trainer_state.json

{
  "best_global_step": 3122,
  "best_metric": 0.26706157640660244,
  "best_model_checkpoint": "outputs/bilstm-spam-multiclass/checkpoint-3122",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 3122,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.797143280506134,
      "learning_rate": 0.0009997543852189499,
      "loss": 0.7942,
      "step": 446
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7290485192186515,
      "eval_f1": 0.21082361516034986,
      "eval_loss": 0.8068332076072693,
      "eval_precision": 0.1822621298046629,
      "eval_recall": 0.25,
      "eval_runtime": 6.2702,
      "eval_samples_per_second": 253.101,
      "eval_steps_per_second": 7.974,
      "step": 446
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6989365816116333,
      "learning_rate": 0.0009990155744361903,
      "loss": 0.7488,
      "step": 892
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7290485192186515,
      "eval_f1": 0.21082361516034986,
      "eval_loss": 0.7541048526763916,
      "eval_precision": 0.1822621298046629,
      "eval_recall": 0.25,
      "eval_runtime": 6.266,
      "eval_samples_per_second": 253.271,
      "eval_steps_per_second": 7.98,
      "step": 892
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9377701878547668,
      "learning_rate": 0.0009977842955283425,
      "loss": 0.7286,
      "step": 1338
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7290485192186515,
      "eval_f1": 0.21082361516034986,
      "eval_loss": 0.7448248863220215,
      "eval_precision": 0.1822621298046629,
      "eval_recall": 0.25,
      "eval_runtime": 6.2601,
      "eval_samples_per_second": 253.511,
      "eval_steps_per_second": 7.987,
      "step": 1338
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.436852216720581,
      "learning_rate": 0.0009960617636190344,
      "loss": 0.7228,
      "step": 1784
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7296786389413988,
      "eval_f1": 0.23500136448309822,
      "eval_loss": 0.7346429824829102,
      "eval_precision": 0.2942928298170524,
      "eval_recall": 0.2605128413143665,
      "eval_runtime": 6.2563,
      "eval_samples_per_second": 253.663,
      "eval_steps_per_second": 7.992,
      "step": 1784
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.0002644062042236,
      "learning_rate": 0.0009938496786392973,
      "loss": 0.7174,
      "step": 2230
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7227473219911783,
      "eval_f1": 0.2605779960514537,
      "eval_loss": 0.7398474812507629,
      "eval_precision": 0.2887123745819398,
      "eval_recall": 0.27392437805977743,
      "eval_runtime": 8.2774,
      "eval_samples_per_second": 191.726,
      "eval_steps_per_second": 6.041,
      "step": 2230
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7430670857429504,
      "learning_rate": 0.0009911502236499372,
      "loss": 0.7166,
      "step": 2676
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7315689981096408,
      "eval_f1": 0.22160087719298247,
      "eval_loss": 0.7539165616035461,
      "eval_precision": 0.37036890436985437,
      "eval_recall": 0.2549830103373283,
      "eval_runtime": 8.322,
      "eval_samples_per_second": 190.699,
      "eval_steps_per_second": 6.008,
      "step": 2676
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.7684730887413025,
      "learning_rate": 0.0009879660626871199,
      "loss": 0.7173,
      "step": 3122
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7334593572778828,
      "eval_f1": 0.26706157640660244,
      "eval_loss": 0.737380862236023,
      "eval_precision": 0.3129218010274318,
      "eval_recall": 0.2789705730929923,
      "eval_runtime": 8.4068,
      "eval_samples_per_second": 188.777,
      "eval_steps_per_second": 5.948,
      "step": 3122
    }
  ],
  "logging_steps": 446,
  "max_steps": 44600,
  "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": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}