{
  "best_metric": 0.2812866270542145,
  "best_model_checkpoint": "data/Mistral-7B_task-3_120-samples_config-2_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": 21.392839431762695,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.1987,
      "step": 1
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 17.403121948242188,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.5805,
      "step": 2
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 14.737586975097656,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.1892,
      "step": 4
    },
    {
      "epoch": 0.9090909090909091,
      "eval_loss": 2.4893863201141357,
      "eval_runtime": 25.893,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 5
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 12.430584907531738,
      "learning_rate": 2.4e-05,
      "loss": 2.6253,
      "step": 6
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 8.785200119018555,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.9485,
      "step": 8
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 5.381682395935059,
      "learning_rate": 4e-05,
      "loss": 1.3236,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.7405276298522949,
      "eval_runtime": 25.8829,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 11
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 3.744516372680664,
      "learning_rate": 4.8e-05,
      "loss": 0.7978,
      "step": 12
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 1.7489300966262817,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.6065,
      "step": 14
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 1.2228829860687256,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.4001,
      "step": 16
    },
    {
      "epoch": 2.909090909090909,
      "eval_loss": 0.4179682433605194,
      "eval_runtime": 25.8942,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 16
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 0.4868534207344055,
      "learning_rate": 7.2e-05,
      "loss": 0.2912,
      "step": 18
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.8989564180374146,
      "learning_rate": 8e-05,
      "loss": 0.3709,
      "step": 20
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7113804817199707,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.3601,
      "step": 22
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.3181956112384796,
      "eval_runtime": 25.8852,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 22
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 0.7411662936210632,
      "learning_rate": 9.6e-05,
      "loss": 0.281,
      "step": 24
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 0.5641128420829773,
      "learning_rate": 9.999512620046522e-05,
      "loss": 0.217,
      "step": 26
    },
    {
      "epoch": 4.909090909090909,
      "eval_loss": 0.2956204116344452,
      "eval_runtime": 25.913,
      "eval_samples_per_second": 0.926,
      "eval_steps_per_second": 0.926,
      "step": 27
    },
    {
      "epoch": 5.090909090909091,
      "grad_norm": 0.7421686053276062,
      "learning_rate": 9.995614150494293e-05,
      "loss": 0.2473,
      "step": 28
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.6080622673034668,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.1727,
      "step": 30
    },
    {
      "epoch": 5.818181818181818,
      "grad_norm": 0.6304150819778442,
      "learning_rate": 9.976136999909156e-05,
      "loss": 0.1679,
      "step": 32
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.2812866270542145,
      "eval_runtime": 25.8858,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 33
    },
    {
      "epoch": 6.181818181818182,
      "grad_norm": 0.38126808404922485,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.1586,
      "step": 34
    },
    {
      "epoch": 6.545454545454545,
      "grad_norm": 0.6826176047325134,
      "learning_rate": 9.941141907232765e-05,
      "loss": 0.166,
      "step": 36
    },
    {
      "epoch": 6.909090909090909,
      "grad_norm": 0.668012261390686,
      "learning_rate": 9.917857354066931e-05,
      "loss": 0.1291,
      "step": 38
    },
    {
      "epoch": 6.909090909090909,
      "eval_loss": 0.31331560015678406,
      "eval_runtime": 25.8869,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 38
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 0.6984208226203918,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.094,
      "step": 40
    },
    {
      "epoch": 7.636363636363637,
      "grad_norm": 0.5483599901199341,
      "learning_rate": 9.859805002892732e-05,
      "loss": 0.0448,
      "step": 42
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.8013001084327698,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.0786,
      "step": 44
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.36205387115478516,
      "eval_runtime": 25.8913,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 44
    },
    {
      "epoch": 8.363636363636363,
      "grad_norm": 0.4033701419830322,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.0353,
      "step": 46
    },
    {
      "epoch": 8.727272727272727,
      "grad_norm": 0.49503079056739807,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.0336,
      "step": 48
    },
    {
      "epoch": 8.909090909090908,
      "eval_loss": 0.4238704741001129,
      "eval_runtime": 25.886,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 49
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 0.5322268605232239,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0393,
      "step": 50
    },
    {
      "epoch": 9.454545454545455,
      "grad_norm": 1.168056845664978,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.0213,
      "step": 52
    },
    {
      "epoch": 9.818181818181818,
      "grad_norm": 0.6037251949310303,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.0221,
      "step": 54
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.4523530900478363,
      "eval_runtime": 25.8868,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 55
    },
    {
      "epoch": 10.181818181818182,
      "grad_norm": 0.3419169485569,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.0126,
      "step": 56
    },
    {
      "epoch": 10.545454545454545,
      "grad_norm": 0.3459678888320923,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.0132,
      "step": 58
    },
    {
      "epoch": 10.909090909090908,
      "grad_norm": 0.19827347993850708,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0153,
      "step": 60
    },
    {
      "epoch": 10.909090909090908,
      "eval_loss": 0.46732887625694275,
      "eval_runtime": 25.8827,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 60
    },
    {
      "epoch": 11.272727272727273,
      "grad_norm": 0.7306903600692749,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.0099,
      "step": 62
    },
    {
      "epoch": 11.636363636363637,
      "grad_norm": 0.4022263288497925,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.008,
      "step": 64
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.450735479593277,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.0094,
      "step": 66
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.4911034405231476,
      "eval_runtime": 25.884,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 66
    },
    {
      "epoch": 12.363636363636363,
      "grad_norm": 0.3320798873901367,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.0026,
      "step": 68
    },
    {
      "epoch": 12.727272727272727,
      "grad_norm": 0.3709675669670105,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0063,
      "step": 70
    },
    {
      "epoch": 12.909090909090908,
      "eval_loss": 0.5208281874656677,
      "eval_runtime": 25.8856,
      "eval_samples_per_second": 0.927,
      "eval_steps_per_second": 0.927,
      "step": 71
    },
    {
      "epoch": 12.909090909090908,
      "step": 71,
      "total_flos": 1.120265252676567e+17,
      "train_loss": 0.5012591263528546,
      "train_runtime": 4162.2804,
      "train_samples_per_second": 1.057,
      "train_steps_per_second": 0.06
    }
  ],
  "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": 1.120265252676567e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}