{
  "best_metric": 0.5565019249916077,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.01638504864311316,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003277009728622632,
      "grad_norm": 30.181488037109375,
      "learning_rate": 5e-05,
      "loss": 15.7506,
      "step": 1
    },
    {
      "epoch": 0.0003277009728622632,
      "eval_loss": 14.837973594665527,
      "eval_runtime": 538.4168,
      "eval_samples_per_second": 38.182,
      "eval_steps_per_second": 4.773,
      "step": 1
    },
    {
      "epoch": 0.0006554019457245264,
      "grad_norm": 28.775192260742188,
      "learning_rate": 0.0001,
      "loss": 15.5087,
      "step": 2
    },
    {
      "epoch": 0.0009831029185867896,
      "grad_norm": 36.533443450927734,
      "learning_rate": 9.989294616193017e-05,
      "loss": 14.2783,
      "step": 3
    },
    {
      "epoch": 0.0013108038914490527,
      "grad_norm": 31.35615348815918,
      "learning_rate": 9.957224306869053e-05,
      "loss": 7.7579,
      "step": 4
    },
    {
      "epoch": 0.001638504864311316,
      "grad_norm": 34.71210861206055,
      "learning_rate": 9.903926402016153e-05,
      "loss": 4.208,
      "step": 5
    },
    {
      "epoch": 0.001966205837173579,
      "grad_norm": 8.36011791229248,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.4882,
      "step": 6
    },
    {
      "epoch": 0.0022939068100358423,
      "grad_norm": 1.6463147401809692,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.1091,
      "step": 7
    },
    {
      "epoch": 0.0026216077828981055,
      "grad_norm": 0.13828271627426147,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0024,
      "step": 8
    },
    {
      "epoch": 0.0029493087557603687,
      "grad_norm": 0.3082248568534851,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0057,
      "step": 9
    },
    {
      "epoch": 0.003277009728622632,
      "grad_norm": 0.014849074184894562,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0002,
      "step": 10
    },
    {
      "epoch": 0.003604710701484895,
      "grad_norm": 0.018249884247779846,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0002,
      "step": 11
    },
    {
      "epoch": 0.003932411674347158,
      "grad_norm": 36.80230712890625,
      "learning_rate": 8.966766701456177e-05,
      "loss": 6.8876,
      "step": 12
    },
    {
      "epoch": 0.004260112647209421,
      "grad_norm": 21.303375244140625,
      "learning_rate": 8.759199037394887e-05,
      "loss": 5.4719,
      "step": 13
    },
    {
      "epoch": 0.004587813620071685,
      "grad_norm": 0.6932873129844666,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0059,
      "step": 14
    },
    {
      "epoch": 0.004915514592933948,
      "grad_norm": 1.0240111351013184,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0868,
      "step": 15
    },
    {
      "epoch": 0.005243215565796211,
      "grad_norm": 0.6676509380340576,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0489,
      "step": 16
    },
    {
      "epoch": 0.005570916538658474,
      "grad_norm": 0.1473751962184906,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0041,
      "step": 17
    },
    {
      "epoch": 0.005898617511520737,
      "grad_norm": 0.912452757358551,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0809,
      "step": 18
    },
    {
      "epoch": 0.0062263184843830005,
      "grad_norm": 0.22649067640304565,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0011,
      "step": 19
    },
    {
      "epoch": 0.006554019457245264,
      "grad_norm": 0.43677258491516113,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0031,
      "step": 20
    },
    {
      "epoch": 0.006881720430107527,
      "grad_norm": 0.06740288436412811,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0005,
      "step": 21
    },
    {
      "epoch": 0.00720942140296979,
      "grad_norm": 0.017923539504408836,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0002,
      "step": 22
    },
    {
      "epoch": 0.007537122375832053,
      "grad_norm": 0.007839135825634003,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0001,
      "step": 23
    },
    {
      "epoch": 0.007864823348694316,
      "grad_norm": 7.1645731925964355,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.2633,
      "step": 24
    },
    {
      "epoch": 0.00819252432155658,
      "grad_norm": 48.91357421875,
      "learning_rate": 5.327015646150716e-05,
      "loss": 7.2444,
      "step": 25
    },
    {
      "epoch": 0.00819252432155658,
      "eval_loss": 0.6356422305107117,
      "eval_runtime": 537.7317,
      "eval_samples_per_second": 38.231,
      "eval_steps_per_second": 4.779,
      "step": 25
    },
    {
      "epoch": 0.008520225294418843,
      "grad_norm": 0.059100646525621414,
      "learning_rate": 5e-05,
      "loss": 0.0004,
      "step": 26
    },
    {
      "epoch": 0.008847926267281106,
      "grad_norm": 0.9721323847770691,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0607,
      "step": 27
    },
    {
      "epoch": 0.00917562724014337,
      "grad_norm": 0.023191077634692192,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0003,
      "step": 28
    },
    {
      "epoch": 0.009503328213005632,
      "grad_norm": 0.12030933797359467,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0012,
      "step": 29
    },
    {
      "epoch": 0.009831029185867896,
      "grad_norm": 0.2080373764038086,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0216,
      "step": 30
    },
    {
      "epoch": 0.010158730158730159,
      "grad_norm": 0.3661039173603058,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0039,
      "step": 31
    },
    {
      "epoch": 0.010486431131592422,
      "grad_norm": 0.04480292275547981,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0006,
      "step": 32
    },
    {
      "epoch": 0.010814132104454685,
      "grad_norm": 0.01847970113158226,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0003,
      "step": 33
    },
    {
      "epoch": 0.011141833077316948,
      "grad_norm": 0.010702378116548061,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0002,
      "step": 34
    },
    {
      "epoch": 0.011469534050179211,
      "grad_norm": 0.011056789197027683,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0002,
      "step": 35
    },
    {
      "epoch": 0.011797235023041475,
      "grad_norm": 0.013891864567995071,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0002,
      "step": 36
    },
    {
      "epoch": 0.012124935995903738,
      "grad_norm": 15.3453369140625,
      "learning_rate": 1.703270924499656e-05,
      "loss": 3.996,
      "step": 37
    },
    {
      "epoch": 0.012452636968766001,
      "grad_norm": 15.295425415039062,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.3321,
      "step": 38
    },
    {
      "epoch": 0.012780337941628264,
      "grad_norm": 1.5840622186660767,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0517,
      "step": 39
    },
    {
      "epoch": 0.013108038914490527,
      "grad_norm": 1.8281114101409912,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.1035,
      "step": 40
    },
    {
      "epoch": 0.01343573988735279,
      "grad_norm": 0.43321263790130615,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0072,
      "step": 41
    },
    {
      "epoch": 0.013763440860215054,
      "grad_norm": 0.007399904541671276,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0001,
      "step": 42
    },
    {
      "epoch": 0.014091141833077317,
      "grad_norm": 0.011308839544653893,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0001,
      "step": 43
    },
    {
      "epoch": 0.01441884280593958,
      "grad_norm": 0.010303402319550514,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0001,
      "step": 44
    },
    {
      "epoch": 0.014746543778801843,
      "grad_norm": 0.022859793156385422,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0002,
      "step": 45
    },
    {
      "epoch": 0.015074244751664106,
      "grad_norm": 0.00979696772992611,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0001,
      "step": 46
    },
    {
      "epoch": 0.01540194572452637,
      "grad_norm": 0.008724894374608994,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0001,
      "step": 47
    },
    {
      "epoch": 0.015729646697388633,
      "grad_norm": 0.00915119331330061,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0001,
      "step": 48
    },
    {
      "epoch": 0.016057347670250896,
      "grad_norm": 1.035159945487976,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.2291,
      "step": 49
    },
    {
      "epoch": 0.01638504864311316,
      "grad_norm": 16.994882583618164,
      "learning_rate": 0.0,
      "loss": 6.3963,
      "step": 50
    },
    {
      "epoch": 0.01638504864311316,
      "eval_loss": 0.5565019249916077,
      "eval_runtime": 537.8031,
      "eval_samples_per_second": 38.226,
      "eval_steps_per_second": 4.779,
      "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": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}