{
  "best_metric": 1.1528342962265015,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.008418783990840364,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6837567981680726e-05,
      "eval_loss": 2.296457529067993,
      "eval_runtime": 1687.1865,
      "eval_samples_per_second": 14.822,
      "eval_steps_per_second": 3.706,
      "step": 1
    },
    {
      "epoch": 0.00016837567981680727,
      "grad_norm": 1.795365571975708,
      "learning_rate": 4.2800000000000004e-05,
      "loss": 1.902,
      "step": 10
    },
    {
      "epoch": 0.00033675135963361454,
      "grad_norm": 2.1661720275878906,
      "learning_rate": 8.560000000000001e-05,
      "loss": 1.3571,
      "step": 20
    },
    {
      "epoch": 0.0005051270394504217,
      "grad_norm": 1.6164090633392334,
      "learning_rate": 0.0001284,
      "loss": 1.2606,
      "step": 30
    },
    {
      "epoch": 0.0006735027192672291,
      "grad_norm": 2.0214858055114746,
      "learning_rate": 0.00017120000000000001,
      "loss": 1.3816,
      "step": 40
    },
    {
      "epoch": 0.0008418783990840363,
      "grad_norm": 3.338027238845825,
      "learning_rate": 0.000214,
      "loss": 1.4541,
      "step": 50
    },
    {
      "epoch": 0.0008418783990840363,
      "eval_loss": 1.289824366569519,
      "eval_runtime": 1685.1162,
      "eval_samples_per_second": 14.84,
      "eval_steps_per_second": 3.71,
      "step": 50
    },
    {
      "epoch": 0.0010102540789008435,
      "grad_norm": 3.690471887588501,
      "learning_rate": 0.00021373935337780118,
      "loss": 1.1769,
      "step": 60
    },
    {
      "epoch": 0.0011786297587176508,
      "grad_norm": 1.5708606243133545,
      "learning_rate": 0.00021295868335534802,
      "loss": 1.0838,
      "step": 70
    },
    {
      "epoch": 0.0013470054385344582,
      "grad_norm": 1.608247995376587,
      "learning_rate": 0.0002116617932785172,
      "loss": 1.1606,
      "step": 80
    },
    {
      "epoch": 0.0015153811183512653,
      "grad_norm": 2.022498607635498,
      "learning_rate": 0.00020985500146540012,
      "loss": 1.2215,
      "step": 90
    },
    {
      "epoch": 0.0016837567981680727,
      "grad_norm": 4.2700910568237305,
      "learning_rate": 0.0002075471104240922,
      "loss": 1.4665,
      "step": 100
    },
    {
      "epoch": 0.0016837567981680727,
      "eval_loss": 1.3164697885513306,
      "eval_runtime": 1686.7665,
      "eval_samples_per_second": 14.825,
      "eval_steps_per_second": 3.707,
      "step": 100
    },
    {
      "epoch": 0.0018521324779848798,
      "grad_norm": 1.7091002464294434,
      "learning_rate": 0.00020474936396775828,
      "loss": 1.293,
      "step": 110
    },
    {
      "epoch": 0.002020508157801687,
      "grad_norm": 1.684004783630371,
      "learning_rate": 0.00020147539243590517,
      "loss": 1.0287,
      "step": 120
    },
    {
      "epoch": 0.0021888838376184945,
      "grad_norm": 1.815836787223816,
      "learning_rate": 0.00019774114628873756,
      "loss": 1.129,
      "step": 130
    },
    {
      "epoch": 0.0023572595174353016,
      "grad_norm": 1.905654788017273,
      "learning_rate": 0.00019356481839811937,
      "loss": 1.1745,
      "step": 140
    },
    {
      "epoch": 0.0025256351972521088,
      "grad_norm": 3.854990005493164,
      "learning_rate": 0.00018896675541373064,
      "loss": 1.538,
      "step": 150
    },
    {
      "epoch": 0.0025256351972521088,
      "eval_loss": 1.274539589881897,
      "eval_runtime": 1688.0862,
      "eval_samples_per_second": 14.814,
      "eval_steps_per_second": 3.704,
      "step": 150
    },
    {
      "epoch": 0.0026940108770689163,
      "grad_norm": 1.3403651714324951,
      "learning_rate": 0.00018396935863623567,
      "loss": 1.2173,
      "step": 160
    },
    {
      "epoch": 0.0028623865568857235,
      "grad_norm": 1.405836820602417,
      "learning_rate": 0.00017859697488039784,
      "loss": 1.0537,
      "step": 170
    },
    {
      "epoch": 0.0030307622367025306,
      "grad_norm": 1.8490408658981323,
      "learning_rate": 0.00017287577785984542,
      "loss": 1.2706,
      "step": 180
    },
    {
      "epoch": 0.0031991379165193378,
      "grad_norm": 2.120272397994995,
      "learning_rate": 0.0001668336406713699,
      "loss": 1.3493,
      "step": 190
    },
    {
      "epoch": 0.0033675135963361453,
      "grad_norm": 2.9566562175750732,
      "learning_rate": 0.0001605,
      "loss": 1.4803,
      "step": 200
    },
    {
      "epoch": 0.0033675135963361453,
      "eval_loss": 1.2688231468200684,
      "eval_runtime": 1688.2003,
      "eval_samples_per_second": 14.813,
      "eval_steps_per_second": 3.703,
      "step": 200
    },
    {
      "epoch": 0.0035358892761529525,
      "grad_norm": 1.4451912641525269,
      "learning_rate": 0.00015390571270643128,
      "loss": 1.0993,
      "step": 210
    },
    {
      "epoch": 0.0037042649559697596,
      "grad_norm": 1.5819648504257202,
      "learning_rate": 0.0001470829054955026,
      "loss": 1.113,
      "step": 220
    },
    {
      "epoch": 0.003872640635786567,
      "grad_norm": 2.1583080291748047,
      "learning_rate": 0.00014006481839811937,
      "loss": 1.2436,
      "step": 230
    },
    {
      "epoch": 0.004041016315603374,
      "grad_norm": 2.5022051334381104,
      "learning_rate": 0.00013288564282916442,
      "loss": 1.3693,
      "step": 240
    },
    {
      "epoch": 0.004209391995420182,
      "grad_norm": 4.059680461883545,
      "learning_rate": 0.00012558035501036158,
      "loss": 1.63,
      "step": 250
    },
    {
      "epoch": 0.004209391995420182,
      "eval_loss": 1.2357275485992432,
      "eval_runtime": 1686.4416,
      "eval_samples_per_second": 14.828,
      "eval_steps_per_second": 3.707,
      "step": 250
    },
    {
      "epoch": 0.004377767675236989,
      "grad_norm": 1.4801981449127197,
      "learning_rate": 0.00011818454556963892,
      "loss": 1.0041,
      "step": 260
    },
    {
      "epoch": 0.004546143355053796,
      "grad_norm": 1.3664003610610962,
      "learning_rate": 0.00011073424614716762,
      "loss": 1.0114,
      "step": 270
    },
    {
      "epoch": 0.004714519034870603,
      "grad_norm": 1.5936243534088135,
      "learning_rate": 0.00010326575385283242,
      "loss": 1.1728,
      "step": 280
    },
    {
      "epoch": 0.00488289471468741,
      "grad_norm": 1.537528157234192,
      "learning_rate": 9.58154544303611e-05,
      "loss": 1.3018,
      "step": 290
    },
    {
      "epoch": 0.0050512703945042176,
      "grad_norm": 2.965649127960205,
      "learning_rate": 8.841964498963846e-05,
      "loss": 1.5497,
      "step": 300
    },
    {
      "epoch": 0.0050512703945042176,
      "eval_loss": 1.223321795463562,
      "eval_runtime": 1686.5734,
      "eval_samples_per_second": 14.827,
      "eval_steps_per_second": 3.707,
      "step": 300
    },
    {
      "epoch": 0.005219646074321025,
      "grad_norm": 1.483461618423462,
      "learning_rate": 8.111435717083556e-05,
      "loss": 1.1607,
      "step": 310
    },
    {
      "epoch": 0.005388021754137833,
      "grad_norm": 1.2739410400390625,
      "learning_rate": 7.393518160188063e-05,
      "loss": 1.0222,
      "step": 320
    },
    {
      "epoch": 0.00555639743395464,
      "grad_norm": 1.644224762916565,
      "learning_rate": 6.69170945044974e-05,
      "loss": 1.1464,
      "step": 330
    },
    {
      "epoch": 0.005724773113771447,
      "grad_norm": 2.106903076171875,
      "learning_rate": 6.009428729356871e-05,
      "loss": 1.2647,
      "step": 340
    },
    {
      "epoch": 0.005893148793588254,
      "grad_norm": 2.470841646194458,
      "learning_rate": 5.3500000000000026e-05,
      "loss": 1.5781,
      "step": 350
    },
    {
      "epoch": 0.005893148793588254,
      "eval_loss": 1.1787070035934448,
      "eval_runtime": 1687.9624,
      "eval_samples_per_second": 14.815,
      "eval_steps_per_second": 3.704,
      "step": 350
    },
    {
      "epoch": 0.006061524473405061,
      "grad_norm": 1.565023422241211,
      "learning_rate": 4.7166359328630106e-05,
      "loss": 1.0986,
      "step": 360
    },
    {
      "epoch": 0.006229900153221868,
      "grad_norm": 1.3808709383010864,
      "learning_rate": 4.112422214015456e-05,
      "loss": 1.078,
      "step": 370
    },
    {
      "epoch": 0.0063982758330386755,
      "grad_norm": 1.5624812841415405,
      "learning_rate": 3.5403025119602206e-05,
      "loss": 1.153,
      "step": 380
    },
    {
      "epoch": 0.0065666515128554835,
      "grad_norm": 1.8611598014831543,
      "learning_rate": 3.0030641363764346e-05,
      "loss": 1.2869,
      "step": 390
    },
    {
      "epoch": 0.006735027192672291,
      "grad_norm": 1.9800591468811035,
      "learning_rate": 2.5033244586269365e-05,
      "loss": 1.3724,
      "step": 400
    },
    {
      "epoch": 0.006735027192672291,
      "eval_loss": 1.1627603769302368,
      "eval_runtime": 1687.9689,
      "eval_samples_per_second": 14.815,
      "eval_steps_per_second": 3.704,
      "step": 400
    },
    {
      "epoch": 0.006903402872489098,
      "grad_norm": 1.244630217552185,
      "learning_rate": 2.0435181601880635e-05,
      "loss": 1.0196,
      "step": 410
    },
    {
      "epoch": 0.007071778552305905,
      "grad_norm": 1.495737075805664,
      "learning_rate": 1.625885371126242e-05,
      "loss": 1.0804,
      "step": 420
    },
    {
      "epoch": 0.007240154232122712,
      "grad_norm": 1.6196967363357544,
      "learning_rate": 1.2524607564094813e-05,
      "loss": 1.1342,
      "step": 430
    },
    {
      "epoch": 0.007408529911939519,
      "grad_norm": 1.6709822416305542,
      "learning_rate": 9.250636032241695e-06,
      "loss": 1.2707,
      "step": 440
    },
    {
      "epoch": 0.007576905591756326,
      "grad_norm": 2.335101366043091,
      "learning_rate": 6.45288957590781e-06,
      "loss": 1.346,
      "step": 450
    },
    {
      "epoch": 0.007576905591756326,
      "eval_loss": 1.1538912057876587,
      "eval_runtime": 1694.9946,
      "eval_samples_per_second": 14.753,
      "eval_steps_per_second": 3.689,
      "step": 450
    },
    {
      "epoch": 0.007745281271573134,
      "grad_norm": 1.5919936895370483,
      "learning_rate": 4.144998534599878e-06,
      "loss": 1.0085,
      "step": 460
    },
    {
      "epoch": 0.00791365695138994,
      "grad_norm": 1.8804110288619995,
      "learning_rate": 2.3382067214827915e-06,
      "loss": 1.0371,
      "step": 470
    },
    {
      "epoch": 0.008082032631206748,
      "grad_norm": 1.4158278703689575,
      "learning_rate": 1.0413166446519713e-06,
      "loss": 1.1094,
      "step": 480
    },
    {
      "epoch": 0.008250408311023557,
      "grad_norm": 1.5951461791992188,
      "learning_rate": 2.6064662219881083e-07,
      "loss": 1.2787,
      "step": 490
    },
    {
      "epoch": 0.008418783990840364,
      "grad_norm": 2.344301223754883,
      "learning_rate": 0.0,
      "loss": 1.2756,
      "step": 500
    },
    {
      "epoch": 0.008418783990840364,
      "eval_loss": 1.1528342962265015,
      "eval_runtime": 1688.0738,
      "eval_samples_per_second": 14.814,
      "eval_steps_per_second": 3.704,
      "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": 1.021628442036142e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}