{
  "best_global_step": 1104,
  "best_metric": 3.125730276107788,
  "best_model_checkpoint": "/kaggle/working/t5_openassistant_chat/checkpoint-1104",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1104,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.36105069518089294,
      "learning_rate": 4.171195652173913e-05,
      "loss": 3.7576,
      "step": 184
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.256053924560547,
      "eval_rougeL": 0.07640182692431968,
      "eval_runtime": 103.7583,
      "eval_samples_per_second": 13.281,
      "eval_steps_per_second": 3.325,
      "step": 184
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3874160647392273,
      "learning_rate": 3.33786231884058e-05,
      "loss": 3.4768,
      "step": 368
    },
    {
      "epoch": 2.0,
      "eval_loss": 3.192178964614868,
      "eval_rougeL": 0.08106104899729127,
      "eval_runtime": 102.3175,
      "eval_samples_per_second": 13.468,
      "eval_steps_per_second": 3.372,
      "step": 368
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.39288660883903503,
      "learning_rate": 2.504528985507246e-05,
      "loss": 3.4223,
      "step": 552
    },
    {
      "epoch": 3.0,
      "eval_loss": 3.1580183506011963,
      "eval_rougeL": 0.08353733643223961,
      "eval_runtime": 102.4521,
      "eval_samples_per_second": 13.45,
      "eval_steps_per_second": 3.367,
      "step": 552
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.4270136058330536,
      "learning_rate": 1.671195652173913e-05,
      "loss": 3.3925,
      "step": 736
    },
    {
      "epoch": 4.0,
      "eval_loss": 3.1398727893829346,
      "eval_rougeL": 0.08246789128825052,
      "eval_runtime": 101.7931,
      "eval_samples_per_second": 13.537,
      "eval_steps_per_second": 3.389,
      "step": 736
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4153004288673401,
      "learning_rate": 8.378623188405797e-06,
      "loss": 3.3752,
      "step": 920
    },
    {
      "epoch": 5.0,
      "eval_loss": 3.129657030105591,
      "eval_rougeL": 0.08303174888320114,
      "eval_runtime": 101.9403,
      "eval_samples_per_second": 13.518,
      "eval_steps_per_second": 3.384,
      "step": 920
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.3171236515045166,
      "learning_rate": 4.528985507246377e-08,
      "loss": 3.3685,
      "step": 1104
    },
    {
      "epoch": 6.0,
      "eval_loss": 3.125730276107788,
      "eval_rougeL": 0.08282438404189152,
      "eval_runtime": 101.4418,
      "eval_samples_per_second": 13.584,
      "eval_steps_per_second": 3.401,
      "step": 1104
    },
    {
      "epoch": 6.0,
      "step": 1104,
      "total_flos": 2.148361619845939e+16,
      "train_loss": 3.4654945152393286,
      "train_runtime": 5654.7517,
      "train_samples_per_second": 56.143,
      "train_steps_per_second": 0.195
    }
  ],
  "logging_steps": 500,
  "max_steps": 1104,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 2.148361619845939e+16,
  "train_batch_size": 36,
  "trial_name": null,
  "trial_params": null
}