{
  "best_global_step": 264,
  "best_metric": 0.4656164050102234,
  "best_model_checkpoint": "tiny_bert_rand_50_v2_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": 7.291563987731934,
      "learning_rate": 4.9e-05,
      "loss": 0.4222,
      "step": 264
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8096330275229358,
      "eval_loss": 0.4656164050102234,
      "eval_runtime": 0.2601,
      "eval_samples_per_second": 3353.151,
      "eval_steps_per_second": 15.381,
      "step": 264
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.364565372467041,
      "learning_rate": 4.8e-05,
      "loss": 0.2394,
      "step": 528
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7912844036697247,
      "eval_loss": 0.586814820766449,
      "eval_runtime": 0.281,
      "eval_samples_per_second": 3102.775,
      "eval_steps_per_second": 14.233,
      "step": 528
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.200972080230713,
      "learning_rate": 4.7e-05,
      "loss": 0.1886,
      "step": 792
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7912844036697247,
      "eval_loss": 0.5449909567832947,
      "eval_runtime": 0.2607,
      "eval_samples_per_second": 3344.428,
      "eval_steps_per_second": 15.341,
      "step": 792
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.045272350311279,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.1585,
      "step": 1056
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7947247706422018,
      "eval_loss": 0.6403250098228455,
      "eval_runtime": 0.2673,
      "eval_samples_per_second": 3261.843,
      "eval_steps_per_second": 14.963,
      "step": 1056
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.578564643859863,
      "learning_rate": 4.5e-05,
      "loss": 0.1306,
      "step": 1320
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7855504587155964,
      "eval_loss": 0.6641788482666016,
      "eval_runtime": 0.2607,
      "eval_samples_per_second": 3344.266,
      "eval_steps_per_second": 15.341,
      "step": 1320
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.683089733123779,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.1116,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7809633027522935,
      "eval_loss": 0.7982751131057739,
      "eval_runtime": 0.2583,
      "eval_samples_per_second": 3376.252,
      "eval_steps_per_second": 15.487,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "step": 1584,
      "total_flos": 1.0596790573590528e+16,
      "train_loss": 0.20846537748972574,
      "train_runtime": 218.8625,
      "train_samples_per_second": 15386.142,
      "train_steps_per_second": 60.312
    }
  ],
  "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
}