": 0.2563,
      "step": 1570
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8691012051691593,
      "eval_f1": 0.8625756064004395,
      "eval_loss": 0.300201952457428,
      "eval_precision": 0.8658918299079369,
      "eval_recall": 0.8598985796226895,
      "eval_runtime": 1.5582,
      "eval_samples_per_second": 834.947,
      "eval_steps_per_second": 26.313,
      "step": 1575
    },
    {
      "epoch": 5.980952380952381,
      "grad_norm": 10.076984405517578,
      "learning_rate": 4.9603264443458e-06,
      "loss": 0.2436,
      "step": 1884
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8702991142732684,
      "eval_f1": 0.8640991774392113,
      "eval_loss": 0.29937663674354553,
      "eval_precision": 0.8665212130630453,
      "eval_recall": 0.8620456410474242,
      "eval_runtime": 1.5549,
      "eval_samples_per_second": 836.703,
      "eval_steps_per_second": 26.368,
      "step": 1890
    }
  ],
  "logging_steps": 314,
  "max_steps": 31500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1974227645518848.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}