checkpoint-100/trainer_state.json

{
  "best_global_step": 100,
  "best_metric": 0.5540049076080322,
  "best_model_checkpoint": "./phase2_hate/checkpoint-100",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 3.5325217247009277,
      "learning_rate": 1.62e-05,
      "loss": 0.5928,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.18705035971223022,
      "eval_f1": 0.07878787878787878,
      "eval_loss": 0.5851741433143616,
      "eval_runtime": 0.6117,
      "eval_samples_per_second": 227.244,
      "eval_steps_per_second": 8.174,
      "step": 20
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.1411919593811035,
      "learning_rate": 1.22e-05,
      "loss": 0.571,
      "step": 40
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.18705035971223022,
      "eval_f1": 0.07878787878787878,
      "eval_loss": 0.5669987797737122,
      "eval_runtime": 0.6353,
      "eval_samples_per_second": 218.803,
      "eval_steps_per_second": 7.871,
      "step": 40
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.9315316677093506,
      "learning_rate": 8.2e-06,
      "loss": 0.5582,
      "step": 60
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.18705035971223022,
      "eval_f1": 0.07878787878787878,
      "eval_loss": 0.5586255788803101,
      "eval_runtime": 0.618,
      "eval_samples_per_second": 224.93,
      "eval_steps_per_second": 8.091,
      "step": 60
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.3887386322021484,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.5552,
      "step": 80
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.2014388489208633,
      "eval_f1": 0.09769449415727971,
      "eval_loss": 0.5553123950958252,
      "eval_runtime": 0.6197,
      "eval_samples_per_second": 224.285,
      "eval_steps_per_second": 8.068,
      "step": 80
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.8084831237792969,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.5556,
      "step": 100
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.19424460431654678,
      "eval_f1": 0.09524295630869743,
      "eval_loss": 0.5540049076080322,
      "eval_runtime": 0.6476,
      "eval_samples_per_second": 214.633,
      "eval_steps_per_second": 7.721,
      "step": 100
    }
  ],
  "logging_steps": 500,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}