{
  "best_metric": 1.0622392892837524,
  "best_model_checkpoint": "data/Llama-31-8B_task-2_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": 0.5169600248336792,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.5956,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.5719379782676697,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.6046,
      "step": 2
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.4639497995376587,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.5616,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 1.5645689964294434,
      "eval_runtime": 12.9782,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 5
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.43013307452201843,
      "learning_rate": 2.4e-05,
      "loss": 1.5469,
      "step": 6
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.4737662971019745,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.5401,
      "step": 8
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.35715150833129883,
      "learning_rate": 4e-05,
      "loss": 1.5234,
      "step": 10
    },
    {
      "epoch": 1.9130434782608696,
      "eval_loss": 1.461713194847107,
      "eval_runtime": 12.9809,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 11
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.38341426849365234,
      "learning_rate": 4.8e-05,
      "loss": 1.4674,
      "step": 12
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.308226615190506,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.3736,
      "step": 14
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.24405591189861298,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.4186,
      "step": 16
    },
    {
      "epoch": 2.9565217391304346,
      "eval_loss": 1.3542251586914062,
      "eval_runtime": 12.9777,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 17
    },
    {
      "epoch": 3.130434782608696,
      "grad_norm": 0.2537368834018707,
      "learning_rate": 7.2e-05,
      "loss": 1.3081,
      "step": 18
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 0.2890937328338623,
      "learning_rate": 8e-05,
      "loss": 1.2946,
      "step": 20
    },
    {
      "epoch": 3.8260869565217392,
      "grad_norm": 0.26166918873786926,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.2508,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.244210124015808,
      "eval_runtime": 12.9733,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 23
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.25255441665649414,
      "learning_rate": 9.6e-05,
      "loss": 1.2456,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.3032490313053131,
      "learning_rate": 9.999512620046522e-05,
      "loss": 1.1783,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.26784947514533997,
      "learning_rate": 9.995614150494293e-05,
      "loss": 1.1191,
      "step": 28
    },
    {
      "epoch": 4.869565217391305,
      "eval_loss": 1.14983332157135,
      "eval_runtime": 12.9774,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 28
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 0.2250259667634964,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.0355,
      "step": 30
    },
    {
      "epoch": 5.565217391304348,
      "grad_norm": 0.19060257077217102,
      "learning_rate": 9.976136999909156e-05,
      "loss": 1.0818,
      "step": 32
    },
    {
      "epoch": 5.913043478260869,
      "grad_norm": 0.17199891805648804,
      "learning_rate": 9.96057350657239e-05,
      "loss": 1.0371,
      "step": 34
    },
    {
      "epoch": 5.913043478260869,
      "eval_loss": 1.1009820699691772,
      "eval_runtime": 12.976,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 34
    },
    {
      "epoch": 6.260869565217392,
      "grad_norm": 0.15584895014762878,
      "learning_rate": 9.941141907232765e-05,
      "loss": 1.0046,
      "step": 36
    },
    {
      "epoch": 6.608695652173913,
      "grad_norm": 0.17626440525054932,
      "learning_rate": 9.917857354066931e-05,
      "loss": 1.0342,
      "step": 38
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 0.16024109721183777,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9695,
      "step": 40
    },
    {
      "epoch": 6.956521739130435,
      "eval_loss": 1.0839170217514038,
      "eval_runtime": 12.9799,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 40
    },
    {
      "epoch": 7.304347826086957,
      "grad_norm": 0.1579640954732895,
      "learning_rate": 9.859805002892732e-05,
      "loss": 1.0287,
      "step": 42
    },
    {
      "epoch": 7.6521739130434785,
      "grad_norm": 0.15491770207881927,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.9668,
      "step": 44
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.1564716398715973,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.968,
      "step": 46
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.0704442262649536,
      "eval_runtime": 12.9763,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 46
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 0.16076144576072693,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.9709,
      "step": 48
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 0.18459276854991913,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.9532,
      "step": 50
    },
    {
      "epoch": 8.869565217391305,
      "eval_loss": 1.064635157585144,
      "eval_runtime": 12.978,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 51
    },
    {
      "epoch": 9.043478260869565,
      "grad_norm": 0.1734301596879959,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.9396,
      "step": 52
    },
    {
      "epoch": 9.391304347826088,
      "grad_norm": 0.17895378172397614,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.8944,
      "step": 54
    },
    {
      "epoch": 9.73913043478261,
      "grad_norm": 0.2069927155971527,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.9439,
      "step": 56
    },
    {
      "epoch": 9.91304347826087,
      "eval_loss": 1.0622392892837524,
      "eval_runtime": 12.9867,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 57
    },
    {
      "epoch": 10.08695652173913,
      "grad_norm": 0.19146595895290375,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.9318,
      "step": 58
    },
    {
      "epoch": 10.434782608695652,
      "grad_norm": 0.19947046041488647,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.898,
      "step": 60
    },
    {
      "epoch": 10.782608695652174,
      "grad_norm": 0.24781489372253418,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.8579,
      "step": 62
    },
    {
      "epoch": 10.956521739130435,
      "eval_loss": 1.0686115026474,
      "eval_runtime": 12.9836,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 63
    },
    {
      "epoch": 11.130434782608695,
      "grad_norm": 0.24519693851470947,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.8425,
      "step": 64
    },
    {
      "epoch": 11.478260869565217,
      "grad_norm": 0.22730785608291626,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.9092,
      "step": 66
    },
    {
      "epoch": 11.826086956521738,
      "grad_norm": 0.271567702293396,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.8117,
      "step": 68
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.0770955085754395,
      "eval_runtime": 12.9775,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 69
    },
    {
      "epoch": 12.173913043478262,
      "grad_norm": 0.25126487016677856,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8277,
      "step": 70
    },
    {
      "epoch": 12.521739130434783,
      "grad_norm": 0.3141935467720032,
      "learning_rate": 8.961448216775954e-05,
      "loss": 0.7534,
      "step": 72
    },
    {
      "epoch": 12.869565217391305,
      "grad_norm": 0.34278011322021484,
      "learning_rate": 8.874722443520899e-05,
      "loss": 0.8138,
      "step": 74
    },
    {
      "epoch": 12.869565217391305,
      "eval_loss": 1.0898820161819458,
      "eval_runtime": 12.981,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 74
    },
    {
      "epoch": 13.217391304347826,
      "grad_norm": 0.34557563066482544,
      "learning_rate": 8.784975278258783e-05,
      "loss": 0.7593,
      "step": 76
    },
    {
      "epoch": 13.565217391304348,
      "grad_norm": 0.4051405191421509,
      "learning_rate": 8.692276703129421e-05,
      "loss": 0.7631,
      "step": 78
    },
    {
      "epoch": 13.91304347826087,
      "grad_norm": 0.5333661437034607,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.7059,
      "step": 80
    },
    {
      "epoch": 13.91304347826087,
      "eval_loss": 1.1196229457855225,
      "eval_runtime": 12.9799,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 80
    },
    {
      "epoch": 14.26086956521739,
      "grad_norm": 0.8778398633003235,
      "learning_rate": 8.498316702566828e-05,
      "loss": 0.6443,
      "step": 82
    },
    {
      "epoch": 14.608695652173914,
      "grad_norm": 0.5189895033836365,
      "learning_rate": 8.397206521307584e-05,
      "loss": 0.6464,
      "step": 84
    },
    {
      "epoch": 14.956521739130435,
      "grad_norm": 0.5316717028617859,
      "learning_rate": 8.293447300593402e-05,
      "loss": 0.6519,
      "step": 86
    },
    {
      "epoch": 14.956521739130435,
      "eval_loss": 1.1534786224365234,
      "eval_runtime": 12.9777,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 86
    },
    {
      "epoch": 15.304347826086957,
      "grad_norm": 0.5730365514755249,
      "learning_rate": 8.18711994874345e-05,
      "loss": 0.6042,
      "step": 88
    },
    {
      "epoch": 15.652173913043478,
      "grad_norm": 0.6490305066108704,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.4823,
      "step": 90
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.5794640183448792,
      "learning_rate": 7.967094433018508e-05,
      "loss": 0.65,
      "step": 92
    },
    {
      "epoch": 16.0,
      "eval_loss": 1.20449697971344,
      "eval_runtime": 12.9877,
      "eval_samples_per_second": 0.924,
      "eval_steps_per_second": 0.924,
      "step": 92
    },
    {
      "epoch": 16.347826086956523,
      "grad_norm": 1.153088927268982,
      "learning_rate": 7.85356783842216e-05,
      "loss": 0.5196,
      "step": 94
    },
    {
      "epoch": 16.695652173913043,
      "grad_norm": 0.7702380418777466,
      "learning_rate": 7.737816117462752e-05,
      "loss": 0.405,
      "step": 96
    },
    {
      "epoch": 16.869565217391305,
      "eval_loss": 1.254443883895874,
      "eval_runtime": 12.9788,
      "eval_samples_per_second": 0.925,
      "eval_steps_per_second": 0.925,
      "step": 97
    },
    {
      "epoch": 16.869565217391305,
      "step": 97,
      "total_flos": 7.557782026846208e+16,
      "train_loss": 0.9939013191105164,
      "train_runtime": 2720.2971,
      "train_samples_per_second": 0.845,
      "train_steps_per_second": 0.092
    }
  ],
  "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": 7.557782026846208e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}