{
  "best_metric": 1.1311696767807007,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.3487020534676482,
  "eval_steps": 50,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007748934521503294,
      "eval_loss": 2.042634963989258,
      "eval_runtime": 19.3191,
      "eval_samples_per_second": 28.159,
      "eval_steps_per_second": 7.04,
      "step": 1
    },
    {
      "epoch": 0.0077489345215032935,
      "grad_norm": 2.596163511276245,
      "learning_rate": 4.0600000000000004e-05,
      "loss": 1.637,
      "step": 10
    },
    {
      "epoch": 0.015497869043006587,
      "grad_norm": 1.8155604600906372,
      "learning_rate": 8.120000000000001e-05,
      "loss": 1.4282,
      "step": 20
    },
    {
      "epoch": 0.02324680356450988,
      "grad_norm": 2.010477066040039,
      "learning_rate": 0.00012179999999999999,
      "loss": 1.3096,
      "step": 30
    },
    {
      "epoch": 0.030995738086013174,
      "grad_norm": 1.7271562814712524,
      "learning_rate": 0.00016240000000000002,
      "loss": 1.2131,
      "step": 40
    },
    {
      "epoch": 0.03874467260751647,
      "grad_norm": 3.4388530254364014,
      "learning_rate": 0.000203,
      "loss": 1.2151,
      "step": 50
    },
    {
      "epoch": 0.03874467260751647,
      "eval_loss": 1.2415974140167236,
      "eval_runtime": 19.4264,
      "eval_samples_per_second": 28.003,
      "eval_steps_per_second": 7.001,
      "step": 50
    },
    {
      "epoch": 0.04649360712901976,
      "grad_norm": 1.669398307800293,
      "learning_rate": 0.00020275275110137215,
      "loss": 1.1596,
      "step": 60
    },
    {
      "epoch": 0.05424254165052305,
      "grad_norm": 1.3598785400390625,
      "learning_rate": 0.00020201220897726938,
      "loss": 1.2513,
      "step": 70
    },
    {
      "epoch": 0.06199147617202635,
      "grad_norm": 1.4303092956542969,
      "learning_rate": 0.00020078198147448128,
      "loss": 1.1887,
      "step": 80
    },
    {
      "epoch": 0.06974041069352964,
      "grad_norm": 1.7135754823684692,
      "learning_rate": 0.00019906806213773937,
      "loss": 1.1901,
      "step": 90
    },
    {
      "epoch": 0.07748934521503294,
      "grad_norm": 4.795324325561523,
      "learning_rate": 0.0001968788010097697,
      "loss": 1.1915,
      "step": 100
    },
    {
      "epoch": 0.07748934521503294,
      "eval_loss": 1.2326695919036865,
      "eval_runtime": 19.5546,
      "eval_samples_per_second": 27.82,
      "eval_steps_per_second": 6.955,
      "step": 100
    },
    {
      "epoch": 0.08523827973653622,
      "grad_norm": 1.4039335250854492,
      "learning_rate": 0.00019422486395072398,
      "loss": 1.1134,
      "step": 110
    },
    {
      "epoch": 0.09298721425803952,
      "grad_norm": 1.290767788887024,
      "learning_rate": 0.0001911191806751811,
      "loss": 1.1767,
      "step": 120
    },
    {
      "epoch": 0.10073614877954282,
      "grad_norm": 1.4741291999816895,
      "learning_rate": 0.00018757688175987723,
      "loss": 1.2077,
      "step": 130
    },
    {
      "epoch": 0.1084850833010461,
      "grad_norm": 1.580878496170044,
      "learning_rate": 0.00018361522492905716,
      "loss": 1.1455,
      "step": 140
    },
    {
      "epoch": 0.1162340178225494,
      "grad_norm": 6.502963066101074,
      "learning_rate": 0.00017925351097657625,
      "loss": 1.2151,
      "step": 150
    },
    {
      "epoch": 0.1162340178225494,
      "eval_loss": 1.1908780336380005,
      "eval_runtime": 19.4086,
      "eval_samples_per_second": 28.029,
      "eval_steps_per_second": 7.007,
      "step": 150
    },
    {
      "epoch": 0.1239829523440527,
      "grad_norm": 1.1870495080947876,
      "learning_rate": 0.00017451298973437308,
      "loss": 0.9819,
      "step": 160
    },
    {
      "epoch": 0.13173188686555598,
      "grad_norm": 1.2544339895248413,
      "learning_rate": 0.0001694167565454241,
      "loss": 1.149,
      "step": 170
    },
    {
      "epoch": 0.13948082138705928,
      "grad_norm": 1.5018516778945923,
      "learning_rate": 0.0001639896397455543,
      "loss": 1.1653,
      "step": 180
    },
    {
      "epoch": 0.14722975590856258,
      "grad_norm": 1.6409251689910889,
      "learning_rate": 0.0001582580797022808,
      "loss": 1.1748,
      "step": 190
    },
    {
      "epoch": 0.15497869043006587,
      "grad_norm": 3.206493377685547,
      "learning_rate": 0.00015225,
      "loss": 1.1795,
      "step": 200
    },
    {
      "epoch": 0.15497869043006587,
      "eval_loss": 1.1657546758651733,
      "eval_runtime": 19.4529,
      "eval_samples_per_second": 27.965,
      "eval_steps_per_second": 6.991,
      "step": 200
    },
    {
      "epoch": 0.16272762495156917,
      "grad_norm": 1.2450393438339233,
      "learning_rate": 0.00014599467139909136,
      "loss": 1.0438,
      "step": 210
    },
    {
      "epoch": 0.17047655947307244,
      "grad_norm": 1.2467765808105469,
      "learning_rate": 0.0001395225692317151,
      "loss": 1.109,
      "step": 220
    },
    {
      "epoch": 0.17822549399457574,
      "grad_norm": 1.5617730617523193,
      "learning_rate": 0.00013286522492905717,
      "loss": 1.1722,
      "step": 230
    },
    {
      "epoch": 0.18597442851607904,
      "grad_norm": 1.4881824254989624,
      "learning_rate": 0.00012605507240336626,
      "loss": 1.1899,
      "step": 240
    },
    {
      "epoch": 0.19372336303758234,
      "grad_norm": 3.424774169921875,
      "learning_rate": 0.00011912529003319345,
      "loss": 1.2232,
      "step": 250
    },
    {
      "epoch": 0.19372336303758234,
      "eval_loss": 1.154661774635315,
      "eval_runtime": 19.4078,
      "eval_samples_per_second": 28.03,
      "eval_steps_per_second": 7.007,
      "step": 250
    },
    {
      "epoch": 0.20147229755908563,
      "grad_norm": 1.3052321672439575,
      "learning_rate": 0.00011210963902166683,
      "loss": 1.1019,
      "step": 260
    },
    {
      "epoch": 0.20922123208058893,
      "grad_norm": 1.3270354270935059,
      "learning_rate": 0.00010504229891530386,
      "loss": 1.1695,
      "step": 270
    },
    {
      "epoch": 0.2169701666020922,
      "grad_norm": 1.625852346420288,
      "learning_rate": 9.795770108469618e-05,
      "loss": 1.1769,
      "step": 280
    },
    {
      "epoch": 0.2247191011235955,
      "grad_norm": 1.5025311708450317,
      "learning_rate": 9.08903609783332e-05,
      "loss": 1.1659,
      "step": 290
    },
    {
      "epoch": 0.2324680356450988,
      "grad_norm": 3.024522066116333,
      "learning_rate": 8.387470996680658e-05,
      "loss": 1.1329,
      "step": 300
    },
    {
      "epoch": 0.2324680356450988,
      "eval_loss": 1.1374027729034424,
      "eval_runtime": 19.4072,
      "eval_samples_per_second": 28.031,
      "eval_steps_per_second": 7.008,
      "step": 300
    },
    {
      "epoch": 0.2402169701666021,
      "grad_norm": 1.227674961090088,
      "learning_rate": 7.694492759663374e-05,
      "loss": 1.1127,
      "step": 310
    },
    {
      "epoch": 0.2479659046881054,
      "grad_norm": 1.371392011642456,
      "learning_rate": 7.013477507094284e-05,
      "loss": 1.2046,
      "step": 320
    },
    {
      "epoch": 0.2557148392096087,
      "grad_norm": 1.4349315166473389,
      "learning_rate": 6.347743076828492e-05,
      "loss": 1.1213,
      "step": 330
    },
    {
      "epoch": 0.26346377373111196,
      "grad_norm": 1.58314847946167,
      "learning_rate": 5.700532860090863e-05,
      "loss": 1.1533,
      "step": 340
    },
    {
      "epoch": 0.2712127082526153,
      "grad_norm": 3.6435108184814453,
      "learning_rate": 5.075000000000002e-05,
      "loss": 1.155,
      "step": 350
    },
    {
      "epoch": 0.2712127082526153,
      "eval_loss": 1.1427217721939087,
      "eval_runtime": 19.5093,
      "eval_samples_per_second": 27.884,
      "eval_steps_per_second": 6.971,
      "step": 350
    },
    {
      "epoch": 0.27896164277411856,
      "grad_norm": 1.3242435455322266,
      "learning_rate": 4.4741920297719214e-05,
      "loss": 1.0931,
      "step": 360
    },
    {
      "epoch": 0.2867105772956218,
      "grad_norm": 1.3505114316940308,
      "learning_rate": 3.901036025444568e-05,
      "loss": 1.1299,
      "step": 370
    },
    {
      "epoch": 0.29445951181712515,
      "grad_norm": 1.325255036354065,
      "learning_rate": 3.358324345457592e-05,
      "loss": 1.1477,
      "step": 380
    },
    {
      "epoch": 0.3022084463386284,
      "grad_norm": 1.5533366203308105,
      "learning_rate": 2.8487010265626928e-05,
      "loss": 1.148,
      "step": 390
    },
    {
      "epoch": 0.30995738086013175,
      "grad_norm": 2.8041539192199707,
      "learning_rate": 2.3746489023423744e-05,
      "loss": 1.1461,
      "step": 400
    },
    {
      "epoch": 0.30995738086013175,
      "eval_loss": 1.1326929330825806,
      "eval_runtime": 19.4266,
      "eval_samples_per_second": 28.003,
      "eval_steps_per_second": 7.001,
      "step": 400
    },
    {
      "epoch": 0.317706315381635,
      "grad_norm": 1.2059953212738037,
      "learning_rate": 1.9384775070942844e-05,
      "loss": 0.8901,
      "step": 410
    },
    {
      "epoch": 0.32545524990313834,
      "grad_norm": 1.4342598915100098,
      "learning_rate": 1.5423118240122765e-05,
      "loss": 1.1229,
      "step": 420
    },
    {
      "epoch": 0.3332041844246416,
      "grad_norm": 1.244903802871704,
      "learning_rate": 1.188081932481891e-05,
      "loss": 1.1037,
      "step": 430
    },
    {
      "epoch": 0.3409531189461449,
      "grad_norm": 1.8167920112609863,
      "learning_rate": 8.775136049276001e-06,
      "loss": 1.131,
      "step": 440
    },
    {
      "epoch": 0.3487020534676482,
      "grad_norm": 2.944375991821289,
      "learning_rate": 6.121198990230306e-06,
      "loss": 1.0648,
      "step": 450
    },
    {
      "epoch": 0.3487020534676482,
      "eval_loss": 1.1311696767807007,
      "eval_runtime": 19.3838,
      "eval_samples_per_second": 28.065,
      "eval_steps_per_second": 7.016,
      "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": 2.344858262647603e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}