{
  "best_metric": 0.4396927058696747,
  "best_model_checkpoint": "bert_tiny_lda_5_v1_sst2/checkpoint-264",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1584,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 9.570955276489258,
      "learning_rate": 4.9e-05,
      "loss": 0.402,
      "step": 264
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8153669724770642,
      "eval_loss": 0.4396927058696747,
      "eval_runtime": 0.2768,
      "eval_samples_per_second": 3150.401,
      "eval_steps_per_second": 14.451,
      "step": 264
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.17089557647705,
      "learning_rate": 4.8e-05,
      "loss": 0.2385,
      "step": 528
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8038990825688074,
      "eval_loss": 0.49887505173683167,
      "eval_runtime": 0.2789,
      "eval_samples_per_second": 3126.276,
      "eval_steps_per_second": 14.341,
      "step": 528
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.174217224121094,
      "learning_rate": 4.7e-05,
      "loss": 0.1813,
      "step": 792
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7970183486238532,
      "eval_loss": 0.5259420871734619,
      "eval_runtime": 0.2888,
      "eval_samples_per_second": 3019.151,
      "eval_steps_per_second": 13.849,
      "step": 792
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.113431930541992,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.1449,
      "step": 1056
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8004587155963303,
      "eval_loss": 0.5909135341644287,
      "eval_runtime": 0.2819,
      "eval_samples_per_second": 3093.767,
      "eval_steps_per_second": 14.192,
      "step": 1056
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.880650043487549,
      "learning_rate": 4.5e-05,
      "loss": 0.1159,
      "step": 1320
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8027522935779816,
      "eval_loss": 0.6297979950904846,
      "eval_runtime": 0.2757,
      "eval_samples_per_second": 3162.953,
      "eval_steps_per_second": 14.509,
      "step": 1320
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.169188976287842,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.0955,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7935779816513762,
      "eval_loss": 0.6731319427490234,
      "eval_runtime": 0.2813,
      "eval_samples_per_second": 3100.384,
      "eval_steps_per_second": 14.222,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "step": 1584,
      "total_flos": 1.0596790573590528e+16,
      "train_loss": 0.19634188305247913,
      "train_runtime": 225.2591,
      "train_samples_per_second": 14949.233,
      "train_steps_per_second": 58.599
    }
  ],
  "logging_steps": 1,
  "max_steps": 13200,
  "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": 1.0596790573590528e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}