run-7/checkpoint-86/trainer_state.json

{
  "best_metric": 4.218845844268799,
  "best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-7/checkpoint-86",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 86,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.03513513513513514,
      "eval_f1": 0.005422726152329307,
      "eval_loss": 4.674714088439941,
      "eval_precision": 0.0045026606631191155,
      "eval_recall": 0.006815365551425031,
      "eval_runtime": 0.3698,
      "eval_samples_per_second": 786.889,
      "eval_steps_per_second": 100.051,
      "step": 43
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.12372372372372373,
      "eval_f1": 0.01993148551853005,
      "eval_loss": 4.218845844268799,
      "eval_precision": 0.020037570444583593,
      "eval_recall": 0.01982651796778191,
      "eval_runtime": 0.6278,
      "eval_samples_per_second": 463.528,
      "eval_steps_per_second": 58.937,
      "step": 86
    }
  ],
  "logging_steps": 500,
  "max_steps": 516,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "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": 0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.57667136663323e-05,
    "num_train_epochs": 12,
    "per_device_train_batch_size": 32,
    "warmup_steps": 334,
    "weight_decay": 0.22302258049583742
  }
}