last-checkpoint/trainer_state.json

{
  "best_metric": 2.1078147888183594,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.08522727272727272,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005681818181818182,
      "eval_loss": 6.134354591369629,
      "eval_runtime": 47.1556,
      "eval_samples_per_second": 15.714,
      "eval_steps_per_second": 3.944,
      "step": 1
    },
    {
      "epoch": 0.005681818181818182,
      "grad_norm": 10.32190227508545,
      "learning_rate": 5.05e-06,
      "loss": 4.6056,
      "step": 10
    },
    {
      "epoch": 0.011363636363636364,
      "grad_norm": 8.61007022857666,
      "learning_rate": 1.01e-05,
      "loss": 4.191,
      "step": 20
    },
    {
      "epoch": 0.017045454545454544,
      "grad_norm": 8.55370044708252,
      "learning_rate": 9.323076923076924e-06,
      "loss": 3.2708,
      "step": 30
    },
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 8.809952735900879,
      "learning_rate": 8.546153846153847e-06,
      "loss": 2.3297,
      "step": 40
    },
    {
      "epoch": 0.028409090909090908,
      "grad_norm": 19.515151977539062,
      "learning_rate": 7.76923076923077e-06,
      "loss": 1.6582,
      "step": 50
    },
    {
      "epoch": 0.028409090909090908,
      "eval_loss": 2.4909262657165527,
      "eval_runtime": 47.5356,
      "eval_samples_per_second": 15.588,
      "eval_steps_per_second": 3.913,
      "step": 50
    },
    {
      "epoch": 0.03409090909090909,
      "grad_norm": 6.00586462020874,
      "learning_rate": 6.992307692307692e-06,
      "loss": 2.9064,
      "step": 60
    },
    {
      "epoch": 0.03977272727272727,
      "grad_norm": 6.616552352905273,
      "learning_rate": 6.215384615384615e-06,
      "loss": 2.5966,
      "step": 70
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 7.654419898986816,
      "learning_rate": 5.438461538461538e-06,
      "loss": 2.2871,
      "step": 80
    },
    {
      "epoch": 0.05113636363636364,
      "grad_norm": 6.925200939178467,
      "learning_rate": 4.661538461538462e-06,
      "loss": 1.8554,
      "step": 90
    },
    {
      "epoch": 0.056818181818181816,
      "grad_norm": 13.769781112670898,
      "learning_rate": 3.884615384615385e-06,
      "loss": 1.2905,
      "step": 100
    },
    {
      "epoch": 0.056818181818181816,
      "eval_loss": 2.180443048477173,
      "eval_runtime": 47.2352,
      "eval_samples_per_second": 15.687,
      "eval_steps_per_second": 3.938,
      "step": 100
    },
    {
      "epoch": 0.0625,
      "grad_norm": 6.1928181648254395,
      "learning_rate": 3.1076923076923076e-06,
      "loss": 2.8003,
      "step": 110
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 6.664099216461182,
      "learning_rate": 2.330769230769231e-06,
      "loss": 2.417,
      "step": 120
    },
    {
      "epoch": 0.07386363636363637,
      "grad_norm": 7.768091201782227,
      "learning_rate": 1.5538461538461538e-06,
      "loss": 1.9968,
      "step": 130
    },
    {
      "epoch": 0.07954545454545454,
      "grad_norm": 10.426623344421387,
      "learning_rate": 7.769230769230769e-07,
      "loss": 1.6976,
      "step": 140
    },
    {
      "epoch": 0.08522727272727272,
      "grad_norm": 14.00831413269043,
      "learning_rate": 0.0,
      "loss": 1.2394,
      "step": 150
    },
    {
      "epoch": 0.08522727272727272,
      "eval_loss": 2.1078147888183594,
      "eval_runtime": 47.3252,
      "eval_samples_per_second": 15.658,
      "eval_steps_per_second": 3.93,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.979554657914061e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}