{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14720314033366044,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001962708537782139,
      "grad_norm": 20.81890106201172,
      "learning_rate": 1e-05,
      "loss": 9.4225,
      "step": 1
    },
    {
      "epoch": 0.001962708537782139,
      "eval_loss": 8.840479850769043,
      "eval_runtime": 52.2007,
      "eval_samples_per_second": 8.218,
      "eval_steps_per_second": 1.034,
      "step": 1
    },
    {
      "epoch": 0.003925417075564278,
      "grad_norm": 16.247425079345703,
      "learning_rate": 2e-05,
      "loss": 8.8323,
      "step": 2
    },
    {
      "epoch": 0.005888125613346418,
      "grad_norm": 17.129257202148438,
      "learning_rate": 3e-05,
      "loss": 9.7792,
      "step": 3
    },
    {
      "epoch": 0.007850834151128557,
      "grad_norm": 15.433220863342285,
      "learning_rate": 4e-05,
      "loss": 8.5797,
      "step": 4
    },
    {
      "epoch": 0.009813542688910697,
      "grad_norm": 13.5704927444458,
      "learning_rate": 5e-05,
      "loss": 7.7854,
      "step": 5
    },
    {
      "epoch": 0.011776251226692836,
      "grad_norm": 14.451172828674316,
      "learning_rate": 6e-05,
      "loss": 7.6687,
      "step": 6
    },
    {
      "epoch": 0.013738959764474975,
      "grad_norm": 17.657636642456055,
      "learning_rate": 7e-05,
      "loss": 6.804,
      "step": 7
    },
    {
      "epoch": 0.015701668302257114,
      "grad_norm": 25.692893981933594,
      "learning_rate": 8e-05,
      "loss": 5.6844,
      "step": 8
    },
    {
      "epoch": 0.017664376840039256,
      "grad_norm": 16.068389892578125,
      "learning_rate": 9e-05,
      "loss": 4.5304,
      "step": 9
    },
    {
      "epoch": 0.017664376840039256,
      "eval_loss": 3.219860076904297,
      "eval_runtime": 51.8093,
      "eval_samples_per_second": 8.28,
      "eval_steps_per_second": 1.042,
      "step": 9
    },
    {
      "epoch": 0.019627085377821395,
      "grad_norm": 13.496415138244629,
      "learning_rate": 0.0001,
      "loss": 3.1004,
      "step": 10
    },
    {
      "epoch": 0.021589793915603533,
      "grad_norm": 11.793410301208496,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.1632,
      "step": 11
    },
    {
      "epoch": 0.023552502453385672,
      "grad_norm": 12.152811050415039,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.0349,
      "step": 12
    },
    {
      "epoch": 0.02551521099116781,
      "grad_norm": 7.9459919929504395,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.422,
      "step": 13
    },
    {
      "epoch": 0.02747791952894995,
      "grad_norm": 2.51922869682312,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.14,
      "step": 14
    },
    {
      "epoch": 0.029440628066732092,
      "grad_norm": 10.466949462890625,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.3396,
      "step": 15
    },
    {
      "epoch": 0.03140333660451423,
      "grad_norm": 4.913854122161865,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2676,
      "step": 16
    },
    {
      "epoch": 0.033366045142296366,
      "grad_norm": 3.1969945430755615,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.151,
      "step": 17
    },
    {
      "epoch": 0.03532875368007851,
      "grad_norm": 2.624812602996826,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1735,
      "step": 18
    },
    {
      "epoch": 0.03532875368007851,
      "eval_loss": 0.1688159704208374,
      "eval_runtime": 51.8215,
      "eval_samples_per_second": 8.278,
      "eval_steps_per_second": 1.042,
      "step": 18
    },
    {
      "epoch": 0.03729146221786065,
      "grad_norm": 4.066593647003174,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1576,
      "step": 19
    },
    {
      "epoch": 0.03925417075564279,
      "grad_norm": 2.2764923572540283,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0787,
      "step": 20
    },
    {
      "epoch": 0.04121687929342493,
      "grad_norm": 2.3905651569366455,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.1805,
      "step": 21
    },
    {
      "epoch": 0.04317958783120707,
      "grad_norm": 1.5698174238204956,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.146,
      "step": 22
    },
    {
      "epoch": 0.045142296368989206,
      "grad_norm": 1.9719736576080322,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1639,
      "step": 23
    },
    {
      "epoch": 0.047105004906771344,
      "grad_norm": 1.390785813331604,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.1304,
      "step": 24
    },
    {
      "epoch": 0.04906771344455348,
      "grad_norm": 0.9126207232475281,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.156,
      "step": 25
    },
    {
      "epoch": 0.05103042198233562,
      "grad_norm": 2.437849283218384,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1155,
      "step": 26
    },
    {
      "epoch": 0.05299313052011776,
      "grad_norm": 0.4617787003517151,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.123,
      "step": 27
    },
    {
      "epoch": 0.05299313052011776,
      "eval_loss": 0.1673201620578766,
      "eval_runtime": 51.8705,
      "eval_samples_per_second": 8.271,
      "eval_steps_per_second": 1.041,
      "step": 27
    },
    {
      "epoch": 0.0549558390578999,
      "grad_norm": 1.0778998136520386,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1533,
      "step": 28
    },
    {
      "epoch": 0.05691854759568204,
      "grad_norm": 2.6037826538085938,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.2361,
      "step": 29
    },
    {
      "epoch": 0.058881256133464184,
      "grad_norm": 1.1255934238433838,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.133,
      "step": 30
    },
    {
      "epoch": 0.06084396467124632,
      "grad_norm": 0.5252030491828918,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0579,
      "step": 31
    },
    {
      "epoch": 0.06280667320902845,
      "grad_norm": 0.34210190176963806,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0365,
      "step": 32
    },
    {
      "epoch": 0.0647693817468106,
      "grad_norm": 4.503533840179443,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.3934,
      "step": 33
    },
    {
      "epoch": 0.06673209028459273,
      "grad_norm": 1.0601013898849487,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1153,
      "step": 34
    },
    {
      "epoch": 0.06869479882237488,
      "grad_norm": 2.3702797889709473,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.2298,
      "step": 35
    },
    {
      "epoch": 0.07065750736015702,
      "grad_norm": 0.9476222991943359,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1219,
      "step": 36
    },
    {
      "epoch": 0.07065750736015702,
      "eval_loss": 0.22275131940841675,
      "eval_runtime": 51.8318,
      "eval_samples_per_second": 8.277,
      "eval_steps_per_second": 1.042,
      "step": 36
    },
    {
      "epoch": 0.07262021589793916,
      "grad_norm": 4.955600261688232,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1983,
      "step": 37
    },
    {
      "epoch": 0.0745829244357213,
      "grad_norm": 5.591402053833008,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.2904,
      "step": 38
    },
    {
      "epoch": 0.07654563297350343,
      "grad_norm": 5.275705337524414,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.232,
      "step": 39
    },
    {
      "epoch": 0.07850834151128558,
      "grad_norm": 1.338252305984497,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1405,
      "step": 40
    },
    {
      "epoch": 0.08047105004906771,
      "grad_norm": 1.6821722984313965,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.1187,
      "step": 41
    },
    {
      "epoch": 0.08243375858684986,
      "grad_norm": 1.2487791776657104,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.1329,
      "step": 42
    },
    {
      "epoch": 0.08439646712463199,
      "grad_norm": 2.20461368560791,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.1637,
      "step": 43
    },
    {
      "epoch": 0.08635917566241413,
      "grad_norm": 0.9710573554039001,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.109,
      "step": 44
    },
    {
      "epoch": 0.08832188420019627,
      "grad_norm": 0.7090091705322266,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0919,
      "step": 45
    },
    {
      "epoch": 0.08832188420019627,
      "eval_loss": 0.11113426089286804,
      "eval_runtime": 51.8528,
      "eval_samples_per_second": 8.273,
      "eval_steps_per_second": 1.041,
      "step": 45
    },
    {
      "epoch": 0.09028459273797841,
      "grad_norm": 0.7625433206558228,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1295,
      "step": 46
    },
    {
      "epoch": 0.09224730127576054,
      "grad_norm": 1.3009706735610962,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.09,
      "step": 47
    },
    {
      "epoch": 0.09421000981354269,
      "grad_norm": 0.7470637559890747,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0984,
      "step": 48
    },
    {
      "epoch": 0.09617271835132483,
      "grad_norm": 0.5593076348304749,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0986,
      "step": 49
    },
    {
      "epoch": 0.09813542688910697,
      "grad_norm": 0.45251327753067017,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0453,
      "step": 50
    },
    {
      "epoch": 0.10009813542688911,
      "grad_norm": 0.6971419453620911,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0857,
      "step": 51
    },
    {
      "epoch": 0.10206084396467124,
      "grad_norm": 1.4667972326278687,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.1401,
      "step": 52
    },
    {
      "epoch": 0.10402355250245339,
      "grad_norm": 0.5915104150772095,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0572,
      "step": 53
    },
    {
      "epoch": 0.10598626104023552,
      "grad_norm": 0.9713770747184753,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0795,
      "step": 54
    },
    {
      "epoch": 0.10598626104023552,
      "eval_loss": 0.07904753088951111,
      "eval_runtime": 51.8493,
      "eval_samples_per_second": 8.274,
      "eval_steps_per_second": 1.041,
      "step": 54
    },
    {
      "epoch": 0.10794896957801767,
      "grad_norm": 0.7951352596282959,
      "learning_rate": 5e-05,
      "loss": 0.0704,
      "step": 55
    },
    {
      "epoch": 0.1099116781157998,
      "grad_norm": 2.8656163215637207,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.1262,
      "step": 56
    },
    {
      "epoch": 0.11187438665358194,
      "grad_norm": 0.786283016204834,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0959,
      "step": 57
    },
    {
      "epoch": 0.11383709519136408,
      "grad_norm": 0.9875638484954834,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0507,
      "step": 58
    },
    {
      "epoch": 0.11579980372914622,
      "grad_norm": 0.8965640068054199,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0643,
      "step": 59
    },
    {
      "epoch": 0.11776251226692837,
      "grad_norm": 0.4218522608280182,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0271,
      "step": 60
    },
    {
      "epoch": 0.1197252208047105,
      "grad_norm": 1.05173659324646,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0416,
      "step": 61
    },
    {
      "epoch": 0.12168792934249265,
      "grad_norm": 0.9266757965087891,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0968,
      "step": 62
    },
    {
      "epoch": 0.12365063788027478,
      "grad_norm": 2.450507164001465,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1366,
      "step": 63
    },
    {
      "epoch": 0.12365063788027478,
      "eval_loss": 0.06722546368837357,
      "eval_runtime": 51.8533,
      "eval_samples_per_second": 8.273,
      "eval_steps_per_second": 1.041,
      "step": 63
    },
    {
      "epoch": 0.1256133464180569,
      "grad_norm": 0.7940893769264221,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0558,
      "step": 64
    },
    {
      "epoch": 0.12757605495583907,
      "grad_norm": 1.0147578716278076,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0655,
      "step": 65
    },
    {
      "epoch": 0.1295387634936212,
      "grad_norm": 0.7361927032470703,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0467,
      "step": 66
    },
    {
      "epoch": 0.13150147203140333,
      "grad_norm": 0.8373685479164124,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0838,
      "step": 67
    },
    {
      "epoch": 0.13346418056918546,
      "grad_norm": 0.41943085193634033,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0278,
      "step": 68
    },
    {
      "epoch": 0.13542688910696762,
      "grad_norm": 0.35588350892066956,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.025,
      "step": 69
    },
    {
      "epoch": 0.13738959764474976,
      "grad_norm": 0.7751619219779968,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0516,
      "step": 70
    },
    {
      "epoch": 0.1393523061825319,
      "grad_norm": 0.735934853553772,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0708,
      "step": 71
    },
    {
      "epoch": 0.14131501472031405,
      "grad_norm": 0.5799421668052673,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0559,
      "step": 72
    },
    {
      "epoch": 0.14131501472031405,
      "eval_loss": 0.06862723082304001,
      "eval_runtime": 51.8315,
      "eval_samples_per_second": 8.277,
      "eval_steps_per_second": 1.042,
      "step": 72
    },
    {
      "epoch": 0.14327772325809618,
      "grad_norm": 1.0606155395507812,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0798,
      "step": 73
    },
    {
      "epoch": 0.1452404317958783,
      "grad_norm": 0.8018274903297424,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0536,
      "step": 74
    },
    {
      "epoch": 0.14720314033366044,
      "grad_norm": 0.9818136692047119,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.076,
      "step": 75
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.56415764660224e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}