{
  "best_metric": 0.42271220684051514,
  "best_model_checkpoint": "data/Gemma-2-2B_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": 10.146446228027344,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.3607,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 3.9102349281311035,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.5129,
      "step": 2
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 4.964460849761963,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.2369,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 3.1359078884124756,
      "eval_runtime": 4.3268,
      "eval_samples_per_second": 2.773,
      "eval_steps_per_second": 2.773,
      "step": 5
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 6.353696823120117,
      "learning_rate": 2.4e-05,
      "loss": 3.1786,
      "step": 6
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 7.290201663970947,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.9415,
      "step": 8
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 6.413881778717041,
      "learning_rate": 4e-05,
      "loss": 2.5226,
      "step": 10
    },
    {
      "epoch": 1.9130434782608696,
      "eval_loss": 1.7106043100357056,
      "eval_runtime": 4.1466,
      "eval_samples_per_second": 2.894,
      "eval_steps_per_second": 2.894,
      "step": 11
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 2.802180051803589,
      "learning_rate": 4.8e-05,
      "loss": 1.8672,
      "step": 12
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 4.53109073638916,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.4697,
      "step": 14
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 2.7835044860839844,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.1016,
      "step": 16
    },
    {
      "epoch": 2.9565217391304346,
      "eval_loss": 0.7912492156028748,
      "eval_runtime": 4.1534,
      "eval_samples_per_second": 2.889,
      "eval_steps_per_second": 2.889,
      "step": 17
    },
    {
      "epoch": 3.130434782608696,
      "grad_norm": 1.4576541185379028,
      "learning_rate": 7.2e-05,
      "loss": 1.0054,
      "step": 18
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 1.0580472946166992,
      "learning_rate": 8e-05,
      "loss": 0.7351,
      "step": 20
    },
    {
      "epoch": 3.8260869565217392,
      "grad_norm": 1.0042097568511963,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.45,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5231990218162537,
      "eval_runtime": 4.1455,
      "eval_samples_per_second": 2.895,
      "eval_steps_per_second": 2.895,
      "step": 23
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.7644234299659729,
      "learning_rate": 9.6e-05,
      "loss": 0.4357,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.7768363952636719,
      "learning_rate": 9.999512620046522e-05,
      "loss": 0.5259,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.6981846690177917,
      "learning_rate": 9.995614150494293e-05,
      "loss": 0.3492,
      "step": 28
    },
    {
      "epoch": 4.869565217391305,
      "eval_loss": 0.4661372900009155,
      "eval_runtime": 4.1458,
      "eval_samples_per_second": 2.894,
      "eval_steps_per_second": 2.894,
      "step": 28
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 0.6776373982429504,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.4199,
      "step": 30
    },
    {
      "epoch": 5.565217391304348,
      "grad_norm": 0.5079626441001892,
      "learning_rate": 9.976136999909156e-05,
      "loss": 0.3505,
      "step": 32
    },
    {
      "epoch": 5.913043478260869,
      "grad_norm": 0.4722975194454193,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.2407,
      "step": 34
    },
    {
      "epoch": 5.913043478260869,
      "eval_loss": 0.42708635330200195,
      "eval_runtime": 4.1456,
      "eval_samples_per_second": 2.895,
      "eval_steps_per_second": 2.895,
      "step": 34
    },
    {
      "epoch": 6.260869565217392,
      "grad_norm": 0.4819077253341675,
      "learning_rate": 9.941141907232765e-05,
      "loss": 0.2277,
      "step": 36
    },
    {
      "epoch": 6.608695652173913,
      "grad_norm": 0.6771033406257629,
      "learning_rate": 9.917857354066931e-05,
      "loss": 0.3285,
      "step": 38
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 0.5343215465545654,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2032,
      "step": 40
    },
    {
      "epoch": 6.956521739130435,
      "eval_loss": 0.42271220684051514,
      "eval_runtime": 4.1435,
      "eval_samples_per_second": 2.896,
      "eval_steps_per_second": 2.896,
      "step": 40
    },
    {
      "epoch": 7.304347826086957,
      "grad_norm": 1.0948623418807983,
      "learning_rate": 9.859805002892732e-05,
      "loss": 0.17,
      "step": 42
    },
    {
      "epoch": 7.6521739130434785,
      "grad_norm": 0.5120678544044495,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.1442,
      "step": 44
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.6902849078178406,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.2575,
      "step": 46
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.4339255392551422,
      "eval_runtime": 4.1392,
      "eval_samples_per_second": 2.899,
      "eval_steps_per_second": 2.899,
      "step": 46
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 0.5653378367424011,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.1162,
      "step": 48
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 0.5017738342285156,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1486,
      "step": 50
    },
    {
      "epoch": 8.869565217391305,
      "eval_loss": 0.48427414894104004,
      "eval_runtime": 4.1461,
      "eval_samples_per_second": 2.894,
      "eval_steps_per_second": 2.894,
      "step": 51
    },
    {
      "epoch": 9.043478260869565,
      "grad_norm": 1.150048851966858,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.1247,
      "step": 52
    },
    {
      "epoch": 9.391304347826088,
      "grad_norm": 0.5316926836967468,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.0568,
      "step": 54
    },
    {
      "epoch": 9.73913043478261,
      "grad_norm": 0.6746953725814819,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.0961,
      "step": 56
    },
    {
      "epoch": 9.91304347826087,
      "eval_loss": 0.5847387313842773,
      "eval_runtime": 4.1449,
      "eval_samples_per_second": 2.895,
      "eval_steps_per_second": 2.895,
      "step": 57
    },
    {
      "epoch": 10.08695652173913,
      "grad_norm": 0.5914088487625122,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.074,
      "step": 58
    },
    {
      "epoch": 10.434782608695652,
      "grad_norm": 0.5299249887466431,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0294,
      "step": 60
    },
    {
      "epoch": 10.782608695652174,
      "grad_norm": 0.919384777545929,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.0285,
      "step": 62
    },
    {
      "epoch": 10.956521739130435,
      "eval_loss": 0.7613394856452942,
      "eval_runtime": 4.144,
      "eval_samples_per_second": 2.896,
      "eval_steps_per_second": 2.896,
      "step": 63
    },
    {
      "epoch": 11.130434782608695,
      "grad_norm": 0.4312540888786316,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.0218,
      "step": 64
    },
    {
      "epoch": 11.478260869565217,
      "grad_norm": 0.10152506828308105,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.0079,
      "step": 66
    },
    {
      "epoch": 11.826086956521738,
      "grad_norm": 1.1622179746627808,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.0231,
      "step": 68
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.8746951222419739,
      "eval_runtime": 4.1414,
      "eval_samples_per_second": 2.898,
      "eval_steps_per_second": 2.898,
      "step": 69
    },
    {
      "epoch": 12.173913043478262,
      "grad_norm": 0.28440412878990173,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0052,
      "step": 70
    },
    {
      "epoch": 12.521739130434783,
      "grad_norm": 0.2543913424015045,
      "learning_rate": 8.961448216775954e-05,
      "loss": 0.0042,
      "step": 72
    },
    {
      "epoch": 12.869565217391305,
      "grad_norm": 1.0935192108154297,
      "learning_rate": 8.874722443520899e-05,
      "loss": 0.0118,
      "step": 74
    },
    {
      "epoch": 12.869565217391305,
      "eval_loss": 0.9378873705863953,
      "eval_runtime": 4.145,
      "eval_samples_per_second": 2.895,
      "eval_steps_per_second": 2.895,
      "step": 74
    },
    {
      "epoch": 13.217391304347826,
      "grad_norm": 0.28088173270225525,
      "learning_rate": 8.784975278258783e-05,
      "loss": 0.0044,
      "step": 76
    },
    {
      "epoch": 13.565217391304348,
      "grad_norm": 0.14173804223537445,
      "learning_rate": 8.692276703129421e-05,
      "loss": 0.0027,
      "step": 78
    },
    {
      "epoch": 13.91304347826087,
      "grad_norm": 1.3909518718719482,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0095,
      "step": 80
    },
    {
      "epoch": 13.91304347826087,
      "eval_loss": 1.0328662395477295,
      "eval_runtime": 4.1433,
      "eval_samples_per_second": 2.896,
      "eval_steps_per_second": 2.896,
      "step": 80
    },
    {
      "epoch": 13.91304347826087,
      "step": 80,
      "total_flos": 1.7573306278346752e+16,
      "train_loss": 0.6591164629440754,
      "train_runtime": 754.5401,
      "train_samples_per_second": 3.048,
      "train_steps_per_second": 0.331
    }
  ],
  "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": 1.7573306278346752e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}