{
  "best_metric": 2.550354242324829,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.11377858686995107,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022755717373990216,
      "eval_loss": 2.9036054611206055,
      "eval_runtime": 184.2385,
      "eval_samples_per_second": 10.047,
      "eval_steps_per_second": 2.513,
      "step": 1
    },
    {
      "epoch": 0.0022755717373990213,
      "grad_norm": 0.3486361503601074,
      "learning_rate": 4.16e-05,
      "loss": 2.918,
      "step": 10
    },
    {
      "epoch": 0.004551143474798043,
      "grad_norm": 0.4807929992675781,
      "learning_rate": 8.32e-05,
      "loss": 2.7357,
      "step": 20
    },
    {
      "epoch": 0.006826715212197064,
      "grad_norm": 0.5630984306335449,
      "learning_rate": 0.0001248,
      "loss": 2.8322,
      "step": 30
    },
    {
      "epoch": 0.009102286949596085,
      "grad_norm": 0.544504702091217,
      "learning_rate": 0.0001664,
      "loss": 2.6563,
      "step": 40
    },
    {
      "epoch": 0.011377858686995108,
      "grad_norm": 1.6601486206054688,
      "learning_rate": 0.000208,
      "loss": 2.8123,
      "step": 50
    },
    {
      "epoch": 0.011377858686995108,
      "eval_loss": 2.7227728366851807,
      "eval_runtime": 184.1917,
      "eval_samples_per_second": 10.049,
      "eval_steps_per_second": 2.514,
      "step": 50
    },
    {
      "epoch": 0.013653430424394129,
      "grad_norm": 0.5499740242958069,
      "learning_rate": 0.0002077466612270217,
      "loss": 2.6736,
      "step": 60
    },
    {
      "epoch": 0.01592900216179315,
      "grad_norm": 0.5605274438858032,
      "learning_rate": 0.0002069878791491233,
      "loss": 2.7277,
      "step": 70
    },
    {
      "epoch": 0.01820457389919217,
      "grad_norm": 0.5069101452827454,
      "learning_rate": 0.00020572735047631578,
      "loss": 2.6469,
      "step": 80
    },
    {
      "epoch": 0.020480145636591195,
      "grad_norm": 0.5251340866088867,
      "learning_rate": 0.00020397121637758515,
      "loss": 2.5055,
      "step": 90
    },
    {
      "epoch": 0.022755717373990215,
      "grad_norm": 2.59476375579834,
      "learning_rate": 0.00020172803256173445,
      "loss": 2.7778,
      "step": 100
    },
    {
      "epoch": 0.022755717373990215,
      "eval_loss": 2.6594133377075195,
      "eval_runtime": 184.2257,
      "eval_samples_per_second": 10.047,
      "eval_steps_per_second": 2.513,
      "step": 100
    },
    {
      "epoch": 0.025031289111389236,
      "grad_norm": 0.5118083953857422,
      "learning_rate": 0.00019900872759483047,
      "loss": 2.7046,
      "step": 110
    },
    {
      "epoch": 0.027306860848788257,
      "grad_norm": 0.6953938603401184,
      "learning_rate": 0.0001958265496573284,
      "loss": 2.7211,
      "step": 120
    },
    {
      "epoch": 0.029582432586187278,
      "grad_norm": 0.4843135178089142,
      "learning_rate": 0.00019219700200026827,
      "loss": 2.6335,
      "step": 130
    },
    {
      "epoch": 0.0318580043235863,
      "grad_norm": 0.48902738094329834,
      "learning_rate": 0.0001881377674149945,
      "loss": 2.5555,
      "step": 140
    },
    {
      "epoch": 0.03413357606098532,
      "grad_norm": 0.9428099989891052,
      "learning_rate": 0.00018366862208437368,
      "loss": 2.6027,
      "step": 150
    },
    {
      "epoch": 0.03413357606098532,
      "eval_loss": 2.6243715286254883,
      "eval_runtime": 184.6541,
      "eval_samples_per_second": 10.024,
      "eval_steps_per_second": 2.507,
      "step": 150
    },
    {
      "epoch": 0.03640914779838434,
      "grad_norm": 0.5289075970649719,
      "learning_rate": 0.00017881133923521971,
      "loss": 2.6422,
      "step": 160
    },
    {
      "epoch": 0.03868471953578337,
      "grad_norm": 0.5151132345199585,
      "learning_rate": 0.00017358958306132124,
      "loss": 2.61,
      "step": 170
    },
    {
      "epoch": 0.04096029127318239,
      "grad_norm": 0.5393058061599731,
      "learning_rate": 0.00016802879343386844,
      "loss": 2.5273,
      "step": 180
    },
    {
      "epoch": 0.04323586301058141,
      "grad_norm": 0.599901556968689,
      "learning_rate": 0.00016215606196095766,
      "loss": 2.4814,
      "step": 190
    },
    {
      "epoch": 0.04551143474798043,
      "grad_norm": 1.3163615465164185,
      "learning_rate": 0.000156,
      "loss": 2.6113,
      "step": 200
    },
    {
      "epoch": 0.04551143474798043,
      "eval_loss": 2.606013059616089,
      "eval_runtime": 184.8057,
      "eval_samples_per_second": 10.016,
      "eval_steps_per_second": 2.505,
      "step": 200
    },
    {
      "epoch": 0.04778700648537945,
      "grad_norm": 0.5513772964477539,
      "learning_rate": 0.00014959059926606403,
      "loss": 2.6334,
      "step": 210
    },
    {
      "epoch": 0.05006257822277847,
      "grad_norm": 0.4891476035118103,
      "learning_rate": 0.00014295908571525487,
      "loss": 2.5474,
      "step": 220
    },
    {
      "epoch": 0.052338149960177494,
      "grad_norm": 0.5638535022735596,
      "learning_rate": 0.00013613776741499452,
      "loss": 2.6109,
      "step": 230
    },
    {
      "epoch": 0.054613721697576514,
      "grad_norm": 0.5022374987602234,
      "learning_rate": 0.00012915987714236542,
      "loss": 2.5818,
      "step": 240
    },
    {
      "epoch": 0.056889293434975535,
      "grad_norm": 1.3279516696929932,
      "learning_rate": 0.00012205941047736077,
      "loss": 2.4663,
      "step": 250
    },
    {
      "epoch": 0.056889293434975535,
      "eval_loss": 2.584219217300415,
      "eval_runtime": 184.6096,
      "eval_samples_per_second": 10.027,
      "eval_steps_per_second": 2.508,
      "step": 250
    },
    {
      "epoch": 0.059164865172374556,
      "grad_norm": 0.539516270160675,
      "learning_rate": 0.00011487096017983597,
      "loss": 2.6549,
      "step": 260
    },
    {
      "epoch": 0.061440436909773584,
      "grad_norm": 0.4973564147949219,
      "learning_rate": 0.00010762954765706012,
      "loss": 2.5091,
      "step": 270
    },
    {
      "epoch": 0.0637160086471726,
      "grad_norm": 0.5017938613891602,
      "learning_rate": 0.00010037045234293992,
      "loss": 2.4611,
      "step": 280
    },
    {
      "epoch": 0.06599158038457162,
      "grad_norm": 0.519973635673523,
      "learning_rate": 9.312903982016405e-05,
      "loss": 2.4266,
      "step": 290
    },
    {
      "epoch": 0.06826715212197064,
      "grad_norm": 2.7459232807159424,
      "learning_rate": 8.594058952263925e-05,
      "loss": 2.6504,
      "step": 300
    },
    {
      "epoch": 0.06826715212197064,
      "eval_loss": 2.5742878913879395,
      "eval_runtime": 184.451,
      "eval_samples_per_second": 10.035,
      "eval_steps_per_second": 2.51,
      "step": 300
    },
    {
      "epoch": 0.07054272385936966,
      "grad_norm": 0.5434854030609131,
      "learning_rate": 7.884012285763457e-05,
      "loss": 2.6699,
      "step": 310
    },
    {
      "epoch": 0.07281829559676868,
      "grad_norm": 0.48433616757392883,
      "learning_rate": 7.186223258500548e-05,
      "loss": 2.6301,
      "step": 320
    },
    {
      "epoch": 0.07509386733416772,
      "grad_norm": 0.5066972374916077,
      "learning_rate": 6.504091428474514e-05,
      "loss": 2.4588,
      "step": 330
    },
    {
      "epoch": 0.07736943907156674,
      "grad_norm": 0.5236348509788513,
      "learning_rate": 5.840940073393593e-05,
      "loss": 2.4142,
      "step": 340
    },
    {
      "epoch": 0.07964501080896576,
      "grad_norm": 2.0875391960144043,
      "learning_rate": 5.200000000000002e-05,
      "loss": 2.4484,
      "step": 350
    },
    {
      "epoch": 0.07964501080896576,
      "eval_loss": 2.5629172325134277,
      "eval_runtime": 184.6435,
      "eval_samples_per_second": 10.025,
      "eval_steps_per_second": 2.508,
      "step": 350
    },
    {
      "epoch": 0.08192058254636478,
      "grad_norm": 0.5457383394241333,
      "learning_rate": 4.5843938039042344e-05,
      "loss": 2.6142,
      "step": 360
    },
    {
      "epoch": 0.0841961542837638,
      "grad_norm": 0.5010927319526672,
      "learning_rate": 3.997120656613154e-05,
      "loss": 2.5545,
      "step": 370
    },
    {
      "epoch": 0.08647172602116282,
      "grad_norm": 0.5765501856803894,
      "learning_rate": 3.441041693867878e-05,
      "loss": 2.4515,
      "step": 380
    },
    {
      "epoch": 0.08874729775856184,
      "grad_norm": 0.5465764999389648,
      "learning_rate": 2.9188660764780296e-05,
      "loss": 2.4339,
      "step": 390
    },
    {
      "epoch": 0.09102286949596086,
      "grad_norm": 0.9333412647247314,
      "learning_rate": 2.4331377915626298e-05,
      "loss": 2.4501,
      "step": 400
    },
    {
      "epoch": 0.09102286949596086,
      "eval_loss": 2.5573015213012695,
      "eval_runtime": 184.621,
      "eval_samples_per_second": 10.026,
      "eval_steps_per_second": 2.508,
      "step": 400
    },
    {
      "epoch": 0.09329844123335988,
      "grad_norm": 0.5412922501564026,
      "learning_rate": 1.9862232585005475e-05,
      "loss": 2.5775,
      "step": 410
    },
    {
      "epoch": 0.0955740129707589,
      "grad_norm": 0.5537426471710205,
      "learning_rate": 1.58029979997317e-05,
      "loss": 2.5315,
      "step": 420
    },
    {
      "epoch": 0.09784958470815792,
      "grad_norm": 0.532833993434906,
      "learning_rate": 1.2173450342671593e-05,
      "loss": 2.4957,
      "step": 430
    },
    {
      "epoch": 0.10012515644555695,
      "grad_norm": 0.5533403158187866,
      "learning_rate": 8.991272405169498e-06,
      "loss": 2.512,
      "step": 440
    },
    {
      "epoch": 0.10240072818295597,
      "grad_norm": 1.024665117263794,
      "learning_rate": 6.271967438265535e-06,
      "loss": 2.4862,
      "step": 450
    },
    {
      "epoch": 0.10240072818295597,
      "eval_loss": 2.5509848594665527,
      "eval_runtime": 184.5083,
      "eval_samples_per_second": 10.032,
      "eval_steps_per_second": 2.509,
      "step": 450
    },
    {
      "epoch": 0.10467629992035499,
      "grad_norm": 0.542321503162384,
      "learning_rate": 4.028783622414835e-06,
      "loss": 2.6094,
      "step": 460
    },
    {
      "epoch": 0.10695187165775401,
      "grad_norm": 0.5314146280288696,
      "learning_rate": 2.272649523684208e-06,
      "loss": 2.6186,
      "step": 470
    },
    {
      "epoch": 0.10922744339515303,
      "grad_norm": 0.523740828037262,
      "learning_rate": 1.0121208508766823e-06,
      "loss": 2.5175,
      "step": 480
    },
    {
      "epoch": 0.11150301513255205,
      "grad_norm": 0.53782719373703,
      "learning_rate": 2.533387729782834e-07,
      "loss": 2.3776,
      "step": 490
    },
    {
      "epoch": 0.11377858686995107,
      "grad_norm": 1.0320826768875122,
      "learning_rate": 0.0,
      "loss": 2.5147,
      "step": 500
    },
    {
      "epoch": 0.11377858686995107,
      "eval_loss": 2.550354242324829,
      "eval_runtime": 184.627,
      "eval_samples_per_second": 10.026,
      "eval_steps_per_second": 2.508,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6471099211513856e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}