{
  "best_metric": 0.9273486137390137,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.35842293906810035,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014336917562724014,
      "grad_norm": 0.6213638782501221,
      "learning_rate": 5e-05,
      "loss": 1.0649,
      "step": 1
    },
    {
      "epoch": 0.014336917562724014,
      "eval_loss": 1.3422572612762451,
      "eval_runtime": 5.6069,
      "eval_samples_per_second": 83.826,
      "eval_steps_per_second": 10.523,
      "step": 1
    },
    {
      "epoch": 0.02867383512544803,
      "grad_norm": 0.649164080619812,
      "learning_rate": 0.0001,
      "loss": 1.095,
      "step": 2
    },
    {
      "epoch": 0.043010752688172046,
      "grad_norm": 0.5671748518943787,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.9873,
      "step": 3
    },
    {
      "epoch": 0.05734767025089606,
      "grad_norm": 0.4552786946296692,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.0297,
      "step": 4
    },
    {
      "epoch": 0.07168458781362007,
      "grad_norm": 0.4016531705856323,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.9408,
      "step": 5
    },
    {
      "epoch": 0.08602150537634409,
      "grad_norm": 0.4510401487350464,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.9504,
      "step": 6
    },
    {
      "epoch": 0.1003584229390681,
      "grad_norm": 0.4686371088027954,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.9787,
      "step": 7
    },
    {
      "epoch": 0.11469534050179211,
      "grad_norm": 0.5549091696739197,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.9985,
      "step": 8
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 0.5296815633773804,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.0088,
      "step": 9
    },
    {
      "epoch": 0.14336917562724014,
      "grad_norm": 0.5552384853363037,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.1156,
      "step": 10
    },
    {
      "epoch": 0.15770609318996415,
      "grad_norm": 0.5902155637741089,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.2264,
      "step": 11
    },
    {
      "epoch": 0.17204301075268819,
      "grad_norm": 0.8949041366577148,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.3434,
      "step": 12
    },
    {
      "epoch": 0.1863799283154122,
      "grad_norm": 0.6701123714447021,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.0776,
      "step": 13
    },
    {
      "epoch": 0.2007168458781362,
      "grad_norm": 0.5380650758743286,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.918,
      "step": 14
    },
    {
      "epoch": 0.21505376344086022,
      "grad_norm": 0.44414275884628296,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.8055,
      "step": 15
    },
    {
      "epoch": 0.22939068100358423,
      "grad_norm": 0.32161274552345276,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.8237,
      "step": 16
    },
    {
      "epoch": 0.24372759856630824,
      "grad_norm": 0.2952149212360382,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.8208,
      "step": 17
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 0.2965078353881836,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8949,
      "step": 18
    },
    {
      "epoch": 0.2724014336917563,
      "grad_norm": 0.3145495057106018,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.8765,
      "step": 19
    },
    {
      "epoch": 0.2867383512544803,
      "grad_norm": 0.30555495619773865,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.9,
      "step": 20
    },
    {
      "epoch": 0.3010752688172043,
      "grad_norm": 0.3113645017147064,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.9633,
      "step": 21
    },
    {
      "epoch": 0.3154121863799283,
      "grad_norm": 0.3889707326889038,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.9765,
      "step": 22
    },
    {
      "epoch": 0.32974910394265233,
      "grad_norm": 0.4638270437717438,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.0945,
      "step": 23
    },
    {
      "epoch": 0.34408602150537637,
      "grad_norm": 0.49984094500541687,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.0843,
      "step": 24
    },
    {
      "epoch": 0.35842293906810035,
      "grad_norm": 0.8894054889678955,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.1579,
      "step": 25
    },
    {
      "epoch": 0.35842293906810035,
      "eval_loss": 0.9273486137390137,
      "eval_runtime": 5.6191,
      "eval_samples_per_second": 83.643,
      "eval_steps_per_second": 10.5,
      "step": 25
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.337414377668608e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}