last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0859106529209622,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003436426116838488,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.003436426116838488,
      "eval_loss": NaN,
      "eval_runtime": 31.7734,
      "eval_samples_per_second": 15.422,
      "eval_steps_per_second": 3.871,
      "step": 1
    },
    {
      "epoch": 0.006872852233676976,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.013745704467353952,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.01718213058419244,
      "eval_loss": NaN,
      "eval_runtime": 29.9163,
      "eval_samples_per_second": 16.379,
      "eval_steps_per_second": 4.111,
      "step": 5
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.024054982817869417,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": NaN,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.03436426116838488,
      "eval_loss": NaN,
      "eval_runtime": 29.7955,
      "eval_samples_per_second": 16.445,
      "eval_steps_per_second": 4.128,
      "step": 10
    },
    {
      "epoch": 0.037800687285223365,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.044673539518900345,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.048109965635738834,
      "grad_norm": NaN,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.05154639175257732,
      "eval_loss": NaN,
      "eval_runtime": 29.7223,
      "eval_samples_per_second": 16.486,
      "eval_steps_per_second": 4.138,
      "step": 15
    },
    {
      "epoch": 0.054982817869415807,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.058419243986254296,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": NaN,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.06529209621993128,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.06872852233676977,
      "eval_loss": NaN,
      "eval_runtime": 29.8257,
      "eval_samples_per_second": 16.429,
      "eval_steps_per_second": 4.124,
      "step": 20
    },
    {
      "epoch": 0.07216494845360824,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.07560137457044673,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.07903780068728522,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": NaN,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0859106529209622,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0859106529209622,
      "eval_loss": NaN,
      "eval_runtime": 29.5695,
      "eval_samples_per_second": 16.571,
      "eval_steps_per_second": 4.16,
      "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": 2836679467991040.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}