{
  "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": 10.28883171081543,
      "learning_rate": 2e-05,
      "loss": 2.6361,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 7.904043197631836,
      "learning_rate": 4e-05,
      "loss": 2.7168,
      "step": 2
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 7.175183296203613,
      "learning_rate": 6e-05,
      "loss": 2.5857,
      "step": 3
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 10.86050033569336,
      "learning_rate": 8e-05,
      "loss": 2.6506,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 8.235480308532715,
      "learning_rate": 0.0001,
      "loss": 2.4973,
      "step": 5
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 8.710506439208984,
      "learning_rate": 0.00012,
      "loss": 3.7313,
      "step": 6
    },
    {
      "epoch": 1.2608695652173914,
      "grad_norm": 4.005091667175293,
      "learning_rate": 0.00014,
      "loss": 1.9344,
      "step": 7
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 1.7361865043640137,
      "learning_rate": 0.00016,
      "loss": 1.6744,
      "step": 8
    },
    {
      "epoch": 1.608695652173913,
      "grad_norm": 1.129019021987915,
      "learning_rate": 0.00018,
      "loss": 1.2627,
      "step": 9
    },
    {
      "epoch": 1.7826086956521738,
      "grad_norm": 2.075225830078125,
      "learning_rate": 0.0002,
      "loss": 1.1692,
      "step": 10
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 3.220959424972534,
      "learning_rate": 0.0001998629534754574,
      "loss": 1.3969,
      "step": 11
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 2.02755069732666,
      "learning_rate": 0.00019945218953682734,
      "loss": 0.6773,
      "step": 12
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 2.5127182006835938,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.5633,
      "step": 13
    },
    {
      "epoch": 2.5217391304347827,
      "grad_norm": 1.7217646837234497,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.451,
      "step": 14
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 0.879663348197937,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.3685,
      "step": 15
    },
    {
      "epoch": 2.869565217391304,
      "grad_norm": 0.5109443664550781,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.3015,
      "step": 16
    },
    {
      "epoch": 3.0869565217391304,
      "grad_norm": 0.9060106873512268,
      "learning_rate": 0.00019335804264972018,
      "loss": 0.4393,
      "step": 17
    },
    {
      "epoch": 3.260869565217391,
      "grad_norm": 0.3581462800502777,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.1748,
      "step": 18
    },
    {
      "epoch": 3.4347826086956523,
      "grad_norm": 0.3196995258331299,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.1477,
      "step": 19
    },
    {
      "epoch": 3.608695652173913,
      "grad_norm": 0.5006406307220459,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.1849,
      "step": 20
    },
    {
      "epoch": 3.782608695652174,
      "grad_norm": 0.6925095319747925,
      "learning_rate": 0.00018386705679454242,
      "loss": 0.1369,
      "step": 21
    },
    {
      "epoch": 3.9565217391304346,
      "grad_norm": 0.9922828674316406,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.1964,
      "step": 22
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.19768103957176208,
      "learning_rate": 0.0001777145961456971,
      "loss": 0.0935,
      "step": 23
    },
    {
      "epoch": 4.3478260869565215,
      "grad_norm": 0.357398122549057,
      "learning_rate": 0.00017431448254773944,
      "loss": 0.0992,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.223428413271904,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.086,
      "step": 25
    },
    {
      "epoch": 4.695652173913043,
      "grad_norm": 0.169768288731575,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0732,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.4857354164123535,
      "learning_rate": 0.00016293203910498376,
      "loss": 0.0819,
      "step": 27
    },
    {
      "epoch": 5.086956521739131,
      "grad_norm": 0.7584252953529358,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.1377,
      "step": 28
    },
    {
      "epoch": 5.260869565217392,
      "grad_norm": 0.301729291677475,
      "learning_rate": 0.00015446390350150273,
      "loss": 0.0559,
      "step": 29
    },
    {
      "epoch": 5.434782608695652,
      "grad_norm": 0.25065937638282776,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0744,
      "step": 30
    },
    {
      "epoch": 5.608695652173913,
      "grad_norm": 0.24226656556129456,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.0687,
      "step": 31
    },
    {
      "epoch": 5.782608695652174,
      "grad_norm": 0.2135501354932785,
      "learning_rate": 0.00014067366430758004,
      "loss": 0.0574,
      "step": 32
    },
    {
      "epoch": 5.956521739130435,
      "grad_norm": 0.2674519121646881,
      "learning_rate": 0.00013583679495453,
      "loss": 0.0868,
      "step": 33
    },
    {
      "epoch": 6.173913043478261,
      "grad_norm": 0.22415511310100555,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0557,
      "step": 34
    },
    {
      "epoch": 6.3478260869565215,
      "grad_norm": 0.16434131562709808,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.0475,
      "step": 35
    },
    {
      "epoch": 6.521739130434782,
      "grad_norm": 0.15994659066200256,
      "learning_rate": 0.00012079116908177593,
      "loss": 0.0466,
      "step": 36
    },
    {
      "epoch": 6.695652173913043,
      "grad_norm": 0.1557261049747467,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.0571,
      "step": 37
    },
    {
      "epoch": 6.869565217391305,
      "grad_norm": 0.14265908300876617,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0495,
      "step": 38
    },
    {
      "epoch": 7.086956521739131,
      "grad_norm": 0.15171098709106445,
      "learning_rate": 0.0001052335956242944,
      "loss": 0.0531,
      "step": 39
    },
    {
      "epoch": 7.260869565217392,
      "grad_norm": 0.11054924130439758,
      "learning_rate": 0.0001,
      "loss": 0.0422,
      "step": 40
    },
    {
      "epoch": 7.434782608695652,
      "grad_norm": 0.13466708362102509,
      "learning_rate": 9.476640437570562e-05,
      "loss": 0.0428,
      "step": 41
    },
    {
      "epoch": 7.608695652173913,
      "grad_norm": 0.6286543607711792,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0521,
      "step": 42
    },
    {
      "epoch": 7.782608695652174,
      "grad_norm": 0.08527137339115143,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0284,
      "step": 43
    },
    {
      "epoch": 7.956521739130435,
      "grad_norm": 0.1831391453742981,
      "learning_rate": 7.920883091822408e-05,
      "loss": 0.0535,
      "step": 44
    },
    {
      "epoch": 8.173913043478262,
      "grad_norm": 0.25190696120262146,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.0423,
      "step": 45
    },
    {
      "epoch": 8.347826086956522,
      "grad_norm": 0.12309681624174118,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.042,
      "step": 46
    },
    {
      "epoch": 8.521739130434783,
      "grad_norm": 0.22868376970291138,
      "learning_rate": 6.416320504546997e-05,
      "loss": 0.045,
      "step": 47
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 0.07320209592580795,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 0.0326,
      "step": 48
    },
    {
      "epoch": 8.869565217391305,
      "grad_norm": 0.35984838008880615,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.0363,
      "step": 49
    },
    {
      "epoch": 9.08695652173913,
      "grad_norm": 0.1674010455608368,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0511,
      "step": 50
    },
    {
      "epoch": 9.26086956521739,
      "grad_norm": 0.08465681225061417,
      "learning_rate": 4.5536096498497295e-05,
      "loss": 0.0351,
      "step": 51
    },
    {
      "epoch": 9.434782608695652,
      "grad_norm": 0.10184628516435623,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0262,
      "step": 52
    },
    {
      "epoch": 9.608695652173914,
      "grad_norm": 0.062240391969680786,
      "learning_rate": 3.7067960895016275e-05,
      "loss": 0.0304,
      "step": 53
    },
    {
      "epoch": 9.782608695652174,
      "grad_norm": 0.09094466269016266,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.0385,
      "step": 54
    },
    {
      "epoch": 9.956521739130435,
      "grad_norm": 0.27231261134147644,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0544,
      "step": 55
    },
    {
      "epoch": 10.173913043478262,
      "grad_norm": 0.07962878793478012,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 0.0401,
      "step": 56
    },
    {
      "epoch": 10.347826086956522,
      "grad_norm": 0.12017780542373657,
      "learning_rate": 2.2285403854302912e-05,
      "loss": 0.0316,
      "step": 57
    },
    {
      "epoch": 10.521739130434783,
      "grad_norm": 0.09102747589349747,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0418,
      "step": 58
    },
    {
      "epoch": 10.695652173913043,
      "grad_norm": 0.0645853728055954,
      "learning_rate": 1.6132943205457606e-05,
      "loss": 0.0309,
      "step": 59
    },
    {
      "epoch": 10.869565217391305,
      "grad_norm": 0.08740692585706711,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.0333,
      "step": 60
    },
    {
      "epoch": 11.08695652173913,
      "grad_norm": 0.11425518244504929,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0392,
      "step": 61
    },
    {
      "epoch": 11.26086956521739,
      "grad_norm": 0.09765691310167313,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.0344,
      "step": 62
    },
    {
      "epoch": 11.434782608695652,
      "grad_norm": 0.06935255229473114,
      "learning_rate": 6.6419573502798374e-06,
      "loss": 0.0327,
      "step": 63
    },
    {
      "epoch": 11.608695652173914,
      "grad_norm": 0.06399647146463394,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.0281,
      "step": 64
    },
    {
      "epoch": 11.782608695652174,
      "grad_norm": 0.18286477029323578,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.0373,
      "step": 65
    },
    {
      "epoch": 11.956521739130435,
      "grad_norm": 0.154697448015213,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.0547,
      "step": 66
    },
    {
      "epoch": 12.173913043478262,
      "grad_norm": 0.22570864856243134,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.0328,
      "step": 67
    },
    {
      "epoch": 12.347826086956522,
      "grad_norm": 0.08155275881290436,
      "learning_rate": 5.478104631726711e-07,
      "loss": 0.0388,
      "step": 68
    },
    {
      "epoch": 12.521739130434783,
      "grad_norm": 0.07228947430849075,
      "learning_rate": 1.3704652454261668e-07,
      "loss": 0.0272,
      "step": 69
    },
    {
      "epoch": 12.695652173913043,
      "grad_norm": 0.0742647722363472,
      "learning_rate": 0.0,
      "loss": 0.0308,
      "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
}