{
  "best_metric": 1.356024980545044,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.18392495861688432,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003678499172337686,
      "eval_loss": 4.303531169891357,
      "eval_runtime": 107.5379,
      "eval_samples_per_second": 10.647,
      "eval_steps_per_second": 2.669,
      "step": 1
    },
    {
      "epoch": 0.0036784991723376862,
      "grad_norm": 1.8898500204086304,
      "learning_rate": 4.36e-05,
      "loss": 3.7144,
      "step": 10
    },
    {
      "epoch": 0.0073569983446753725,
      "grad_norm": 1.033040165901184,
      "learning_rate": 8.72e-05,
      "loss": 2.381,
      "step": 20
    },
    {
      "epoch": 0.011035497517013059,
      "grad_norm": 0.8872012495994568,
      "learning_rate": 0.0001308,
      "loss": 1.7757,
      "step": 30
    },
    {
      "epoch": 0.014713996689350745,
      "grad_norm": 0.9310850501060486,
      "learning_rate": 0.0001744,
      "loss": 1.6203,
      "step": 40
    },
    {
      "epoch": 0.01839249586168843,
      "grad_norm": 0.9658544063568115,
      "learning_rate": 0.000218,
      "loss": 1.4421,
      "step": 50
    },
    {
      "epoch": 0.01839249586168843,
      "eval_loss": 1.661220669746399,
      "eval_runtime": 107.1147,
      "eval_samples_per_second": 10.689,
      "eval_steps_per_second": 2.679,
      "step": 50
    },
    {
      "epoch": 0.022070995034026118,
      "grad_norm": 0.6637513637542725,
      "learning_rate": 0.00021773448147832086,
      "loss": 1.695,
      "step": 60
    },
    {
      "epoch": 0.025749494206363802,
      "grad_norm": 0.7009419202804565,
      "learning_rate": 0.0002169392194928312,
      "loss": 1.5961,
      "step": 70
    },
    {
      "epoch": 0.02942799337870149,
      "grad_norm": 0.7631779313087463,
      "learning_rate": 0.00021561808847998484,
      "loss": 1.5457,
      "step": 80
    },
    {
      "epoch": 0.033106492551039174,
      "grad_norm": 0.7046871185302734,
      "learning_rate": 0.00021377752485727676,
      "loss": 1.4687,
      "step": 90
    },
    {
      "epoch": 0.03678499172337686,
      "grad_norm": 0.961662769317627,
      "learning_rate": 0.00021142649566566402,
      "loss": 1.4402,
      "step": 100
    },
    {
      "epoch": 0.03678499172337686,
      "eval_loss": 1.5570803880691528,
      "eval_runtime": 107.2267,
      "eval_samples_per_second": 10.678,
      "eval_steps_per_second": 2.677,
      "step": 100
    },
    {
      "epoch": 0.04046349089571455,
      "grad_norm": 0.6058881878852844,
      "learning_rate": 0.0002085764548830435,
      "loss": 1.6218,
      "step": 110
    },
    {
      "epoch": 0.044141990068052236,
      "grad_norm": 0.73408043384552,
      "learning_rate": 0.00020524128762162305,
      "loss": 1.4987,
      "step": 120
    },
    {
      "epoch": 0.047820489240389924,
      "grad_norm": 0.6772788763046265,
      "learning_rate": 0.00020143724248105043,
      "loss": 1.5004,
      "step": 130
    },
    {
      "epoch": 0.051498988412727605,
      "grad_norm": 0.6476417183876038,
      "learning_rate": 0.0001971828523868693,
      "loss": 1.4431,
      "step": 140
    },
    {
      "epoch": 0.05517748758506529,
      "grad_norm": 0.8651573657989502,
      "learning_rate": 0.0001924988442999686,
      "loss": 1.3421,
      "step": 150
    },
    {
      "epoch": 0.05517748758506529,
      "eval_loss": 1.5231226682662964,
      "eval_runtime": 107.1783,
      "eval_samples_per_second": 10.683,
      "eval_steps_per_second": 2.678,
      "step": 150
    },
    {
      "epoch": 0.05885598675740298,
      "grad_norm": 0.6997436285018921,
      "learning_rate": 0.00018740803823691298,
      "loss": 1.5923,
      "step": 160
    },
    {
      "epoch": 0.06253448592974066,
      "grad_norm": 0.657393217086792,
      "learning_rate": 0.00018193523609311556,
      "loss": 1.5695,
      "step": 170
    },
    {
      "epoch": 0.06621298510207835,
      "grad_norm": 0.6620543003082275,
      "learning_rate": 0.00017610710081049675,
      "loss": 1.4328,
      "step": 180
    },
    {
      "epoch": 0.06989148427441604,
      "grad_norm": 0.6951943635940552,
      "learning_rate": 0.00016995202647831142,
      "loss": 1.3771,
      "step": 190
    },
    {
      "epoch": 0.07356998344675372,
      "grad_norm": 0.8763971924781799,
      "learning_rate": 0.00016350000000000002,
      "loss": 1.3408,
      "step": 200
    },
    {
      "epoch": 0.07356998344675372,
      "eval_loss": 1.497921347618103,
      "eval_runtime": 107.1984,
      "eval_samples_per_second": 10.681,
      "eval_steps_per_second": 2.677,
      "step": 200
    },
    {
      "epoch": 0.07724848261909141,
      "grad_norm": 0.6477477550506592,
      "learning_rate": 0.00015678245500000943,
      "loss": 1.533,
      "step": 210
    },
    {
      "epoch": 0.0809269817914291,
      "grad_norm": 0.6087270975112915,
      "learning_rate": 0.00014983211868233444,
      "loss": 1.4701,
      "step": 220
    },
    {
      "epoch": 0.08460548096376679,
      "grad_norm": 0.6840710043907166,
      "learning_rate": 0.00014268285238686927,
      "loss": 1.4357,
      "step": 230
    },
    {
      "epoch": 0.08828398013610447,
      "grad_norm": 0.6622298359870911,
      "learning_rate": 0.00013536948662036378,
      "loss": 1.3774,
      "step": 240
    },
    {
      "epoch": 0.09196247930844216,
      "grad_norm": 0.7629197835922241,
      "learning_rate": 0.00012792765136569544,
      "loss": 1.2905,
      "step": 250
    },
    {
      "epoch": 0.09196247930844216,
      "eval_loss": 1.455014944076538,
      "eval_runtime": 107.2008,
      "eval_samples_per_second": 10.681,
      "eval_steps_per_second": 2.677,
      "step": 250
    },
    {
      "epoch": 0.09564097848077985,
      "grad_norm": 0.595523476600647,
      "learning_rate": 0.00012039360249617425,
      "loss": 1.582,
      "step": 260
    },
    {
      "epoch": 0.09931947765311752,
      "grad_norm": 0.5969820618629456,
      "learning_rate": 0.00011280404514057264,
      "loss": 1.4637,
      "step": 270
    },
    {
      "epoch": 0.10299797682545521,
      "grad_norm": 0.6512609124183655,
      "learning_rate": 0.00010519595485942743,
      "loss": 1.4196,
      "step": 280
    },
    {
      "epoch": 0.1066764759977929,
      "grad_norm": 0.6744258403778076,
      "learning_rate": 9.76063975038258e-05,
      "loss": 1.3897,
      "step": 290
    },
    {
      "epoch": 0.11035497517013058,
      "grad_norm": 0.8375758528709412,
      "learning_rate": 9.00723486343046e-05,
      "loss": 1.2334,
      "step": 300
    },
    {
      "epoch": 0.11035497517013058,
      "eval_loss": 1.4276777505874634,
      "eval_runtime": 107.3683,
      "eval_samples_per_second": 10.664,
      "eval_steps_per_second": 2.673,
      "step": 300
    },
    {
      "epoch": 0.11403347434246827,
      "grad_norm": 0.576554000377655,
      "learning_rate": 8.263051337963623e-05,
      "loss": 1.5197,
      "step": 310
    },
    {
      "epoch": 0.11771197351480596,
      "grad_norm": 0.5713962912559509,
      "learning_rate": 7.531714761313074e-05,
      "loss": 1.5168,
      "step": 320
    },
    {
      "epoch": 0.12139047268714365,
      "grad_norm": 0.5897490382194519,
      "learning_rate": 6.816788131766559e-05,
      "loss": 1.4228,
      "step": 330
    },
    {
      "epoch": 0.12506897185948132,
      "grad_norm": 0.5949689745903015,
      "learning_rate": 6.121754499999055e-05,
      "loss": 1.2882,
      "step": 340
    },
    {
      "epoch": 0.12874747103181902,
      "grad_norm": 0.8545028567314148,
      "learning_rate": 5.450000000000003e-05,
      "loss": 1.2774,
      "step": 350
    },
    {
      "epoch": 0.12874747103181902,
      "eval_loss": 1.39708411693573,
      "eval_runtime": 107.4334,
      "eval_samples_per_second": 10.658,
      "eval_steps_per_second": 2.671,
      "step": 350
    },
    {
      "epoch": 0.1324259702041567,
      "grad_norm": 0.5843435525894165,
      "learning_rate": 4.804797352168861e-05,
      "loss": 1.4973,
      "step": 360
    },
    {
      "epoch": 0.1361044693764944,
      "grad_norm": 0.6044478416442871,
      "learning_rate": 4.189289918950325e-05,
      "loss": 1.4441,
      "step": 370
    },
    {
      "epoch": 0.13978296854883207,
      "grad_norm": 0.597599446773529,
      "learning_rate": 3.606476390688449e-05,
      "loss": 1.3198,
      "step": 380
    },
    {
      "epoch": 0.14346146772116977,
      "grad_norm": 0.6726983785629272,
      "learning_rate": 3.0591961763087043e-05,
      "loss": 1.3688,
      "step": 390
    },
    {
      "epoch": 0.14713996689350745,
      "grad_norm": 0.7687901258468628,
      "learning_rate": 2.550115570003141e-05,
      "loss": 1.2919,
      "step": 400
    },
    {
      "epoch": 0.14713996689350745,
      "eval_loss": 1.367588758468628,
      "eval_runtime": 107.2738,
      "eval_samples_per_second": 10.674,
      "eval_steps_per_second": 2.675,
      "step": 400
    },
    {
      "epoch": 0.15081846606584515,
      "grad_norm": 0.5578694343566895,
      "learning_rate": 2.081714761313074e-05,
      "loss": 1.458,
      "step": 410
    },
    {
      "epoch": 0.15449696523818282,
      "grad_norm": 0.5921757817268372,
      "learning_rate": 1.656275751894957e-05,
      "loss": 1.409,
      "step": 420
    },
    {
      "epoch": 0.1581754644105205,
      "grad_norm": 0.6388791799545288,
      "learning_rate": 1.275871237837696e-05,
      "loss": 1.3534,
      "step": 430
    },
    {
      "epoch": 0.1618539635828582,
      "grad_norm": 0.6216919422149658,
      "learning_rate": 9.423545116956494e-06,
      "loss": 1.3128,
      "step": 440
    },
    {
      "epoch": 0.16553246275519587,
      "grad_norm": 0.7831223607063293,
      "learning_rate": 6.573504334335994e-06,
      "loss": 1.2688,
      "step": 450
    },
    {
      "epoch": 0.16553246275519587,
      "eval_loss": 1.3581713438034058,
      "eval_runtime": 107.1785,
      "eval_samples_per_second": 10.683,
      "eval_steps_per_second": 2.678,
      "step": 450
    },
    {
      "epoch": 0.16921096192753357,
      "grad_norm": 0.6016820073127747,
      "learning_rate": 4.22247514272324e-06,
      "loss": 1.4669,
      "step": 460
    },
    {
      "epoch": 0.17288946109987124,
      "grad_norm": 0.5830768942832947,
      "learning_rate": 2.38191152001518e-06,
      "loss": 1.3645,
      "step": 470
    },
    {
      "epoch": 0.17656796027220895,
      "grad_norm": 0.591723620891571,
      "learning_rate": 1.0607805071688306e-06,
      "loss": 1.344,
      "step": 480
    },
    {
      "epoch": 0.18024645944454662,
      "grad_norm": 0.6654506325721741,
      "learning_rate": 2.655185216791625e-07,
      "loss": 1.2938,
      "step": 490
    },
    {
      "epoch": 0.18392495861688432,
      "grad_norm": 0.8405947685241699,
      "learning_rate": 0.0,
      "loss": 1.2712,
      "step": 500
    },
    {
      "epoch": 0.18392495861688432,
      "eval_loss": 1.356024980545044,
      "eval_runtime": 107.3265,
      "eval_samples_per_second": 10.668,
      "eval_steps_per_second": 2.674,
      "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": 1.6758482141184e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}