{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.37593984962406013,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005012531328320802,
      "grad_norm": 20.869874954223633,
      "learning_rate": 1e-05,
      "loss": 20.1344,
      "step": 1
    },
    {
      "epoch": 0.005012531328320802,
      "eval_loss": 10.39857006072998,
      "eval_runtime": 28.3062,
      "eval_samples_per_second": 5.935,
      "eval_steps_per_second": 0.742,
      "step": 1
    },
    {
      "epoch": 0.010025062656641603,
      "grad_norm": 20.313007354736328,
      "learning_rate": 2e-05,
      "loss": 22.4254,
      "step": 2
    },
    {
      "epoch": 0.015037593984962405,
      "grad_norm": 15.272883415222168,
      "learning_rate": 3e-05,
      "loss": 20.2144,
      "step": 3
    },
    {
      "epoch": 0.020050125313283207,
      "grad_norm": 22.251083374023438,
      "learning_rate": 4e-05,
      "loss": 22.7775,
      "step": 4
    },
    {
      "epoch": 0.02506265664160401,
      "grad_norm": 18.530513763427734,
      "learning_rate": 5e-05,
      "loss": 19.4961,
      "step": 5
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 20.28190803527832,
      "learning_rate": 6e-05,
      "loss": 21.2481,
      "step": 6
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 20.61719512939453,
      "learning_rate": 7e-05,
      "loss": 20.0061,
      "step": 7
    },
    {
      "epoch": 0.040100250626566414,
      "grad_norm": 24.68893814086914,
      "learning_rate": 8e-05,
      "loss": 17.2958,
      "step": 8
    },
    {
      "epoch": 0.045112781954887216,
      "grad_norm": 21.156003952026367,
      "learning_rate": 9e-05,
      "loss": 16.7236,
      "step": 9
    },
    {
      "epoch": 0.045112781954887216,
      "eval_loss": 8.052587509155273,
      "eval_runtime": 28.367,
      "eval_samples_per_second": 5.922,
      "eval_steps_per_second": 0.74,
      "step": 9
    },
    {
      "epoch": 0.05012531328320802,
      "grad_norm": 22.940866470336914,
      "learning_rate": 0.0001,
      "loss": 15.396,
      "step": 10
    },
    {
      "epoch": 0.05513784461152882,
      "grad_norm": 28.320890426635742,
      "learning_rate": 9.99695413509548e-05,
      "loss": 17.2894,
      "step": 11
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 25.803590774536133,
      "learning_rate": 9.987820251299122e-05,
      "loss": 12.782,
      "step": 12
    },
    {
      "epoch": 0.06516290726817042,
      "grad_norm": 22.771900177001953,
      "learning_rate": 9.972609476841367e-05,
      "loss": 11.7643,
      "step": 13
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 24.09734344482422,
      "learning_rate": 9.951340343707852e-05,
      "loss": 8.7052,
      "step": 14
    },
    {
      "epoch": 0.07518796992481203,
      "grad_norm": 17.444034576416016,
      "learning_rate": 9.924038765061042e-05,
      "loss": 5.8894,
      "step": 15
    },
    {
      "epoch": 0.08020050125313283,
      "grad_norm": 20.63741111755371,
      "learning_rate": 9.890738003669029e-05,
      "loss": 5.2684,
      "step": 16
    },
    {
      "epoch": 0.08521303258145363,
      "grad_norm": 17.476707458496094,
      "learning_rate": 9.851478631379982e-05,
      "loss": 5.7511,
      "step": 17
    },
    {
      "epoch": 0.09022556390977443,
      "grad_norm": 12.589031219482422,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.3076,
      "step": 18
    },
    {
      "epoch": 0.09022556390977443,
      "eval_loss": 1.4214398860931396,
      "eval_runtime": 28.3828,
      "eval_samples_per_second": 5.919,
      "eval_steps_per_second": 0.74,
      "step": 18
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 12.787721633911133,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.5447,
      "step": 19
    },
    {
      "epoch": 0.10025062656641603,
      "grad_norm": 13.530546188354492,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.2347,
      "step": 20
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 15.857293128967285,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.0769,
      "step": 21
    },
    {
      "epoch": 0.11027568922305764,
      "grad_norm": 11.907310485839844,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.9489,
      "step": 22
    },
    {
      "epoch": 0.11528822055137844,
      "grad_norm": 7.293683052062988,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.6826,
      "step": 23
    },
    {
      "epoch": 0.12030075187969924,
      "grad_norm": 7.3750128746032715,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.6393,
      "step": 24
    },
    {
      "epoch": 0.12531328320802004,
      "grad_norm": 4.739354133605957,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5386,
      "step": 25
    },
    {
      "epoch": 0.13032581453634084,
      "grad_norm": 2.824436664581299,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.4438,
      "step": 26
    },
    {
      "epoch": 0.13533834586466165,
      "grad_norm": 3.13669753074646,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.3126,
      "step": 27
    },
    {
      "epoch": 0.13533834586466165,
      "eval_loss": 0.7911556959152222,
      "eval_runtime": 28.3428,
      "eval_samples_per_second": 5.927,
      "eval_steps_per_second": 0.741,
      "step": 27
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 3.12079119682312,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2441,
      "step": 28
    },
    {
      "epoch": 0.14536340852130325,
      "grad_norm": 5.930524826049805,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.6673,
      "step": 29
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 9.300253868103027,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.6697,
      "step": 30
    },
    {
      "epoch": 0.15538847117794485,
      "grad_norm": 4.563720226287842,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.6332,
      "step": 31
    },
    {
      "epoch": 0.16040100250626566,
      "grad_norm": 2.8544657230377197,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1952,
      "step": 32
    },
    {
      "epoch": 0.16541353383458646,
      "grad_norm": 2.8571174144744873,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.4034,
      "step": 33
    },
    {
      "epoch": 0.17042606516290726,
      "grad_norm": 1.2488484382629395,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.3455,
      "step": 34
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 2.6949751377105713,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.4473,
      "step": 35
    },
    {
      "epoch": 0.18045112781954886,
      "grad_norm": 2.7027854919433594,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.4684,
      "step": 36
    },
    {
      "epoch": 0.18045112781954886,
      "eval_loss": 0.6932310461997986,
      "eval_runtime": 28.3344,
      "eval_samples_per_second": 5.929,
      "eval_steps_per_second": 0.741,
      "step": 36
    },
    {
      "epoch": 0.18546365914786966,
      "grad_norm": 2.977766990661621,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.4411,
      "step": 37
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 4.639328479766846,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.4076,
      "step": 38
    },
    {
      "epoch": 0.19548872180451127,
      "grad_norm": 2.0679614543914795,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.3722,
      "step": 39
    },
    {
      "epoch": 0.20050125313283207,
      "grad_norm": 3.201908826828003,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4205,
      "step": 40
    },
    {
      "epoch": 0.20551378446115287,
      "grad_norm": 4.107055187225342,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.4506,
      "step": 41
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.4563536643981934,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.3362,
      "step": 42
    },
    {
      "epoch": 0.21553884711779447,
      "grad_norm": 2.039797306060791,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.4047,
      "step": 43
    },
    {
      "epoch": 0.22055137844611528,
      "grad_norm": 10.926207542419434,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.7363,
      "step": 44
    },
    {
      "epoch": 0.22556390977443608,
      "grad_norm": 3.743892192840576,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5538,
      "step": 45
    },
    {
      "epoch": 0.22556390977443608,
      "eval_loss": 0.7266060709953308,
      "eval_runtime": 28.3355,
      "eval_samples_per_second": 5.929,
      "eval_steps_per_second": 0.741,
      "step": 45
    },
    {
      "epoch": 0.23057644110275688,
      "grad_norm": 3.3518729209899902,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5224,
      "step": 46
    },
    {
      "epoch": 0.23558897243107768,
      "grad_norm": 2.9565675258636475,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.4815,
      "step": 47
    },
    {
      "epoch": 0.24060150375939848,
      "grad_norm": 2.0785973072052,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.382,
      "step": 48
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 2.082721710205078,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.4032,
      "step": 49
    },
    {
      "epoch": 0.2506265664160401,
      "grad_norm": 1.7393074035644531,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.3792,
      "step": 50
    },
    {
      "epoch": 0.2556390977443609,
      "grad_norm": 1.3042017221450806,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.3079,
      "step": 51
    },
    {
      "epoch": 0.2606516290726817,
      "grad_norm": 2.5631418228149414,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.2139,
      "step": 52
    },
    {
      "epoch": 0.2656641604010025,
      "grad_norm": 1.2268803119659424,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.2679,
      "step": 53
    },
    {
      "epoch": 0.2706766917293233,
      "grad_norm": 2.560192584991455,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.3228,
      "step": 54
    },
    {
      "epoch": 0.2706766917293233,
      "eval_loss": 0.734089195728302,
      "eval_runtime": 28.3315,
      "eval_samples_per_second": 5.93,
      "eval_steps_per_second": 0.741,
      "step": 54
    },
    {
      "epoch": 0.2756892230576441,
      "grad_norm": 1.112692952156067,
      "learning_rate": 5e-05,
      "loss": 1.1927,
      "step": 55
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 3.5040154457092285,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.6805,
      "step": 56
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.8913439512252808,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.2348,
      "step": 57
    },
    {
      "epoch": 0.2907268170426065,
      "grad_norm": 3.6960103511810303,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.7078,
      "step": 58
    },
    {
      "epoch": 0.2957393483709273,
      "grad_norm": 3.0150368213653564,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.5443,
      "step": 59
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 2.5609323978424072,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.4539,
      "step": 60
    },
    {
      "epoch": 0.3057644110275689,
      "grad_norm": 2.451897382736206,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.5173,
      "step": 61
    },
    {
      "epoch": 0.3107769423558897,
      "grad_norm": 2.140015125274658,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.4675,
      "step": 62
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 2.0622689723968506,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.345,
      "step": 63
    },
    {
      "epoch": 0.3157894736842105,
      "eval_loss": 0.6988301873207092,
      "eval_runtime": 28.3304,
      "eval_samples_per_second": 5.93,
      "eval_steps_per_second": 0.741,
      "step": 63
    },
    {
      "epoch": 0.3208020050125313,
      "grad_norm": 3.642866373062134,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.4744,
      "step": 64
    },
    {
      "epoch": 0.3258145363408521,
      "grad_norm": 1.6694496870040894,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.445,
      "step": 65
    },
    {
      "epoch": 0.3308270676691729,
      "grad_norm": 2.037517547607422,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.4296,
      "step": 66
    },
    {
      "epoch": 0.3358395989974937,
      "grad_norm": 1.9167176485061646,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.3653,
      "step": 67
    },
    {
      "epoch": 0.3408521303258145,
      "grad_norm": 1.5640507936477661,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.3799,
      "step": 68
    },
    {
      "epoch": 0.3458646616541353,
      "grad_norm": 1.5936436653137207,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.3459,
      "step": 69
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 1.5570849180221558,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.3129,
      "step": 70
    },
    {
      "epoch": 0.3558897243107769,
      "grad_norm": 1.6648975610733032,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.2919,
      "step": 71
    },
    {
      "epoch": 0.3609022556390977,
      "grad_norm": 1.4776012897491455,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.4474,
      "step": 72
    },
    {
      "epoch": 0.3609022556390977,
      "eval_loss": 0.689708411693573,
      "eval_runtime": 28.3408,
      "eval_samples_per_second": 5.928,
      "eval_steps_per_second": 0.741,
      "step": 72
    },
    {
      "epoch": 0.3659147869674185,
      "grad_norm": 9.771589279174805,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.7794,
      "step": 73
    },
    {
      "epoch": 0.37092731829573933,
      "grad_norm": 2.208794355392456,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.4788,
      "step": 74
    },
    {
      "epoch": 0.37593984962406013,
      "grad_norm": 2.5760669708251953,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.5225,
      "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": 8.887031545882214e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}