{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21691973969631237,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004338394793926247,
      "grad_norm": 0.9592865705490112,
      "learning_rate": 1e-05,
      "loss": 4.282,
      "step": 1
    },
    {
      "epoch": 0.004338394793926247,
      "eval_loss": 4.6311469078063965,
      "eval_runtime": 47.1625,
      "eval_samples_per_second": 8.248,
      "eval_steps_per_second": 4.135,
      "step": 1
    },
    {
      "epoch": 0.008676789587852495,
      "grad_norm": 0.8076575994491577,
      "learning_rate": 2e-05,
      "loss": 4.1393,
      "step": 2
    },
    {
      "epoch": 0.013015184381778741,
      "grad_norm": 0.7931267619132996,
      "learning_rate": 3e-05,
      "loss": 4.0148,
      "step": 3
    },
    {
      "epoch": 0.01735357917570499,
      "grad_norm": 0.8286021947860718,
      "learning_rate": 4e-05,
      "loss": 4.0935,
      "step": 4
    },
    {
      "epoch": 0.021691973969631236,
      "grad_norm": 0.8951513767242432,
      "learning_rate": 5e-05,
      "loss": 4.1972,
      "step": 5
    },
    {
      "epoch": 0.026030368763557483,
      "grad_norm": 1.0082049369812012,
      "learning_rate": 6e-05,
      "loss": 4.4165,
      "step": 6
    },
    {
      "epoch": 0.03036876355748373,
      "grad_norm": 0.8596186637878418,
      "learning_rate": 7e-05,
      "loss": 4.0273,
      "step": 7
    },
    {
      "epoch": 0.03470715835140998,
      "grad_norm": 0.7011109590530396,
      "learning_rate": 8e-05,
      "loss": 3.7726,
      "step": 8
    },
    {
      "epoch": 0.039045553145336226,
      "grad_norm": 0.9478129148483276,
      "learning_rate": 9e-05,
      "loss": 4.0187,
      "step": 9
    },
    {
      "epoch": 0.04338394793926247,
      "grad_norm": 0.9030329585075378,
      "learning_rate": 0.0001,
      "loss": 3.8042,
      "step": 10
    },
    {
      "epoch": 0.04772234273318872,
      "grad_norm": 1.1288987398147583,
      "learning_rate": 9.98458666866564e-05,
      "loss": 3.8743,
      "step": 11
    },
    {
      "epoch": 0.052060737527114966,
      "grad_norm": 0.8573070764541626,
      "learning_rate": 9.938441702975689e-05,
      "loss": 3.4308,
      "step": 12
    },
    {
      "epoch": 0.05639913232104121,
      "grad_norm": 0.9345530867576599,
      "learning_rate": 9.861849601988383e-05,
      "loss": 3.76,
      "step": 13
    },
    {
      "epoch": 0.05639913232104121,
      "eval_loss": 3.9019081592559814,
      "eval_runtime": 29.6147,
      "eval_samples_per_second": 13.135,
      "eval_steps_per_second": 6.585,
      "step": 13
    },
    {
      "epoch": 0.06073752711496746,
      "grad_norm": 0.8706801533699036,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.874,
      "step": 14
    },
    {
      "epoch": 0.0650759219088937,
      "grad_norm": 0.8751348257064819,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.7313,
      "step": 15
    },
    {
      "epoch": 0.06941431670281996,
      "grad_norm": 0.958247721195221,
      "learning_rate": 9.45503262094184e-05,
      "loss": 3.5899,
      "step": 16
    },
    {
      "epoch": 0.0737527114967462,
      "grad_norm": 0.9930692315101624,
      "learning_rate": 9.263200821770461e-05,
      "loss": 3.5972,
      "step": 17
    },
    {
      "epoch": 0.07809110629067245,
      "grad_norm": 0.8314181566238403,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.6647,
      "step": 18
    },
    {
      "epoch": 0.0824295010845987,
      "grad_norm": 1.0243431329727173,
      "learning_rate": 8.802029828000156e-05,
      "loss": 3.613,
      "step": 19
    },
    {
      "epoch": 0.08676789587852494,
      "grad_norm": 0.7895156741142273,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.477,
      "step": 20
    },
    {
      "epoch": 0.0911062906724512,
      "grad_norm": 0.9564393758773804,
      "learning_rate": 8.247240241650918e-05,
      "loss": 3.4972,
      "step": 21
    },
    {
      "epoch": 0.09544468546637744,
      "grad_norm": 0.9817779660224915,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.72,
      "step": 22
    },
    {
      "epoch": 0.09978308026030369,
      "grad_norm": 0.9549041390419006,
      "learning_rate": 7.612492823579745e-05,
      "loss": 3.4953,
      "step": 23
    },
    {
      "epoch": 0.10412147505422993,
      "grad_norm": 0.8034272193908691,
      "learning_rate": 7.269952498697734e-05,
      "loss": 3.6123,
      "step": 24
    },
    {
      "epoch": 0.10845986984815618,
      "grad_norm": 0.9502893090248108,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.7805,
      "step": 25
    },
    {
      "epoch": 0.11279826464208242,
      "grad_norm": 0.8888735771179199,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.5974,
      "step": 26
    },
    {
      "epoch": 0.11279826464208242,
      "eval_loss": 3.667881488800049,
      "eval_runtime": 29.639,
      "eval_samples_per_second": 13.125,
      "eval_steps_per_second": 6.579,
      "step": 26
    },
    {
      "epoch": 0.11713665943600868,
      "grad_norm": 0.9501574039459229,
      "learning_rate": 6.167226819279528e-05,
      "loss": 3.5286,
      "step": 27
    },
    {
      "epoch": 0.12147505422993492,
      "grad_norm": 0.979643702507019,
      "learning_rate": 5.782172325201155e-05,
      "loss": 3.6129,
      "step": 28
    },
    {
      "epoch": 0.12581344902386118,
      "grad_norm": 0.8400367498397827,
      "learning_rate": 5.392295478639225e-05,
      "loss": 3.6122,
      "step": 29
    },
    {
      "epoch": 0.1301518438177874,
      "grad_norm": 0.9588121771812439,
      "learning_rate": 5e-05,
      "loss": 3.3589,
      "step": 30
    },
    {
      "epoch": 0.13449023861171366,
      "grad_norm": 0.9330855011940002,
      "learning_rate": 4.607704521360776e-05,
      "loss": 3.5589,
      "step": 31
    },
    {
      "epoch": 0.13882863340563992,
      "grad_norm": 0.9061364531517029,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 3.4334,
      "step": 32
    },
    {
      "epoch": 0.14316702819956617,
      "grad_norm": 0.8837863206863403,
      "learning_rate": 3.832773180720475e-05,
      "loss": 3.564,
      "step": 33
    },
    {
      "epoch": 0.1475054229934924,
      "grad_norm": 0.9357448220252991,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.3525,
      "step": 34
    },
    {
      "epoch": 0.15184381778741865,
      "grad_norm": 0.8831885457038879,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.5098,
      "step": 35
    },
    {
      "epoch": 0.1561822125813449,
      "grad_norm": 0.8763655424118042,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 3.5621,
      "step": 36
    },
    {
      "epoch": 0.16052060737527116,
      "grad_norm": 0.9227960109710693,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 3.5769,
      "step": 37
    },
    {
      "epoch": 0.1648590021691974,
      "grad_norm": 0.6684260964393616,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.7166,
      "step": 38
    },
    {
      "epoch": 0.16919739696312364,
      "grad_norm": 1.0996284484863281,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 3.5902,
      "step": 39
    },
    {
      "epoch": 0.16919739696312364,
      "eval_loss": 3.601860523223877,
      "eval_runtime": 29.6178,
      "eval_samples_per_second": 13.134,
      "eval_steps_per_second": 6.584,
      "step": 39
    },
    {
      "epoch": 0.1735357917570499,
      "grad_norm": 0.8120056390762329,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.101,
      "step": 40
    },
    {
      "epoch": 0.17787418655097614,
      "grad_norm": 1.084051251411438,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 3.5951,
      "step": 41
    },
    {
      "epoch": 0.1822125813449024,
      "grad_norm": 0.8113239407539368,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.2588,
      "step": 42
    },
    {
      "epoch": 0.18655097613882862,
      "grad_norm": 0.8805438280105591,
      "learning_rate": 7.367991782295391e-06,
      "loss": 3.4257,
      "step": 43
    },
    {
      "epoch": 0.19088937093275488,
      "grad_norm": 0.9256657958030701,
      "learning_rate": 5.449673790581611e-06,
      "loss": 3.4759,
      "step": 44
    },
    {
      "epoch": 0.19522776572668113,
      "grad_norm": 0.9354608058929443,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.5507,
      "step": 45
    },
    {
      "epoch": 0.19956616052060738,
      "grad_norm": 0.8996797204017639,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 3.2725,
      "step": 46
    },
    {
      "epoch": 0.2039045553145336,
      "grad_norm": 0.9552720189094543,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 3.4802,
      "step": 47
    },
    {
      "epoch": 0.20824295010845986,
      "grad_norm": 0.9154345393180847,
      "learning_rate": 6.15582970243117e-07,
      "loss": 3.6361,
      "step": 48
    },
    {
      "epoch": 0.21258134490238612,
      "grad_norm": 0.7522619962692261,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 3.4707,
      "step": 49
    },
    {
      "epoch": 0.21691973969631237,
      "grad_norm": 0.7439150214195251,
      "learning_rate": 0.0,
      "loss": 3.2768,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.117937171693568e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}