last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.03372681281618887,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016863406408094434,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0016863406408094434,
      "eval_loss": NaN,
      "eval_runtime": 24.5865,
      "eval_samples_per_second": 10.168,
      "eval_steps_per_second": 5.084,
      "step": 1
    },
    {
      "epoch": 0.003372681281618887,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00505902192242833,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.006745362563237774,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.008431703204047217,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.008431703204047217,
      "eval_loss": NaN,
      "eval_runtime": 20.4694,
      "eval_samples_per_second": 12.213,
      "eval_steps_per_second": 6.107,
      "step": 5
    },
    {
      "epoch": 0.01011804384485666,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.011804384485666104,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.013490725126475547,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.01517706576728499,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.016863406408094434,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.016863406408094434,
      "eval_loss": NaN,
      "eval_runtime": 20.534,
      "eval_samples_per_second": 12.175,
      "eval_steps_per_second": 6.087,
      "step": 10
    },
    {
      "epoch": 0.01854974704890388,
      "grad_norm": NaN,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.02023608768971332,
      "grad_norm": NaN,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.021922428330522766,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.023608768971332208,
      "grad_norm": NaN,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.025295109612141653,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.025295109612141653,
      "eval_loss": NaN,
      "eval_runtime": 20.7077,
      "eval_samples_per_second": 12.073,
      "eval_steps_per_second": 6.036,
      "step": 15
    },
    {
      "epoch": 0.026981450252951095,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.02866779089376054,
      "grad_norm": NaN,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.03035413153456998,
      "grad_norm": NaN,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.03204047217537943,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.03372681281618887,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.03372681281618887,
      "eval_loss": NaN,
      "eval_runtime": 20.5418,
      "eval_samples_per_second": 12.17,
      "eval_steps_per_second": 6.085,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 156783555379200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}