last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.008051448757560814,
  "eval_steps": 100,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.025724378780407e-05,
      "eval_loss": NaN,
      "eval_runtime": 1418.5159,
      "eval_samples_per_second": 7.374,
      "eval_steps_per_second": 3.687,
      "step": 1
    },
    {
      "epoch": 0.0004025724378780407,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0008051448757560814,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.001207717313634122,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0016102897515121628,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0020128621893902034,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.002415434627268244,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.0028180070651462846,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.0032205795030243256,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.0036231519409023662,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.004025724378780407,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.004025724378780407,
      "eval_loss": NaN,
      "eval_runtime": 1421.3319,
      "eval_samples_per_second": 7.359,
      "eval_steps_per_second": 3.68,
      "step": 100
    },
    {
      "epoch": 0.004428296816658447,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.004830869254536488,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.005233441692414529,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.005636014130292569,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.00603858656817061,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.006441159006048651,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.006843731443926692,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.0072463038818047325,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.007648876319682773,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.008051448757560814,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.008051448757560814,
      "eval_loss": NaN,
      "eval_runtime": 1419.7108,
      "eval_samples_per_second": 7.368,
      "eval_steps_per_second": 3.684,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.45128942174208e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}