{
  "best_metric": 0.8026256561279297,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.09679370840895342,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00024198427102238354,
      "eval_loss": 1.3080251216888428,
      "eval_runtime": 53.1456,
      "eval_samples_per_second": 32.74,
      "eval_steps_per_second": 8.185,
      "step": 1
    },
    {
      "epoch": 0.0024198427102238356,
      "grad_norm": 1.103469967842102,
      "learning_rate": 4.2600000000000005e-05,
      "loss": 0.9286,
      "step": 10
    },
    {
      "epoch": 0.004839685420447671,
      "grad_norm": 1.7151211500167847,
      "learning_rate": 8.520000000000001e-05,
      "loss": 0.9736,
      "step": 20
    },
    {
      "epoch": 0.007259528130671506,
      "grad_norm": 1.8954715728759766,
      "learning_rate": 0.0001278,
      "loss": 1.108,
      "step": 30
    },
    {
      "epoch": 0.009679370840895343,
      "grad_norm": 2.3523519039154053,
      "learning_rate": 0.00017040000000000002,
      "loss": 1.1477,
      "step": 40
    },
    {
      "epoch": 0.012099213551119177,
      "grad_norm": 2.1743710041046143,
      "learning_rate": 0.000213,
      "loss": 1.0015,
      "step": 50
    },
    {
      "epoch": 0.012099213551119177,
      "eval_loss": 1.0154005289077759,
      "eval_runtime": 52.97,
      "eval_samples_per_second": 32.849,
      "eval_steps_per_second": 8.212,
      "step": 50
    },
    {
      "epoch": 0.014519056261343012,
      "grad_norm": 1.202251672744751,
      "learning_rate": 0.00021274057135267128,
      "loss": 0.8938,
      "step": 60
    },
    {
      "epoch": 0.01693889897156685,
      "grad_norm": 1.0863494873046875,
      "learning_rate": 0.00021196354932097723,
      "loss": 0.9626,
      "step": 70
    },
    {
      "epoch": 0.019358741681790685,
      "grad_norm": 1.537191390991211,
      "learning_rate": 0.0002106727194781503,
      "loss": 1.0011,
      "step": 80
    },
    {
      "epoch": 0.021778584392014518,
      "grad_norm": 2.1484382152557373,
      "learning_rate": 0.00020887437061743096,
      "loss": 1.1008,
      "step": 90
    },
    {
      "epoch": 0.024198427102238355,
      "grad_norm": 2.325395107269287,
      "learning_rate": 0.00020657726411369925,
      "loss": 0.9323,
      "step": 100
    },
    {
      "epoch": 0.024198427102238355,
      "eval_loss": 1.0085864067077637,
      "eval_runtime": 53.2168,
      "eval_samples_per_second": 32.696,
      "eval_steps_per_second": 8.174,
      "step": 100
    },
    {
      "epoch": 0.02661826981246219,
      "grad_norm": 0.9922317266464233,
      "learning_rate": 0.000203792591238937,
      "loss": 0.8588,
      "step": 110
    },
    {
      "epoch": 0.029038112522686024,
      "grad_norm": 1.1746575832366943,
      "learning_rate": 0.0002005339186394757,
      "loss": 0.8886,
      "step": 120
    },
    {
      "epoch": 0.03145795523290986,
      "grad_norm": 1.4047287702560425,
      "learning_rate": 0.00019681712224065936,
      "loss": 0.9517,
      "step": 130
    },
    {
      "epoch": 0.0338777979431337,
      "grad_norm": 2.049302816390991,
      "learning_rate": 0.0001926603099009319,
      "loss": 1.0665,
      "step": 140
    },
    {
      "epoch": 0.036297640653357534,
      "grad_norm": 1.6594562530517578,
      "learning_rate": 0.00018808373319217114,
      "loss": 0.8871,
      "step": 150
    },
    {
      "epoch": 0.036297640653357534,
      "eval_loss": 0.9642200469970703,
      "eval_runtime": 53.2251,
      "eval_samples_per_second": 32.691,
      "eval_steps_per_second": 8.173,
      "step": 150
    },
    {
      "epoch": 0.03871748336358137,
      "grad_norm": 0.8076631426811218,
      "learning_rate": 0.00018310968873606635,
      "loss": 0.7604,
      "step": 160
    },
    {
      "epoch": 0.0411373260738052,
      "grad_norm": 1.2448451519012451,
      "learning_rate": 0.0001777624095772184,
      "loss": 0.8971,
      "step": 170
    },
    {
      "epoch": 0.043557168784029036,
      "grad_norm": 1.4778797626495361,
      "learning_rate": 0.0001720679471221826,
      "loss": 0.9395,
      "step": 180
    },
    {
      "epoch": 0.04597701149425287,
      "grad_norm": 2.3277740478515625,
      "learning_rate": 0.00016605404421963453,
      "loss": 1.0046,
      "step": 190
    },
    {
      "epoch": 0.04839685420447671,
      "grad_norm": 2.7840893268585205,
      "learning_rate": 0.00015975,
      "loss": 0.9651,
      "step": 200
    },
    {
      "epoch": 0.04839685420447671,
      "eval_loss": 0.9314111471176147,
      "eval_runtime": 53.3426,
      "eval_samples_per_second": 32.619,
      "eval_steps_per_second": 8.155,
      "step": 200
    },
    {
      "epoch": 0.050816696914700546,
      "grad_norm": 0.8467873930931091,
      "learning_rate": 0.00015318652713303674,
      "loss": 0.7771,
      "step": 210
    },
    {
      "epoch": 0.05323653962492438,
      "grad_norm": 1.810876488685608,
      "learning_rate": 0.00014639560219879464,
      "loss": 0.8956,
      "step": 220
    },
    {
      "epoch": 0.05565638233514821,
      "grad_norm": 1.5156196355819702,
      "learning_rate": 0.0001394103099009319,
      "loss": 0.953,
      "step": 230
    },
    {
      "epoch": 0.05807622504537205,
      "grad_norm": 1.6678131818771362,
      "learning_rate": 0.0001322646818813646,
      "loss": 0.971,
      "step": 240
    },
    {
      "epoch": 0.060496067755595885,
      "grad_norm": 2.130657196044922,
      "learning_rate": 0.0001249935309215281,
      "loss": 0.8652,
      "step": 250
    },
    {
      "epoch": 0.060496067755595885,
      "eval_loss": 0.8826441168785095,
      "eval_runtime": 53.194,
      "eval_samples_per_second": 32.71,
      "eval_steps_per_second": 8.178,
      "step": 250
    },
    {
      "epoch": 0.06291591046581972,
      "grad_norm": 0.86822110414505,
      "learning_rate": 0.0001176322813380051,
      "loss": 0.7765,
      "step": 260
    },
    {
      "epoch": 0.06533575317604355,
      "grad_norm": 1.0380805730819702,
      "learning_rate": 0.00011021679639881638,
      "loss": 0.8417,
      "step": 270
    },
    {
      "epoch": 0.0677555958862674,
      "grad_norm": 1.1815681457519531,
      "learning_rate": 0.00010278320360118368,
      "loss": 0.8916,
      "step": 280
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 2.9040372371673584,
      "learning_rate": 9.536771866199493e-05,
      "loss": 0.8656,
      "step": 290
    },
    {
      "epoch": 0.07259528130671507,
      "grad_norm": 2.076068878173828,
      "learning_rate": 8.800646907847192e-05,
      "loss": 0.8418,
      "step": 300
    },
    {
      "epoch": 0.07259528130671507,
      "eval_loss": 0.8545441031455994,
      "eval_runtime": 53.1112,
      "eval_samples_per_second": 32.761,
      "eval_steps_per_second": 8.19,
      "step": 300
    },
    {
      "epoch": 0.0750151240169389,
      "grad_norm": 0.856940507888794,
      "learning_rate": 8.07353181186354e-05,
      "loss": 0.7956,
      "step": 310
    },
    {
      "epoch": 0.07743496672716274,
      "grad_norm": 0.9584810137748718,
      "learning_rate": 7.35896900990681e-05,
      "loss": 0.7721,
      "step": 320
    },
    {
      "epoch": 0.07985480943738657,
      "grad_norm": 1.5156158208847046,
      "learning_rate": 6.660439780120536e-05,
      "loss": 0.9232,
      "step": 330
    },
    {
      "epoch": 0.0822746521476104,
      "grad_norm": 2.322288990020752,
      "learning_rate": 5.981347286696324e-05,
      "loss": 0.8629,
      "step": 340
    },
    {
      "epoch": 0.08469449485783424,
      "grad_norm": 1.789493441581726,
      "learning_rate": 5.325000000000002e-05,
      "loss": 0.8331,
      "step": 350
    },
    {
      "epoch": 0.08469449485783424,
      "eval_loss": 0.8212170600891113,
      "eval_runtime": 53.0695,
      "eval_samples_per_second": 32.787,
      "eval_steps_per_second": 8.197,
      "step": 350
    },
    {
      "epoch": 0.08711433756805807,
      "grad_norm": 0.8615260720252991,
      "learning_rate": 4.6945955780365475e-05,
      "loss": 0.7184,
      "step": 360
    },
    {
      "epoch": 0.08953418027828192,
      "grad_norm": 1.1007622480392456,
      "learning_rate": 4.0932052877817393e-05,
      "loss": 0.8244,
      "step": 370
    },
    {
      "epoch": 0.09195402298850575,
      "grad_norm": 1.265352725982666,
      "learning_rate": 3.523759042278163e-05,
      "loss": 0.8621,
      "step": 380
    },
    {
      "epoch": 0.09437386569872959,
      "grad_norm": 1.663914680480957,
      "learning_rate": 2.989031126393367e-05,
      "loss": 0.8621,
      "step": 390
    },
    {
      "epoch": 0.09679370840895342,
      "grad_norm": 1.8117319345474243,
      "learning_rate": 2.4916266807828855e-05,
      "loss": 0.7855,
      "step": 400
    },
    {
      "epoch": 0.09679370840895342,
      "eval_loss": 0.8026256561279297,
      "eval_runtime": 53.2521,
      "eval_samples_per_second": 32.675,
      "eval_steps_per_second": 8.169,
      "step": 400
    }
  ],
  "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": 1.88932260102144e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}