{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2306805074971165,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00461361014994233,
      "grad_norm": 72.1630630493164,
      "learning_rate": 2e-05,
      "loss": 13.1626,
      "step": 1
    },
    {
      "epoch": 0.00461361014994233,
      "eval_loss": 13.253607749938965,
      "eval_runtime": 17.4993,
      "eval_samples_per_second": 20.858,
      "eval_steps_per_second": 5.257,
      "step": 1
    },
    {
      "epoch": 0.00922722029988466,
      "grad_norm": 71.25870513916016,
      "learning_rate": 4e-05,
      "loss": 13.2979,
      "step": 2
    },
    {
      "epoch": 0.01384083044982699,
      "grad_norm": 69.70768737792969,
      "learning_rate": 6e-05,
      "loss": 12.9017,
      "step": 3
    },
    {
      "epoch": 0.01845444059976932,
      "grad_norm": 73.10421752929688,
      "learning_rate": 8e-05,
      "loss": 12.0195,
      "step": 4
    },
    {
      "epoch": 0.02306805074971165,
      "grad_norm": 69.51506805419922,
      "learning_rate": 0.0001,
      "loss": 9.6283,
      "step": 5
    },
    {
      "epoch": 0.02306805074971165,
      "eval_loss": 7.585133075714111,
      "eval_runtime": 17.0118,
      "eval_samples_per_second": 21.456,
      "eval_steps_per_second": 5.408,
      "step": 5
    },
    {
      "epoch": 0.02768166089965398,
      "grad_norm": 90.7542953491211,
      "learning_rate": 0.00012,
      "loss": 7.6748,
      "step": 6
    },
    {
      "epoch": 0.03229527104959631,
      "grad_norm": 49.42520523071289,
      "learning_rate": 0.00014,
      "loss": 5.5897,
      "step": 7
    },
    {
      "epoch": 0.03690888119953864,
      "grad_norm": 49.269920349121094,
      "learning_rate": 0.00016,
      "loss": 2.9578,
      "step": 8
    },
    {
      "epoch": 0.04152249134948097,
      "grad_norm": 54.2545280456543,
      "learning_rate": 0.00018,
      "loss": 1.9525,
      "step": 9
    },
    {
      "epoch": 0.0461361014994233,
      "grad_norm": 24.106416702270508,
      "learning_rate": 0.0002,
      "loss": 0.7472,
      "step": 10
    },
    {
      "epoch": 0.0461361014994233,
      "eval_loss": 0.12861251831054688,
      "eval_runtime": 17.1371,
      "eval_samples_per_second": 21.299,
      "eval_steps_per_second": 5.368,
      "step": 10
    },
    {
      "epoch": 0.05074971164936563,
      "grad_norm": 4.841038227081299,
      "learning_rate": 0.0001996917333733128,
      "loss": 0.0818,
      "step": 11
    },
    {
      "epoch": 0.05536332179930796,
      "grad_norm": 11.173221588134766,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.0946,
      "step": 12
    },
    {
      "epoch": 0.05997693194925029,
      "grad_norm": 0.47547468543052673,
      "learning_rate": 0.00019723699203976766,
      "loss": 0.0066,
      "step": 13
    },
    {
      "epoch": 0.06459054209919261,
      "grad_norm": 0.24113191664218903,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0018,
      "step": 14
    },
    {
      "epoch": 0.06920415224913495,
      "grad_norm": 6.167793273925781,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0264,
      "step": 15
    },
    {
      "epoch": 0.06920415224913495,
      "eval_loss": 0.0003013078821823001,
      "eval_runtime": 17.0346,
      "eval_samples_per_second": 21.427,
      "eval_steps_per_second": 5.401,
      "step": 15
    },
    {
      "epoch": 0.07381776239907728,
      "grad_norm": 0.018830670043826103,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.0003,
      "step": 16
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 0.011459613218903542,
      "learning_rate": 0.00018526401643540922,
      "loss": 0.0002,
      "step": 17
    },
    {
      "epoch": 0.08304498269896193,
      "grad_norm": 0.00807697232812643,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0001,
      "step": 18
    },
    {
      "epoch": 0.08765859284890427,
      "grad_norm": 0.041298918426036835,
      "learning_rate": 0.0001760405965600031,
      "loss": 0.0003,
      "step": 19
    },
    {
      "epoch": 0.0922722029988466,
      "grad_norm": 0.010275812819600105,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0002,
      "step": 20
    },
    {
      "epoch": 0.0922722029988466,
      "eval_loss": 0.00012042788875987753,
      "eval_runtime": 17.0576,
      "eval_samples_per_second": 21.398,
      "eval_steps_per_second": 5.393,
      "step": 20
    },
    {
      "epoch": 0.09688581314878893,
      "grad_norm": 0.006219527684152126,
      "learning_rate": 0.00016494480483301836,
      "loss": 0.0001,
      "step": 21
    },
    {
      "epoch": 0.10149942329873125,
      "grad_norm": 0.004248109646141529,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.0001,
      "step": 22
    },
    {
      "epoch": 0.1061130334486736,
      "grad_norm": 0.004604709800332785,
      "learning_rate": 0.0001522498564715949,
      "loss": 0.0001,
      "step": 23
    },
    {
      "epoch": 0.11072664359861592,
      "grad_norm": 0.003502492792904377,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.0001,
      "step": 24
    },
    {
      "epoch": 0.11534025374855825,
      "grad_norm": 0.0035225688479840755,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0001,
      "step": 25
    },
    {
      "epoch": 0.11534025374855825,
      "eval_loss": 8.34934544400312e-05,
      "eval_runtime": 17.0525,
      "eval_samples_per_second": 21.404,
      "eval_steps_per_second": 5.395,
      "step": 25
    },
    {
      "epoch": 0.11995386389850057,
      "grad_norm": 0.003679639892652631,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0001,
      "step": 26
    },
    {
      "epoch": 0.1245674740484429,
      "grad_norm": 0.003532982897013426,
      "learning_rate": 0.00012334453638559057,
      "loss": 0.0001,
      "step": 27
    },
    {
      "epoch": 0.12918108419838523,
      "grad_norm": 0.0030222227796912193,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.0001,
      "step": 28
    },
    {
      "epoch": 0.13379469434832755,
      "grad_norm": 0.0029425821267068386,
      "learning_rate": 0.0001078459095727845,
      "loss": 0.0001,
      "step": 29
    },
    {
      "epoch": 0.1384083044982699,
      "grad_norm": 0.0026237634010612965,
      "learning_rate": 0.0001,
      "loss": 0.0001,
      "step": 30
    },
    {
      "epoch": 0.1384083044982699,
      "eval_loss": 6.395620584953576e-05,
      "eval_runtime": 17.1212,
      "eval_samples_per_second": 21.319,
      "eval_steps_per_second": 5.373,
      "step": 30
    },
    {
      "epoch": 0.14302191464821223,
      "grad_norm": 0.0022466089576482773,
      "learning_rate": 9.215409042721552e-05,
      "loss": 0.0001,
      "step": 31
    },
    {
      "epoch": 0.14763552479815456,
      "grad_norm": 0.002309126313775778,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0001,
      "step": 32
    },
    {
      "epoch": 0.1522491349480969,
      "grad_norm": 0.002271483652293682,
      "learning_rate": 7.66554636144095e-05,
      "loss": 0.0001,
      "step": 33
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 0.003420888213440776,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0001,
      "step": 34
    },
    {
      "epoch": 0.16147635524798154,
      "grad_norm": 0.001877190312370658,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.0001,
      "step": 35
    },
    {
      "epoch": 0.16147635524798154,
      "eval_loss": 5.225171844358556e-05,
      "eval_runtime": 17.0508,
      "eval_samples_per_second": 21.407,
      "eval_steps_per_second": 5.396,
      "step": 35
    },
    {
      "epoch": 0.16608996539792387,
      "grad_norm": 0.0021744396071881056,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.0001,
      "step": 36
    },
    {
      "epoch": 0.1707035755478662,
      "grad_norm": 0.0019249645993113518,
      "learning_rate": 4.7750143528405126e-05,
      "loss": 0.0001,
      "step": 37
    },
    {
      "epoch": 0.17531718569780855,
      "grad_norm": 0.001645832322537899,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.17993079584775087,
      "grad_norm": 0.0016277554677799344,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.1845444059976932,
      "grad_norm": 0.0032778542954474688,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0001,
      "step": 40
    },
    {
      "epoch": 0.1845444059976932,
      "eval_loss": 4.700600038631819e-05,
      "eval_runtime": 17.1053,
      "eval_samples_per_second": 21.338,
      "eval_steps_per_second": 5.378,
      "step": 40
    },
    {
      "epoch": 0.18915801614763553,
      "grad_norm": 0.0014399398351088166,
      "learning_rate": 2.3959403439996907e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.19377162629757785,
      "grad_norm": 0.0013151218881830573,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.19838523644752018,
      "grad_norm": 0.001369544188492,
      "learning_rate": 1.4735983564590783e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.2029988465974625,
      "grad_norm": 0.0016482905484735966,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.20761245674740483,
      "grad_norm": 0.001386096584610641,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.20761245674740483,
      "eval_loss": 4.529163925326429e-05,
      "eval_runtime": 17.0572,
      "eval_samples_per_second": 21.399,
      "eval_steps_per_second": 5.394,
      "step": 45
    },
    {
      "epoch": 0.2122260668973472,
      "grad_norm": 0.0013259489787742496,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.21683967704728951,
      "grad_norm": 0.0013276770478114486,
      "learning_rate": 2.7630079602323442e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.22145328719723184,
      "grad_norm": 0.0014235457638278604,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.22606689734717417,
      "grad_norm": 0.001371592516079545,
      "learning_rate": 3.0826662668720364e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.2306805074971165,
      "grad_norm": 0.0014171238290145993,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.2306805074971165,
      "eval_loss": 4.512478335527703e-05,
      "eval_runtime": 17.0887,
      "eval_samples_per_second": 21.359,
      "eval_steps_per_second": 5.384,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 7209543008256000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}