last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.1111111111111112,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.044444444444444446,
      "eval_loss": NaN,
      "eval_runtime": 0.4655,
      "eval_samples_per_second": 107.402,
      "eval_steps_per_second": 27.924,
      "step": 1
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": NaN,
      "learning_rate": 9.99474502074547e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": NaN,
      "learning_rate": 9.978992356229419e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": NaN,
      "learning_rate": 9.95277879752973e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": NaN,
      "learning_rate": 9.916165567627362e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": NaN,
      "learning_rate": 9.869238178417235e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.4,
      "grad_norm": NaN,
      "learning_rate": 9.812106230991248e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": NaN,
      "learning_rate": 9.744903159659843e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": NaN,
      "learning_rate": 9.667785920309994e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": NaN,
      "learning_rate": 9.580934623827455e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": NaN,
      "learning_rate": 9.484552115439445e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": NaN,
      "learning_rate": 9.378863500960222e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": NaN,
      "learning_rate": 9.26411562104602e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": NaN,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": NaN,
      "learning_rate": 9.008534593284501e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.8,
      "grad_norm": NaN,
      "learning_rate": 8.868298366769954e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": NaN,
      "learning_rate": 8.720195323348545e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": NaN,
      "learning_rate": 8.564571364540588e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": NaN,
      "learning_rate": 8.401789957312768e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": NaN,
      "learning_rate": 8.232231285184201e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": NaN,
      "learning_rate": 8.056291360290201e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": NaN,
      "learning_rate": 7.874381098477599e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": NaN,
      "learning_rate": 7.686925359591727e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.1111111111111112,
      "eval_loss": NaN,
      "eval_runtime": 0.4689,
      "eval_samples_per_second": 106.639,
      "eval_steps_per_second": 27.726,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 68,
  "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": 3.91521434075136e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}