{
  "best_metric": 0.2352096140384674,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.24524831391784183,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006131207847946045,
      "eval_loss": 1.695329189300537,
      "eval_runtime": 42.4889,
      "eval_samples_per_second": 16.169,
      "eval_steps_per_second": 4.048,
      "step": 1
    },
    {
      "epoch": 0.0061312078479460455,
      "grad_norm": 2.3003127574920654,
      "learning_rate": 4.0600000000000004e-05,
      "loss": 1.0413,
      "step": 10
    },
    {
      "epoch": 0.012262415695892091,
      "grad_norm": 2.6552650928497314,
      "learning_rate": 8.120000000000001e-05,
      "loss": 0.658,
      "step": 20
    },
    {
      "epoch": 0.018393623543838136,
      "grad_norm": 2.388611078262329,
      "learning_rate": 0.00012179999999999999,
      "loss": 0.5488,
      "step": 30
    },
    {
      "epoch": 0.024524831391784182,
      "grad_norm": 2.153262138366699,
      "learning_rate": 0.00016240000000000002,
      "loss": 0.4848,
      "step": 40
    },
    {
      "epoch": 0.030656039239730228,
      "grad_norm": 5.431114673614502,
      "learning_rate": 0.000203,
      "loss": 0.5842,
      "step": 50
    },
    {
      "epoch": 0.030656039239730228,
      "eval_loss": 0.7501240968704224,
      "eval_runtime": 42.4899,
      "eval_samples_per_second": 16.169,
      "eval_steps_per_second": 4.048,
      "step": 50
    },
    {
      "epoch": 0.03678724708767627,
      "grad_norm": 1.6866220235824585,
      "learning_rate": 0.00020275275110137215,
      "loss": 0.5527,
      "step": 60
    },
    {
      "epoch": 0.04291845493562232,
      "grad_norm": 1.1154528856277466,
      "learning_rate": 0.00020201220897726938,
      "loss": 0.4032,
      "step": 70
    },
    {
      "epoch": 0.049049662783568364,
      "grad_norm": 1.4410632848739624,
      "learning_rate": 0.00020078198147448128,
      "loss": 0.3966,
      "step": 80
    },
    {
      "epoch": 0.05518087063151441,
      "grad_norm": 3.099368095397949,
      "learning_rate": 0.00019906806213773937,
      "loss": 0.4807,
      "step": 90
    },
    {
      "epoch": 0.061312078479460456,
      "grad_norm": 3.0066134929656982,
      "learning_rate": 0.0001968788010097697,
      "loss": 0.579,
      "step": 100
    },
    {
      "epoch": 0.061312078479460456,
      "eval_loss": 0.7241560220718384,
      "eval_runtime": 42.4229,
      "eval_samples_per_second": 16.194,
      "eval_steps_per_second": 4.054,
      "step": 100
    },
    {
      "epoch": 0.0674432863274065,
      "grad_norm": 1.458212971687317,
      "learning_rate": 0.00019422486395072398,
      "loss": 0.4646,
      "step": 110
    },
    {
      "epoch": 0.07357449417535254,
      "grad_norm": 2.532667636871338,
      "learning_rate": 0.0001911191806751811,
      "loss": 0.3873,
      "step": 120
    },
    {
      "epoch": 0.07970570202329859,
      "grad_norm": 1.281633973121643,
      "learning_rate": 0.00018757688175987723,
      "loss": 0.3839,
      "step": 130
    },
    {
      "epoch": 0.08583690987124463,
      "grad_norm": 1.9844921827316284,
      "learning_rate": 0.00018361522492905716,
      "loss": 0.392,
      "step": 140
    },
    {
      "epoch": 0.09196811771919068,
      "grad_norm": 3.228635787963867,
      "learning_rate": 0.00017925351097657625,
      "loss": 0.5286,
      "step": 150
    },
    {
      "epoch": 0.09196811771919068,
      "eval_loss": 0.510759711265564,
      "eval_runtime": 42.5096,
      "eval_samples_per_second": 16.161,
      "eval_steps_per_second": 4.046,
      "step": 150
    },
    {
      "epoch": 0.09809932556713673,
      "grad_norm": 1.5365837812423706,
      "learning_rate": 0.00017451298973437308,
      "loss": 0.4629,
      "step": 160
    },
    {
      "epoch": 0.10423053341508277,
      "grad_norm": 1.242377758026123,
      "learning_rate": 0.0001694167565454241,
      "loss": 0.3206,
      "step": 170
    },
    {
      "epoch": 0.11036174126302882,
      "grad_norm": 1.5754390954971313,
      "learning_rate": 0.0001639896397455543,
      "loss": 0.3554,
      "step": 180
    },
    {
      "epoch": 0.11649294911097487,
      "grad_norm": 1.201021671295166,
      "learning_rate": 0.0001582580797022808,
      "loss": 0.3257,
      "step": 190
    },
    {
      "epoch": 0.12262415695892091,
      "grad_norm": 3.3874385356903076,
      "learning_rate": 0.00015225,
      "loss": 0.4783,
      "step": 200
    },
    {
      "epoch": 0.12262415695892091,
      "eval_loss": 0.4689219892024994,
      "eval_runtime": 42.4861,
      "eval_samples_per_second": 16.17,
      "eval_steps_per_second": 4.048,
      "step": 200
    },
    {
      "epoch": 0.12875536480686695,
      "grad_norm": 1.6585816144943237,
      "learning_rate": 0.00014599467139909136,
      "loss": 0.3804,
      "step": 210
    },
    {
      "epoch": 0.134886572654813,
      "grad_norm": 1.9046809673309326,
      "learning_rate": 0.0001395225692317151,
      "loss": 0.2832,
      "step": 220
    },
    {
      "epoch": 0.14101778050275904,
      "grad_norm": 1.5646591186523438,
      "learning_rate": 0.00013286522492905717,
      "loss": 0.2826,
      "step": 230
    },
    {
      "epoch": 0.14714898835070508,
      "grad_norm": 1.3657160997390747,
      "learning_rate": 0.00012605507240336626,
      "loss": 0.3027,
      "step": 240
    },
    {
      "epoch": 0.15328019619865113,
      "grad_norm": 2.369676351547241,
      "learning_rate": 0.00011912529003319345,
      "loss": 0.345,
      "step": 250
    },
    {
      "epoch": 0.15328019619865113,
      "eval_loss": 0.44708386063575745,
      "eval_runtime": 42.5334,
      "eval_samples_per_second": 16.152,
      "eval_steps_per_second": 4.044,
      "step": 250
    },
    {
      "epoch": 0.15941140404659718,
      "grad_norm": 0.9845743179321289,
      "learning_rate": 0.00011210963902166683,
      "loss": 0.3695,
      "step": 260
    },
    {
      "epoch": 0.16554261189454322,
      "grad_norm": 0.9960480332374573,
      "learning_rate": 0.00010504229891530386,
      "loss": 0.2659,
      "step": 270
    },
    {
      "epoch": 0.17167381974248927,
      "grad_norm": 1.5102771520614624,
      "learning_rate": 9.795770108469618e-05,
      "loss": 0.2588,
      "step": 280
    },
    {
      "epoch": 0.17780502759043532,
      "grad_norm": 1.1536074876785278,
      "learning_rate": 9.08903609783332e-05,
      "loss": 0.3202,
      "step": 290
    },
    {
      "epoch": 0.18393623543838136,
      "grad_norm": 2.6907193660736084,
      "learning_rate": 8.387470996680658e-05,
      "loss": 0.3257,
      "step": 300
    },
    {
      "epoch": 0.18393623543838136,
      "eval_loss": 0.3584211468696594,
      "eval_runtime": 42.5021,
      "eval_samples_per_second": 16.164,
      "eval_steps_per_second": 4.047,
      "step": 300
    },
    {
      "epoch": 0.1900674432863274,
      "grad_norm": 0.8187077045440674,
      "learning_rate": 7.694492759663374e-05,
      "loss": 0.3159,
      "step": 310
    },
    {
      "epoch": 0.19619865113427346,
      "grad_norm": 1.3781569004058838,
      "learning_rate": 7.013477507094284e-05,
      "loss": 0.2493,
      "step": 320
    },
    {
      "epoch": 0.2023298589822195,
      "grad_norm": 1.7643306255340576,
      "learning_rate": 6.347743076828492e-05,
      "loss": 0.3,
      "step": 330
    },
    {
      "epoch": 0.20846106683016555,
      "grad_norm": 1.2391196489334106,
      "learning_rate": 5.700532860090863e-05,
      "loss": 0.2239,
      "step": 340
    },
    {
      "epoch": 0.2145922746781116,
      "grad_norm": 2.802654266357422,
      "learning_rate": 5.075000000000002e-05,
      "loss": 0.3528,
      "step": 350
    },
    {
      "epoch": 0.2145922746781116,
      "eval_loss": 0.2691604793071747,
      "eval_runtime": 42.5737,
      "eval_samples_per_second": 16.137,
      "eval_steps_per_second": 4.04,
      "step": 350
    },
    {
      "epoch": 0.22072348252605764,
      "grad_norm": 1.1769925355911255,
      "learning_rate": 4.4741920297719214e-05,
      "loss": 0.2879,
      "step": 360
    },
    {
      "epoch": 0.2268546903740037,
      "grad_norm": 0.720497727394104,
      "learning_rate": 3.901036025444568e-05,
      "loss": 0.2497,
      "step": 370
    },
    {
      "epoch": 0.23298589822194973,
      "grad_norm": 1.1331359148025513,
      "learning_rate": 3.358324345457592e-05,
      "loss": 0.2348,
      "step": 380
    },
    {
      "epoch": 0.23911710606989578,
      "grad_norm": 0.9605158567428589,
      "learning_rate": 2.8487010265626928e-05,
      "loss": 0.1956,
      "step": 390
    },
    {
      "epoch": 0.24524831391784183,
      "grad_norm": 2.6143555641174316,
      "learning_rate": 2.3746489023423744e-05,
      "loss": 0.2959,
      "step": 400
    },
    {
      "epoch": 0.24524831391784183,
      "eval_loss": 0.2352096140384674,
      "eval_runtime": 42.5049,
      "eval_samples_per_second": 16.163,
      "eval_steps_per_second": 4.047,
      "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": 7.551996103596442e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}