last-checkpoint/trainer_state.json

{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.322061191626409,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006441223832528181,
      "eval_loss": 11.5,
      "eval_runtime": 17.441,
      "eval_samples_per_second": 149.934,
      "eval_steps_per_second": 37.498,
      "step": 1
    },
    {
      "epoch": 0.0322061191626409,
      "grad_norm": 0.0003120787732768804,
      "learning_rate": 0.0001025,
      "loss": 92.0,
      "step": 50
    },
    {
      "epoch": 0.0644122383252818,
      "grad_norm": 0.002143029822036624,
      "learning_rate": 0.000205,
      "loss": 92.0,
      "step": 100
    },
    {
      "epoch": 0.0966183574879227,
      "grad_norm": 0.0024146120995283127,
      "learning_rate": 0.0001971976520824069,
      "loss": 92.0,
      "step": 150
    },
    {
      "epoch": 0.1288244766505636,
      "grad_norm": 0.004354597069323063,
      "learning_rate": 0.0001749784450716211,
      "loss": 92.0,
      "step": 200
    },
    {
      "epoch": 0.1610305958132045,
      "grad_norm": 0.00207455363124609,
      "learning_rate": 0.0001417250518174217,
      "loss": 92.0,
      "step": 250
    },
    {
      "epoch": 0.1932367149758454,
      "grad_norm": 0.003958873450756073,
      "learning_rate": 0.0001025,
      "loss": 92.0,
      "step": 300
    },
    {
      "epoch": 0.22544283413848631,
      "grad_norm": 0.002959570148959756,
      "learning_rate": 6.32749481825783e-05,
      "loss": 92.0,
      "step": 350
    },
    {
      "epoch": 0.2576489533011272,
      "grad_norm": 0.003939197398722172,
      "learning_rate": 3.0021554928378886e-05,
      "loss": 92.0,
      "step": 400
    },
    {
      "epoch": 0.2898550724637681,
      "grad_norm": 0.004173987079411745,
      "learning_rate": 7.80234791759311e-06,
      "loss": 92.0,
      "step": 450
    },
    {
      "epoch": 0.322061191626409,
      "grad_norm": 0.00423756567761302,
      "learning_rate": 0.0,
      "loss": 92.0,
      "step": 500
    },
    {
      "epoch": 0.322061191626409,
      "eval_loss": 11.5,
      "eval_runtime": 17.4811,
      "eval_samples_per_second": 149.59,
      "eval_steps_per_second": 37.412,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 80496652124160.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}