{
  "best_metric": 0.46561405062675476,
  "best_model_checkpoint": "bert_tiny_lda_20_v1_sst2/checkpoint-528",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 1848,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 12.078267097473145,
      "learning_rate": 4.9e-05,
      "loss": 0.4233,
      "step": 264
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7844036697247706,
      "eval_loss": 0.4931957721710205,
      "eval_runtime": 0.2795,
      "eval_samples_per_second": 3119.529,
      "eval_steps_per_second": 14.31,
      "step": 264
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.435814380645752,
      "learning_rate": 4.8e-05,
      "loss": 0.2592,
      "step": 528
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8165137614678899,
      "eval_loss": 0.46561405062675476,
      "eval_runtime": 0.2723,
      "eval_samples_per_second": 3202.14,
      "eval_steps_per_second": 14.689,
      "step": 528
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.6048450469970703,
      "learning_rate": 4.7e-05,
      "loss": 0.1987,
      "step": 792
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8130733944954128,
      "eval_loss": 0.47246110439300537,
      "eval_runtime": 0.2782,
      "eval_samples_per_second": 3134.998,
      "eval_steps_per_second": 14.381,
      "step": 792
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.613548755645752,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.161,
      "step": 1056
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8107798165137615,
      "eval_loss": 0.531734824180603,
      "eval_runtime": 0.278,
      "eval_samples_per_second": 3136.958,
      "eval_steps_per_second": 14.39,
      "step": 1056
    },
    {
      "epoch": 5.0,
      "grad_norm": 9.82017993927002,
      "learning_rate": 4.5e-05,
      "loss": 0.1363,
      "step": 1320
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8073394495412844,
      "eval_loss": 0.5661426782608032,
      "eval_runtime": 0.2752,
      "eval_samples_per_second": 3168.806,
      "eval_steps_per_second": 14.536,
      "step": 1320
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.2137458324432373,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.1147,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8084862385321101,
      "eval_loss": 0.6461686491966248,
      "eval_runtime": 0.2696,
      "eval_samples_per_second": 3234.111,
      "eval_steps_per_second": 14.835,
      "step": 1584
    },
    {
      "epoch": 7.0,
      "grad_norm": 4.09332799911499,
      "learning_rate": 4.3e-05,
      "loss": 0.0959,
      "step": 1848
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7970183486238532,
      "eval_loss": 0.7102797627449036,
      "eval_runtime": 0.2804,
      "eval_samples_per_second": 3109.959,
      "eval_steps_per_second": 14.266,
      "step": 1848
    },
    {
      "epoch": 7.0,
      "step": 1848,
      "total_flos": 1.2362922335855616e+16,
      "train_loss": 0.19844082836464885,
      "train_runtime": 261.6164,
      "train_samples_per_second": 12871.711,
      "train_steps_per_second": 50.456
    }
  ],
  "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": 1.2362922335855616e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}