checkpoint-20/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "autotrain-t5-large-gpt4o/checkpoint-20",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.1,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.15,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.2,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.25,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.3,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.35,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.4,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.45,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.5,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.55,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.6,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.65,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.7,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.75,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.8,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.85,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.9,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.95,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.0,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 19.0,
      "eval_loss": NaN,
      "eval_rouge1": 13.0563,
      "eval_rouge2": 5.3373,
      "eval_rougeL": 10.9311,
      "eval_rougeLsum": 12.1825,
      "eval_runtime": 9.0826,
      "eval_samples_per_second": 1.101,
      "eval_steps_per_second": 0.33,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 162708378624000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}