{
  "best_metric": 11.767305374145508,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.100502512562814,
  "eval_steps": 25,
  "global_step": 38,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08040201005025126,
      "grad_norm": 0.09012410789728165,
      "learning_rate": 5e-05,
      "loss": 11.3311,
      "step": 1
    },
    {
      "epoch": 0.08040201005025126,
      "eval_loss": 11.777422904968262,
      "eval_runtime": 0.1456,
      "eval_samples_per_second": 576.803,
      "eval_steps_per_second": 75.534,
      "step": 1
    },
    {
      "epoch": 0.16080402010050251,
      "grad_norm": 0.2074303776025772,
      "learning_rate": 0.0001,
      "loss": 10.9869,
      "step": 2
    },
    {
      "epoch": 0.24120603015075376,
      "grad_norm": 0.28062117099761963,
      "learning_rate": 9.980973490458728e-05,
      "loss": 10.371,
      "step": 3
    },
    {
      "epoch": 0.32160804020100503,
      "grad_norm": 0.0985487848520279,
      "learning_rate": 9.924038765061042e-05,
      "loss": 11.3234,
      "step": 4
    },
    {
      "epoch": 0.4020100502512563,
      "grad_norm": 0.18397016823291779,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.9766,
      "step": 5
    },
    {
      "epoch": 0.4824120603015075,
      "grad_norm": 0.3028811514377594,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.308,
      "step": 6
    },
    {
      "epoch": 0.5628140703517588,
      "grad_norm": 0.10475285351276398,
      "learning_rate": 9.53153893518325e-05,
      "loss": 11.3174,
      "step": 7
    },
    {
      "epoch": 0.6432160804020101,
      "grad_norm": 0.1775769591331482,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.9895,
      "step": 8
    },
    {
      "epoch": 0.7236180904522613,
      "grad_norm": 0.304249107837677,
      "learning_rate": 9.09576022144496e-05,
      "loss": 10.358,
      "step": 9
    },
    {
      "epoch": 0.8040201005025126,
      "grad_norm": 0.09947295486927032,
      "learning_rate": 8.83022221559489e-05,
      "loss": 11.3382,
      "step": 10
    },
    {
      "epoch": 0.8844221105527639,
      "grad_norm": 0.19411100447177887,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.0198,
      "step": 11
    },
    {
      "epoch": 0.964824120603015,
      "grad_norm": 0.3085010349750519,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3536,
      "step": 12
    },
    {
      "epoch": 1.0603015075376885,
      "grad_norm": 0.17965899407863617,
      "learning_rate": 7.86788218175523e-05,
      "loss": 20.5415,
      "step": 13
    },
    {
      "epoch": 1.1407035175879396,
      "grad_norm": 0.19990818202495575,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.9364,
      "step": 14
    },
    {
      "epoch": 1.221105527638191,
      "grad_norm": 0.28082919120788574,
      "learning_rate": 7.113091308703498e-05,
      "loss": 10.5718,
      "step": 15
    },
    {
      "epoch": 1.3015075376884422,
      "grad_norm": 0.1590864509344101,
      "learning_rate": 6.710100716628344e-05,
      "loss": 11.2554,
      "step": 16
    },
    {
      "epoch": 1.3819095477386933,
      "grad_norm": 0.2059917151927948,
      "learning_rate": 6.294095225512603e-05,
      "loss": 10.837,
      "step": 17
    },
    {
      "epoch": 1.4623115577889447,
      "grad_norm": 0.2859290540218353,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.4912,
      "step": 18
    },
    {
      "epoch": 1.542713567839196,
      "grad_norm": 0.17937739193439484,
      "learning_rate": 5.435778713738292e-05,
      "loss": 11.3839,
      "step": 19
    },
    {
      "epoch": 1.6231155778894473,
      "grad_norm": 0.1938363015651703,
      "learning_rate": 5e-05,
      "loss": 10.7518,
      "step": 20
    },
    {
      "epoch": 1.7035175879396984,
      "grad_norm": 0.3071121275424957,
      "learning_rate": 4.564221286261709e-05,
      "loss": 10.5182,
      "step": 21
    },
    {
      "epoch": 1.7839195979899496,
      "grad_norm": 0.21606698632240295,
      "learning_rate": 4.131759111665349e-05,
      "loss": 11.3058,
      "step": 22
    },
    {
      "epoch": 1.864321608040201,
      "grad_norm": 0.20309078693389893,
      "learning_rate": 3.705904774487396e-05,
      "loss": 10.8257,
      "step": 23
    },
    {
      "epoch": 1.9447236180904524,
      "grad_norm": 0.4092361032962799,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.4848,
      "step": 24
    },
    {
      "epoch": 2.040201005025126,
      "grad_norm": 0.28117260336875916,
      "learning_rate": 2.886908691296504e-05,
      "loss": 20.1121,
      "step": 25
    },
    {
      "epoch": 2.040201005025126,
      "eval_loss": 11.767305374145508,
      "eval_runtime": 0.1443,
      "eval_samples_per_second": 582.265,
      "eval_steps_per_second": 76.249,
      "step": 25
    },
    {
      "epoch": 2.120603015075377,
      "grad_norm": 0.18161916732788086,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.5824,
      "step": 26
    },
    {
      "epoch": 2.201005025125628,
      "grad_norm": 0.2802564203739166,
      "learning_rate": 2.132117818244771e-05,
      "loss": 10.6324,
      "step": 27
    },
    {
      "epoch": 2.2814070351758793,
      "grad_norm": 0.2961265742778778,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 11.3607,
      "step": 28
    },
    {
      "epoch": 2.3618090452261304,
      "grad_norm": 0.1732824742794037,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.4676,
      "step": 29
    },
    {
      "epoch": 2.442211055276382,
      "grad_norm": 0.26101455092430115,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.9159,
      "step": 30
    },
    {
      "epoch": 2.522613065326633,
      "grad_norm": 0.23604969680309296,
      "learning_rate": 9.042397785550405e-06,
      "loss": 11.4271,
      "step": 31
    },
    {
      "epoch": 2.6030150753768844,
      "grad_norm": 0.1926390826702118,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.4621,
      "step": 32
    },
    {
      "epoch": 2.6834170854271355,
      "grad_norm": 0.3302035629749298,
      "learning_rate": 4.684610648167503e-06,
      "loss": 10.6902,
      "step": 33
    },
    {
      "epoch": 2.7638190954773867,
      "grad_norm": 0.2632927894592285,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 11.2976,
      "step": 34
    },
    {
      "epoch": 2.8442211055276383,
      "grad_norm": 0.1927858144044876,
      "learning_rate": 1.70370868554659e-06,
      "loss": 10.4873,
      "step": 35
    },
    {
      "epoch": 2.9246231155778895,
      "grad_norm": 0.2852284014225006,
      "learning_rate": 7.596123493895991e-07,
      "loss": 11.0213,
      "step": 36
    },
    {
      "epoch": 3.020100502512563,
      "grad_norm": 0.315874844789505,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 19.506,
      "step": 37
    },
    {
      "epoch": 3.100502512562814,
      "grad_norm": 0.14532816410064697,
      "learning_rate": 0.0,
      "loss": 10.3719,
      "step": 38
    }
  ],
  "logging_steps": 1,
  "max_steps": 38,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 124553464381440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}