last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.8547008547008547,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03418803418803419,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.03418803418803419,
      "eval_loss": NaN,
      "eval_runtime": 1.1257,
      "eval_samples_per_second": 44.415,
      "eval_steps_per_second": 11.548,
      "step": 1
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": NaN,
      "learning_rate": 9.996926770643604e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": NaN,
      "learning_rate": 9.987711280236048e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": NaN,
      "learning_rate": 9.972366116028733e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": NaN,
      "learning_rate": 9.950912237670159e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": NaN,
      "learning_rate": 9.923378948577559e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": NaN,
      "learning_rate": 9.889803855911966e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": NaN,
      "learning_rate": 9.850232819211343e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.37606837606837606,
      "grad_norm": NaN,
      "learning_rate": 9.804719887751984e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": NaN,
      "learning_rate": 9.753327226723689e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": NaN,
      "learning_rate": 9.6961250323196e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": NaN,
      "learning_rate": 9.633191435856655e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": NaN,
      "learning_rate": 9.56461239705758e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": NaN,
      "learning_rate": 9.490481586640278e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.5811965811965812,
      "grad_norm": NaN,
      "learning_rate": 9.410900258374877e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": NaN,
      "learning_rate": 9.325977110783264e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.6495726495726496,
      "grad_norm": NaN,
      "learning_rate": 9.235828138669979e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": NaN,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": NaN,
      "learning_rate": 9.040352221150675e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": NaN,
      "learning_rate": 8.935292272334964e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.7863247863247863,
      "grad_norm": NaN,
      "learning_rate": 8.825540127492967e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": NaN,
      "learning_rate": 8.711245694852886e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": NaN,
      "learning_rate": 8.592565086861683e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.8547008547008547,
      "eval_loss": NaN,
      "eval_runtime": 1.1338,
      "eval_samples_per_second": 44.101,
      "eval_steps_per_second": 11.466,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 88,
  "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
}