{
  "best_metric": 0.31598106026649475,
  "best_model_checkpoint": "./opt_trained/checkpoint-43",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 43,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 1.4262398481369019,
      "learning_rate": 9.995238095238095e-05,
      "loss": 2.4722,
      "step": 1
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 12.206507682800293,
      "learning_rate": 9.990476190476191e-05,
      "loss": 3.176,
      "step": 2
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 11.578840255737305,
      "learning_rate": 9.985714285714287e-05,
      "loss": 2.8396,
      "step": 3
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 9.648161888122559,
      "learning_rate": 9.980952380952382e-05,
      "loss": 2.7336,
      "step": 4
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 3.8782691955566406,
      "learning_rate": 9.976190476190477e-05,
      "loss": 2.6955,
      "step": 5
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 12.644487380981445,
      "learning_rate": 9.971428571428571e-05,
      "loss": 2.6405,
      "step": 6
    },
    {
      "epoch": 0.16374269005847952,
      "grad_norm": 11.057122230529785,
      "learning_rate": 9.966666666666667e-05,
      "loss": 2.7113,
      "step": 7
    },
    {
      "epoch": 0.1871345029239766,
      "grad_norm": 4.860190391540527,
      "learning_rate": 9.961904761904762e-05,
      "loss": 2.7076,
      "step": 8
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 4.317215442657471,
      "learning_rate": 9.957142857142858e-05,
      "loss": 2.6377,
      "step": 9
    },
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 3.3068416118621826,
      "learning_rate": 9.952380952380953e-05,
      "loss": 2.5995,
      "step": 10
    },
    {
      "epoch": 0.2573099415204678,
      "grad_norm": 1.2752724885940552,
      "learning_rate": 9.947619047619048e-05,
      "loss": 2.6285,
      "step": 11
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 8.849737167358398,
      "learning_rate": 9.942857142857144e-05,
      "loss": 2.6217,
      "step": 12
    },
    {
      "epoch": 0.30409356725146197,
      "grad_norm": 5.594025611877441,
      "learning_rate": 9.938095238095238e-05,
      "loss": 2.6265,
      "step": 13
    },
    {
      "epoch": 0.32748538011695905,
      "grad_norm": 3.581617593765259,
      "learning_rate": 9.933333333333334e-05,
      "loss": 2.5984,
      "step": 14
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 5.33600378036499,
      "learning_rate": 9.92857142857143e-05,
      "loss": 2.6071,
      "step": 15
    },
    {
      "epoch": 0.3742690058479532,
      "grad_norm": 4.4274983406066895,
      "learning_rate": 9.923809523809524e-05,
      "loss": 2.5908,
      "step": 16
    },
    {
      "epoch": 0.39766081871345027,
      "grad_norm": 4.5507307052612305,
      "learning_rate": 9.91904761904762e-05,
      "loss": 2.5616,
      "step": 17
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 3.189161777496338,
      "learning_rate": 9.914285714285715e-05,
      "loss": 2.5784,
      "step": 18
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.706615924835205,
      "learning_rate": 9.909523809523809e-05,
      "loss": 2.5413,
      "step": 19
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 2.146662712097168,
      "learning_rate": 9.904761904761905e-05,
      "loss": 2.6019,
      "step": 20
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 3.2252964973449707,
      "learning_rate": 9.900000000000001e-05,
      "loss": 2.5914,
      "step": 21
    },
    {
      "epoch": 0.5146198830409356,
      "grad_norm": 2.8859879970550537,
      "learning_rate": 9.895238095238095e-05,
      "loss": 2.6133,
      "step": 22
    },
    {
      "epoch": 0.5380116959064327,
      "grad_norm": 2.5647897720336914,
      "learning_rate": 9.890476190476191e-05,
      "loss": 2.5425,
      "step": 23
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 3.0347073078155518,
      "learning_rate": 9.885714285714286e-05,
      "loss": 2.5732,
      "step": 24
    },
    {
      "epoch": 0.5847953216374269,
      "grad_norm": 1.8412858247756958,
      "learning_rate": 9.880952380952381e-05,
      "loss": 2.5776,
      "step": 25
    },
    {
      "epoch": 0.6081871345029239,
      "grad_norm": 3.1820366382598877,
      "learning_rate": 9.876190476190477e-05,
      "loss": 2.5566,
      "step": 26
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 2.4613687992095947,
      "learning_rate": 9.871428571428572e-05,
      "loss": 2.5113,
      "step": 27
    },
    {
      "epoch": 0.6549707602339181,
      "grad_norm": 5.942374229431152,
      "learning_rate": 9.866666666666668e-05,
      "loss": 2.575,
      "step": 28
    },
    {
      "epoch": 0.6783625730994152,
      "grad_norm": 7.427689075469971,
      "learning_rate": 9.861904761904762e-05,
      "loss": 2.5692,
      "step": 29
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 3.163085699081421,
      "learning_rate": 9.857142857142858e-05,
      "loss": 2.5192,
      "step": 30
    },
    {
      "epoch": 0.7251461988304093,
      "grad_norm": 3.421778678894043,
      "learning_rate": 9.852380952380952e-05,
      "loss": 2.5533,
      "step": 31
    },
    {
      "epoch": 0.7485380116959064,
      "grad_norm": 2.486320734024048,
      "learning_rate": 9.847619047619048e-05,
      "loss": 2.515,
      "step": 32
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 3.2825722694396973,
      "learning_rate": 9.842857142857144e-05,
      "loss": 2.4994,
      "step": 33
    },
    {
      "epoch": 0.7953216374269005,
      "grad_norm": 3.5643672943115234,
      "learning_rate": 9.838095238095238e-05,
      "loss": 2.5327,
      "step": 34
    },
    {
      "epoch": 0.8187134502923976,
      "grad_norm": 3.3127200603485107,
      "learning_rate": 9.833333333333333e-05,
      "loss": 2.6251,
      "step": 35
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 3.187095880508423,
      "learning_rate": 9.828571428571429e-05,
      "loss": 2.5233,
      "step": 36
    },
    {
      "epoch": 0.8654970760233918,
      "grad_norm": 3.3743860721588135,
      "learning_rate": 9.823809523809525e-05,
      "loss": 2.4999,
      "step": 37
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.3684120178222656,
      "learning_rate": 9.81904761904762e-05,
      "loss": 2.5302,
      "step": 38
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 3.7091619968414307,
      "learning_rate": 9.814285714285715e-05,
      "loss": 2.5003,
      "step": 39
    },
    {
      "epoch": 0.935672514619883,
      "grad_norm": 4.230418682098389,
      "learning_rate": 9.80952380952381e-05,
      "loss": 2.5379,
      "step": 40
    },
    {
      "epoch": 0.9590643274853801,
      "grad_norm": 3.5879616737365723,
      "learning_rate": 9.804761904761905e-05,
      "loss": 2.5652,
      "step": 41
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 2.621013879776001,
      "learning_rate": 9.8e-05,
      "loss": 2.5704,
      "step": 42
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.3536667823791504,
      "learning_rate": 9.795238095238097e-05,
      "loss": 1.9135,
      "step": 43
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.31598106026649475,
      "eval_runtime": 3.4639,
      "eval_samples_per_second": 62.358,
      "eval_steps_per_second": 15.59,
      "step": 43
    }
  ],
  "logging_steps": 1,
  "max_steps": 2100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2151327228493824.0,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}