trainer_state.json

{
  "best_metric": 0.28987887501716614,
  "best_model_checkpoint": "albert-base-v2-Tweet_About_Disaster_Or_Not/checkpoint-286",
  "epoch": 5.0,
  "global_step": 715,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.9972027972027975e-05,
      "loss": 0.7326,
      "step": 1
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.3598,
      "step": 143
    },
    {
      "epoch": 1.0,
      "eval_F1": 0.7495429616087751,
      "eval_Precision": 0.6612903225806451,
      "eval_Recall": 0.8649789029535865,
      "eval_accuracy": 0.8795074758135444,
      "eval_loss": 0.30249279737472534,
      "eval_runtime": 115.7537,
      "eval_samples_per_second": 9.823,
      "eval_steps_per_second": 0.156,
      "step": 143
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.2e-05,
      "loss": 0.234,
      "step": 286
    },
    {
      "epoch": 2.0,
      "eval_F1": 0.7784200385356455,
      "eval_Precision": 0.7163120567375887,
      "eval_Recall": 0.8523206751054853,
      "eval_accuracy": 0.8988566402814424,
      "eval_loss": 0.28987887501716614,
      "eval_runtime": 115.0134,
      "eval_samples_per_second": 9.886,
      "eval_steps_per_second": 0.157,
      "step": 286
    },
    {
      "epoch": 3.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1557,
      "step": 429
    },
    {
      "epoch": 3.0,
      "eval_F1": 0.7903930131004366,
      "eval_Precision": 0.8190045248868778,
      "eval_Recall": 0.7637130801687764,
      "eval_accuracy": 0.9155672823218998,
      "eval_loss": 0.3423578143119812,
      "eval_runtime": 116.483,
      "eval_samples_per_second": 9.761,
      "eval_steps_per_second": 0.155,
      "step": 429
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0871,
      "step": 572
    },
    {
      "epoch": 4.0,
      "eval_F1": 0.7900677200902935,
      "eval_Precision": 0.8495145631067961,
      "eval_Recall": 0.7383966244725738,
      "eval_accuracy": 0.9182058047493403,
      "eval_loss": 0.41887184977531433,
      "eval_runtime": 116.7674,
      "eval_samples_per_second": 9.737,
      "eval_steps_per_second": 0.154,
      "step": 572
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.0517,
      "step": 715
    },
    {
      "epoch": 5.0,
      "eval_F1": 0.8043010752688171,
      "eval_Precision": 0.8201754385964912,
      "eval_Recall": 0.7890295358649789,
      "eval_accuracy": 0.9199648197009674,
      "eval_loss": 0.4395843744277954,
      "eval_runtime": 116.7323,
      "eval_samples_per_second": 9.74,
      "eval_steps_per_second": 0.154,
      "step": 715
    },
    {
      "epoch": 5.0,
      "step": 715,
      "total_flos": 178317179913600.0,
      "train_loss": 0.1781961868692945,
      "train_runtime": 14453.0536,
      "train_samples_per_second": 3.147,
      "train_steps_per_second": 0.049
    }
  ],
  "max_steps": 715,
  "num_train_epochs": 5,
  "total_flos": 178317179913600.0,
  "trial_name": null,
  "trial_params": null
}