{
  "best_metric": 0.1640225350856781,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0513347022587269,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002053388090349076,
      "grad_norm": 0.3271373212337494,
      "learning_rate": 2e-05,
      "loss": 1.2882,
      "step": 1
    },
    {
      "epoch": 0.002053388090349076,
      "eval_loss": 0.26198530197143555,
      "eval_runtime": 125.5577,
      "eval_samples_per_second": 1.633,
      "eval_steps_per_second": 0.82,
      "step": 1
    },
    {
      "epoch": 0.004106776180698152,
      "grad_norm": 7.554069995880127,
      "learning_rate": 4e-05,
      "loss": 0.8789,
      "step": 2
    },
    {
      "epoch": 0.006160164271047228,
      "grad_norm": 0.2214900255203247,
      "learning_rate": 6e-05,
      "loss": 0.952,
      "step": 3
    },
    {
      "epoch": 0.008213552361396304,
      "grad_norm": 0.2103765457868576,
      "learning_rate": 8e-05,
      "loss": 1.3037,
      "step": 4
    },
    {
      "epoch": 0.01026694045174538,
      "grad_norm": 1.9728167057037354,
      "learning_rate": 0.0001,
      "loss": 1.0605,
      "step": 5
    },
    {
      "epoch": 0.01026694045174538,
      "eval_loss": 0.25988999009132385,
      "eval_runtime": 125.7482,
      "eval_samples_per_second": 1.63,
      "eval_steps_per_second": 0.819,
      "step": 5
    },
    {
      "epoch": 0.012320328542094456,
      "grad_norm": 0.40636464953422546,
      "learning_rate": 0.00012,
      "loss": 1.2973,
      "step": 6
    },
    {
      "epoch": 0.014373716632443531,
      "grad_norm": 0.7276555895805359,
      "learning_rate": 0.00014,
      "loss": 0.8676,
      "step": 7
    },
    {
      "epoch": 0.01642710472279261,
      "grad_norm": 0.5593207478523254,
      "learning_rate": 0.00016,
      "loss": 1.0125,
      "step": 8
    },
    {
      "epoch": 0.018480492813141684,
      "grad_norm": 0.5940679907798767,
      "learning_rate": 0.00018,
      "loss": 1.5996,
      "step": 9
    },
    {
      "epoch": 0.02053388090349076,
      "grad_norm": 0.5274785757064819,
      "learning_rate": 0.0002,
      "loss": 0.9687,
      "step": 10
    },
    {
      "epoch": 0.02053388090349076,
      "eval_loss": 0.21561506390571594,
      "eval_runtime": 125.2682,
      "eval_samples_per_second": 1.636,
      "eval_steps_per_second": 0.822,
      "step": 10
    },
    {
      "epoch": 0.022587268993839837,
      "grad_norm": 0.4873046576976776,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.8108,
      "step": 11
    },
    {
      "epoch": 0.024640657084188913,
      "grad_norm": 1.2536036968231201,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.8677,
      "step": 12
    },
    {
      "epoch": 0.026694045174537988,
      "grad_norm": 0.5732755661010742,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.6277,
      "step": 13
    },
    {
      "epoch": 0.028747433264887063,
      "grad_norm": 0.9946852922439575,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.6009,
      "step": 14
    },
    {
      "epoch": 0.030800821355236138,
      "grad_norm": 1.7237969636917114,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.3754,
      "step": 15
    },
    {
      "epoch": 0.030800821355236138,
      "eval_loss": 0.17570358514785767,
      "eval_runtime": 125.2636,
      "eval_samples_per_second": 1.637,
      "eval_steps_per_second": 0.822,
      "step": 15
    },
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 0.5874133110046387,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6055,
      "step": 16
    },
    {
      "epoch": 0.03490759753593429,
      "grad_norm": 0.89844810962677,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.0147,
      "step": 17
    },
    {
      "epoch": 0.03696098562628337,
      "grad_norm": 0.6273627877235413,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.0306,
      "step": 18
    },
    {
      "epoch": 0.039014373716632446,
      "grad_norm": 0.5554535984992981,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.4201,
      "step": 19
    },
    {
      "epoch": 0.04106776180698152,
      "grad_norm": 3.349839925765991,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.4115,
      "step": 20
    },
    {
      "epoch": 0.04106776180698152,
      "eval_loss": 0.16609641909599304,
      "eval_runtime": 125.7958,
      "eval_samples_per_second": 1.63,
      "eval_steps_per_second": 0.819,
      "step": 20
    },
    {
      "epoch": 0.043121149897330596,
      "grad_norm": 0.8708037734031677,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.6053,
      "step": 21
    },
    {
      "epoch": 0.045174537987679675,
      "grad_norm": 0.9391026496887207,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.6941,
      "step": 22
    },
    {
      "epoch": 0.04722792607802875,
      "grad_norm": 0.6442247033119202,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.7088,
      "step": 23
    },
    {
      "epoch": 0.049281314168377825,
      "grad_norm": 0.5883622169494629,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.7006,
      "step": 24
    },
    {
      "epoch": 0.0513347022587269,
      "grad_norm": 0.6451522707939148,
      "learning_rate": 0.0,
      "loss": 0.8123,
      "step": 25
    },
    {
      "epoch": 0.0513347022587269,
      "eval_loss": 0.1640225350856781,
      "eval_runtime": 125.5464,
      "eval_samples_per_second": 1.633,
      "eval_steps_per_second": 0.82,
      "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": 1.519787666571264e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}