checkpoint-100/trainer_state.json

{
  "best_metric": 0.8240470006184293,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-100",
  "epoch": 22.22222222222222,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 11.11111111111111,
      "grad_norm": 3.250781297683716,
      "learning_rate": 0.00027532317171194046,
      "loss": 0.8288,
      "step": 50
    },
    {
      "epoch": 11.11111111111111,
      "eval_accuracy": 0.8131868131868132,
      "eval_confusion_matrix": [
        [
          60,
          11,
          1,
          7
        ],
        [
          9,
          40,
          17,
          0
        ],
        [
          0,
          6,
          63,
          0
        ],
        [
          0,
          0,
          0,
          59
        ]
      ],
      "eval_f1": 0.8081937118034679,
      "eval_loss": 0.7091822624206543,
      "eval_precision": 0.8110642218193705,
      "eval_recall": 0.8131868131868132,
      "eval_runtime": 3.0071,
      "eval_samples_per_second": 90.786,
      "eval_steps_per_second": 0.998,
      "step": 50
    },
    {
      "epoch": 22.22222222222222,
      "grad_norm": 2.9194233417510986,
      "learning_rate": 0.00015290869976577364,
      "loss": 0.4125,
      "step": 100
    },
    {
      "epoch": 22.22222222222222,
      "eval_accuracy": 0.8278388278388278,
      "eval_confusion_matrix": [
        [
          63,
          7,
          2,
          7
        ],
        [
          5,
          41,
          20,
          0
        ],
        [
          0,
          6,
          63,
          0
        ],
        [
          0,
          0,
          0,
          59
        ]
      ],
      "eval_f1": 0.8240470006184293,
      "eval_loss": 0.8097973465919495,
      "eval_precision": 0.8321827410062705,
      "eval_recall": 0.8278388278388278,
      "eval_runtime": 3.0011,
      "eval_samples_per_second": 90.968,
      "eval_steps_per_second": 1.0,
      "step": 100
    }
  ],
  "logging_steps": 50,
  "max_steps": 180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 45,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.511815490816e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}