last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.33585222502099077,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01343408900083963,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.01343408900083963,
      "eval_loss": NaN,
      "eval_runtime": 3.4448,
      "eval_samples_per_second": 14.515,
      "eval_steps_per_second": 3.774,
      "step": 1
    },
    {
      "epoch": 0.02686817800167926,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.04030226700251889,
      "grad_norm": NaN,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.05373635600335852,
      "grad_norm": NaN,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.06717044500419815,
      "grad_norm": NaN,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.08060453400503778,
      "grad_norm": NaN,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.09403862300587741,
      "grad_norm": NaN,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.10747271200671704,
      "grad_norm": NaN,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.12090680100755667,
      "grad_norm": NaN,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.1343408900083963,
      "grad_norm": NaN,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.14777497900923595,
      "grad_norm": NaN,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.16120906801007556,
      "grad_norm": NaN,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.1746431570109152,
      "grad_norm": NaN,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.18807724601175482,
      "grad_norm": NaN,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.20151133501259447,
      "grad_norm": NaN,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.21494542401343408,
      "grad_norm": NaN,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.22837951301427373,
      "grad_norm": NaN,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.24181360201511334,
      "grad_norm": NaN,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.25524769101595296,
      "grad_norm": NaN,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.2686817800167926,
      "grad_norm": NaN,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.28211586901763225,
      "grad_norm": NaN,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.2955499580184719,
      "grad_norm": NaN,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.3089840470193115,
      "grad_norm": NaN,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.3224181360201511,
      "grad_norm": NaN,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.33585222502099077,
      "grad_norm": NaN,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.33585222502099077,
      "eval_loss": NaN,
      "eval_runtime": 3.0656,
      "eval_samples_per_second": 16.31,
      "eval_steps_per_second": 4.241,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.654300032425001e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}