checkpoint-182/trainer_state.json

{
  "best_metric": 0.8516746411483254,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-182",
  "epoch": 3.989041095890411,
  "eval_steps": 500,
  "global_step": 182,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9863013698630136,
      "eval_accuracy": 0.7942583732057417,
      "eval_loss": 0.5718334913253784,
      "eval_runtime": 1.0678,
      "eval_samples_per_second": 391.448,
      "eval_steps_per_second": 49.633,
      "step": 45
    },
    {
      "epoch": 1.9945205479452055,
      "eval_accuracy": 0.80622009569378,
      "eval_loss": 0.45444098114967346,
      "eval_runtime": 1.0491,
      "eval_samples_per_second": 398.444,
      "eval_steps_per_second": 50.52,
      "step": 91
    },
    {
      "epoch": 2.9808219178082194,
      "eval_accuracy": 0.8397129186602871,
      "eval_loss": 0.3911355435848236,
      "eval_runtime": 1.0412,
      "eval_samples_per_second": 401.464,
      "eval_steps_per_second": 50.903,
      "step": 136
    },
    {
      "epoch": 3.989041095890411,
      "eval_accuracy": 0.8516746411483254,
      "eval_loss": 0.431730717420578,
      "eval_runtime": 1.0687,
      "eval_samples_per_second": 391.122,
      "eval_steps_per_second": 49.592,
      "step": 182
    }
  ],
  "logging_steps": 500,
  "max_steps": 270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.655386931456e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}