{
  "best_metric": 0.6713224649429321,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.003800294522825519,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015201178091302076,
      "grad_norm": 3.6806018352508545,
      "learning_rate": 5e-05,
      "loss": 10.9362,
      "step": 1
    },
    {
      "epoch": 0.00015201178091302076,
      "eval_loss": 2.270036220550537,
      "eval_runtime": 2215.3772,
      "eval_samples_per_second": 20.005,
      "eval_steps_per_second": 2.501,
      "step": 1
    },
    {
      "epoch": 0.0003040235618260415,
      "grad_norm": 4.281136512756348,
      "learning_rate": 0.0001,
      "loss": 12.8607,
      "step": 2
    },
    {
      "epoch": 0.00045603534273906226,
      "grad_norm": 4.480587959289551,
      "learning_rate": 9.989294616193017e-05,
      "loss": 13.5915,
      "step": 3
    },
    {
      "epoch": 0.000608047123652083,
      "grad_norm": 5.4237823486328125,
      "learning_rate": 9.957224306869053e-05,
      "loss": 14.347,
      "step": 4
    },
    {
      "epoch": 0.0007600589045651038,
      "grad_norm": 7.418390274047852,
      "learning_rate": 9.903926402016153e-05,
      "loss": 16.8128,
      "step": 5
    },
    {
      "epoch": 0.0009120706854781245,
      "grad_norm": 7.381852149963379,
      "learning_rate": 9.829629131445342e-05,
      "loss": 16.2258,
      "step": 6
    },
    {
      "epoch": 0.0010640824663911454,
      "grad_norm": 8.722169876098633,
      "learning_rate": 9.73465064747553e-05,
      "loss": 16.6006,
      "step": 7
    },
    {
      "epoch": 0.001216094247304166,
      "grad_norm": 18.175546646118164,
      "learning_rate": 9.619397662556435e-05,
      "loss": 19.5808,
      "step": 8
    },
    {
      "epoch": 0.0013681060282171868,
      "grad_norm": 56.33650207519531,
      "learning_rate": 9.484363707663442e-05,
      "loss": 27.3127,
      "step": 9
    },
    {
      "epoch": 0.0015201178091302076,
      "grad_norm": 42.97586441040039,
      "learning_rate": 9.330127018922194e-05,
      "loss": 25.7631,
      "step": 10
    },
    {
      "epoch": 0.0016721295900432283,
      "grad_norm": 37.800636291503906,
      "learning_rate": 9.157348061512727e-05,
      "loss": 25.2524,
      "step": 11
    },
    {
      "epoch": 0.001824141370956249,
      "grad_norm": 23.808109283447266,
      "learning_rate": 8.966766701456177e-05,
      "loss": 19.2508,
      "step": 12
    },
    {
      "epoch": 0.00197615315186927,
      "grad_norm": 5.850672721862793,
      "learning_rate": 8.759199037394887e-05,
      "loss": 11.7128,
      "step": 13
    },
    {
      "epoch": 0.0021281649327822907,
      "grad_norm": 1.9108561277389526,
      "learning_rate": 8.535533905932738e-05,
      "loss": 8.8461,
      "step": 14
    },
    {
      "epoch": 0.0022801767136953113,
      "grad_norm": 1.9549922943115234,
      "learning_rate": 8.296729075500344e-05,
      "loss": 9.9272,
      "step": 15
    },
    {
      "epoch": 0.002432188494608332,
      "grad_norm": 2.2086598873138428,
      "learning_rate": 8.043807145043604e-05,
      "loss": 10.741,
      "step": 16
    },
    {
      "epoch": 0.0025842002755213527,
      "grad_norm": 3.0374670028686523,
      "learning_rate": 7.777851165098012e-05,
      "loss": 11.058,
      "step": 17
    },
    {
      "epoch": 0.0027362120564343737,
      "grad_norm": 4.240527153015137,
      "learning_rate": 7.500000000000001e-05,
      "loss": 12.878,
      "step": 18
    },
    {
      "epoch": 0.0028882238373473946,
      "grad_norm": 5.368109703063965,
      "learning_rate": 7.211443451095007e-05,
      "loss": 11.87,
      "step": 19
    },
    {
      "epoch": 0.003040235618260415,
      "grad_norm": 6.570104598999023,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.8896,
      "step": 20
    },
    {
      "epoch": 0.003192247399173436,
      "grad_norm": 12.811237335205078,
      "learning_rate": 6.607197326515808e-05,
      "loss": 11.5877,
      "step": 21
    },
    {
      "epoch": 0.0033442591800864566,
      "grad_norm": 11.7667236328125,
      "learning_rate": 6.294095225512603e-05,
      "loss": 9.7508,
      "step": 22
    },
    {
      "epoch": 0.0034962709609994776,
      "grad_norm": 14.377885818481445,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 11.7073,
      "step": 23
    },
    {
      "epoch": 0.003648282741912498,
      "grad_norm": 17.36256980895996,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 12.8663,
      "step": 24
    },
    {
      "epoch": 0.003800294522825519,
      "grad_norm": 9.72043514251709,
      "learning_rate": 5.327015646150716e-05,
      "loss": 12.1365,
      "step": 25
    },
    {
      "epoch": 0.003800294522825519,
      "eval_loss": 0.6713224649429321,
      "eval_runtime": 2215.1165,
      "eval_samples_per_second": 20.007,
      "eval_steps_per_second": 2.501,
      "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": 5.537984561503273e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}