last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.13227513227513227,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008818342151675485,
      "eval_loss": NaN,
      "eval_runtime": 25.574,
      "eval_samples_per_second": 18.691,
      "eval_steps_per_second": 4.692,
      "step": 1
    },
    {
      "epoch": 0.008818342151675485,
      "grad_norm": NaN,
      "learning_rate": 5.05e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.01763668430335097,
      "grad_norm": NaN,
      "learning_rate": 1.01e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.026455026455026454,
      "grad_norm": NaN,
      "learning_rate": 9.323076923076924e-06,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.03527336860670194,
      "grad_norm": NaN,
      "learning_rate": 8.546153846153847e-06,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.04409171075837742,
      "grad_norm": NaN,
      "learning_rate": 7.76923076923077e-06,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.04409171075837742,
      "eval_loss": NaN,
      "eval_runtime": 24.4933,
      "eval_samples_per_second": 19.516,
      "eval_steps_per_second": 4.899,
      "step": 50
    },
    {
      "epoch": 0.05291005291005291,
      "grad_norm": NaN,
      "learning_rate": 6.992307692307692e-06,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.06172839506172839,
      "grad_norm": NaN,
      "learning_rate": 6.215384615384615e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.07054673721340388,
      "grad_norm": NaN,
      "learning_rate": 5.438461538461538e-06,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": NaN,
      "learning_rate": 4.661538461538462e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.08818342151675485,
      "grad_norm": NaN,
      "learning_rate": 3.884615384615385e-06,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.08818342151675485,
      "eval_loss": NaN,
      "eval_runtime": 24.5008,
      "eval_samples_per_second": 19.51,
      "eval_steps_per_second": 4.898,
      "step": 100
    },
    {
      "epoch": 0.09700176366843033,
      "grad_norm": NaN,
      "learning_rate": 3.1076923076923076e-06,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": NaN,
      "learning_rate": 2.330769230769231e-06,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.1146384479717813,
      "grad_norm": NaN,
      "learning_rate": 1.5538461538461538e-06,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": NaN,
      "learning_rate": 7.769230769230769e-07,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.13227513227513227,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.13227513227513227,
      "eval_loss": NaN,
      "eval_runtime": 24.4951,
      "eval_samples_per_second": 19.514,
      "eval_steps_per_second": 4.899,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "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": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.36624253370368e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}