last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.021592442645074223,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010796221322537112,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0010796221322537112,
      "eval_loss": NaN,
      "eval_runtime": 48.648,
      "eval_samples_per_second": 8.017,
      "eval_steps_per_second": 4.008,
      "step": 1
    },
    {
      "epoch": 0.0021592442645074223,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0032388663967611335,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.004318488529014845,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.005398110661268556,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.005398110661268556,
      "eval_loss": NaN,
      "eval_runtime": 47.5462,
      "eval_samples_per_second": 8.203,
      "eval_steps_per_second": 4.101,
      "step": 5
    },
    {
      "epoch": 0.006477732793522267,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.007557354925775978,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00863697705802969,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.009716599190283401,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.010796221322537112,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.010796221322537112,
      "eval_loss": NaN,
      "eval_runtime": 47.5521,
      "eval_samples_per_second": 8.202,
      "eval_steps_per_second": 4.101,
      "step": 10
    },
    {
      "epoch": 0.011875843454790824,
      "grad_norm": NaN,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.012955465587044534,
      "grad_norm": NaN,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.015114709851551956,
      "grad_norm": NaN,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.016194331983805668,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.016194331983805668,
      "eval_loss": NaN,
      "eval_runtime": 47.623,
      "eval_samples_per_second": 8.189,
      "eval_steps_per_second": 4.095,
      "step": 15
    },
    {
      "epoch": 0.01727395411605938,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.01835357624831309,
      "grad_norm": NaN,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.019433198380566803,
      "grad_norm": NaN,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.020512820512820513,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.021592442645074223,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.021592442645074223,
      "eval_loss": NaN,
      "eval_runtime": 47.3721,
      "eval_samples_per_second": 8.233,
      "eval_steps_per_second": 4.116,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4642434302607360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}