{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 13.695652173913043,
  "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": 1.7925595045089722,
      "learning_rate": 2e-05,
      "loss": 2.3441,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 1.6493580341339111,
      "learning_rate": 4e-05,
      "loss": 2.3631,
      "step": 2
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 1.601073980331421,
      "learning_rate": 6e-05,
      "loss": 2.2615,
      "step": 3
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 1.6346150636672974,
      "learning_rate": 8e-05,
      "loss": 2.3701,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 1.5244935750961304,
      "learning_rate": 0.0001,
      "loss": 1.9692,
      "step": 5
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 3.000169038772583,
      "learning_rate": 0.00012,
      "loss": 3.3233,
      "step": 6
    },
    {
      "epoch": 1.2608695652173914,
      "grad_norm": 1.265796184539795,
      "learning_rate": 0.00014,
      "loss": 1.4917,
      "step": 7
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 1.1824357509613037,
      "learning_rate": 0.00016,
      "loss": 1.3508,
      "step": 8
    },
    {
      "epoch": 1.608695652173913,
      "grad_norm": 1.0549633502960205,
      "learning_rate": 0.00018,
      "loss": 0.7712,
      "step": 9
    },
    {
      "epoch": 1.7826086956521738,
      "grad_norm": 0.9444736242294312,
      "learning_rate": 0.0002,
      "loss": 0.6453,
      "step": 10
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 1.1795233488082886,
      "learning_rate": 0.0001998629534754574,
      "loss": 0.6652,
      "step": 11
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 1.0760518312454224,
      "learning_rate": 0.00019945218953682734,
      "loss": 0.3256,
      "step": 12
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 0.7688791155815125,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.287,
      "step": 13
    },
    {
      "epoch": 2.5217391304347827,
      "grad_norm": 0.5655398368835449,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.2031,
      "step": 14
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 0.5574740171432495,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.1848,
      "step": 15
    },
    {
      "epoch": 2.869565217391304,
      "grad_norm": 0.409333199262619,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.1504,
      "step": 16
    },
    {
      "epoch": 3.0869565217391304,
      "grad_norm": 0.48374369740486145,
      "learning_rate": 0.00019335804264972018,
      "loss": 0.2207,
      "step": 17
    },
    {
      "epoch": 3.260869565217391,
      "grad_norm": 0.31125733256340027,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.1039,
      "step": 18
    },
    {
      "epoch": 3.4347826086956523,
      "grad_norm": 0.24773700535297394,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.0904,
      "step": 19
    },
    {
      "epoch": 3.608695652173913,
      "grad_norm": 0.4116332232952118,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.1124,
      "step": 20
    },
    {
      "epoch": 3.782608695652174,
      "grad_norm": 0.29519736766815186,
      "learning_rate": 0.00018386705679454242,
      "loss": 0.0816,
      "step": 21
    },
    {
      "epoch": 3.9565217391304346,
      "grad_norm": 0.48144784569740295,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.1117,
      "step": 22
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.12347900867462158,
      "learning_rate": 0.0001777145961456971,
      "loss": 0.0595,
      "step": 23
    },
    {
      "epoch": 4.3478260869565215,
      "grad_norm": 0.345081627368927,
      "learning_rate": 0.00017431448254773944,
      "loss": 0.07,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.16552160680294037,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0497,
      "step": 25
    },
    {
      "epoch": 4.695652173913043,
      "grad_norm": 0.20713075995445251,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0495,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.273133784532547,
      "learning_rate": 0.00016293203910498376,
      "loss": 0.0745,
      "step": 27
    },
    {
      "epoch": 5.086956521739131,
      "grad_norm": 0.3325965404510498,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.0893,
      "step": 28
    },
    {
      "epoch": 5.260869565217392,
      "grad_norm": 0.0951855406165123,
      "learning_rate": 0.00015446390350150273,
      "loss": 0.0319,
      "step": 29
    },
    {
      "epoch": 5.434782608695652,
      "grad_norm": 0.2029908150434494,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0542,
      "step": 30
    },
    {
      "epoch": 5.608695652173913,
      "grad_norm": 0.220689058303833,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.0512,
      "step": 31
    },
    {
      "epoch": 5.782608695652174,
      "grad_norm": 0.21392984688282013,
      "learning_rate": 0.00014067366430758004,
      "loss": 0.0446,
      "step": 32
    },
    {
      "epoch": 5.956521739130435,
      "grad_norm": 0.18461254239082336,
      "learning_rate": 0.00013583679495453,
      "loss": 0.0611,
      "step": 33
    },
    {
      "epoch": 6.173913043478261,
      "grad_norm": 2.2200334072113037,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.1033,
      "step": 34
    },
    {
      "epoch": 6.3478260869565215,
      "grad_norm": 0.11724428087472916,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.0358,
      "step": 35
    },
    {
      "epoch": 6.521739130434782,
      "grad_norm": 0.19415688514709473,
      "learning_rate": 0.00012079116908177593,
      "loss": 0.0391,
      "step": 36
    },
    {
      "epoch": 6.695652173913043,
      "grad_norm": 0.19208520650863647,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.0454,
      "step": 37
    },
    {
      "epoch": 6.869565217391305,
      "grad_norm": 0.18963392078876495,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0438,
      "step": 38
    },
    {
      "epoch": 7.086956521739131,
      "grad_norm": 0.15887770056724548,
      "learning_rate": 0.0001052335956242944,
      "loss": 0.0529,
      "step": 39
    },
    {
      "epoch": 7.260869565217392,
      "grad_norm": 0.10326984524726868,
      "learning_rate": 0.0001,
      "loss": 0.0302,
      "step": 40
    },
    {
      "epoch": 7.434782608695652,
      "grad_norm": 0.10307444632053375,
      "learning_rate": 9.476640437570562e-05,
      "loss": 0.0389,
      "step": 41
    },
    {
      "epoch": 7.608695652173913,
      "grad_norm": 0.16696208715438843,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0427,
      "step": 42
    },
    {
      "epoch": 7.782608695652174,
      "grad_norm": 0.12140149623155594,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0324,
      "step": 43
    },
    {
      "epoch": 7.956521739130435,
      "grad_norm": 0.15214045345783234,
      "learning_rate": 7.920883091822408e-05,
      "loss": 0.0465,
      "step": 44
    },
    {
      "epoch": 8.173913043478262,
      "grad_norm": 0.1985018402338028,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.0366,
      "step": 45
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 0.06822706758975983,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0284,
      "step": 46
    },
    {
      "epoch": 8.521739130434783,
      "grad_norm": 0.07317953556776047,
      "learning_rate": 6.416320504546997e-05,
      "loss": 0.0358,
      "step": 47
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 0.05046230927109718,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 0.0284,
      "step": 48
    },
    {
      "epoch": 8.869565217391305,
      "grad_norm": 0.07171109318733215,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.0313,
      "step": 49
    },
    {
      "epoch": 9.08695652173913,
      "grad_norm": 0.09738242626190186,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0381,
      "step": 50
    },
    {
      "epoch": 9.26086956521739,
      "grad_norm": 0.07053200155496597,
      "learning_rate": 4.5536096498497295e-05,
      "loss": 0.0293,
      "step": 51
    },
    {
      "epoch": 9.434782608695652,
      "grad_norm": 0.11508598923683167,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0257,
      "step": 52
    },
    {
      "epoch": 9.608695652173914,
      "grad_norm": 0.06967729330062866,
      "learning_rate": 3.7067960895016275e-05,
      "loss": 0.0273,
      "step": 53
    },
    {
      "epoch": 9.782608695652174,
      "grad_norm": 0.06969133019447327,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.0327,
      "step": 54
    },
    {
      "epoch": 9.956521739130435,
      "grad_norm": 0.12203659862279892,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0453,
      "step": 55
    },
    {
      "epoch": 11.173913043478262,
      "grad_norm": 0.12760570645332336,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 0.0278,
      "step": 56
    },
    {
      "epoch": 11.347826086956522,
      "grad_norm": 0.06412295252084732,
      "learning_rate": 2.2285403854302912e-05,
      "loss": 0.0234,
      "step": 57
    },
    {
      "epoch": 11.521739130434783,
      "grad_norm": 0.11282885074615479,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0332,
      "step": 58
    },
    {
      "epoch": 11.695652173913043,
      "grad_norm": 0.07060640305280685,
      "learning_rate": 1.6132943205457606e-05,
      "loss": 0.0286,
      "step": 59
    },
    {
      "epoch": 11.869565217391305,
      "grad_norm": 0.14442871510982513,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.0319,
      "step": 60
    },
    {
      "epoch": 12.08695652173913,
      "grad_norm": 0.17993809282779694,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0532,
      "step": 61
    },
    {
      "epoch": 12.26086956521739,
      "grad_norm": 0.0468832366168499,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.0234,
      "step": 62
    },
    {
      "epoch": 12.434782608695652,
      "grad_norm": 0.09955104440450668,
      "learning_rate": 6.6419573502798374e-06,
      "loss": 0.0321,
      "step": 63
    },
    {
      "epoch": 12.608695652173914,
      "grad_norm": 0.1094796434044838,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.0315,
      "step": 64
    },
    {
      "epoch": 12.782608695652174,
      "grad_norm": 0.06971123814582825,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.0208,
      "step": 65
    },
    {
      "epoch": 12.956521739130435,
      "grad_norm": 0.21308307349681854,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.0427,
      "step": 66
    },
    {
      "epoch": 13.173913043478262,
      "grad_norm": 0.06157653033733368,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.0258,
      "step": 67
    },
    {
      "epoch": 13.347826086956522,
      "grad_norm": 0.05918806418776512,
      "learning_rate": 5.478104631726711e-07,
      "loss": 0.0277,
      "step": 68
    },
    {
      "epoch": 13.521739130434783,
      "grad_norm": 0.08736610412597656,
      "learning_rate": 1.3704652454261668e-07,
      "loss": 0.024,
      "step": 69
    },
    {
      "epoch": 13.695652173913043,
      "grad_norm": 0.09696591645479202,
      "learning_rate": 0.0,
      "loss": 0.0337,
      "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": 393796424564736.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}