{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.695652173913043,
  "eval_steps": 500,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 6.764804363250732,
      "learning_rate": 2e-05,
      "loss": 2.5611,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 5.956302165985107,
      "learning_rate": 4e-05,
      "loss": 2.6708,
      "step": 2
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 5.123376369476318,
      "learning_rate": 6e-05,
      "loss": 2.5466,
      "step": 3
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 6.901731014251709,
      "learning_rate": 8e-05,
      "loss": 2.6007,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 7.963821887969971,
      "learning_rate": 0.0001,
      "loss": 2.4327,
      "step": 5
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 24.67555046081543,
      "learning_rate": 0.00012,
      "loss": 3.6948,
      "step": 6
    },
    {
      "epoch": 1.2608695652173914,
      "grad_norm": 11.961183547973633,
      "learning_rate": 0.00014,
      "loss": 1.8845,
      "step": 7
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 7.313081741333008,
      "learning_rate": 0.00016,
      "loss": 1.6564,
      "step": 8
    },
    {
      "epoch": 1.608695652173913,
      "grad_norm": 7.329380512237549,
      "learning_rate": 0.00018,
      "loss": 1.2679,
      "step": 9
    },
    {
      "epoch": 1.7826086956521738,
      "grad_norm": 5.3990092277526855,
      "learning_rate": 0.0002,
      "loss": 1.1521,
      "step": 10
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 19.579421997070312,
      "learning_rate": 0.0001998629534754574,
      "loss": 1.3572,
      "step": 11
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 9.876869201660156,
      "learning_rate": 0.00019945218953682734,
      "loss": 0.6523,
      "step": 12
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 4.188257217407227,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.5632,
      "step": 13
    },
    {
      "epoch": 2.5217391304347827,
      "grad_norm": 5.128059387207031,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.4172,
      "step": 14
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 1.45033597946167,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.3559,
      "step": 15
    },
    {
      "epoch": 2.869565217391304,
      "grad_norm": 4.084733963012695,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.2889,
      "step": 16
    },
    {
      "epoch": 3.0869565217391304,
      "grad_norm": 1.971590518951416,
      "learning_rate": 0.00019335804264972018,
      "loss": 0.3996,
      "step": 17
    },
    {
      "epoch": 3.260869565217391,
      "grad_norm": 0.9812415838241577,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.1805,
      "step": 18
    },
    {
      "epoch": 3.4347826086956523,
      "grad_norm": 0.5682662129402161,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.1469,
      "step": 19
    },
    {
      "epoch": 3.608695652173913,
      "grad_norm": 0.7722249627113342,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.16,
      "step": 20
    },
    {
      "epoch": 3.782608695652174,
      "grad_norm": 2.2477004528045654,
      "learning_rate": 0.00018386705679454242,
      "loss": 0.1266,
      "step": 21
    },
    {
      "epoch": 3.9565217391304346,
      "grad_norm": 1.3397961854934692,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.1924,
      "step": 22
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 1.588268518447876,
      "learning_rate": 0.0001777145961456971,
      "loss": 0.0942,
      "step": 23
    },
    {
      "epoch": 4.3478260869565215,
      "grad_norm": 0.5260263085365295,
      "learning_rate": 0.00017431448254773944,
      "loss": 0.0984,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.6609199643135071,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0809,
      "step": 25
    },
    {
      "epoch": 4.695652173913043,
      "grad_norm": 0.3053271770477295,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0661,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.39704304933547974,
      "learning_rate": 0.00016293203910498376,
      "loss": 0.0811,
      "step": 27
    },
    {
      "epoch": 5.086956521739131,
      "grad_norm": 1.004157543182373,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.1324,
      "step": 28
    },
    {
      "epoch": 5.260869565217392,
      "grad_norm": 0.3579670488834381,
      "learning_rate": 0.00015446390350150273,
      "loss": 0.0494,
      "step": 29
    },
    {
      "epoch": 5.434782608695652,
      "grad_norm": 0.2634657621383667,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0637,
      "step": 30
    },
    {
      "epoch": 5.608695652173913,
      "grad_norm": 0.3780810534954071,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.0603,
      "step": 31
    },
    {
      "epoch": 5.782608695652174,
      "grad_norm": 0.4811391532421112,
      "learning_rate": 0.00014067366430758004,
      "loss": 0.059,
      "step": 32
    },
    {
      "epoch": 5.956521739130435,
      "grad_norm": 0.4578228294849396,
      "learning_rate": 0.00013583679495453,
      "loss": 0.0881,
      "step": 33
    },
    {
      "epoch": 6.173913043478261,
      "grad_norm": 0.7382459044456482,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0523,
      "step": 34
    },
    {
      "epoch": 6.3478260869565215,
      "grad_norm": 0.6557295322418213,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.042,
      "step": 35
    },
    {
      "epoch": 6.521739130434782,
      "grad_norm": 0.5470027327537537,
      "learning_rate": 0.00012079116908177593,
      "loss": 0.0415,
      "step": 36
    },
    {
      "epoch": 6.695652173913043,
      "grad_norm": 0.6779957413673401,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.0563,
      "step": 37
    },
    {
      "epoch": 6.869565217391305,
      "grad_norm": 0.16265903413295746,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0416,
      "step": 38
    },
    {
      "epoch": 7.086956521739131,
      "grad_norm": 0.1718588024377823,
      "learning_rate": 0.0001052335956242944,
      "loss": 0.0563,
      "step": 39
    },
    {
      "epoch": 7.260869565217392,
      "grad_norm": 0.9964053630828857,
      "learning_rate": 0.0001,
      "loss": 0.0415,
      "step": 40
    },
    {
      "epoch": 7.434782608695652,
      "grad_norm": 1.2380071878433228,
      "learning_rate": 9.476640437570562e-05,
      "loss": 0.0486,
      "step": 41
    },
    {
      "epoch": 7.608695652173913,
      "grad_norm": 0.38603806495666504,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0467,
      "step": 42
    },
    {
      "epoch": 7.782608695652174,
      "grad_norm": 0.2892161011695862,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0298,
      "step": 43
    },
    {
      "epoch": 7.956521739130435,
      "grad_norm": 0.32837310433387756,
      "learning_rate": 7.920883091822408e-05,
      "loss": 0.0544,
      "step": 44
    },
    {
      "epoch": 8.173913043478262,
      "grad_norm": 0.12985481321811676,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.0347,
      "step": 45
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 0.2492673248052597,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0441,
      "step": 46
    },
    {
      "epoch": 8.521739130434783,
      "grad_norm": 2.073184013366699,
      "learning_rate": 6.416320504546997e-05,
      "loss": 0.043,
      "step": 47
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 0.09984829276800156,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 0.0328,
      "step": 48
    },
    {
      "epoch": 8.869565217391305,
      "grad_norm": 1.290177345275879,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.0382,
      "step": 49
    },
    {
      "epoch": 9.08695652173913,
      "grad_norm": 0.8741787672042847,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0487,
      "step": 50
    },
    {
      "epoch": 9.26086956521739,
      "grad_norm": 1.1984590291976929,
      "learning_rate": 4.5536096498497295e-05,
      "loss": 0.0382,
      "step": 51
    },
    {
      "epoch": 9.434782608695652,
      "grad_norm": 0.1054629385471344,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0275,
      "step": 52
    },
    {
      "epoch": 9.608695652173914,
      "grad_norm": 0.06806695461273193,
      "learning_rate": 3.7067960895016275e-05,
      "loss": 0.0314,
      "step": 53
    },
    {
      "epoch": 9.782608695652174,
      "grad_norm": 0.29768458008766174,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.039,
      "step": 54
    },
    {
      "epoch": 9.956521739130435,
      "grad_norm": 1.4097405672073364,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0516,
      "step": 55
    },
    {
      "epoch": 10.173913043478262,
      "grad_norm": 0.31604883074760437,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 0.0375,
      "step": 56
    },
    {
      "epoch": 10.347826086956522,
      "grad_norm": 0.14812345802783966,
      "learning_rate": 2.2285403854302912e-05,
      "loss": 0.0296,
      "step": 57
    },
    {
      "epoch": 10.521739130434783,
      "grad_norm": 0.1633218377828598,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0437,
      "step": 58
    },
    {
      "epoch": 10.695652173913043,
      "grad_norm": 0.1193070039153099,
      "learning_rate": 1.6132943205457606e-05,
      "loss": 0.0298,
      "step": 59
    },
    {
      "epoch": 10.869565217391305,
      "grad_norm": 0.1309748888015747,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.0345,
      "step": 60
    },
    {
      "epoch": 11.08695652173913,
      "grad_norm": 0.1206737831234932,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0327,
      "step": 61
    },
    {
      "epoch": 11.26086956521739,
      "grad_norm": 0.07418113946914673,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.0309,
      "step": 62
    },
    {
      "epoch": 11.434782608695652,
      "grad_norm": 0.24486000835895538,
      "learning_rate": 6.6419573502798374e-06,
      "loss": 0.0347,
      "step": 63
    },
    {
      "epoch": 11.608695652173914,
      "grad_norm": 0.2284393310546875,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.0252,
      "step": 64
    },
    {
      "epoch": 11.782608695652174,
      "grad_norm": 0.19318842887878418,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.0377,
      "step": 65
    },
    {
      "epoch": 11.956521739130435,
      "grad_norm": 0.1955549567937851,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.0564,
      "step": 66
    },
    {
      "epoch": 12.173913043478262,
      "grad_norm": 0.14949171245098114,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.0364,
      "step": 67
    },
    {
      "epoch": 12.347826086956522,
      "grad_norm": 0.32537975907325745,
      "learning_rate": 5.478104631726711e-07,
      "loss": 0.0402,
      "step": 68
    },
    {
      "epoch": 12.521739130434783,
      "grad_norm": 0.08832496404647827,
      "learning_rate": 1.3704652454261668e-07,
      "loss": 0.0289,
      "step": 69
    },
    {
      "epoch": 12.695652173913043,
      "grad_norm": 0.10512495785951614,
      "learning_rate": 0.0,
      "loss": 0.0324,
      "step": 70
    }
  ],
  "logging_steps": 1,
  "max_steps": 70,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 14,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 144357206261760.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}