{
  "best_metric": 1.1949564218521118,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.13966480446927373,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006983240223463687,
      "eval_loss": 1.370945930480957,
      "eval_runtime": 52.0353,
      "eval_samples_per_second": 11.588,
      "eval_steps_per_second": 2.902,
      "step": 1
    },
    {
      "epoch": 0.006983240223463687,
      "grad_norm": 0.7985172271728516,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 1.0747,
      "step": 10
    },
    {
      "epoch": 0.013966480446927373,
      "grad_norm": 0.5064533352851868,
      "learning_rate": 8.400000000000001e-05,
      "loss": 0.9049,
      "step": 20
    },
    {
      "epoch": 0.02094972067039106,
      "grad_norm": 0.6195475459098816,
      "learning_rate": 0.000126,
      "loss": 0.9139,
      "step": 30
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 0.5974525213241577,
      "learning_rate": 0.00016800000000000002,
      "loss": 0.8777,
      "step": 40
    },
    {
      "epoch": 0.034916201117318434,
      "grad_norm": 1.1508451700210571,
      "learning_rate": 0.00021,
      "loss": 2.2731,
      "step": 50
    },
    {
      "epoch": 0.034916201117318434,
      "eval_loss": 1.2975257635116577,
      "eval_runtime": 52.0378,
      "eval_samples_per_second": 11.588,
      "eval_steps_per_second": 2.902,
      "step": 50
    },
    {
      "epoch": 0.04189944134078212,
      "grad_norm": 0.47768744826316833,
      "learning_rate": 0.00020974422527728155,
      "loss": 0.9301,
      "step": 60
    },
    {
      "epoch": 0.04888268156424581,
      "grad_norm": 0.4488859176635742,
      "learning_rate": 0.0002089781472178649,
      "loss": 0.8632,
      "step": 70
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 0.4876834750175476,
      "learning_rate": 0.0002077054980770496,
      "loss": 0.9053,
      "step": 80
    },
    {
      "epoch": 0.06284916201117319,
      "grad_norm": 0.6040335893630981,
      "learning_rate": 0.00020593247807352348,
      "loss": 0.9912,
      "step": 90
    },
    {
      "epoch": 0.06983240223463687,
      "grad_norm": 1.2908031940460205,
      "learning_rate": 0.00020366772518252038,
      "loss": 2.3175,
      "step": 100
    },
    {
      "epoch": 0.06983240223463687,
      "eval_loss": 1.2717502117156982,
      "eval_runtime": 52.2379,
      "eval_samples_per_second": 11.543,
      "eval_steps_per_second": 2.891,
      "step": 100
    },
    {
      "epoch": 0.07681564245810056,
      "grad_norm": 0.556641697883606,
      "learning_rate": 0.0002009222730524731,
      "loss": 0.9617,
      "step": 110
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": 0.45357635617256165,
      "learning_rate": 0.00019770949725018733,
      "loss": 0.9447,
      "step": 120
    },
    {
      "epoch": 0.09078212290502793,
      "grad_norm": 0.530303418636322,
      "learning_rate": 0.00019404505009642473,
      "loss": 0.8661,
      "step": 130
    },
    {
      "epoch": 0.09776536312849161,
      "grad_norm": 0.544837474822998,
      "learning_rate": 0.0001899467844093695,
      "loss": 0.8477,
      "step": 140
    },
    {
      "epoch": 0.10474860335195531,
      "grad_norm": 1.3659236431121826,
      "learning_rate": 0.00018543466652749268,
      "loss": 2.1598,
      "step": 150
    },
    {
      "epoch": 0.10474860335195531,
      "eval_loss": 1.2168477773666382,
      "eval_runtime": 52.7182,
      "eval_samples_per_second": 11.438,
      "eval_steps_per_second": 2.864,
      "step": 150
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": 0.4937569499015808,
      "learning_rate": 0.00018053067903555837,
      "loss": 0.9268,
      "step": 160
    },
    {
      "epoch": 0.11871508379888268,
      "grad_norm": 0.45097047090530396,
      "learning_rate": 0.00017525871366768012,
      "loss": 0.8534,
      "step": 170
    },
    {
      "epoch": 0.12569832402234637,
      "grad_norm": 0.442699670791626,
      "learning_rate": 0.00016964445490919413,
      "loss": 0.8584,
      "step": 180
    },
    {
      "epoch": 0.13268156424581007,
      "grad_norm": 0.49953675270080566,
      "learning_rate": 0.00016371525486442843,
      "loss": 0.7786,
      "step": 190
    },
    {
      "epoch": 0.13966480446927373,
      "grad_norm": 1.2703161239624023,
      "learning_rate": 0.0001575,
      "loss": 1.9828,
      "step": 200
    },
    {
      "epoch": 0.13966480446927373,
      "eval_loss": 1.1949564218521118,
      "eval_runtime": 51.9478,
      "eval_samples_per_second": 11.608,
      "eval_steps_per_second": 2.907,
      "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": 5.652007524237312e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}