trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.975609756097561,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 1.7610267400741577,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.5609,
      "num_input_tokens_seen": 49664,
      "step": 5
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.7405933141708374,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.7089,
      "num_input_tokens_seen": 99456,
      "step": 10
    },
    {
      "epoch": 0.975609756097561,
      "num_input_tokens_seen": 99456,
      "step": 10,
      "total_flos": 1689302520299520.0,
      "train_loss": 1.1348845720291139,
      "train_runtime": 897.1693,
      "train_samples_per_second": 1.458,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 5,
  "max_steps": 10,
  "num_input_tokens_seen": 99456,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1689302520299520.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}