checkpoint-800/trainer_state.json

{
  "best_global_step": 200,
  "best_metric": 0.9943516121440339,
  "best_model_checkpoint": "/content/drive/MyDrive/model/roberta_model/checkpoint-200",
  "epoch": 0.16433853738701726,
  "eval_steps": 200,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020542317173377156,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 1.5291,
      "step": 1
    },
    {
      "epoch": 0.020542317173377157,
      "grad_norm": 8.729037284851074,
      "learning_rate": 1.3278576317590692e-06,
      "loss": 1.4449,
      "step": 100
    },
    {
      "epoch": 0.041084634346754315,
      "grad_norm": 0.5065429210662842,
      "learning_rate": 2.69678302532512e-06,
      "loss": 0.4001,
      "step": 200
    },
    {
      "epoch": 0.041084634346754315,
      "eval_accuracy": 0.9943516121440339,
      "eval_f1_macro": 0.24929195185272598,
      "eval_f1_weighted": 0.9915354168771638,
      "eval_loss": 0.047249794006347656,
      "eval_runtime": 27.6034,
      "eval_samples_per_second": 153.93,
      "eval_steps_per_second": 9.636,
      "step": 200
    },
    {
      "epoch": 0.06162695152013147,
      "grad_norm": 0.1958896368741989,
      "learning_rate": 4.05201916495551e-06,
      "loss": 0.0866,
      "step": 300
    },
    {
      "epoch": 0.08216926869350863,
      "grad_norm": 9.922837257385254,
      "learning_rate": 5.4209445585215615e-06,
      "loss": 0.0725,
      "step": 400
    },
    {
      "epoch": 0.08216926869350863,
      "eval_accuracy": 0.9943516121440339,
      "eval_f1_macro": 0.24929195185272598,
      "eval_f1_weighted": 0.9915354168771638,
      "eval_loss": 0.04173773154616356,
      "eval_runtime": 28.0068,
      "eval_samples_per_second": 151.713,
      "eval_steps_per_second": 9.498,
      "step": 400
    },
    {
      "epoch": 0.10271158586688578,
      "grad_norm": 0.244202122092247,
      "learning_rate": 6.789869952087612e-06,
      "loss": 0.0603,
      "step": 500
    },
    {
      "epoch": 0.12325390304026294,
      "grad_norm": 0.06597892194986343,
      "learning_rate": 8.158795345653663e-06,
      "loss": 0.0591,
      "step": 600
    },
    {
      "epoch": 0.12325390304026294,
      "eval_accuracy": 0.9943516121440339,
      "eval_f1_macro": 0.24929195185272598,
      "eval_f1_weighted": 0.9915354168771638,
      "eval_loss": 0.043345339596271515,
      "eval_runtime": 27.0783,
      "eval_samples_per_second": 156.915,
      "eval_steps_per_second": 9.823,
      "step": 600
    },
    {
      "epoch": 0.1437962202136401,
      "grad_norm": 13.586718559265137,
      "learning_rate": 9.527720739219714e-06,
      "loss": 0.048,
      "step": 700
    },
    {
      "epoch": 0.16433853738701726,
      "grad_norm": 0.03302786871790886,
      "learning_rate": 1.0896646132785765e-05,
      "loss": 0.0443,
      "step": 800
    },
    {
      "epoch": 0.16433853738701726,
      "eval_accuracy": 0.9943516121440339,
      "eval_f1_macro": 0.24929195185272598,
      "eval_f1_weighted": 0.9915354168771638,
      "eval_loss": 0.04462751746177673,
      "eval_runtime": 27.0732,
      "eval_samples_per_second": 156.945,
      "eval_steps_per_second": 9.825,
      "step": 800
    }
  ],
  "logging_steps": 100,
  "max_steps": 14604,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2525934167654400.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}