{
  "best_metric": 0.6966096758842468,
  "best_model_checkpoint": "bert_uncased_L-2_H-128_A-2_mnli/checkpoint-16874",
  "epoch": 16.0,
  "eval_steps": 500,
  "global_step": 24544,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.641183853149414,
      "learning_rate": 4.9e-05,
      "loss": 0.9155,
      "step": 1534
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6342333163525217,
      "eval_loss": 0.8197218775749207,
      "eval_runtime": 3.1144,
      "eval_samples_per_second": 3151.502,
      "eval_steps_per_second": 12.523,
      "step": 1534
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.0699892044067383,
      "learning_rate": 4.8e-05,
      "loss": 0.8189,
      "step": 3068
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6625573102394294,
      "eval_loss": 0.7689471244812012,
      "eval_runtime": 3.0712,
      "eval_samples_per_second": 3195.829,
      "eval_steps_per_second": 12.699,
      "step": 3068
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.7944191694259644,
      "learning_rate": 4.7e-05,
      "loss": 0.7747,
      "step": 4602
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6760061130922058,
      "eval_loss": 0.7416538596153259,
      "eval_runtime": 3.0841,
      "eval_samples_per_second": 3182.445,
      "eval_steps_per_second": 12.645,
      "step": 4602
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.8538000583648682,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.7449,
      "step": 6136
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6851757514009169,
      "eval_loss": 0.7284622192382812,
      "eval_runtime": 3.0649,
      "eval_samples_per_second": 3202.403,
      "eval_steps_per_second": 12.725,
      "step": 6136
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.2576873302459717,
      "learning_rate": 4.5e-05,
      "loss": 0.7198,
      "step": 7670
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.693428425878757,
      "eval_loss": 0.7110932469367981,
      "eval_runtime": 3.0825,
      "eval_samples_per_second": 3184.117,
      "eval_steps_per_second": 12.652,
      "step": 7670
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.2374134063720703,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6996,
      "step": 9204
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6977075904228223,
      "eval_loss": 0.7117594480514526,
      "eval_runtime": 3.0866,
      "eval_samples_per_second": 3179.874,
      "eval_steps_per_second": 12.635,
      "step": 9204
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.3460779190063477,
      "learning_rate": 4.3e-05,
      "loss": 0.6812,
      "step": 10738
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7030056036678554,
      "eval_loss": 0.7004757523536682,
      "eval_runtime": 3.0836,
      "eval_samples_per_second": 3182.923,
      "eval_steps_per_second": 12.647,
      "step": 10738
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.158047914505005,
      "learning_rate": 4.2e-05,
      "loss": 0.6649,
      "step": 12272
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7043301069791136,
      "eval_loss": 0.6981356739997864,
      "eval_runtime": 3.0881,
      "eval_samples_per_second": 3178.334,
      "eval_steps_per_second": 12.629,
      "step": 12272
    },
    {
      "epoch": 9.0,
      "grad_norm": 2.4495298862457275,
      "learning_rate": 4.1e-05,
      "loss": 0.6491,
      "step": 13806
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7036169128884361,
      "eval_loss": 0.7056555151939392,
      "eval_runtime": 3.0711,
      "eval_samples_per_second": 3195.888,
      "eval_steps_per_second": 12.699,
      "step": 13806
    },
    {
      "epoch": 10.0,
      "grad_norm": 2.2467546463012695,
      "learning_rate": 4e-05,
      "loss": 0.6358,
      "step": 15340
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.7076923076923077,
      "eval_loss": 0.698304295539856,
      "eval_runtime": 3.0715,
      "eval_samples_per_second": 3195.477,
      "eval_steps_per_second": 12.697,
      "step": 15340
    },
    {
      "epoch": 11.0,
      "grad_norm": 2.603757619857788,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.6224,
      "step": 16874
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.7063678043810494,
      "eval_loss": 0.6966096758842468,
      "eval_runtime": 3.0786,
      "eval_samples_per_second": 3188.18,
      "eval_steps_per_second": 12.668,
      "step": 16874
    },
    {
      "epoch": 12.0,
      "grad_norm": 2.9877541065216064,
      "learning_rate": 3.8e-05,
      "loss": 0.6109,
      "step": 18408
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.7145185939887927,
      "eval_loss": 0.7001488208770752,
      "eval_runtime": 3.1144,
      "eval_samples_per_second": 3151.457,
      "eval_steps_per_second": 12.522,
      "step": 18408
    },
    {
      "epoch": 13.0,
      "grad_norm": 2.9254136085510254,
      "learning_rate": 3.7e-05,
      "loss": 0.5994,
      "step": 19942
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.7112582781456953,
      "eval_loss": 0.7014375329017639,
      "eval_runtime": 3.0536,
      "eval_samples_per_second": 3214.286,
      "eval_steps_per_second": 12.772,
      "step": 19942
    },
    {
      "epoch": 14.0,
      "grad_norm": 2.3332672119140625,
      "learning_rate": 3.6e-05,
      "loss": 0.5872,
      "step": 21476
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.7084055017829852,
      "eval_loss": 0.7061210870742798,
      "eval_runtime": 3.0601,
      "eval_samples_per_second": 3207.409,
      "eval_steps_per_second": 12.745,
      "step": 21476
    },
    {
      "epoch": 15.0,
      "grad_norm": 3.173841953277588,
      "learning_rate": 3.5e-05,
      "loss": 0.5779,
      "step": 23010
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.716760061130922,
      "eval_loss": 0.7053535580635071,
      "eval_runtime": 3.016,
      "eval_samples_per_second": 3254.334,
      "eval_steps_per_second": 12.931,
      "step": 23010
    },
    {
      "epoch": 16.0,
      "grad_norm": 2.5497801303863525,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.5681,
      "step": 24544
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.7147223637289862,
      "eval_loss": 0.7059070467948914,
      "eval_runtime": 3.034,
      "eval_samples_per_second": 3234.976,
      "eval_steps_per_second": 12.854,
      "step": 24544
    },
    {
      "epoch": 16.0,
      "step": 24544,
      "total_flos": 3992627397378048.0,
      "train_loss": 0.6793889937220527,
      "train_runtime": 2308.8944,
      "train_samples_per_second": 8504.114,
      "train_steps_per_second": 33.219
    }
  ],
  "logging_steps": 1,
  "max_steps": 76700,
  "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": 3992627397378048.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}