{
  "best_metric": 2.4283339977264404,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.4550625711035267,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009101251422070534,
      "grad_norm": 2.209428310394287,
      "learning_rate": 5e-05,
      "loss": 4.9719,
      "step": 1
    },
    {
      "epoch": 0.009101251422070534,
      "eval_loss": 4.942025184631348,
      "eval_runtime": 3.9301,
      "eval_samples_per_second": 188.545,
      "eval_steps_per_second": 23.664,
      "step": 1
    },
    {
      "epoch": 0.01820250284414107,
      "grad_norm": 1.7319118976593018,
      "learning_rate": 0.0001,
      "loss": 4.9787,
      "step": 2
    },
    {
      "epoch": 0.027303754266211604,
      "grad_norm": 1.4984430074691772,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.834,
      "step": 3
    },
    {
      "epoch": 0.03640500568828214,
      "grad_norm": 1.723325252532959,
      "learning_rate": 9.957224306869053e-05,
      "loss": 5.0757,
      "step": 4
    },
    {
      "epoch": 0.04550625711035267,
      "grad_norm": 1.8475040197372437,
      "learning_rate": 9.903926402016153e-05,
      "loss": 5.0175,
      "step": 5
    },
    {
      "epoch": 0.05460750853242321,
      "grad_norm": 1.380941390991211,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.4863,
      "step": 6
    },
    {
      "epoch": 0.06370875995449374,
      "grad_norm": 1.980647087097168,
      "learning_rate": 9.73465064747553e-05,
      "loss": 4.8039,
      "step": 7
    },
    {
      "epoch": 0.07281001137656427,
      "grad_norm": 1.38150155544281,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.8026,
      "step": 8
    },
    {
      "epoch": 0.08191126279863481,
      "grad_norm": 1.7724114656448364,
      "learning_rate": 9.484363707663442e-05,
      "loss": 4.9867,
      "step": 9
    },
    {
      "epoch": 0.09101251422070535,
      "grad_norm": 1.2675881385803223,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.3271,
      "step": 10
    },
    {
      "epoch": 0.10011376564277588,
      "grad_norm": 1.3056012392044067,
      "learning_rate": 9.157348061512727e-05,
      "loss": 4.4681,
      "step": 11
    },
    {
      "epoch": 0.10921501706484642,
      "grad_norm": 1.3030096292495728,
      "learning_rate": 8.966766701456177e-05,
      "loss": 4.0861,
      "step": 12
    },
    {
      "epoch": 0.11831626848691695,
      "grad_norm": 1.2706266641616821,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.8508,
      "step": 13
    },
    {
      "epoch": 0.12741751990898748,
      "grad_norm": 1.6742432117462158,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.7126,
      "step": 14
    },
    {
      "epoch": 0.13651877133105803,
      "grad_norm": 1.458900809288025,
      "learning_rate": 8.296729075500344e-05,
      "loss": 3.5975,
      "step": 15
    },
    {
      "epoch": 0.14562002275312855,
      "grad_norm": 1.443761944770813,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.5467,
      "step": 16
    },
    {
      "epoch": 0.1547212741751991,
      "grad_norm": 1.7539066076278687,
      "learning_rate": 7.777851165098012e-05,
      "loss": 3.653,
      "step": 17
    },
    {
      "epoch": 0.16382252559726962,
      "grad_norm": 1.558334469795227,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.4541,
      "step": 18
    },
    {
      "epoch": 0.17292377701934017,
      "grad_norm": 1.7318171262741089,
      "learning_rate": 7.211443451095007e-05,
      "loss": 3.3867,
      "step": 19
    },
    {
      "epoch": 0.1820250284414107,
      "grad_norm": 1.4786357879638672,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.5035,
      "step": 20
    },
    {
      "epoch": 0.19112627986348124,
      "grad_norm": 1.769963264465332,
      "learning_rate": 6.607197326515808e-05,
      "loss": 3.8702,
      "step": 21
    },
    {
      "epoch": 0.20022753128555176,
      "grad_norm": 1.5237165689468384,
      "learning_rate": 6.294095225512603e-05,
      "loss": 3.6431,
      "step": 22
    },
    {
      "epoch": 0.20932878270762229,
      "grad_norm": 1.3721243143081665,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 3.7161,
      "step": 23
    },
    {
      "epoch": 0.21843003412969283,
      "grad_norm": 1.449666142463684,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 3.5503,
      "step": 24
    },
    {
      "epoch": 0.22753128555176336,
      "grad_norm": 1.7347791194915771,
      "learning_rate": 5.327015646150716e-05,
      "loss": 3.1498,
      "step": 25
    },
    {
      "epoch": 0.22753128555176336,
      "eval_loss": 3.064283847808838,
      "eval_runtime": 3.9326,
      "eval_samples_per_second": 188.426,
      "eval_steps_per_second": 23.649,
      "step": 25
    },
    {
      "epoch": 0.2366325369738339,
      "grad_norm": 2.2044360637664795,
      "learning_rate": 5e-05,
      "loss": 2.6249,
      "step": 26
    },
    {
      "epoch": 0.24573378839590443,
      "grad_norm": 1.9901007413864136,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 2.7054,
      "step": 27
    },
    {
      "epoch": 0.25483503981797495,
      "grad_norm": 1.8822261095046997,
      "learning_rate": 4.347369038899744e-05,
      "loss": 2.6927,
      "step": 28
    },
    {
      "epoch": 0.26393629124004553,
      "grad_norm": 1.774219036102295,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 2.6195,
      "step": 29
    },
    {
      "epoch": 0.27303754266211605,
      "grad_norm": 1.9437421560287476,
      "learning_rate": 3.705904774487396e-05,
      "loss": 2.5941,
      "step": 30
    },
    {
      "epoch": 0.2821387940841866,
      "grad_norm": 1.8226627111434937,
      "learning_rate": 3.392802673484193e-05,
      "loss": 2.6137,
      "step": 31
    },
    {
      "epoch": 0.2912400455062571,
      "grad_norm": 1.937389850616455,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.4284,
      "step": 32
    },
    {
      "epoch": 0.3003412969283277,
      "grad_norm": 1.5420129299163818,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 2.8111,
      "step": 33
    },
    {
      "epoch": 0.3094425483503982,
      "grad_norm": 2.2800674438476562,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.174,
      "step": 34
    },
    {
      "epoch": 0.3185437997724687,
      "grad_norm": 1.8032552003860474,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 2.8876,
      "step": 35
    },
    {
      "epoch": 0.32764505119453924,
      "grad_norm": 1.6756423711776733,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 3.0813,
      "step": 36
    },
    {
      "epoch": 0.33674630261660976,
      "grad_norm": 1.791947603225708,
      "learning_rate": 1.703270924499656e-05,
      "loss": 2.807,
      "step": 37
    },
    {
      "epoch": 0.34584755403868034,
      "grad_norm": 1.6586705446243286,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.2985,
      "step": 38
    },
    {
      "epoch": 0.35494880546075086,
      "grad_norm": 2.1676206588745117,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 2.1452,
      "step": 39
    },
    {
      "epoch": 0.3640500568828214,
      "grad_norm": 1.8072509765625,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 2.163,
      "step": 40
    },
    {
      "epoch": 0.3731513083048919,
      "grad_norm": 1.7898691892623901,
      "learning_rate": 8.426519384872733e-06,
      "loss": 2.1325,
      "step": 41
    },
    {
      "epoch": 0.3822525597269625,
      "grad_norm": 1.9742748737335205,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.139,
      "step": 42
    },
    {
      "epoch": 0.391353811149033,
      "grad_norm": 1.9127507209777832,
      "learning_rate": 5.156362923365588e-06,
      "loss": 2.1425,
      "step": 43
    },
    {
      "epoch": 0.4004550625711035,
      "grad_norm": 1.9670830965042114,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.0155,
      "step": 44
    },
    {
      "epoch": 0.40955631399317405,
      "grad_norm": 1.6419051885604858,
      "learning_rate": 2.653493525244721e-06,
      "loss": 2.33,
      "step": 45
    },
    {
      "epoch": 0.41865756541524457,
      "grad_norm": 2.231081485748291,
      "learning_rate": 1.70370868554659e-06,
      "loss": 2.8802,
      "step": 46
    },
    {
      "epoch": 0.42775881683731515,
      "grad_norm": 2.0120363235473633,
      "learning_rate": 9.607359798384785e-07,
      "loss": 2.7045,
      "step": 47
    },
    {
      "epoch": 0.43686006825938567,
      "grad_norm": 1.669359564781189,
      "learning_rate": 4.277569313094809e-07,
      "loss": 2.8704,
      "step": 48
    },
    {
      "epoch": 0.4459613196814562,
      "grad_norm": 1.785393238067627,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 2.9493,
      "step": 49
    },
    {
      "epoch": 0.4550625711035267,
      "grad_norm": 2.4181904792785645,
      "learning_rate": 0.0,
      "loss": 2.5716,
      "step": 50
    },
    {
      "epoch": 0.4550625711035267,
      "eval_loss": 2.4283339977264404,
      "eval_runtime": 3.9225,
      "eval_samples_per_second": 188.908,
      "eval_steps_per_second": 23.709,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 9120441905971200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}