{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 13,
  "global_step": 69,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 0.358293741941452,
      "learning_rate": 0.0,
      "loss": 1.4248046875,
      "step": 1
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 0.25040334463119507,
      "learning_rate": 2.5e-05,
      "loss": 1.28076171875,
      "step": 2
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 0.2750855088233948,
      "learning_rate": 5e-05,
      "loss": 1.325927734375,
      "step": 3
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.11012878268957138,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9765625,
      "step": 4
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.09100934118032455,
      "learning_rate": 0.0001,
      "loss": 1.094482421875,
      "step": 5
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 0.07628698647022247,
      "learning_rate": 9.99474502074547e-05,
      "loss": 1.09716796875,
      "step": 6
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 0.112603560090065,
      "learning_rate": 9.978992356229419e-05,
      "loss": 1.08056640625,
      "step": 7
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.10804687440395355,
      "learning_rate": 9.95277879752973e-05,
      "loss": 1.145263671875,
      "step": 8
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 0.06533285230398178,
      "learning_rate": 9.916165567627362e-05,
      "loss": 0.8206787109375,
      "step": 9
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.07664325088262558,
      "learning_rate": 9.869238178417235e-05,
      "loss": 1.02685546875,
      "step": 10
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 0.057490020990371704,
      "learning_rate": 9.812106230991248e-05,
      "loss": 1.053466796875,
      "step": 11
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.05530868470668793,
      "learning_rate": 9.744903159659843e-05,
      "loss": 0.9140625,
      "step": 12
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 0.05087924003601074,
      "learning_rate": 9.667785920309994e-05,
      "loss": 0.74609375,
      "step": 13
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 0.05897296220064163,
      "learning_rate": 9.580934623827455e-05,
      "loss": 1.062744140625,
      "step": 14
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.05015362799167633,
      "learning_rate": 9.484552115439445e-05,
      "loss": 0.8336181640625,
      "step": 15
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.05686900392174721,
      "learning_rate": 9.378863500960222e-05,
      "loss": 0.977294921875,
      "step": 16
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 0.05482611432671547,
      "learning_rate": 9.26411562104602e-05,
      "loss": 0.946044921875,
      "step": 17
    },
    {
      "epoch": 0.7391304347826086,
      "eval_loss": 0.72613525390625,
      "eval_runtime": 14.3944,
      "eval_samples_per_second": 0.834,
      "eval_steps_per_second": 0.139,
      "step": 17
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 0.05088166147470474,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.9462890625,
      "step": 18
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 0.06613270193338394,
      "learning_rate": 9.008534593284501e-05,
      "loss": 0.92626953125,
      "step": 19
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.04615642875432968,
      "learning_rate": 8.868298366769954e-05,
      "loss": 0.815673828125,
      "step": 20
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 0.04247715696692467,
      "learning_rate": 8.720195323348545e-05,
      "loss": 0.922607421875,
      "step": 21
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 0.049818702042102814,
      "learning_rate": 8.564571364540588e-05,
      "loss": 0.79443359375,
      "step": 22
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.05298414081335068,
      "learning_rate": 8.401789957312768e-05,
      "loss": 0.9482421875,
      "step": 23
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.044772692024707794,
      "learning_rate": 8.232231285184201e-05,
      "loss": 0.869873046875,
      "step": 24
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 0.04113435000181198,
      "learning_rate": 8.056291360290201e-05,
      "loss": 0.85302734375,
      "step": 25
    },
    {
      "epoch": 1.1304347826086956,
      "grad_norm": 0.0595691055059433,
      "learning_rate": 7.874381098477599e-05,
      "loss": 0.83441162109375,
      "step": 26
    },
    {
      "epoch": 1.1739130434782608,
      "grad_norm": 0.04168998450040817,
      "learning_rate": 7.686925359591727e-05,
      "loss": 0.675537109375,
      "step": 27
    },
    {
      "epoch": 1.2173913043478262,
      "grad_norm": 0.04582676291465759,
      "learning_rate": 7.494361955196587e-05,
      "loss": 0.870849609375,
      "step": 28
    },
    {
      "epoch": 1.2608695652173914,
      "grad_norm": 0.05049782246351242,
      "learning_rate": 7.29714062604563e-05,
      "loss": 0.85888671875,
      "step": 29
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 0.07165031135082245,
      "learning_rate": 7.095721991691411e-05,
      "loss": 0.804443359375,
      "step": 30
    },
    {
      "epoch": 1.3043478260869565,
      "eval_loss": 0.6904144287109375,
      "eval_runtime": 14.3475,
      "eval_samples_per_second": 0.836,
      "eval_steps_per_second": 0.139,
      "step": 30
    },
    {
      "epoch": 1.3478260869565217,
      "grad_norm": 0.0479128323495388,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.89892578125,
      "step": 31
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.03726751357316971,
      "learning_rate": 6.682183201893642e-05,
      "loss": 0.681640625,
      "step": 32
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 0.04471711814403534,
      "learning_rate": 6.471028885455128e-05,
      "loss": 0.84130859375,
      "step": 33
    },
    {
      "epoch": 1.4782608695652173,
      "grad_norm": 0.05034560337662697,
      "learning_rate": 6.257606686061673e-05,
      "loss": 0.9072265625,
      "step": 34
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 0.055396828800439835,
      "learning_rate": 6.042415061148954e-05,
      "loss": 0.7825927734375,
      "step": 35
    },
    {
      "epoch": 1.5652173913043477,
      "grad_norm": 0.04246706888079643,
      "learning_rate": 5.825956600727932e-05,
      "loss": 0.629150390625,
      "step": 36
    },
    {
      "epoch": 1.608695652173913,
      "grad_norm": 0.043250035494565964,
      "learning_rate": 5.608736853562596e-05,
      "loss": 0.9273681640625,
      "step": 37
    },
    {
      "epoch": 1.6521739130434783,
      "grad_norm": 0.047257207334041595,
      "learning_rate": 5.3912631464374064e-05,
      "loss": 0.7127685546875,
      "step": 38
    },
    {
      "epoch": 1.6956521739130435,
      "grad_norm": 0.05000508949160576,
      "learning_rate": 5.1740433992720704e-05,
      "loss": 0.833740234375,
      "step": 39
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.04959021136164665,
      "learning_rate": 4.9575849388510473e-05,
      "loss": 0.8233642578125,
      "step": 40
    },
    {
      "epoch": 1.7826086956521738,
      "grad_norm": 0.05467933416366577,
      "learning_rate": 4.742393313938327e-05,
      "loss": 0.831298828125,
      "step": 41
    },
    {
      "epoch": 1.8260869565217392,
      "grad_norm": 0.054576389491558075,
      "learning_rate": 4.5289711145448735e-05,
      "loss": 0.77880859375,
      "step": 42
    },
    {
      "epoch": 1.8695652173913042,
      "grad_norm": 0.04331353306770325,
      "learning_rate": 4.317816798106359e-05,
      "loss": 0.7177734375,
      "step": 43
    },
    {
      "epoch": 1.8695652173913042,
      "eval_loss": 0.673248291015625,
      "eval_runtime": 14.4253,
      "eval_samples_per_second": 0.832,
      "eval_steps_per_second": 0.139,
      "step": 43
    },
    {
      "epoch": 1.9130434782608696,
      "grad_norm": 0.04586687311530113,
      "learning_rate": 4.109423525312738e-05,
      "loss": 0.8203125,
      "step": 44
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 0.053318217396736145,
      "learning_rate": 3.904278008308589e-05,
      "loss": 0.700927734375,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.05544498935341835,
      "learning_rate": 3.7028593739543715e-05,
      "loss": 0.807373046875,
      "step": 46
    },
    {
      "epoch": 2.0434782608695654,
      "grad_norm": 0.050077639520168304,
      "learning_rate": 3.5056380448034144e-05,
      "loss": 0.73681640625,
      "step": 47
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.06725457310676575,
      "learning_rate": 3.313074640408273e-05,
      "loss": 0.76904296875,
      "step": 48
    },
    {
      "epoch": 2.130434782608696,
      "grad_norm": 0.06313300877809525,
      "learning_rate": 3.1256189015224025e-05,
      "loss": 0.7218017578125,
      "step": 49
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 0.04141499847173691,
      "learning_rate": 2.9437086397097995e-05,
      "loss": 0.603759765625,
      "step": 50
    },
    {
      "epoch": 2.217391304347826,
      "grad_norm": 0.04309592768549919,
      "learning_rate": 2.7677687148157998e-05,
      "loss": 0.7939453125,
      "step": 51
    },
    {
      "epoch": 2.260869565217391,
      "grad_norm": 0.05010441690683365,
      "learning_rate": 2.5982100426872337e-05,
      "loss": 0.77099609375,
      "step": 52
    },
    {
      "epoch": 2.3043478260869565,
      "grad_norm": 0.058069441467523575,
      "learning_rate": 2.4354286354594124e-05,
      "loss": 0.69580078125,
      "step": 53
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 0.05351916328072548,
      "learning_rate": 2.2798046766514558e-05,
      "loss": 0.797607421875,
      "step": 54
    },
    {
      "epoch": 2.391304347826087,
      "grad_norm": 0.04243462532758713,
      "learning_rate": 2.1317016332300447e-05,
      "loss": 0.6273193359375,
      "step": 55
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.048237577080726624,
      "learning_rate": 1.9914654067154996e-05,
      "loss": 0.7635498046875,
      "step": 56
    },
    {
      "epoch": 2.4347826086956523,
      "eval_loss": 0.66748046875,
      "eval_runtime": 14.3507,
      "eval_samples_per_second": 0.836,
      "eval_steps_per_second": 0.139,
      "step": 56
    },
    {
      "epoch": 2.4782608695652173,
      "grad_norm": 0.047005217522382736,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 0.83544921875,
      "step": 57
    },
    {
      "epoch": 2.5217391304347827,
      "grad_norm": 0.046434249728918076,
      "learning_rate": 1.7358843789539798e-05,
      "loss": 0.718994140625,
      "step": 58
    },
    {
      "epoch": 2.5652173913043477,
      "grad_norm": 0.04582000523805618,
      "learning_rate": 1.6211364990397783e-05,
      "loss": 0.571533203125,
      "step": 59
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 0.05002902075648308,
      "learning_rate": 1.515447884560556e-05,
      "loss": 0.8602294921875,
      "step": 60
    },
    {
      "epoch": 2.6521739130434785,
      "grad_norm": 0.059897541999816895,
      "learning_rate": 1.4190653761725458e-05,
      "loss": 0.64892578125,
      "step": 61
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 0.04995943605899811,
      "learning_rate": 1.3322140796900066e-05,
      "loss": 0.764404296875,
      "step": 62
    },
    {
      "epoch": 2.7391304347826084,
      "grad_norm": 0.05093064531683922,
      "learning_rate": 1.2550968403401558e-05,
      "loss": 0.758056640625,
      "step": 63
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.049988217651844025,
      "learning_rate": 1.1878937690087522e-05,
      "loss": 0.772705078125,
      "step": 64
    },
    {
      "epoch": 2.8260869565217392,
      "grad_norm": 0.061050303280353546,
      "learning_rate": 1.130761821582766e-05,
      "loss": 0.69873046875,
      "step": 65
    },
    {
      "epoch": 2.869565217391304,
      "grad_norm": 0.04839232936501503,
      "learning_rate": 1.0838344323726395e-05,
      "loss": 0.672119140625,
      "step": 66
    },
    {
      "epoch": 2.9130434782608696,
      "grad_norm": 0.05217154324054718,
      "learning_rate": 1.04722120247027e-05,
      "loss": 0.77099609375,
      "step": 67
    },
    {
      "epoch": 2.9565217391304346,
      "grad_norm": 0.06360427290201187,
      "learning_rate": 1.0210076437705812e-05,
      "loss": 0.658447265625,
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.05940975621342659,
      "learning_rate": 1.0052549792545301e-05,
      "loss": 0.733642578125,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6625900268554688,
      "eval_runtime": 14.3729,
      "eval_samples_per_second": 0.835,
      "eval_steps_per_second": 0.139,
      "step": 69
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 69,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.6283174402759066e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}