trainer_state.json

{
  "best_metric": 1.393009066581726,
  "best_model_checkpoint": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/distilbert-finetuned-uncased/checkpoint-900",
  "epoch": 1.9607843137254903,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.39,
      "learning_rate": 1.607843137254902e-05,
      "loss": 3.6437,
      "step": 100
    },
    {
      "epoch": 0.39,
      "eval_loss": 2.1780340671539307,
      "eval_runtime": 8.4412,
      "eval_samples_per_second": 1417.927,
      "eval_steps_per_second": 11.136,
      "step": 100
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.215686274509804e-05,
      "loss": 2.1596,
      "step": 200
    },
    {
      "epoch": 0.78,
      "eval_loss": 1.6557185649871826,
      "eval_runtime": 8.3581,
      "eval_samples_per_second": 1432.022,
      "eval_steps_per_second": 11.247,
      "step": 200
    },
    {
      "epoch": 1.18,
      "learning_rate": 8.23529411764706e-06,
      "loss": 1.8138,
      "step": 300
    },
    {
      "epoch": 1.18,
      "eval_loss": 1.5682721138000488,
      "eval_runtime": 8.4191,
      "eval_samples_per_second": 1421.643,
      "eval_steps_per_second": 11.165,
      "step": 300
    },
    {
      "epoch": 1.57,
      "learning_rate": 4.313725490196079e-06,
      "loss": 1.6987,
      "step": 400
    },
    {
      "epoch": 1.57,
      "eval_loss": 1.5075817108154297,
      "eval_runtime": 8.3595,
      "eval_samples_per_second": 1431.779,
      "eval_steps_per_second": 11.245,
      "step": 400
    },
    {
      "epoch": 1.96,
      "learning_rate": 3.921568627450981e-07,
      "loss": 1.6586,
      "step": 500
    },
    {
      "epoch": 1.96,
      "eval_loss": 1.535025715827942,
      "eval_runtime": 8.4289,
      "eval_samples_per_second": 1419.991,
      "eval_steps_per_second": 11.152,
      "step": 500
    },
    {
      "epoch": 1.18,
      "learning_rate": 8.23529411764706e-06,
      "loss": 1.5957,
      "step": 600
    },
    {
      "epoch": 1.18,
      "eval_loss": 1.4431041479110718,
      "eval_runtime": 8.5594,
      "eval_samples_per_second": 1398.342,
      "eval_steps_per_second": 21.964,
      "step": 600
    },
    {
      "epoch": 1.37,
      "learning_rate": 6.274509803921569e-06,
      "loss": 1.5825,
      "step": 700
    },
    {
      "epoch": 1.37,
      "eval_loss": 1.495514154434204,
      "eval_runtime": 8.5285,
      "eval_samples_per_second": 1403.419,
      "eval_steps_per_second": 22.044,
      "step": 700
    },
    {
      "epoch": 1.57,
      "learning_rate": 4.313725490196079e-06,
      "loss": 1.5523,
      "step": 800
    },
    {
      "epoch": 1.57,
      "eval_loss": 1.4444433450698853,
      "eval_runtime": 8.5112,
      "eval_samples_per_second": 1406.272,
      "eval_steps_per_second": 22.089,
      "step": 800
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 1.5346,
      "step": 900
    },
    {
      "epoch": 1.76,
      "eval_loss": 1.393009066581726,
      "eval_runtime": 8.5265,
      "eval_samples_per_second": 1403.737,
      "eval_steps_per_second": 22.049,
      "step": 900
    },
    {
      "epoch": 1.96,
      "learning_rate": 3.921568627450981e-07,
      "loss": 1.5098,
      "step": 1000
    },
    {
      "epoch": 1.96,
      "eval_loss": 1.4284701347351074,
      "eval_runtime": 8.5994,
      "eval_samples_per_second": 1391.84,
      "eval_steps_per_second": 21.862,
      "step": 1000
    },
    {
      "epoch": 1.96,
      "step": 1000,
      "total_flos": 5.015589595888435e+16,
      "train_loss": 0.0,
      "train_runtime": 0.3572,
      "train_samples_per_second": 730670.816,
      "train_steps_per_second": 1427.715
    },
    {
      "epoch": 1.96,
      "eval_loss": 1.3930128812789917,
      "eval_runtime": 8.2864,
      "eval_samples_per_second": 1444.423,
      "eval_steps_per_second": 11.344,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 510,
  "num_train_epochs": 2,
  "save_steps": 100,
  "total_flos": 5.015589595888435e+16,
  "trial_name": null,
  "trial_params": null
}