{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3003003003003003,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003003003003003003,
      "grad_norm": 1.031739354133606,
      "learning_rate": 1e-05,
      "loss": 1.9291,
      "step": 1
    },
    {
      "epoch": 0.003003003003003003,
      "eval_loss": 1.886456847190857,
      "eval_runtime": 63.4329,
      "eval_samples_per_second": 4.43,
      "eval_steps_per_second": 0.568,
      "step": 1
    },
    {
      "epoch": 0.006006006006006006,
      "grad_norm": 1.023872971534729,
      "learning_rate": 2e-05,
      "loss": 1.9021,
      "step": 2
    },
    {
      "epoch": 0.009009009009009009,
      "grad_norm": 1.0211207866668701,
      "learning_rate": 3e-05,
      "loss": 1.8857,
      "step": 3
    },
    {
      "epoch": 0.012012012012012012,
      "grad_norm": 0.890316367149353,
      "learning_rate": 4e-05,
      "loss": 1.8535,
      "step": 4
    },
    {
      "epoch": 0.015015015015015015,
      "grad_norm": 0.8935955762863159,
      "learning_rate": 5e-05,
      "loss": 1.8881,
      "step": 5
    },
    {
      "epoch": 0.018018018018018018,
      "grad_norm": 0.7172915935516357,
      "learning_rate": 6e-05,
      "loss": 1.7194,
      "step": 6
    },
    {
      "epoch": 0.021021021021021023,
      "grad_norm": 0.6998835206031799,
      "learning_rate": 7e-05,
      "loss": 1.6528,
      "step": 7
    },
    {
      "epoch": 0.024024024024024024,
      "grad_norm": 1.0133540630340576,
      "learning_rate": 8e-05,
      "loss": 1.6748,
      "step": 8
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 1.1556763648986816,
      "learning_rate": 9e-05,
      "loss": 1.7526,
      "step": 9
    },
    {
      "epoch": 0.02702702702702703,
      "eval_loss": 1.6583313941955566,
      "eval_runtime": 62.8385,
      "eval_samples_per_second": 4.472,
      "eval_steps_per_second": 0.573,
      "step": 9
    },
    {
      "epoch": 0.03003003003003003,
      "grad_norm": 0.973503589630127,
      "learning_rate": 0.0001,
      "loss": 1.6329,
      "step": 10
    },
    {
      "epoch": 0.03303303303303303,
      "grad_norm": 0.817086398601532,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.5464,
      "step": 11
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 0.7001307606697083,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.49,
      "step": 12
    },
    {
      "epoch": 0.03903903903903904,
      "grad_norm": 0.7110887169837952,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.5194,
      "step": 13
    },
    {
      "epoch": 0.042042042042042045,
      "grad_norm": 0.7024288177490234,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.5195,
      "step": 14
    },
    {
      "epoch": 0.04504504504504504,
      "grad_norm": 0.7325843572616577,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.5147,
      "step": 15
    },
    {
      "epoch": 0.04804804804804805,
      "grad_norm": 0.6620925664901733,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.4085,
      "step": 16
    },
    {
      "epoch": 0.05105105105105105,
      "grad_norm": 0.51695716381073,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.4237,
      "step": 17
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 0.5765568017959595,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.502,
      "step": 18
    },
    {
      "epoch": 0.05405405405405406,
      "eval_loss": 1.4250683784484863,
      "eval_runtime": 62.8113,
      "eval_samples_per_second": 4.474,
      "eval_steps_per_second": 0.573,
      "step": 18
    },
    {
      "epoch": 0.057057057057057055,
      "grad_norm": 0.6175252199172974,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4511,
      "step": 19
    },
    {
      "epoch": 0.06006006006006006,
      "grad_norm": 0.6237648725509644,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.351,
      "step": 20
    },
    {
      "epoch": 0.06306306306306306,
      "grad_norm": 0.6306739449501038,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.3199,
      "step": 21
    },
    {
      "epoch": 0.06606606606606606,
      "grad_norm": 0.49844619631767273,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.3723,
      "step": 22
    },
    {
      "epoch": 0.06906906906906907,
      "grad_norm": 0.5354206562042236,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.3546,
      "step": 23
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 0.5377964377403259,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.3483,
      "step": 24
    },
    {
      "epoch": 0.07507507507507508,
      "grad_norm": 0.5178672075271606,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.2779,
      "step": 25
    },
    {
      "epoch": 0.07807807807807808,
      "grad_norm": 0.5024471282958984,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.2697,
      "step": 26
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 0.5718808770179749,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.2743,
      "step": 27
    },
    {
      "epoch": 0.08108108108108109,
      "eval_loss": 1.3096789121627808,
      "eval_runtime": 62.829,
      "eval_samples_per_second": 4.472,
      "eval_steps_per_second": 0.573,
      "step": 27
    },
    {
      "epoch": 0.08408408408408409,
      "grad_norm": 0.5483112931251526,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2454,
      "step": 28
    },
    {
      "epoch": 0.08708708708708708,
      "grad_norm": 0.5792304873466492,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.2741,
      "step": 29
    },
    {
      "epoch": 0.09009009009009009,
      "grad_norm": 0.5762671828269958,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.2769,
      "step": 30
    },
    {
      "epoch": 0.09309309309309309,
      "grad_norm": 0.5792064070701599,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.2854,
      "step": 31
    },
    {
      "epoch": 0.0960960960960961,
      "grad_norm": 0.5290413498878479,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.242,
      "step": 32
    },
    {
      "epoch": 0.0990990990990991,
      "grad_norm": 0.6523710489273071,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.3281,
      "step": 33
    },
    {
      "epoch": 0.1021021021021021,
      "grad_norm": 0.5404489636421204,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.1963,
      "step": 34
    },
    {
      "epoch": 0.10510510510510511,
      "grad_norm": 0.5534884929656982,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.2266,
      "step": 35
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.6106987595558167,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.2606,
      "step": 36
    },
    {
      "epoch": 0.10810810810810811,
      "eval_loss": 1.221689224243164,
      "eval_runtime": 62.7867,
      "eval_samples_per_second": 4.475,
      "eval_steps_per_second": 0.573,
      "step": 36
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.44786205887794495,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2073,
      "step": 37
    },
    {
      "epoch": 0.11411411411411411,
      "grad_norm": 0.5416382551193237,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.1682,
      "step": 38
    },
    {
      "epoch": 0.11711711711711711,
      "grad_norm": 0.572591245174408,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.2197,
      "step": 39
    },
    {
      "epoch": 0.12012012012012012,
      "grad_norm": 0.5145111680030823,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0935,
      "step": 40
    },
    {
      "epoch": 0.12312312312312312,
      "grad_norm": 0.6535457372665405,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.0762,
      "step": 41
    },
    {
      "epoch": 0.12612612612612611,
      "grad_norm": 0.5444203615188599,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.0495,
      "step": 42
    },
    {
      "epoch": 0.12912912912912913,
      "grad_norm": 0.6166582703590393,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.0792,
      "step": 43
    },
    {
      "epoch": 0.13213213213213212,
      "grad_norm": 0.531032145023346,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.9994,
      "step": 44
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 0.6408705115318298,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.2118,
      "step": 45
    },
    {
      "epoch": 0.13513513513513514,
      "eval_loss": 1.1635631322860718,
      "eval_runtime": 62.7574,
      "eval_samples_per_second": 4.478,
      "eval_steps_per_second": 0.574,
      "step": 45
    },
    {
      "epoch": 0.13813813813813813,
      "grad_norm": 0.5408794283866882,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1765,
      "step": 46
    },
    {
      "epoch": 0.14114114114114115,
      "grad_norm": 0.6319204568862915,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.1065,
      "step": 47
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 0.5713602900505066,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.1523,
      "step": 48
    },
    {
      "epoch": 0.14714714714714713,
      "grad_norm": 0.5445019602775574,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.1104,
      "step": 49
    },
    {
      "epoch": 0.15015015015015015,
      "grad_norm": 0.7082126140594482,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.2276,
      "step": 50
    },
    {
      "epoch": 0.15315315315315314,
      "grad_norm": 0.6700219511985779,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.1085,
      "step": 51
    },
    {
      "epoch": 0.15615615615615616,
      "grad_norm": 0.70674067735672,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.0032,
      "step": 52
    },
    {
      "epoch": 0.15915915915915915,
      "grad_norm": 0.6413066387176514,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.0976,
      "step": 53
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 0.5945645570755005,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.0874,
      "step": 54
    },
    {
      "epoch": 0.16216216216216217,
      "eval_loss": 1.1248000860214233,
      "eval_runtime": 62.8374,
      "eval_samples_per_second": 4.472,
      "eval_steps_per_second": 0.573,
      "step": 54
    },
    {
      "epoch": 0.16516516516516516,
      "grad_norm": 0.5928006172180176,
      "learning_rate": 5e-05,
      "loss": 1.1226,
      "step": 55
    },
    {
      "epoch": 0.16816816816816818,
      "grad_norm": 0.5897536277770996,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.061,
      "step": 56
    },
    {
      "epoch": 0.17117117117117117,
      "grad_norm": 0.6264550089836121,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.0425,
      "step": 57
    },
    {
      "epoch": 0.17417417417417416,
      "grad_norm": 0.5464336276054382,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.0925,
      "step": 58
    },
    {
      "epoch": 0.17717717717717718,
      "grad_norm": 0.5804792642593384,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.1799,
      "step": 59
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 0.6067994832992554,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.0761,
      "step": 60
    },
    {
      "epoch": 0.1831831831831832,
      "grad_norm": 0.5299519896507263,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.0996,
      "step": 61
    },
    {
      "epoch": 0.18618618618618618,
      "grad_norm": 0.7131068706512451,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.0971,
      "step": 62
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 0.5988982915878296,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.0842,
      "step": 63
    },
    {
      "epoch": 0.1891891891891892,
      "eval_loss": 1.098732352256775,
      "eval_runtime": 62.8005,
      "eval_samples_per_second": 4.474,
      "eval_steps_per_second": 0.573,
      "step": 63
    },
    {
      "epoch": 0.1921921921921922,
      "grad_norm": 0.7022519111633301,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.046,
      "step": 64
    },
    {
      "epoch": 0.19519519519519518,
      "grad_norm": 0.5209968686103821,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.013,
      "step": 65
    },
    {
      "epoch": 0.1981981981981982,
      "grad_norm": 0.6534311771392822,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.0596,
      "step": 66
    },
    {
      "epoch": 0.2012012012012012,
      "grad_norm": 0.6855350136756897,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.1311,
      "step": 67
    },
    {
      "epoch": 0.2042042042042042,
      "grad_norm": 0.5221145749092102,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.0387,
      "step": 68
    },
    {
      "epoch": 0.2072072072072072,
      "grad_norm": 0.48642462491989136,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.0218,
      "step": 69
    },
    {
      "epoch": 0.21021021021021022,
      "grad_norm": 0.6832244396209717,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.9763,
      "step": 70
    },
    {
      "epoch": 0.2132132132132132,
      "grad_norm": 0.5838537812232971,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.0369,
      "step": 71
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.579451322555542,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.9797,
      "step": 72
    },
    {
      "epoch": 0.21621621621621623,
      "eval_loss": 1.0829377174377441,
      "eval_runtime": 63.4887,
      "eval_samples_per_second": 4.426,
      "eval_steps_per_second": 0.567,
      "step": 72
    },
    {
      "epoch": 0.21921921921921922,
      "grad_norm": 0.688620924949646,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0522,
      "step": 73
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.5413029193878174,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.0064,
      "step": 74
    },
    {
      "epoch": 0.22522522522522523,
      "grad_norm": 0.5388117432594299,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.0725,
      "step": 75
    },
    {
      "epoch": 0.22822822822822822,
      "grad_norm": 0.5668699145317078,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.0711,
      "step": 76
    },
    {
      "epoch": 0.23123123123123124,
      "grad_norm": 0.5445249676704407,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.0106,
      "step": 77
    },
    {
      "epoch": 0.23423423423423423,
      "grad_norm": 0.6580765843391418,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.08,
      "step": 78
    },
    {
      "epoch": 0.23723723723723725,
      "grad_norm": 0.5185084939002991,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.0145,
      "step": 79
    },
    {
      "epoch": 0.24024024024024024,
      "grad_norm": 0.6230930089950562,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.0017,
      "step": 80
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 0.5382445454597473,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.0962,
      "step": 81
    },
    {
      "epoch": 0.24324324324324326,
      "eval_loss": 1.0725353956222534,
      "eval_runtime": 62.8805,
      "eval_samples_per_second": 4.469,
      "eval_steps_per_second": 0.573,
      "step": 81
    },
    {
      "epoch": 0.24624624624624625,
      "grad_norm": 0.5744390487670898,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.0982,
      "step": 82
    },
    {
      "epoch": 0.24924924924924924,
      "grad_norm": 0.5682293176651001,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.0377,
      "step": 83
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": 0.5965850949287415,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.0009,
      "step": 84
    },
    {
      "epoch": 0.2552552552552553,
      "grad_norm": 0.47231999039649963,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.0434,
      "step": 85
    },
    {
      "epoch": 0.25825825825825827,
      "grad_norm": 0.5315771698951721,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.9827,
      "step": 86
    },
    {
      "epoch": 0.26126126126126126,
      "grad_norm": 0.5202770829200745,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.0421,
      "step": 87
    },
    {
      "epoch": 0.26426426426426425,
      "grad_norm": 0.551384449005127,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.1419,
      "step": 88
    },
    {
      "epoch": 0.2672672672672673,
      "grad_norm": 0.48965591192245483,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.0447,
      "step": 89
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 0.5531151294708252,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.0893,
      "step": 90
    },
    {
      "epoch": 0.2702702702702703,
      "eval_loss": 1.0678226947784424,
      "eval_runtime": 62.7776,
      "eval_samples_per_second": 4.476,
      "eval_steps_per_second": 0.573,
      "step": 90
    },
    {
      "epoch": 0.2732732732732733,
      "grad_norm": 0.4997876286506653,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.0278,
      "step": 91
    },
    {
      "epoch": 0.27627627627627627,
      "grad_norm": 0.5054656267166138,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.0288,
      "step": 92
    },
    {
      "epoch": 0.27927927927927926,
      "grad_norm": 0.5292591452598572,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.9494,
      "step": 93
    },
    {
      "epoch": 0.2822822822822823,
      "grad_norm": 0.47419047355651855,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.9839,
      "step": 94
    },
    {
      "epoch": 0.2852852852852853,
      "grad_norm": 0.49080803990364075,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.0356,
      "step": 95
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 0.5078819990158081,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.1231,
      "step": 96
    },
    {
      "epoch": 0.2912912912912913,
      "grad_norm": 0.4944559931755066,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.0759,
      "step": 97
    },
    {
      "epoch": 0.29429429429429427,
      "grad_norm": 0.4932954013347626,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.0656,
      "step": 98
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 0.4978138208389282,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.0526,
      "step": 99
    },
    {
      "epoch": 0.2972972972972973,
      "eval_loss": 1.066880702972412,
      "eval_runtime": 62.8204,
      "eval_samples_per_second": 4.473,
      "eval_steps_per_second": 0.573,
      "step": 99
    },
    {
      "epoch": 0.3003003003003003,
      "grad_norm": 0.47974127531051636,
      "learning_rate": 0.0,
      "loss": 1.0622,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.483774567120896e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}