last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.2452830188679247,
  "eval_steps": 25,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10062893081761007,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.10062893081761007,
      "eval_loss": NaN,
      "eval_runtime": 3.4665,
      "eval_samples_per_second": 19.328,
      "eval_steps_per_second": 2.596,
      "step": 1
    },
    {
      "epoch": 0.20125786163522014,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.3018867924528302,
      "grad_norm": NaN,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.4025157232704403,
      "grad_norm": NaN,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.5031446540880503,
      "grad_norm": NaN,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": NaN,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.7044025157232704,
      "grad_norm": NaN,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.8050314465408805,
      "grad_norm": NaN,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.9056603773584906,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 1.0817610062893082,
      "grad_norm": NaN,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 1.1823899371069182,
      "grad_norm": NaN,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 1.2830188679245282,
      "grad_norm": NaN,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.3836477987421385,
      "grad_norm": NaN,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.4842767295597485,
      "grad_norm": NaN,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.5849056603773586,
      "grad_norm": NaN,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.6855345911949686,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.7861635220125787,
      "grad_norm": NaN,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": NaN,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 2.0628930817610063,
      "grad_norm": NaN,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 2.1635220125786163,
      "grad_norm": NaN,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 2.2641509433962264,
      "grad_norm": NaN,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 2.3647798742138364,
      "grad_norm": NaN,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 2.4654088050314464,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 2.5660377358490565,
      "grad_norm": NaN,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": NaN,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 2.6666666666666665,
      "eval_loss": NaN,
      "eval_runtime": 3.4708,
      "eval_samples_per_second": 19.304,
      "eval_steps_per_second": 2.593,
      "step": 25
    },
    {
      "epoch": 2.767295597484277,
      "grad_norm": NaN,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 2.867924528301887,
      "grad_norm": NaN,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 3.0440251572327046,
      "grad_norm": NaN,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": NaN,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 3.2452830188679247,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.666942012614246e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}