{
  "best_metric": 0.7548462748527527,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.019807863721897592,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00039615727443795186,
      "grad_norm": 14.697911262512207,
      "learning_rate": 5e-06,
      "loss": 2.5987,
      "step": 1
    },
    {
      "epoch": 0.00039615727443795186,
      "eval_loss": 1.2088950872421265,
      "eval_runtime": 341.1554,
      "eval_samples_per_second": 12.464,
      "eval_steps_per_second": 6.232,
      "step": 1
    },
    {
      "epoch": 0.0007923145488759037,
      "grad_norm": 16.757488250732422,
      "learning_rate": 1e-05,
      "loss": 3.394,
      "step": 2
    },
    {
      "epoch": 0.0011884718233138556,
      "grad_norm": 19.087627410888672,
      "learning_rate": 1.5e-05,
      "loss": 3.0496,
      "step": 3
    },
    {
      "epoch": 0.0015846290977518075,
      "grad_norm": 18.1752986907959,
      "learning_rate": 2e-05,
      "loss": 3.2584,
      "step": 4
    },
    {
      "epoch": 0.0019807863721897595,
      "grad_norm": 14.575785636901855,
      "learning_rate": 2.5e-05,
      "loss": 2.986,
      "step": 5
    },
    {
      "epoch": 0.0023769436466277113,
      "grad_norm": 13.09287166595459,
      "learning_rate": 3e-05,
      "loss": 2.952,
      "step": 6
    },
    {
      "epoch": 0.002773100921065663,
      "grad_norm": 11.316363334655762,
      "learning_rate": 3.5e-05,
      "loss": 2.6524,
      "step": 7
    },
    {
      "epoch": 0.003169258195503615,
      "grad_norm": 11.73412036895752,
      "learning_rate": 4e-05,
      "loss": 2.669,
      "step": 8
    },
    {
      "epoch": 0.0035654154699415667,
      "grad_norm": 12.15320110321045,
      "learning_rate": 4.5e-05,
      "loss": 2.9467,
      "step": 9
    },
    {
      "epoch": 0.003961572744379519,
      "grad_norm": 10.565752983093262,
      "learning_rate": 5e-05,
      "loss": 2.5971,
      "step": 10
    },
    {
      "epoch": 0.004357730018817471,
      "grad_norm": 10.899881362915039,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.5928,
      "step": 11
    },
    {
      "epoch": 0.004753887293255423,
      "grad_norm": 10.57030200958252,
      "learning_rate": 6e-05,
      "loss": 3.0548,
      "step": 12
    },
    {
      "epoch": 0.005150044567693374,
      "grad_norm": 9.254692077636719,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.5015,
      "step": 13
    },
    {
      "epoch": 0.005546201842131326,
      "grad_norm": 9.80490779876709,
      "learning_rate": 7e-05,
      "loss": 2.2598,
      "step": 14
    },
    {
      "epoch": 0.005942359116569278,
      "grad_norm": 10.694642066955566,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.7476,
      "step": 15
    },
    {
      "epoch": 0.00633851639100723,
      "grad_norm": 10.605643272399902,
      "learning_rate": 8e-05,
      "loss": 2.5001,
      "step": 16
    },
    {
      "epoch": 0.006734673665445182,
      "grad_norm": 13.457276344299316,
      "learning_rate": 8.5e-05,
      "loss": 2.797,
      "step": 17
    },
    {
      "epoch": 0.0071308309398831335,
      "grad_norm": 10.881452560424805,
      "learning_rate": 9e-05,
      "loss": 2.497,
      "step": 18
    },
    {
      "epoch": 0.007526988214321085,
      "grad_norm": 10.051718711853027,
      "learning_rate": 9.5e-05,
      "loss": 2.4237,
      "step": 19
    },
    {
      "epoch": 0.007923145488759038,
      "grad_norm": 9.118144989013672,
      "learning_rate": 0.0001,
      "loss": 2.2963,
      "step": 20
    },
    {
      "epoch": 0.008319302763196989,
      "grad_norm": 10.652849197387695,
      "learning_rate": 9.999238475781957e-05,
      "loss": 2.4412,
      "step": 21
    },
    {
      "epoch": 0.008715460037634942,
      "grad_norm": 12.306429862976074,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.689,
      "step": 22
    },
    {
      "epoch": 0.009111617312072893,
      "grad_norm": 10.86596393585205,
      "learning_rate": 9.99314767377287e-05,
      "loss": 2.6179,
      "step": 23
    },
    {
      "epoch": 0.009507774586510845,
      "grad_norm": 10.322020530700684,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.3587,
      "step": 24
    },
    {
      "epoch": 0.009903931860948796,
      "grad_norm": 10.52370834350586,
      "learning_rate": 9.980973490458728e-05,
      "loss": 2.3825,
      "step": 25
    },
    {
      "epoch": 0.010300089135386749,
      "grad_norm": 12.126945495605469,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.8174,
      "step": 26
    },
    {
      "epoch": 0.0106962464098247,
      "grad_norm": 10.495783805847168,
      "learning_rate": 9.962730758206611e-05,
      "loss": 2.5925,
      "step": 27
    },
    {
      "epoch": 0.011092403684262652,
      "grad_norm": 11.440340995788574,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.5071,
      "step": 28
    },
    {
      "epoch": 0.011488560958700603,
      "grad_norm": 11.15341854095459,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.431,
      "step": 29
    },
    {
      "epoch": 0.011884718233138556,
      "grad_norm": 12.230130195617676,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.8904,
      "step": 30
    },
    {
      "epoch": 0.012280875507576509,
      "grad_norm": 11.259504318237305,
      "learning_rate": 9.908135917238321e-05,
      "loss": 2.7206,
      "step": 31
    },
    {
      "epoch": 0.01267703278201446,
      "grad_norm": 12.922420501708984,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.0273,
      "step": 32
    },
    {
      "epoch": 0.013073190056452412,
      "grad_norm": 9.90955924987793,
      "learning_rate": 9.871850323926177e-05,
      "loss": 2.0496,
      "step": 33
    },
    {
      "epoch": 0.013469347330890363,
      "grad_norm": 13.736802101135254,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.8411,
      "step": 34
    },
    {
      "epoch": 0.013865504605328316,
      "grad_norm": 10.806241035461426,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.2993,
      "step": 35
    },
    {
      "epoch": 0.014261661879766267,
      "grad_norm": 10.51795768737793,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.3481,
      "step": 36
    },
    {
      "epoch": 0.01465781915420422,
      "grad_norm": 11.385435104370117,
      "learning_rate": 9.781523779815179e-05,
      "loss": 2.7561,
      "step": 37
    },
    {
      "epoch": 0.01505397642864217,
      "grad_norm": 13.5595703125,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.1686,
      "step": 38
    },
    {
      "epoch": 0.015450133703080123,
      "grad_norm": 12.45494556427002,
      "learning_rate": 9.727592877996585e-05,
      "loss": 2.5412,
      "step": 39
    },
    {
      "epoch": 0.015846290977518076,
      "grad_norm": 11.393204689025879,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.3917,
      "step": 40
    },
    {
      "epoch": 0.016242448251956025,
      "grad_norm": 14.68457317352295,
      "learning_rate": 9.667902132486009e-05,
      "loss": 3.2398,
      "step": 41
    },
    {
      "epoch": 0.016638605526393978,
      "grad_norm": 12.070296287536621,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.431,
      "step": 42
    },
    {
      "epoch": 0.01703476280083193,
      "grad_norm": 21.221527099609375,
      "learning_rate": 9.602524267262203e-05,
      "loss": 3.3495,
      "step": 43
    },
    {
      "epoch": 0.017430920075269883,
      "grad_norm": 13.779664039611816,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.8153,
      "step": 44
    },
    {
      "epoch": 0.017827077349707832,
      "grad_norm": 13.476646423339844,
      "learning_rate": 9.53153893518325e-05,
      "loss": 3.2993,
      "step": 45
    },
    {
      "epoch": 0.018223234624145785,
      "grad_norm": 16.80905532836914,
      "learning_rate": 9.493970231495835e-05,
      "loss": 3.6182,
      "step": 46
    },
    {
      "epoch": 0.018619391898583738,
      "grad_norm": 13.21243953704834,
      "learning_rate": 9.45503262094184e-05,
      "loss": 3.0093,
      "step": 47
    },
    {
      "epoch": 0.01901554917302169,
      "grad_norm": 14.631463050842285,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.7913,
      "step": 48
    },
    {
      "epoch": 0.019411706447459643,
      "grad_norm": 12.769938468933105,
      "learning_rate": 9.373098535696979e-05,
      "loss": 2.2544,
      "step": 49
    },
    {
      "epoch": 0.019807863721897592,
      "grad_norm": 17.29874038696289,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.2499,
      "step": 50
    },
    {
      "epoch": 0.019807863721897592,
      "eval_loss": 0.7548462748527527,
      "eval_runtime": 343.3265,
      "eval_samples_per_second": 12.385,
      "eval_steps_per_second": 6.192,
      "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": 7.15499004493824e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}