last-checkpoint/trainer_state.json

{
  "best_metric": 3.8233513832092285,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.00036778565452054543,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.677856545205454e-05,
      "grad_norm": 2.1201064586639404,
      "learning_rate": 1e-05,
      "loss": 14.0814,
      "step": 1
    },
    {
      "epoch": 3.677856545205454e-05,
      "eval_loss": 3.8606455326080322,
      "eval_runtime": 739.1058,
      "eval_samples_per_second": 15.49,
      "eval_steps_per_second": 7.746,
      "step": 1
    },
    {
      "epoch": 7.355713090410909e-05,
      "grad_norm": 3.3264341354370117,
      "learning_rate": 2e-05,
      "loss": 16.4635,
      "step": 2
    },
    {
      "epoch": 0.00011033569635616363,
      "grad_norm": 2.497408866882324,
      "learning_rate": 3e-05,
      "loss": 15.8726,
      "step": 3
    },
    {
      "epoch": 0.00014711426180821817,
      "grad_norm": 3.2194437980651855,
      "learning_rate": 4e-05,
      "loss": 14.8162,
      "step": 4
    },
    {
      "epoch": 0.00018389282726027272,
      "grad_norm": 3.457934617996216,
      "learning_rate": 5e-05,
      "loss": 15.1606,
      "step": 5
    },
    {
      "epoch": 0.00018389282726027272,
      "eval_loss": 3.8564059734344482,
      "eval_runtime": 738.9862,
      "eval_samples_per_second": 15.493,
      "eval_steps_per_second": 7.747,
      "step": 5
    },
    {
      "epoch": 0.00022067139271232726,
      "grad_norm": 2.7731423377990723,
      "learning_rate": 6e-05,
      "loss": 14.1681,
      "step": 6
    },
    {
      "epoch": 0.0002574499581643818,
      "grad_norm": 2.2123680114746094,
      "learning_rate": 7e-05,
      "loss": 14.4528,
      "step": 7
    },
    {
      "epoch": 0.00029422852361643635,
      "grad_norm": 2.2788443565368652,
      "learning_rate": 8e-05,
      "loss": 15.9437,
      "step": 8
    },
    {
      "epoch": 0.0003310070890684909,
      "grad_norm": 6.673981666564941,
      "learning_rate": 9e-05,
      "loss": 15.1776,
      "step": 9
    },
    {
      "epoch": 0.00036778565452054543,
      "grad_norm": 2.5079147815704346,
      "learning_rate": 0.0001,
      "loss": 15.3765,
      "step": 10
    },
    {
      "epoch": 0.00036778565452054543,
      "eval_loss": 3.8233513832092285,
      "eval_runtime": 741.3845,
      "eval_samples_per_second": 15.443,
      "eval_steps_per_second": 7.722,
      "step": 10
    }
  ],
  "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 150139305984000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}