{
  "best_metric": 1.1645187139511108,
  "best_model_checkpoint": "data/Llama-31-8B_task-3_60-samples_config-1_full/checkpoint-57",
  "epoch": 16.869565217391305,
  "eval_steps": 500,
  "global_step": 97,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.592536449432373,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.7189,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.6408989429473877,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.7155,
      "step": 2
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.476033478975296,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.6787,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 1.676098346710205,
      "eval_runtime": 11.1928,
      "eval_samples_per_second": 1.072,
      "eval_steps_per_second": 1.072,
      "step": 5
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.4531095623970032,
      "learning_rate": 2.4e-05,
      "loss": 1.6721,
      "step": 6
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.48008444905281067,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.6656,
      "step": 8
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.3266219198703766,
      "learning_rate": 4e-05,
      "loss": 1.6422,
      "step": 10
    },
    {
      "epoch": 1.9130434782608696,
      "eval_loss": 1.5859484672546387,
      "eval_runtime": 11.1977,
      "eval_samples_per_second": 1.072,
      "eval_steps_per_second": 1.072,
      "step": 11
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.3387700617313385,
      "learning_rate": 4.8e-05,
      "loss": 1.609,
      "step": 12
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.351455420255661,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.5144,
      "step": 14
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.2647564709186554,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.5493,
      "step": 16
    },
    {
      "epoch": 2.9565217391304346,
      "eval_loss": 1.4786046743392944,
      "eval_runtime": 11.1944,
      "eval_samples_per_second": 1.072,
      "eval_steps_per_second": 1.072,
      "step": 17
    },
    {
      "epoch": 3.130434782608696,
      "grad_norm": 0.2552366256713867,
      "learning_rate": 7.2e-05,
      "loss": 1.4257,
      "step": 18
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 0.27941399812698364,
      "learning_rate": 8e-05,
      "loss": 1.4275,
      "step": 20
    },
    {
      "epoch": 3.8260869565217392,
      "grad_norm": 0.2629425823688507,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.3749,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.3612533807754517,
      "eval_runtime": 11.1921,
      "eval_samples_per_second": 1.072,
      "eval_steps_per_second": 1.072,
      "step": 23
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.308207243680954,
      "learning_rate": 9.6e-05,
      "loss": 1.3649,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.3441653251647949,
      "learning_rate": 9.999512620046522e-05,
      "loss": 1.2861,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.45420464873313904,
      "learning_rate": 9.995614150494293e-05,
      "loss": 1.2143,
      "step": 28
    },
    {
      "epoch": 4.869565217391305,
      "eval_loss": 1.255916953086853,
      "eval_runtime": 11.1845,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 28
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 0.24635568261146545,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.1452,
      "step": 30
    },
    {
      "epoch": 5.565217391304348,
      "grad_norm": 0.23990486562252045,
      "learning_rate": 9.976136999909156e-05,
      "loss": 1.1866,
      "step": 32
    },
    {
      "epoch": 5.913043478260869,
      "grad_norm": 0.18167296051979065,
      "learning_rate": 9.96057350657239e-05,
      "loss": 1.1354,
      "step": 34
    },
    {
      "epoch": 5.913043478260869,
      "eval_loss": 1.2057816982269287,
      "eval_runtime": 11.1866,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 34
    },
    {
      "epoch": 6.260869565217392,
      "grad_norm": 0.18317623436450958,
      "learning_rate": 9.941141907232765e-05,
      "loss": 1.1145,
      "step": 36
    },
    {
      "epoch": 6.608695652173913,
      "grad_norm": 0.20497700572013855,
      "learning_rate": 9.917857354066931e-05,
      "loss": 1.1246,
      "step": 38
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 0.20193497836589813,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.0603,
      "step": 40
    },
    {
      "epoch": 6.956521739130435,
      "eval_loss": 1.1849656105041504,
      "eval_runtime": 11.1823,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 40
    },
    {
      "epoch": 7.304347826086957,
      "grad_norm": 0.19203776121139526,
      "learning_rate": 9.859805002892732e-05,
      "loss": 1.1279,
      "step": 42
    },
    {
      "epoch": 7.6521739130434785,
      "grad_norm": 0.18547101318836212,
      "learning_rate": 9.825082472361557e-05,
      "loss": 1.0544,
      "step": 44
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.19855879247188568,
      "learning_rate": 9.786597487660337e-05,
      "loss": 1.0521,
      "step": 46
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.171064853668213,
      "eval_runtime": 11.1853,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 46
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 0.1863618642091751,
      "learning_rate": 9.744380058222483e-05,
      "loss": 1.0626,
      "step": 48
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 0.23284262418746948,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.0417,
      "step": 50
    },
    {
      "epoch": 8.869565217391305,
      "eval_loss": 1.1645785570144653,
      "eval_runtime": 11.1847,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 51
    },
    {
      "epoch": 9.043478260869565,
      "grad_norm": 0.21001140773296356,
      "learning_rate": 9.648882429441257e-05,
      "loss": 1.0175,
      "step": 52
    },
    {
      "epoch": 9.391304347826088,
      "grad_norm": 0.223481222987175,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.9784,
      "step": 54
    },
    {
      "epoch": 9.73913043478261,
      "grad_norm": 0.24497197568416595,
      "learning_rate": 9.538887392664544e-05,
      "loss": 1.025,
      "step": 56
    },
    {
      "epoch": 9.91304347826087,
      "eval_loss": 1.1645187139511108,
      "eval_runtime": 11.1854,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 57
    },
    {
      "epoch": 10.08695652173913,
      "grad_norm": 0.2217385470867157,
      "learning_rate": 9.478558801197065e-05,
      "loss": 1.0144,
      "step": 58
    },
    {
      "epoch": 10.434782608695652,
      "grad_norm": 0.2677067518234253,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.9797,
      "step": 60
    },
    {
      "epoch": 10.782608695652174,
      "grad_norm": 0.3020663261413574,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.9238,
      "step": 62
    },
    {
      "epoch": 10.956521739130435,
      "eval_loss": 1.1722332239151,
      "eval_runtime": 11.1879,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 63
    },
    {
      "epoch": 11.130434782608695,
      "grad_norm": 0.3325958251953125,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.9142,
      "step": 64
    },
    {
      "epoch": 11.478260869565217,
      "grad_norm": 0.300712525844574,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.9823,
      "step": 66
    },
    {
      "epoch": 11.826086956521738,
      "grad_norm": 0.34848660230636597,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.8752,
      "step": 68
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.1790670156478882,
      "eval_runtime": 11.1839,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 69
    },
    {
      "epoch": 12.173913043478262,
      "grad_norm": 0.3527248203754425,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8924,
      "step": 70
    },
    {
      "epoch": 12.521739130434783,
      "grad_norm": 0.39320820569992065,
      "learning_rate": 8.961448216775954e-05,
      "loss": 0.8006,
      "step": 72
    },
    {
      "epoch": 12.869565217391305,
      "grad_norm": 0.47677960991859436,
      "learning_rate": 8.874722443520899e-05,
      "loss": 0.8737,
      "step": 74
    },
    {
      "epoch": 12.869565217391305,
      "eval_loss": 1.1912249326705933,
      "eval_runtime": 11.1852,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 74
    },
    {
      "epoch": 13.217391304347826,
      "grad_norm": 0.5323153734207153,
      "learning_rate": 8.784975278258783e-05,
      "loss": 0.8161,
      "step": 76
    },
    {
      "epoch": 13.565217391304348,
      "grad_norm": 0.6827120184898376,
      "learning_rate": 8.692276703129421e-05,
      "loss": 0.8145,
      "step": 78
    },
    {
      "epoch": 13.91304347826087,
      "grad_norm": 0.7033717632293701,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.7418,
      "step": 80
    },
    {
      "epoch": 13.91304347826087,
      "eval_loss": 1.2408862113952637,
      "eval_runtime": 11.1864,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 80
    },
    {
      "epoch": 14.26086956521739,
      "grad_norm": 0.6471558809280396,
      "learning_rate": 8.498316702566828e-05,
      "loss": 0.6792,
      "step": 82
    },
    {
      "epoch": 14.608695652173914,
      "grad_norm": 0.6807418465614319,
      "learning_rate": 8.397206521307584e-05,
      "loss": 0.6814,
      "step": 84
    },
    {
      "epoch": 14.956521739130435,
      "grad_norm": 0.6488949060440063,
      "learning_rate": 8.293447300593402e-05,
      "loss": 0.6853,
      "step": 86
    },
    {
      "epoch": 14.956521739130435,
      "eval_loss": 1.325171709060669,
      "eval_runtime": 11.1859,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 86
    },
    {
      "epoch": 15.304347826086957,
      "grad_norm": 0.7560678720474243,
      "learning_rate": 8.18711994874345e-05,
      "loss": 0.6334,
      "step": 88
    },
    {
      "epoch": 15.652173913043478,
      "grad_norm": 1.0549603700637817,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.4972,
      "step": 90
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.8922441005706787,
      "learning_rate": 7.967094433018508e-05,
      "loss": 0.6937,
      "step": 92
    },
    {
      "epoch": 16.0,
      "eval_loss": 1.2865952253341675,
      "eval_runtime": 11.1867,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 92
    },
    {
      "epoch": 16.347826086956523,
      "grad_norm": 0.8491520285606384,
      "learning_rate": 7.85356783842216e-05,
      "loss": 0.5464,
      "step": 94
    },
    {
      "epoch": 16.695652173913043,
      "grad_norm": 2.7820653915405273,
      "learning_rate": 7.737816117462752e-05,
      "loss": 0.442,
      "step": 96
    },
    {
      "epoch": 16.869565217391305,
      "eval_loss": 1.3294283151626587,
      "eval_runtime": 11.1849,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 97
    },
    {
      "epoch": 16.869565217391305,
      "step": 97,
      "total_flos": 6.196040276587315e+16,
      "train_loss": 1.0774920527468022,
      "train_runtime": 2292.4001,
      "train_samples_per_second": 1.003,
      "train_steps_per_second": 0.109
    }
  ],
  "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": 6.196040276587315e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}