last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.7278617710583153,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06911447084233262,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.06911447084233262,
      "eval_loss": NaN,
      "eval_runtime": 1.9974,
      "eval_samples_per_second": 25.033,
      "eval_steps_per_second": 6.508,
      "step": 1
    },
    {
      "epoch": 0.13822894168466524,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.20734341252699784,
      "grad_norm": NaN,
      "learning_rate": 9.987417087315311e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.27645788336933047,
      "grad_norm": NaN,
      "learning_rate": 9.949738718013078e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.34557235421166305,
      "grad_norm": NaN,
      "learning_rate": 9.887175604818206e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.4146868250539957,
      "grad_norm": NaN,
      "learning_rate": 9.800077626037634e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.4838012958963283,
      "grad_norm": NaN,
      "learning_rate": 9.688931868898919e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.5529157667386609,
      "grad_norm": NaN,
      "learning_rate": 9.554359905560886e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.6220302375809935,
      "grad_norm": NaN,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.6911447084233261,
      "grad_norm": NaN,
      "learning_rate": 9.218074484421978e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.7602591792656588,
      "grad_norm": NaN,
      "learning_rate": 9.018241671106134e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.8293736501079914,
      "grad_norm": NaN,
      "learning_rate": 8.798733423234218e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.8984881209503239,
      "grad_norm": NaN,
      "learning_rate": 8.560777319969136e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.9676025917926566,
      "grad_norm": NaN,
      "learning_rate": 8.305704108364301e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.0367170626349893,
      "grad_norm": NaN,
      "learning_rate": 8.034940261286298e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.1058315334773219,
      "grad_norm": NaN,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.1749460043196545,
      "grad_norm": NaN,
      "learning_rate": 7.452476826029011e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.244060475161987,
      "grad_norm": NaN,
      "learning_rate": 7.14403460964878e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.3131749460043196,
      "grad_norm": NaN,
      "learning_rate": 6.82639828484907e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.3822894168466522,
      "grad_norm": NaN,
      "learning_rate": 6.501344202803414e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.451403887688985,
      "grad_norm": NaN,
      "learning_rate": 6.170690197792785e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.5205183585313176,
      "grad_norm": NaN,
      "learning_rate": 5.83628542113891e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.5896328293736501,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.6587473002159827,
      "grad_norm": NaN,
      "learning_rate": 5.163714578861091e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.7278617710583153,
      "grad_norm": NaN,
      "learning_rate": 4.829309802207215e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.7278617710583153,
      "eval_loss": NaN,
      "eval_runtime": 2.0022,
      "eval_samples_per_second": 24.973,
      "eval_steps_per_second": 6.493,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 44,
  "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": 5.29768176943104e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}