{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1394700139470014,
  "eval_steps": 9,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002789400278940028,
      "grad_norm": 1.3559156656265259,
      "learning_rate": 1e-05,
      "loss": 2.2982,
      "step": 1
    },
    {
      "epoch": 0.002789400278940028,
      "eval_loss": 2.324856758117676,
      "eval_runtime": 52.9801,
      "eval_samples_per_second": 5.7,
      "eval_steps_per_second": 0.717,
      "step": 1
    },
    {
      "epoch": 0.005578800557880056,
      "grad_norm": 1.4949768781661987,
      "learning_rate": 2e-05,
      "loss": 2.3912,
      "step": 2
    },
    {
      "epoch": 0.008368200836820083,
      "grad_norm": 1.295521855354309,
      "learning_rate": 3e-05,
      "loss": 2.1321,
      "step": 3
    },
    {
      "epoch": 0.011157601115760111,
      "grad_norm": 1.3849579095840454,
      "learning_rate": 4e-05,
      "loss": 2.0892,
      "step": 4
    },
    {
      "epoch": 0.01394700139470014,
      "grad_norm": 1.410709261894226,
      "learning_rate": 5e-05,
      "loss": 2.1073,
      "step": 5
    },
    {
      "epoch": 0.016736401673640166,
      "grad_norm": 1.835424542427063,
      "learning_rate": 6e-05,
      "loss": 2.4634,
      "step": 6
    },
    {
      "epoch": 0.019525801952580194,
      "grad_norm": 1.9201370477676392,
      "learning_rate": 7e-05,
      "loss": 2.3361,
      "step": 7
    },
    {
      "epoch": 0.022315202231520222,
      "grad_norm": 1.8919646739959717,
      "learning_rate": 8e-05,
      "loss": 2.3183,
      "step": 8
    },
    {
      "epoch": 0.02510460251046025,
      "grad_norm": 2.5362789630889893,
      "learning_rate": 9e-05,
      "loss": 2.3376,
      "step": 9
    },
    {
      "epoch": 0.02510460251046025,
      "eval_loss": 1.8519941568374634,
      "eval_runtime": 52.8507,
      "eval_samples_per_second": 5.714,
      "eval_steps_per_second": 0.719,
      "step": 9
    },
    {
      "epoch": 0.02789400278940028,
      "grad_norm": 2.107351064682007,
      "learning_rate": 0.0001,
      "loss": 1.9185,
      "step": 10
    },
    {
      "epoch": 0.030683403068340307,
      "grad_norm": 1.8538174629211426,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.5435,
      "step": 11
    },
    {
      "epoch": 0.03347280334728033,
      "grad_norm": 1.4159091711044312,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.2372,
      "step": 12
    },
    {
      "epoch": 0.03626220362622036,
      "grad_norm": 2.1776630878448486,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.4526,
      "step": 13
    },
    {
      "epoch": 0.03905160390516039,
      "grad_norm": 1.743064284324646,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.2122,
      "step": 14
    },
    {
      "epoch": 0.04184100418410042,
      "grad_norm": 1.6609395742416382,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.0635,
      "step": 15
    },
    {
      "epoch": 0.044630404463040445,
      "grad_norm": 1.647965431213379,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9718,
      "step": 16
    },
    {
      "epoch": 0.04741980474198047,
      "grad_norm": 1.6228158473968506,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.8951,
      "step": 17
    },
    {
      "epoch": 0.0502092050209205,
      "grad_norm": 1.300998330116272,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.8446,
      "step": 18
    },
    {
      "epoch": 0.0502092050209205,
      "eval_loss": 0.7097400426864624,
      "eval_runtime": 52.745,
      "eval_samples_per_second": 5.726,
      "eval_steps_per_second": 0.72,
      "step": 18
    },
    {
      "epoch": 0.05299860529986053,
      "grad_norm": 1.0316293239593506,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.665,
      "step": 19
    },
    {
      "epoch": 0.05578800557880056,
      "grad_norm": 0.992760181427002,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.707,
      "step": 20
    },
    {
      "epoch": 0.058577405857740586,
      "grad_norm": 1.0852915048599243,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.5554,
      "step": 21
    },
    {
      "epoch": 0.061366806136680614,
      "grad_norm": 1.189538598060608,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.5806,
      "step": 22
    },
    {
      "epoch": 0.06415620641562064,
      "grad_norm": 1.0849921703338623,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.5446,
      "step": 23
    },
    {
      "epoch": 0.06694560669456066,
      "grad_norm": 1.1741552352905273,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.5985,
      "step": 24
    },
    {
      "epoch": 0.0697350069735007,
      "grad_norm": 0.9880762100219727,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.4832,
      "step": 25
    },
    {
      "epoch": 0.07252440725244072,
      "grad_norm": 1.2720280885696411,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.5232,
      "step": 26
    },
    {
      "epoch": 0.07531380753138076,
      "grad_norm": 0.8770483732223511,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.5127,
      "step": 27
    },
    {
      "epoch": 0.07531380753138076,
      "eval_loss": 0.4544554054737091,
      "eval_runtime": 52.7242,
      "eval_samples_per_second": 5.728,
      "eval_steps_per_second": 0.721,
      "step": 27
    },
    {
      "epoch": 0.07810320781032078,
      "grad_norm": 1.0763133764266968,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4893,
      "step": 28
    },
    {
      "epoch": 0.08089260808926081,
      "grad_norm": 4.231393337249756,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.5389,
      "step": 29
    },
    {
      "epoch": 0.08368200836820083,
      "grad_norm": 2.0894691944122314,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.5256,
      "step": 30
    },
    {
      "epoch": 0.08647140864714087,
      "grad_norm": 0.9810737371444702,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.4633,
      "step": 31
    },
    {
      "epoch": 0.08926080892608089,
      "grad_norm": 0.6633622050285339,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.3574,
      "step": 32
    },
    {
      "epoch": 0.09205020920502092,
      "grad_norm": 0.9858479499816895,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.4049,
      "step": 33
    },
    {
      "epoch": 0.09483960948396095,
      "grad_norm": 0.8702887892723083,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.3425,
      "step": 34
    },
    {
      "epoch": 0.09762900976290098,
      "grad_norm": 0.8333115577697754,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.3372,
      "step": 35
    },
    {
      "epoch": 0.100418410041841,
      "grad_norm": 0.7566404938697815,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.33,
      "step": 36
    },
    {
      "epoch": 0.100418410041841,
      "eval_loss": 0.3604300320148468,
      "eval_runtime": 52.7348,
      "eval_samples_per_second": 5.727,
      "eval_steps_per_second": 0.721,
      "step": 36
    },
    {
      "epoch": 0.10320781032078104,
      "grad_norm": 0.7114524841308594,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2738,
      "step": 37
    },
    {
      "epoch": 0.10599721059972106,
      "grad_norm": 0.6801817417144775,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.3377,
      "step": 38
    },
    {
      "epoch": 0.1087866108786611,
      "grad_norm": 0.72431480884552,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2961,
      "step": 39
    },
    {
      "epoch": 0.11157601115760112,
      "grad_norm": 0.9961448907852173,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3979,
      "step": 40
    },
    {
      "epoch": 0.11436541143654114,
      "grad_norm": 0.7426677346229553,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.304,
      "step": 41
    },
    {
      "epoch": 0.11715481171548117,
      "grad_norm": 0.634848952293396,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2814,
      "step": 42
    },
    {
      "epoch": 0.1199442119944212,
      "grad_norm": 0.7828645706176758,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.3165,
      "step": 43
    },
    {
      "epoch": 0.12273361227336123,
      "grad_norm": 0.9621155261993408,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.3042,
      "step": 44
    },
    {
      "epoch": 0.12552301255230125,
      "grad_norm": 0.7523605823516846,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.3727,
      "step": 45
    },
    {
      "epoch": 0.12552301255230125,
      "eval_loss": 0.3056940734386444,
      "eval_runtime": 52.7202,
      "eval_samples_per_second": 5.728,
      "eval_steps_per_second": 0.721,
      "step": 45
    },
    {
      "epoch": 0.12831241283124128,
      "grad_norm": 0.7485724091529846,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2883,
      "step": 46
    },
    {
      "epoch": 0.13110181311018132,
      "grad_norm": 0.6190716028213501,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.2932,
      "step": 47
    },
    {
      "epoch": 0.13389121338912133,
      "grad_norm": 0.8940878510475159,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.3347,
      "step": 48
    },
    {
      "epoch": 0.13668061366806136,
      "grad_norm": 0.7823814749717712,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.2572,
      "step": 49
    },
    {
      "epoch": 0.1394700139470014,
      "grad_norm": 0.7668711543083191,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.3296,
      "step": 50
    }
  ],
  "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": 6.411270135742464e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}