last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.01633186346562143,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006532745386248571,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0006532745386248571,
      "eval_loss": NaN,
      "eval_runtime": 111.5891,
      "eval_samples_per_second": 23.103,
      "eval_steps_per_second": 5.78,
      "step": 1
    },
    {
      "epoch": 0.0013065490772497142,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0019598236158745713,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0026130981544994283,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0032663726931242854,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0032663726931242854,
      "eval_loss": NaN,
      "eval_runtime": 108.2189,
      "eval_samples_per_second": 23.822,
      "eval_steps_per_second": 5.96,
      "step": 5
    },
    {
      "epoch": 0.0039196472317491425,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.004572921770374,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.005226196308998857,
      "grad_norm": NaN,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.005879470847623714,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.006532745386248571,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.006532745386248571,
      "eval_loss": NaN,
      "eval_runtime": 107.2241,
      "eval_samples_per_second": 24.043,
      "eval_steps_per_second": 6.015,
      "step": 10
    },
    {
      "epoch": 0.007186019924873428,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.007839294463498285,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.008492569002123142,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.009145843540748,
      "grad_norm": NaN,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.009799118079372856,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.009799118079372856,
      "eval_loss": NaN,
      "eval_runtime": 110.5086,
      "eval_samples_per_second": 23.329,
      "eval_steps_per_second": 5.837,
      "step": 15
    },
    {
      "epoch": 0.010452392617997713,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.01110566715662257,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.011758941695247428,
      "grad_norm": NaN,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.012412216233872285,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.013065490772497142,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.013065490772497142,
      "eval_loss": NaN,
      "eval_runtime": 107.0162,
      "eval_samples_per_second": 24.09,
      "eval_steps_per_second": 6.027,
      "step": 20
    },
    {
      "epoch": 0.013718765311121999,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.014372039849746856,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.015025314388371713,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.01567858892699657,
      "grad_norm": NaN,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.01633186346562143,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.01633186346562143,
      "eval_loss": NaN,
      "eval_runtime": 106.7733,
      "eval_samples_per_second": 24.145,
      "eval_steps_per_second": 6.041,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5146843860172800.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}