{
  "best_global_step": 100,
  "best_metric": 1.582080602645874,
  "best_model_checkpoint": "./Llama-3.2-4b-ru-lora/checkpoint-100",
  "epoch": 0.411522633744856,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.102880658436214,
      "grad_norm": 0.8221918344497681,
      "learning_rate": 8e-05,
      "loss": 2.379297180175781,
      "step": 25
    },
    {
      "epoch": 0.205761316872428,
      "grad_norm": 0.8748275637626648,
      "learning_rate": 9.728183118741059e-05,
      "loss": 1.9784544372558595,
      "step": 50
    },
    {
      "epoch": 0.30864197530864196,
      "grad_norm": 0.750031590461731,
      "learning_rate": 9.370529327610873e-05,
      "loss": 1.8810975646972656,
      "step": 75
    },
    {
      "epoch": 0.411522633744856,
      "grad_norm": 0.9241881966590881,
      "learning_rate": 9.012875536480687e-05,
      "loss": 1.8589222717285157,
      "step": 100
    },
    {
      "epoch": 0.411522633744856,
      "eval_loss": 1.582080602645874,
      "eval_runtime": 22.7091,
      "eval_samples_per_second": 4.536,
      "eval_steps_per_second": 4.536,
      "step": 100
    }
  ],
  "logging_steps": 25,
  "max_steps": 729,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6941196214763520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}