{
  "best_metric": 0.13098983466625214,
  "best_model_checkpoint": "results/outputs_qwen/checkpoint-100",
  "epoch": 3.9209486166007905,
  "eval_steps": 50,
  "global_step": 124,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6324110671936759,
      "grad_norm": 1.193028211593628,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.5006,
      "step": 20
    },
    {
      "epoch": 1.2648221343873518,
      "grad_norm": 0.8042491674423218,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.3752,
      "step": 40
    },
    {
      "epoch": 1.5810276679841897,
      "eval_loss": 0.19735823571681976,
      "eval_runtime": 61.0265,
      "eval_samples_per_second": 3.195,
      "eval_steps_per_second": 0.41,
      "step": 50
    },
    {
      "epoch": 1.8972332015810278,
      "grad_norm": 0.5734511613845825,
      "learning_rate": 4e-05,
      "loss": 0.2164,
      "step": 60
    },
    {
      "epoch": 2.5296442687747036,
      "grad_norm": 0.29235631227493286,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.1755,
      "step": 80
    },
    {
      "epoch": 3.1620553359683794,
      "grad_norm": 0.8599438071250916,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.1416,
      "step": 100
    },
    {
      "epoch": 3.1620553359683794,
      "eval_loss": 0.13098983466625214,
      "eval_runtime": 61.0025,
      "eval_samples_per_second": 3.197,
      "eval_steps_per_second": 0.41,
      "step": 100
    },
    {
      "epoch": 3.794466403162055,
      "grad_norm": 0.7246127724647522,
      "learning_rate": 8e-05,
      "loss": 0.1233,
      "step": 120
    }
  ],
  "logging_steps": 20,
  "max_steps": 124,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 3.2979340098453504e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}