{
  "best_metric": 0.8006419539451599,
  "best_model_checkpoint": "data/Mistral-7B_task-1_120-samples_config-2_auto/checkpoint-22",
  "epoch": 10.909090909090908,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 2.5200440883636475,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.0757,
      "step": 1
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.74460768699646,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0848,
      "step": 2
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 2.399035930633545,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.0732,
      "step": 4
    },
    {
      "epoch": 0.9090909090909091,
      "eval_loss": 1.0410027503967285,
      "eval_runtime": 9.9786,
      "eval_samples_per_second": 2.405,
      "eval_steps_per_second": 2.405,
      "step": 5
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 2.24735689163208,
      "learning_rate": 2.4e-05,
      "loss": 1.0927,
      "step": 6
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 1.4750593900680542,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.9017,
      "step": 8
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.4488487243652344,
      "learning_rate": 4e-05,
      "loss": 0.9533,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8651717305183411,
      "eval_runtime": 9.9797,
      "eval_samples_per_second": 2.405,
      "eval_steps_per_second": 2.405,
      "step": 11
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 1.1370949745178223,
      "learning_rate": 4.8e-05,
      "loss": 0.7473,
      "step": 12
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 1.217821478843689,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.8209,
      "step": 14
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 1.2512751817703247,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.77,
      "step": 16
    },
    {
      "epoch": 2.909090909090909,
      "eval_loss": 0.8181025385856628,
      "eval_runtime": 9.9892,
      "eval_samples_per_second": 2.403,
      "eval_steps_per_second": 2.403,
      "step": 16
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 0.911823034286499,
      "learning_rate": 7.2e-05,
      "loss": 0.6774,
      "step": 18
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.9840978384017944,
      "learning_rate": 8e-05,
      "loss": 0.6603,
      "step": 20
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0185283422470093,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.6091,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.8006419539451599,
      "eval_runtime": 9.9803,
      "eval_samples_per_second": 2.405,
      "eval_steps_per_second": 2.405,
      "step": 22
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 1.0211368799209595,
      "learning_rate": 9.6e-05,
      "loss": 0.5531,
      "step": 24
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 1.279502511024475,
      "learning_rate": 9.999512620046522e-05,
      "loss": 0.4937,
      "step": 26
    },
    {
      "epoch": 4.909090909090909,
      "eval_loss": 0.8277094960212708,
      "eval_runtime": 9.98,
      "eval_samples_per_second": 2.405,
      "eval_steps_per_second": 2.405,
      "step": 27
    },
    {
      "epoch": 5.090909090909091,
      "grad_norm": 1.2927266359329224,
      "learning_rate": 9.995614150494293e-05,
      "loss": 0.4136,
      "step": 28
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 1.0783287286758423,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.3471,
      "step": 30
    },
    {
      "epoch": 5.818181818181818,
      "grad_norm": 1.5167845487594604,
      "learning_rate": 9.976136999909156e-05,
      "loss": 0.3093,
      "step": 32
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.9963887333869934,
      "eval_runtime": 9.9808,
      "eval_samples_per_second": 2.405,
      "eval_steps_per_second": 2.405,
      "step": 33
    },
    {
      "epoch": 6.181818181818182,
      "grad_norm": 1.3760337829589844,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.2358,
      "step": 34
    },
    {
      "epoch": 6.545454545454545,
      "grad_norm": 1.3134976625442505,
      "learning_rate": 9.941141907232765e-05,
      "loss": 0.1933,
      "step": 36
    },
    {
      "epoch": 6.909090909090909,
      "grad_norm": 1.4621546268463135,
      "learning_rate": 9.917857354066931e-05,
      "loss": 0.1731,
      "step": 38
    },
    {
      "epoch": 6.909090909090909,
      "eval_loss": 1.081476092338562,
      "eval_runtime": 9.9877,
      "eval_samples_per_second": 2.403,
      "eval_steps_per_second": 2.403,
      "step": 38
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 1.1559796333312988,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1331,
      "step": 40
    },
    {
      "epoch": 7.636363636363637,
      "grad_norm": 1.1186745166778564,
      "learning_rate": 9.859805002892732e-05,
      "loss": 0.0815,
      "step": 42
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.7643119096755981,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.1045,
      "step": 44
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.3043652772903442,
      "eval_runtime": 9.9847,
      "eval_samples_per_second": 2.404,
      "eval_steps_per_second": 2.404,
      "step": 44
    },
    {
      "epoch": 8.363636363636363,
      "grad_norm": 1.0151166915893555,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.0489,
      "step": 46
    },
    {
      "epoch": 8.727272727272727,
      "grad_norm": 2.2880821228027344,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.0642,
      "step": 48
    },
    {
      "epoch": 8.909090909090908,
      "eval_loss": 1.3456028699874878,
      "eval_runtime": 9.9818,
      "eval_samples_per_second": 2.404,
      "eval_steps_per_second": 2.404,
      "step": 49
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 1.4389766454696655,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0681,
      "step": 50
    },
    {
      "epoch": 9.454545454545455,
      "grad_norm": 0.7696138620376587,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.0378,
      "step": 52
    },
    {
      "epoch": 9.818181818181818,
      "grad_norm": 1.0077182054519653,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.0552,
      "step": 54
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.4000715017318726,
      "eval_runtime": 9.9796,
      "eval_samples_per_second": 2.405,
      "eval_steps_per_second": 2.405,
      "step": 55
    },
    {
      "epoch": 10.181818181818182,
      "grad_norm": 1.0939630270004272,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.0368,
      "step": 56
    },
    {
      "epoch": 10.545454545454545,
      "grad_norm": 1.0606611967086792,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.0318,
      "step": 58
    },
    {
      "epoch": 10.909090909090908,
      "grad_norm": 0.8217382431030273,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0359,
      "step": 60
    },
    {
      "epoch": 10.909090909090908,
      "eval_loss": 1.489484429359436,
      "eval_runtime": 9.984,
      "eval_samples_per_second": 2.404,
      "eval_steps_per_second": 2.404,
      "step": 60
    },
    {
      "epoch": 10.909090909090908,
      "step": 60,
      "total_flos": 1.5952182167732224e+16,
      "train_loss": 0.42697442828988036,
      "train_runtime": 1180.2738,
      "train_samples_per_second": 3.728,
      "train_steps_per_second": 0.212
    }
  ],
  "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": 1.5952182167732224e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}