{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.8465608465608465,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016931216931216932,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.016931216931216932,
      "eval_loss": NaN,
      "eval_runtime": 13.3899,
      "eval_samples_per_second": 29.724,
      "eval_steps_per_second": 3.734,
      "step": 1
    },
    {
      "epoch": 0.033862433862433865,
      "grad_norm": 0.0,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.050793650793650794,
      "grad_norm": 0.0,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.06772486772486773,
      "grad_norm": 0.0,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 0.0,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.10158730158730159,
      "grad_norm": 0.0,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.0,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.13544973544973546,
      "grad_norm": 0.0,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 0.0,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.1693121693121693,
      "grad_norm": 0.0,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.18624338624338624,
      "grad_norm": 0.0,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.20317460317460317,
      "grad_norm": 0.0,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.2201058201058201,
      "grad_norm": 0.0,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.0,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.0,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.2708994708994709,
      "grad_norm": 0.0,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.2878306878306878,
      "grad_norm": 0.0,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 0.0,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.3216931216931217,
      "grad_norm": 0.0,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.3386243386243386,
      "grad_norm": 0.0,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.0,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.3724867724867725,
      "grad_norm": 0.0,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.38941798941798944,
      "grad_norm": 0.0,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.40634920634920635,
      "grad_norm": 0.0,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.42328042328042326,
      "grad_norm": 0.0,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.42328042328042326,
      "eval_loss": NaN,
      "eval_runtime": 13.3712,
      "eval_samples_per_second": 29.766,
      "eval_steps_per_second": 3.739,
      "step": 25
    },
    {
      "epoch": 0.4402116402116402,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.0,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.0,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.491005291005291,
      "grad_norm": 0.0,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.0,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.5248677248677248,
      "grad_norm": 0.0,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.5417989417989418,
      "grad_norm": 0.0,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.5587301587301587,
      "grad_norm": 0.0,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.5756613756613757,
      "grad_norm": 0.0,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.0,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 0.0,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.6264550264550265,
      "grad_norm": 0.0,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.6433862433862434,
      "grad_norm": 0.0,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.6603174603174603,
      "grad_norm": 0.0,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.6772486772486772,
      "grad_norm": 0.0,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.6941798941798942,
      "grad_norm": 0.0,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.0,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.728042328042328,
      "grad_norm": 0.0,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.744973544973545,
      "grad_norm": 0.0,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.0,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.7788359788359789,
      "grad_norm": 0.0,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.7957671957671958,
      "grad_norm": 0.0,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.8126984126984127,
      "grad_norm": 0.0,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.0,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.8465608465608465,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.8465608465608465,
      "eval_loss": NaN,
      "eval_runtime": 13.3791,
      "eval_samples_per_second": 29.748,
      "eval_steps_per_second": 3.737,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.967137622687744e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}