last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.1422475106685633,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005689900426742532,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.005689900426742532,
      "eval_loss": NaN,
      "eval_runtime": 7.3837,
      "eval_samples_per_second": 10.022,
      "eval_steps_per_second": 5.011,
      "step": 1
    },
    {
      "epoch": 0.011379800853485065,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.017069701280227598,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.02275960170697013,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.02844950213371266,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.034139402560455195,
      "grad_norm": NaN,
      "learning_rate": 0.00019994532573409262,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.03982930298719772,
      "grad_norm": NaN,
      "learning_rate": 0.00019978136272187747,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.04551920341394026,
      "grad_norm": NaN,
      "learning_rate": 0.00019950829025450114,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.051209103840682786,
      "grad_norm": NaN,
      "learning_rate": 0.00019912640693269752,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.05689900426742532,
      "grad_norm": NaN,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.06258890469416785,
      "grad_norm": NaN,
      "learning_rate": 0.00019803799658748094,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.06827880512091039,
      "grad_norm": NaN,
      "learning_rate": 0.0001973326597248006,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.07396870554765292,
      "grad_norm": NaN,
      "learning_rate": 0.00019652089102773488,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.07965860597439545,
      "grad_norm": NaN,
      "learning_rate": 0.00019560357815343577,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.08534850640113797,
      "grad_norm": NaN,
      "learning_rate": 0.00019458172417006347,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.09103840682788052,
      "grad_norm": NaN,
      "learning_rate": 0.0001934564464599461,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.09672830725462304,
      "grad_norm": NaN,
      "learning_rate": 0.00019222897549773848,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.10241820768136557,
      "grad_norm": NaN,
      "learning_rate": 0.00019090065350491626,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": NaN,
      "learning_rate": 0.00018947293298207635,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.11379800853485064,
      "grad_norm": NaN,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.11948790896159317,
      "grad_norm": NaN,
      "learning_rate": 0.00018632564809575742,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.1251778093883357,
      "grad_norm": NaN,
      "learning_rate": 0.00018460952524209355,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.13086770981507823,
      "grad_norm": NaN,
      "learning_rate": 0.00018280088311480201,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.13655761024182078,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.1422475106685633,
      "grad_norm": NaN,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.1422475106685633,
      "eval_loss": NaN,
      "eval_runtime": 7.3949,
      "eval_samples_per_second": 10.007,
      "eval_steps_per_second": 5.003,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 5146843860172800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}