{
  "best_metric": 1.3565335273742676,
  "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": 107.0593,
      "eval_samples_per_second": 10.695,
      "eval_steps_per_second": 2.681,
      "step": 1
    },
    {
      "epoch": 0.0036784991723376862,
      "grad_norm": 1.8631224632263184,
      "learning_rate": 4.36e-05,
      "loss": 3.7124,
      "step": 10
    },
    {
      "epoch": 0.0073569983446753725,
      "grad_norm": 1.0357885360717773,
      "learning_rate": 8.72e-05,
      "loss": 2.3794,
      "step": 20
    },
    {
      "epoch": 0.011035497517013059,
      "grad_norm": 0.8365756273269653,
      "learning_rate": 0.0001308,
      "loss": 1.7752,
      "step": 30
    },
    {
      "epoch": 0.014713996689350745,
      "grad_norm": 0.9363265037536621,
      "learning_rate": 0.0001744,
      "loss": 1.62,
      "step": 40
    },
    {
      "epoch": 0.01839249586168843,
      "grad_norm": 0.9486646056175232,
      "learning_rate": 0.000218,
      "loss": 1.4426,
      "step": 50
    },
    {
      "epoch": 0.01839249586168843,
      "eval_loss": 1.658852458000183,
      "eval_runtime": 107.1756,
      "eval_samples_per_second": 10.683,
      "eval_steps_per_second": 2.678,
      "step": 50
    },
    {
      "epoch": 0.022070995034026118,
      "grad_norm": 0.6641014814376831,
      "learning_rate": 0.00021773448147832086,
      "loss": 1.6935,
      "step": 60
    },
    {
      "epoch": 0.025749494206363802,
      "grad_norm": 0.6979497671127319,
      "learning_rate": 0.0002169392194928312,
      "loss": 1.5954,
      "step": 70
    },
    {
      "epoch": 0.02942799337870149,
      "grad_norm": 0.8027070760726929,
      "learning_rate": 0.00021561808847998484,
      "loss": 1.5455,
      "step": 80
    },
    {
      "epoch": 0.033106492551039174,
      "grad_norm": 0.6991447806358337,
      "learning_rate": 0.00021377752485727676,
      "loss": 1.4689,
      "step": 90
    },
    {
      "epoch": 0.03678499172337686,
      "grad_norm": 0.9628053903579712,
      "learning_rate": 0.00021142649566566402,
      "loss": 1.4403,
      "step": 100
    },
    {
      "epoch": 0.03678499172337686,
      "eval_loss": 1.5630460977554321,
      "eval_runtime": 107.2017,
      "eval_samples_per_second": 10.681,
      "eval_steps_per_second": 2.677,
      "step": 100
    },
    {
      "epoch": 0.04046349089571455,
      "grad_norm": 0.6026347875595093,
      "learning_rate": 0.0002085764548830435,
      "loss": 1.6232,
      "step": 110
    },
    {
      "epoch": 0.044141990068052236,
      "grad_norm": 0.7379695773124695,
      "learning_rate": 0.00020524128762162305,
      "loss": 1.4991,
      "step": 120
    },
    {
      "epoch": 0.047820489240389924,
      "grad_norm": 0.6722536683082581,
      "learning_rate": 0.00020143724248105043,
      "loss": 1.5017,
      "step": 130
    },
    {
      "epoch": 0.051498988412727605,
      "grad_norm": 0.6395397186279297,
      "learning_rate": 0.0001971828523868693,
      "loss": 1.4441,
      "step": 140
    },
    {
      "epoch": 0.05517748758506529,
      "grad_norm": 0.8695403933525085,
      "learning_rate": 0.0001924988442999686,
      "loss": 1.3411,
      "step": 150
    },
    {
      "epoch": 0.05517748758506529,
      "eval_loss": 1.5262999534606934,
      "eval_runtime": 107.2361,
      "eval_samples_per_second": 10.677,
      "eval_steps_per_second": 2.676,
      "step": 150
    },
    {
      "epoch": 0.05885598675740298,
      "grad_norm": 0.6810901165008545,
      "learning_rate": 0.00018740803823691298,
      "loss": 1.5936,
      "step": 160
    },
    {
      "epoch": 0.06253448592974066,
      "grad_norm": 0.657184362411499,
      "learning_rate": 0.00018193523609311556,
      "loss": 1.5681,
      "step": 170
    },
    {
      "epoch": 0.06621298510207835,
      "grad_norm": 0.6586466431617737,
      "learning_rate": 0.00017610710081049675,
      "loss": 1.4321,
      "step": 180
    },
    {
      "epoch": 0.06989148427441604,
      "grad_norm": 0.7010196447372437,
      "learning_rate": 0.00016995202647831142,
      "loss": 1.3784,
      "step": 190
    },
    {
      "epoch": 0.07356998344675372,
      "grad_norm": 0.8979406356811523,
      "learning_rate": 0.00016350000000000002,
      "loss": 1.341,
      "step": 200
    },
    {
      "epoch": 0.07356998344675372,
      "eval_loss": 1.4965966939926147,
      "eval_runtime": 107.3593,
      "eval_samples_per_second": 10.665,
      "eval_steps_per_second": 2.673,
      "step": 200
    },
    {
      "epoch": 0.07724848261909141,
      "grad_norm": 0.6285237073898315,
      "learning_rate": 0.00015678245500000943,
      "loss": 1.5321,
      "step": 210
    },
    {
      "epoch": 0.0809269817914291,
      "grad_norm": 0.6141915321350098,
      "learning_rate": 0.00014983211868233444,
      "loss": 1.4692,
      "step": 220
    },
    {
      "epoch": 0.08460548096376679,
      "grad_norm": 0.6756523251533508,
      "learning_rate": 0.00014268285238686927,
      "loss": 1.436,
      "step": 230
    },
    {
      "epoch": 0.08828398013610447,
      "grad_norm": 0.6676588654518127,
      "learning_rate": 0.00013536948662036378,
      "loss": 1.3784,
      "step": 240
    },
    {
      "epoch": 0.09196247930844216,
      "grad_norm": 0.7657578587532043,
      "learning_rate": 0.00012792765136569544,
      "loss": 1.2896,
      "step": 250
    },
    {
      "epoch": 0.09196247930844216,
      "eval_loss": 1.4555139541625977,
      "eval_runtime": 107.2583,
      "eval_samples_per_second": 10.675,
      "eval_steps_per_second": 2.676,
      "step": 250
    },
    {
      "epoch": 0.09564097848077985,
      "grad_norm": 0.596019446849823,
      "learning_rate": 0.00012039360249617425,
      "loss": 1.5842,
      "step": 260
    },
    {
      "epoch": 0.09931947765311752,
      "grad_norm": 0.6011001467704773,
      "learning_rate": 0.00011280404514057264,
      "loss": 1.4633,
      "step": 270
    },
    {
      "epoch": 0.10299797682545521,
      "grad_norm": 0.6597139835357666,
      "learning_rate": 0.00010519595485942743,
      "loss": 1.4199,
      "step": 280
    },
    {
      "epoch": 0.1066764759977929,
      "grad_norm": 0.6663433313369751,
      "learning_rate": 9.76063975038258e-05,
      "loss": 1.3892,
      "step": 290
    },
    {
      "epoch": 0.11035497517013058,
      "grad_norm": 0.845330536365509,
      "learning_rate": 9.00723486343046e-05,
      "loss": 1.2336,
      "step": 300
    },
    {
      "epoch": 0.11035497517013058,
      "eval_loss": 1.4274946451187134,
      "eval_runtime": 107.2541,
      "eval_samples_per_second": 10.676,
      "eval_steps_per_second": 2.676,
      "step": 300
    },
    {
      "epoch": 0.11403347434246827,
      "grad_norm": 0.5652741193771362,
      "learning_rate": 8.263051337963623e-05,
      "loss": 1.5192,
      "step": 310
    },
    {
      "epoch": 0.11771197351480596,
      "grad_norm": 0.5754914879798889,
      "learning_rate": 7.531714761313074e-05,
      "loss": 1.5169,
      "step": 320
    },
    {
      "epoch": 0.12139047268714365,
      "grad_norm": 0.5873494744300842,
      "learning_rate": 6.816788131766559e-05,
      "loss": 1.4227,
      "step": 330
    },
    {
      "epoch": 0.12506897185948132,
      "grad_norm": 0.5985251069068909,
      "learning_rate": 6.121754499999055e-05,
      "loss": 1.2899,
      "step": 340
    },
    {
      "epoch": 0.12874747103181902,
      "grad_norm": 0.8635291457176208,
      "learning_rate": 5.450000000000003e-05,
      "loss": 1.2777,
      "step": 350
    },
    {
      "epoch": 0.12874747103181902,
      "eval_loss": 1.4000242948532104,
      "eval_runtime": 107.1832,
      "eval_samples_per_second": 10.683,
      "eval_steps_per_second": 2.678,
      "step": 350
    },
    {
      "epoch": 0.1324259702041567,
      "grad_norm": 0.5911391973495483,
      "learning_rate": 4.804797352168861e-05,
      "loss": 1.4978,
      "step": 360
    },
    {
      "epoch": 0.1361044693764944,
      "grad_norm": 0.6037421226501465,
      "learning_rate": 4.189289918950325e-05,
      "loss": 1.4423,
      "step": 370
    },
    {
      "epoch": 0.13978296854883207,
      "grad_norm": 0.5900255441665649,
      "learning_rate": 3.606476390688449e-05,
      "loss": 1.3197,
      "step": 380
    },
    {
      "epoch": 0.14346146772116977,
      "grad_norm": 0.6815835237503052,
      "learning_rate": 3.0591961763087043e-05,
      "loss": 1.3703,
      "step": 390
    },
    {
      "epoch": 0.14713996689350745,
      "grad_norm": 0.7701212167739868,
      "learning_rate": 2.550115570003141e-05,
      "loss": 1.2902,
      "step": 400
    },
    {
      "epoch": 0.14713996689350745,
      "eval_loss": 1.3680524826049805,
      "eval_runtime": 107.1594,
      "eval_samples_per_second": 10.685,
      "eval_steps_per_second": 2.678,
      "step": 400
    },
    {
      "epoch": 0.15081846606584515,
      "grad_norm": 0.5527030229568481,
      "learning_rate": 2.081714761313074e-05,
      "loss": 1.458,
      "step": 410
    },
    {
      "epoch": 0.15449696523818282,
      "grad_norm": 0.5901045203208923,
      "learning_rate": 1.656275751894957e-05,
      "loss": 1.4088,
      "step": 420
    },
    {
      "epoch": 0.1581754644105205,
      "grad_norm": 0.6328750848770142,
      "learning_rate": 1.275871237837696e-05,
      "loss": 1.3526,
      "step": 430
    },
    {
      "epoch": 0.1618539635828582,
      "grad_norm": 0.619103193283081,
      "learning_rate": 9.423545116956494e-06,
      "loss": 1.3128,
      "step": 440
    },
    {
      "epoch": 0.16553246275519587,
      "grad_norm": 0.7719127535820007,
      "learning_rate": 6.573504334335994e-06,
      "loss": 1.2669,
      "step": 450
    },
    {
      "epoch": 0.16553246275519587,
      "eval_loss": 1.3588438034057617,
      "eval_runtime": 107.2217,
      "eval_samples_per_second": 10.679,
      "eval_steps_per_second": 2.677,
      "step": 450
    },
    {
      "epoch": 0.16921096192753357,
      "grad_norm": 0.6076942682266235,
      "learning_rate": 4.22247514272324e-06,
      "loss": 1.4677,
      "step": 460
    },
    {
      "epoch": 0.17288946109987124,
      "grad_norm": 0.5937750935554504,
      "learning_rate": 2.38191152001518e-06,
      "loss": 1.3644,
      "step": 470
    },
    {
      "epoch": 0.17656796027220895,
      "grad_norm": 0.5931702852249146,
      "learning_rate": 1.0607805071688306e-06,
      "loss": 1.3443,
      "step": 480
    },
    {
      "epoch": 0.18024645944454662,
      "grad_norm": 0.6748533844947815,
      "learning_rate": 2.655185216791625e-07,
      "loss": 1.2941,
      "step": 490
    },
    {
      "epoch": 0.18392495861688432,
      "grad_norm": 0.8280065059661865,
      "learning_rate": 0.0,
      "loss": 1.2717,
      "step": 500
    },
    {
      "epoch": 0.18392495861688432,
      "eval_loss": 1.3565335273742676,
      "eval_runtime": 107.2901,
      "eval_samples_per_second": 10.672,
      "eval_steps_per_second": 2.675,
      "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
}