{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 16,
  "global_step": 81,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 3.603320360183716,
      "learning_rate": 0.0,
      "loss": 3.13580322265625,
      "step": 1
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 7.633277416229248,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 3.724609375,
      "step": 2
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 3.1807398796081543,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 3.18798828125,
      "step": 3
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 26.3658390045166,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.86737060546875,
      "step": 4
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 3.1732168197631836,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 3.5654296875,
      "step": 5
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 7.057729721069336,
      "learning_rate": 5.555555555555556e-05,
      "loss": 3.50390625,
      "step": 6
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 29.021793365478516,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.162109375,
      "step": 7
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 7.539449691772461,
      "learning_rate": 7.777777777777778e-05,
      "loss": 2.75537109375,
      "step": 8
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.3787728548049927,
      "learning_rate": 8.888888888888889e-05,
      "loss": 2.073245048522949,
      "step": 9
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 2.590653419494629,
      "learning_rate": 0.0001,
      "loss": 1.955169677734375,
      "step": 10
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 5.739391803741455,
      "learning_rate": 9.99571699711836e-05,
      "loss": 2.02783203125,
      "step": 11
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.040536403656006,
      "learning_rate": 9.982876141412856e-05,
      "loss": 1.96630859375,
      "step": 12
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 1.7213687896728516,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.35302734375,
      "step": 13
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 1.929543137550354,
      "learning_rate": 9.931634888554937e-05,
      "loss": 1.7919921875,
      "step": 14
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.9385697841644287,
      "learning_rate": 9.893332032039701e-05,
      "loss": 1.3902435302734375,
      "step": 15
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.7352836728096008,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.740234375,
      "step": 16
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 2.1352813243865967,
      "learning_rate": 9.791726278367022e-05,
      "loss": 1.576171875,
      "step": 17
    },
    {
      "epoch": 0.6296296296296297,
      "eval_loss": 1.34814453125,
      "eval_runtime": 9.3439,
      "eval_samples_per_second": 0.535,
      "eval_steps_per_second": 0.107,
      "step": 17
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 3.195157051086426,
      "learning_rate": 9.728616793536588e-05,
      "loss": 1.487548828125,
      "step": 18
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 0.5804216861724854,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.50244140625,
      "step": 19
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.6442767381668091,
      "learning_rate": 9.578385041664925e-05,
      "loss": 1.4619140625,
      "step": 20
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.595580518245697,
      "learning_rate": 9.491548749301997e-05,
      "loss": 1.38671875,
      "step": 21
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 71.91153717041016,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.3408203125,
      "step": 22
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 0.4385150671005249,
      "learning_rate": 9.295261506157986e-05,
      "loss": 1.309814453125,
      "step": 23
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.5251197814941406,
      "learning_rate": 9.186184199300464e-05,
      "loss": 1.227783203125,
      "step": 24
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.46668022871017456,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.25146484375,
      "step": 25
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 14.799480438232422,
      "learning_rate": 8.947199994035401e-05,
      "loss": 1.197509765625,
      "step": 26
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6169384121894836,
      "learning_rate": 8.817748015645558e-05,
      "loss": 1.129150390625,
      "step": 27
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": 0.2736778259277344,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.137969970703125,
      "step": 28
    },
    {
      "epoch": 1.074074074074074,
      "grad_norm": 1.0230766534805298,
      "learning_rate": 8.540155934270471e-05,
      "loss": 1.297119140625,
      "step": 29
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.33532634377479553,
      "learning_rate": 8.392544243589427e-05,
      "loss": 1.181884765625,
      "step": 30
    },
    {
      "epoch": 1.1481481481481481,
      "grad_norm": 0.15526258945465088,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.030364990234375,
      "step": 31
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.3886986970901489,
      "learning_rate": 8.081093963579707e-05,
      "loss": 1.21435546875,
      "step": 32
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.22374582290649414,
      "learning_rate": 7.917848237560709e-05,
      "loss": 1.21533203125,
      "step": 33
    },
    {
      "epoch": 1.2222222222222223,
      "eval_loss": 0.998291015625,
      "eval_runtime": 9.314,
      "eval_samples_per_second": 0.537,
      "eval_steps_per_second": 0.107,
      "step": 33
    },
    {
      "epoch": 1.2592592592592593,
      "grad_norm": 0.26931798458099365,
      "learning_rate": 7.75e-05,
      "loss": 1.14697265625,
      "step": 34
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 0.5589653253555298,
      "learning_rate": 7.577868759557654e-05,
      "loss": 1.065185546875,
      "step": 35
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.3567545413970947,
      "learning_rate": 7.401782177833148e-05,
      "loss": 0.8294367790222168,
      "step": 36
    },
    {
      "epoch": 1.3703703703703702,
      "grad_norm": 0.18000337481498718,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.8375091552734375,
      "step": 37
    },
    {
      "epoch": 1.4074074074074074,
      "grad_norm": 0.8078757524490356,
      "learning_rate": 7.03909064496551e-05,
      "loss": 1.0029296875,
      "step": 38
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.16444790363311768,
      "learning_rate": 6.853176097769229e-05,
      "loss": 1.0390625,
      "step": 39
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.2736102342605591,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.21240234375,
      "step": 40
    },
    {
      "epoch": 1.5185185185185186,
      "grad_norm": 0.11317350715398788,
      "learning_rate": 6.473978262721463e-05,
      "loss": 1.069091796875,
      "step": 41
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.2357257455587387,
      "learning_rate": 6.281416799501188e-05,
      "loss": 0.8784103393554688,
      "step": 42
    },
    {
      "epoch": 1.5925925925925926,
      "grad_norm": 0.26080557703971863,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.12451171875,
      "step": 43
    },
    {
      "epoch": 1.6296296296296298,
      "grad_norm": 0.23005779087543488,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 1.072998046875,
      "step": 44
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.1561451256275177,
      "learning_rate": 5.696287243144013e-05,
      "loss": 1.0537109375,
      "step": 45
    },
    {
      "epoch": 1.7037037037037037,
      "grad_norm": 0.25621458888053894,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.09716796875,
      "step": 46
    },
    {
      "epoch": 1.7407407407407407,
      "grad_norm": 0.5164171457290649,
      "learning_rate": 5.303712756855988e-05,
      "loss": 1.090087890625,
      "step": 47
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.09791528433561325,
      "learning_rate": 5.107799157635538e-05,
      "loss": 1.091552734375,
      "step": 48
    },
    {
      "epoch": 1.8148148148148149,
      "grad_norm": 0.5729214549064636,
      "learning_rate": 4.912632135009769e-05,
      "loss": 1.0859375,
      "step": 49
    },
    {
      "epoch": 1.8148148148148149,
      "eval_loss": 0.9398193359375,
      "eval_runtime": 9.3411,
      "eval_samples_per_second": 0.535,
      "eval_steps_per_second": 0.107,
      "step": 49
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 0.4189198911190033,
      "learning_rate": 4.718583200498814e-05,
      "loss": 1.086181640625,
      "step": 50
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.5916740298271179,
      "learning_rate": 4.526021737278538e-05,
      "loss": 1.03759765625,
      "step": 51
    },
    {
      "epoch": 1.925925925925926,
      "grad_norm": 0.20379354059696198,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.064453125,
      "step": 52
    },
    {
      "epoch": 1.9629629629629628,
      "grad_norm": 0.12169843912124634,
      "learning_rate": 4.146823902230772e-05,
      "loss": 1.01416015625,
      "step": 53
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2611161172389984,
      "learning_rate": 3.960909355034491e-05,
      "loss": 0.963134765625,
      "step": 54
    },
    {
      "epoch": 2.037037037037037,
      "grad_norm": 0.6009112000465393,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.9714813232421875,
      "step": 55
    },
    {
      "epoch": 2.074074074074074,
      "grad_norm": 0.15203095972537994,
      "learning_rate": 3.598217822166854e-05,
      "loss": 1.120361328125,
      "step": 56
    },
    {
      "epoch": 2.111111111111111,
      "grad_norm": 0.06331958621740341,
      "learning_rate": 3.422131240442349e-05,
      "loss": 1.034423828125,
      "step": 57
    },
    {
      "epoch": 2.148148148148148,
      "grad_norm": 4.770232677459717,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.913543701171875,
      "step": 58
    },
    {
      "epoch": 2.185185185185185,
      "grad_norm": 0.20527023077011108,
      "learning_rate": 3.082151762439293e-05,
      "loss": 1.099365234375,
      "step": 59
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.1961517482995987,
      "learning_rate": 2.9189060364202943e-05,
      "loss": 1.1103515625,
      "step": 60
    },
    {
      "epoch": 2.259259259259259,
      "grad_norm": 0.26783716678619385,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.058837890625,
      "step": 61
    },
    {
      "epoch": 2.2962962962962963,
      "grad_norm": 0.11685217916965485,
      "learning_rate": 2.6074557564105727e-05,
      "loss": 0.989990234375,
      "step": 62
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.14141230285167694,
      "learning_rate": 2.459844065729529e-05,
      "loss": 0.7748198509216309,
      "step": 63
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.1857534795999527,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.7857666015625,
      "step": 64
    },
    {
      "epoch": 2.4074074074074074,
      "grad_norm": 0.37999841570854187,
      "learning_rate": 2.1822519843544424e-05,
      "loss": 0.945068359375,
      "step": 65
    },
    {
      "epoch": 2.4074074074074074,
      "eval_loss": 0.920654296875,
      "eval_runtime": 9.3651,
      "eval_samples_per_second": 0.534,
      "eval_steps_per_second": 0.107,
      "step": 65
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.15239450335502625,
      "learning_rate": 2.0528000059645997e-05,
      "loss": 0.97900390625,
      "step": 66
    },
    {
      "epoch": 2.4814814814814814,
      "grad_norm": 0.18943148851394653,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.13427734375,
      "step": 67
    },
    {
      "epoch": 2.5185185185185186,
      "grad_norm": 0.2281315177679062,
      "learning_rate": 1.8138158006995364e-05,
      "loss": 1.007080078125,
      "step": 68
    },
    {
      "epoch": 2.5555555555555554,
      "grad_norm": 0.17008155584335327,
      "learning_rate": 1.7047384938420154e-05,
      "loss": 0.8326797485351562,
      "step": 69
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 0.7526993751525879,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.0673828125,
      "step": 70
    },
    {
      "epoch": 2.6296296296296298,
      "grad_norm": 0.20475514233112335,
      "learning_rate": 1.5084512506980026e-05,
      "loss": 1.022705078125,
      "step": 71
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.36841246485710144,
      "learning_rate": 1.4216149583350754e-05,
      "loss": 1.00927734375,
      "step": 72
    },
    {
      "epoch": 2.7037037037037037,
      "grad_norm": 0.23206254839897156,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.05712890625,
      "step": 73
    },
    {
      "epoch": 2.7407407407407405,
      "grad_norm": 1.6135830879211426,
      "learning_rate": 1.2713832064634126e-05,
      "loss": 1.049560546875,
      "step": 74
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.1320762187242508,
      "learning_rate": 1.2082737216329794e-05,
      "loss": 1.0556640625,
      "step": 75
    },
    {
      "epoch": 2.814814814814815,
      "grad_norm": 0.2588306963443756,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.052490234375,
      "step": 76
    },
    {
      "epoch": 2.851851851851852,
      "grad_norm": 0.15002970397472382,
      "learning_rate": 1.1066679679603e-05,
      "loss": 1.054931640625,
      "step": 77
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.0859217718243599,
      "learning_rate": 1.0683651114450641e-05,
      "loss": 1.009033203125,
      "step": 78
    },
    {
      "epoch": 2.925925925925926,
      "grad_norm": 0.39869746565818787,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.037353515625,
      "step": 79
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.16209864616394043,
      "learning_rate": 1.017123858587145e-05,
      "loss": 0.98876953125,
      "step": 80
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.16407747566699982,
      "learning_rate": 1.00428300288164e-05,
      "loss": 0.93994140625,
      "step": 81
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.912109375,
      "eval_runtime": 9.3249,
      "eval_samples_per_second": 0.536,
      "eval_steps_per_second": 0.107,
      "step": 81
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 81,
  "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": 5.587311831401103e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}