last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.013213094176328741,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005285237670531497,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 14518310.0,
      "step": 1
    },
    {
      "epoch": 0.0005285237670531497,
      "eval_loss": NaN,
      "eval_runtime": 2.0498,
      "eval_samples_per_second": 24.392,
      "eval_steps_per_second": 6.342,
      "step": 1
    },
    {
      "epoch": 0.0010570475341062993,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.001585571301159449,
      "grad_norm": NaN,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0021140950682125986,
      "grad_norm": NaN,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0026426188352657483,
      "grad_norm": NaN,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.003171142602318898,
      "grad_norm": NaN,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0036996663693720476,
      "grad_norm": NaN,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.004228190136425197,
      "grad_norm": NaN,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.004756713903478347,
      "grad_norm": NaN,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.005285237670531497,
      "grad_norm": NaN,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.005813761437584646,
      "grad_norm": NaN,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.006342285204637796,
      "grad_norm": NaN,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0068708089716909455,
      "grad_norm": NaN,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.007399332738744095,
      "grad_norm": NaN,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.007927856505797245,
      "grad_norm": NaN,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.008456380272850395,
      "grad_norm": NaN,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.008984904039903544,
      "grad_norm": NaN,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.009513427806956694,
      "grad_norm": NaN,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.010041951574009843,
      "grad_norm": NaN,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.010570475341062993,
      "grad_norm": NaN,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.011098999108116143,
      "grad_norm": NaN,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.011627522875169292,
      "grad_norm": NaN,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.012156046642222442,
      "grad_norm": NaN,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.012684570409275592,
      "grad_norm": NaN,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.013213094176328741,
      "grad_norm": NaN,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.013213094176328741,
      "eval_loss": NaN,
      "eval_runtime": 1.9911,
      "eval_samples_per_second": 25.111,
      "eval_steps_per_second": 6.529,
      "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": 5.302648335394406e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}