last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 2.6315789473684212,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10526315789473684,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": NaN,
      "eval_runtime": 1.6471,
      "eval_samples_per_second": 38.856,
      "eval_steps_per_second": 4.857,
      "step": 1
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": NaN,
      "learning_rate": 9.966191788709716e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": NaN,
      "learning_rate": 9.865224352899119e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": NaN,
      "learning_rate": 9.468163201617062e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": NaN,
      "learning_rate": 9.177439057064683e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": NaN,
      "learning_rate": 8.43120818934367e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": NaN,
      "learning_rate": 7.985792958513931e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": NaN,
      "learning_rate": 6.980398830195785e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.368421052631579,
      "grad_norm": NaN,
      "learning_rate": 6.434016163555452e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": NaN,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": NaN,
      "learning_rate": 5.290724144552379e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": NaN,
      "learning_rate": 4.709275855447621e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": NaN,
      "learning_rate": 3.5659838364445505e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 2.0,
      "grad_norm": NaN,
      "learning_rate": 3.019601169804216e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": NaN,
      "learning_rate": 2.0142070414860704e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": NaN,
      "learning_rate": 1.5687918106563326e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": NaN,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": NaN,
      "learning_rate": 8.225609429353187e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": NaN,
      "learning_rate": 5.318367983829392e-06,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 2.6315789473684212,
      "eval_loss": NaN,
      "eval_runtime": 1.6466,
      "eval_samples_per_second": 38.868,
      "eval_steps_per_second": 4.858,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 29,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.812028905324544e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}