last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.721518987341772,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06751054852320675,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.06751054852320675,
      "eval_loss": NaN,
      "eval_runtime": 2.741,
      "eval_samples_per_second": 36.483,
      "eval_steps_per_second": 4.743,
      "step": 1
    },
    {
      "epoch": 0.1350210970464135,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": NaN,
      "learning_rate": 9.986661418317759e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.270042194092827,
      "grad_norm": NaN,
      "learning_rate": 9.946716840375551e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.33755274261603374,
      "grad_norm": NaN,
      "learning_rate": 9.880379387779637e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": NaN,
      "learning_rate": 9.78800299954203e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.47257383966244726,
      "grad_norm": NaN,
      "learning_rate": 9.67008054366274e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.540084388185654,
      "grad_norm": NaN,
      "learning_rate": 9.527241187465734e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": NaN,
      "learning_rate": 9.360247040719039e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.6751054852320675,
      "grad_norm": NaN,
      "learning_rate": 9.16998908944939e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.7426160337552743,
      "grad_norm": NaN,
      "learning_rate": 8.957482442146272e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": NaN,
      "learning_rate": 8.72386091371891e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.8776371308016878,
      "grad_norm": NaN,
      "learning_rate": 8.47037097610317e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.9451476793248945,
      "grad_norm": NaN,
      "learning_rate": 8.198365107794457e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.0464135021097047,
      "grad_norm": NaN,
      "learning_rate": 7.909294577789766e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.1139240506329113,
      "grad_norm": NaN,
      "learning_rate": 7.604701702439651e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.1814345991561181,
      "grad_norm": NaN,
      "learning_rate": 7.286211616523193e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.248945147679325,
      "grad_norm": NaN,
      "learning_rate": 6.95552360245078e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.3164556962025316,
      "grad_norm": NaN,
      "learning_rate": 6.614402023857232e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.3839662447257384,
      "grad_norm": NaN,
      "learning_rate": 6.264666911958404e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.4514767932489452,
      "grad_norm": NaN,
      "learning_rate": 5.908184254897182e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": NaN,
      "learning_rate": 5.546856041889373e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.5864978902953588,
      "grad_norm": NaN,
      "learning_rate": 5.182610115288295e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.6540084388185654,
      "grad_norm": NaN,
      "learning_rate": 4.817389884711705e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.721518987341772,
      "grad_norm": NaN,
      "learning_rate": 4.4531439581106295e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.721518987341772,
      "eval_loss": NaN,
      "eval_runtime": 2.7396,
      "eval_samples_per_second": 36.501,
      "eval_steps_per_second": 4.745,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 45,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 2.829010669142016e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}