{
  "best_metric": 0.6915754675865173,
  "best_model_checkpoint": "hBERTv1_new_pretrain_w_init__rte/checkpoint-40",
  "epoch": 7.0,
  "global_step": 140,
  "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": 0.7478,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5270758122743683,
      "eval_loss": 0.6921254396438599,
      "eval_runtime": 0.5047,
      "eval_samples_per_second": 548.867,
      "eval_steps_per_second": 5.944,
      "step": 20
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.7195,
      "step": 40
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5270758122743683,
      "eval_loss": 0.6915754675865173,
      "eval_runtime": 0.5093,
      "eval_samples_per_second": 543.914,
      "eval_steps_per_second": 5.891,
      "step": 40
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.76e-05,
      "loss": 0.7087,
      "step": 60
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5270758122743683,
      "eval_loss": 0.6944946646690369,
      "eval_runtime": 0.5115,
      "eval_samples_per_second": 541.534,
      "eval_steps_per_second": 5.865,
      "step": 60
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.680000000000001e-05,
      "loss": 0.7025,
      "step": 80
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5379061371841155,
      "eval_loss": 0.6916882991790771,
      "eval_runtime": 0.5103,
      "eval_samples_per_second": 542.815,
      "eval_steps_per_second": 5.879,
      "step": 80
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.6e-05,
      "loss": 0.721,
      "step": 100
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5379061371841155,
      "eval_loss": 0.692407488822937,
      "eval_runtime": 0.5081,
      "eval_samples_per_second": 545.175,
      "eval_steps_per_second": 5.904,
      "step": 100
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.52e-05,
      "loss": 0.6992,
      "step": 120
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4620938628158845,
      "eval_loss": 0.7301867008209229,
      "eval_runtime": 0.5054,
      "eval_samples_per_second": 548.056,
      "eval_steps_per_second": 5.936,
      "step": 120
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.44e-05,
      "loss": 0.685,
      "step": 140
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5379061371841155,
      "eval_loss": 0.712432324886322,
      "eval_runtime": 0.5054,
      "eval_samples_per_second": 548.13,
      "eval_steps_per_second": 5.936,
      "step": 140
    },
    {
      "epoch": 7.0,
      "step": 140,
      "total_flos": 2581326716731392.0,
      "train_loss": 0.7119564056396485,
      "train_runtime": 150.7778,
      "train_samples_per_second": 825.718,
      "train_steps_per_second": 6.632
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 50,
  "total_flos": 2581326716731392.0,
  "trial_name": null,
  "trial_params": null
}