trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_pretrain_qqp/checkpoint-2843",
  "epoch": 6.0,
  "global_step": 17058,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.9e-05,
      "loss": 0.0,
      "step": 2843
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6318327974276527,
      "eval_combined_score": 0.3159163987138264,
      "eval_f1": 0.0,
      "eval_loss": NaN,
      "eval_runtime": 69.9966,
      "eval_samples_per_second": 577.599,
      "eval_steps_per_second": 4.515,
      "step": 2843
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8e-05,
      "loss": 0.0,
      "step": 5686
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6318327974276527,
      "eval_combined_score": 0.3159163987138264,
      "eval_f1": 0.0,
      "eval_loss": NaN,
      "eval_runtime": 70.1515,
      "eval_samples_per_second": 576.324,
      "eval_steps_per_second": 4.505,
      "step": 5686
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.7e-05,
      "loss": 0.0,
      "step": 8529
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6318327974276527,
      "eval_combined_score": 0.3159163987138264,
      "eval_f1": 0.0,
      "eval_loss": NaN,
      "eval_runtime": 69.8055,
      "eval_samples_per_second": 579.181,
      "eval_steps_per_second": 4.527,
      "step": 8529
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.0,
      "step": 11372
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6318327974276527,
      "eval_combined_score": 0.3159163987138264,
      "eval_f1": 0.0,
      "eval_loss": NaN,
      "eval_runtime": 70.0897,
      "eval_samples_per_second": 576.832,
      "eval_steps_per_second": 4.509,
      "step": 11372
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.5e-05,
      "loss": 0.0,
      "step": 14215
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6318327974276527,
      "eval_combined_score": 0.3159163987138264,
      "eval_f1": 0.0,
      "eval_loss": NaN,
      "eval_runtime": 69.7345,
      "eval_samples_per_second": 579.77,
      "eval_steps_per_second": 4.531,
      "step": 14215
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.0,
      "step": 17058
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6318327974276527,
      "eval_combined_score": 0.3159163987138264,
      "eval_f1": 0.0,
      "eval_loss": NaN,
      "eval_runtime": 70.0089,
      "eval_samples_per_second": 577.498,
      "eval_steps_per_second": 4.514,
      "step": 17058
    },
    {
      "epoch": 6.0,
      "step": 17058,
      "total_flos": 6.545692508867789e+16,
      "train_loss": 0.0,
      "train_runtime": 9415.3889,
      "train_samples_per_second": 1932.188,
      "train_steps_per_second": 15.098
    }
  ],
  "max_steps": 142150,
  "num_train_epochs": 50,
  "total_flos": 6.545692508867789e+16,
  "trial_name": null,
  "trial_params": null
}