last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.6528925619834711,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06611570247933884,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.06611570247933884,
      "eval_loss": NaN,
      "eval_runtime": 2.7019,
      "eval_samples_per_second": 37.751,
      "eval_steps_per_second": 4.811,
      "step": 1
    },
    {
      "epoch": 0.1322314049586777,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.19834710743801653,
      "grad_norm": NaN,
      "learning_rate": 9.987260573051269e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.2644628099173554,
      "grad_norm": NaN,
      "learning_rate": 9.949107209404665e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.3305785123966942,
      "grad_norm": NaN,
      "learning_rate": 9.885734329855798e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.39669421487603307,
      "grad_norm": NaN,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.4628099173553719,
      "grad_norm": NaN,
      "learning_rate": 9.68474862499881e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.5289256198347108,
      "grad_norm": NaN,
      "learning_rate": 9.548159976772592e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.5950413223140496,
      "grad_norm": NaN,
      "learning_rate": 9.388394947836279e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.6611570247933884,
      "grad_norm": NaN,
      "learning_rate": 9.206267664155907e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": NaN,
      "learning_rate": 9.002706204621803e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.7933884297520661,
      "grad_norm": NaN,
      "learning_rate": 8.778747871771292e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.859504132231405,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.9256198347107438,
      "grad_norm": NaN,
      "learning_rate": 8.274303669726426e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.9917355371900827,
      "grad_norm": NaN,
      "learning_rate": 7.996388332556735e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.0578512396694215,
      "grad_norm": NaN,
      "learning_rate": 7.703204087277988e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.1239669421487604,
      "grad_norm": NaN,
      "learning_rate": 7.396244933600285e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.1900826446280992,
      "grad_norm": NaN,
      "learning_rate": 7.077075065009433e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.256198347107438,
      "grad_norm": NaN,
      "learning_rate": 6.747320897995493e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.322314049586777,
      "grad_norm": NaN,
      "learning_rate": 6.408662784207149e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.3884297520661157,
      "grad_norm": NaN,
      "learning_rate": 6.062826447764883e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": NaN,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.5206611570247934,
      "grad_norm": NaN,
      "learning_rate": 5.3566959159961615e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.5867768595041323,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.6528925619834711,
      "grad_norm": NaN,
      "learning_rate": 4.643304084003839e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.6528925619834711,
      "eval_loss": NaN,
      "eval_runtime": 2.7044,
      "eval_samples_per_second": 37.717,
      "eval_steps_per_second": 4.807,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 46,
  "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": 2.629578157719552e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}