last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.5979073243647235,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02391629297458894,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.1793,
      "step": 1
    },
    {
      "epoch": 0.02391629297458894,
      "eval_loss": NaN,
      "eval_runtime": 2.4079,
      "eval_samples_per_second": 20.765,
      "eval_steps_per_second": 5.399,
      "step": 1
    },
    {
      "epoch": 0.04783258594917788,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.07174887892376682,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.09566517189835576,
      "grad_norm": NaN,
      "learning_rate": 9.99571699711836e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.11958146487294469,
      "grad_norm": NaN,
      "learning_rate": 9.982876141412856e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.14349775784753363,
      "grad_norm": NaN,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.16741405082212257,
      "grad_norm": NaN,
      "learning_rate": 9.931634888554937e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.19133034379671152,
      "grad_norm": NaN,
      "learning_rate": 9.893332032039701e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.21524663677130046,
      "grad_norm": NaN,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.23916292974588937,
      "grad_norm": NaN,
      "learning_rate": 9.791726278367022e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.26307922272047835,
      "grad_norm": NaN,
      "learning_rate": 9.728616793536588e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.28699551569506726,
      "grad_norm": NaN,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.3109118086696562,
      "grad_norm": NaN,
      "learning_rate": 9.578385041664925e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.33482810164424515,
      "grad_norm": NaN,
      "learning_rate": 9.491548749301997e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.35874439461883406,
      "grad_norm": NaN,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.38266068759342303,
      "grad_norm": NaN,
      "learning_rate": 9.295261506157986e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.40657698056801195,
      "grad_norm": NaN,
      "learning_rate": 9.186184199300464e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.4304932735426009,
      "grad_norm": NaN,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.45440956651718983,
      "grad_norm": NaN,
      "learning_rate": 8.947199994035401e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.47832585949177875,
      "grad_norm": NaN,
      "learning_rate": 8.817748015645558e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.5022421524663677,
      "grad_norm": NaN,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.5261584454409567,
      "grad_norm": NaN,
      "learning_rate": 8.540155934270471e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.5500747384155455,
      "grad_norm": NaN,
      "learning_rate": 8.392544243589427e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.5739910313901345,
      "grad_norm": NaN,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.5979073243647235,
      "grad_norm": NaN,
      "learning_rate": 8.081093963579707e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.5979073243647235,
      "eval_loss": NaN,
      "eval_runtime": 2.2658,
      "eval_samples_per_second": 22.067,
      "eval_steps_per_second": 5.737,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.229920304973742e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}