last-checkpoint/trainer_state.json

{
  "best_metric": 0.017324844375252724,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0050729232720355105,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001690974424011837,
      "eval_loss": 1.9996156692504883,
      "eval_runtime": 274.0185,
      "eval_samples_per_second": 9.087,
      "eval_steps_per_second": 4.543,
      "step": 1
    },
    {
      "epoch": 0.000507292327203551,
      "grad_norm": 1.7137808799743652,
      "learning_rate": 0.00012,
      "loss": 7.994,
      "step": 3
    },
    {
      "epoch": 0.0008454872120059184,
      "eval_loss": 1.5608346462249756,
      "eval_runtime": 277.0964,
      "eval_samples_per_second": 8.986,
      "eval_steps_per_second": 4.493,
      "step": 5
    },
    {
      "epoch": 0.001014584654407102,
      "grad_norm": 3.349550247192383,
      "learning_rate": 0.0001992114701314478,
      "loss": 7.1278,
      "step": 6
    },
    {
      "epoch": 0.0015218769816106531,
      "grad_norm": 7.611365795135498,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.6226,
      "step": 9
    },
    {
      "epoch": 0.0016909744240118367,
      "eval_loss": 0.2576157748699188,
      "eval_runtime": 277.8804,
      "eval_samples_per_second": 8.961,
      "eval_steps_per_second": 4.48,
      "step": 10
    },
    {
      "epoch": 0.002029169308814204,
      "grad_norm": 7.3718037605285645,
      "learning_rate": 0.000163742398974869,
      "loss": 1.0619,
      "step": 12
    },
    {
      "epoch": 0.0025364616360177552,
      "grad_norm": 1.747843623161316,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.2561,
      "step": 15
    },
    {
      "epoch": 0.0025364616360177552,
      "eval_loss": 0.036673061549663544,
      "eval_runtime": 277.2407,
      "eval_samples_per_second": 8.981,
      "eval_steps_per_second": 4.491,
      "step": 15
    },
    {
      "epoch": 0.0030437539632213063,
      "grad_norm": 1.052754521369934,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.116,
      "step": 18
    },
    {
      "epoch": 0.0033819488480236735,
      "eval_loss": 0.019720349460840225,
      "eval_runtime": 277.3036,
      "eval_samples_per_second": 8.979,
      "eval_steps_per_second": 4.49,
      "step": 20
    },
    {
      "epoch": 0.0035510462904248573,
      "grad_norm": 0.6280816197395325,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.0721,
      "step": 21
    },
    {
      "epoch": 0.004058338617628408,
      "grad_norm": 0.6697679162025452,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.0797,
      "step": 24
    },
    {
      "epoch": 0.004227436060029592,
      "eval_loss": 0.018337341025471687,
      "eval_runtime": 277.3108,
      "eval_samples_per_second": 8.979,
      "eval_steps_per_second": 4.49,
      "step": 25
    },
    {
      "epoch": 0.004565630944831959,
      "grad_norm": 0.7023375630378723,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.076,
      "step": 27
    },
    {
      "epoch": 0.0050729232720355105,
      "grad_norm": 0.6577435731887817,
      "learning_rate": 0.0,
      "loss": 0.0726,
      "step": 30
    },
    {
      "epoch": 0.0050729232720355105,
      "eval_loss": 0.017324844375252724,
      "eval_runtime": 277.3945,
      "eval_samples_per_second": 8.976,
      "eval_steps_per_second": 4.488,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9818930738626560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}