{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9904761904761905,
  "eval_steps": 500,
  "global_step": 195,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 0.25375691056251526,
      "learning_rate": 4.9918932703355256e-05,
      "loss": 0.2783,
      "num_input_tokens_seen": 211280,
      "step": 5
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 0.1986791342496872,
      "learning_rate": 4.967625656594782e-05,
      "loss": 0.1989,
      "num_input_tokens_seen": 419136,
      "step": 10
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.1764397770166397,
      "learning_rate": 4.92735454356513e-05,
      "loss": 0.1331,
      "num_input_tokens_seen": 631632,
      "step": 15
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 0.14602281153202057,
      "learning_rate": 4.8713411048678635e-05,
      "loss": 0.1029,
      "num_input_tokens_seen": 836896,
      "step": 20
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.14543306827545166,
      "learning_rate": 4.799948609147061e-05,
      "loss": 0.08,
      "num_input_tokens_seen": 1042416,
      "step": 25
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.14905446767807007,
      "learning_rate": 4.713640064133025e-05,
      "loss": 0.0767,
      "num_input_tokens_seen": 1244384,
      "step": 30
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.12417428195476532,
      "learning_rate": 4.6129752138594874e-05,
      "loss": 0.0596,
      "num_input_tokens_seen": 1445168,
      "step": 35
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 0.1181894913315773,
      "learning_rate": 4.498606908508754e-05,
      "loss": 0.0619,
      "num_input_tokens_seen": 1651760,
      "step": 40
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.13109543919563293,
      "learning_rate": 4.371276870427753e-05,
      "loss": 0.0585,
      "num_input_tokens_seen": 1849920,
      "step": 45
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.1899598389863968,
      "learning_rate": 4.231810883773999e-05,
      "loss": 0.0642,
      "num_input_tokens_seen": 2056592,
      "step": 50
    },
    {
      "epoch": 0.8380952380952381,
      "grad_norm": 0.11073227226734161,
      "learning_rate": 4.0811134389884433e-05,
      "loss": 0.053,
      "num_input_tokens_seen": 2265056,
      "step": 55
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.11537300050258636,
      "learning_rate": 3.920161866827889e-05,
      "loss": 0.0566,
      "num_input_tokens_seen": 2471328,
      "step": 60
    },
    {
      "epoch": 0.9904761904761905,
      "grad_norm": 0.1397155374288559,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.0496,
      "num_input_tokens_seen": 2676640,
      "step": 65
    },
    {
      "epoch": 1.0761904761904761,
      "grad_norm": 0.1408267617225647,
      "learning_rate": 3.5717314035076355e-05,
      "loss": 0.0577,
      "num_input_tokens_seen": 2897712,
      "step": 70
    },
    {
      "epoch": 1.1523809523809523,
      "grad_norm": 0.11563374847173691,
      "learning_rate": 3.386512217606339e-05,
      "loss": 0.0442,
      "num_input_tokens_seen": 3089808,
      "step": 75
    },
    {
      "epoch": 1.2285714285714286,
      "grad_norm": 0.1368333101272583,
      "learning_rate": 3.195543659791132e-05,
      "loss": 0.0469,
      "num_input_tokens_seen": 3296576,
      "step": 80
    },
    {
      "epoch": 1.3047619047619048,
      "grad_norm": 0.11226939409971237,
      "learning_rate": 3.0000642344401113e-05,
      "loss": 0.0417,
      "num_input_tokens_seen": 3508416,
      "step": 85
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.12701162695884705,
      "learning_rate": 2.8013417006383076e-05,
      "loss": 0.0451,
      "num_input_tokens_seen": 3706512,
      "step": 90
    },
    {
      "epoch": 1.457142857142857,
      "grad_norm": 0.11398270726203918,
      "learning_rate": 2.600664850273538e-05,
      "loss": 0.0438,
      "num_input_tokens_seen": 3913120,
      "step": 95
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 0.15226365625858307,
      "learning_rate": 2.399335149726463e-05,
      "loss": 0.038,
      "num_input_tokens_seen": 4121248,
      "step": 100
    },
    {
      "epoch": 1.6095238095238096,
      "grad_norm": 0.12406383454799652,
      "learning_rate": 2.1986582993616926e-05,
      "loss": 0.038,
      "num_input_tokens_seen": 4327824,
      "step": 105
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.11916245520114899,
      "learning_rate": 1.9999357655598893e-05,
      "loss": 0.0397,
      "num_input_tokens_seen": 4537936,
      "step": 110
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.14286760985851288,
      "learning_rate": 1.8044563402088684e-05,
      "loss": 0.0404,
      "num_input_tokens_seen": 4744432,
      "step": 115
    },
    {
      "epoch": 1.8380952380952382,
      "grad_norm": 0.09759990125894547,
      "learning_rate": 1.613487782393661e-05,
      "loss": 0.0362,
      "num_input_tokens_seen": 4955296,
      "step": 120
    },
    {
      "epoch": 1.9142857142857141,
      "grad_norm": 0.13581913709640503,
      "learning_rate": 1.4282685964923642e-05,
      "loss": 0.0397,
      "num_input_tokens_seen": 5154784,
      "step": 125
    },
    {
      "epoch": 1.9904761904761905,
      "grad_norm": 0.12309057265520096,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.0343,
      "num_input_tokens_seen": 5358160,
      "step": 130
    },
    {
      "epoch": 2.0761904761904764,
      "grad_norm": 0.11022833734750748,
      "learning_rate": 1.0798381331721109e-05,
      "loss": 0.0396,
      "num_input_tokens_seen": 5577808,
      "step": 135
    },
    {
      "epoch": 2.1523809523809523,
      "grad_norm": 0.10238117724657059,
      "learning_rate": 9.18886561011557e-06,
      "loss": 0.0394,
      "num_input_tokens_seen": 5775552,
      "step": 140
    },
    {
      "epoch": 2.2285714285714286,
      "grad_norm": 0.09375017136335373,
      "learning_rate": 7.681891162260015e-06,
      "loss": 0.0311,
      "num_input_tokens_seen": 5986112,
      "step": 145
    },
    {
      "epoch": 2.3047619047619046,
      "grad_norm": 0.13229627907276154,
      "learning_rate": 6.28723129572247e-06,
      "loss": 0.048,
      "num_input_tokens_seen": 6185568,
      "step": 150
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.1364370435476303,
      "learning_rate": 5.013930914912476e-06,
      "loss": 0.0374,
      "num_input_tokens_seen": 6389392,
      "step": 155
    },
    {
      "epoch": 2.4571428571428573,
      "grad_norm": 0.11261958628892899,
      "learning_rate": 3.8702478614051355e-06,
      "loss": 0.0334,
      "num_input_tokens_seen": 6594256,
      "step": 160
    },
    {
      "epoch": 2.533333333333333,
      "grad_norm": 0.09721696376800537,
      "learning_rate": 2.8635993586697553e-06,
      "loss": 0.0324,
      "num_input_tokens_seen": 6802240,
      "step": 165
    },
    {
      "epoch": 2.6095238095238096,
      "grad_norm": 0.11983498930931091,
      "learning_rate": 2.0005139085293945e-06,
      "loss": 0.0342,
      "num_input_tokens_seen": 7004816,
      "step": 170
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 0.13199082016944885,
      "learning_rate": 1.286588951321363e-06,
      "loss": 0.0384,
      "num_input_tokens_seen": 7208608,
      "step": 175
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.10022356361150742,
      "learning_rate": 7.264545643486997e-07,
      "loss": 0.0357,
      "num_input_tokens_seen": 7418320,
      "step": 180
    },
    {
      "epoch": 2.8380952380952382,
      "grad_norm": 0.11056291311979294,
      "learning_rate": 3.237434340521789e-07,
      "loss": 0.0351,
      "num_input_tokens_seen": 7633248,
      "step": 185
    },
    {
      "epoch": 2.914285714285714,
      "grad_norm": 0.12205488979816437,
      "learning_rate": 8.106729664475176e-08,
      "loss": 0.0324,
      "num_input_tokens_seen": 7838576,
      "step": 190
    },
    {
      "epoch": 2.9904761904761905,
      "grad_norm": 0.10819905996322632,
      "learning_rate": 0.0,
      "loss": 0.0357,
      "num_input_tokens_seen": 8039616,
      "step": 195
    },
    {
      "epoch": 2.9904761904761905,
      "num_input_tokens_seen": 8039616,
      "step": 195,
      "total_flos": 3.746411207808123e+17,
      "train_loss": 0.05875852833955716,
      "train_runtime": 3746.4527,
      "train_samples_per_second": 0.841,
      "train_steps_per_second": 0.052
    }
  ],
  "logging_steps": 5,
  "max_steps": 195,
  "num_input_tokens_seen": 8039616,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.746411207808123e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}