last-checkpoint/trainer_state.json

{
  "best_metric": 0.0012022015871480107,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.3876720294630742,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007753440589261484,
      "eval_loss": 0.5509790182113647,
      "eval_runtime": 124.9083,
      "eval_samples_per_second": 17.397,
      "eval_steps_per_second": 4.355,
      "step": 1
    },
    {
      "epoch": 0.03876720294630742,
      "grad_norm": 57.208030700683594,
      "learning_rate": 0.0001085,
      "loss": 8.8377,
      "step": 50
    },
    {
      "epoch": 0.07753440589261484,
      "grad_norm": 50.1111946105957,
      "learning_rate": 0.000217,
      "loss": 1.944,
      "step": 100
    },
    {
      "epoch": 0.11630160883892227,
      "grad_norm": 48.036537170410156,
      "learning_rate": 0.0002087409292774746,
      "loss": 0.5307,
      "step": 150
    },
    {
      "epoch": 0.1550688117852297,
      "grad_norm": 7.461704254150391,
      "learning_rate": 0.0001852210857587404,
      "loss": 0.2826,
      "step": 200
    },
    {
      "epoch": 0.1938360147315371,
      "grad_norm": 17.702455520629883,
      "learning_rate": 0.00015002115241161224,
      "loss": 0.2013,
      "step": 250
    },
    {
      "epoch": 0.23260321767784453,
      "grad_norm": 16.163862228393555,
      "learning_rate": 0.0001085,
      "loss": 0.1545,
      "step": 300
    },
    {
      "epoch": 0.27137042062415195,
      "grad_norm": 30.95184898376465,
      "learning_rate": 6.697884758838776e-05,
      "loss": 0.1242,
      "step": 350
    },
    {
      "epoch": 0.3101376235704594,
      "grad_norm": 6.224905490875244,
      "learning_rate": 3.17789142412596e-05,
      "loss": 0.0839,
      "step": 400
    },
    {
      "epoch": 0.3489048265167668,
      "grad_norm": 18.724435806274414,
      "learning_rate": 8.259070722525389e-06,
      "loss": 0.054,
      "step": 450
    },
    {
      "epoch": 0.3876720294630742,
      "grad_norm": 5.79263973236084,
      "learning_rate": 0.0,
      "loss": 0.0668,
      "step": 500
    },
    {
      "epoch": 0.3876720294630742,
      "eval_loss": 0.0012022015871480107,
      "eval_runtime": 125.0541,
      "eval_samples_per_second": 17.376,
      "eval_steps_per_second": 4.35,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "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": 3.062452043340841e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}