{
  "best_metric": 1.3987419605255127,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.28425241614553726,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005685048322910744,
      "eval_loss": 1.9435316324234009,
      "eval_runtime": 68.5626,
      "eval_samples_per_second": 10.808,
      "eval_steps_per_second": 2.713,
      "step": 1
    },
    {
      "epoch": 0.005685048322910745,
      "grad_norm": 3.069612503051758,
      "learning_rate": 4.08e-05,
      "loss": 3.128,
      "step": 10
    },
    {
      "epoch": 0.01137009664582149,
      "grad_norm": 4.051701068878174,
      "learning_rate": 8.16e-05,
      "loss": 3.3624,
      "step": 20
    },
    {
      "epoch": 0.017055144968732235,
      "grad_norm": 3.853865146636963,
      "learning_rate": 0.0001224,
      "loss": 2.9052,
      "step": 30
    },
    {
      "epoch": 0.02274019329164298,
      "grad_norm": 4.710514545440674,
      "learning_rate": 0.0001632,
      "loss": 2.944,
      "step": 40
    },
    {
      "epoch": 0.028425241614553724,
      "grad_norm": 40.267189025878906,
      "learning_rate": 0.000204,
      "loss": 2.8684,
      "step": 50
    },
    {
      "epoch": 0.028425241614553724,
      "eval_loss": 1.691328763961792,
      "eval_runtime": 68.2464,
      "eval_samples_per_second": 10.858,
      "eval_steps_per_second": 2.725,
      "step": 50
    },
    {
      "epoch": 0.03411028993746447,
      "grad_norm": 3.3239216804504395,
      "learning_rate": 0.00020375153312650207,
      "loss": 2.5603,
      "step": 60
    },
    {
      "epoch": 0.039795338260375214,
      "grad_norm": 3.307145595550537,
      "learning_rate": 0.00020300734301164017,
      "loss": 3.1017,
      "step": 70
    },
    {
      "epoch": 0.04548038658328596,
      "grad_norm": 4.276277542114258,
      "learning_rate": 0.00020177105527484818,
      "loss": 3.3892,
      "step": 80
    },
    {
      "epoch": 0.051165434906196704,
      "grad_norm": 6.920476913452148,
      "learning_rate": 0.00020004869298570854,
      "loss": 2.7897,
      "step": 90
    },
    {
      "epoch": 0.05685048322910745,
      "grad_norm": 21.554874420166016,
      "learning_rate": 0.00019784864732016265,
      "loss": 2.6079,
      "step": 100
    },
    {
      "epoch": 0.05685048322910745,
      "eval_loss": 1.8583825826644897,
      "eval_runtime": 68.2278,
      "eval_samples_per_second": 10.861,
      "eval_steps_per_second": 2.726,
      "step": 100
    },
    {
      "epoch": 0.06253553155201819,
      "grad_norm": 3.7841274738311768,
      "learning_rate": 0.00019518163667954527,
      "loss": 2.6824,
      "step": 110
    },
    {
      "epoch": 0.06822057987492894,
      "grad_norm": 3.257988452911377,
      "learning_rate": 0.00019206065447161056,
      "loss": 2.777,
      "step": 120
    },
    {
      "epoch": 0.07390562819783968,
      "grad_norm": 4.051051616668701,
      "learning_rate": 0.00018850090580795544,
      "loss": 3.6913,
      "step": 130
    },
    {
      "epoch": 0.07959067652075043,
      "grad_norm": 6.902204513549805,
      "learning_rate": 0.00018451973342624464,
      "loss": 3.2365,
      "step": 140
    },
    {
      "epoch": 0.08527572484366117,
      "grad_norm": 47.04884719848633,
      "learning_rate": 0.00018013653319813575,
      "loss": 2.7994,
      "step": 150
    },
    {
      "epoch": 0.08527572484366117,
      "eval_loss": 1.5659745931625366,
      "eval_runtime": 68.2701,
      "eval_samples_per_second": 10.854,
      "eval_steps_per_second": 2.724,
      "step": 150
    },
    {
      "epoch": 0.09096077316657192,
      "grad_norm": 3.0065667629241943,
      "learning_rate": 0.0001753726596345424,
      "loss": 2.9537,
      "step": 160
    },
    {
      "epoch": 0.09664582148948266,
      "grad_norm": 3.099189519882202,
      "learning_rate": 0.00017025132184860355,
      "loss": 3.0517,
      "step": 170
    },
    {
      "epoch": 0.10233086981239341,
      "grad_norm": 3.6827144622802734,
      "learning_rate": 0.00016479747048321714,
      "loss": 3.5192,
      "step": 180
    },
    {
      "epoch": 0.10801591813530415,
      "grad_norm": 7.355824947357178,
      "learning_rate": 0.00015903767615401616,
      "loss": 3.0137,
      "step": 190
    },
    {
      "epoch": 0.1137009664582149,
      "grad_norm": 14.326348304748535,
      "learning_rate": 0.000153,
      "loss": 2.8734,
      "step": 200
    },
    {
      "epoch": 0.1137009664582149,
      "eval_loss": 1.535672903060913,
      "eval_runtime": 67.9931,
      "eval_samples_per_second": 10.898,
      "eval_steps_per_second": 2.736,
      "step": 200
    },
    {
      "epoch": 0.11938601478112564,
      "grad_norm": 2.603611469268799,
      "learning_rate": 0.0001467138569724859,
      "loss": 2.4002,
      "step": 210
    },
    {
      "epoch": 0.12507106310403637,
      "grad_norm": 3.106489658355713,
      "learning_rate": 0.00014020987252842305,
      "loss": 3.1293,
      "step": 220
    },
    {
      "epoch": 0.13075611142694712,
      "grad_norm": 3.54360294342041,
      "learning_rate": 0.00013351973342624464,
      "loss": 3.3809,
      "step": 230
    },
    {
      "epoch": 0.13644115974985788,
      "grad_norm": 5.519043922424316,
      "learning_rate": 0.00012667603335116609,
      "loss": 2.7644,
      "step": 240
    },
    {
      "epoch": 0.14212620807276863,
      "grad_norm": 22.177762985229492,
      "learning_rate": 0.00011971211412202691,
      "loss": 2.7882,
      "step": 250
    },
    {
      "epoch": 0.14212620807276863,
      "eval_loss": 1.4961472749710083,
      "eval_runtime": 68.4935,
      "eval_samples_per_second": 10.819,
      "eval_steps_per_second": 2.716,
      "step": 250
    },
    {
      "epoch": 0.14781125639567935,
      "grad_norm": 2.693026304244995,
      "learning_rate": 0.00011266190325330066,
      "loss": 3.0899,
      "step": 260
    },
    {
      "epoch": 0.1534963047185901,
      "grad_norm": 7.191518306732178,
      "learning_rate": 0.00010555974866365511,
      "loss": 2.9899,
      "step": 270
    },
    {
      "epoch": 0.15918135304150086,
      "grad_norm": 4.4006028175354,
      "learning_rate": 9.844025133634492e-05,
      "loss": 3.0914,
      "step": 280
    },
    {
      "epoch": 0.1648664013644116,
      "grad_norm": 6.061286926269531,
      "learning_rate": 9.133809674669937e-05,
      "loss": 2.8825,
      "step": 290
    },
    {
      "epoch": 0.17055144968732233,
      "grad_norm": 18.585689544677734,
      "learning_rate": 8.428788587797311e-05,
      "loss": 2.1726,
      "step": 300
    },
    {
      "epoch": 0.17055144968732233,
      "eval_loss": 1.4905575513839722,
      "eval_runtime": 68.056,
      "eval_samples_per_second": 10.888,
      "eval_steps_per_second": 2.733,
      "step": 300
    },
    {
      "epoch": 0.17623649801023308,
      "grad_norm": 3.150554895401001,
      "learning_rate": 7.73239666488339e-05,
      "loss": 2.9069,
      "step": 310
    },
    {
      "epoch": 0.18192154633314384,
      "grad_norm": 3.780085802078247,
      "learning_rate": 7.048026657375537e-05,
      "loss": 3.1427,
      "step": 320
    },
    {
      "epoch": 0.1876065946560546,
      "grad_norm": 3.767456531524658,
      "learning_rate": 6.379012747157697e-05,
      "loss": 3.3117,
      "step": 330
    },
    {
      "epoch": 0.1932916429789653,
      "grad_norm": 8.545947074890137,
      "learning_rate": 5.7286143027514095e-05,
      "loss": 2.9684,
      "step": 340
    },
    {
      "epoch": 0.19897669130187606,
      "grad_norm": 14.986133575439453,
      "learning_rate": 5.100000000000002e-05,
      "loss": 2.9029,
      "step": 350
    },
    {
      "epoch": 0.19897669130187606,
      "eval_loss": 1.449243187904358,
      "eval_runtime": 68.6437,
      "eval_samples_per_second": 10.795,
      "eval_steps_per_second": 2.71,
      "step": 350
    },
    {
      "epoch": 0.20466173962478681,
      "grad_norm": 2.6051387786865234,
      "learning_rate": 4.496232384598384e-05,
      "loss": 2.7807,
      "step": 360
    },
    {
      "epoch": 0.21034678794769757,
      "grad_norm": 2.8948583602905273,
      "learning_rate": 3.9202529516782854e-05,
      "loss": 3.2851,
      "step": 370
    },
    {
      "epoch": 0.2160318362706083,
      "grad_norm": 4.121320724487305,
      "learning_rate": 3.374867815139649e-05,
      "loss": 3.2988,
      "step": 380
    },
    {
      "epoch": 0.22171688459351904,
      "grad_norm": 6.426261901855469,
      "learning_rate": 2.8627340365457602e-05,
      "loss": 2.8684,
      "step": 390
    },
    {
      "epoch": 0.2274019329164298,
      "grad_norm": 20.456893920898438,
      "learning_rate": 2.3863466801864254e-05,
      "loss": 2.2538,
      "step": 400
    },
    {
      "epoch": 0.2274019329164298,
      "eval_loss": 1.4112082719802856,
      "eval_runtime": 68.5395,
      "eval_samples_per_second": 10.811,
      "eval_steps_per_second": 2.714,
      "step": 400
    },
    {
      "epoch": 0.23308698123934055,
      "grad_norm": 3.0374252796173096,
      "learning_rate": 1.9480266573755372e-05,
      "loss": 2.4258,
      "step": 410
    },
    {
      "epoch": 0.23877202956225127,
      "grad_norm": 3.4767048358917236,
      "learning_rate": 1.5499094192044554e-05,
      "loss": 3.0519,
      "step": 420
    },
    {
      "epoch": 0.24445707788516202,
      "grad_norm": 4.919350624084473,
      "learning_rate": 1.1939345528389446e-05,
      "loss": 3.2507,
      "step": 430
    },
    {
      "epoch": 0.25014212620807275,
      "grad_norm": 7.929502487182617,
      "learning_rate": 8.818363320454701e-06,
      "loss": 2.8546,
      "step": 440
    },
    {
      "epoch": 0.2558271745309835,
      "grad_norm": 26.788230895996094,
      "learning_rate": 6.1513526798373514e-06,
      "loss": 2.4219,
      "step": 450
    },
    {
      "epoch": 0.2558271745309835,
      "eval_loss": 1.3987419605255127,
      "eval_runtime": 68.6583,
      "eval_samples_per_second": 10.793,
      "eval_steps_per_second": 2.709,
      "step": 450
    },
    {
      "epoch": 0.26151222285389425,
      "grad_norm": 2.4997353553771973,
      "learning_rate": 3.9513070142914725e-06,
      "loss": 2.8869,
      "step": 460
    },
    {
      "epoch": 0.26719727117680503,
      "grad_norm": 4.465632915496826,
      "learning_rate": 2.2289447251518195e-06,
      "loss": 3.2354,
      "step": 470
    },
    {
      "epoch": 0.27288231949971575,
      "grad_norm": 4.705733776092529,
      "learning_rate": 9.92656988359823e-07,
      "loss": 3.124,
      "step": 480
    },
    {
      "epoch": 0.2785673678226265,
      "grad_norm": 4.500922679901123,
      "learning_rate": 2.4846687349793185e-07,
      "loss": 2.7457,
      "step": 490
    },
    {
      "epoch": 0.28425241614553726,
      "grad_norm": 22.040611267089844,
      "learning_rate": 0.0,
      "loss": 2.8161,
      "step": 500
    },
    {
      "epoch": 0.28425241614553726,
      "eval_loss": 1.4063708782196045,
      "eval_runtime": 69.6065,
      "eval_samples_per_second": 10.646,
      "eval_steps_per_second": 2.672,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5434051934486528e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}