{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.976,
  "eval_steps": 500,
  "global_step": 93,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.032,
      "grad_norm": 6.086521555575525,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.8709,
      "step": 1
    },
    {
      "epoch": 0.064,
      "grad_norm": 5.862669428136825,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8625,
      "step": 2
    },
    {
      "epoch": 0.096,
      "grad_norm": 5.665430905084772,
      "learning_rate": 6e-06,
      "loss": 0.8709,
      "step": 3
    },
    {
      "epoch": 0.128,
      "grad_norm": 3.9717562012437484,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.7764,
      "step": 4
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.2462420454815217,
      "learning_rate": 1e-05,
      "loss": 0.7977,
      "step": 5
    },
    {
      "epoch": 0.192,
      "grad_norm": 4.275087411533909,
      "learning_rate": 1.2e-05,
      "loss": 0.8235,
      "step": 6
    },
    {
      "epoch": 0.224,
      "grad_norm": 4.540127453722676,
      "learning_rate": 1.4e-05,
      "loss": 0.7536,
      "step": 7
    },
    {
      "epoch": 0.256,
      "grad_norm": 5.958818552449376,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7817,
      "step": 8
    },
    {
      "epoch": 0.288,
      "grad_norm": 4.615179916049989,
      "learning_rate": 1.8e-05,
      "loss": 0.7716,
      "step": 9
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.3655854780686663,
      "learning_rate": 2e-05,
      "loss": 0.6932,
      "step": 10
    },
    {
      "epoch": 0.352,
      "grad_norm": 2.478544642789441,
      "learning_rate": 1.9992837548163315e-05,
      "loss": 0.7029,
      "step": 11
    },
    {
      "epoch": 0.384,
      "grad_norm": 1.9787874769183103,
      "learning_rate": 1.9971360452796523e-05,
      "loss": 0.7003,
      "step": 12
    },
    {
      "epoch": 0.416,
      "grad_norm": 1.3386567233728712,
      "learning_rate": 1.993559947963185e-05,
      "loss": 0.6677,
      "step": 13
    },
    {
      "epoch": 0.448,
      "grad_norm": 1.177972539602327,
      "learning_rate": 1.9885605855918887e-05,
      "loss": 0.6495,
      "step": 14
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.1019717904815112,
      "learning_rate": 1.9821451197042028e-05,
      "loss": 0.5967,
      "step": 15
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.972479825971204,
      "learning_rate": 1.9743227403932135e-05,
      "loss": 0.6233,
      "step": 16
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.9169380714246801,
      "learning_rate": 1.9651046531419335e-05,
      "loss": 0.5939,
      "step": 17
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.7484870741589357,
      "learning_rate": 1.9545040627715554e-05,
      "loss": 0.5913,
      "step": 18
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.8433187788934118,
      "learning_rate": 1.942536154525673e-05,
      "loss": 0.5926,
      "step": 19
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.7004246074241133,
      "learning_rate": 1.9292180723175656e-05,
      "loss": 0.5679,
      "step": 20
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.9310125911747377,
      "learning_rate": 1.9145688941717074e-05,
      "loss": 0.5644,
      "step": 21
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.7970495324653322,
      "learning_rate": 1.8986096048946826e-05,
      "loss": 0.608,
      "step": 22
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.8089072723260873,
      "learning_rate": 1.881363066014649e-05,
      "loss": 0.5677,
      "step": 23
    },
    {
      "epoch": 0.768,
      "grad_norm": 1.0367436501959517,
      "learning_rate": 1.862853983032423e-05,
      "loss": 0.6124,
      "step": 24
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6549565017520195,
      "learning_rate": 1.8431088700310846e-05,
      "loss": 0.565,
      "step": 25
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.8100479455474157,
      "learning_rate": 1.8221560116948103e-05,
      "loss": 0.5536,
      "step": 26
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.6655173946648272,
      "learning_rate": 1.8000254227913346e-05,
      "loss": 0.5927,
      "step": 27
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.6489458832967611,
      "learning_rate": 1.7767488051760858e-05,
      "loss": 0.5996,
      "step": 28
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.6556791371183601,
      "learning_rate": 1.7523595023795814e-05,
      "loss": 0.5565,
      "step": 29
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.6656680446819412,
      "learning_rate": 1.7268924518431437e-05,
      "loss": 0.5691,
      "step": 30
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.6975728008241743,
      "learning_rate": 1.700384134871351e-05,
      "loss": 0.5634,
      "step": 31
    },
    {
      "epoch": 1.024,
      "grad_norm": 1.0956954168489788,
      "learning_rate": 1.672872524372919e-05,
      "loss": 0.9416,
      "step": 32
    },
    {
      "epoch": 1.056,
      "grad_norm": 0.48720084397077673,
      "learning_rate": 1.644397030464877e-05,
      "loss": 0.4704,
      "step": 33
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.7718389138248645,
      "learning_rate": 1.614998444017954e-05,
      "loss": 0.5326,
      "step": 34
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.6152935642153501,
      "learning_rate": 1.5847188782240473e-05,
      "loss": 0.5174,
      "step": 35
    },
    {
      "epoch": 1.152,
      "grad_norm": 0.5860900719025863,
      "learning_rate": 1.5536017082694846e-05,
      "loss": 0.5031,
      "step": 36
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.9098930960008285,
      "learning_rate": 1.5216915092004847e-05,
      "loss": 0.4993,
      "step": 37
    },
    {
      "epoch": 1.216,
      "grad_norm": 0.6433773311840126,
      "learning_rate": 1.4890339920698334e-05,
      "loss": 0.4832,
      "step": 38
    },
    {
      "epoch": 1.248,
      "grad_norm": 0.574508872316764,
      "learning_rate": 1.4556759384562418e-05,
      "loss": 0.5301,
      "step": 39
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.6177654141668454,
      "learning_rate": 1.421665133450184e-05,
      "loss": 0.4809,
      "step": 40
    },
    {
      "epoch": 1.312,
      "grad_norm": 0.5915067861936215,
      "learning_rate": 1.3870502972022175e-05,
      "loss": 0.4947,
      "step": 41
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 0.6003229031077386,
      "learning_rate": 1.351881015131833e-05,
      "loss": 0.5285,
      "step": 42
    },
    {
      "epoch": 1.376,
      "grad_norm": 0.5286636651815204,
      "learning_rate": 1.316207666896824e-05,
      "loss": 0.5134,
      "step": 43
    },
    {
      "epoch": 1.408,
      "grad_norm": 0.5729916541561343,
      "learning_rate": 1.2800813542249073e-05,
      "loss": 0.4392,
      "step": 44
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.5389286220120857,
      "learning_rate": 1.2435538277109919e-05,
      "loss": 0.4811,
      "step": 45
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.5162482888115615,
      "learning_rate": 1.206677412684953e-05,
      "loss": 0.5603,
      "step": 46
    },
    {
      "epoch": 1.504,
      "grad_norm": 0.5836229105696747,
      "learning_rate": 1.1695049342560969e-05,
      "loss": 0.452,
      "step": 47
    },
    {
      "epoch": 1.536,
      "grad_norm": 0.5251402934459473,
      "learning_rate": 1.1320896416417026e-05,
      "loss": 0.5007,
      "step": 48
    },
    {
      "epoch": 1.568,
      "grad_norm": 0.49581981068641073,
      "learning_rate": 1.0944851318880314e-05,
      "loss": 0.4815,
      "step": 49
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.6328540516916794,
      "learning_rate": 1.0567452730930743e-05,
      "loss": 0.559,
      "step": 50
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 0.48288716820093464,
      "learning_rate": 1.0189241272410191e-05,
      "loss": 0.4568,
      "step": 51
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 0.43453357593747727,
      "learning_rate": 9.810758727589814e-06,
      "loss": 0.5136,
      "step": 52
    },
    {
      "epoch": 1.696,
      "grad_norm": 0.43509974292321796,
      "learning_rate": 9.43254726906926e-06,
      "loss": 0.4613,
      "step": 53
    },
    {
      "epoch": 1.728,
      "grad_norm": 0.5105120033270906,
      "learning_rate": 9.055148681119688e-06,
      "loss": 0.5104,
      "step": 54
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.4655178250091279,
      "learning_rate": 8.67910358358298e-06,
      "loss": 0.515,
      "step": 55
    },
    {
      "epoch": 1.792,
      "grad_norm": 0.4271675109217912,
      "learning_rate": 8.304950657439034e-06,
      "loss": 0.4594,
      "step": 56
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 0.49279836130724164,
      "learning_rate": 7.93322587315047e-06,
      "loss": 0.5102,
      "step": 57
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 0.4312602763649386,
      "learning_rate": 7.564461722890082e-06,
      "loss": 0.461,
      "step": 58
    },
    {
      "epoch": 1.888,
      "grad_norm": 0.39722581396114753,
      "learning_rate": 7.199186457750931e-06,
      "loss": 0.5036,
      "step": 59
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.3707840503108745,
      "learning_rate": 6.837923331031761e-06,
      "loss": 0.4449,
      "step": 60
    },
    {
      "epoch": 1.952,
      "grad_norm": 0.5482704117501644,
      "learning_rate": 6.48118984868167e-06,
      "loss": 0.492,
      "step": 61
    },
    {
      "epoch": 1.984,
      "grad_norm": 0.37776373909746913,
      "learning_rate": 6.129497027977829e-06,
      "loss": 0.4131,
      "step": 62
    },
    {
      "epoch": 2.016,
      "grad_norm": 0.8547764035968157,
      "learning_rate": 5.78334866549816e-06,
      "loss": 0.8721,
      "step": 63
    },
    {
      "epoch": 2.048,
      "grad_norm": 0.4825739846598577,
      "learning_rate": 5.443240615437586e-06,
      "loss": 0.4129,
      "step": 64
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.48613435690189827,
      "learning_rate": 5.109660079301668e-06,
      "loss": 0.4016,
      "step": 65
    },
    {
      "epoch": 2.112,
      "grad_norm": 0.5173122404541247,
      "learning_rate": 4.783084907995156e-06,
      "loss": 0.4602,
      "step": 66
    },
    {
      "epoch": 2.144,
      "grad_norm": 0.4177033225672536,
      "learning_rate": 4.463982917305155e-06,
      "loss": 0.4306,
      "step": 67
    },
    {
      "epoch": 2.176,
      "grad_norm": 0.47335210102568437,
      "learning_rate": 4.152811217759529e-06,
      "loss": 0.4554,
      "step": 68
    },
    {
      "epoch": 2.208,
      "grad_norm": 0.5212910634677221,
      "learning_rate": 3.850015559820465e-06,
      "loss": 0.4453,
      "step": 69
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.4937857543597342,
      "learning_rate": 3.5560296953512296e-06,
      "loss": 0.4501,
      "step": 70
    },
    {
      "epoch": 2.2720000000000002,
      "grad_norm": 0.456794357715941,
      "learning_rate": 3.2712747562708115e-06,
      "loss": 0.4418,
      "step": 71
    },
    {
      "epoch": 2.304,
      "grad_norm": 0.41067614923626466,
      "learning_rate": 2.9961586512864947e-06,
      "loss": 0.3938,
      "step": 72
    },
    {
      "epoch": 2.336,
      "grad_norm": 0.5398460548951893,
      "learning_rate": 2.7310754815685627e-06,
      "loss": 0.5264,
      "step": 73
    },
    {
      "epoch": 2.368,
      "grad_norm": 0.39421897779539533,
      "learning_rate": 2.4764049762041874e-06,
      "loss": 0.4214,
      "step": 74
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.45677772727826993,
      "learning_rate": 2.2325119482391466e-06,
      "loss": 0.4438,
      "step": 75
    },
    {
      "epoch": 2.432,
      "grad_norm": 0.3614990193323558,
      "learning_rate": 1.9997457720866554e-06,
      "loss": 0.3733,
      "step": 76
    },
    {
      "epoch": 2.464,
      "grad_norm": 0.4657826146229637,
      "learning_rate": 1.7784398830519002e-06,
      "loss": 0.4528,
      "step": 77
    },
    {
      "epoch": 2.496,
      "grad_norm": 0.37950794177613073,
      "learning_rate": 1.5689112996891576e-06,
      "loss": 0.4219,
      "step": 78
    },
    {
      "epoch": 2.528,
      "grad_norm": 0.40926112347112487,
      "learning_rate": 1.3714601696757713e-06,
      "loss": 0.4557,
      "step": 79
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.3444002577522251,
      "learning_rate": 1.1863693398535115e-06,
      "loss": 0.3943,
      "step": 80
    },
    {
      "epoch": 2.592,
      "grad_norm": 0.3404781664005299,
      "learning_rate": 1.01390395105318e-06,
      "loss": 0.4281,
      "step": 81
    },
    {
      "epoch": 2.624,
      "grad_norm": 0.3448953746542976,
      "learning_rate": 8.543110582829272e-07,
      "loss": 0.4293,
      "step": 82
    },
    {
      "epoch": 2.656,
      "grad_norm": 0.320896402093994,
      "learning_rate": 7.078192768243486e-07,
      "loss": 0.3955,
      "step": 83
    },
    {
      "epoch": 2.6879999999999997,
      "grad_norm": 0.3635340073918507,
      "learning_rate": 5.746384547432738e-07,
      "loss": 0.4496,
      "step": 84
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.3153399588065185,
      "learning_rate": 4.549593722844492e-07,
      "loss": 0.3784,
      "step": 85
    },
    {
      "epoch": 2.752,
      "grad_norm": 0.32229126417822246,
      "learning_rate": 3.4895346858066723e-07,
      "loss": 0.4526,
      "step": 86
    },
    {
      "epoch": 2.784,
      "grad_norm": 0.33084039803529036,
      "learning_rate": 2.5677259606786686e-07,
      "loss": 0.3698,
      "step": 87
    },
    {
      "epoch": 2.816,
      "grad_norm": 0.3521643205936658,
      "learning_rate": 1.7854880295797406e-07,
      "loss": 0.4528,
      "step": 88
    },
    {
      "epoch": 2.848,
      "grad_norm": 0.3379615978848595,
      "learning_rate": 1.1439414408111471e-07,
      "loss": 0.4464,
      "step": 89
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.3383417229866119,
      "learning_rate": 6.440052036815081e-08,
      "loss": 0.3912,
      "step": 90
    },
    {
      "epoch": 2.912,
      "grad_norm": 0.3088668241871979,
      "learning_rate": 2.86395472034795e-08,
      "loss": 0.4426,
      "step": 91
    },
    {
      "epoch": 2.944,
      "grad_norm": 0.32476651809192353,
      "learning_rate": 7.162451836685291e-09,
      "loss": 0.4281,
      "step": 92
    },
    {
      "epoch": 2.976,
      "grad_norm": 0.3358967063808013,
      "learning_rate": 0.0,
      "loss": 0.4736,
      "step": 93
    },
    {
      "epoch": 2.976,
      "step": 93,
      "total_flos": 1.818538711009198e+17,
      "train_loss": 0.53916282679445,
      "train_runtime": 9093.0931,
      "train_samples_per_second": 0.989,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 93,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.818538711009198e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}