{
  "best_metric": 1.2806880474090576,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.021174477696216828,
  "eval_steps": 50,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.7054394880481836e-05,
      "eval_loss": 2.291715383529663,
      "eval_runtime": 1053.328,
      "eval_samples_per_second": 8.496,
      "eval_steps_per_second": 2.125,
      "step": 1
    },
    {
      "epoch": 0.0004705439488048184,
      "grad_norm": 0.5230432152748108,
      "learning_rate": 4.24e-05,
      "loss": 2.7622,
      "step": 10
    },
    {
      "epoch": 0.0009410878976096367,
      "grad_norm": 0.7896382212638855,
      "learning_rate": 8.48e-05,
      "loss": 3.1207,
      "step": 20
    },
    {
      "epoch": 0.001411631846414455,
      "grad_norm": 0.8223176002502441,
      "learning_rate": 0.0001272,
      "loss": 3.3159,
      "step": 30
    },
    {
      "epoch": 0.0018821757952192735,
      "grad_norm": 1.2859474420547485,
      "learning_rate": 0.0001696,
      "loss": 2.6552,
      "step": 40
    },
    {
      "epoch": 0.002352719744024092,
      "grad_norm": 1.6215729713439941,
      "learning_rate": 0.000212,
      "loss": 3.2582,
      "step": 50
    },
    {
      "epoch": 0.002352719744024092,
      "eval_loss": 1.5773438215255737,
      "eval_runtime": 1052.3497,
      "eval_samples_per_second": 8.504,
      "eval_steps_per_second": 2.127,
      "step": 50
    },
    {
      "epoch": 0.00282326369282891,
      "grad_norm": 0.46075549721717834,
      "learning_rate": 0.00021174178932754136,
      "loss": 2.1986,
      "step": 60
    },
    {
      "epoch": 0.0032938076416337285,
      "grad_norm": 0.6075234413146973,
      "learning_rate": 0.00021096841528660647,
      "loss": 2.8469,
      "step": 70
    },
    {
      "epoch": 0.003764351590438547,
      "grad_norm": 0.7672594785690308,
      "learning_rate": 0.0002096836456777834,
      "loss": 3.25,
      "step": 80
    },
    {
      "epoch": 0.004234895539243365,
      "grad_norm": 0.9351806640625,
      "learning_rate": 0.00020789373976946182,
      "loss": 2.4935,
      "step": 90
    },
    {
      "epoch": 0.004705439488048184,
      "grad_norm": 1.1365292072296143,
      "learning_rate": 0.0002056074178033063,
      "loss": 3.0859,
      "step": 100
    },
    {
      "epoch": 0.004705439488048184,
      "eval_loss": 1.4719538688659668,
      "eval_runtime": 1052.0449,
      "eval_samples_per_second": 8.506,
      "eval_steps_per_second": 2.127,
      "step": 100
    },
    {
      "epoch": 0.005175983436853002,
      "grad_norm": 0.4256722927093506,
      "learning_rate": 0.00020283581851011567,
      "loss": 2.0301,
      "step": 110
    },
    {
      "epoch": 0.00564652738565782,
      "grad_norm": 0.5135687589645386,
      "learning_rate": 0.00019959244484304625,
      "loss": 2.9534,
      "step": 120
    },
    {
      "epoch": 0.006117071334462639,
      "grad_norm": 0.9111499786376953,
      "learning_rate": 0.00019589309819258114,
      "loss": 2.9244,
      "step": 130
    },
    {
      "epoch": 0.006587615283267457,
      "grad_norm": 0.9945178031921387,
      "learning_rate": 0.00019175580140374444,
      "loss": 2.7275,
      "step": 140
    },
    {
      "epoch": 0.007058159232072276,
      "grad_norm": 1.4719926118850708,
      "learning_rate": 0.00018720071097061167,
      "loss": 3.1501,
      "step": 150
    },
    {
      "epoch": 0.007058159232072276,
      "eval_loss": 1.5417993068695068,
      "eval_runtime": 1051.4913,
      "eval_samples_per_second": 8.511,
      "eval_steps_per_second": 2.128,
      "step": 150
    },
    {
      "epoch": 0.007528703180877094,
      "grad_norm": 0.5069376230239868,
      "learning_rate": 0.00018225001883589702,
      "loss": 2.131,
      "step": 160
    },
    {
      "epoch": 0.007999247129681912,
      "grad_norm": 0.6495153307914734,
      "learning_rate": 0.00017692784427403898,
      "loss": 2.7595,
      "step": 170
    },
    {
      "epoch": 0.00846979107848673,
      "grad_norm": 0.8190892338752747,
      "learning_rate": 0.00017126011638451976,
      "loss": 3.0714,
      "step": 180
    },
    {
      "epoch": 0.00894033502729155,
      "grad_norm": 1.1729865074157715,
      "learning_rate": 0.00016527444776789915,
      "loss": 2.568,
      "step": 190
    },
    {
      "epoch": 0.009410878976096368,
      "grad_norm": 1.1141877174377441,
      "learning_rate": 0.00015900000000000002,
      "loss": 3.0678,
      "step": 200
    },
    {
      "epoch": 0.009410878976096368,
      "eval_loss": 1.5443755388259888,
      "eval_runtime": 1050.9688,
      "eval_samples_per_second": 8.515,
      "eval_steps_per_second": 2.129,
      "step": 200
    },
    {
      "epoch": 0.009881422924901186,
      "grad_norm": 0.42763814330101013,
      "learning_rate": 0.0001524673415596422,
      "loss": 2.0902,
      "step": 210
    },
    {
      "epoch": 0.010351966873706004,
      "grad_norm": 0.5467658638954163,
      "learning_rate": 0.00014570829890208668,
      "loss": 3.0582,
      "step": 220
    },
    {
      "epoch": 0.010822510822510822,
      "grad_norm": 0.8129895329475403,
      "learning_rate": 0.00013875580140374443,
      "loss": 2.9275,
      "step": 230
    },
    {
      "epoch": 0.01129305477131564,
      "grad_norm": 1.2014703750610352,
      "learning_rate": 0.00013164372093356477,
      "loss": 2.5216,
      "step": 240
    },
    {
      "epoch": 0.01176359872012046,
      "grad_norm": 1.4856128692626953,
      "learning_rate": 0.00012440670683269464,
      "loss": 2.8509,
      "step": 250
    },
    {
      "epoch": 0.01176359872012046,
      "eval_loss": 1.4362162351608276,
      "eval_runtime": 1052.317,
      "eval_samples_per_second": 8.504,
      "eval_steps_per_second": 2.127,
      "step": 250
    },
    {
      "epoch": 0.012234142668925278,
      "grad_norm": 0.44174057245254517,
      "learning_rate": 0.00011708001710637128,
      "loss": 2.0934,
      "step": 260
    },
    {
      "epoch": 0.012704686617730096,
      "grad_norm": 0.7299515008926392,
      "learning_rate": 0.00010969934665046512,
      "loss": 2.5203,
      "step": 270
    },
    {
      "epoch": 0.013175230566534914,
      "grad_norm": 0.7253561615943909,
      "learning_rate": 0.00010230065334953492,
      "loss": 3.0399,
      "step": 280
    },
    {
      "epoch": 0.013645774515339732,
      "grad_norm": 1.0471400022506714,
      "learning_rate": 9.491998289362875e-05,
      "loss": 2.7184,
      "step": 290
    },
    {
      "epoch": 0.014116318464144552,
      "grad_norm": 1.5433595180511475,
      "learning_rate": 8.759329316730539e-05,
      "loss": 2.949,
      "step": 300
    },
    {
      "epoch": 0.014116318464144552,
      "eval_loss": 1.3197296857833862,
      "eval_runtime": 1055.1737,
      "eval_samples_per_second": 8.481,
      "eval_steps_per_second": 2.121,
      "step": 300
    },
    {
      "epoch": 0.01458686241294937,
      "grad_norm": 0.5331817269325256,
      "learning_rate": 8.035627906643523e-05,
      "loss": 1.9766,
      "step": 310
    },
    {
      "epoch": 0.015057406361754188,
      "grad_norm": 0.42347341775894165,
      "learning_rate": 7.324419859625559e-05,
      "loss": 2.3662,
      "step": 320
    },
    {
      "epoch": 0.015527950310559006,
      "grad_norm": 0.7347255349159241,
      "learning_rate": 6.629170109791332e-05,
      "loss": 2.7505,
      "step": 330
    },
    {
      "epoch": 0.015998494259363824,
      "grad_norm": 0.8511791229248047,
      "learning_rate": 5.9532658440357784e-05,
      "loss": 2.3891,
      "step": 340
    },
    {
      "epoch": 0.016469038208168644,
      "grad_norm": 1.1082268953323364,
      "learning_rate": 5.300000000000002e-05,
      "loss": 2.7131,
      "step": 350
    },
    {
      "epoch": 0.016469038208168644,
      "eval_loss": 1.2930166721343994,
      "eval_runtime": 1050.6728,
      "eval_samples_per_second": 8.517,
      "eval_steps_per_second": 2.13,
      "step": 350
    },
    {
      "epoch": 0.01693958215697346,
      "grad_norm": 0.4141283929347992,
      "learning_rate": 4.672555223210085e-05,
      "loss": 1.9025,
      "step": 360
    },
    {
      "epoch": 0.01741012610577828,
      "grad_norm": 0.4382825195789337,
      "learning_rate": 4.073988361548022e-05,
      "loss": 2.5644,
      "step": 370
    },
    {
      "epoch": 0.0178806700545831,
      "grad_norm": 0.7108925580978394,
      "learning_rate": 3.507215572596106e-05,
      "loss": 2.9241,
      "step": 380
    },
    {
      "epoch": 0.018351214003387916,
      "grad_norm": 0.8783855438232422,
      "learning_rate": 2.9749981164102997e-05,
      "loss": 2.4924,
      "step": 390
    },
    {
      "epoch": 0.018821757952192736,
      "grad_norm": 1.2412166595458984,
      "learning_rate": 2.479928902938834e-05,
      "loss": 2.8697,
      "step": 400
    },
    {
      "epoch": 0.018821757952192736,
      "eval_loss": 1.2847579717636108,
      "eval_runtime": 1052.7564,
      "eval_samples_per_second": 8.501,
      "eval_steps_per_second": 2.126,
      "step": 400
    },
    {
      "epoch": 0.019292301900997552,
      "grad_norm": 0.3955267369747162,
      "learning_rate": 2.024419859625558e-05,
      "loss": 1.9078,
      "step": 410
    },
    {
      "epoch": 0.019762845849802372,
      "grad_norm": 0.4896032512187958,
      "learning_rate": 1.610690180741885e-05,
      "loss": 2.5107,
      "step": 420
    },
    {
      "epoch": 0.020233389798607188,
      "grad_norm": 0.688621461391449,
      "learning_rate": 1.240755515695374e-05,
      "loss": 3.0001,
      "step": 430
    },
    {
      "epoch": 0.020703933747412008,
      "grad_norm": 0.7938734292984009,
      "learning_rate": 9.164181489884296e-06,
      "loss": 2.5139,
      "step": 440
    },
    {
      "epoch": 0.021174477696216828,
      "grad_norm": 1.0540862083435059,
      "learning_rate": 6.392582196693718e-06,
      "loss": 2.7921,
      "step": 450
    },
    {
      "epoch": 0.021174477696216828,
      "eval_loss": 1.2806880474090576,
      "eval_runtime": 1054.9988,
      "eval_samples_per_second": 8.482,
      "eval_steps_per_second": 2.121,
      "step": 450
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9223752445263872e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}