last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.3372681281618887,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013490725126475547,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.013490725126475547,
      "eval_loss": NaN,
      "eval_runtime": 15.9047,
      "eval_samples_per_second": 7.859,
      "eval_steps_per_second": 2.012,
      "step": 1
    },
    {
      "epoch": 0.026981450252951095,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.04047217537942664,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.05396290050590219,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.06745362563237774,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.06745362563237774,
      "eval_loss": NaN,
      "eval_runtime": 14.8179,
      "eval_samples_per_second": 8.436,
      "eval_steps_per_second": 2.16,
      "step": 5
    },
    {
      "epoch": 0.08094435075885328,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.09443507588532883,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.10792580101180438,
      "grad_norm": NaN,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.12141652613827993,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.13490725126475547,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.13490725126475547,
      "eval_loss": NaN,
      "eval_runtime": 14.7922,
      "eval_samples_per_second": 8.45,
      "eval_steps_per_second": 2.163,
      "step": 10
    },
    {
      "epoch": 0.14839797639123103,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.16188870151770657,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.17537942664418213,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.18887015177065766,
      "grad_norm": NaN,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.20236087689713322,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.20236087689713322,
      "eval_loss": NaN,
      "eval_runtime": 14.7758,
      "eval_samples_per_second": 8.46,
      "eval_steps_per_second": 2.166,
      "step": 15
    },
    {
      "epoch": 0.21585160202360876,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.22934232715008432,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.24283305227655985,
      "grad_norm": NaN,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.2563237774030354,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.26981450252951095,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.26981450252951095,
      "eval_loss": NaN,
      "eval_runtime": 14.8633,
      "eval_samples_per_second": 8.41,
      "eval_steps_per_second": 2.153,
      "step": 20
    },
    {
      "epoch": 0.28330522765598654,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.29679595278246207,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.3102866779089376,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.32377740303541314,
      "grad_norm": NaN,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.3372681281618887,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.3372681281618887,
      "eval_loss": NaN,
      "eval_runtime": 14.848,
      "eval_samples_per_second": 8.419,
      "eval_steps_per_second": 2.155,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.51565151993856e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}