last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.9174311926605505,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03669724770642202,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.03669724770642202,
      "eval_loss": NaN,
      "eval_runtime": 3.5828,
      "eval_samples_per_second": 12.839,
      "eval_steps_per_second": 1.675,
      "step": 1
    },
    {
      "epoch": 0.07339449541284404,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.11009174311926606,
      "grad_norm": NaN,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.14678899082568808,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.1834862385321101,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.22018348623853212,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.25688073394495414,
      "grad_norm": NaN,
      "learning_rate": 3.5e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.29357798165137616,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.3302752293577982,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.3669724770642202,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.4036697247706422,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.44036697247706424,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.47706422018348627,
      "grad_norm": NaN,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.5137614678899083,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.5504587155963303,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.5871559633027523,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.6238532110091743,
      "grad_norm": NaN,
      "learning_rate": 8.5e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.6605504587155964,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.6972477064220184,
      "grad_norm": NaN,
      "learning_rate": 9.5e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.7339449541284404,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.7706422018348624,
      "grad_norm": NaN,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.8073394495412844,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.8440366972477065,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.8807339449541285,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.9174311926605505,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.9174311926605505,
      "eval_loss": NaN,
      "eval_runtime": 3.1103,
      "eval_samples_per_second": 14.79,
      "eval_steps_per_second": 1.929,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 3.5547217133568e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}