{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 2.5636942675159236,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.050955414012738856,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.050955414012738856,
      "eval_loss": NaN,
      "eval_runtime": 1.4807,
      "eval_samples_per_second": 33.768,
      "eval_steps_per_second": 8.78,
      "step": 1
    },
    {
      "epoch": 0.10191082802547771,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.15286624203821655,
      "grad_norm": NaN,
      "learning_rate": 9.993166823949923e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.20382165605095542,
      "grad_norm": NaN,
      "learning_rate": 9.972688047930772e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.25477707006369427,
      "grad_norm": NaN,
      "learning_rate": 9.938625865312251e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.3057324840764331,
      "grad_norm": NaN,
      "learning_rate": 9.891083721823461e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.35668789808917195,
      "grad_norm": NaN,
      "learning_rate": 9.830206001391626e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.40764331210191085,
      "grad_norm": NaN,
      "learning_rate": 9.756177587652856e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.4585987261146497,
      "grad_norm": NaN,
      "learning_rate": 9.669223302466608e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.5095541401273885,
      "grad_norm": NaN,
      "learning_rate": 9.5696072231391e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.5605095541401274,
      "grad_norm": NaN,
      "learning_rate": 9.4576318804292e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.6114649681528662,
      "grad_norm": NaN,
      "learning_rate": 9.333637339772472e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.6624203821656051,
      "grad_norm": NaN,
      "learning_rate": 9.198000168513604e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.7133757961783439,
      "grad_norm": NaN,
      "learning_rate": 9.051132292283771e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.7643312101910829,
      "grad_norm": NaN,
      "learning_rate": 8.893479743996034e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.8152866242038217,
      "grad_norm": NaN,
      "learning_rate": 8.725521309258031e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.8662420382165605,
      "grad_norm": NaN,
      "learning_rate": 8.547767072315835e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.9171974522292994,
      "grad_norm": NaN,
      "learning_rate": 8.360756866944858e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.9681528662420382,
      "grad_norm": NaN,
      "learning_rate": 8.165058636992411e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.0270700636942676,
      "grad_norm": NaN,
      "learning_rate": 7.961266711550922e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.0780254777070064,
      "grad_norm": NaN,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.1289808917197452,
      "grad_norm": NaN,
      "learning_rate": 7.531900112399004e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.179936305732484,
      "grad_norm": NaN,
      "learning_rate": 7.307629410938363e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.230891719745223,
      "grad_norm": NaN,
      "learning_rate": 7.077868998367395e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.2818471337579618,
      "grad_norm": NaN,
      "learning_rate": 6.843316649507626e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.2818471337579618,
      "eval_loss": NaN,
      "eval_runtime": 1.4788,
      "eval_samples_per_second": 33.812,
      "eval_steps_per_second": 8.791,
      "step": 25
    },
    {
      "epoch": 1.3328025477707006,
      "grad_norm": NaN,
      "learning_rate": 6.604684692133597e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 1.3837579617834395,
      "grad_norm": NaN,
      "learning_rate": 6.362697843656823e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 1.4347133757961783,
      "grad_norm": NaN,
      "learning_rate": 6.118091010182837e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 1.4856687898089171,
      "grad_norm": NaN,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 1.5366242038216562,
      "grad_norm": NaN,
      "learning_rate": 5.62399454065673e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 1.587579617834395,
      "grad_norm": NaN,
      "learning_rate": 5.376005459343272e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 1.638535031847134,
      "grad_norm": NaN,
      "learning_rate": 5.128392945374505e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 1.6894904458598727,
      "grad_norm": NaN,
      "learning_rate": 4.881908989817163e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 1.7404458598726116,
      "grad_norm": NaN,
      "learning_rate": 4.6373021563431784e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 1.7914012738853504,
      "grad_norm": NaN,
      "learning_rate": 4.395315307866405e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 1.8423566878980893,
      "grad_norm": NaN,
      "learning_rate": 4.156683350492376e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 1.893312101910828,
      "grad_norm": NaN,
      "learning_rate": 3.922131001632606e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 1.944267515923567,
      "grad_norm": NaN,
      "learning_rate": 3.692370589061639e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 2.0031847133757963,
      "grad_norm": NaN,
      "learning_rate": 3.468099887600999e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 2.054140127388535,
      "grad_norm": NaN,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 2.105095541401274,
      "grad_norm": NaN,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 2.156050955414013,
      "grad_norm": NaN,
      "learning_rate": 2.8349413630075906e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 2.2070063694267517,
      "grad_norm": NaN,
      "learning_rate": 2.639243133055145e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 2.2579617834394905,
      "grad_norm": NaN,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 2.3089171974522293,
      "grad_norm": NaN,
      "learning_rate": 2.2744786907419703e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 2.359872611464968,
      "grad_norm": NaN,
      "learning_rate": 2.1065202560039677e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 2.410828025477707,
      "grad_norm": NaN,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 2.461783439490446,
      "grad_norm": NaN,
      "learning_rate": 1.8019998314863974e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 2.5127388535031847,
      "grad_norm": NaN,
      "learning_rate": 1.6663626602275288e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 2.5636942675159236,
      "grad_norm": NaN,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 2.5636942675159236,
      "eval_loss": NaN,
      "eval_runtime": 1.4786,
      "eval_samples_per_second": 33.816,
      "eval_steps_per_second": 8.792,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 59,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 5.259156315439104e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}