{
  "best_metric": 3.6382930278778076,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.4306864064602961,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008613728129205921,
      "grad_norm": 8.621166229248047,
      "learning_rate": 5e-05,
      "loss": 5.9662,
      "step": 1
    },
    {
      "epoch": 0.008613728129205921,
      "eval_loss": 6.015687465667725,
      "eval_runtime": 51.285,
      "eval_samples_per_second": 30.516,
      "eval_steps_per_second": 3.822,
      "step": 1
    },
    {
      "epoch": 0.017227456258411843,
      "grad_norm": 8.646073341369629,
      "learning_rate": 0.0001,
      "loss": 5.9731,
      "step": 2
    },
    {
      "epoch": 0.025841184387617767,
      "grad_norm": 6.40777063369751,
      "learning_rate": 9.989294616193017e-05,
      "loss": 5.3808,
      "step": 3
    },
    {
      "epoch": 0.034454912516823685,
      "grad_norm": 6.907791614532471,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.6488,
      "step": 4
    },
    {
      "epoch": 0.04306864064602961,
      "grad_norm": 6.008575916290283,
      "learning_rate": 9.903926402016153e-05,
      "loss": 4.7241,
      "step": 5
    },
    {
      "epoch": 0.051682368775235535,
      "grad_norm": 2.99879789352417,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.3932,
      "step": 6
    },
    {
      "epoch": 0.06029609690444145,
      "grad_norm": 2.1534507274627686,
      "learning_rate": 9.73465064747553e-05,
      "loss": 4.3133,
      "step": 7
    },
    {
      "epoch": 0.06890982503364737,
      "grad_norm": 1.539284586906433,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.2875,
      "step": 8
    },
    {
      "epoch": 0.0775235531628533,
      "grad_norm": 2.644103765487671,
      "learning_rate": 9.484363707663442e-05,
      "loss": 4.1579,
      "step": 9
    },
    {
      "epoch": 0.08613728129205922,
      "grad_norm": 1.4669588804244995,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.1628,
      "step": 10
    },
    {
      "epoch": 0.09475100942126514,
      "grad_norm": 2.6391141414642334,
      "learning_rate": 9.157348061512727e-05,
      "loss": 4.0895,
      "step": 11
    },
    {
      "epoch": 0.10336473755047107,
      "grad_norm": 2.538189172744751,
      "learning_rate": 8.966766701456177e-05,
      "loss": 4.2041,
      "step": 12
    },
    {
      "epoch": 0.11197846567967698,
      "grad_norm": 1.882711410522461,
      "learning_rate": 8.759199037394887e-05,
      "loss": 4.0812,
      "step": 13
    },
    {
      "epoch": 0.1205921938088829,
      "grad_norm": 2.0528578758239746,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.0125,
      "step": 14
    },
    {
      "epoch": 0.12920592193808883,
      "grad_norm": 1.435665249824524,
      "learning_rate": 8.296729075500344e-05,
      "loss": 3.9734,
      "step": 15
    },
    {
      "epoch": 0.13781965006729474,
      "grad_norm": 1.474025845527649,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.94,
      "step": 16
    },
    {
      "epoch": 0.14643337819650068,
      "grad_norm": 0.8223435282707214,
      "learning_rate": 7.777851165098012e-05,
      "loss": 3.8397,
      "step": 17
    },
    {
      "epoch": 0.1550471063257066,
      "grad_norm": 1.2248499393463135,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.7874,
      "step": 18
    },
    {
      "epoch": 0.16366083445491253,
      "grad_norm": 0.9229756593704224,
      "learning_rate": 7.211443451095007e-05,
      "loss": 3.7918,
      "step": 19
    },
    {
      "epoch": 0.17227456258411844,
      "grad_norm": 1.1294457912445068,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.7745,
      "step": 20
    },
    {
      "epoch": 0.18088829071332435,
      "grad_norm": 0.7340262532234192,
      "learning_rate": 6.607197326515808e-05,
      "loss": 3.7677,
      "step": 21
    },
    {
      "epoch": 0.1895020188425303,
      "grad_norm": 1.462469220161438,
      "learning_rate": 6.294095225512603e-05,
      "loss": 3.6771,
      "step": 22
    },
    {
      "epoch": 0.1981157469717362,
      "grad_norm": 0.8678246140480042,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 3.7254,
      "step": 23
    },
    {
      "epoch": 0.20672947510094214,
      "grad_norm": 1.3767180442810059,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 3.7285,
      "step": 24
    },
    {
      "epoch": 0.21534320323014805,
      "grad_norm": 1.0247037410736084,
      "learning_rate": 5.327015646150716e-05,
      "loss": 3.901,
      "step": 25
    },
    {
      "epoch": 0.21534320323014805,
      "eval_loss": 3.7278997898101807,
      "eval_runtime": 51.3496,
      "eval_samples_per_second": 30.477,
      "eval_steps_per_second": 3.817,
      "step": 25
    },
    {
      "epoch": 0.22395693135935396,
      "grad_norm": 1.2998414039611816,
      "learning_rate": 5e-05,
      "loss": 3.7794,
      "step": 26
    },
    {
      "epoch": 0.2325706594885599,
      "grad_norm": 1.6861227750778198,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 3.756,
      "step": 27
    },
    {
      "epoch": 0.2411843876177658,
      "grad_norm": 1.0421063899993896,
      "learning_rate": 4.347369038899744e-05,
      "loss": 3.7032,
      "step": 28
    },
    {
      "epoch": 0.24979811574697175,
      "grad_norm": 1.0148087739944458,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 3.7074,
      "step": 29
    },
    {
      "epoch": 0.25841184387617766,
      "grad_norm": 1.1693507432937622,
      "learning_rate": 3.705904774487396e-05,
      "loss": 3.682,
      "step": 30
    },
    {
      "epoch": 0.26702557200538357,
      "grad_norm": 0.6761946082115173,
      "learning_rate": 3.392802673484193e-05,
      "loss": 3.6466,
      "step": 31
    },
    {
      "epoch": 0.2756393001345895,
      "grad_norm": 0.856696367263794,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.6619,
      "step": 32
    },
    {
      "epoch": 0.28425302826379545,
      "grad_norm": 0.832834005355835,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 3.6142,
      "step": 33
    },
    {
      "epoch": 0.29286675639300136,
      "grad_norm": 0.8012253642082214,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.6064,
      "step": 34
    },
    {
      "epoch": 0.30148048452220727,
      "grad_norm": 0.8955758213996887,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 3.6216,
      "step": 35
    },
    {
      "epoch": 0.3100942126514132,
      "grad_norm": 0.9002861380577087,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 3.6473,
      "step": 36
    },
    {
      "epoch": 0.3187079407806191,
      "grad_norm": 1.002937912940979,
      "learning_rate": 1.703270924499656e-05,
      "loss": 3.7539,
      "step": 37
    },
    {
      "epoch": 0.32732166890982506,
      "grad_norm": 0.7870951294898987,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.7668,
      "step": 38
    },
    {
      "epoch": 0.33593539703903097,
      "grad_norm": 0.7260990142822266,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 3.6595,
      "step": 39
    },
    {
      "epoch": 0.3445491251682369,
      "grad_norm": 0.726902186870575,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 3.7027,
      "step": 40
    },
    {
      "epoch": 0.3531628532974428,
      "grad_norm": 0.8145126700401306,
      "learning_rate": 8.426519384872733e-06,
      "loss": 3.6087,
      "step": 41
    },
    {
      "epoch": 0.3617765814266487,
      "grad_norm": 0.7508212327957153,
      "learning_rate": 6.698729810778065e-06,
      "loss": 3.6261,
      "step": 42
    },
    {
      "epoch": 0.37039030955585467,
      "grad_norm": 0.7382489442825317,
      "learning_rate": 5.156362923365588e-06,
      "loss": 3.5965,
      "step": 43
    },
    {
      "epoch": 0.3790040376850606,
      "grad_norm": 0.6966142654418945,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.5584,
      "step": 44
    },
    {
      "epoch": 0.3876177658142665,
      "grad_norm": 0.6668608784675598,
      "learning_rate": 2.653493525244721e-06,
      "loss": 3.575,
      "step": 45
    },
    {
      "epoch": 0.3962314939434724,
      "grad_norm": 0.6239801645278931,
      "learning_rate": 1.70370868554659e-06,
      "loss": 3.6472,
      "step": 46
    },
    {
      "epoch": 0.4048452220726783,
      "grad_norm": 0.6501104831695557,
      "learning_rate": 9.607359798384785e-07,
      "loss": 3.5244,
      "step": 47
    },
    {
      "epoch": 0.4134589502018843,
      "grad_norm": 0.7032169103622437,
      "learning_rate": 4.277569313094809e-07,
      "loss": 3.5832,
      "step": 48
    },
    {
      "epoch": 0.4220726783310902,
      "grad_norm": 0.843285858631134,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 3.6745,
      "step": 49
    },
    {
      "epoch": 0.4306864064602961,
      "grad_norm": 1.0279968976974487,
      "learning_rate": 0.0,
      "loss": 3.8446,
      "step": 50
    },
    {
      "epoch": 0.4306864064602961,
      "eval_loss": 3.6382930278778076,
      "eval_runtime": 51.2906,
      "eval_samples_per_second": 30.512,
      "eval_steps_per_second": 3.821,
      "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": 1.2348958688935936e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}