{
  "best_global_step": 200,
  "best_metric": 1.5778809785842896,
  "best_model_checkpoint": "./Llama-3.2-3b-ru-lora/checkpoint-200",
  "epoch": 0.6736842105263158,
  "eval_steps": 100,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.22051513195037842,
      "learning_rate": 8e-05,
      "loss": 2.3452760314941408,
      "step": 25
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.24215690791606903,
      "learning_rate": 9.779326364692218e-05,
      "loss": 1.873732452392578,
      "step": 50
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 0.2318001091480255,
      "learning_rate": 9.488966318234611e-05,
      "loss": 1.7455740356445313,
      "step": 75
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 0.22570297122001648,
      "learning_rate": 9.198606271777003e-05,
      "loss": 1.7174720764160156,
      "step": 100
    },
    {
      "epoch": 0.3368421052631579,
      "eval_loss": 1.6638826131820679,
      "eval_runtime": 41.5175,
      "eval_samples_per_second": 3.011,
      "eval_steps_per_second": 3.011,
      "step": 100
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.2472986876964569,
      "learning_rate": 8.908246225319396e-05,
      "loss": 1.6817715454101563,
      "step": 125
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 0.21928200125694275,
      "learning_rate": 8.61788617886179e-05,
      "loss": 1.5971102905273438,
      "step": 150
    },
    {
      "epoch": 0.5894736842105263,
      "grad_norm": 0.24745388329029083,
      "learning_rate": 8.327526132404182e-05,
      "loss": 1.6087770080566406,
      "step": 175
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 0.23894399404525757,
      "learning_rate": 8.037166085946574e-05,
      "loss": 1.623451690673828,
      "step": 200
    },
    {
      "epoch": 0.6736842105263158,
      "eval_loss": 1.5778809785842896,
      "eval_runtime": 41.3548,
      "eval_samples_per_second": 3.023,
      "eval_steps_per_second": 3.023,
      "step": 200
    }
  ],
  "logging_steps": 25,
  "max_steps": 891,
  "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": 2.336969052468019e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}