{
  "best_metric": 0.4193588197231293,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.031560675398453523,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006312135079690705,
      "grad_norm": 2.510498523712158,
      "learning_rate": 5e-06,
      "loss": 1.3575,
      "step": 1
    },
    {
      "epoch": 0.0006312135079690705,
      "eval_loss": 0.5412741303443909,
      "eval_runtime": 238.8352,
      "eval_samples_per_second": 11.171,
      "eval_steps_per_second": 5.585,
      "step": 1
    },
    {
      "epoch": 0.001262427015938141,
      "grad_norm": 3.5491857528686523,
      "learning_rate": 1e-05,
      "loss": 1.7241,
      "step": 2
    },
    {
      "epoch": 0.0018936405239072117,
      "grad_norm": 3.036754846572876,
      "learning_rate": 1.5e-05,
      "loss": 1.6489,
      "step": 3
    },
    {
      "epoch": 0.002524854031876282,
      "grad_norm": 2.9480931758880615,
      "learning_rate": 2e-05,
      "loss": 1.7361,
      "step": 4
    },
    {
      "epoch": 0.0031560675398453527,
      "grad_norm": 2.8215577602386475,
      "learning_rate": 2.5e-05,
      "loss": 1.7123,
      "step": 5
    },
    {
      "epoch": 0.0037872810478144234,
      "grad_norm": 2.637902021408081,
      "learning_rate": 3e-05,
      "loss": 1.6068,
      "step": 6
    },
    {
      "epoch": 0.004418494555783494,
      "grad_norm": 2.700479745864868,
      "learning_rate": 3.5e-05,
      "loss": 1.6763,
      "step": 7
    },
    {
      "epoch": 0.005049708063752564,
      "grad_norm": 2.643176794052124,
      "learning_rate": 4e-05,
      "loss": 1.6168,
      "step": 8
    },
    {
      "epoch": 0.005680921571721635,
      "grad_norm": 2.6839067935943604,
      "learning_rate": 4.5e-05,
      "loss": 1.6763,
      "step": 9
    },
    {
      "epoch": 0.006312135079690705,
      "grad_norm": 2.832852363586426,
      "learning_rate": 5e-05,
      "loss": 1.6942,
      "step": 10
    },
    {
      "epoch": 0.006943348587659776,
      "grad_norm": 2.4192471504211426,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.7016,
      "step": 11
    },
    {
      "epoch": 0.007574562095628847,
      "grad_norm": 2.353262424468994,
      "learning_rate": 6e-05,
      "loss": 1.7291,
      "step": 12
    },
    {
      "epoch": 0.008205775603597917,
      "grad_norm": 2.393162965774536,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.7481,
      "step": 13
    },
    {
      "epoch": 0.008836989111566988,
      "grad_norm": 2.343433380126953,
      "learning_rate": 7e-05,
      "loss": 1.7567,
      "step": 14
    },
    {
      "epoch": 0.009468202619536058,
      "grad_norm": 2.266066312789917,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.6315,
      "step": 15
    },
    {
      "epoch": 0.010099416127505128,
      "grad_norm": 2.1219441890716553,
      "learning_rate": 8e-05,
      "loss": 1.522,
      "step": 16
    },
    {
      "epoch": 0.0107306296354742,
      "grad_norm": 2.1620051860809326,
      "learning_rate": 8.5e-05,
      "loss": 1.6477,
      "step": 17
    },
    {
      "epoch": 0.01136184314344327,
      "grad_norm": 2.0980477333068848,
      "learning_rate": 9e-05,
      "loss": 1.9465,
      "step": 18
    },
    {
      "epoch": 0.011993056651412341,
      "grad_norm": 2.2929768562316895,
      "learning_rate": 9.5e-05,
      "loss": 1.7456,
      "step": 19
    },
    {
      "epoch": 0.01262427015938141,
      "grad_norm": 2.2193870544433594,
      "learning_rate": 0.0001,
      "loss": 1.7356,
      "step": 20
    },
    {
      "epoch": 0.01325548366735048,
      "grad_norm": 2.251990556716919,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.6963,
      "step": 21
    },
    {
      "epoch": 0.013886697175319552,
      "grad_norm": 2.1346232891082764,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.5908,
      "step": 22
    },
    {
      "epoch": 0.014517910683288622,
      "grad_norm": 2.163315534591675,
      "learning_rate": 9.99314767377287e-05,
      "loss": 1.6235,
      "step": 23
    },
    {
      "epoch": 0.015149124191257694,
      "grad_norm": 2.047973155975342,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.7013,
      "step": 24
    },
    {
      "epoch": 0.015780337699226762,
      "grad_norm": 2.0005741119384766,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.7541,
      "step": 25
    },
    {
      "epoch": 0.016411551207195833,
      "grad_norm": 2.1012520790100098,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.6195,
      "step": 26
    },
    {
      "epoch": 0.017042764715164905,
      "grad_norm": 2.241985321044922,
      "learning_rate": 9.962730758206611e-05,
      "loss": 1.7854,
      "step": 27
    },
    {
      "epoch": 0.017673978223133976,
      "grad_norm": 1.977676510810852,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.7176,
      "step": 28
    },
    {
      "epoch": 0.018305191731103045,
      "grad_norm": 1.9915571212768555,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.8064,
      "step": 29
    },
    {
      "epoch": 0.018936405239072116,
      "grad_norm": 2.151484489440918,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.0075,
      "step": 30
    },
    {
      "epoch": 0.019567618747041188,
      "grad_norm": 1.9701048135757446,
      "learning_rate": 9.908135917238321e-05,
      "loss": 1.5496,
      "step": 31
    },
    {
      "epoch": 0.020198832255010256,
      "grad_norm": 2.0728065967559814,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.7886,
      "step": 32
    },
    {
      "epoch": 0.020830045762979327,
      "grad_norm": 2.117295265197754,
      "learning_rate": 9.871850323926177e-05,
      "loss": 1.6142,
      "step": 33
    },
    {
      "epoch": 0.0214612592709484,
      "grad_norm": 1.9997711181640625,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.6704,
      "step": 34
    },
    {
      "epoch": 0.022092472778917467,
      "grad_norm": 2.1985790729522705,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.9918,
      "step": 35
    },
    {
      "epoch": 0.02272368628688654,
      "grad_norm": 2.025857925415039,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.5683,
      "step": 36
    },
    {
      "epoch": 0.02335489979485561,
      "grad_norm": 2.131359338760376,
      "learning_rate": 9.781523779815179e-05,
      "loss": 1.8734,
      "step": 37
    },
    {
      "epoch": 0.023986113302824682,
      "grad_norm": 2.0778703689575195,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.7188,
      "step": 38
    },
    {
      "epoch": 0.02461732681079375,
      "grad_norm": 2.165473461151123,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.7564,
      "step": 39
    },
    {
      "epoch": 0.02524854031876282,
      "grad_norm": 2.105788230895996,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.707,
      "step": 40
    },
    {
      "epoch": 0.025879753826731893,
      "grad_norm": 2.1210577487945557,
      "learning_rate": 9.667902132486009e-05,
      "loss": 1.724,
      "step": 41
    },
    {
      "epoch": 0.02651096733470096,
      "grad_norm": 2.0978639125823975,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.751,
      "step": 42
    },
    {
      "epoch": 0.027142180842670033,
      "grad_norm": 2.273977279663086,
      "learning_rate": 9.602524267262203e-05,
      "loss": 1.6593,
      "step": 43
    },
    {
      "epoch": 0.027773394350639104,
      "grad_norm": 2.122015953063965,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.756,
      "step": 44
    },
    {
      "epoch": 0.028404607858608173,
      "grad_norm": 2.081787109375,
      "learning_rate": 9.53153893518325e-05,
      "loss": 1.5773,
      "step": 45
    },
    {
      "epoch": 0.029035821366577244,
      "grad_norm": 2.3352270126342773,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.6289,
      "step": 46
    },
    {
      "epoch": 0.029667034874546316,
      "grad_norm": 2.268566370010376,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.7125,
      "step": 47
    },
    {
      "epoch": 0.030298248382515387,
      "grad_norm": 2.2713985443115234,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.5243,
      "step": 48
    },
    {
      "epoch": 0.030929461890484455,
      "grad_norm": 2.297013282775879,
      "learning_rate": 9.373098535696979e-05,
      "loss": 1.4457,
      "step": 49
    },
    {
      "epoch": 0.031560675398453523,
      "grad_norm": 2.792546510696411,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.4837,
      "step": 50
    },
    {
      "epoch": 0.031560675398453523,
      "eval_loss": 0.4193588197231293,
      "eval_runtime": 240.4268,
      "eval_samples_per_second": 11.097,
      "eval_steps_per_second": 5.548,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.942038949881446e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}