trainer_state.json

{
  "best_global_step": null,
  "best_metric": Infinity,
  "best_model_checkpoint": null,
  "epoch": 1.5357534109128737,
  "eval_steps": 62500,
  "global_step": 187500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5119184861956061,
      "grad_norm": 5.65625,
      "learning_rate": 4.146810933007888e-05,
      "loss": 0.7436,
      "step": 62500
    },
    {
      "epoch": 0.5119184861956061,
      "eval_loss": NaN,
      "eval_runtime": 6058.1717,
      "eval_samples_per_second": 25.191,
      "eval_steps_per_second": 25.191,
      "step": 62500
    },
    {
      "epoch": 1.0238349247172673,
      "grad_norm": 5.34375,
      "learning_rate": 3.293608214772283e-05,
      "loss": 0.7106,
      "step": 125000
    },
    {
      "epoch": 1.0238349247172673,
      "eval_loss": NaN,
      "eval_runtime": 5970.2715,
      "eval_samples_per_second": 25.562,
      "eval_steps_per_second": 25.562,
      "step": 125000
    },
    {
      "epoch": 1.5357534109128737,
      "grad_norm": 5.375,
      "learning_rate": 2.4404054965366797e-05,
      "loss": 0.6782,
      "step": 187500
    },
    {
      "epoch": 1.5357534109128737,
      "eval_loss": NaN,
      "eval_runtime": 5980.459,
      "eval_samples_per_second": 25.519,
      "eval_steps_per_second": 25.519,
      "step": 187500
    }
  ],
  "logging_steps": 62500,
  "max_steps": 366267,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 62500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0148356655079752e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}