last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.6126482213438735,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06324110671936758,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.06324110671936758,
      "eval_loss": NaN,
      "eval_runtime": 1.0459,
      "eval_samples_per_second": 102.3,
      "eval_steps_per_second": 13.385,
      "step": 1
    },
    {
      "epoch": 0.12648221343873517,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.18972332015810275,
      "grad_norm": NaN,
      "learning_rate": 9.988343845952697e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.25296442687747034,
      "grad_norm": NaN,
      "learning_rate": 9.953429730181653e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.31620553359683795,
      "grad_norm": NaN,
      "learning_rate": 9.895420438411616e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.3794466403162055,
      "grad_norm": NaN,
      "learning_rate": 9.814586436738998e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.4426877470355731,
      "grad_norm": NaN,
      "learning_rate": 9.711304610594104e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.5059288537549407,
      "grad_norm": NaN,
      "learning_rate": 9.586056507527266e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.5691699604743083,
      "grad_norm": NaN,
      "learning_rate": 9.439426092011875e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.6324110671936759,
      "grad_norm": NaN,
      "learning_rate": 9.272097022732443e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": NaN,
      "learning_rate": 9.08484946505221e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.758893280632411,
      "grad_norm": NaN,
      "learning_rate": 8.8785564535221e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.8221343873517787,
      "grad_norm": NaN,
      "learning_rate": 8.654179821390621e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.8853754940711462,
      "grad_norm": NaN,
      "learning_rate": 8.412765716093272e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.9486166007905138,
      "grad_norm": NaN,
      "learning_rate": 8.155439721630264e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": NaN,
      "learning_rate": 7.883401610574336e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.1067193675889329,
      "grad_norm": NaN,
      "learning_rate": 7.597919750177168e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.1699604743083003,
      "grad_norm": NaN,
      "learning_rate": 7.300325188655761e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.233201581027668,
      "grad_norm": NaN,
      "learning_rate": 6.992005449231208e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.2964426877470356,
      "grad_norm": NaN,
      "learning_rate": 6.674398060854931e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.359683794466403,
      "grad_norm": NaN,
      "learning_rate": 6.348983855785121e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.4229249011857708,
      "grad_norm": NaN,
      "learning_rate": 6.01728006526317e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.4861660079051384,
      "grad_norm": NaN,
      "learning_rate": 5.680833245481234e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.5494071146245059,
      "grad_norm": NaN,
      "learning_rate": 5.341212066823355e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.6126482213438735,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.6126482213438735,
      "eval_loss": NaN,
      "eval_runtime": 1.043,
      "eval_samples_per_second": 102.584,
      "eval_steps_per_second": 13.422,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 48,
  "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": 5.1506187337728e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}