{
  "best_metric": 3.9591970443725586,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.050352467270896276,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002014098690835851,
      "grad_norm": 5.243093490600586,
      "learning_rate": 2e-05,
      "loss": 19.8411,
      "step": 1
    },
    {
      "epoch": 0.002014098690835851,
      "eval_loss": 5.059567928314209,
      "eval_runtime": 9.9585,
      "eval_samples_per_second": 21.088,
      "eval_steps_per_second": 10.544,
      "step": 1
    },
    {
      "epoch": 0.004028197381671702,
      "grad_norm": 4.998810291290283,
      "learning_rate": 4e-05,
      "loss": 21.7359,
      "step": 2
    },
    {
      "epoch": 0.006042296072507553,
      "grad_norm": 6.04394006729126,
      "learning_rate": 6e-05,
      "loss": 24.2109,
      "step": 3
    },
    {
      "epoch": 0.008056394763343404,
      "grad_norm": 6.116606712341309,
      "learning_rate": 8e-05,
      "loss": 22.4319,
      "step": 4
    },
    {
      "epoch": 0.010070493454179255,
      "grad_norm": 4.266777515411377,
      "learning_rate": 0.0001,
      "loss": 19.2349,
      "step": 5
    },
    {
      "epoch": 0.010070493454179255,
      "eval_loss": 4.971032619476318,
      "eval_runtime": 9.9491,
      "eval_samples_per_second": 21.107,
      "eval_steps_per_second": 10.554,
      "step": 5
    },
    {
      "epoch": 0.012084592145015106,
      "grad_norm": 4.383306503295898,
      "learning_rate": 0.00012,
      "loss": 12.7878,
      "step": 6
    },
    {
      "epoch": 0.014098690835850957,
      "grad_norm": 4.937915325164795,
      "learning_rate": 0.00014,
      "loss": 19.7955,
      "step": 7
    },
    {
      "epoch": 0.016112789526686808,
      "grad_norm": 3.5370934009552,
      "learning_rate": 0.00016,
      "loss": 15.5616,
      "step": 8
    },
    {
      "epoch": 0.01812688821752266,
      "grad_norm": 8.180222511291504,
      "learning_rate": 0.00018,
      "loss": 26.651,
      "step": 9
    },
    {
      "epoch": 0.02014098690835851,
      "grad_norm": 8.891468048095703,
      "learning_rate": 0.0002,
      "loss": 26.4958,
      "step": 10
    },
    {
      "epoch": 0.02014098690835851,
      "eval_loss": 4.756030082702637,
      "eval_runtime": 9.965,
      "eval_samples_per_second": 21.074,
      "eval_steps_per_second": 10.537,
      "step": 10
    },
    {
      "epoch": 0.022155085599194362,
      "grad_norm": 6.933834552764893,
      "learning_rate": 0.00019781476007338058,
      "loss": 18.7005,
      "step": 11
    },
    {
      "epoch": 0.02416918429003021,
      "grad_norm": 6.866347312927246,
      "learning_rate": 0.0001913545457642601,
      "loss": 21.0418,
      "step": 12
    },
    {
      "epoch": 0.026183282980866064,
      "grad_norm": 5.648362636566162,
      "learning_rate": 0.00018090169943749476,
      "loss": 16.3807,
      "step": 13
    },
    {
      "epoch": 0.028197381671701913,
      "grad_norm": 8.93856430053711,
      "learning_rate": 0.00016691306063588583,
      "loss": 20.5595,
      "step": 14
    },
    {
      "epoch": 0.030211480362537766,
      "grad_norm": 6.642890930175781,
      "learning_rate": 0.00015000000000000001,
      "loss": 16.273,
      "step": 15
    },
    {
      "epoch": 0.030211480362537766,
      "eval_loss": 4.319993019104004,
      "eval_runtime": 10.0192,
      "eval_samples_per_second": 20.96,
      "eval_steps_per_second": 10.48,
      "step": 15
    },
    {
      "epoch": 0.032225579053373615,
      "grad_norm": 6.6722331047058105,
      "learning_rate": 0.00013090169943749476,
      "loss": 17.0076,
      "step": 16
    },
    {
      "epoch": 0.03423967774420947,
      "grad_norm": 8.032441139221191,
      "learning_rate": 0.00011045284632676536,
      "loss": 16.5987,
      "step": 17
    },
    {
      "epoch": 0.03625377643504532,
      "grad_norm": 8.647908210754395,
      "learning_rate": 8.954715367323468e-05,
      "loss": 17.4807,
      "step": 18
    },
    {
      "epoch": 0.038267875125881166,
      "grad_norm": 9.85554313659668,
      "learning_rate": 6.909830056250527e-05,
      "loss": 18.2034,
      "step": 19
    },
    {
      "epoch": 0.04028197381671702,
      "grad_norm": 6.346075057983398,
      "learning_rate": 5.000000000000002e-05,
      "loss": 13.1005,
      "step": 20
    },
    {
      "epoch": 0.04028197381671702,
      "eval_loss": 4.020318508148193,
      "eval_runtime": 10.0603,
      "eval_samples_per_second": 20.874,
      "eval_steps_per_second": 10.437,
      "step": 20
    },
    {
      "epoch": 0.04229607250755287,
      "grad_norm": 13.50845718383789,
      "learning_rate": 3.308693936411421e-05,
      "loss": 23.3169,
      "step": 21
    },
    {
      "epoch": 0.044310171198388724,
      "grad_norm": 6.7406439781188965,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 14.8342,
      "step": 22
    },
    {
      "epoch": 0.04632426988922457,
      "grad_norm": 7.017367839813232,
      "learning_rate": 8.645454235739903e-06,
      "loss": 14.3364,
      "step": 23
    },
    {
      "epoch": 0.04833836858006042,
      "grad_norm": 7.411367893218994,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 13.5709,
      "step": 24
    },
    {
      "epoch": 0.050352467270896276,
      "grad_norm": 7.053526878356934,
      "learning_rate": 0.0,
      "loss": 16.6839,
      "step": 25
    },
    {
      "epoch": 0.050352467270896276,
      "eval_loss": 3.9591970443725586,
      "eval_runtime": 10.0358,
      "eval_samples_per_second": 20.925,
      "eval_steps_per_second": 10.463,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 54117928009728.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}