{
  "best_metric": 0.4035477638244629,
  "best_model_checkpoint": "data/Llama-31-8B_task-3_60-samples_config-1/checkpoint-40",
  "epoch": 13.91304347826087,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 3.8314883708953857,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.9855,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 1.8149137496948242,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.0019,
      "step": 2
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 2.153667449951172,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.4269,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 2.3329923152923584,
      "eval_runtime": 11.1896,
      "eval_samples_per_second": 1.072,
      "eval_steps_per_second": 1.072,
      "step": 5
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 2.659137487411499,
      "learning_rate": 2.4e-05,
      "loss": 2.3366,
      "step": 6
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 2.862022876739502,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.137,
      "step": 8
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 2.6203739643096924,
      "learning_rate": 4e-05,
      "loss": 1.8916,
      "step": 10
    },
    {
      "epoch": 1.9130434782608696,
      "eval_loss": 1.468563437461853,
      "eval_runtime": 11.1914,
      "eval_samples_per_second": 1.072,
      "eval_steps_per_second": 1.072,
      "step": 11
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 1.6377079486846924,
      "learning_rate": 4.8e-05,
      "loss": 1.5518,
      "step": 12
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 2.481891632080078,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.1619,
      "step": 14
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 1.4599213600158691,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.8252,
      "step": 16
    },
    {
      "epoch": 2.9565217391304346,
      "eval_loss": 0.6677038669586182,
      "eval_runtime": 11.1877,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 17
    },
    {
      "epoch": 3.130434782608696,
      "grad_norm": 0.9547545313835144,
      "learning_rate": 7.2e-05,
      "loss": 0.9158,
      "step": 18
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 0.8306823968887329,
      "learning_rate": 8e-05,
      "loss": 0.6608,
      "step": 20
    },
    {
      "epoch": 3.8260869565217392,
      "grad_norm": 0.8955018520355225,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.4209,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.48618578910827637,
      "eval_runtime": 11.1853,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 23
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 1.083631157875061,
      "learning_rate": 9.6e-05,
      "loss": 0.3913,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 1.0023245811462402,
      "learning_rate": 9.999512620046522e-05,
      "loss": 0.5174,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.3464664816856384,
      "learning_rate": 9.995614150494293e-05,
      "loss": 0.332,
      "step": 28
    },
    {
      "epoch": 4.869565217391305,
      "eval_loss": 0.4469153583049774,
      "eval_runtime": 11.1879,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 28
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 0.7759494781494141,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.4394,
      "step": 30
    },
    {
      "epoch": 5.565217391304348,
      "grad_norm": 1.521958827972412,
      "learning_rate": 9.976136999909156e-05,
      "loss": 0.3773,
      "step": 32
    },
    {
      "epoch": 5.913043478260869,
      "grad_norm": 0.3926154375076294,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.2549,
      "step": 34
    },
    {
      "epoch": 5.913043478260869,
      "eval_loss": 0.42269885540008545,
      "eval_runtime": 11.186,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 34
    },
    {
      "epoch": 6.260869565217392,
      "grad_norm": 0.5048394799232483,
      "learning_rate": 9.941141907232765e-05,
      "loss": 0.2508,
      "step": 36
    },
    {
      "epoch": 6.608695652173913,
      "grad_norm": 0.3910050094127655,
      "learning_rate": 9.917857354066931e-05,
      "loss": 0.3931,
      "step": 38
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 0.3348529040813446,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2452,
      "step": 40
    },
    {
      "epoch": 6.956521739130435,
      "eval_loss": 0.4035477638244629,
      "eval_runtime": 11.1881,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 40
    },
    {
      "epoch": 7.304347826086957,
      "grad_norm": 0.4493715167045593,
      "learning_rate": 9.859805002892732e-05,
      "loss": 0.1967,
      "step": 42
    },
    {
      "epoch": 7.6521739130434785,
      "grad_norm": 0.3937380015850067,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.2896,
      "step": 44
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.6354722380638123,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.3307,
      "step": 46
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.4229266941547394,
      "eval_runtime": 11.1882,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 46
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 0.4818195402622223,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.1406,
      "step": 48
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 0.6015509366989136,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2278,
      "step": 50
    },
    {
      "epoch": 8.869565217391305,
      "eval_loss": 0.4286022484302521,
      "eval_runtime": 11.1871,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 51
    },
    {
      "epoch": 9.043478260869565,
      "grad_norm": 0.5735894441604614,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.2114,
      "step": 52
    },
    {
      "epoch": 9.391304347826088,
      "grad_norm": 0.42579683661460876,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.1073,
      "step": 54
    },
    {
      "epoch": 9.73913043478261,
      "grad_norm": 0.5209540128707886,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.1552,
      "step": 56
    },
    {
      "epoch": 9.91304347826087,
      "eval_loss": 0.5083793997764587,
      "eval_runtime": 11.1857,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 57
    },
    {
      "epoch": 10.08695652173913,
      "grad_norm": 0.7140485048294067,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.1273,
      "step": 58
    },
    {
      "epoch": 10.434782608695652,
      "grad_norm": 1.0909019708633423,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0608,
      "step": 60
    },
    {
      "epoch": 10.782608695652174,
      "grad_norm": 0.671782910823822,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.0554,
      "step": 62
    },
    {
      "epoch": 10.956521739130435,
      "eval_loss": 0.5310074687004089,
      "eval_runtime": 11.1883,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 63
    },
    {
      "epoch": 11.130434782608695,
      "grad_norm": 0.5759596228599548,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.064,
      "step": 64
    },
    {
      "epoch": 11.478260869565217,
      "grad_norm": 0.2150227129459381,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.0195,
      "step": 66
    },
    {
      "epoch": 11.826086956521738,
      "grad_norm": 0.6553301811218262,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.0343,
      "step": 68
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.7841501832008362,
      "eval_runtime": 11.1879,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 69
    },
    {
      "epoch": 12.173913043478262,
      "grad_norm": 0.2658972442150116,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0182,
      "step": 70
    },
    {
      "epoch": 12.521739130434783,
      "grad_norm": 0.30435848236083984,
      "learning_rate": 8.961448216775954e-05,
      "loss": 0.0105,
      "step": 72
    },
    {
      "epoch": 12.869565217391305,
      "grad_norm": 0.5405793190002441,
      "learning_rate": 8.874722443520899e-05,
      "loss": 0.0154,
      "step": 74
    },
    {
      "epoch": 12.869565217391305,
      "eval_loss": 0.7039808630943298,
      "eval_runtime": 11.1884,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 74
    },
    {
      "epoch": 13.217391304347826,
      "grad_norm": 0.4421948790550232,
      "learning_rate": 8.784975278258783e-05,
      "loss": 0.0088,
      "step": 76
    },
    {
      "epoch": 13.565217391304348,
      "grad_norm": 0.3304911255836487,
      "learning_rate": 8.692276703129421e-05,
      "loss": 0.0073,
      "step": 78
    },
    {
      "epoch": 13.91304347826087,
      "grad_norm": 0.14518700540065765,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0048,
      "step": 80
    },
    {
      "epoch": 13.91304347826087,
      "eval_loss": 0.7499859929084778,
      "eval_runtime": 11.1879,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "step": 80
    },
    {
      "epoch": 13.91304347826087,
      "step": 80,
      "total_flos": 5.102621398820454e+16,
      "train_loss": 0.5529784421203658,
      "train_runtime": 1886.9381,
      "train_samples_per_second": 1.219,
      "train_steps_per_second": 0.132
    }
  ],
  "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": 5.102621398820454e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}