{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.074157863855362,
      "epoch": 0.08,
      "grad_norm": 0.9623633623123169,
      "learning_rate": 0.0,
      "loss": 2.8972,
      "mean_token_accuracy": 0.4513181820511818,
      "num_tokens": 2908.0,
      "step": 1
    },
    {
      "entropy": 2.1756343841552734,
      "epoch": 0.16,
      "grad_norm": 1.0783641338348389,
      "learning_rate": 5e-05,
      "loss": 2.989,
      "mean_token_accuracy": 0.4384376108646393,
      "num_tokens": 5086.0,
      "step": 2
    },
    {
      "entropy": 2.1015622317790985,
      "epoch": 0.24,
      "grad_norm": 1.0787147283554077,
      "learning_rate": 0.0001,
      "loss": 2.9231,
      "mean_token_accuracy": 0.4472825303673744,
      "num_tokens": 6703.0,
      "step": 3
    },
    {
      "entropy": 2.318566679954529,
      "epoch": 0.32,
      "grad_norm": 1.0077248811721802,
      "learning_rate": 9.993784606094612e-05,
      "loss": 2.9968,
      "mean_token_accuracy": 0.4545922800898552,
      "num_tokens": 9075.0,
      "step": 4
    },
    {
      "entropy": 2.267362117767334,
      "epoch": 0.4,
      "grad_norm": 0.8960147500038147,
      "learning_rate": 9.975153876827008e-05,
      "loss": 2.7756,
      "mean_token_accuracy": 0.46887098997831345,
      "num_tokens": 11207.0,
      "step": 5
    },
    {
      "entropy": 2.5053298473358154,
      "epoch": 0.48,
      "grad_norm": 0.9175477027893066,
      "learning_rate": 9.944154131125642e-05,
      "loss": 2.8334,
      "mean_token_accuracy": 0.4478325620293617,
      "num_tokens": 13013.0,
      "step": 6
    },
    {
      "entropy": 2.5062224864959717,
      "epoch": 0.56,
      "grad_norm": 0.739920973777771,
      "learning_rate": 9.900862439242719e-05,
      "loss": 2.674,
      "mean_token_accuracy": 0.48493383079767227,
      "num_tokens": 15798.0,
      "step": 7
    },
    {
      "entropy": 2.543445646762848,
      "epoch": 0.64,
      "grad_norm": 0.8454245924949646,
      "learning_rate": 9.84538643114539e-05,
      "loss": 2.6321,
      "mean_token_accuracy": 0.4908815994858742,
      "num_tokens": 17899.0,
      "step": 8
    },
    {
      "entropy": 2.6626943945884705,
      "epoch": 0.72,
      "grad_norm": 0.9240928888320923,
      "learning_rate": 9.777864028930705e-05,
      "loss": 2.7066,
      "mean_token_accuracy": 0.45207490772008896,
      "num_tokens": 19457.0,
      "step": 9
    },
    {
      "entropy": 2.5745842456817627,
      "epoch": 0.8,
      "grad_norm": 0.7333309054374695,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.3685,
      "mean_token_accuracy": 0.5086618214845657,
      "num_tokens": 22198.0,
      "step": 10
    },
    {
      "entropy": 2.744494140148163,
      "epoch": 0.88,
      "grad_norm": 0.9435456395149231,
      "learning_rate": 9.607381059352038e-05,
      "loss": 2.4654,
      "mean_token_accuracy": 0.5047935917973518,
      "num_tokens": 24508.0,
      "step": 11
    },
    {
      "entropy": 2.7561975717544556,
      "epoch": 0.96,
      "grad_norm": 0.9667397737503052,
      "learning_rate": 9.504844339512095e-05,
      "loss": 2.4149,
      "mean_token_accuracy": 0.5050082951784134,
      "num_tokens": 26458.0,
      "step": 12
    },
    {
      "entropy": 2.7281463146209717,
      "epoch": 1.0,
      "grad_norm": 1.060321569442749,
      "learning_rate": 9.391107866851143e-05,
      "loss": 2.5978,
      "mean_token_accuracy": 0.47450077533721924,
      "num_tokens": 27555.0,
      "step": 13
    },
    {
      "entropy": 2.523155093193054,
      "epoch": 1.08,
      "grad_norm": 0.7708236575126648,
      "learning_rate": 9.266454408160779e-05,
      "loss": 2.2798,
      "mean_token_accuracy": 0.5204823762178421,
      "num_tokens": 30557.0,
      "step": 14
    },
    {
      "entropy": 2.4740833044052124,
      "epoch": 1.16,
      "grad_norm": 0.8472949266433716,
      "learning_rate": 9.131193871579975e-05,
      "loss": 2.145,
      "mean_token_accuracy": 0.5561789870262146,
      "num_tokens": 32709.0,
      "step": 15
    },
    {
      "entropy": 2.564497411251068,
      "epoch": 1.24,
      "grad_norm": 0.9041805267333984,
      "learning_rate": 8.985662536114613e-05,
      "loss": 2.5184,
      "mean_token_accuracy": 0.4873481020331383,
      "num_tokens": 34383.0,
      "step": 16
    },
    {
      "entropy": 2.283787727355957,
      "epoch": 1.32,
      "grad_norm": 0.880549967288971,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.0957,
      "mean_token_accuracy": 0.5535659641027451,
      "num_tokens": 36823.0,
      "step": 17
    },
    {
      "entropy": 2.2330291867256165,
      "epoch": 1.4,
      "grad_norm": 0.9609613418579102,
      "learning_rate": 8.665259359149132e-05,
      "loss": 2.0666,
      "mean_token_accuracy": 0.5471859276294708,
      "num_tokens": 38982.0,
      "step": 18
    },
    {
      "entropy": 2.1904984414577484,
      "epoch": 1.48,
      "grad_norm": 1.1095411777496338,
      "learning_rate": 8.491184090430364e-05,
      "loss": 2.3007,
      "mean_token_accuracy": 0.5376310795545578,
      "num_tokens": 40570.0,
      "step": 19
    },
    {
      "entropy": 2.1939757764339447,
      "epoch": 1.56,
      "grad_norm": 0.9360744953155518,
      "learning_rate": 8.308429187984297e-05,
      "loss": 2.2015,
      "mean_token_accuracy": 0.5384656116366386,
      "num_tokens": 43213.0,
      "step": 20
    },
    {
      "entropy": 2.0095443725585938,
      "epoch": 1.6400000000000001,
      "grad_norm": 0.9957161545753479,
      "learning_rate": 8.117449009293668e-05,
      "loss": 2.01,
      "mean_token_accuracy": 0.5757630318403244,
      "num_tokens": 45424.0,
      "step": 21
    },
    {
      "entropy": 2.056138187646866,
      "epoch": 1.72,
      "grad_norm": 1.2742964029312134,
      "learning_rate": 7.91871836117395e-05,
      "loss": 2.1542,
      "mean_token_accuracy": 0.5374337062239647,
      "num_tokens": 47023.0,
      "step": 22
    },
    {
      "entropy": 1.9765421450138092,
      "epoch": 1.8,
      "grad_norm": 0.9705051183700562,
      "learning_rate": 7.712731319328798e-05,
      "loss": 2.0624,
      "mean_token_accuracy": 0.5524236708879471,
      "num_tokens": 49784.0,
      "step": 23
    },
    {
      "entropy": 1.8856642246246338,
      "epoch": 1.88,
      "grad_norm": 1.0250470638275146,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.9065,
      "mean_token_accuracy": 0.5826538950204849,
      "num_tokens": 52011.0,
      "step": 24
    },
    {
      "entropy": 2.021214246749878,
      "epoch": 1.96,
      "grad_norm": 1.2443675994873047,
      "learning_rate": 7.281053286765815e-05,
      "loss": 2.1271,
      "mean_token_accuracy": 0.5555168986320496,
      "num_tokens": 53916.0,
      "step": 25
    },
    {
      "entropy": 2.0159093737602234,
      "epoch": 2.0,
      "grad_norm": 1.4712964296340942,
      "learning_rate": 7.056435515653059e-05,
      "loss": 2.0417,
      "mean_token_accuracy": 0.5624207556247711,
      "num_tokens": 55110.0,
      "step": 26
    },
    {
      "entropy": 1.917511224746704,
      "epoch": 2.08,
      "grad_norm": 0.9676669836044312,
      "learning_rate": 6.826705121831976e-05,
      "loss": 1.7429,
      "mean_token_accuracy": 0.6025293320417404,
      "num_tokens": 57944.0,
      "step": 27
    },
    {
      "entropy": 1.9889066219329834,
      "epoch": 2.16,
      "grad_norm": 1.1242130994796753,
      "learning_rate": 6.592433251258423e-05,
      "loss": 1.7523,
      "mean_token_accuracy": 0.59645976126194,
      "num_tokens": 59993.0,
      "step": 28
    },
    {
      "entropy": 2.039870023727417,
      "epoch": 2.24,
      "grad_norm": 1.4665213823318481,
      "learning_rate": 6.354202340715026e-05,
      "loss": 2.1926,
      "mean_token_accuracy": 0.545217253267765,
      "num_tokens": 61625.0,
      "step": 29
    },
    {
      "entropy": 1.9573059976100922,
      "epoch": 2.32,
      "grad_norm": 1.017709732055664,
      "learning_rate": 6.112604669781572e-05,
      "loss": 1.8044,
      "mean_token_accuracy": 0.5996322631835938,
      "num_tokens": 64409.0,
      "step": 30
    },
    {
      "entropy": 1.8920992612838745,
      "epoch": 2.4,
      "grad_norm": 1.0838905572891235,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.7022,
      "mean_token_accuracy": 0.6239200979471207,
      "num_tokens": 66753.0,
      "step": 31
    },
    {
      "entropy": 2.0309515595436096,
      "epoch": 2.48,
      "grad_norm": 1.3521836996078491,
      "learning_rate": 5.621718523237427e-05,
      "loss": 1.9173,
      "mean_token_accuracy": 0.5637946575880051,
      "num_tokens": 68494.0,
      "step": 32
    },
    {
      "entropy": 1.9445721805095673,
      "epoch": 2.56,
      "grad_norm": 1.1347510814666748,
      "learning_rate": 5.373650467932122e-05,
      "loss": 1.8014,
      "mean_token_accuracy": 0.5944488346576691,
      "num_tokens": 71033.0,
      "step": 33
    },
    {
      "entropy": 1.884565383195877,
      "epoch": 2.64,
      "grad_norm": 1.1540933847427368,
      "learning_rate": 5.124653458690365e-05,
      "loss": 1.7365,
      "mean_token_accuracy": 0.6244822144508362,
      "num_tokens": 73249.0,
      "step": 34
    },
    {
      "entropy": 1.9037934839725494,
      "epoch": 2.7199999999999998,
      "grad_norm": 1.317600965499878,
      "learning_rate": 4.875346541309637e-05,
      "loss": 1.7379,
      "mean_token_accuracy": 0.6134182661771774,
      "num_tokens": 74994.0,
      "step": 35
    },
    {
      "entropy": 1.864166796207428,
      "epoch": 2.8,
      "grad_norm": 1.159854531288147,
      "learning_rate": 4.626349532067879e-05,
      "loss": 1.8124,
      "mean_token_accuracy": 0.6027743518352509,
      "num_tokens": 77504.0,
      "step": 36
    },
    {
      "entropy": 1.730625718832016,
      "epoch": 2.88,
      "grad_norm": 1.2109590768814087,
      "learning_rate": 4.378281476762576e-05,
      "loss": 1.6053,
      "mean_token_accuracy": 0.6425295174121857,
      "num_tokens": 79750.0,
      "step": 37
    },
    {
      "entropy": 1.8132167756557465,
      "epoch": 2.96,
      "grad_norm": 1.3908966779708862,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.8062,
      "mean_token_accuracy": 0.5964024662971497,
      "num_tokens": 81441.0,
      "step": 38
    },
    {
      "entropy": 1.6718182563781738,
      "epoch": 3.0,
      "grad_norm": 1.6227182149887085,
      "learning_rate": 3.887395330218429e-05,
      "loss": 1.5381,
      "mean_token_accuracy": 0.6420005559921265,
      "num_tokens": 82665.0,
      "step": 39
    }
  ],
  "logging_steps": 1,
  "max_steps": 65,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3744731166105600.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}