{
  "best_metric": 0.8472192287445068,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.32051282051282054,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01282051282051282,
      "grad_norm": 1.1491622924804688,
      "learning_rate": 2e-05,
      "loss": 1.7426,
      "step": 1
    },
    {
      "epoch": 0.01282051282051282,
      "eval_loss": 1.7975318431854248,
      "eval_runtime": 8.1228,
      "eval_samples_per_second": 4.063,
      "eval_steps_per_second": 2.093,
      "step": 1
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 1.2566789388656616,
      "learning_rate": 4e-05,
      "loss": 1.8818,
      "step": 2
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 1.1978298425674438,
      "learning_rate": 6e-05,
      "loss": 1.7277,
      "step": 3
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 1.0452884435653687,
      "learning_rate": 8e-05,
      "loss": 1.6969,
      "step": 4
    },
    {
      "epoch": 0.0641025641025641,
      "grad_norm": 1.1321957111358643,
      "learning_rate": 0.0001,
      "loss": 1.5348,
      "step": 5
    },
    {
      "epoch": 0.0641025641025641,
      "eval_loss": 1.513731598854065,
      "eval_runtime": 8.019,
      "eval_samples_per_second": 4.115,
      "eval_steps_per_second": 2.12,
      "step": 5
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 1.239180088043213,
      "learning_rate": 0.00012,
      "loss": 1.482,
      "step": 6
    },
    {
      "epoch": 0.08974358974358974,
      "grad_norm": 1.1951099634170532,
      "learning_rate": 0.00014,
      "loss": 1.3662,
      "step": 7
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 1.5686924457550049,
      "learning_rate": 0.00016,
      "loss": 1.206,
      "step": 8
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": 1.49379563331604,
      "learning_rate": 0.00018,
      "loss": 1.1158,
      "step": 9
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 1.8431353569030762,
      "learning_rate": 0.0002,
      "loss": 1.036,
      "step": 10
    },
    {
      "epoch": 0.1282051282051282,
      "eval_loss": 1.0585706233978271,
      "eval_runtime": 7.8799,
      "eval_samples_per_second": 4.188,
      "eval_steps_per_second": 2.157,
      "step": 10
    },
    {
      "epoch": 0.14102564102564102,
      "grad_norm": 1.9121575355529785,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.0458,
      "step": 11
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 1.6511411666870117,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.0956,
      "step": 12
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 1.3579150438308716,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.9845,
      "step": 13
    },
    {
      "epoch": 0.1794871794871795,
      "grad_norm": 1.286914587020874,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.9154,
      "step": 14
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 1.2005118131637573,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.999,
      "step": 15
    },
    {
      "epoch": 0.19230769230769232,
      "eval_loss": 0.8986483812332153,
      "eval_runtime": 7.8599,
      "eval_samples_per_second": 4.199,
      "eval_steps_per_second": 2.163,
      "step": 15
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.9289887547492981,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.8473,
      "step": 16
    },
    {
      "epoch": 0.21794871794871795,
      "grad_norm": 0.8824356198310852,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.9723,
      "step": 17
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.8716819882392883,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.8567,
      "step": 18
    },
    {
      "epoch": 0.24358974358974358,
      "grad_norm": 0.875042200088501,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.8004,
      "step": 19
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.8217772245407104,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.7364,
      "step": 20
    },
    {
      "epoch": 0.2564102564102564,
      "eval_loss": 0.8620249032974243,
      "eval_runtime": 7.6797,
      "eval_samples_per_second": 4.297,
      "eval_steps_per_second": 2.214,
      "step": 20
    },
    {
      "epoch": 0.2692307692307692,
      "grad_norm": 0.9040417075157166,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.8305,
      "step": 21
    },
    {
      "epoch": 0.28205128205128205,
      "grad_norm": 0.8873067498207092,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.7411,
      "step": 22
    },
    {
      "epoch": 0.2948717948717949,
      "grad_norm": 0.9786880016326904,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.8167,
      "step": 23
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.903166651725769,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.9055,
      "step": 24
    },
    {
      "epoch": 0.32051282051282054,
      "grad_norm": 0.9008116126060486,
      "learning_rate": 0.0,
      "loss": 0.8732,
      "step": 25
    },
    {
      "epoch": 0.32051282051282054,
      "eval_loss": 0.8472192287445068,
      "eval_runtime": 8.0806,
      "eval_samples_per_second": 4.084,
      "eval_steps_per_second": 2.104,
      "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": 5130984043315200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}