{
  "best_metric": 0.5998861789703369,
  "best_model_checkpoint": "data/Llama-31-8B_task-2_60-samples_config-1_auto/checkpoint-34",
  "epoch": 12.869565217391305,
  "eval_steps": 500,
  "global_step": 74,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.42300620675086975,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.824,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.4288937449455261,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9683,
      "step": 2
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.3874884247779846,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.8547,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 0.8787198066711426,
      "eval_runtime": 13.3407,
      "eval_samples_per_second": 0.9,
      "eval_steps_per_second": 0.9,
      "step": 5
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.4130929708480835,
      "learning_rate": 2.4e-05,
      "loss": 0.873,
      "step": 6
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.416022926568985,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.8494,
      "step": 8
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.36378711462020874,
      "learning_rate": 4e-05,
      "loss": 0.8316,
      "step": 10
    },
    {
      "epoch": 1.9130434782608696,
      "eval_loss": 0.7977904677391052,
      "eval_runtime": 13.3416,
      "eval_samples_per_second": 0.899,
      "eval_steps_per_second": 0.899,
      "step": 11
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.3718477785587311,
      "learning_rate": 4.8e-05,
      "loss": 0.8102,
      "step": 12
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.3050856292247772,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.7164,
      "step": 14
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.3262587785720825,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.7352,
      "step": 16
    },
    {
      "epoch": 2.9565217391304346,
      "eval_loss": 0.7124518752098083,
      "eval_runtime": 13.3427,
      "eval_samples_per_second": 0.899,
      "eval_steps_per_second": 0.899,
      "step": 17
    },
    {
      "epoch": 3.130434782608696,
      "grad_norm": 0.3741619288921356,
      "learning_rate": 7.2e-05,
      "loss": 0.6842,
      "step": 18
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 0.3369562029838562,
      "learning_rate": 8e-05,
      "loss": 0.6401,
      "step": 20
    },
    {
      "epoch": 3.8260869565217392,
      "grad_norm": 0.30441024899482727,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.6096,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6426070332527161,
      "eval_runtime": 13.3438,
      "eval_samples_per_second": 0.899,
      "eval_steps_per_second": 0.899,
      "step": 23
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.33171817660331726,
      "learning_rate": 9.6e-05,
      "loss": 0.6115,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.39163708686828613,
      "learning_rate": 9.999512620046522e-05,
      "loss": 0.5717,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.38159558176994324,
      "learning_rate": 9.995614150494293e-05,
      "loss": 0.5369,
      "step": 28
    },
    {
      "epoch": 4.869565217391305,
      "eval_loss": 0.6109557747840881,
      "eval_runtime": 13.3464,
      "eval_samples_per_second": 0.899,
      "eval_steps_per_second": 0.899,
      "step": 28
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 0.37450674176216125,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.4848,
      "step": 30
    },
    {
      "epoch": 5.565217391304348,
      "grad_norm": 0.3854338824748993,
      "learning_rate": 9.976136999909156e-05,
      "loss": 0.5116,
      "step": 32
    },
    {
      "epoch": 5.913043478260869,
      "grad_norm": 0.3476805090904236,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.4624,
      "step": 34
    },
    {
      "epoch": 5.913043478260869,
      "eval_loss": 0.5998861789703369,
      "eval_runtime": 13.3403,
      "eval_samples_per_second": 0.9,
      "eval_steps_per_second": 0.9,
      "step": 34
    },
    {
      "epoch": 6.260869565217392,
      "grad_norm": 0.3531424403190613,
      "learning_rate": 9.941141907232765e-05,
      "loss": 0.4299,
      "step": 36
    },
    {
      "epoch": 6.608695652173913,
      "grad_norm": 0.4284851551055908,
      "learning_rate": 9.917857354066931e-05,
      "loss": 0.4254,
      "step": 38
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 0.43844202160835266,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.3577,
      "step": 40
    },
    {
      "epoch": 6.956521739130435,
      "eval_loss": 0.631374180316925,
      "eval_runtime": 13.3436,
      "eval_samples_per_second": 0.899,
      "eval_steps_per_second": 0.899,
      "step": 40
    },
    {
      "epoch": 7.304347826086957,
      "grad_norm": 0.4331451654434204,
      "learning_rate": 9.859805002892732e-05,
      "loss": 0.3568,
      "step": 42
    },
    {
      "epoch": 7.6521739130434785,
      "grad_norm": 0.5172120332717896,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.2935,
      "step": 44
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.5505191087722778,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.3027,
      "step": 46
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.6915586590766907,
      "eval_runtime": 13.3429,
      "eval_samples_per_second": 0.899,
      "eval_steps_per_second": 0.899,
      "step": 46
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 0.5537309050559998,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.2301,
      "step": 48
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 0.6507230401039124,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2146,
      "step": 50
    },
    {
      "epoch": 8.869565217391305,
      "eval_loss": 0.7508694529533386,
      "eval_runtime": 13.3407,
      "eval_samples_per_second": 0.9,
      "eval_steps_per_second": 0.9,
      "step": 51
    },
    {
      "epoch": 9.043478260869565,
      "grad_norm": 0.6203398108482361,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.1959,
      "step": 52
    },
    {
      "epoch": 9.391304347826088,
      "grad_norm": 0.562064528465271,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.1165,
      "step": 54
    },
    {
      "epoch": 9.73913043478261,
      "grad_norm": 0.6549424529075623,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.1132,
      "step": 56
    },
    {
      "epoch": 9.91304347826087,
      "eval_loss": 0.9555017948150635,
      "eval_runtime": 13.3405,
      "eval_samples_per_second": 0.9,
      "eval_steps_per_second": 0.9,
      "step": 57
    },
    {
      "epoch": 10.08695652173913,
      "grad_norm": 0.798380970954895,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.1154,
      "step": 58
    },
    {
      "epoch": 10.434782608695652,
      "grad_norm": 0.5680138468742371,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0512,
      "step": 60
    },
    {
      "epoch": 10.782608695652174,
      "grad_norm": 0.665852963924408,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.0626,
      "step": 62
    },
    {
      "epoch": 10.956521739130435,
      "eval_loss": 1.0439895391464233,
      "eval_runtime": 13.3424,
      "eval_samples_per_second": 0.899,
      "eval_steps_per_second": 0.899,
      "step": 63
    },
    {
      "epoch": 11.130434782608695,
      "grad_norm": 0.5211048126220703,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.0456,
      "step": 64
    },
    {
      "epoch": 11.478260869565217,
      "grad_norm": 0.5096816420555115,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.0349,
      "step": 66
    },
    {
      "epoch": 11.826086956521738,
      "grad_norm": 0.9088841080665588,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.0376,
      "step": 68
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.1408032178878784,
      "eval_runtime": 13.3441,
      "eval_samples_per_second": 0.899,
      "eval_steps_per_second": 0.899,
      "step": 69
    },
    {
      "epoch": 12.173913043478262,
      "grad_norm": 0.2537411153316498,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0219,
      "step": 70
    },
    {
      "epoch": 12.521739130434783,
      "grad_norm": 0.5168859362602234,
      "learning_rate": 8.961448216775954e-05,
      "loss": 0.0166,
      "step": 72
    },
    {
      "epoch": 12.869565217391305,
      "grad_norm": 0.6679970026016235,
      "learning_rate": 8.874722443520899e-05,
      "loss": 0.0262,
      "step": 74
    },
    {
      "epoch": 12.869565217391305,
      "eval_loss": 1.1577156782150269,
      "eval_runtime": 13.3402,
      "eval_samples_per_second": 0.9,
      "eval_steps_per_second": 0.9,
      "step": 74
    },
    {
      "epoch": 12.869565217391305,
      "step": 74,
      "total_flos": 6.016355399001702e+16,
      "train_loss": 0.40909132293450673,
      "train_runtime": 2152.0328,
      "train_samples_per_second": 1.069,
      "train_steps_per_second": 0.116
    }
  ],
  "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": 6.016355399001702e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}