{
  "best_metric": 0.33410218358039856,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.012825445684237527,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025650891368475054,
      "grad_norm": 0.2452760636806488,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.4425,
      "step": 1
    },
    {
      "epoch": 0.00025650891368475054,
      "eval_loss": 0.39530715346336365,
      "eval_runtime": 31.6895,
      "eval_samples_per_second": 1.578,
      "eval_steps_per_second": 0.221,
      "step": 1
    },
    {
      "epoch": 0.0005130178273695011,
      "grad_norm": 0.17752642929553986,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.299,
      "step": 2
    },
    {
      "epoch": 0.0007695267410542517,
      "grad_norm": 0.24689655005931854,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.5197,
      "step": 3
    },
    {
      "epoch": 0.0010260356547390022,
      "grad_norm": 0.19504807889461517,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.3453,
      "step": 4
    },
    {
      "epoch": 0.0012825445684237528,
      "grad_norm": 0.1986263245344162,
      "learning_rate": 0.00015,
      "loss": 1.3429,
      "step": 5
    },
    {
      "epoch": 0.0015390534821085034,
      "grad_norm": 0.310422420501709,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.3507,
      "step": 6
    },
    {
      "epoch": 0.0017955623957932538,
      "grad_norm": 0.2197422981262207,
      "learning_rate": 0.00020999999999999998,
      "loss": 1.3089,
      "step": 7
    },
    {
      "epoch": 0.0020520713094780044,
      "grad_norm": 0.22613106667995453,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.161,
      "step": 8
    },
    {
      "epoch": 0.002308580223162755,
      "grad_norm": 0.2758508026599884,
      "learning_rate": 0.00027,
      "loss": 1.3218,
      "step": 9
    },
    {
      "epoch": 0.0025650891368475055,
      "grad_norm": 0.24372389912605286,
      "learning_rate": 0.0003,
      "loss": 1.2277,
      "step": 10
    },
    {
      "epoch": 0.002821598050532256,
      "grad_norm": 0.24940873682498932,
      "learning_rate": 0.0002999794957488703,
      "loss": 1.1953,
      "step": 11
    },
    {
      "epoch": 0.0030781069642170067,
      "grad_norm": 0.23299287259578705,
      "learning_rate": 0.0002999179886011389,
      "loss": 1.1864,
      "step": 12
    },
    {
      "epoch": 0.003334615877901757,
      "grad_norm": 0.20366379618644714,
      "learning_rate": 0.0002998154953722457,
      "loss": 1.2584,
      "step": 13
    },
    {
      "epoch": 0.0035911247915865075,
      "grad_norm": 0.2235558032989502,
      "learning_rate": 0.00029967204408281613,
      "loss": 1.1625,
      "step": 14
    },
    {
      "epoch": 0.003847633705271258,
      "grad_norm": 0.198708176612854,
      "learning_rate": 0.00029948767395100045,
      "loss": 1.1748,
      "step": 15
    },
    {
      "epoch": 0.004104142618956009,
      "grad_norm": 0.1967567503452301,
      "learning_rate": 0.0002992624353817517,
      "loss": 1.1347,
      "step": 16
    },
    {
      "epoch": 0.004360651532640759,
      "grad_norm": 0.15366947650909424,
      "learning_rate": 0.0002989963899530457,
      "loss": 1.0114,
      "step": 17
    },
    {
      "epoch": 0.00461716044632551,
      "grad_norm": 0.18661633133888245,
      "learning_rate": 0.00029868961039904624,
      "loss": 1.2625,
      "step": 18
    },
    {
      "epoch": 0.00487366936001026,
      "grad_norm": 3.7823309898376465,
      "learning_rate": 0.00029834218059022024,
      "loss": 1.2615,
      "step": 19
    },
    {
      "epoch": 0.005130178273695011,
      "grad_norm": 0.20137062668800354,
      "learning_rate": 0.00029795419551040833,
      "loss": 1.27,
      "step": 20
    },
    {
      "epoch": 0.005386687187379761,
      "grad_norm": 0.18843530118465424,
      "learning_rate": 0.00029752576123085736,
      "loss": 1.0947,
      "step": 21
    },
    {
      "epoch": 0.005643196101064512,
      "grad_norm": 0.17115682363510132,
      "learning_rate": 0.0002970569948812214,
      "loss": 1.1604,
      "step": 22
    },
    {
      "epoch": 0.0058997050147492625,
      "grad_norm": 0.17423115670681,
      "learning_rate": 0.0002965480246175399,
      "loss": 1.2279,
      "step": 23
    },
    {
      "epoch": 0.0061562139284340135,
      "grad_norm": 0.20533309876918793,
      "learning_rate": 0.0002959989895872009,
      "loss": 1.3852,
      "step": 24
    },
    {
      "epoch": 0.006412722842118764,
      "grad_norm": 0.19516155123710632,
      "learning_rate": 0.0002954100398908995,
      "loss": 1.3035,
      "step": 25
    },
    {
      "epoch": 0.006412722842118764,
      "eval_loss": 0.3231082558631897,
      "eval_runtime": 31.8559,
      "eval_samples_per_second": 1.57,
      "eval_steps_per_second": 0.22,
      "step": 25
    },
    {
      "epoch": 0.006669231755803514,
      "grad_norm": 0.3001914322376251,
      "learning_rate": 0.0002947813365416023,
      "loss": 1.3519,
      "step": 26
    },
    {
      "epoch": 0.006925740669488265,
      "grad_norm": 0.2448321133852005,
      "learning_rate": 0.0002941130514205272,
      "loss": 1.3134,
      "step": 27
    },
    {
      "epoch": 0.007182249583173015,
      "grad_norm": 0.21013857424259186,
      "learning_rate": 0.0002934053672301536,
      "loss": 1.1908,
      "step": 28
    },
    {
      "epoch": 0.007438758496857766,
      "grad_norm": 0.2920572757720947,
      "learning_rate": 0.00029265847744427303,
      "loss": 1.2764,
      "step": 29
    },
    {
      "epoch": 0.007695267410542516,
      "grad_norm": 0.23325499892234802,
      "learning_rate": 0.00029187258625509513,
      "loss": 1.2081,
      "step": 30
    },
    {
      "epoch": 0.007951776324227267,
      "grad_norm": 0.24203185737133026,
      "learning_rate": 0.00029104790851742417,
      "loss": 1.2996,
      "step": 31
    },
    {
      "epoch": 0.008208285237912017,
      "grad_norm": 0.20244275033473969,
      "learning_rate": 0.0002901846696899191,
      "loss": 1.2741,
      "step": 32
    },
    {
      "epoch": 0.008464794151596768,
      "grad_norm": 0.24007591605186462,
      "learning_rate": 0.00028928310577345606,
      "loss": 1.2926,
      "step": 33
    },
    {
      "epoch": 0.008721303065281518,
      "grad_norm": 2.9329335689544678,
      "learning_rate": 0.0002883434632466077,
      "loss": 1.3904,
      "step": 34
    },
    {
      "epoch": 0.00897781197896627,
      "grad_norm": 0.2622990906238556,
      "learning_rate": 0.00028736599899825856,
      "loss": 1.3224,
      "step": 35
    },
    {
      "epoch": 0.00923432089265102,
      "grad_norm": 0.3389492630958557,
      "learning_rate": 0.00028635098025737434,
      "loss": 1.3022,
      "step": 36
    },
    {
      "epoch": 0.00949082980633577,
      "grad_norm": 0.3291040062904358,
      "learning_rate": 0.00028529868451994384,
      "loss": 1.3772,
      "step": 37
    },
    {
      "epoch": 0.00974733872002052,
      "grad_norm": 0.29008948802948,
      "learning_rate": 0.0002842093994731145,
      "loss": 1.3874,
      "step": 38
    },
    {
      "epoch": 0.010003847633705272,
      "grad_norm": 0.2444349229335785,
      "learning_rate": 0.00028308342291654174,
      "loss": 1.3194,
      "step": 39
    },
    {
      "epoch": 0.010260356547390022,
      "grad_norm": 0.2349006086587906,
      "learning_rate": 0.00028192106268097334,
      "loss": 1.2226,
      "step": 40
    },
    {
      "epoch": 0.010516865461074772,
      "grad_norm": 0.3519050180912018,
      "learning_rate": 0.00028072263654409154,
      "loss": 1.2642,
      "step": 41
    },
    {
      "epoch": 0.010773374374759523,
      "grad_norm": 3.122650384902954,
      "learning_rate": 0.0002794884721436361,
      "loss": 1.3993,
      "step": 42
    },
    {
      "epoch": 0.011029883288444273,
      "grad_norm": 0.4444164037704468,
      "learning_rate": 0.00027821890688783083,
      "loss": 1.2325,
      "step": 43
    },
    {
      "epoch": 0.011286392202129025,
      "grad_norm": 0.3635028302669525,
      "learning_rate": 0.0002769142878631403,
      "loss": 1.2689,
      "step": 44
    },
    {
      "epoch": 0.011542901115813775,
      "grad_norm": 0.5229223370552063,
      "learning_rate": 0.00027557497173937923,
      "loss": 1.3902,
      "step": 45
    },
    {
      "epoch": 0.011799410029498525,
      "grad_norm": 0.6191115379333496,
      "learning_rate": 0.000274201324672203,
      "loss": 1.4242,
      "step": 46
    },
    {
      "epoch": 0.012055918943183275,
      "grad_norm": 1.497909665107727,
      "learning_rate": 0.00027279372220300385,
      "loss": 1.7142,
      "step": 47
    },
    {
      "epoch": 0.012312427856868027,
      "grad_norm": 1.673071026802063,
      "learning_rate": 0.0002713525491562421,
      "loss": 1.6996,
      "step": 48
    },
    {
      "epoch": 0.012568936770552777,
      "grad_norm": 7.249523639678955,
      "learning_rate": 0.00026987819953423867,
      "loss": 1.9288,
      "step": 49
    },
    {
      "epoch": 0.012825445684237527,
      "grad_norm": 6.95615816116333,
      "learning_rate": 0.00026837107640945905,
      "loss": 2.1629,
      "step": 50
    },
    {
      "epoch": 0.012825445684237527,
      "eval_loss": 0.33410218358039856,
      "eval_runtime": 31.8447,
      "eval_samples_per_second": 1.57,
      "eval_steps_per_second": 0.22,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.7850713268224e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}