{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 13,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.6484919786453247,
      "learning_rate": 0.0,
      "loss": 1.5302734375,
      "step": 1
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.6537308692932129,
      "learning_rate": 2.5e-05,
      "loss": 1.50732421875,
      "step": 2
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.673050582408905,
      "learning_rate": 5e-05,
      "loss": 1.5185546875,
      "step": 3
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.5060420036315918,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.511138916015625,
      "step": 4
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.30887529253959656,
      "learning_rate": 0.0001,
      "loss": 1.40087890625,
      "step": 5
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.20122277736663818,
      "learning_rate": 9.994224282269737e-05,
      "loss": 1.3603515625,
      "step": 6
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.24981580674648285,
      "learning_rate": 9.976911955263529e-05,
      "loss": 1.353271484375,
      "step": 7
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.27218642830848694,
      "learning_rate": 9.948107459476501e-05,
      "loss": 1.30078125,
      "step": 8
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.23594558238983154,
      "learning_rate": 9.907884735636226e-05,
      "loss": 1.2880859375,
      "step": 9
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.22113916277885437,
      "learning_rate": 9.856347034897919e-05,
      "loss": 1.26611328125,
      "step": 10
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.207451730966568,
      "learning_rate": 9.793626653800219e-05,
      "loss": 1.226318359375,
      "step": 11
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.20755015313625336,
      "learning_rate": 9.719884594661864e-05,
      "loss": 1.2568359375,
      "step": 12
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.17007851600646973,
      "learning_rate": 9.635310152291039e-05,
      "loss": 1.239501953125,
      "step": 13
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.1428622305393219,
      "learning_rate": 9.540120428068338e-05,
      "loss": 1.202880859375,
      "step": 14
    },
    {
      "epoch": 0.6363636363636364,
      "eval_loss": 1.1806640625,
      "eval_runtime": 5.1037,
      "eval_samples_per_second": 0.784,
      "eval_steps_per_second": 0.196,
      "step": 14
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.13083815574645996,
      "learning_rate": 9.43455977265062e-05,
      "loss": 1.197509765625,
      "step": 15
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.13909989595413208,
      "learning_rate": 9.31889915872638e-05,
      "loss": 1.187744140625,
      "step": 16
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.14068648219108582,
      "learning_rate": 9.193435485432745e-05,
      "loss": 1.18115234375,
      "step": 17
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.14103928208351135,
      "learning_rate": 9.058490816219643e-05,
      "loss": 1.152587890625,
      "step": 18
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.1104067787528038,
      "learning_rate": 8.914411552117559e-05,
      "loss": 1.05517578125,
      "step": 19
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.11927060782909393,
      "learning_rate": 8.76156754253104e-05,
      "loss": 1.193359375,
      "step": 20
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.11170849949121475,
      "learning_rate": 8.600351135840589e-05,
      "loss": 1.12890625,
      "step": 21
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.1104699969291687,
      "learning_rate": 8.431176172250002e-05,
      "loss": 1.13330078125,
      "step": 22
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 0.09613741189241409,
      "learning_rate": 8.254476921464484e-05,
      "loss": 1.119140625,
      "step": 23
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.09008456021547318,
      "learning_rate": 8.070706967926565e-05,
      "loss": 1.09521484375,
      "step": 24
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 0.09935105592012405,
      "learning_rate": 7.880338046471331e-05,
      "loss": 1.09326171875,
      "step": 25
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.09212969243526459,
      "learning_rate": 7.683858831389867e-05,
      "loss": 1.159027099609375,
      "step": 26
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 0.08778497576713562,
      "learning_rate": 7.481773682009356e-05,
      "loss": 1.083740234375,
      "step": 27
    },
    {
      "epoch": 1.2272727272727273,
      "eval_loss": 1.0927734375,
      "eval_runtime": 5.117,
      "eval_samples_per_second": 0.782,
      "eval_steps_per_second": 0.195,
      "step": 27
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.08414468914270401,
      "learning_rate": 7.274601348009935e-05,
      "loss": 1.099609375,
      "step": 28
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 0.08235311508178711,
      "learning_rate": 7.062873637801692e-05,
      "loss": 1.10400390625,
      "step": 29
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.0841815173625946,
      "learning_rate": 6.847134053380112e-05,
      "loss": 1.07568359375,
      "step": 30
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 0.07870905101299286,
      "learning_rate": 6.627936395164243e-05,
      "loss": 1.087158203125,
      "step": 31
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.09404882043600082,
      "learning_rate": 6.40584334039897e-05,
      "loss": 1.08837890625,
      "step": 32
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.07923950999975204,
      "learning_rate": 6.181424998770595e-05,
      "loss": 1.05810546875,
      "step": 33
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.08308933675289154,
      "learning_rate": 5.955257448943445e-05,
      "loss": 1.1044921875,
      "step": 34
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 0.07987320423126221,
      "learning_rate": 5.727921259774208e-05,
      "loss": 1.099365234375,
      "step": 35
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.07347641885280609,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.08056640625,
      "step": 36
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 0.08490364253520966,
      "learning_rate": 5.2720787402257935e-05,
      "loss": 1.07666015625,
      "step": 37
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.07508078962564468,
      "learning_rate": 5.044742551056556e-05,
      "loss": 1.074951171875,
      "step": 38
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 0.07631556689739227,
      "learning_rate": 4.8185750012294065e-05,
      "loss": 1.07568359375,
      "step": 39
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.08071254193782806,
      "learning_rate": 4.594156659601029e-05,
      "loss": 1.05029296875,
      "step": 40
    },
    {
      "epoch": 1.8181818181818183,
      "eval_loss": 1.055419921875,
      "eval_runtime": 5.1075,
      "eval_samples_per_second": 0.783,
      "eval_steps_per_second": 0.196,
      "step": 40
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 0.0675211250782013,
      "learning_rate": 4.372063604835758e-05,
      "loss": 0.97119140625,
      "step": 41
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.08918321132659912,
      "learning_rate": 4.152865946619889e-05,
      "loss": 1.106689453125,
      "step": 42
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 0.06920626759529114,
      "learning_rate": 3.93712636219831e-05,
      "loss": 1.04638671875,
      "step": 43
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.09061622619628906,
      "learning_rate": 3.725398651990067e-05,
      "loss": 1.0537109375,
      "step": 44
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 0.07046699523925781,
      "learning_rate": 3.518226317990646e-05,
      "loss": 1.046142578125,
      "step": 45
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 0.06979958713054657,
      "learning_rate": 3.3161411686101364e-05,
      "loss": 1.0283203125,
      "step": 46
    },
    {
      "epoch": 2.1363636363636362,
      "grad_norm": 0.07331069558858871,
      "learning_rate": 3.119661953528671e-05,
      "loss": 1.03173828125,
      "step": 47
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.07536927610635757,
      "learning_rate": 2.9292930320734335e-05,
      "loss": 1.0992240905761719,
      "step": 48
    },
    {
      "epoch": 2.227272727272727,
      "grad_norm": 0.07666821032762527,
      "learning_rate": 2.745523078535517e-05,
      "loss": 1.026611328125,
      "step": 49
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.06852415204048157,
      "learning_rate": 2.568823827750001e-05,
      "loss": 1.045654296875,
      "step": 50
    },
    {
      "epoch": 2.3181818181818183,
      "grad_norm": 0.07268761098384857,
      "learning_rate": 2.39964886415941e-05,
      "loss": 1.05419921875,
      "step": 51
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.07941761612892151,
      "learning_rate": 2.2384324574689612e-05,
      "loss": 1.030029296875,
      "step": 52
    },
    {
      "epoch": 2.409090909090909,
      "grad_norm": 0.06556671112775803,
      "learning_rate": 2.0855884478824412e-05,
      "loss": 1.0439453125,
      "step": 53
    },
    {
      "epoch": 2.409090909090909,
      "eval_loss": 1.040771484375,
      "eval_runtime": 5.1085,
      "eval_samples_per_second": 0.783,
      "eval_steps_per_second": 0.196,
      "step": 53
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 0.0690130963921547,
      "learning_rate": 1.9415091837803573e-05,
      "loss": 1.046875,
      "step": 54
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.07252095639705658,
      "learning_rate": 1.806564514567258e-05,
      "loss": 1.015380859375,
      "step": 55
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.07445185631513596,
      "learning_rate": 1.6811008412736208e-05,
      "loss": 1.06787109375,
      "step": 56
    },
    {
      "epoch": 2.590909090909091,
      "grad_norm": 0.07511234283447266,
      "learning_rate": 1.5654402273493805e-05,
      "loss": 1.0625,
      "step": 57
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 0.06960045546293259,
      "learning_rate": 1.459879571931663e-05,
      "loss": 1.047119140625,
      "step": 58
    },
    {
      "epoch": 2.6818181818181817,
      "grad_norm": 0.07280787080526352,
      "learning_rate": 1.3646898477089626e-05,
      "loss": 1.0400390625,
      "step": 59
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.07160894572734833,
      "learning_rate": 1.2801154053381386e-05,
      "loss": 1.046142578125,
      "step": 60
    },
    {
      "epoch": 2.7727272727272725,
      "grad_norm": 0.06884549558162689,
      "learning_rate": 1.2063733461997805e-05,
      "loss": 1.048095703125,
      "step": 61
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 0.07696957141160965,
      "learning_rate": 1.1436529651020813e-05,
      "loss": 1.02294921875,
      "step": 62
    },
    {
      "epoch": 2.8636363636363638,
      "grad_norm": 0.06252304464578629,
      "learning_rate": 1.092115264363775e-05,
      "loss": 0.94873046875,
      "step": 63
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.0684686005115509,
      "learning_rate": 1.0518925405234989e-05,
      "loss": 1.083984375,
      "step": 64
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 0.06993022561073303,
      "learning_rate": 1.023088044736472e-05,
      "loss": 1.02392578125,
      "step": 65
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.07079355418682098,
      "learning_rate": 1.0057757177302627e-05,
      "loss": 1.0322265625,
      "step": 66
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.032470703125,
      "eval_runtime": 5.1167,
      "eval_samples_per_second": 0.782,
      "eval_steps_per_second": 0.195,
      "step": 66
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 66,
  "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": 4.335415292244001e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}