{
  "best_metric": 0.6981092095375061,
  "best_model_checkpoint": "hBERTv2_new_no_pretrain_rte/checkpoint-80",
  "epoch": 9.0,
  "global_step": 180,
  "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": 0.7697,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5270758122743683,
      "eval_loss": 0.7525500059127808,
      "eval_runtime": 1.2347,
      "eval_samples_per_second": 224.352,
      "eval_steps_per_second": 2.43,
      "step": 20
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.7285,
      "step": 40
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5270758122743683,
      "eval_loss": 0.7207568883895874,
      "eval_runtime": 1.2348,
      "eval_samples_per_second": 224.333,
      "eval_steps_per_second": 2.43,
      "step": 40
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.76e-05,
      "loss": 0.7201,
      "step": 60
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5342960288808665,
      "eval_loss": 0.711172878742218,
      "eval_runtime": 1.2352,
      "eval_samples_per_second": 224.258,
      "eval_steps_per_second": 2.429,
      "step": 60
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.680000000000001e-05,
      "loss": 0.7043,
      "step": 80
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5306859205776173,
      "eval_loss": 0.6981092095375061,
      "eval_runtime": 1.2363,
      "eval_samples_per_second": 224.056,
      "eval_steps_per_second": 2.427,
      "step": 80
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.6e-05,
      "loss": 0.6569,
      "step": 100
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5234657039711191,
      "eval_loss": 0.7251222133636475,
      "eval_runtime": 1.2329,
      "eval_samples_per_second": 224.67,
      "eval_steps_per_second": 2.433,
      "step": 100
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.52e-05,
      "loss": 0.5762,
      "step": 120
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.47653429602888087,
      "eval_loss": 0.8571105003356934,
      "eval_runtime": 1.2323,
      "eval_samples_per_second": 224.79,
      "eval_steps_per_second": 2.435,
      "step": 120
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.44e-05,
      "loss": 0.4336,
      "step": 140
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.47653429602888087,
      "eval_loss": 0.9540057182312012,
      "eval_runtime": 1.2314,
      "eval_samples_per_second": 224.941,
      "eval_steps_per_second": 2.436,
      "step": 140
    },
    {
      "epoch": 8.0,
      "learning_rate": 3.3600000000000004e-05,
      "loss": 0.3299,
      "step": 160
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.48375451263537905,
      "eval_loss": 1.2463710308074951,
      "eval_runtime": 1.2289,
      "eval_samples_per_second": 225.397,
      "eval_steps_per_second": 2.441,
      "step": 160
    },
    {
      "epoch": 9.0,
      "learning_rate": 3.28e-05,
      "loss": 0.2561,
      "step": 180
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.5018050541516246,
      "eval_loss": 1.4298744201660156,
      "eval_runtime": 1.2283,
      "eval_samples_per_second": 225.522,
      "eval_steps_per_second": 2.442,
      "step": 180
    },
    {
      "epoch": 9.0,
      "step": 180,
      "total_flos": 3279460698685440.0,
      "train_loss": 0.5750118308597141,
      "train_runtime": 406.7196,
      "train_samples_per_second": 306.108,
      "train_steps_per_second": 2.459
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 50,
  "total_flos": 3279460698685440.0,
  "trial_name": null,
  "trial_params": null
}