trainer_state.json

{
  "best_global_step": 500,
  "best_metric": 0.03948367014527321,
  "best_model_checkpoint": "/teamspace/studios/this_studio/secure_modern_bert/Models/reranker-securebert2-cmnrl/checkpoint-500",
  "epoch": 2.242152466367713,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004484304932735426,
      "grad_norm": 3.019306495843921e-05,
      "learning_rate": 0.0,
      "loss": 0.0007,
      "step": 1
    },
    {
      "epoch": 0.2242152466367713,
      "grad_norm": 0.4142322838306427,
      "learning_rate": 4.394618834080718e-06,
      "loss": 0.0031,
      "step": 50
    },
    {
      "epoch": 0.4484304932735426,
      "grad_norm": 0.06909839808940887,
      "learning_rate": 8.878923766816144e-06,
      "loss": 0.0023,
      "step": 100
    },
    {
      "epoch": 0.672645739910314,
      "grad_norm": 3.889437675476074,
      "learning_rate": 1.3363228699551571e-05,
      "loss": 0.0029,
      "step": 150
    },
    {
      "epoch": 0.8968609865470852,
      "grad_norm": 0.008452645502984524,
      "learning_rate": 1.7847533632286997e-05,
      "loss": 0.0029,
      "step": 200
    },
    {
      "epoch": 1.1210762331838564,
      "grad_norm": 0.017008045688271523,
      "learning_rate": 1.974090682610862e-05,
      "loss": 0.0034,
      "step": 250
    },
    {
      "epoch": 1.3452914798206277,
      "grad_norm": 0.12214717268943787,
      "learning_rate": 1.9242650722471353e-05,
      "loss": 0.0029,
      "step": 300
    },
    {
      "epoch": 1.5695067264573992,
      "grad_norm": 0.01061748992651701,
      "learning_rate": 1.8744394618834082e-05,
      "loss": 0.0034,
      "step": 350
    },
    {
      "epoch": 1.7937219730941703,
      "grad_norm": 0.017459532245993614,
      "learning_rate": 1.824613851519681e-05,
      "loss": 0.0048,
      "step": 400
    },
    {
      "epoch": 2.0179372197309418,
      "grad_norm": 0.0639125257730484,
      "learning_rate": 1.7747882411559544e-05,
      "loss": 0.0064,
      "step": 450
    },
    {
      "epoch": 2.242152466367713,
      "grad_norm": 1.5931968688964844,
      "learning_rate": 1.7249626307922273e-05,
      "loss": 0.0052,
      "step": 500
    },
    {
      "epoch": 2.242152466367713,
      "eval_loss": 0.03948367014527321,
      "eval_runtime": 38.1763,
      "eval_samples_per_second": 233.836,
      "eval_steps_per_second": 1.467,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 2230,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 20,
  "trial_name": null,
  "trial_params": null
}