{
  "best_metric": 0.6583801507949829,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.031039031582214636,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012415612632885853,
      "grad_norm": 0.4326339662075043,
      "learning_rate": 5e-05,
      "loss": 0.9528,
      "step": 1
    },
    {
      "epoch": 0.0012415612632885853,
      "eval_loss": 0.8670604228973389,
      "eval_runtime": 86.7004,
      "eval_samples_per_second": 62.583,
      "eval_steps_per_second": 7.832,
      "step": 1
    },
    {
      "epoch": 0.0024831225265771707,
      "grad_norm": 0.31606096029281616,
      "learning_rate": 0.0001,
      "loss": 0.8354,
      "step": 2
    },
    {
      "epoch": 0.003724683789865756,
      "grad_norm": 0.34394755959510803,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.8952,
      "step": 3
    },
    {
      "epoch": 0.004966245053154341,
      "grad_norm": 0.2672635614871979,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.8739,
      "step": 4
    },
    {
      "epoch": 0.006207806316442927,
      "grad_norm": 0.245578333735466,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.8213,
      "step": 5
    },
    {
      "epoch": 0.007449367579731512,
      "grad_norm": 0.2544446289539337,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.828,
      "step": 6
    },
    {
      "epoch": 0.008690928843020097,
      "grad_norm": 0.26478007435798645,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.7942,
      "step": 7
    },
    {
      "epoch": 0.009932490106308683,
      "grad_norm": 0.27469292283058167,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.8026,
      "step": 8
    },
    {
      "epoch": 0.011174051369597269,
      "grad_norm": 0.2647610008716583,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.7335,
      "step": 9
    },
    {
      "epoch": 0.012415612632885854,
      "grad_norm": 0.25258561968803406,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7,
      "step": 10
    },
    {
      "epoch": 0.01365717389617444,
      "grad_norm": 0.2425445020198822,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.6056,
      "step": 11
    },
    {
      "epoch": 0.014898735159463024,
      "grad_norm": 0.2843758165836334,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5097,
      "step": 12
    },
    {
      "epoch": 0.01614029642275161,
      "grad_norm": 0.5850368738174438,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.894,
      "step": 13
    },
    {
      "epoch": 0.017381857686040194,
      "grad_norm": 0.2032504379749298,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6675,
      "step": 14
    },
    {
      "epoch": 0.01862341894932878,
      "grad_norm": 0.1841326802968979,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.6916,
      "step": 15
    },
    {
      "epoch": 0.019864980212617366,
      "grad_norm": 0.1865765005350113,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.7363,
      "step": 16
    },
    {
      "epoch": 0.021106541475905953,
      "grad_norm": 0.17130893468856812,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.6748,
      "step": 17
    },
    {
      "epoch": 0.022348102739194537,
      "grad_norm": 0.18940648436546326,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7294,
      "step": 18
    },
    {
      "epoch": 0.02358966400248312,
      "grad_norm": 0.18071648478507996,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.6936,
      "step": 19
    },
    {
      "epoch": 0.02483122526577171,
      "grad_norm": 0.18491078913211823,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7372,
      "step": 20
    },
    {
      "epoch": 0.026072786529060293,
      "grad_norm": 0.17880083620548248,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.7103,
      "step": 21
    },
    {
      "epoch": 0.02731434779234888,
      "grad_norm": 0.16440188884735107,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.6136,
      "step": 22
    },
    {
      "epoch": 0.028555909055637464,
      "grad_norm": 0.17268064618110657,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.6092,
      "step": 23
    },
    {
      "epoch": 0.02979747031892605,
      "grad_norm": 0.17315348982810974,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.4767,
      "step": 24
    },
    {
      "epoch": 0.031039031582214636,
      "grad_norm": 0.23280172049999237,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.3756,
      "step": 25
    },
    {
      "epoch": 0.031039031582214636,
      "eval_loss": 0.6583801507949829,
      "eval_runtime": 85.9422,
      "eval_samples_per_second": 63.135,
      "eval_steps_per_second": 7.901,
      "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": 4.216566050298266e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}