{
  "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": 9.599616050720215,
      "learning_rate": 1e-05,
      "loss": 6.80078125,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 7.92846155166626,
      "learning_rate": 9.986018985905901e-06,
      "loss": 6.84375,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 6.05684232711792,
      "learning_rate": 9.944154131125643e-06,
      "loss": 6.1484375,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 6.677191257476807,
      "learning_rate": 9.874639560909118e-06,
      "loss": 6.16015625,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 5.712176322937012,
      "learning_rate": 9.777864028930705e-06,
      "loss": 5.44140625,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 5.569811820983887,
      "learning_rate": 9.654368743221022e-06,
      "loss": 5.19921875,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 6.5552449226379395,
      "learning_rate": 9.504844339512096e-06,
      "loss": 5.13671875,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 5.020793914794922,
      "learning_rate": 9.330127018922195e-06,
      "loss": 4.375,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 5.119137287139893,
      "learning_rate": 9.131193871579975e-06,
      "loss": 3.998046875,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 4.953500747680664,
      "learning_rate": 8.90915741234015e-06,
      "loss": 3.822265625,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 4.168428421020508,
      "learning_rate": 8.665259359149132e-06,
      "loss": 3.51171875,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 3.239715576171875,
      "learning_rate": 8.400863688854598e-06,
      "loss": 3.283203125,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 2.55800199508667,
      "learning_rate": 8.117449009293668e-06,
      "loss": 3.1953125,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.0577316284179688,
      "learning_rate": 7.81660029031811e-06,
      "loss": 3.015625,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 2.1846179962158203,
      "learning_rate": 7.500000000000001e-06,
      "loss": 2.970703125,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 2.22184681892395,
      "learning_rate": 7.169418695587791e-06,
      "loss": 2.958984375,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 2.0178980827331543,
      "learning_rate": 6.8267051218319766e-06,
      "loss": 2.837890625,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.9504748582839966,
      "learning_rate": 6.473775872054522e-06,
      "loss": 2.8232421875,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 1.5024254322052002,
      "learning_rate": 6.112604669781572e-06,
      "loss": 2.71484375,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.9985494613647461,
      "learning_rate": 5.745211330880872e-06,
      "loss": 2.5693359375,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1964644193649292,
      "learning_rate": 5.373650467932122e-06,
      "loss": 2.57421875,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.9260289072990417,
      "learning_rate": 5e-06,
      "loss": 2.5615234375,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.8866318464279175,
      "learning_rate": 4.626349532067879e-06,
      "loss": 2.5771484375,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.7876430153846741,
      "learning_rate": 4.254788669119127e-06,
      "loss": 2.5751953125,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.7711585164070129,
      "learning_rate": 3.887395330218429e-06,
      "loss": 2.515625,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.6984349489212036,
      "learning_rate": 3.526224127945479e-06,
      "loss": 2.4931640625,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.6593084931373596,
      "learning_rate": 3.173294878168025e-06,
      "loss": 2.48046875,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.6935004591941833,
      "learning_rate": 2.83058130441221e-06,
      "loss": 2.44921875,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.5799071788787842,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 2.474609375,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.5451619029045105,
      "learning_rate": 2.1833997096818897e-06,
      "loss": 2.353515625,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.5938615798950195,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 2.43359375,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.5384805798530579,
      "learning_rate": 1.5991363111454023e-06,
      "loss": 2.3935546875,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.5119157433509827,
      "learning_rate": 1.3347406408508695e-06,
      "loss": 2.3857421875,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.5446591377258301,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 2.4072265625,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.47655045986175537,
      "learning_rate": 8.688061284200266e-07,
      "loss": 2.3916015625,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.4848061800003052,
      "learning_rate": 6.698729810778065e-07,
      "loss": 2.376953125,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.5174354910850525,
      "learning_rate": 4.951556604879049e-07,
      "loss": 2.4248046875,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.5028664469718933,
      "learning_rate": 3.4563125677897936e-07,
      "loss": 2.384765625,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.5503596067428589,
      "learning_rate": 2.2213597106929608e-07,
      "loss": 2.38671875,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.5344513654708862,
      "learning_rate": 1.253604390908819e-07,
      "loss": 2.3603515625,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.4360624849796295,
      "learning_rate": 5.584586887435739e-08,
      "loss": 2.3193359375,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6491678357124329,
      "learning_rate": 1.3981014094099354e-08,
      "loss": 2.27978515625,
      "step": 42
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.36328125,
      "eval_runtime": 0.5089,
      "eval_samples_per_second": 3.93,
      "eval_steps_per_second": 1.965,
      "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": 3.2096305635393536e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}