{
  "best_metric": 1.0981956720352173,
  "best_model_checkpoint": "hBERTv2_new_no_pretrain_mnli/checkpoint-6136",
  "epoch": 7.0,
  "global_step": 21476,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 3.9200000000000004e-05,
      "loss": 1.1022,
      "step": 3068
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.0985970497131348,
      "eval_runtime": 42.8492,
      "eval_samples_per_second": 229.059,
      "eval_steps_per_second": 1.797,
      "step": 3068
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 1.0988,
      "step": 6136
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3544574630667346,
      "eval_loss": 1.0981956720352173,
      "eval_runtime": 42.7817,
      "eval_samples_per_second": 229.421,
      "eval_steps_per_second": 1.8,
      "step": 6136
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.76e-05,
      "loss": 1.0987,
      "step": 9204
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3273560876209883,
      "eval_loss": 1.0986144542694092,
      "eval_runtime": 42.6833,
      "eval_samples_per_second": 229.949,
      "eval_steps_per_second": 1.804,
      "step": 9204
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.680000000000001e-05,
      "loss": 1.0988,
      "step": 12272
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.0987833738327026,
      "eval_runtime": 42.6772,
      "eval_samples_per_second": 229.983,
      "eval_steps_per_second": 1.804,
      "step": 12272
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.6e-05,
      "loss": 1.0986,
      "step": 15340
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3273560876209883,
      "eval_loss": 1.0986013412475586,
      "eval_runtime": 42.8795,
      "eval_samples_per_second": 228.897,
      "eval_steps_per_second": 1.796,
      "step": 15340
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.52e-05,
      "loss": 1.0987,
      "step": 18408
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.0986175537109375,
      "eval_runtime": 42.7584,
      "eval_samples_per_second": 229.546,
      "eval_steps_per_second": 1.801,
      "step": 18408
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.44e-05,
      "loss": 1.0986,
      "step": 21476
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.31818644931227713,
      "eval_loss": 1.098616600036621,
      "eval_runtime": 42.7391,
      "eval_samples_per_second": 229.649,
      "eval_steps_per_second": 1.802,
      "step": 21476
    },
    {
      "epoch": 7.0,
      "step": 21476,
      "total_flos": 4.022770393541509e+17,
      "train_loss": 1.099199021855065,
      "train_runtime": 36252.3204,
      "train_samples_per_second": 541.623,
      "train_steps_per_second": 4.231
    }
  ],
  "max_steps": 153400,
  "num_train_epochs": 50,
  "total_flos": 4.022770393541509e+17,
  "trial_name": null,
  "trial_params": null
}