{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 42,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.5142271518707275,
      "learning_rate": 1e-05,
      "loss": 1.3115234375,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.43172329664230347,
      "learning_rate": 9.986018985905901e-06,
      "loss": 1.11279296875,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.5781334638595581,
      "learning_rate": 9.944154131125643e-06,
      "loss": 1.3701171875,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.5276030898094177,
      "learning_rate": 9.874639560909118e-06,
      "loss": 1.2041015625,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.3694753050804138,
      "learning_rate": 9.777864028930705e-06,
      "loss": 0.8466796875,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.45660197734832764,
      "learning_rate": 9.654368743221022e-06,
      "loss": 0.87744140625,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.4934976100921631,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.91943359375,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.33858343958854675,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.83984375,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.42119961977005005,
      "learning_rate": 9.131193871579975e-06,
      "loss": 0.8779296875,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.30643510818481445,
      "learning_rate": 8.90915741234015e-06,
      "loss": 0.69775390625,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.3659510016441345,
      "learning_rate": 8.665259359149132e-06,
      "loss": 0.701171875,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.30956700444221497,
      "learning_rate": 8.400863688854598e-06,
      "loss": 0.7119140625,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.3042762279510498,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.69775390625,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.21307909488677979,
      "learning_rate": 7.81660029031811e-06,
      "loss": 0.60009765625,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.24255751073360443,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.619140625,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.19554612040519714,
      "learning_rate": 7.169418695587791e-06,
      "loss": 0.56884765625,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.22255103290081024,
      "learning_rate": 6.8267051218319766e-06,
      "loss": 0.56640625,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.2525923550128937,
      "learning_rate": 6.473775872054522e-06,
      "loss": 0.588623046875,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.23009464144706726,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.55078125,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.16877399384975433,
      "learning_rate": 5.745211330880872e-06,
      "loss": 0.494384765625,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.20204387605190277,
      "learning_rate": 5.373650467932122e-06,
      "loss": 0.51171875,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.1933034509420395,
      "learning_rate": 5e-06,
      "loss": 0.49267578125,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.14990267157554626,
      "learning_rate": 4.626349532067879e-06,
      "loss": 0.443115234375,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.17792868614196777,
      "learning_rate": 4.254788669119127e-06,
      "loss": 0.477783203125,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.15274128317832947,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.466796875,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.10674764215946198,
      "learning_rate": 3.526224127945479e-06,
      "loss": 0.405517578125,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.11595381796360016,
      "learning_rate": 3.173294878168025e-06,
      "loss": 0.42578125,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.12971355020999908,
      "learning_rate": 2.83058130441221e-06,
      "loss": 0.4383544921875,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.12511298060417175,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.4404296875,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.1366412192583084,
      "learning_rate": 2.1833997096818897e-06,
      "loss": 0.44384765625,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.10178292542695999,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.4154052734375,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.11457493156194687,
      "learning_rate": 1.5991363111454023e-06,
      "loss": 0.399658203125,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.11893026530742645,
      "learning_rate": 1.3347406408508695e-06,
      "loss": 0.4320068359375,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.128859743475914,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 0.4263916015625,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.10783348977565765,
      "learning_rate": 8.688061284200266e-07,
      "loss": 0.4080810546875,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.12428561598062515,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.415283203125,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.10516267269849777,
      "learning_rate": 4.951556604879049e-07,
      "loss": 0.4168701171875,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.11817852407693863,
      "learning_rate": 3.4563125677897936e-07,
      "loss": 0.41162109375,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.13531376421451569,
      "learning_rate": 2.2213597106929608e-07,
      "loss": 0.432373046875,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.12316219508647919,
      "learning_rate": 1.253604390908819e-07,
      "loss": 0.422119140625,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.09918029606342316,
      "learning_rate": 5.584586887435739e-08,
      "loss": 0.4091796875,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.12201837450265884,
      "learning_rate": 1.3981014094099354e-08,
      "loss": 0.42333984375,
      "step": 42
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.3968505859375,
      "eval_runtime": 5.1716,
      "eval_samples_per_second": 0.967,
      "eval_steps_per_second": 0.193,
      "step": 42
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.330465319638794e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}