{
  "best_metric": 2.2128450870513916,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.07216308858019123,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036081544290095615,
      "eval_loss": 2.921983242034912,
      "eval_runtime": 73.4498,
      "eval_samples_per_second": 15.888,
      "eval_steps_per_second": 3.976,
      "step": 1
    },
    {
      "epoch": 0.0036081544290095615,
      "grad_norm": 1.535165548324585,
      "learning_rate": 4.36e-05,
      "loss": 2.4652,
      "step": 10
    },
    {
      "epoch": 0.007216308858019123,
      "grad_norm": 1.88742196559906,
      "learning_rate": 8.72e-05,
      "loss": 2.3561,
      "step": 20
    },
    {
      "epoch": 0.010824463287028685,
      "grad_norm": 1.9067068099975586,
      "learning_rate": 0.0001308,
      "loss": 2.2395,
      "step": 30
    },
    {
      "epoch": 0.014432617716038246,
      "grad_norm": 2.238699436187744,
      "learning_rate": 0.0001744,
      "loss": 2.1678,
      "step": 40
    },
    {
      "epoch": 0.018040772145047807,
      "grad_norm": 4.385190963745117,
      "learning_rate": 0.000218,
      "loss": 2.1124,
      "step": 50
    },
    {
      "epoch": 0.018040772145047807,
      "eval_loss": 2.351407289505005,
      "eval_runtime": 73.4767,
      "eval_samples_per_second": 15.883,
      "eval_steps_per_second": 3.974,
      "step": 50
    },
    {
      "epoch": 0.02164892657405737,
      "grad_norm": 1.5297818183898926,
      "learning_rate": 0.00021773448147832086,
      "loss": 2.0854,
      "step": 60
    },
    {
      "epoch": 0.025257081003066933,
      "grad_norm": 1.3838398456573486,
      "learning_rate": 0.0002169392194928312,
      "loss": 2.0998,
      "step": 70
    },
    {
      "epoch": 0.028865235432076492,
      "grad_norm": 2.074045181274414,
      "learning_rate": 0.00021561808847998484,
      "loss": 2.2113,
      "step": 80
    },
    {
      "epoch": 0.032473389861086055,
      "grad_norm": 2.1741549968719482,
      "learning_rate": 0.00021377752485727676,
      "loss": 2.1485,
      "step": 90
    },
    {
      "epoch": 0.036081544290095614,
      "grad_norm": 6.557363986968994,
      "learning_rate": 0.00021142649566566402,
      "loss": 2.1276,
      "step": 100
    },
    {
      "epoch": 0.036081544290095614,
      "eval_loss": 2.3574182987213135,
      "eval_runtime": 73.3643,
      "eval_samples_per_second": 15.907,
      "eval_steps_per_second": 3.98,
      "step": 100
    },
    {
      "epoch": 0.03968969871910518,
      "grad_norm": 1.5597459077835083,
      "learning_rate": 0.0002085764548830435,
      "loss": 2.2556,
      "step": 110
    },
    {
      "epoch": 0.04329785314811474,
      "grad_norm": 1.775914192199707,
      "learning_rate": 0.00020524128762162305,
      "loss": 2.3104,
      "step": 120
    },
    {
      "epoch": 0.0469060075771243,
      "grad_norm": 1.6727547645568848,
      "learning_rate": 0.00020143724248105043,
      "loss": 2.1549,
      "step": 130
    },
    {
      "epoch": 0.050514162006133866,
      "grad_norm": 2.4896557331085205,
      "learning_rate": 0.0001971828523868693,
      "loss": 2.1205,
      "step": 140
    },
    {
      "epoch": 0.054122316435143425,
      "grad_norm": 4.250438213348389,
      "learning_rate": 0.0001924988442999686,
      "loss": 2.0478,
      "step": 150
    },
    {
      "epoch": 0.054122316435143425,
      "eval_loss": 2.2884583473205566,
      "eval_runtime": 73.1329,
      "eval_samples_per_second": 15.957,
      "eval_steps_per_second": 3.993,
      "step": 150
    },
    {
      "epoch": 0.057730470864152984,
      "grad_norm": 1.366658329963684,
      "learning_rate": 0.00018740803823691298,
      "loss": 2.172,
      "step": 160
    },
    {
      "epoch": 0.06133862529316255,
      "grad_norm": 1.5560624599456787,
      "learning_rate": 0.00018193523609311556,
      "loss": 2.3027,
      "step": 170
    },
    {
      "epoch": 0.06494677972217211,
      "grad_norm": 1.9186638593673706,
      "learning_rate": 0.00017610710081049675,
      "loss": 2.1255,
      "step": 180
    },
    {
      "epoch": 0.06855493415118168,
      "grad_norm": 2.413241386413574,
      "learning_rate": 0.00016995202647831142,
      "loss": 2.1701,
      "step": 190
    },
    {
      "epoch": 0.07216308858019123,
      "grad_norm": 4.694942474365234,
      "learning_rate": 0.00016350000000000002,
      "loss": 2.0427,
      "step": 200
    },
    {
      "epoch": 0.07216308858019123,
      "eval_loss": 2.2128450870513916,
      "eval_runtime": 73.3767,
      "eval_samples_per_second": 15.904,
      "eval_steps_per_second": 3.979,
      "step": 200
    }
  ],
  "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": 3.893850675137741e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}