{
  "best_metric": 0.6890723705291748,
  "best_model_checkpoint": "bert_tiny_lda_5_v1_book_rte/checkpoint-30",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.535357654094696,
      "learning_rate": 4.9e-05,
      "loss": 0.7089,
      "step": 10
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.48375451263537905,
      "eval_loss": 0.6936625838279724,
      "eval_runtime": 0.0949,
      "eval_samples_per_second": 2918.961,
      "eval_steps_per_second": 21.076,
      "step": 10
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6238802671432495,
      "learning_rate": 4.8e-05,
      "loss": 0.6904,
      "step": 20
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5306859205776173,
      "eval_loss": 0.689996063709259,
      "eval_runtime": 0.1041,
      "eval_samples_per_second": 2661.531,
      "eval_steps_per_second": 19.217,
      "step": 20
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5024715662002563,
      "learning_rate": 4.7e-05,
      "loss": 0.6812,
      "step": 30
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5523465703971119,
      "eval_loss": 0.6890723705291748,
      "eval_runtime": 0.0954,
      "eval_samples_per_second": 2904.229,
      "eval_steps_per_second": 20.969,
      "step": 30
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7870733737945557,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.6636,
      "step": 40
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5776173285198556,
      "eval_loss": 0.6905460357666016,
      "eval_runtime": 0.098,
      "eval_samples_per_second": 2826.46,
      "eval_steps_per_second": 20.408,
      "step": 40
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.5894250869750977,
      "learning_rate": 4.5e-05,
      "loss": 0.628,
      "step": 50
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.516245487364621,
      "eval_loss": 0.7492067813873291,
      "eval_runtime": 0.1065,
      "eval_samples_per_second": 2600.359,
      "eval_steps_per_second": 18.775,
      "step": 50
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.2344086170196533,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.583,
      "step": 60
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5415162454873647,
      "eval_loss": 0.7529385089874268,
      "eval_runtime": 0.0937,
      "eval_samples_per_second": 2955.343,
      "eval_steps_per_second": 21.338,
      "step": 60
    },
    {
      "epoch": 7.0,
      "grad_norm": 3.4890828132629395,
      "learning_rate": 4.3e-05,
      "loss": 0.4924,
      "step": 70
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5090252707581228,
      "eval_loss": 0.8327918648719788,
      "eval_runtime": 0.1018,
      "eval_samples_per_second": 2722.189,
      "eval_steps_per_second": 19.655,
      "step": 70
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.4623568058013916,
      "learning_rate": 4.2e-05,
      "loss": 0.3942,
      "step": 80
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5306859205776173,
      "eval_loss": 0.9865634441375732,
      "eval_runtime": 0.0959,
      "eval_samples_per_second": 2889.214,
      "eval_steps_per_second": 20.861,
      "step": 80
    },
    {
      "epoch": 8.0,
      "step": 80,
      "total_flos": 522373675991040.0,
      "train_loss": 0.6052042096853256,
      "train_runtime": 19.8861,
      "train_samples_per_second": 6260.643,
      "train_steps_per_second": 25.143
    }
  ],
  "logging_steps": 1,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 522373675991040.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}