checkpoint-180/trainer_state.json

{
  "best_metric": 0.8109192582521296,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-100",
  "epoch": 20.0,
  "eval_steps": 100,
  "global_step": 180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.555555555555555,
      "grad_norm": 5.775369644165039,
      "learning_rate": 0.0002768979638879761,
      "loss": 0.9596,
      "step": 50
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 1.9409778118133545,
      "learning_rate": 0.0001558163056885225,
      "loss": 0.57,
      "step": 100
    },
    {
      "epoch": 11.11111111111111,
      "eval_accuracy": 0.8095238095238095,
      "eval_confusion_matrix": [
        [
          69,
          11,
          1,
          3
        ],
        [
          9,
          37,
          10,
          0
        ],
        [
          3,
          13,
          58,
          0
        ],
        [
          2,
          0,
          0,
          57
        ]
      ],
      "eval_f1": 0.8109192582521296,
      "eval_loss": 0.7797720432281494,
      "eval_normalized_confusion_matrix": [
        [
          0.8214285714285714,
          0.13095238095238096,
          0.011904761904761904,
          0.03571428571428571
        ],
        [
          0.16071428571428573,
          0.6607142857142857,
          0.17857142857142858,
          0.0
        ],
        [
          0.04054054054054054,
          0.17567567567567569,
          0.7837837837837838,
          0.0
        ],
        [
          0.03389830508474576,
          0.0,
          0.0,
          0.9661016949152542
        ]
      ],
      "eval_precision": 0.8133752269841887,
      "eval_recall": 0.8095238095238095,
      "eval_runtime": 2.8407,
      "eval_samples_per_second": 96.102,
      "eval_steps_per_second": 1.76,
      "step": 100
    },
    {
      "epoch": 16.666666666666668,
      "grad_norm": 0.1650346964597702,
      "learning_rate": 2.9681521086743422e-05,
      "loss": 0.3729,
      "step": 150
    }
  ],
  "logging_steps": 50,
  "max_steps": 180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.9578139008e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}