{
  "best_metric": 0.6467951536178589,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.007600589045651038,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015201178091302076,
      "grad_norm": 3.6593680381774902,
      "learning_rate": 5e-05,
      "loss": 10.9362,
      "step": 1
    },
    {
      "epoch": 0.00015201178091302076,
      "eval_loss": 2.270036220550537,
      "eval_runtime": 2217.9223,
      "eval_samples_per_second": 19.982,
      "eval_steps_per_second": 2.498,
      "step": 1
    },
    {
      "epoch": 0.0003040235618260415,
      "grad_norm": 4.245506763458252,
      "learning_rate": 0.0001,
      "loss": 12.8607,
      "step": 2
    },
    {
      "epoch": 0.00045603534273906226,
      "grad_norm": 4.411743640899658,
      "learning_rate": 9.989294616193017e-05,
      "loss": 13.5941,
      "step": 3
    },
    {
      "epoch": 0.000608047123652083,
      "grad_norm": 5.3891096115112305,
      "learning_rate": 9.957224306869053e-05,
      "loss": 14.3746,
      "step": 4
    },
    {
      "epoch": 0.0007600589045651038,
      "grad_norm": 7.611150741577148,
      "learning_rate": 9.903926402016153e-05,
      "loss": 16.8511,
      "step": 5
    },
    {
      "epoch": 0.0009120706854781245,
      "grad_norm": 7.441198348999023,
      "learning_rate": 9.829629131445342e-05,
      "loss": 16.271,
      "step": 6
    },
    {
      "epoch": 0.0010640824663911454,
      "grad_norm": 8.687851905822754,
      "learning_rate": 9.73465064747553e-05,
      "loss": 16.6546,
      "step": 7
    },
    {
      "epoch": 0.001216094247304166,
      "grad_norm": 18.38853645324707,
      "learning_rate": 9.619397662556435e-05,
      "loss": 19.7066,
      "step": 8
    },
    {
      "epoch": 0.0013681060282171868,
      "grad_norm": 55.841705322265625,
      "learning_rate": 9.484363707663442e-05,
      "loss": 27.5424,
      "step": 9
    },
    {
      "epoch": 0.0015201178091302076,
      "grad_norm": 42.36283874511719,
      "learning_rate": 9.330127018922194e-05,
      "loss": 25.9464,
      "step": 10
    },
    {
      "epoch": 0.0016721295900432283,
      "grad_norm": 37.95155715942383,
      "learning_rate": 9.157348061512727e-05,
      "loss": 25.4448,
      "step": 11
    },
    {
      "epoch": 0.001824141370956249,
      "grad_norm": 23.544416427612305,
      "learning_rate": 8.966766701456177e-05,
      "loss": 19.4115,
      "step": 12
    },
    {
      "epoch": 0.00197615315186927,
      "grad_norm": 6.003608226776123,
      "learning_rate": 8.759199037394887e-05,
      "loss": 11.717,
      "step": 13
    },
    {
      "epoch": 0.0021281649327822907,
      "grad_norm": 1.9133445024490356,
      "learning_rate": 8.535533905932738e-05,
      "loss": 8.8507,
      "step": 14
    },
    {
      "epoch": 0.0022801767136953113,
      "grad_norm": 1.9236044883728027,
      "learning_rate": 8.296729075500344e-05,
      "loss": 9.9265,
      "step": 15
    },
    {
      "epoch": 0.002432188494608332,
      "grad_norm": 2.067864179611206,
      "learning_rate": 8.043807145043604e-05,
      "loss": 10.75,
      "step": 16
    },
    {
      "epoch": 0.0025842002755213527,
      "grad_norm": 2.5621371269226074,
      "learning_rate": 7.777851165098012e-05,
      "loss": 11.0612,
      "step": 17
    },
    {
      "epoch": 0.0027362120564343737,
      "grad_norm": 4.215025901794434,
      "learning_rate": 7.500000000000001e-05,
      "loss": 12.8646,
      "step": 18
    },
    {
      "epoch": 0.0028882238373473946,
      "grad_norm": 5.507603168487549,
      "learning_rate": 7.211443451095007e-05,
      "loss": 11.8597,
      "step": 19
    },
    {
      "epoch": 0.003040235618260415,
      "grad_norm": 6.5292134284973145,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.8724,
      "step": 20
    },
    {
      "epoch": 0.003192247399173436,
      "grad_norm": 12.831018447875977,
      "learning_rate": 6.607197326515808e-05,
      "loss": 11.5659,
      "step": 21
    },
    {
      "epoch": 0.0033442591800864566,
      "grad_norm": 11.646411895751953,
      "learning_rate": 6.294095225512603e-05,
      "loss": 9.7654,
      "step": 22
    },
    {
      "epoch": 0.0034962709609994776,
      "grad_norm": 14.624390602111816,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 11.7632,
      "step": 23
    },
    {
      "epoch": 0.003648282741912498,
      "grad_norm": 17.542835235595703,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 12.8791,
      "step": 24
    },
    {
      "epoch": 0.003800294522825519,
      "grad_norm": 9.677604675292969,
      "learning_rate": 5.327015646150716e-05,
      "loss": 12.1658,
      "step": 25
    },
    {
      "epoch": 0.003800294522825519,
      "eval_loss": 0.6706960797309875,
      "eval_runtime": 2218.0335,
      "eval_samples_per_second": 19.981,
      "eval_steps_per_second": 2.498,
      "step": 25
    },
    {
      "epoch": 0.00395230630373854,
      "grad_norm": 1.5809613466262817,
      "learning_rate": 5e-05,
      "loss": 8.0624,
      "step": 26
    },
    {
      "epoch": 0.00410431808465156,
      "grad_norm": 1.5702935457229614,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 9.5761,
      "step": 27
    },
    {
      "epoch": 0.0042563298655645815,
      "grad_norm": 1.5925304889678955,
      "learning_rate": 4.347369038899744e-05,
      "loss": 9.387,
      "step": 28
    },
    {
      "epoch": 0.004408341646477602,
      "grad_norm": 1.8622325658798218,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 9.7713,
      "step": 29
    },
    {
      "epoch": 0.0045603534273906225,
      "grad_norm": 2.6215012073516846,
      "learning_rate": 3.705904774487396e-05,
      "loss": 10.6637,
      "step": 30
    },
    {
      "epoch": 0.004712365208303644,
      "grad_norm": 2.9679672718048096,
      "learning_rate": 3.392802673484193e-05,
      "loss": 11.3137,
      "step": 31
    },
    {
      "epoch": 0.004864376989216664,
      "grad_norm": 5.380817413330078,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.4652,
      "step": 32
    },
    {
      "epoch": 0.005016388770129685,
      "grad_norm": 7.637914657592773,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 10.5382,
      "step": 33
    },
    {
      "epoch": 0.0051684005510427055,
      "grad_norm": 18.107852935791016,
      "learning_rate": 2.500000000000001e-05,
      "loss": 11.4912,
      "step": 34
    },
    {
      "epoch": 0.005320412331955727,
      "grad_norm": 15.613152503967285,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 10.7273,
      "step": 35
    },
    {
      "epoch": 0.005472424112868747,
      "grad_norm": 19.3842830657959,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 12.1613,
      "step": 36
    },
    {
      "epoch": 0.005624435893781768,
      "grad_norm": 9.611380577087402,
      "learning_rate": 1.703270924499656e-05,
      "loss": 10.761,
      "step": 37
    },
    {
      "epoch": 0.005776447674694789,
      "grad_norm": 4.896385669708252,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.5633,
      "step": 38
    },
    {
      "epoch": 0.00592845945560781,
      "grad_norm": 1.013009786605835,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 8.4005,
      "step": 39
    },
    {
      "epoch": 0.00608047123652083,
      "grad_norm": 1.1705186367034912,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 9.1887,
      "step": 40
    },
    {
      "epoch": 0.006232483017433851,
      "grad_norm": 1.3294516801834106,
      "learning_rate": 8.426519384872733e-06,
      "loss": 9.906,
      "step": 41
    },
    {
      "epoch": 0.006384494798346872,
      "grad_norm": 2.011843681335449,
      "learning_rate": 6.698729810778065e-06,
      "loss": 9.8106,
      "step": 42
    },
    {
      "epoch": 0.006536506579259893,
      "grad_norm": 2.1309995651245117,
      "learning_rate": 5.156362923365588e-06,
      "loss": 10.9305,
      "step": 43
    },
    {
      "epoch": 0.006688518360172913,
      "grad_norm": 2.600017547607422,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.1133,
      "step": 44
    },
    {
      "epoch": 0.006840530141085934,
      "grad_norm": 2.881525754928589,
      "learning_rate": 2.653493525244721e-06,
      "loss": 10.9566,
      "step": 45
    },
    {
      "epoch": 0.006992541921998955,
      "grad_norm": 10.933311462402344,
      "learning_rate": 1.70370868554659e-06,
      "loss": 10.6738,
      "step": 46
    },
    {
      "epoch": 0.007144553702911976,
      "grad_norm": 10.83802318572998,
      "learning_rate": 9.607359798384785e-07,
      "loss": 10.5406,
      "step": 47
    },
    {
      "epoch": 0.007296565483824996,
      "grad_norm": 11.648588180541992,
      "learning_rate": 4.277569313094809e-07,
      "loss": 12.5734,
      "step": 48
    },
    {
      "epoch": 0.007448577264738018,
      "grad_norm": 15.444548606872559,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 11.7787,
      "step": 49
    },
    {
      "epoch": 0.007600589045651038,
      "grad_norm": 11.467397689819336,
      "learning_rate": 0.0,
      "loss": 12.5185,
      "step": 50
    },
    {
      "epoch": 0.007600589045651038,
      "eval_loss": 0.6467951536178589,
      "eval_runtime": 2213.672,
      "eval_samples_per_second": 20.02,
      "eval_steps_per_second": 2.503,
      "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": 1.1089660061406986e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}