last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.21231422505307856,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008492569002123142,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.008492569002123142,
      "eval_loss": NaN,
      "eval_runtime": 1.8649,
      "eval_samples_per_second": 26.811,
      "eval_steps_per_second": 6.971,
      "step": 1
    },
    {
      "epoch": 0.016985138004246284,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.03397027600849257,
      "grad_norm": NaN,
      "learning_rate": 9.997376600647783e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.04246284501061571,
      "grad_norm": NaN,
      "learning_rate": 9.989509461357426e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.050955414012738856,
      "grad_norm": NaN,
      "learning_rate": 9.976407754861426e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.059447983014861996,
      "grad_norm": NaN,
      "learning_rate": 9.958086757163489e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.06794055201698514,
      "grad_norm": NaN,
      "learning_rate": 9.934567829727386e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.07643312101910828,
      "grad_norm": NaN,
      "learning_rate": 9.905878394570453e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.08492569002123142,
      "grad_norm": NaN,
      "learning_rate": 9.872051902290737e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.09341825902335456,
      "grad_norm": NaN,
      "learning_rate": 9.833127793065098e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.10191082802547771,
      "grad_norm": NaN,
      "learning_rate": 9.789151450663723e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.11040339702760085,
      "grad_norm": NaN,
      "learning_rate": 9.740174149534693e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.11889596602972399,
      "grad_norm": NaN,
      "learning_rate": 9.686252995020249e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.12738853503184713,
      "grad_norm": NaN,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.13588110403397027,
      "grad_norm": NaN,
      "learning_rate": 9.563836295460398e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.14437367303609341,
      "grad_norm": NaN,
      "learning_rate": 9.495483482810688e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.15286624203821655,
      "grad_norm": NaN,
      "learning_rate": 9.422472115147382e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.1613588110403397,
      "grad_norm": NaN,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.16985138004246284,
      "grad_norm": NaN,
      "learning_rate": 9.2628195591462e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.17834394904458598,
      "grad_norm": NaN,
      "learning_rate": 9.176364518546989e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.18683651804670912,
      "grad_norm": NaN,
      "learning_rate": 9.08562300137157e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.19532908704883228,
      "grad_norm": NaN,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.20382165605095542,
      "grad_norm": NaN,
      "learning_rate": 8.891708613973126e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.21231422505307856,
      "grad_norm": NaN,
      "learning_rate": 8.788761839251559e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.21231422505307856,
      "eval_loss": NaN,
      "eval_runtime": 1.8608,
      "eval_samples_per_second": 26.87,
      "eval_steps_per_second": 6.986,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.114626154561536e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}