last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.3050570962479608,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.052202283849918436,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0996,
      "step": 1
    },
    {
      "epoch": 0.052202283849918436,
      "eval_loss": NaN,
      "eval_runtime": 0.8713,
      "eval_samples_per_second": 57.383,
      "eval_steps_per_second": 14.92,
      "step": 1
    },
    {
      "epoch": 0.10440456769983687,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.1566068515497553,
      "grad_norm": NaN,
      "learning_rate": 9.992920667580176e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.20880913539967375,
      "grad_norm": NaN,
      "learning_rate": 9.971704944519594e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.26101141924959215,
      "grad_norm": NaN,
      "learning_rate": 9.936419583332062e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.3132137030995106,
      "grad_norm": NaN,
      "learning_rate": 9.887175604818206e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.36541598694942906,
      "grad_norm": NaN,
      "learning_rate": 9.82412794875295e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.4176182707993475,
      "grad_norm": NaN,
      "learning_rate": 9.747474986387654e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.4698205546492659,
      "grad_norm": NaN,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.5220228384991843,
      "grad_norm": NaN,
      "learning_rate": 9.554359905560886e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.5742251223491027,
      "grad_norm": NaN,
      "learning_rate": 9.438505398589392e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.6264274061990212,
      "grad_norm": NaN,
      "learning_rate": 9.310258896527278e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.6786296900489397,
      "grad_norm": NaN,
      "learning_rate": 9.17002391031667e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.7308319738988581,
      "grad_norm": NaN,
      "learning_rate": 9.018241671106134e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.7830342577487766,
      "grad_norm": NaN,
      "learning_rate": 8.855389741974244e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.835236541598695,
      "grad_norm": NaN,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.8874388254486134,
      "grad_norm": NaN,
      "learning_rate": 8.498559600784018e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.9396411092985318,
      "grad_norm": NaN,
      "learning_rate": 8.305704108364301e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.9918433931484503,
      "grad_norm": NaN,
      "learning_rate": 8.104020832809127e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.0440456769983686,
      "grad_norm": NaN,
      "learning_rate": 7.894144344319014e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.0962479608482871,
      "grad_norm": NaN,
      "learning_rate": 7.67673499197358e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.1484502446982057,
      "grad_norm": NaN,
      "learning_rate": 7.452476826029011e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.200652528548124,
      "grad_norm": NaN,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.2528548123980423,
      "grad_norm": NaN,
      "learning_rate": 6.986255778798253e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.3050570962479608,
      "grad_norm": NaN,
      "learning_rate": 6.745759801411822e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.3050570962479608,
      "eval_loss": NaN,
      "eval_runtime": 0.8705,
      "eval_samples_per_second": 57.438,
      "eval_steps_per_second": 14.934,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 58,
  "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": 6.401917324361728e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}