{
  "best_metric": 1.9051249027252197,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.338409475465313,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00676818950930626,
      "grad_norm": 2.9296860694885254,
      "learning_rate": 5e-05,
      "loss": 2.5055,
      "step": 1
    },
    {
      "epoch": 0.00676818950930626,
      "eval_loss": 2.3484981060028076,
      "eval_runtime": 43.3068,
      "eval_samples_per_second": 22.999,
      "eval_steps_per_second": 2.886,
      "step": 1
    },
    {
      "epoch": 0.01353637901861252,
      "grad_norm": 2.674210548400879,
      "learning_rate": 0.0001,
      "loss": 2.4759,
      "step": 2
    },
    {
      "epoch": 0.02030456852791878,
      "grad_norm": 1.9132170677185059,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.3506,
      "step": 3
    },
    {
      "epoch": 0.02707275803722504,
      "grad_norm": 0.577763557434082,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.1336,
      "step": 4
    },
    {
      "epoch": 0.0338409475465313,
      "grad_norm": 0.7641364336013794,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.1191,
      "step": 5
    },
    {
      "epoch": 0.04060913705583756,
      "grad_norm": 0.791408360004425,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.0239,
      "step": 6
    },
    {
      "epoch": 0.047377326565143825,
      "grad_norm": 0.5952112078666687,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.8898,
      "step": 7
    },
    {
      "epoch": 0.05414551607445008,
      "grad_norm": 0.4372492730617523,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7989,
      "step": 8
    },
    {
      "epoch": 0.06091370558375635,
      "grad_norm": 0.4423554539680481,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.6365,
      "step": 9
    },
    {
      "epoch": 0.0676818950930626,
      "grad_norm": 0.4779082238674164,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.594,
      "step": 10
    },
    {
      "epoch": 0.07445008460236886,
      "grad_norm": 0.4887543320655823,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.6653,
      "step": 11
    },
    {
      "epoch": 0.08121827411167512,
      "grad_norm": 0.8437167406082153,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.9598,
      "step": 12
    },
    {
      "epoch": 0.08798646362098139,
      "grad_norm": 0.4406662583351135,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.2112,
      "step": 13
    },
    {
      "epoch": 0.09475465313028765,
      "grad_norm": 0.3242863416671753,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.2017,
      "step": 14
    },
    {
      "epoch": 0.10152284263959391,
      "grad_norm": 0.3156057596206665,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.1439,
      "step": 15
    },
    {
      "epoch": 0.10829103214890017,
      "grad_norm": 0.3377864360809326,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.1071,
      "step": 16
    },
    {
      "epoch": 0.11505922165820642,
      "grad_norm": 0.4013800024986267,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.0067,
      "step": 17
    },
    {
      "epoch": 0.1218274111675127,
      "grad_norm": 0.41989168524742126,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.9837,
      "step": 18
    },
    {
      "epoch": 0.12859560067681894,
      "grad_norm": 0.4310426115989685,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.9328,
      "step": 19
    },
    {
      "epoch": 0.1353637901861252,
      "grad_norm": 0.4445689916610718,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.7692,
      "step": 20
    },
    {
      "epoch": 0.14213197969543148,
      "grad_norm": 0.43501874804496765,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.6823,
      "step": 21
    },
    {
      "epoch": 0.14890016920473773,
      "grad_norm": 0.40112319588661194,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.6067,
      "step": 22
    },
    {
      "epoch": 0.155668358714044,
      "grad_norm": 0.36905568838119507,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.543,
      "step": 23
    },
    {
      "epoch": 0.16243654822335024,
      "grad_norm": 0.6415027379989624,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.7442,
      "step": 24
    },
    {
      "epoch": 0.1692047377326565,
      "grad_norm": 1.0896086692810059,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.9124,
      "step": 25
    },
    {
      "epoch": 0.1692047377326565,
      "eval_loss": 1.9359509944915771,
      "eval_runtime": 43.1524,
      "eval_samples_per_second": 23.081,
      "eval_steps_per_second": 2.897,
      "step": 25
    },
    {
      "epoch": 0.17597292724196278,
      "grad_norm": 0.2750670909881592,
      "learning_rate": 5e-05,
      "loss": 2.1265,
      "step": 26
    },
    {
      "epoch": 0.18274111675126903,
      "grad_norm": 0.38232484459877014,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 2.1345,
      "step": 27
    },
    {
      "epoch": 0.1895093062605753,
      "grad_norm": 0.4169054925441742,
      "learning_rate": 4.347369038899744e-05,
      "loss": 2.0528,
      "step": 28
    },
    {
      "epoch": 0.19627749576988154,
      "grad_norm": 0.40570560097694397,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 2.0143,
      "step": 29
    },
    {
      "epoch": 0.20304568527918782,
      "grad_norm": 0.3528883457183838,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.9312,
      "step": 30
    },
    {
      "epoch": 0.2098138747884941,
      "grad_norm": 0.3033808469772339,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.8836,
      "step": 31
    },
    {
      "epoch": 0.21658206429780033,
      "grad_norm": 0.2766481041908264,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.7806,
      "step": 32
    },
    {
      "epoch": 0.2233502538071066,
      "grad_norm": 0.2640785872936249,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.6759,
      "step": 33
    },
    {
      "epoch": 0.23011844331641285,
      "grad_norm": 0.28005650639533997,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.6188,
      "step": 34
    },
    {
      "epoch": 0.23688663282571912,
      "grad_norm": 0.37474751472473145,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.4857,
      "step": 35
    },
    {
      "epoch": 0.2436548223350254,
      "grad_norm": 0.37401193380355835,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.6013,
      "step": 36
    },
    {
      "epoch": 0.25042301184433163,
      "grad_norm": 0.42353835701942444,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.7093,
      "step": 37
    },
    {
      "epoch": 0.2571912013536379,
      "grad_norm": 0.20915140211582184,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.2199,
      "step": 38
    },
    {
      "epoch": 0.2639593908629442,
      "grad_norm": 0.18331202864646912,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 2.1516,
      "step": 39
    },
    {
      "epoch": 0.2707275803722504,
      "grad_norm": 0.20476865768432617,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 2.0795,
      "step": 40
    },
    {
      "epoch": 0.27749576988155666,
      "grad_norm": 0.20578041672706604,
      "learning_rate": 8.426519384872733e-06,
      "loss": 2.0425,
      "step": 41
    },
    {
      "epoch": 0.28426395939086296,
      "grad_norm": 0.21516215801239014,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.0114,
      "step": 42
    },
    {
      "epoch": 0.2910321489001692,
      "grad_norm": 0.22728796303272247,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.9486,
      "step": 43
    },
    {
      "epoch": 0.29780033840947545,
      "grad_norm": 0.23517738282680511,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.9551,
      "step": 44
    },
    {
      "epoch": 0.30456852791878175,
      "grad_norm": 0.24790968000888824,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.8253,
      "step": 45
    },
    {
      "epoch": 0.311336717428088,
      "grad_norm": 0.28092682361602783,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.6885,
      "step": 46
    },
    {
      "epoch": 0.31810490693739424,
      "grad_norm": 0.317545086145401,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.5831,
      "step": 47
    },
    {
      "epoch": 0.3248730964467005,
      "grad_norm": 0.3611891269683838,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.5272,
      "step": 48
    },
    {
      "epoch": 0.3316412859560068,
      "grad_norm": 0.3798593282699585,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.6716,
      "step": 49
    },
    {
      "epoch": 0.338409475465313,
      "grad_norm": 0.7036547660827637,
      "learning_rate": 0.0,
      "loss": 2.0506,
      "step": 50
    },
    {
      "epoch": 0.338409475465313,
      "eval_loss": 1.9051249027252197,
      "eval_runtime": 44.154,
      "eval_samples_per_second": 22.557,
      "eval_steps_per_second": 2.831,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1.684216011995218e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}