trainer_state.json

{
  "best_metric": 1.0824099779129028,
  "best_model_checkpoint": "bygpt5_quatags_con/base/en/checkpoint-90840",
  "epoch": 8.0,
  "global_step": 90840,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 3.948826997701317e-05,
      "loss": 1.2611,
      "step": 11355
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1518595218658447,
      "eval_runtime": 242.6001,
      "eval_samples_per_second": 83.207,
      "eval_steps_per_second": 10.404,
      "step": 11355
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.704445954688097e-05,
      "loss": 1.1532,
      "step": 22710
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.1212660074234009,
      "eval_runtime": 241.8691,
      "eval_samples_per_second": 83.458,
      "eval_steps_per_second": 10.435,
      "step": 22710
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.282832230852865e-05,
      "loss": 1.1187,
      "step": 34065
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.1034783124923706,
      "eval_runtime": 243.698,
      "eval_samples_per_second": 82.832,
      "eval_steps_per_second": 10.357,
      "step": 34065
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.7278263072276784e-05,
      "loss": 1.0945,
      "step": 45420
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.0929205417633057,
      "eval_runtime": 242.4754,
      "eval_samples_per_second": 83.25,
      "eval_steps_per_second": 10.409,
      "step": 45420
    },
    {
      "epoch": 5.0,
      "learning_rate": 2.0971391293814688e-05,
      "loss": 1.0758,
      "step": 56775
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.086612343788147,
      "eval_runtime": 243.5145,
      "eval_samples_per_second": 82.894,
      "eval_steps_per_second": 10.365,
      "step": 56775
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.4563511746431305e-05,
      "loss": 1.0611,
      "step": 68130
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.084080696105957,
      "eval_runtime": 242.803,
      "eval_samples_per_second": 83.137,
      "eval_steps_per_second": 10.395,
      "step": 68130
    },
    {
      "epoch": 7.0,
      "learning_rate": 8.72093225141226e-06,
      "loss": 1.0501,
      "step": 79485
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.082816243171692,
      "eval_runtime": 242.3815,
      "eval_samples_per_second": 83.282,
      "eval_steps_per_second": 10.413,
      "step": 79485
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.051179274451455e-06,
      "loss": 1.0422,
      "step": 90840
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.0824099779129028,
      "eval_runtime": 242.3799,
      "eval_samples_per_second": 83.282,
      "eval_steps_per_second": 10.413,
      "step": 90840
    }
  ],
  "max_steps": 113550,
  "num_train_epochs": 10,
  "total_flos": 2.506903706824704e+17,
  "trial_name": null,
  "trial_params": null
}