trainer_state.json

{
  "best_metric": 0.6180860996246338,
  "best_model_checkpoint": "hBERTv2_data_aug_cola/checkpoint-2505",
  "epoch": 8.0,
  "global_step": 6680,
  "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": 0.6082,
      "step": 835
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6237233281135559,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.2319,
      "eval_samples_per_second": 846.646,
      "eval_steps_per_second": 4.059,
      "step": 835
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8001197604790424e-05,
      "loss": 0.6068,
      "step": 1670
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6185952425003052,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.2376,
      "eval_samples_per_second": 842.788,
      "eval_steps_per_second": 4.04,
      "step": 1670
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.700119760479042e-05,
      "loss": 0.6064,
      "step": 2505
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6180860996246338,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.2346,
      "eval_samples_per_second": 844.783,
      "eval_steps_per_second": 4.05,
      "step": 2505
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.6001197604790416e-05,
      "loss": 0.6062,
      "step": 3340
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6217709183692932,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.235,
      "eval_samples_per_second": 844.562,
      "eval_steps_per_second": 4.049,
      "step": 3340
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.5001197604790425e-05,
      "loss": 0.6061,
      "step": 4175
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6211623549461365,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.2344,
      "eval_samples_per_second": 844.918,
      "eval_steps_per_second": 4.05,
      "step": 4175
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.400119760479042e-05,
      "loss": 0.6062,
      "step": 5010
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6185929179191589,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.2333,
      "eval_samples_per_second": 845.728,
      "eval_steps_per_second": 4.054,
      "step": 5010
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.3001197604790424e-05,
      "loss": 0.606,
      "step": 5845
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.618870735168457,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.2325,
      "eval_samples_per_second": 846.237,
      "eval_steps_per_second": 4.057,
      "step": 5845
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.200119760479042e-05,
      "loss": 0.6062,
      "step": 6680
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.6202924847602844,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.2311,
      "eval_samples_per_second": 847.224,
      "eval_steps_per_second": 4.061,
      "step": 6680
    },
    {
      "epoch": 8.0,
      "step": 6680,
      "total_flos": 2.1284586608656384e+17,
      "train_loss": 0.6065069872462107,
      "train_runtime": 5969.0208,
      "train_samples_per_second": 1789.314,
      "train_steps_per_second": 6.994
    }
  ],
  "max_steps": 41750,
  "num_train_epochs": 50,
  "total_flos": 2.1284586608656384e+17,
  "trial_name": null,
  "trial_params": null
}