last-checkpoint/trainer_state.json

{
  "best_metric": 1.1973159313201904,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.2810304449648712,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00936768149882904,
      "eval_loss": 1.5999226570129395,
      "eval_runtime": 16.0712,
      "eval_samples_per_second": 2.8,
      "eval_steps_per_second": 1.431,
      "step": 1
    },
    {
      "epoch": 0.02810304449648712,
      "grad_norm": 0.7878350615501404,
      "learning_rate": 6e-05,
      "loss": 6.5914,
      "step": 3
    },
    {
      "epoch": 0.0468384074941452,
      "eval_loss": 1.5757285356521606,
      "eval_runtime": 15.8761,
      "eval_samples_per_second": 2.834,
      "eval_steps_per_second": 1.449,
      "step": 5
    },
    {
      "epoch": 0.05620608899297424,
      "grad_norm": 1.1830600500106812,
      "learning_rate": 9.96057350657239e-05,
      "loss": 6.266,
      "step": 6
    },
    {
      "epoch": 0.08430913348946135,
      "grad_norm": 1.2790220975875854,
      "learning_rate": 9.381533400219318e-05,
      "loss": 6.1728,
      "step": 9
    },
    {
      "epoch": 0.0936768149882904,
      "eval_loss": 1.3997441530227661,
      "eval_runtime": 15.9123,
      "eval_samples_per_second": 2.828,
      "eval_steps_per_second": 1.445,
      "step": 10
    },
    {
      "epoch": 0.11241217798594848,
      "grad_norm": 2.0864598751068115,
      "learning_rate": 8.18711994874345e-05,
      "loss": 5.2922,
      "step": 12
    },
    {
      "epoch": 0.1405152224824356,
      "grad_norm": 2.491011619567871,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.0416,
      "step": 15
    },
    {
      "epoch": 0.1405152224824356,
      "eval_loss": 1.2667834758758545,
      "eval_runtime": 15.8816,
      "eval_samples_per_second": 2.833,
      "eval_steps_per_second": 1.448,
      "step": 15
    },
    {
      "epoch": 0.1686182669789227,
      "grad_norm": 2.8564693927764893,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 4.7651,
      "step": 18
    },
    {
      "epoch": 0.1873536299765808,
      "eval_loss": 1.214084267616272,
      "eval_runtime": 15.8452,
      "eval_samples_per_second": 2.84,
      "eval_steps_per_second": 1.452,
      "step": 20
    },
    {
      "epoch": 0.19672131147540983,
      "grad_norm": 2.2935969829559326,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 4.7574,
      "step": 21
    },
    {
      "epoch": 0.22482435597189696,
      "grad_norm": 2.7670748233795166,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 4.8248,
      "step": 24
    },
    {
      "epoch": 0.234192037470726,
      "eval_loss": 1.2001515626907349,
      "eval_runtime": 15.9259,
      "eval_samples_per_second": 2.826,
      "eval_steps_per_second": 1.444,
      "step": 25
    },
    {
      "epoch": 0.2529274004683841,
      "grad_norm": 2.2447752952575684,
      "learning_rate": 3.511175705587433e-06,
      "loss": 4.5805,
      "step": 27
    },
    {
      "epoch": 0.2810304449648712,
      "grad_norm": 2.4564874172210693,
      "learning_rate": 0.0,
      "loss": 4.534,
      "step": 30
    },
    {
      "epoch": 0.2810304449648712,
      "eval_loss": 1.1973159313201904,
      "eval_runtime": 15.9572,
      "eval_samples_per_second": 2.82,
      "eval_steps_per_second": 1.441,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": 3.77252109877248e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}