checkpoint-10/trainer_state.json

{
  "best_metric": 1.2905054092407227,
  "best_model_checkpoint": "./llama3/28-05-24-Weni-runpod_debug_Experiment with SFT and Llama3 8B, 1.0.5.-2_max_steps-30_batch_1_2024-05-28_ppid_9/checkpoint-10",
  "epoch": 0.11976047904191617,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11976047904191617,
      "grad_norm": 0.2804673910140991,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.5929,
      "step": 10
    },
    {
      "epoch": 0.11976047904191617,
      "eval_loss": 1.2905054092407227,
      "eval_runtime": 24.052,
      "eval_samples_per_second": 3.118,
      "eval_steps_per_second": 3.118,
      "step": 10
    }
  ],
  "logging_steps": 10,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5696637275136000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}