{
  "best_metric": 0.8840153813362122,
  "best_model_checkpoint": "data/Llama-31-8B_task-1_120-samples_config-2_auto/checkpoint-33",
  "epoch": 12.909090909090908,
  "eval_steps": 500,
  "global_step": 71,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.8231478333473206,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.1614,
      "step": 1
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.7646258473396301,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0994,
      "step": 2
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.7370247840881348,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.1727,
      "step": 4
    },
    {
      "epoch": 0.9090909090909091,
      "eval_loss": 1.2189840078353882,
      "eval_runtime": 9.885,
      "eval_samples_per_second": 2.428,
      "eval_steps_per_second": 2.428,
      "step": 5
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.765868604183197,
      "learning_rate": 2.4e-05,
      "loss": 1.2015,
      "step": 6
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.7423933744430542,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.0773,
      "step": 8
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.7272891998291016,
      "learning_rate": 4e-05,
      "loss": 1.1492,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0506871938705444,
      "eval_runtime": 9.8683,
      "eval_samples_per_second": 2.432,
      "eval_steps_per_second": 2.432,
      "step": 11
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.416668564081192,
      "learning_rate": 4.8e-05,
      "loss": 0.9201,
      "step": 12
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.4836718440055847,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.0136,
      "step": 14
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.621853232383728,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.9803,
      "step": 16
    },
    {
      "epoch": 2.909090909090909,
      "eval_loss": 1.0035327672958374,
      "eval_runtime": 9.8774,
      "eval_samples_per_second": 2.43,
      "eval_steps_per_second": 2.43,
      "step": 16
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 0.5383903980255127,
      "learning_rate": 7.2e-05,
      "loss": 0.8576,
      "step": 18
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.4518912434577942,
      "learning_rate": 8e-05,
      "loss": 0.9125,
      "step": 20
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3614003658294678,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.8687,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.9365265965461731,
      "eval_runtime": 9.8731,
      "eval_samples_per_second": 2.431,
      "eval_steps_per_second": 2.431,
      "step": 22
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 0.42301425337791443,
      "learning_rate": 9.6e-05,
      "loss": 0.8496,
      "step": 24
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 0.484470933675766,
      "learning_rate": 9.999512620046522e-05,
      "loss": 0.7872,
      "step": 26
    },
    {
      "epoch": 4.909090909090909,
      "eval_loss": 0.9064176082611084,
      "eval_runtime": 9.8735,
      "eval_samples_per_second": 2.431,
      "eval_steps_per_second": 2.431,
      "step": 27
    },
    {
      "epoch": 5.090909090909091,
      "grad_norm": 0.5472301244735718,
      "learning_rate": 9.995614150494293e-05,
      "loss": 0.743,
      "step": 28
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.43318992853164673,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.6851,
      "step": 30
    },
    {
      "epoch": 5.818181818181818,
      "grad_norm": 0.5325647592544556,
      "learning_rate": 9.976136999909156e-05,
      "loss": 0.7171,
      "step": 32
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.8840153813362122,
      "eval_runtime": 9.8767,
      "eval_samples_per_second": 2.43,
      "eval_steps_per_second": 2.43,
      "step": 33
    },
    {
      "epoch": 6.181818181818182,
      "grad_norm": 0.46143198013305664,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.6393,
      "step": 34
    },
    {
      "epoch": 6.545454545454545,
      "grad_norm": 0.5249224901199341,
      "learning_rate": 9.941141907232765e-05,
      "loss": 0.6673,
      "step": 36
    },
    {
      "epoch": 6.909090909090909,
      "grad_norm": 0.5732040405273438,
      "learning_rate": 9.917857354066931e-05,
      "loss": 0.5563,
      "step": 38
    },
    {
      "epoch": 6.909090909090909,
      "eval_loss": 0.9091019034385681,
      "eval_runtime": 9.8678,
      "eval_samples_per_second": 2.432,
      "eval_steps_per_second": 2.432,
      "step": 38
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 0.5529835820198059,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.5694,
      "step": 40
    },
    {
      "epoch": 7.636363636363637,
      "grad_norm": 0.6050636768341064,
      "learning_rate": 9.859805002892732e-05,
      "loss": 0.4485,
      "step": 42
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.7332842350006104,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.4878,
      "step": 44
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.0011078119277954,
      "eval_runtime": 9.8664,
      "eval_samples_per_second": 2.432,
      "eval_steps_per_second": 2.432,
      "step": 44
    },
    {
      "epoch": 8.363636363636363,
      "grad_norm": 0.6613210439682007,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.3535,
      "step": 46
    },
    {
      "epoch": 8.727272727272727,
      "grad_norm": 0.8845905661582947,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.3849,
      "step": 48
    },
    {
      "epoch": 8.909090909090908,
      "eval_loss": 1.0698117017745972,
      "eval_runtime": 9.8689,
      "eval_samples_per_second": 2.432,
      "eval_steps_per_second": 2.432,
      "step": 49
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 0.8460261225700378,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.3467,
      "step": 50
    },
    {
      "epoch": 9.454545454545455,
      "grad_norm": 0.7633416056632996,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.2411,
      "step": 52
    },
    {
      "epoch": 9.818181818181818,
      "grad_norm": 1.0061150789260864,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.2449,
      "step": 54
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.190703272819519,
      "eval_runtime": 9.9063,
      "eval_samples_per_second": 2.423,
      "eval_steps_per_second": 2.423,
      "step": 55
    },
    {
      "epoch": 10.181818181818182,
      "grad_norm": 0.6788498163223267,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.1964,
      "step": 56
    },
    {
      "epoch": 10.545454545454545,
      "grad_norm": 0.9161595106124878,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.1524,
      "step": 58
    },
    {
      "epoch": 10.909090909090908,
      "grad_norm": 1.1366978883743286,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.1483,
      "step": 60
    },
    {
      "epoch": 10.909090909090908,
      "eval_loss": 1.3619922399520874,
      "eval_runtime": 9.8696,
      "eval_samples_per_second": 2.432,
      "eval_steps_per_second": 2.432,
      "step": 60
    },
    {
      "epoch": 11.272727272727273,
      "grad_norm": 0.7969510555267334,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.0986,
      "step": 62
    },
    {
      "epoch": 11.636363636363637,
      "grad_norm": 0.6498268246650696,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.0751,
      "step": 64
    },
    {
      "epoch": 12.0,
      "grad_norm": 1.2433557510375977,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.1039,
      "step": 66
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.4584633111953735,
      "eval_runtime": 9.8663,
      "eval_samples_per_second": 2.433,
      "eval_steps_per_second": 2.433,
      "step": 66
    },
    {
      "epoch": 12.363636363636363,
      "grad_norm": 0.7402978539466858,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.0559,
      "step": 68
    },
    {
      "epoch": 12.727272727272727,
      "grad_norm": 0.8068957328796387,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0637,
      "step": 70
    },
    {
      "epoch": 12.909090909090908,
      "eval_loss": 1.6114619970321655,
      "eval_runtime": 9.8735,
      "eval_samples_per_second": 2.431,
      "eval_steps_per_second": 2.431,
      "step": 71
    },
    {
      "epoch": 12.909090909090908,
      "step": 71,
      "total_flos": 1.9037713390895104e+16,
      "train_loss": 0.5900322046708053,
      "train_runtime": 1379.2357,
      "train_samples_per_second": 3.19,
      "train_steps_per_second": 0.181
    }
  ],
  "logging_steps": 2,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 7,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9037713390895104e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}