{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0354735721887194,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000709471443774388,
      "grad_norm": 265.86757613893764,
      "learning_rate": 0.0,
      "loss": 2.1209,
      "step": 1
    },
    {
      "epoch": 0.001418942887548776,
      "grad_norm": 256.9364781809131,
      "learning_rate": 2.1276595744680852e-07,
      "loss": 1.9508,
      "step": 2
    },
    {
      "epoch": 0.002128414331323164,
      "grad_norm": 261.72185657120684,
      "learning_rate": 4.2553191489361704e-07,
      "loss": 2.1995,
      "step": 3
    },
    {
      "epoch": 0.002837885775097552,
      "grad_norm": 261.0961921742672,
      "learning_rate": 6.382978723404255e-07,
      "loss": 2.0081,
      "step": 4
    },
    {
      "epoch": 0.0035473572188719402,
      "grad_norm": 255.1019965019492,
      "learning_rate": 8.510638297872341e-07,
      "loss": 2.0828,
      "step": 5
    },
    {
      "epoch": 0.004256828662646328,
      "grad_norm": 201.9040896756704,
      "learning_rate": 1.0638297872340427e-06,
      "loss": 1.6403,
      "step": 6
    },
    {
      "epoch": 0.004966300106420717,
      "grad_norm": 198.32057240838185,
      "learning_rate": 1.276595744680851e-06,
      "loss": 1.6037,
      "step": 7
    },
    {
      "epoch": 0.005675771550195104,
      "grad_norm": 91.64675018232528,
      "learning_rate": 1.4893617021276596e-06,
      "loss": 1.0155,
      "step": 8
    },
    {
      "epoch": 0.006385242993969493,
      "grad_norm": 71.73605818031255,
      "learning_rate": 1.7021276595744682e-06,
      "loss": 0.8153,
      "step": 9
    },
    {
      "epoch": 0.0070947144377438804,
      "grad_norm": 24.941283646351614,
      "learning_rate": 1.9148936170212763e-06,
      "loss": 0.3811,
      "step": 10
    },
    {
      "epoch": 0.007804185881518269,
      "grad_norm": 31.071639133351898,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 0.3851,
      "step": 11
    },
    {
      "epoch": 0.008513657325292657,
      "grad_norm": 20.77631646223411,
      "learning_rate": 2.340425531914894e-06,
      "loss": 0.2891,
      "step": 12
    },
    {
      "epoch": 0.009223128769067045,
      "grad_norm": 13.477671793796729,
      "learning_rate": 2.553191489361702e-06,
      "loss": 0.2528,
      "step": 13
    },
    {
      "epoch": 0.009932600212841433,
      "grad_norm": 2.6555809333853024,
      "learning_rate": 2.7659574468085106e-06,
      "loss": 0.1542,
      "step": 14
    },
    {
      "epoch": 0.010642071656615822,
      "grad_norm": 2.898054397668401,
      "learning_rate": 2.978723404255319e-06,
      "loss": 0.1762,
      "step": 15
    },
    {
      "epoch": 0.011351543100390209,
      "grad_norm": 2.1504034279865385,
      "learning_rate": 3.1914893617021277e-06,
      "loss": 0.1403,
      "step": 16
    },
    {
      "epoch": 0.012061014544164597,
      "grad_norm": 5.259173556940105,
      "learning_rate": 3.4042553191489363e-06,
      "loss": 0.1561,
      "step": 17
    },
    {
      "epoch": 0.012770485987938986,
      "grad_norm": 4.169332828012237,
      "learning_rate": 3.6170212765957445e-06,
      "loss": 0.1632,
      "step": 18
    },
    {
      "epoch": 0.013479957431713374,
      "grad_norm": 1.9000129489744462,
      "learning_rate": 3.829787234042553e-06,
      "loss": 0.1667,
      "step": 19
    },
    {
      "epoch": 0.014189428875487761,
      "grad_norm": 7.769485079957688,
      "learning_rate": 4.042553191489362e-06,
      "loss": 0.1893,
      "step": 20
    },
    {
      "epoch": 0.01489890031926215,
      "grad_norm": 11.504242044440007,
      "learning_rate": 4.255319148936171e-06,
      "loss": 0.2085,
      "step": 21
    },
    {
      "epoch": 0.015608371763036538,
      "grad_norm": 7.145142567820805,
      "learning_rate": 4.468085106382979e-06,
      "loss": 0.1913,
      "step": 22
    },
    {
      "epoch": 0.016317843206810925,
      "grad_norm": 2.736186486725912,
      "learning_rate": 4.680851063829788e-06,
      "loss": 0.1741,
      "step": 23
    },
    {
      "epoch": 0.017027314650585313,
      "grad_norm": 5.7916893585600695,
      "learning_rate": 4.893617021276596e-06,
      "loss": 0.1408,
      "step": 24
    },
    {
      "epoch": 0.0177367860943597,
      "grad_norm": 4.68647394202743,
      "learning_rate": 5.106382978723404e-06,
      "loss": 0.1632,
      "step": 25
    },
    {
      "epoch": 0.01844625753813409,
      "grad_norm": 2.0524513403445757,
      "learning_rate": 5.319148936170213e-06,
      "loss": 0.1563,
      "step": 26
    },
    {
      "epoch": 0.01915572898190848,
      "grad_norm": 1.588252902269814,
      "learning_rate": 5.531914893617021e-06,
      "loss": 0.1582,
      "step": 27
    },
    {
      "epoch": 0.019865200425682867,
      "grad_norm": 3.5755825255555225,
      "learning_rate": 5.74468085106383e-06,
      "loss": 0.1451,
      "step": 28
    },
    {
      "epoch": 0.020574671869457255,
      "grad_norm": 7.715437458161659,
      "learning_rate": 5.957446808510638e-06,
      "loss": 0.157,
      "step": 29
    },
    {
      "epoch": 0.021284143313231644,
      "grad_norm": 19.70487906339096,
      "learning_rate": 6.1702127659574465e-06,
      "loss": 0.1725,
      "step": 30
    },
    {
      "epoch": 0.02199361475700603,
      "grad_norm": 2.21235512385039,
      "learning_rate": 6.3829787234042555e-06,
      "loss": 0.1318,
      "step": 31
    },
    {
      "epoch": 0.022703086200780417,
      "grad_norm": 5.021653379215672,
      "learning_rate": 6.5957446808510645e-06,
      "loss": 0.1795,
      "step": 32
    },
    {
      "epoch": 0.023412557644554806,
      "grad_norm": 25.495061679606632,
      "learning_rate": 6.808510638297873e-06,
      "loss": 0.1586,
      "step": 33
    },
    {
      "epoch": 0.024122029088329194,
      "grad_norm": 4.7481186730757035,
      "learning_rate": 7.021276595744681e-06,
      "loss": 0.1552,
      "step": 34
    },
    {
      "epoch": 0.024831500532103583,
      "grad_norm": 3.6399107060391365,
      "learning_rate": 7.234042553191489e-06,
      "loss": 0.1573,
      "step": 35
    },
    {
      "epoch": 0.02554097197587797,
      "grad_norm": 3.3754400837055707,
      "learning_rate": 7.446808510638298e-06,
      "loss": 0.149,
      "step": 36
    },
    {
      "epoch": 0.02625044341965236,
      "grad_norm": 2.8787349588257842,
      "learning_rate": 7.659574468085105e-06,
      "loss": 0.154,
      "step": 37
    },
    {
      "epoch": 0.026959914863426748,
      "grad_norm": 2.7404452323712416,
      "learning_rate": 7.872340425531914e-06,
      "loss": 0.1563,
      "step": 38
    },
    {
      "epoch": 0.027669386307201137,
      "grad_norm": 1.8896448248412065,
      "learning_rate": 8.085106382978723e-06,
      "loss": 0.1568,
      "step": 39
    },
    {
      "epoch": 0.028378857750975522,
      "grad_norm": 6.6357403507533395,
      "learning_rate": 8.297872340425532e-06,
      "loss": 0.1608,
      "step": 40
    },
    {
      "epoch": 0.02908832919474991,
      "grad_norm": 5.2141592606599545,
      "learning_rate": 8.510638297872341e-06,
      "loss": 0.1495,
      "step": 41
    },
    {
      "epoch": 0.0297978006385243,
      "grad_norm": 2.653621690332451,
      "learning_rate": 8.723404255319149e-06,
      "loss": 0.1746,
      "step": 42
    },
    {
      "epoch": 0.030507272082298687,
      "grad_norm": 2.1695013496806483,
      "learning_rate": 8.936170212765958e-06,
      "loss": 0.1501,
      "step": 43
    },
    {
      "epoch": 0.031216743526073076,
      "grad_norm": 1.9610946251979264,
      "learning_rate": 9.148936170212767e-06,
      "loss": 0.1614,
      "step": 44
    },
    {
      "epoch": 0.03192621496984746,
      "grad_norm": 3.806116355988534,
      "learning_rate": 9.361702127659576e-06,
      "loss": 0.1649,
      "step": 45
    },
    {
      "epoch": 0.03263568641362185,
      "grad_norm": 1.6308337200888532,
      "learning_rate": 9.574468085106385e-06,
      "loss": 0.1528,
      "step": 46
    },
    {
      "epoch": 0.03334515785739624,
      "grad_norm": 1.0471741398584304,
      "learning_rate": 9.787234042553192e-06,
      "loss": 0.151,
      "step": 47
    },
    {
      "epoch": 0.034054629301170626,
      "grad_norm": 2.1098801420979885,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.15,
      "step": 48
    },
    {
      "epoch": 0.034764100744945015,
      "grad_norm": 1.4498470002731845,
      "learning_rate": 1.0212765957446808e-05,
      "loss": 0.1385,
      "step": 49
    },
    {
      "epoch": 0.0354735721887194,
      "grad_norm": 2.4843540113556632,
      "learning_rate": 1.0425531914893617e-05,
      "loss": 0.1822,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 2820,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 31813017403392.0,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}