last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.5287508261731659,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021150033046926635,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.021150033046926635,
      "eval_loss": NaN,
      "eval_runtime": 0.761,
      "eval_samples_per_second": 65.703,
      "eval_steps_per_second": 17.083,
      "step": 1
    },
    {
      "epoch": 0.04230006609385327,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.06345009914077991,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.08460013218770654,
      "grad_norm": NaN,
      "learning_rate": 9.997376600647783e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.10575016523463318,
      "grad_norm": NaN,
      "learning_rate": 9.989509461357426e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.12690019828155982,
      "grad_norm": NaN,
      "learning_rate": 9.976407754861426e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.14805023132848646,
      "grad_norm": NaN,
      "learning_rate": 9.958086757163489e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.16920026437541308,
      "grad_norm": NaN,
      "learning_rate": 9.934567829727386e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.19035029742233972,
      "grad_norm": NaN,
      "learning_rate": 9.905878394570453e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.21150033046926636,
      "grad_norm": NaN,
      "learning_rate": 9.872051902290737e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.232650363516193,
      "grad_norm": NaN,
      "learning_rate": 9.833127793065098e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.25380039656311965,
      "grad_norm": NaN,
      "learning_rate": 9.789151450663723e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.2749504296100463,
      "grad_norm": NaN,
      "learning_rate": 9.740174149534693e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.29610046265697293,
      "grad_norm": NaN,
      "learning_rate": 9.686252995020249e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.3172504957038995,
      "grad_norm": NaN,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.33840052875082616,
      "grad_norm": NaN,
      "learning_rate": 9.563836295460398e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.3595505617977528,
      "grad_norm": NaN,
      "learning_rate": 9.495483482810688e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.38070059484467944,
      "grad_norm": NaN,
      "learning_rate": 9.422472115147382e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.4018506278916061,
      "grad_norm": NaN,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.4230006609385327,
      "grad_norm": NaN,
      "learning_rate": 9.2628195591462e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.44415069398545937,
      "grad_norm": NaN,
      "learning_rate": 9.176364518546989e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.465300727032386,
      "grad_norm": NaN,
      "learning_rate": 9.08562300137157e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.48645076007931265,
      "grad_norm": NaN,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.5076007931262393,
      "grad_norm": NaN,
      "learning_rate": 8.891708613973126e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.5287508261731659,
      "grad_norm": NaN,
      "learning_rate": 8.788761839251559e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.5287508261731659,
      "eval_loss": NaN,
      "eval_runtime": 0.7392,
      "eval_samples_per_second": 67.638,
      "eval_steps_per_second": 17.586,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.47650456322048e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}