{
  "best_metric": 6.922487258911133,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.63441712926249,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025376685170499604,
      "grad_norm": 0.7004460096359253,
      "learning_rate": 5e-05,
      "loss": 6.9221,
      "step": 1
    },
    {
      "epoch": 0.025376685170499604,
      "eval_loss": 6.944462299346924,
      "eval_runtime": 0.1152,
      "eval_samples_per_second": 434.074,
      "eval_steps_per_second": 112.859,
      "step": 1
    },
    {
      "epoch": 0.05075337034099921,
      "grad_norm": 0.6931402087211609,
      "learning_rate": 0.0001,
      "loss": 6.9198,
      "step": 2
    },
    {
      "epoch": 0.0761300555114988,
      "grad_norm": 0.23951783776283264,
      "learning_rate": 9.990365154573717e-05,
      "loss": 6.9389,
      "step": 3
    },
    {
      "epoch": 0.10150674068199841,
      "grad_norm": 0.24534912407398224,
      "learning_rate": 9.961501876182148e-05,
      "loss": 6.9407,
      "step": 4
    },
    {
      "epoch": 0.126883425852498,
      "grad_norm": 0.23312632739543915,
      "learning_rate": 9.913533761814537e-05,
      "loss": 6.9474,
      "step": 5
    },
    {
      "epoch": 0.1522601110229976,
      "grad_norm": 0.2653202712535858,
      "learning_rate": 9.846666218300807e-05,
      "loss": 6.9404,
      "step": 6
    },
    {
      "epoch": 0.17763679619349723,
      "grad_norm": 0.29398810863494873,
      "learning_rate": 9.761185582727977e-05,
      "loss": 6.9344,
      "step": 7
    },
    {
      "epoch": 0.20301348136399683,
      "grad_norm": 0.33159613609313965,
      "learning_rate": 9.657457896300791e-05,
      "loss": 6.9315,
      "step": 8
    },
    {
      "epoch": 0.22839016653449642,
      "grad_norm": 0.33163586258888245,
      "learning_rate": 9.535927336897098e-05,
      "loss": 6.9403,
      "step": 9
    },
    {
      "epoch": 0.253766851704996,
      "grad_norm": 0.3883456587791443,
      "learning_rate": 9.397114317029975e-05,
      "loss": 6.9259,
      "step": 10
    },
    {
      "epoch": 0.27914353687549565,
      "grad_norm": 0.6985044479370117,
      "learning_rate": 9.241613255361455e-05,
      "loss": 6.8995,
      "step": 11
    },
    {
      "epoch": 0.3045202220459952,
      "grad_norm": 0.5428418517112732,
      "learning_rate": 9.070090031310558e-05,
      "loss": 6.909,
      "step": 12
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 0.2652731239795685,
      "learning_rate": 8.883279133655399e-05,
      "loss": 6.9292,
      "step": 13
    },
    {
      "epoch": 0.35527359238699446,
      "grad_norm": 0.2631296217441559,
      "learning_rate": 8.681980515339464e-05,
      "loss": 6.9314,
      "step": 14
    },
    {
      "epoch": 0.38065027755749403,
      "grad_norm": 0.23014403879642487,
      "learning_rate": 8.467056167950311e-05,
      "loss": 6.937,
      "step": 15
    },
    {
      "epoch": 0.40602696272799366,
      "grad_norm": 0.2576012909412384,
      "learning_rate": 8.239426430539243e-05,
      "loss": 6.9293,
      "step": 16
    },
    {
      "epoch": 0.4314036478984933,
      "grad_norm": 0.2961735129356384,
      "learning_rate": 8.000066048588211e-05,
      "loss": 6.9245,
      "step": 17
    },
    {
      "epoch": 0.45678033306899285,
      "grad_norm": 0.30337101221084595,
      "learning_rate": 7.75e-05,
      "loss": 6.9231,
      "step": 18
    },
    {
      "epoch": 0.4821570182394925,
      "grad_norm": 0.2677088677883148,
      "learning_rate": 7.490299105985507e-05,
      "loss": 6.9252,
      "step": 19
    },
    {
      "epoch": 0.507533703409992,
      "grad_norm": 0.5016420483589172,
      "learning_rate": 7.222075445642904e-05,
      "loss": 6.9028,
      "step": 20
    },
    {
      "epoch": 0.5329103885804917,
      "grad_norm": 0.6997107267379761,
      "learning_rate": 6.946477593864228e-05,
      "loss": 6.8873,
      "step": 21
    },
    {
      "epoch": 0.5582870737509913,
      "grad_norm": 0.37420928478240967,
      "learning_rate": 6.664685702961344e-05,
      "loss": 6.9067,
      "step": 22
    },
    {
      "epoch": 0.5836637589214909,
      "grad_norm": 0.2798817455768585,
      "learning_rate": 6.377906449072578e-05,
      "loss": 6.9219,
      "step": 23
    },
    {
      "epoch": 0.6090404440919904,
      "grad_norm": 0.25544771552085876,
      "learning_rate": 6.087367864990233e-05,
      "loss": 6.9211,
      "step": 24
    },
    {
      "epoch": 0.63441712926249,
      "grad_norm": 0.21856531500816345,
      "learning_rate": 5.794314081535644e-05,
      "loss": 6.9325,
      "step": 25
    },
    {
      "epoch": 0.63441712926249,
      "eval_loss": 6.922487258911133,
      "eval_runtime": 0.1164,
      "eval_samples_per_second": 429.492,
      "eval_steps_per_second": 111.668,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2852978688000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}