{
  "best_metric": 0.9771736264228821,
  "best_model_checkpoint": "data/Gemma-2-2B_task-1_60-samples_config-1_auto/checkpoint-28",
  "epoch": 12.0,
  "eval_steps": 500,
  "global_step": 69,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 2.026529312133789,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.4932,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 1.7795902490615845,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.8179,
      "step": 2
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 1.760023832321167,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.5831,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 1.5867716073989868,
      "eval_runtime": 1.1144,
      "eval_samples_per_second": 10.768,
      "eval_steps_per_second": 10.768,
      "step": 5
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 1.921859860420227,
      "learning_rate": 2.4e-05,
      "loss": 1.6549,
      "step": 6
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 1.9553648233413696,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.4656,
      "step": 8
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 1.486262559890747,
      "learning_rate": 4e-05,
      "loss": 1.4338,
      "step": 10
    },
    {
      "epoch": 1.9130434782608696,
      "eval_loss": 1.2779364585876465,
      "eval_runtime": 1.0853,
      "eval_samples_per_second": 11.057,
      "eval_steps_per_second": 11.057,
      "step": 11
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 1.286026120185852,
      "learning_rate": 4.8e-05,
      "loss": 1.4128,
      "step": 12
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 1.2502280473709106,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.1645,
      "step": 14
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 1.1574251651763916,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.0588,
      "step": 16
    },
    {
      "epoch": 2.9565217391304346,
      "eval_loss": 1.0678033828735352,
      "eval_runtime": 1.0826,
      "eval_samples_per_second": 11.085,
      "eval_steps_per_second": 11.085,
      "step": 17
    },
    {
      "epoch": 3.130434782608696,
      "grad_norm": 1.0754584074020386,
      "learning_rate": 7.2e-05,
      "loss": 1.0552,
      "step": 18
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 0.944169282913208,
      "learning_rate": 8e-05,
      "loss": 0.9459,
      "step": 20
    },
    {
      "epoch": 3.8260869565217392,
      "grad_norm": 1.0114011764526367,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.9374,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.0077917575836182,
      "eval_runtime": 1.083,
      "eval_samples_per_second": 11.08,
      "eval_steps_per_second": 11.08,
      "step": 23
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.9251099824905396,
      "learning_rate": 9.6e-05,
      "loss": 0.9526,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.8357123732566833,
      "learning_rate": 9.999512620046522e-05,
      "loss": 0.7848,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.8466804027557373,
      "learning_rate": 9.995614150494293e-05,
      "loss": 0.7559,
      "step": 28
    },
    {
      "epoch": 4.869565217391305,
      "eval_loss": 0.9771736264228821,
      "eval_runtime": 1.0849,
      "eval_samples_per_second": 11.061,
      "eval_steps_per_second": 11.061,
      "step": 28
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 0.8675097227096558,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.681,
      "step": 30
    },
    {
      "epoch": 5.565217391304348,
      "grad_norm": 0.9894130229949951,
      "learning_rate": 9.976136999909156e-05,
      "loss": 0.7126,
      "step": 32
    },
    {
      "epoch": 5.913043478260869,
      "grad_norm": 1.1242010593414307,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.6571,
      "step": 34
    },
    {
      "epoch": 5.913043478260869,
      "eval_loss": 0.9865288138389587,
      "eval_runtime": 1.0869,
      "eval_samples_per_second": 11.041,
      "eval_steps_per_second": 11.041,
      "step": 34
    },
    {
      "epoch": 6.260869565217392,
      "grad_norm": 0.8915111422538757,
      "learning_rate": 9.941141907232765e-05,
      "loss": 0.5573,
      "step": 36
    },
    {
      "epoch": 6.608695652173913,
      "grad_norm": 1.0277915000915527,
      "learning_rate": 9.917857354066931e-05,
      "loss": 0.5516,
      "step": 38
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 1.3185209035873413,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.4598,
      "step": 40
    },
    {
      "epoch": 6.956521739130435,
      "eval_loss": 1.0228421688079834,
      "eval_runtime": 1.0882,
      "eval_samples_per_second": 11.028,
      "eval_steps_per_second": 11.028,
      "step": 40
    },
    {
      "epoch": 7.304347826086957,
      "grad_norm": 1.01520836353302,
      "learning_rate": 9.859805002892732e-05,
      "loss": 0.4091,
      "step": 42
    },
    {
      "epoch": 7.6521739130434785,
      "grad_norm": 1.1463963985443115,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.3405,
      "step": 44
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.176679253578186,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.3646,
      "step": 46
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.1914697885513306,
      "eval_runtime": 1.1,
      "eval_samples_per_second": 10.909,
      "eval_steps_per_second": 10.909,
      "step": 46
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 1.1157606840133667,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.2334,
      "step": 48
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 1.0794093608856201,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2273,
      "step": 50
    },
    {
      "epoch": 8.869565217391305,
      "eval_loss": 1.4645131826400757,
      "eval_runtime": 1.105,
      "eval_samples_per_second": 10.86,
      "eval_steps_per_second": 10.86,
      "step": 51
    },
    {
      "epoch": 9.043478260869565,
      "grad_norm": 1.7337605953216553,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.2184,
      "step": 52
    },
    {
      "epoch": 9.391304347826088,
      "grad_norm": 1.0715246200561523,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.1223,
      "step": 54
    },
    {
      "epoch": 9.73913043478261,
      "grad_norm": 1.4430582523345947,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.1298,
      "step": 56
    },
    {
      "epoch": 9.91304347826087,
      "eval_loss": 1.8401902914047241,
      "eval_runtime": 1.0983,
      "eval_samples_per_second": 10.926,
      "eval_steps_per_second": 10.926,
      "step": 57
    },
    {
      "epoch": 10.08695652173913,
      "grad_norm": 1.7137335538864136,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.1398,
      "step": 58
    },
    {
      "epoch": 10.434782608695652,
      "grad_norm": 1.0176777839660645,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0637,
      "step": 60
    },
    {
      "epoch": 10.782608695652174,
      "grad_norm": 1.0919629335403442,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.0881,
      "step": 62
    },
    {
      "epoch": 10.956521739130435,
      "eval_loss": 2.1072986125946045,
      "eval_runtime": 1.0919,
      "eval_samples_per_second": 10.99,
      "eval_steps_per_second": 10.99,
      "step": 63
    },
    {
      "epoch": 11.130434782608695,
      "grad_norm": 1.0109983682632446,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.0554,
      "step": 64
    },
    {
      "epoch": 11.478260869565217,
      "grad_norm": 1.0501949787139893,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.0428,
      "step": 66
    },
    {
      "epoch": 11.826086956521738,
      "grad_norm": 2.1661949157714844,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.0555,
      "step": 68
    },
    {
      "epoch": 12.0,
      "eval_loss": 2.3284802436828613,
      "eval_runtime": 1.0891,
      "eval_samples_per_second": 11.019,
      "eval_steps_per_second": 11.019,
      "step": 69
    },
    {
      "epoch": 12.0,
      "step": 69,
      "total_flos": 2356609663631360.0,
      "train_loss": 0.6664440068213836,
      "train_runtime": 251.8108,
      "train_samples_per_second": 9.134,
      "train_steps_per_second": 0.993
    }
  ],
  "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": 2356609663631360.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}