last-checkpoint/trainer_state.json

{
  "best_metric": 1.04743492603302,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.014166981488477521,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.444654325651681e-05,
      "eval_loss": 1.392892837524414,
      "eval_runtime": 256.0791,
      "eval_samples_per_second": 17.409,
      "eval_steps_per_second": 4.354,
      "step": 1
    },
    {
      "epoch": 0.0009444654325651682,
      "grad_norm": 0.7860835790634155,
      "learning_rate": 4.36e-05,
      "loss": 1.2044,
      "step": 10
    },
    {
      "epoch": 0.0018889308651303363,
      "grad_norm": 1.0544121265411377,
      "learning_rate": 8.72e-05,
      "loss": 1.1564,
      "step": 20
    },
    {
      "epoch": 0.0028333962976955043,
      "grad_norm": 1.270194411277771,
      "learning_rate": 0.0001308,
      "loss": 1.0678,
      "step": 30
    },
    {
      "epoch": 0.0037778617302606727,
      "grad_norm": 1.6109638214111328,
      "learning_rate": 0.0001744,
      "loss": 0.9977,
      "step": 40
    },
    {
      "epoch": 0.004722327162825841,
      "grad_norm": 2.586062431335449,
      "learning_rate": 0.000218,
      "loss": 0.9803,
      "step": 50
    },
    {
      "epoch": 0.004722327162825841,
      "eval_loss": 1.0977070331573486,
      "eval_runtime": 256.1997,
      "eval_samples_per_second": 17.4,
      "eval_steps_per_second": 4.352,
      "step": 50
    },
    {
      "epoch": 0.0056667925953910086,
      "grad_norm": 0.8779242634773254,
      "learning_rate": 0.00021773448147832086,
      "loss": 1.0668,
      "step": 60
    },
    {
      "epoch": 0.0066112580279561765,
      "grad_norm": 1.3890700340270996,
      "learning_rate": 0.0002169392194928312,
      "loss": 1.0106,
      "step": 70
    },
    {
      "epoch": 0.007555723460521345,
      "grad_norm": 0.963046669960022,
      "learning_rate": 0.00021561808847998484,
      "loss": 1.0095,
      "step": 80
    },
    {
      "epoch": 0.008500188893086513,
      "grad_norm": 1.1754647493362427,
      "learning_rate": 0.00021377752485727676,
      "loss": 0.9492,
      "step": 90
    },
    {
      "epoch": 0.009444654325651681,
      "grad_norm": 1.9377000331878662,
      "learning_rate": 0.00021142649566566402,
      "loss": 0.7452,
      "step": 100
    },
    {
      "epoch": 0.009444654325651681,
      "eval_loss": 1.0563247203826904,
      "eval_runtime": 256.3063,
      "eval_samples_per_second": 17.393,
      "eval_steps_per_second": 4.35,
      "step": 100
    },
    {
      "epoch": 0.01038911975821685,
      "grad_norm": 0.8509911894798279,
      "learning_rate": 0.0002085764548830435,
      "loss": 1.0203,
      "step": 110
    },
    {
      "epoch": 0.011333585190782017,
      "grad_norm": 0.8470553755760193,
      "learning_rate": 0.00020524128762162305,
      "loss": 0.9954,
      "step": 120
    },
    {
      "epoch": 0.012278050623347185,
      "grad_norm": 0.9998864531517029,
      "learning_rate": 0.00020143724248105043,
      "loss": 0.9616,
      "step": 130
    },
    {
      "epoch": 0.013222516055912353,
      "grad_norm": 1.3236018419265747,
      "learning_rate": 0.0001971828523868693,
      "loss": 1.0109,
      "step": 140
    },
    {
      "epoch": 0.014166981488477521,
      "grad_norm": 1.5146818161010742,
      "learning_rate": 0.0001924988442999686,
      "loss": 0.8894,
      "step": 150
    },
    {
      "epoch": 0.014166981488477521,
      "eval_loss": 1.04743492603302,
      "eval_runtime": 256.4077,
      "eval_samples_per_second": 17.386,
      "eval_steps_per_second": 4.349,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 2.5317253054464e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}