trainer_state.json

{
  "best_metric": 0.1812099814414978,
  "best_model_checkpoint": "/content/drive/MyDrive/BERT/np_model_es/checkpoint-486",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 1701,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9390050468637346,
      "eval_f1": 0.7960042060988434,
      "eval_loss": 0.19681523740291595,
      "eval_precision": 0.7577577577577578,
      "eval_recall": 0.8383167220376523,
      "eval_runtime": 5.2116,
      "eval_samples_per_second": 46.435,
      "eval_steps_per_second": 11.705,
      "step": 243
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.949098774333093,
      "eval_f1": 0.8397027600849256,
      "eval_loss": 0.1812099814414978,
      "eval_precision": 0.8063200815494393,
      "eval_recall": 0.875968992248062,
      "eval_runtime": 5.4915,
      "eval_samples_per_second": 44.069,
      "eval_steps_per_second": 11.108,
      "step": 486
    },
    {
      "epoch": 2.06,
      "learning_rate": 7.94238683127572e-06,
      "loss": 0.2577,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9495313626532084,
      "eval_f1": 0.8511326860841423,
      "eval_loss": 0.19488638639450073,
      "eval_precision": 0.8296529968454258,
      "eval_recall": 0.8737541528239202,
      "eval_runtime": 5.0485,
      "eval_samples_per_second": 47.935,
      "eval_steps_per_second": 12.083,
      "step": 729
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.950396539293439,
      "eval_f1": 0.8493297587131368,
      "eval_loss": 0.21376554667949677,
      "eval_precision": 0.8232848232848233,
      "eval_recall": 0.8770764119601329,
      "eval_runtime": 4.8302,
      "eval_samples_per_second": 50.101,
      "eval_steps_per_second": 12.629,
      "step": 972
    },
    {
      "epoch": 4.12,
      "learning_rate": 5.884773662551441e-06,
      "loss": 0.1112,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9499639509733238,
      "eval_f1": 0.8502732240437159,
      "eval_loss": 0.24179881811141968,
      "eval_precision": 0.8392664509169363,
      "eval_recall": 0.8615725359911407,
      "eval_runtime": 4.8298,
      "eval_samples_per_second": 50.106,
      "eval_steps_per_second": 12.63,
      "step": 1215
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9492429704397981,
      "eval_f1": 0.8493449781659388,
      "eval_loss": 0.24828843772411346,
      "eval_precision": 0.83745963401507,
      "eval_recall": 0.8615725359911407,
      "eval_runtime": 5.5749,
      "eval_samples_per_second": 43.409,
      "eval_steps_per_second": 10.942,
      "step": 1458
    },
    {
      "epoch": 6.17,
      "learning_rate": 3.827160493827161e-06,
      "loss": 0.0661,
      "step": 1500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.949098774333093,
      "eval_f1": 0.8526200873362445,
      "eval_loss": 0.2728496193885803,
      "eval_precision": 0.8406889128094726,
      "eval_recall": 0.8648947951273532,
      "eval_runtime": 4.9946,
      "eval_samples_per_second": 48.452,
      "eval_steps_per_second": 12.213,
      "step": 1701
    }
  ],
  "logging_steps": 500,
  "max_steps": 2430,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 224033373641160.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}