{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04435573297848747,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008871146595697493,
      "grad_norm": 2.552351713180542,
      "learning_rate": 5e-06,
      "loss": 2.0461,
      "step": 1
    },
    {
      "epoch": 0.0008871146595697493,
      "eval_loss": 2.357318878173828,
      "eval_runtime": 22.7138,
      "eval_samples_per_second": 20.912,
      "eval_steps_per_second": 10.478,
      "step": 1
    },
    {
      "epoch": 0.0017742293191394987,
      "grad_norm": 1.873948097229004,
      "learning_rate": 1e-05,
      "loss": 1.5926,
      "step": 2
    },
    {
      "epoch": 0.0026613439787092482,
      "grad_norm": 3.1655471324920654,
      "learning_rate": 1.5e-05,
      "loss": 2.3712,
      "step": 3
    },
    {
      "epoch": 0.0035484586382789974,
      "grad_norm": 2.2303149700164795,
      "learning_rate": 2e-05,
      "loss": 1.7694,
      "step": 4
    },
    {
      "epoch": 0.004435573297848747,
      "grad_norm": 2.6942412853240967,
      "learning_rate": 2.5e-05,
      "loss": 2.3172,
      "step": 5
    },
    {
      "epoch": 0.0053226879574184965,
      "grad_norm": 2.11533260345459,
      "learning_rate": 3e-05,
      "loss": 1.7689,
      "step": 6
    },
    {
      "epoch": 0.006209802616988246,
      "grad_norm": 2.6214680671691895,
      "learning_rate": 3.5e-05,
      "loss": 1.8771,
      "step": 7
    },
    {
      "epoch": 0.007096917276557995,
      "grad_norm": 2.7126352787017822,
      "learning_rate": 4e-05,
      "loss": 1.7355,
      "step": 8
    },
    {
      "epoch": 0.007984031936127744,
      "grad_norm": 2.914896011352539,
      "learning_rate": 4.5e-05,
      "loss": 1.7516,
      "step": 9
    },
    {
      "epoch": 0.008871146595697495,
      "grad_norm": 3.065276861190796,
      "learning_rate": 5e-05,
      "loss": 1.7267,
      "step": 10
    },
    {
      "epoch": 0.009758261255267244,
      "grad_norm": 3.1432533264160156,
      "learning_rate": 4.99229333433282e-05,
      "loss": 2.071,
      "step": 11
    },
    {
      "epoch": 0.010645375914836993,
      "grad_norm": 2.5506999492645264,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 1.4475,
      "step": 12
    },
    {
      "epoch": 0.011532490574406742,
      "grad_norm": 2.507850170135498,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 1.3582,
      "step": 13
    },
    {
      "epoch": 0.011532490574406742,
      "eval_loss": 1.3111391067504883,
      "eval_runtime": 22.7388,
      "eval_samples_per_second": 20.889,
      "eval_steps_per_second": 10.467,
      "step": 13
    },
    {
      "epoch": 0.012419605233976491,
      "grad_norm": 2.5213797092437744,
      "learning_rate": 4.877641290737884e-05,
      "loss": 1.3541,
      "step": 14
    },
    {
      "epoch": 0.01330671989354624,
      "grad_norm": 2.1459462642669678,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.9014,
      "step": 15
    },
    {
      "epoch": 0.01419383455311599,
      "grad_norm": 2.892573833465576,
      "learning_rate": 4.72751631047092e-05,
      "loss": 1.0082,
      "step": 16
    },
    {
      "epoch": 0.01508094921268574,
      "grad_norm": 2.568525791168213,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 0.8953,
      "step": 17
    },
    {
      "epoch": 0.015968063872255488,
      "grad_norm": 2.7149441242218018,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.9834,
      "step": 18
    },
    {
      "epoch": 0.01685517853182524,
      "grad_norm": 1.9368983507156372,
      "learning_rate": 4.401014914000078e-05,
      "loss": 0.8917,
      "step": 19
    },
    {
      "epoch": 0.01774229319139499,
      "grad_norm": 2.554739236831665,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.7854,
      "step": 20
    },
    {
      "epoch": 0.018629407850964737,
      "grad_norm": 2.128541946411133,
      "learning_rate": 4.123620120825459e-05,
      "loss": 0.7922,
      "step": 21
    },
    {
      "epoch": 0.019516522510534488,
      "grad_norm": 1.9166874885559082,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.6496,
      "step": 22
    },
    {
      "epoch": 0.020403637170104235,
      "grad_norm": 1.746896743774414,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 0.6681,
      "step": 23
    },
    {
      "epoch": 0.021290751829673986,
      "grad_norm": 2.7109410762786865,
      "learning_rate": 3.634976249348867e-05,
      "loss": 0.8622,
      "step": 24
    },
    {
      "epoch": 0.022177866489243733,
      "grad_norm": 2.082806348800659,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.6218,
      "step": 25
    },
    {
      "epoch": 0.023064981148813484,
      "grad_norm": 1.8518857955932617,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.5705,
      "step": 26
    },
    {
      "epoch": 0.023064981148813484,
      "eval_loss": 0.6528695225715637,
      "eval_runtime": 22.7482,
      "eval_samples_per_second": 20.881,
      "eval_steps_per_second": 10.462,
      "step": 26
    },
    {
      "epoch": 0.023952095808383235,
      "grad_norm": 2.120460271835327,
      "learning_rate": 3.083613409639764e-05,
      "loss": 0.4645,
      "step": 27
    },
    {
      "epoch": 0.024839210467952982,
      "grad_norm": 1.6701194047927856,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 0.6054,
      "step": 28
    },
    {
      "epoch": 0.025726325127522733,
      "grad_norm": 1.8231170177459717,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 0.4044,
      "step": 29
    },
    {
      "epoch": 0.02661343978709248,
      "grad_norm": 1.5324640274047852,
      "learning_rate": 2.5e-05,
      "loss": 0.3928,
      "step": 30
    },
    {
      "epoch": 0.02750055444666223,
      "grad_norm": 3.182884693145752,
      "learning_rate": 2.303852260680388e-05,
      "loss": 0.6412,
      "step": 31
    },
    {
      "epoch": 0.02838766910623198,
      "grad_norm": 1.9924638271331787,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 0.5593,
      "step": 32
    },
    {
      "epoch": 0.02927478376580173,
      "grad_norm": 1.4829778671264648,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 0.471,
      "step": 33
    },
    {
      "epoch": 0.03016189842537148,
      "grad_norm": 1.884485125541687,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 0.5697,
      "step": 34
    },
    {
      "epoch": 0.031049013084941228,
      "grad_norm": 1.922612190246582,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.3865,
      "step": 35
    },
    {
      "epoch": 0.031936127744510975,
      "grad_norm": 1.9512248039245605,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 0.4733,
      "step": 36
    },
    {
      "epoch": 0.03282324240408073,
      "grad_norm": 1.9390307664871216,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 0.5349,
      "step": 37
    },
    {
      "epoch": 0.03371035706365048,
      "grad_norm": 1.8721624612808228,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.7239,
      "step": 38
    },
    {
      "epoch": 0.034597471723220224,
      "grad_norm": 1.7561758756637573,
      "learning_rate": 8.763798791745411e-06,
      "loss": 0.5401,
      "step": 39
    },
    {
      "epoch": 0.034597471723220224,
      "eval_loss": 0.583450198173523,
      "eval_runtime": 22.7264,
      "eval_samples_per_second": 20.901,
      "eval_steps_per_second": 10.472,
      "step": 39
    },
    {
      "epoch": 0.03548458638278998,
      "grad_norm": 1.6044561862945557,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.525,
      "step": 40
    },
    {
      "epoch": 0.036371701042359726,
      "grad_norm": 2.315598726272583,
      "learning_rate": 5.989850859999227e-06,
      "loss": 0.6067,
      "step": 41
    },
    {
      "epoch": 0.037258815701929474,
      "grad_norm": 1.8639142513275146,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.6147,
      "step": 42
    },
    {
      "epoch": 0.03814593036149922,
      "grad_norm": 2.1164658069610596,
      "learning_rate": 3.6839958911476957e-06,
      "loss": 0.5504,
      "step": 43
    },
    {
      "epoch": 0.039033045021068975,
      "grad_norm": 2.0981204509735107,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 0.6325,
      "step": 44
    },
    {
      "epoch": 0.03992015968063872,
      "grad_norm": 1.7437758445739746,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.4499,
      "step": 45
    },
    {
      "epoch": 0.04080727434020847,
      "grad_norm": 2.0806751251220703,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 0.5006,
      "step": 46
    },
    {
      "epoch": 0.041694388999778224,
      "grad_norm": 2.024292469024658,
      "learning_rate": 6.907519900580861e-07,
      "loss": 0.5585,
      "step": 47
    },
    {
      "epoch": 0.04258150365934797,
      "grad_norm": 1.8988577127456665,
      "learning_rate": 3.077914851215585e-07,
      "loss": 0.4586,
      "step": 48
    },
    {
      "epoch": 0.04346861831891772,
      "grad_norm": 2.1858489513397217,
      "learning_rate": 7.706665667180091e-08,
      "loss": 0.5561,
      "step": 49
    },
    {
      "epoch": 0.04435573297848747,
      "grad_norm": 2.0317609310150146,
      "learning_rate": 0.0,
      "loss": 0.5758,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.02619680866304e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}