{
  "best_metric": 2.0704262256622314,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.03065134099616858,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006130268199233716,
      "grad_norm": 0.1599140763282776,
      "learning_rate": 2e-05,
      "loss": 1.7499,
      "step": 1
    },
    {
      "epoch": 0.0006130268199233716,
      "eval_loss": 2.2616496086120605,
      "eval_runtime": 28.2683,
      "eval_samples_per_second": 97.176,
      "eval_steps_per_second": 12.169,
      "step": 1
    },
    {
      "epoch": 0.0012260536398467432,
      "grad_norm": 0.11475073546171188,
      "learning_rate": 4e-05,
      "loss": 1.2192,
      "step": 2
    },
    {
      "epoch": 0.0018390804597701149,
      "grad_norm": 0.1026509627699852,
      "learning_rate": 6e-05,
      "loss": 1.0756,
      "step": 3
    },
    {
      "epoch": 0.0024521072796934865,
      "grad_norm": 0.09442941099405289,
      "learning_rate": 8e-05,
      "loss": 1.0182,
      "step": 4
    },
    {
      "epoch": 0.0030651340996168583,
      "grad_norm": 0.1117192953824997,
      "learning_rate": 0.0001,
      "loss": 1.3139,
      "step": 5
    },
    {
      "epoch": 0.0036781609195402297,
      "grad_norm": 0.0832456722855568,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.0814,
      "step": 6
    },
    {
      "epoch": 0.004291187739463602,
      "grad_norm": 0.08672433346509933,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.9724,
      "step": 7
    },
    {
      "epoch": 0.004904214559386973,
      "grad_norm": 0.08209044486284256,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.3123,
      "step": 8
    },
    {
      "epoch": 0.005517241379310344,
      "grad_norm": 0.08572620153427124,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.3791,
      "step": 9
    },
    {
      "epoch": 0.006130268199233717,
      "grad_norm": 0.08743157982826233,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.4284,
      "step": 10
    },
    {
      "epoch": 0.006743295019157088,
      "grad_norm": 0.08872254192829132,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.5766,
      "step": 11
    },
    {
      "epoch": 0.0073563218390804595,
      "grad_norm": 0.09597641229629517,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.7662,
      "step": 12
    },
    {
      "epoch": 0.007969348659003832,
      "grad_norm": 0.09931649267673492,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.8283,
      "step": 13
    },
    {
      "epoch": 0.008582375478927203,
      "grad_norm": 0.09531239420175552,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6962,
      "step": 14
    },
    {
      "epoch": 0.009195402298850575,
      "grad_norm": 0.09666506946086884,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.691,
      "step": 15
    },
    {
      "epoch": 0.009808429118773946,
      "grad_norm": 0.08586005866527557,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.7425,
      "step": 16
    },
    {
      "epoch": 0.010421455938697317,
      "grad_norm": 0.09137546271085739,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.746,
      "step": 17
    },
    {
      "epoch": 0.011034482758620689,
      "grad_norm": 0.0885305404663086,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.7776,
      "step": 18
    },
    {
      "epoch": 0.011647509578544062,
      "grad_norm": 0.08917354047298431,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.0048,
      "step": 19
    },
    {
      "epoch": 0.012260536398467433,
      "grad_norm": 0.08948740363121033,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.8872,
      "step": 20
    },
    {
      "epoch": 0.012873563218390805,
      "grad_norm": 0.08577539771795273,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.8264,
      "step": 21
    },
    {
      "epoch": 0.013486590038314176,
      "grad_norm": 0.10036402195692062,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.4494,
      "step": 22
    },
    {
      "epoch": 0.014099616858237548,
      "grad_norm": 0.10516292601823807,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.6296,
      "step": 23
    },
    {
      "epoch": 0.014712643678160919,
      "grad_norm": 0.11859121173620224,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.6962,
      "step": 24
    },
    {
      "epoch": 0.01532567049808429,
      "grad_norm": 0.14447887241840363,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.9676,
      "step": 25
    },
    {
      "epoch": 0.01532567049808429,
      "eval_loss": 2.169510841369629,
      "eval_runtime": 28.2778,
      "eval_samples_per_second": 97.143,
      "eval_steps_per_second": 12.165,
      "step": 25
    },
    {
      "epoch": 0.015938697318007664,
      "grad_norm": 0.16475293040275574,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.5398,
      "step": 26
    },
    {
      "epoch": 0.016551724137931035,
      "grad_norm": 0.22766101360321045,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.229,
      "step": 27
    },
    {
      "epoch": 0.017164750957854406,
      "grad_norm": 0.24101488292217255,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.3215,
      "step": 28
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 0.1988028734922409,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.2015,
      "step": 29
    },
    {
      "epoch": 0.01839080459770115,
      "grad_norm": 0.21405185759067535,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.3046,
      "step": 30
    },
    {
      "epoch": 0.01900383141762452,
      "grad_norm": 0.17964892089366913,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.3912,
      "step": 31
    },
    {
      "epoch": 0.019616858237547892,
      "grad_norm": 0.188919797539711,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.3432,
      "step": 32
    },
    {
      "epoch": 0.020229885057471263,
      "grad_norm": 0.26917535066604614,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.0052,
      "step": 33
    },
    {
      "epoch": 0.020842911877394635,
      "grad_norm": 0.3175217807292938,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.9935,
      "step": 34
    },
    {
      "epoch": 0.021455938697318006,
      "grad_norm": 0.469002902507782,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.5468,
      "step": 35
    },
    {
      "epoch": 0.022068965517241378,
      "grad_norm": 0.653257429599762,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.6147,
      "step": 36
    },
    {
      "epoch": 0.022681992337164752,
      "grad_norm": 1.0501368045806885,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 3.5708,
      "step": 37
    },
    {
      "epoch": 0.023295019157088124,
      "grad_norm": 1.2141762971878052,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 3.5634,
      "step": 38
    },
    {
      "epoch": 0.023908045977011495,
      "grad_norm": 1.6670536994934082,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 4.1478,
      "step": 39
    },
    {
      "epoch": 0.024521072796934867,
      "grad_norm": 1.5715434551239014,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 3.7665,
      "step": 40
    },
    {
      "epoch": 0.025134099616858238,
      "grad_norm": 1.349192500114441,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.5277,
      "step": 41
    },
    {
      "epoch": 0.02574712643678161,
      "grad_norm": 1.0553473234176636,
      "learning_rate": 7.597595192178702e-06,
      "loss": 3.1882,
      "step": 42
    },
    {
      "epoch": 0.02636015325670498,
      "grad_norm": 1.0868961811065674,
      "learning_rate": 5.852620357053651e-06,
      "loss": 3.2809,
      "step": 43
    },
    {
      "epoch": 0.026973180076628352,
      "grad_norm": 0.9385594129562378,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.2855,
      "step": 44
    },
    {
      "epoch": 0.027586206896551724,
      "grad_norm": 1.038495421409607,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 3.2324,
      "step": 45
    },
    {
      "epoch": 0.028199233716475095,
      "grad_norm": 1.0660349130630493,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.3868,
      "step": 46
    },
    {
      "epoch": 0.028812260536398467,
      "grad_norm": 1.0207303762435913,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 3.1981,
      "step": 47
    },
    {
      "epoch": 0.029425287356321838,
      "grad_norm": 1.0714794397354126,
      "learning_rate": 4.865965629214819e-07,
      "loss": 3.2815,
      "step": 48
    },
    {
      "epoch": 0.03003831417624521,
      "grad_norm": 1.0691288709640503,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 3.1973,
      "step": 49
    },
    {
      "epoch": 0.03065134099616858,
      "grad_norm": 1.2095760107040405,
      "learning_rate": 0.0,
      "loss": 3.7897,
      "step": 50
    },
    {
      "epoch": 0.03065134099616858,
      "eval_loss": 2.0704262256622314,
      "eval_runtime": 28.2582,
      "eval_samples_per_second": 97.211,
      "eval_steps_per_second": 12.173,
      "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": 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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2447038336204800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}