{
  "best_metric": 0.875745415687561,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.03259133722256624,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.518267444513249e-05,
      "eval_loss": 2.850663900375366,
      "eval_runtime": 443.5942,
      "eval_samples_per_second": 14.563,
      "eval_steps_per_second": 3.641,
      "step": 1
    },
    {
      "epoch": 0.0006518267444513248,
      "grad_norm": 3.971789598464966,
      "learning_rate": 4.16e-05,
      "loss": 2.0815,
      "step": 10
    },
    {
      "epoch": 0.0013036534889026496,
      "grad_norm": 2.8578591346740723,
      "learning_rate": 8.32e-05,
      "loss": 1.8557,
      "step": 20
    },
    {
      "epoch": 0.0019554802333539745,
      "grad_norm": 3.0689802169799805,
      "learning_rate": 0.0001248,
      "loss": 1.5229,
      "step": 30
    },
    {
      "epoch": 0.002607306977805299,
      "grad_norm": 4.3151397705078125,
      "learning_rate": 0.0001664,
      "loss": 1.3099,
      "step": 40
    },
    {
      "epoch": 0.0032591337222566243,
      "grad_norm": 4.729147434234619,
      "learning_rate": 0.000208,
      "loss": 1.6873,
      "step": 50
    },
    {
      "epoch": 0.0032591337222566243,
      "eval_loss": 1.273123025894165,
      "eval_runtime": 445.0677,
      "eval_samples_per_second": 14.515,
      "eval_steps_per_second": 3.629,
      "step": 50
    },
    {
      "epoch": 0.003910960466707949,
      "grad_norm": 2.3496737480163574,
      "learning_rate": 0.0002077466612270217,
      "loss": 1.0568,
      "step": 60
    },
    {
      "epoch": 0.004562787211159274,
      "grad_norm": 2.499488353729248,
      "learning_rate": 0.0002069878791491233,
      "loss": 1.1359,
      "step": 70
    },
    {
      "epoch": 0.005214613955610598,
      "grad_norm": 3.1299209594726562,
      "learning_rate": 0.00020572735047631578,
      "loss": 1.2264,
      "step": 80
    },
    {
      "epoch": 0.005866440700061924,
      "grad_norm": 3.3837058544158936,
      "learning_rate": 0.00020397121637758515,
      "loss": 1.2004,
      "step": 90
    },
    {
      "epoch": 0.006518267444513249,
      "grad_norm": 2.973175287246704,
      "learning_rate": 0.00020172803256173445,
      "loss": 1.545,
      "step": 100
    },
    {
      "epoch": 0.006518267444513249,
      "eval_loss": 1.275679111480713,
      "eval_runtime": 446.3022,
      "eval_samples_per_second": 14.474,
      "eval_steps_per_second": 3.619,
      "step": 100
    },
    {
      "epoch": 0.007170094188964573,
      "grad_norm": 2.3844895362854004,
      "learning_rate": 0.00019900872759483047,
      "loss": 1.0244,
      "step": 110
    },
    {
      "epoch": 0.007821920933415898,
      "grad_norm": 2.4352855682373047,
      "learning_rate": 0.0001958265496573284,
      "loss": 1.1891,
      "step": 120
    },
    {
      "epoch": 0.008473747677867223,
      "grad_norm": 3.231959819793701,
      "learning_rate": 0.00019219700200026827,
      "loss": 1.2308,
      "step": 130
    },
    {
      "epoch": 0.009125574422318547,
      "grad_norm": 2.5154852867126465,
      "learning_rate": 0.0001881377674149945,
      "loss": 1.2077,
      "step": 140
    },
    {
      "epoch": 0.009777401166769872,
      "grad_norm": 3.0093817710876465,
      "learning_rate": 0.00018366862208437368,
      "loss": 1.3988,
      "step": 150
    },
    {
      "epoch": 0.009777401166769872,
      "eval_loss": 1.1874332427978516,
      "eval_runtime": 447.657,
      "eval_samples_per_second": 14.431,
      "eval_steps_per_second": 3.608,
      "step": 150
    },
    {
      "epoch": 0.010429227911221197,
      "grad_norm": 2.5995352268218994,
      "learning_rate": 0.00017881133923521971,
      "loss": 1.0265,
      "step": 160
    },
    {
      "epoch": 0.011081054655672521,
      "grad_norm": 2.5440680980682373,
      "learning_rate": 0.00017358958306132124,
      "loss": 0.9651,
      "step": 170
    },
    {
      "epoch": 0.011732881400123848,
      "grad_norm": 2.6204676628112793,
      "learning_rate": 0.00016802879343386844,
      "loss": 1.0322,
      "step": 180
    },
    {
      "epoch": 0.012384708144575172,
      "grad_norm": 2.2899601459503174,
      "learning_rate": 0.00016215606196095766,
      "loss": 1.1977,
      "step": 190
    },
    {
      "epoch": 0.013036534889026497,
      "grad_norm": 3.2127535343170166,
      "learning_rate": 0.000156,
      "loss": 1.6102,
      "step": 200
    },
    {
      "epoch": 0.013036534889026497,
      "eval_loss": 1.1086701154708862,
      "eval_runtime": 446.4333,
      "eval_samples_per_second": 14.47,
      "eval_steps_per_second": 3.618,
      "step": 200
    },
    {
      "epoch": 0.013688361633477822,
      "grad_norm": 1.3613508939743042,
      "learning_rate": 0.00014959059926606403,
      "loss": 0.838,
      "step": 210
    },
    {
      "epoch": 0.014340188377929147,
      "grad_norm": 1.6068763732910156,
      "learning_rate": 0.00014295908571525487,
      "loss": 0.9718,
      "step": 220
    },
    {
      "epoch": 0.014992015122380471,
      "grad_norm": 2.977311849594116,
      "learning_rate": 0.00013613776741499452,
      "loss": 1.0673,
      "step": 230
    },
    {
      "epoch": 0.015643841866831796,
      "grad_norm": 2.3362767696380615,
      "learning_rate": 0.00012915987714236542,
      "loss": 1.1417,
      "step": 240
    },
    {
      "epoch": 0.01629566861128312,
      "grad_norm": 5.354211807250977,
      "learning_rate": 0.00012205941047736077,
      "loss": 1.3597,
      "step": 250
    },
    {
      "epoch": 0.01629566861128312,
      "eval_loss": 1.0507456064224243,
      "eval_runtime": 446.5699,
      "eval_samples_per_second": 14.466,
      "eval_steps_per_second": 3.616,
      "step": 250
    },
    {
      "epoch": 0.016947495355734445,
      "grad_norm": 2.0789878368377686,
      "learning_rate": 0.00011487096017983597,
      "loss": 0.8857,
      "step": 260
    },
    {
      "epoch": 0.01759932210018577,
      "grad_norm": 1.4197766780853271,
      "learning_rate": 0.00010762954765706012,
      "loss": 0.903,
      "step": 270
    },
    {
      "epoch": 0.018251148844637095,
      "grad_norm": 2.561424732208252,
      "learning_rate": 0.00010037045234293992,
      "loss": 0.9548,
      "step": 280
    },
    {
      "epoch": 0.01890297558908842,
      "grad_norm": 1.98018217086792,
      "learning_rate": 9.312903982016405e-05,
      "loss": 1.1046,
      "step": 290
    },
    {
      "epoch": 0.019554802333539744,
      "grad_norm": 5.7000837326049805,
      "learning_rate": 8.594058952263925e-05,
      "loss": 1.3285,
      "step": 300
    },
    {
      "epoch": 0.019554802333539744,
      "eval_loss": 0.9808639287948608,
      "eval_runtime": 446.8663,
      "eval_samples_per_second": 14.456,
      "eval_steps_per_second": 3.614,
      "step": 300
    },
    {
      "epoch": 0.02020662907799107,
      "grad_norm": 1.3622760772705078,
      "learning_rate": 7.884012285763457e-05,
      "loss": 0.7478,
      "step": 310
    },
    {
      "epoch": 0.020858455822442393,
      "grad_norm": 1.826834797859192,
      "learning_rate": 7.186223258500548e-05,
      "loss": 0.8517,
      "step": 320
    },
    {
      "epoch": 0.021510282566893718,
      "grad_norm": 1.2498234510421753,
      "learning_rate": 6.504091428474514e-05,
      "loss": 1.0577,
      "step": 330
    },
    {
      "epoch": 0.022162109311345043,
      "grad_norm": 2.1019372940063477,
      "learning_rate": 5.840940073393593e-05,
      "loss": 0.8884,
      "step": 340
    },
    {
      "epoch": 0.02281393605579637,
      "grad_norm": 2.712697744369507,
      "learning_rate": 5.200000000000002e-05,
      "loss": 1.0915,
      "step": 350
    },
    {
      "epoch": 0.02281393605579637,
      "eval_loss": 0.9416553974151611,
      "eval_runtime": 449.3829,
      "eval_samples_per_second": 14.375,
      "eval_steps_per_second": 3.594,
      "step": 350
    },
    {
      "epoch": 0.023465762800247696,
      "grad_norm": 1.5010788440704346,
      "learning_rate": 4.5843938039042344e-05,
      "loss": 0.829,
      "step": 360
    },
    {
      "epoch": 0.02411758954469902,
      "grad_norm": 3.3226091861724854,
      "learning_rate": 3.997120656613154e-05,
      "loss": 0.9773,
      "step": 370
    },
    {
      "epoch": 0.024769416289150345,
      "grad_norm": 1.6384238004684448,
      "learning_rate": 3.441041693867878e-05,
      "loss": 0.8725,
      "step": 380
    },
    {
      "epoch": 0.02542124303360167,
      "grad_norm": 2.352992534637451,
      "learning_rate": 2.9188660764780296e-05,
      "loss": 0.9907,
      "step": 390
    },
    {
      "epoch": 0.026073069778052994,
      "grad_norm": 3.1694495677948,
      "learning_rate": 2.4331377915626298e-05,
      "loss": 1.2449,
      "step": 400
    },
    {
      "epoch": 0.026073069778052994,
      "eval_loss": 0.8955165147781372,
      "eval_runtime": 446.7108,
      "eval_samples_per_second": 14.461,
      "eval_steps_per_second": 3.615,
      "step": 400
    },
    {
      "epoch": 0.02672489652250432,
      "grad_norm": 2.0528738498687744,
      "learning_rate": 1.9862232585005475e-05,
      "loss": 0.7577,
      "step": 410
    },
    {
      "epoch": 0.027376723266955644,
      "grad_norm": 1.3070178031921387,
      "learning_rate": 1.58029979997317e-05,
      "loss": 0.7595,
      "step": 420
    },
    {
      "epoch": 0.02802855001140697,
      "grad_norm": 2.6197099685668945,
      "learning_rate": 1.2173450342671593e-05,
      "loss": 0.7412,
      "step": 430
    },
    {
      "epoch": 0.028680376755858293,
      "grad_norm": 2.77477765083313,
      "learning_rate": 8.991272405169498e-06,
      "loss": 0.9327,
      "step": 440
    },
    {
      "epoch": 0.029332203500309618,
      "grad_norm": 4.5697340965271,
      "learning_rate": 6.271967438265535e-06,
      "loss": 1.0734,
      "step": 450
    },
    {
      "epoch": 0.029332203500309618,
      "eval_loss": 0.876220166683197,
      "eval_runtime": 443.5926,
      "eval_samples_per_second": 14.563,
      "eval_steps_per_second": 3.641,
      "step": 450
    },
    {
      "epoch": 0.029984030244760942,
      "grad_norm": 2.2378225326538086,
      "learning_rate": 4.028783622414835e-06,
      "loss": 0.6365,
      "step": 460
    },
    {
      "epoch": 0.030635856989212267,
      "grad_norm": 2.819683074951172,
      "learning_rate": 2.272649523684208e-06,
      "loss": 0.8311,
      "step": 470
    },
    {
      "epoch": 0.03128768373366359,
      "grad_norm": 1.4101600646972656,
      "learning_rate": 1.0121208508766823e-06,
      "loss": 0.9517,
      "step": 480
    },
    {
      "epoch": 0.03193951047811492,
      "grad_norm": 1.9987350702285767,
      "learning_rate": 2.533387729782834e-07,
      "loss": 0.8854,
      "step": 490
    },
    {
      "epoch": 0.03259133722256624,
      "grad_norm": 5.414979934692383,
      "learning_rate": 0.0,
      "loss": 1.0317,
      "step": 500
    },
    {
      "epoch": 0.03259133722256624,
      "eval_loss": 0.875745415687561,
      "eval_runtime": 444.3276,
      "eval_samples_per_second": 14.539,
      "eval_steps_per_second": 3.635,
      "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": 1.0400815009234944e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}