last-checkpoint/trainer_state.json

{
  "best_metric": 0.09226811677217484,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.29459419649432905,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005891883929886581,
      "eval_loss": 1.4878911972045898,
      "eval_runtime": 302.6677,
      "eval_samples_per_second": 9.446,
      "eval_steps_per_second": 2.362,
      "step": 1
    },
    {
      "epoch": 0.029459419649432907,
      "grad_norm": 17.25750160217285,
      "learning_rate": 0.0001035,
      "loss": 3.0964,
      "step": 50
    },
    {
      "epoch": 0.058918839298865815,
      "grad_norm": 15.095850944519043,
      "learning_rate": 0.000207,
      "loss": 1.9876,
      "step": 100
    },
    {
      "epoch": 0.08837825894829872,
      "grad_norm": 13.579780578613281,
      "learning_rate": 0.00019912153161491818,
      "loss": 1.9922,
      "step": 150
    },
    {
      "epoch": 0.11783767859773163,
      "grad_norm": 11.583715438842773,
      "learning_rate": 0.00017668555185280767,
      "loss": 1.6798,
      "step": 200
    },
    {
      "epoch": 0.14729709824716453,
      "grad_norm": 12.069087982177734,
      "learning_rate": 0.0001431077352497868,
      "loss": 1.5442,
      "step": 250
    },
    {
      "epoch": 0.17675651789659744,
      "grad_norm": 11.045920372009277,
      "learning_rate": 0.0001035,
      "loss": 1.2986,
      "step": 300
    },
    {
      "epoch": 0.20621593754603035,
      "grad_norm": 8.735687255859375,
      "learning_rate": 6.389226475021321e-05,
      "loss": 1.0951,
      "step": 350
    },
    {
      "epoch": 0.23567535719546326,
      "grad_norm": 10.485920906066895,
      "learning_rate": 3.0314448147192338e-05,
      "loss": 0.8972,
      "step": 400
    },
    {
      "epoch": 0.26513477684489617,
      "grad_norm": 6.716992378234863,
      "learning_rate": 7.878468385081822e-06,
      "loss": 0.8396,
      "step": 450
    },
    {
      "epoch": 0.29459419649432905,
      "grad_norm": 8.605260848999023,
      "learning_rate": 0.0,
      "loss": 0.7214,
      "step": 500
    },
    {
      "epoch": 0.29459419649432905,
      "eval_loss": 0.09226811677217484,
      "eval_runtime": 302.2865,
      "eval_samples_per_second": 9.458,
      "eval_steps_per_second": 2.365,
      "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": 7.159871941996708e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}