{
  "best_metric": 0.8310017585754395,
  "best_model_checkpoint": "data/Mistral-7B_task-1_120-samples_config-2_full_auto/checkpoint-33",
  "epoch": 12.909090909090908,
  "eval_steps": 500,
  "global_step": 71,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 1.9838634729385376,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.7113,
      "step": 1
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.1368112564086914,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.8137,
      "step": 2
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.8914555311203003,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.7345,
      "step": 4
    },
    {
      "epoch": 0.9090909090909091,
      "eval_loss": 1.6530523300170898,
      "eval_runtime": 9.9736,
      "eval_samples_per_second": 2.406,
      "eval_steps_per_second": 2.406,
      "step": 5
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 1.875381588935852,
      "learning_rate": 2.4e-05,
      "loss": 1.7388,
      "step": 6
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 1.2540829181671143,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.5623,
      "step": 8
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.1384962797164917,
      "learning_rate": 4e-05,
      "loss": 1.5053,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.3127946853637695,
      "eval_runtime": 9.9703,
      "eval_samples_per_second": 2.407,
      "eval_steps_per_second": 2.407,
      "step": 11
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 1.1722956895828247,
      "learning_rate": 4.8e-05,
      "loss": 1.2826,
      "step": 12
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 1.5166568756103516,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.2215,
      "step": 14
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 1.1790285110473633,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.0785,
      "step": 16
    },
    {
      "epoch": 2.909090909090909,
      "eval_loss": 0.9975817203521729,
      "eval_runtime": 9.9664,
      "eval_samples_per_second": 2.408,
      "eval_steps_per_second": 2.408,
      "step": 16
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 1.091530203819275,
      "learning_rate": 7.2e-05,
      "loss": 0.939,
      "step": 18
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.8115152716636658,
      "learning_rate": 8e-05,
      "loss": 0.8785,
      "step": 20
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7138871550559998,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.8576,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.8724855780601501,
      "eval_runtime": 9.9808,
      "eval_samples_per_second": 2.405,
      "eval_steps_per_second": 2.405,
      "step": 22
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 0.621791660785675,
      "learning_rate": 9.6e-05,
      "loss": 0.8156,
      "step": 24
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 0.547651469707489,
      "learning_rate": 9.999512620046522e-05,
      "loss": 0.7886,
      "step": 26
    },
    {
      "epoch": 4.909090909090909,
      "eval_loss": 0.835381031036377,
      "eval_runtime": 9.9679,
      "eval_samples_per_second": 2.408,
      "eval_steps_per_second": 2.408,
      "step": 27
    },
    {
      "epoch": 5.090909090909091,
      "grad_norm": 0.6008999347686768,
      "learning_rate": 9.995614150494293e-05,
      "loss": 0.7344,
      "step": 28
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.5711919665336609,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.6908,
      "step": 30
    },
    {
      "epoch": 5.818181818181818,
      "grad_norm": 0.6187372207641602,
      "learning_rate": 9.976136999909156e-05,
      "loss": 0.6952,
      "step": 32
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.8310017585754395,
      "eval_runtime": 9.9648,
      "eval_samples_per_second": 2.408,
      "eval_steps_per_second": 2.408,
      "step": 33
    },
    {
      "epoch": 6.181818181818182,
      "grad_norm": 0.6039671897888184,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.6334,
      "step": 34
    },
    {
      "epoch": 6.545454545454545,
      "grad_norm": 0.650557279586792,
      "learning_rate": 9.941141907232765e-05,
      "loss": 0.6245,
      "step": 36
    },
    {
      "epoch": 6.909090909090909,
      "grad_norm": 0.7548458576202393,
      "learning_rate": 9.917857354066931e-05,
      "loss": 0.5826,
      "step": 38
    },
    {
      "epoch": 6.909090909090909,
      "eval_loss": 0.8411148190498352,
      "eval_runtime": 9.9977,
      "eval_samples_per_second": 2.401,
      "eval_steps_per_second": 2.401,
      "step": 38
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 0.7017354965209961,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.532,
      "step": 40
    },
    {
      "epoch": 7.636363636363637,
      "grad_norm": 0.8429603576660156,
      "learning_rate": 9.859805002892732e-05,
      "loss": 0.462,
      "step": 42
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.2680151462554932,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.4708,
      "step": 44
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.8912167549133301,
      "eval_runtime": 9.9668,
      "eval_samples_per_second": 2.408,
      "eval_steps_per_second": 2.408,
      "step": 44
    },
    {
      "epoch": 8.363636363636363,
      "grad_norm": 0.962690532207489,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.3822,
      "step": 46
    },
    {
      "epoch": 8.727272727272727,
      "grad_norm": 0.9863336682319641,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.3586,
      "step": 48
    },
    {
      "epoch": 8.909090909090908,
      "eval_loss": 0.9640557765960693,
      "eval_runtime": 9.9737,
      "eval_samples_per_second": 2.406,
      "eval_steps_per_second": 2.406,
      "step": 49
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 1.2356395721435547,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.3379,
      "step": 50
    },
    {
      "epoch": 9.454545454545455,
      "grad_norm": 1.0257391929626465,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.261,
      "step": 52
    },
    {
      "epoch": 9.818181818181818,
      "grad_norm": 1.2543127536773682,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.2553,
      "step": 54
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.0596362352371216,
      "eval_runtime": 9.9679,
      "eval_samples_per_second": 2.408,
      "eval_steps_per_second": 2.408,
      "step": 55
    },
    {
      "epoch": 10.181818181818182,
      "grad_norm": 0.8665857911109924,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.2243,
      "step": 56
    },
    {
      "epoch": 10.545454545454545,
      "grad_norm": 0.9961050152778625,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.193,
      "step": 58
    },
    {
      "epoch": 10.909090909090908,
      "grad_norm": 1.193697452545166,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2006,
      "step": 60
    },
    {
      "epoch": 10.909090909090908,
      "eval_loss": 1.1654163599014282,
      "eval_runtime": 9.9703,
      "eval_samples_per_second": 2.407,
      "eval_steps_per_second": 2.407,
      "step": 60
    },
    {
      "epoch": 11.272727272727273,
      "grad_norm": 0.8195732831954956,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.1562,
      "step": 62
    },
    {
      "epoch": 11.636363636363637,
      "grad_norm": 1.2003705501556396,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.1497,
      "step": 64
    },
    {
      "epoch": 12.0,
      "grad_norm": 1.547230839729309,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.1612,
      "step": 66
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.235763430595398,
      "eval_runtime": 9.9721,
      "eval_samples_per_second": 2.407,
      "eval_steps_per_second": 2.407,
      "step": 66
    },
    {
      "epoch": 12.363636363636363,
      "grad_norm": 0.8761946558952332,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.1261,
      "step": 68
    },
    {
      "epoch": 12.727272727272727,
      "grad_norm": 1.0304591655731201,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1398,
      "step": 70
    },
    {
      "epoch": 12.909090909090908,
      "eval_loss": 1.2212626934051514,
      "eval_runtime": 9.9686,
      "eval_samples_per_second": 2.408,
      "eval_steps_per_second": 2.408,
      "step": 71
    },
    {
      "epoch": 12.909090909090908,
      "step": 71,
      "total_flos": 1.885257891787571e+16,
      "train_loss": 0.6939811198644235,
      "train_runtime": 1389.882,
      "train_samples_per_second": 3.166,
      "train_steps_per_second": 0.18
    }
  ],
  "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": 1.885257891787571e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}