{
  "best_metric": 2.090728282928467,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.08431703204047218,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003372681281618887,
      "grad_norm": 1.417541265487671,
      "learning_rate": 2e-05,
      "loss": 3.6623,
      "step": 1
    },
    {
      "epoch": 0.003372681281618887,
      "eval_loss": 3.225717067718506,
      "eval_runtime": 19.339,
      "eval_samples_per_second": 6.464,
      "eval_steps_per_second": 3.258,
      "step": 1
    },
    {
      "epoch": 0.006745362563237774,
      "grad_norm": 1.2096680402755737,
      "learning_rate": 4e-05,
      "loss": 2.796,
      "step": 2
    },
    {
      "epoch": 0.01011804384485666,
      "grad_norm": 1.092326283454895,
      "learning_rate": 6e-05,
      "loss": 2.9494,
      "step": 3
    },
    {
      "epoch": 0.013490725126475547,
      "grad_norm": 0.9202325344085693,
      "learning_rate": 8e-05,
      "loss": 2.6686,
      "step": 4
    },
    {
      "epoch": 0.016863406408094434,
      "grad_norm": 1.5893256664276123,
      "learning_rate": 0.0001,
      "loss": 3.4625,
      "step": 5
    },
    {
      "epoch": 0.016863406408094434,
      "eval_loss": 3.213568925857544,
      "eval_runtime": 18.3512,
      "eval_samples_per_second": 6.812,
      "eval_steps_per_second": 3.433,
      "step": 5
    },
    {
      "epoch": 0.02023608768971332,
      "grad_norm": 1.2070389986038208,
      "learning_rate": 0.00012,
      "loss": 2.904,
      "step": 6
    },
    {
      "epoch": 0.023608768971332208,
      "grad_norm": 1.7667227983474731,
      "learning_rate": 0.00014,
      "loss": 3.1713,
      "step": 7
    },
    {
      "epoch": 0.026981450252951095,
      "grad_norm": 1.2589635848999023,
      "learning_rate": 0.00016,
      "loss": 3.0576,
      "step": 8
    },
    {
      "epoch": 0.03035413153456998,
      "grad_norm": 1.7349282503128052,
      "learning_rate": 0.00018,
      "loss": 2.9782,
      "step": 9
    },
    {
      "epoch": 0.03372681281618887,
      "grad_norm": 2.6368513107299805,
      "learning_rate": 0.0002,
      "loss": 3.2474,
      "step": 10
    },
    {
      "epoch": 0.03372681281618887,
      "eval_loss": 2.887220859527588,
      "eval_runtime": 18.1428,
      "eval_samples_per_second": 6.89,
      "eval_steps_per_second": 3.472,
      "step": 10
    },
    {
      "epoch": 0.03709949409780776,
      "grad_norm": 2.249255895614624,
      "learning_rate": 0.00019781476007338058,
      "loss": 3.0063,
      "step": 11
    },
    {
      "epoch": 0.04047217537942664,
      "grad_norm": 2.5278384685516357,
      "learning_rate": 0.0001913545457642601,
      "loss": 2.845,
      "step": 12
    },
    {
      "epoch": 0.04384485666104553,
      "grad_norm": 2.5744972229003906,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.4101,
      "step": 13
    },
    {
      "epoch": 0.047217537942664416,
      "grad_norm": 2.417795419692993,
      "learning_rate": 0.00016691306063588583,
      "loss": 2.247,
      "step": 14
    },
    {
      "epoch": 0.050590219224283306,
      "grad_norm": 2.620561361312866,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.8745,
      "step": 15
    },
    {
      "epoch": 0.050590219224283306,
      "eval_loss": 2.2684640884399414,
      "eval_runtime": 18.1715,
      "eval_samples_per_second": 6.879,
      "eval_steps_per_second": 3.467,
      "step": 15
    },
    {
      "epoch": 0.05396290050590219,
      "grad_norm": 2.6527938842773438,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.0356,
      "step": 16
    },
    {
      "epoch": 0.05733558178752108,
      "grad_norm": 3.06416654586792,
      "learning_rate": 0.00011045284632676536,
      "loss": 2.5972,
      "step": 17
    },
    {
      "epoch": 0.06070826306913996,
      "grad_norm": 4.44185733795166,
      "learning_rate": 8.954715367323468e-05,
      "loss": 2.0945,
      "step": 18
    },
    {
      "epoch": 0.06408094435075885,
      "grad_norm": 2.4905245304107666,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.054,
      "step": 19
    },
    {
      "epoch": 0.06745362563237774,
      "grad_norm": 2.5971834659576416,
      "learning_rate": 5.000000000000002e-05,
      "loss": 2.2086,
      "step": 20
    },
    {
      "epoch": 0.06745362563237774,
      "eval_loss": 2.112858772277832,
      "eval_runtime": 18.1213,
      "eval_samples_per_second": 6.898,
      "eval_steps_per_second": 3.477,
      "step": 20
    },
    {
      "epoch": 0.07082630691399663,
      "grad_norm": 2.9609220027923584,
      "learning_rate": 3.308693936411421e-05,
      "loss": 2.1288,
      "step": 21
    },
    {
      "epoch": 0.07419898819561552,
      "grad_norm": 2.6516270637512207,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.2109,
      "step": 22
    },
    {
      "epoch": 0.0775716694772344,
      "grad_norm": 2.68251895904541,
      "learning_rate": 8.645454235739903e-06,
      "loss": 2.2448,
      "step": 23
    },
    {
      "epoch": 0.08094435075885328,
      "grad_norm": 2.136423110961914,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.9205,
      "step": 24
    },
    {
      "epoch": 0.08431703204047218,
      "grad_norm": 2.8987932205200195,
      "learning_rate": 0.0,
      "loss": 2.1777,
      "step": 25
    },
    {
      "epoch": 0.08431703204047218,
      "eval_loss": 2.090728282928467,
      "eval_runtime": 18.0988,
      "eval_samples_per_second": 6.907,
      "eval_steps_per_second": 3.481,
      "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": 4623910620364800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}