{
  "best_metric": 0.8603118658065796,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.1611030478955007,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023222060957910014,
      "grad_norm": 1.3467507362365723,
      "learning_rate": 5e-05,
      "loss": 1.5246,
      "step": 1
    },
    {
      "epoch": 0.023222060957910014,
      "eval_loss": 1.612884521484375,
      "eval_runtime": 14.3424,
      "eval_samples_per_second": 20.22,
      "eval_steps_per_second": 2.58,
      "step": 1
    },
    {
      "epoch": 0.04644412191582003,
      "grad_norm": 1.4302773475646973,
      "learning_rate": 0.0001,
      "loss": 1.5494,
      "step": 2
    },
    {
      "epoch": 0.06966618287373004,
      "grad_norm": 1.1885151863098145,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.5306,
      "step": 3
    },
    {
      "epoch": 0.09288824383164006,
      "grad_norm": 0.9224026799201965,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.3176,
      "step": 4
    },
    {
      "epoch": 0.11611030478955008,
      "grad_norm": 1.0390187501907349,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.2257,
      "step": 5
    },
    {
      "epoch": 0.13933236574746008,
      "grad_norm": 0.9160548448562622,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.1101,
      "step": 6
    },
    {
      "epoch": 0.1625544267053701,
      "grad_norm": 0.7842693328857422,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.077,
      "step": 7
    },
    {
      "epoch": 0.18577648766328012,
      "grad_norm": 0.8577767014503479,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.1017,
      "step": 8
    },
    {
      "epoch": 0.20899854862119013,
      "grad_norm": 0.8787832856178284,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.0922,
      "step": 9
    },
    {
      "epoch": 0.23222060957910015,
      "grad_norm": 0.7744745016098022,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0785,
      "step": 10
    },
    {
      "epoch": 0.25544267053701014,
      "grad_norm": 0.8764593005180359,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.0612,
      "step": 11
    },
    {
      "epoch": 0.27866473149492016,
      "grad_norm": 0.7107537388801575,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.9849,
      "step": 12
    },
    {
      "epoch": 0.3018867924528302,
      "grad_norm": 0.6566634178161621,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.9391,
      "step": 13
    },
    {
      "epoch": 0.3251088534107402,
      "grad_norm": 0.6309544444084167,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.9475,
      "step": 14
    },
    {
      "epoch": 0.3483309143686502,
      "grad_norm": 0.5804163813591003,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.9126,
      "step": 15
    },
    {
      "epoch": 0.37155297532656023,
      "grad_norm": 0.6566357016563416,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.9324,
      "step": 16
    },
    {
      "epoch": 0.39477503628447025,
      "grad_norm": 0.5939004421234131,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.8877,
      "step": 17
    },
    {
      "epoch": 0.41799709724238027,
      "grad_norm": 0.5620059967041016,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9302,
      "step": 18
    },
    {
      "epoch": 0.4412191582002903,
      "grad_norm": 0.6092360615730286,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.9486,
      "step": 19
    },
    {
      "epoch": 0.4644412191582003,
      "grad_norm": 0.6564576029777527,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.9314,
      "step": 20
    },
    {
      "epoch": 0.4876632801161103,
      "grad_norm": 0.6113615036010742,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.8829,
      "step": 21
    },
    {
      "epoch": 0.5108853410740203,
      "grad_norm": 0.623550295829773,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.9554,
      "step": 22
    },
    {
      "epoch": 0.5341074020319303,
      "grad_norm": 0.6695098876953125,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.8875,
      "step": 23
    },
    {
      "epoch": 0.5573294629898403,
      "grad_norm": 0.6017366051673889,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.8678,
      "step": 24
    },
    {
      "epoch": 0.5805515239477503,
      "grad_norm": 0.5160570740699768,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.8778,
      "step": 25
    },
    {
      "epoch": 0.5805515239477503,
      "eval_loss": 0.888064980506897,
      "eval_runtime": 14.3163,
      "eval_samples_per_second": 20.257,
      "eval_steps_per_second": 2.584,
      "step": 25
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": 0.5614883303642273,
      "learning_rate": 5e-05,
      "loss": 0.8565,
      "step": 26
    },
    {
      "epoch": 0.6269956458635704,
      "grad_norm": 0.6048403978347778,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.8667,
      "step": 27
    },
    {
      "epoch": 0.6502177068214804,
      "grad_norm": 0.5841188430786133,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.89,
      "step": 28
    },
    {
      "epoch": 0.6734397677793904,
      "grad_norm": 0.5607112646102905,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.8729,
      "step": 29
    },
    {
      "epoch": 0.6966618287373004,
      "grad_norm": 0.5376509428024292,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.8794,
      "step": 30
    },
    {
      "epoch": 0.7198838896952104,
      "grad_norm": 0.5627703666687012,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.8813,
      "step": 31
    },
    {
      "epoch": 0.7431059506531205,
      "grad_norm": 0.6090062260627747,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.841,
      "step": 32
    },
    {
      "epoch": 0.7663280116110305,
      "grad_norm": 0.5763826966285706,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.8806,
      "step": 33
    },
    {
      "epoch": 0.7895500725689405,
      "grad_norm": 0.6495899558067322,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8241,
      "step": 34
    },
    {
      "epoch": 0.8127721335268505,
      "grad_norm": 0.5492468476295471,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.8429,
      "step": 35
    },
    {
      "epoch": 0.8359941944847605,
      "grad_norm": 0.519008457660675,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.8832,
      "step": 36
    },
    {
      "epoch": 0.8592162554426706,
      "grad_norm": 0.5007856488227844,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.8834,
      "step": 37
    },
    {
      "epoch": 0.8824383164005806,
      "grad_norm": 0.5180608034133911,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8838,
      "step": 38
    },
    {
      "epoch": 0.9056603773584906,
      "grad_norm": 0.5399318337440491,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.855,
      "step": 39
    },
    {
      "epoch": 0.9288824383164006,
      "grad_norm": 0.577284574508667,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.8981,
      "step": 40
    },
    {
      "epoch": 0.9521044992743106,
      "grad_norm": 0.6111936569213867,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.8761,
      "step": 41
    },
    {
      "epoch": 0.9753265602322206,
      "grad_norm": 0.5520212650299072,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.8957,
      "step": 42
    },
    {
      "epoch": 0.9985486211901307,
      "grad_norm": 0.5935046672821045,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.8572,
      "step": 43
    },
    {
      "epoch": 1.0217706821480406,
      "grad_norm": 2.43267560005188,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.8794,
      "step": 44
    },
    {
      "epoch": 1.0449927431059507,
      "grad_norm": 0.47028273344039917,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.7591,
      "step": 45
    },
    {
      "epoch": 1.0682148040638606,
      "grad_norm": 0.48551949858665466,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.8037,
      "step": 46
    },
    {
      "epoch": 1.0914368650217707,
      "grad_norm": 0.4666672348976135,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.8321,
      "step": 47
    },
    {
      "epoch": 1.1146589259796806,
      "grad_norm": 0.47201839089393616,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.7327,
      "step": 48
    },
    {
      "epoch": 1.1378809869375908,
      "grad_norm": 0.5046037435531616,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.7715,
      "step": 49
    },
    {
      "epoch": 1.1611030478955007,
      "grad_norm": 0.5255216956138611,
      "learning_rate": 0.0,
      "loss": 0.8312,
      "step": 50
    },
    {
      "epoch": 1.1611030478955007,
      "eval_loss": 0.8603118658065796,
      "eval_runtime": 14.3151,
      "eval_samples_per_second": 20.258,
      "eval_steps_per_second": 2.585,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0547313194953605e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}