{
  "best_metric": 2.034497022628784,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.02387774594078319,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004775549188156638,
      "grad_norm": 9.347432136535645,
      "learning_rate": 5.000000000000001e-07,
      "loss": 5.3462,
      "step": 1
    },
    {
      "epoch": 0.0004775549188156638,
      "eval_loss": 5.48677921295166,
      "eval_runtime": 284.3378,
      "eval_samples_per_second": 12.404,
      "eval_steps_per_second": 3.102,
      "step": 1
    },
    {
      "epoch": 0.0009551098376313276,
      "grad_norm": 12.377089500427246,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 5.1933,
      "step": 2
    },
    {
      "epoch": 0.0014326647564469914,
      "grad_norm": 12.349013328552246,
      "learning_rate": 1.5e-06,
      "loss": 4.9968,
      "step": 3
    },
    {
      "epoch": 0.0019102196752626551,
      "grad_norm": 11.239097595214844,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 4.6409,
      "step": 4
    },
    {
      "epoch": 0.002387774594078319,
      "grad_norm": 11.543905258178711,
      "learning_rate": 2.5e-06,
      "loss": 4.8898,
      "step": 5
    },
    {
      "epoch": 0.0028653295128939827,
      "grad_norm": 12.293774604797363,
      "learning_rate": 3e-06,
      "loss": 4.8907,
      "step": 6
    },
    {
      "epoch": 0.0033428844317096467,
      "grad_norm": 14.24751091003418,
      "learning_rate": 3.5e-06,
      "loss": 5.0227,
      "step": 7
    },
    {
      "epoch": 0.0038204393505253103,
      "grad_norm": 12.195391654968262,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.8788,
      "step": 8
    },
    {
      "epoch": 0.004297994269340974,
      "grad_norm": 12.437620162963867,
      "learning_rate": 4.5e-06,
      "loss": 4.8141,
      "step": 9
    },
    {
      "epoch": 0.004775549188156638,
      "grad_norm": 13.941622734069824,
      "learning_rate": 5e-06,
      "loss": 5.4908,
      "step": 10
    },
    {
      "epoch": 0.0052531041069723014,
      "grad_norm": 10.540823936462402,
      "learning_rate": 4.99847706754774e-06,
      "loss": 4.571,
      "step": 11
    },
    {
      "epoch": 0.0057306590257879654,
      "grad_norm": 13.182141304016113,
      "learning_rate": 4.993910125649561e-06,
      "loss": 4.7975,
      "step": 12
    },
    {
      "epoch": 0.0062082139446036294,
      "grad_norm": 12.168252944946289,
      "learning_rate": 4.986304738420684e-06,
      "loss": 4.6252,
      "step": 13
    },
    {
      "epoch": 0.0066857688634192934,
      "grad_norm": 13.87367057800293,
      "learning_rate": 4.975670171853926e-06,
      "loss": 5.0089,
      "step": 14
    },
    {
      "epoch": 0.0071633237822349575,
      "grad_norm": 13.06873607635498,
      "learning_rate": 4.962019382530521e-06,
      "loss": 4.9,
      "step": 15
    },
    {
      "epoch": 0.007640878701050621,
      "grad_norm": 12.240724563598633,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 4.8832,
      "step": 16
    },
    {
      "epoch": 0.008118433619866285,
      "grad_norm": 12.596060752868652,
      "learning_rate": 4.925739315689991e-06,
      "loss": 4.6627,
      "step": 17
    },
    {
      "epoch": 0.008595988538681949,
      "grad_norm": 13.38196086883545,
      "learning_rate": 4.903154239845798e-06,
      "loss": 4.6124,
      "step": 18
    },
    {
      "epoch": 0.009073543457497613,
      "grad_norm": 11.647727012634277,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 4.6635,
      "step": 19
    },
    {
      "epoch": 0.009551098376313277,
      "grad_norm": 12.103982925415039,
      "learning_rate": 4.849231551964771e-06,
      "loss": 4.7775,
      "step": 20
    },
    {
      "epoch": 0.01002865329512894,
      "grad_norm": 11.481264114379883,
      "learning_rate": 4.817959636416969e-06,
      "loss": 4.3368,
      "step": 21
    },
    {
      "epoch": 0.010506208213944603,
      "grad_norm": 13.471817970275879,
      "learning_rate": 4.783863644106502e-06,
      "loss": 4.4957,
      "step": 22
    },
    {
      "epoch": 0.010983763132760267,
      "grad_norm": 9.855433464050293,
      "learning_rate": 4.746985115747918e-06,
      "loss": 4.0167,
      "step": 23
    },
    {
      "epoch": 0.011461318051575931,
      "grad_norm": 12.636857986450195,
      "learning_rate": 4.707368982147318e-06,
      "loss": 4.0593,
      "step": 24
    },
    {
      "epoch": 0.011938872970391595,
      "grad_norm": 10.027217864990234,
      "learning_rate": 4.665063509461098e-06,
      "loss": 3.9518,
      "step": 25
    },
    {
      "epoch": 0.012416427889207259,
      "grad_norm": 10.685080528259277,
      "learning_rate": 4.620120240391065e-06,
      "loss": 3.982,
      "step": 26
    },
    {
      "epoch": 0.012893982808022923,
      "grad_norm": 9.640650749206543,
      "learning_rate": 4.572593931387604e-06,
      "loss": 3.5976,
      "step": 27
    },
    {
      "epoch": 0.013371537726838587,
      "grad_norm": 9.506843566894531,
      "learning_rate": 4.522542485937369e-06,
      "loss": 3.7473,
      "step": 28
    },
    {
      "epoch": 0.013849092645654251,
      "grad_norm": 10.801132202148438,
      "learning_rate": 4.470026884016805e-06,
      "loss": 3.5658,
      "step": 29
    },
    {
      "epoch": 0.014326647564469915,
      "grad_norm": 11.784551620483398,
      "learning_rate": 4.415111107797445e-06,
      "loss": 3.7832,
      "step": 30
    },
    {
      "epoch": 0.014804202483285577,
      "grad_norm": 8.963501930236816,
      "learning_rate": 4.357862063693486e-06,
      "loss": 3.5075,
      "step": 31
    },
    {
      "epoch": 0.015281757402101241,
      "grad_norm": 9.36789608001709,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 3.2037,
      "step": 32
    },
    {
      "epoch": 0.015759312320916905,
      "grad_norm": 9.043115615844727,
      "learning_rate": 4.236645926147493e-06,
      "loss": 3.2947,
      "step": 33
    },
    {
      "epoch": 0.01623686723973257,
      "grad_norm": 10.07559585571289,
      "learning_rate": 4.172826515897146e-06,
      "loss": 3.1557,
      "step": 34
    },
    {
      "epoch": 0.016714422158548233,
      "grad_norm": 7.442198753356934,
      "learning_rate": 4.106969024216348e-06,
      "loss": 3.0398,
      "step": 35
    },
    {
      "epoch": 0.017191977077363897,
      "grad_norm": 8.295598030090332,
      "learning_rate": 4.039153688314146e-06,
      "loss": 2.8331,
      "step": 36
    },
    {
      "epoch": 0.01766953199617956,
      "grad_norm": 7.8947672843933105,
      "learning_rate": 3.969463130731183e-06,
      "loss": 2.6244,
      "step": 37
    },
    {
      "epoch": 0.018147086914995225,
      "grad_norm": 7.704997539520264,
      "learning_rate": 3.897982258676867e-06,
      "loss": 2.7215,
      "step": 38
    },
    {
      "epoch": 0.01862464183381089,
      "grad_norm": 8.61429214477539,
      "learning_rate": 3.824798160583012e-06,
      "loss": 2.5506,
      "step": 39
    },
    {
      "epoch": 0.019102196752626553,
      "grad_norm": 8.975998878479004,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 2.714,
      "step": 40
    },
    {
      "epoch": 0.019579751671442217,
      "grad_norm": 7.6730852127075195,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 2.5664,
      "step": 41
    },
    {
      "epoch": 0.02005730659025788,
      "grad_norm": 7.653818130493164,
      "learning_rate": 3.595927866972694e-06,
      "loss": 2.545,
      "step": 42
    },
    {
      "epoch": 0.020534861509073542,
      "grad_norm": 7.733112812042236,
      "learning_rate": 3.516841607689501e-06,
      "loss": 2.7532,
      "step": 43
    },
    {
      "epoch": 0.021012416427889206,
      "grad_norm": 6.177231788635254,
      "learning_rate": 3.436516483539781e-06,
      "loss": 2.2501,
      "step": 44
    },
    {
      "epoch": 0.02148997134670487,
      "grad_norm": 7.65936279296875,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 2.4602,
      "step": 45
    },
    {
      "epoch": 0.021967526265520534,
      "grad_norm": 6.365522861480713,
      "learning_rate": 3.272542485937369e-06,
      "loss": 2.2169,
      "step": 46
    },
    {
      "epoch": 0.022445081184336198,
      "grad_norm": 6.711042881011963,
      "learning_rate": 3.189093389542498e-06,
      "loss": 2.5377,
      "step": 47
    },
    {
      "epoch": 0.022922636103151862,
      "grad_norm": 6.240805149078369,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 2.2621,
      "step": 48
    },
    {
      "epoch": 0.023400191021967526,
      "grad_norm": 7.034709930419922,
      "learning_rate": 3.019779227044398e-06,
      "loss": 2.4773,
      "step": 49
    },
    {
      "epoch": 0.02387774594078319,
      "grad_norm": 8.449440002441406,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 2.6908,
      "step": 50
    },
    {
      "epoch": 0.02387774594078319,
      "eval_loss": 2.034497022628784,
      "eval_runtime": 285.2397,
      "eval_samples_per_second": 12.365,
      "eval_steps_per_second": 3.092,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 7.474514381871514e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}