{
  "best_metric": 1.826446294784546,
  "best_model_checkpoint": "miner_id_24/checkpoint-1350",
  "epoch": 1.1958688168146403,
  "eval_steps": 150,
  "global_step": 1650,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007247689798876608,
      "eval_loss": 3.070380210876465,
      "eval_runtime": 85.9153,
      "eval_samples_per_second": 13.525,
      "eval_steps_per_second": 3.387,
      "step": 1
    },
    {
      "epoch": 0.03623844899438304,
      "grad_norm": 3.273714542388916,
      "learning_rate": 0.0002,
      "loss": 2.1084,
      "step": 50
    },
    {
      "epoch": 0.07247689798876608,
      "grad_norm": 1.639181137084961,
      "learning_rate": 0.0001998582695676762,
      "loss": 1.989,
      "step": 100
    },
    {
      "epoch": 0.10871534698314912,
      "grad_norm": 3.0539445877075195,
      "learning_rate": 0.00019943348002101371,
      "loss": 1.9929,
      "step": 150
    },
    {
      "epoch": 0.10871534698314912,
      "eval_loss": 2.0453155040740967,
      "eval_runtime": 86.7107,
      "eval_samples_per_second": 13.401,
      "eval_steps_per_second": 3.356,
      "step": 150
    },
    {
      "epoch": 0.14495379597753216,
      "grad_norm": 1.7175414562225342,
      "learning_rate": 0.00019872683547213446,
      "loss": 1.9457,
      "step": 200
    },
    {
      "epoch": 0.1811922449719152,
      "grad_norm": 3.7000324726104736,
      "learning_rate": 0.00019774033898178667,
      "loss": 1.9367,
      "step": 250
    },
    {
      "epoch": 0.21743069396629824,
      "grad_norm": 2.244403123855591,
      "learning_rate": 0.0001964767868814516,
      "loss": 1.9372,
      "step": 300
    },
    {
      "epoch": 0.21743069396629824,
      "eval_loss": 1.9559648036956787,
      "eval_runtime": 86.7219,
      "eval_samples_per_second": 13.399,
      "eval_steps_per_second": 3.356,
      "step": 300
    },
    {
      "epoch": 0.25366914296068127,
      "grad_norm": 2.310765027999878,
      "learning_rate": 0.00019493976084683813,
      "loss": 1.9331,
      "step": 350
    },
    {
      "epoch": 0.2899075919550643,
      "grad_norm": 2.4135353565216064,
      "learning_rate": 0.00019313361774523385,
      "loss": 1.9337,
      "step": 400
    },
    {
      "epoch": 0.3261460409494474,
      "grad_norm": 3.474848747253418,
      "learning_rate": 0.00019106347728549135,
      "loss": 1.9164,
      "step": 450
    },
    {
      "epoch": 0.3261460409494474,
      "eval_loss": 1.952536702156067,
      "eval_runtime": 86.9956,
      "eval_samples_per_second": 13.357,
      "eval_steps_per_second": 3.345,
      "step": 450
    },
    {
      "epoch": 0.3623844899438304,
      "grad_norm": 2.140085458755493,
      "learning_rate": 0.00018873520750565718,
      "loss": 1.877,
      "step": 500
    },
    {
      "epoch": 0.39862293893821343,
      "grad_norm": 2.0083487033843994,
      "learning_rate": 0.0001861554081393806,
      "loss": 1.8591,
      "step": 550
    },
    {
      "epoch": 0.4348613879325965,
      "grad_norm": 3.061316967010498,
      "learning_rate": 0.0001833313919082515,
      "loss": 1.9117,
      "step": 600
    },
    {
      "epoch": 0.4348613879325965,
      "eval_loss": 1.942734956741333,
      "eval_runtime": 86.6654,
      "eval_samples_per_second": 13.408,
      "eval_steps_per_second": 3.358,
      "step": 600
    },
    {
      "epoch": 0.47109983692697954,
      "grad_norm": 2.36161470413208,
      "learning_rate": 0.00018027116379309638,
      "loss": 1.9137,
      "step": 650
    },
    {
      "epoch": 0.5073382859213625,
      "grad_norm": 2.791883707046509,
      "learning_rate": 0.00017698339834299061,
      "loss": 1.9284,
      "step": 700
    },
    {
      "epoch": 0.5435767349157457,
      "grad_norm": 2.8679757118225098,
      "learning_rate": 0.00017347741508630672,
      "loss": 1.8691,
      "step": 750
    },
    {
      "epoch": 0.5435767349157457,
      "eval_loss": 1.9142440557479858,
      "eval_runtime": 86.7231,
      "eval_samples_per_second": 13.399,
      "eval_steps_per_second": 3.356,
      "step": 750
    },
    {
      "epoch": 0.5798151839101287,
      "grad_norm": 2.4429304599761963,
      "learning_rate": 0.0001697631521134985,
      "loss": 1.9101,
      "step": 800
    },
    {
      "epoch": 0.6160536329045116,
      "grad_norm": 2.8223161697387695,
      "learning_rate": 0.00016585113790650388,
      "loss": 1.8409,
      "step": 850
    },
    {
      "epoch": 0.6522920818988948,
      "grad_norm": 1.8749058246612549,
      "learning_rate": 0.0001617524614946192,
      "loss": 1.8731,
      "step": 900
    },
    {
      "epoch": 0.6522920818988948,
      "eval_loss": 1.8797276020050049,
      "eval_runtime": 86.9372,
      "eval_samples_per_second": 13.366,
      "eval_steps_per_second": 3.347,
      "step": 900
    },
    {
      "epoch": 0.6885305308932778,
      "grad_norm": 3.5651133060455322,
      "learning_rate": 0.0001574787410214407,
      "loss": 1.8334,
      "step": 950
    },
    {
      "epoch": 0.7247689798876608,
      "grad_norm": 2.771768569946289,
      "learning_rate": 0.00015304209081197425,
      "loss": 1.8534,
      "step": 1000
    },
    {
      "epoch": 0.7610074288820439,
      "grad_norm": 2.3072197437286377,
      "learning_rate": 0.00014845508703326504,
      "loss": 1.8311,
      "step": 1050
    },
    {
      "epoch": 0.7610074288820439,
      "eval_loss": 1.865134835243225,
      "eval_runtime": 86.9546,
      "eval_samples_per_second": 13.363,
      "eval_steps_per_second": 3.347,
      "step": 1050
    },
    {
      "epoch": 0.7972458778764269,
      "grad_norm": 2.7600791454315186,
      "learning_rate": 0.00014373073204588556,
      "loss": 1.8482,
      "step": 1100
    },
    {
      "epoch": 0.83348432687081,
      "grad_norm": 3.6101410388946533,
      "learning_rate": 0.00013888241754733208,
      "loss": 1.8151,
      "step": 1150
    },
    {
      "epoch": 0.869722775865193,
      "grad_norm": 2.4437174797058105,
      "learning_rate": 0.00013392388661180303,
      "loss": 1.836,
      "step": 1200
    },
    {
      "epoch": 0.869722775865193,
      "eval_loss": 1.8474547863006592,
      "eval_runtime": 86.4314,
      "eval_samples_per_second": 13.444,
      "eval_steps_per_second": 3.367,
      "step": 1200
    },
    {
      "epoch": 0.905961224859576,
      "grad_norm": 2.752454996109009,
      "learning_rate": 0.0001288691947339621,
      "loss": 1.8837,
      "step": 1250
    },
    {
      "epoch": 0.9421996738539591,
      "grad_norm": 2.2887587547302246,
      "learning_rate": 0.0001237326699871115,
      "loss": 1.8392,
      "step": 1300
    },
    {
      "epoch": 0.9784381228483421,
      "grad_norm": 4.001684665679932,
      "learning_rate": 0.00011852887240871145,
      "loss": 1.8195,
      "step": 1350
    },
    {
      "epoch": 0.9784381228483421,
      "eval_loss": 1.826446294784546,
      "eval_runtime": 86.7246,
      "eval_samples_per_second": 13.399,
      "eval_steps_per_second": 3.355,
      "step": 1350
    },
    {
      "epoch": 1.014676571842725,
      "grad_norm": 0.9796865582466125,
      "learning_rate": 0.00011327255272837221,
      "loss": 1.7798,
      "step": 1400
    },
    {
      "epoch": 1.050915020837108,
      "grad_norm": 0.8189029693603516,
      "learning_rate": 0.00010797861055530831,
      "loss": 1.4192,
      "step": 1450
    },
    {
      "epoch": 1.0871534698314913,
      "grad_norm": 0.9342411756515503,
      "learning_rate": 0.00010266205214377748,
      "loss": 1.4029,
      "step": 1500
    },
    {
      "epoch": 1.0871534698314913,
      "eval_loss": 1.8509882688522339,
      "eval_runtime": 86.7099,
      "eval_samples_per_second": 13.401,
      "eval_steps_per_second": 3.356,
      "step": 1500
    },
    {
      "epoch": 1.1233919188258743,
      "grad_norm": 0.8776970505714417,
      "learning_rate": 9.733794785622253e-05,
      "loss": 1.3963,
      "step": 1550
    },
    {
      "epoch": 1.1596303678202573,
      "grad_norm": 0.9756889939308167,
      "learning_rate": 9.202138944469168e-05,
      "loss": 1.393,
      "step": 1600
    },
    {
      "epoch": 1.1958688168146403,
      "grad_norm": 0.8379771113395691,
      "learning_rate": 8.672744727162781e-05,
      "loss": 1.4002,
      "step": 1650
    },
    {
      "epoch": 1.1958688168146403,
      "eval_loss": 1.837064504623413,
      "eval_runtime": 86.6691,
      "eval_samples_per_second": 13.407,
      "eval_steps_per_second": 3.358,
      "step": 1650
    }
  ],
  "logging_steps": 50,
  "max_steps": 3000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 150,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1904824490055434e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}