last-checkpoint/trainer_state.json

{
  "best_metric": 0.4316163659095764,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.9562514941429596,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019125029882859192,
      "eval_loss": 0.8754523992538452,
      "eval_runtime": 49.0819,
      "eval_samples_per_second": 17.95,
      "eval_steps_per_second": 4.503,
      "step": 1
    },
    {
      "epoch": 0.09562514941429597,
      "grad_norm": 28.803590774536133,
      "learning_rate": 0.0001015,
      "loss": 10.3733,
      "step": 50
    },
    {
      "epoch": 0.19125029882859193,
      "grad_norm": 26.106788635253906,
      "learning_rate": 0.000203,
      "loss": 5.1132,
      "step": 100
    },
    {
      "epoch": 0.28687544824288785,
      "grad_norm": 19.607568740844727,
      "learning_rate": 0.0001952737725498956,
      "loss": 4.5551,
      "step": 150
    },
    {
      "epoch": 0.38250059765718386,
      "grad_norm": 19.669126510620117,
      "learning_rate": 0.00017327133829043458,
      "loss": 4.4034,
      "step": 200
    },
    {
      "epoch": 0.4781257470714798,
      "grad_norm": 14.908707618713379,
      "learning_rate": 0.00014034236838505662,
      "loss": 4.1202,
      "step": 250
    },
    {
      "epoch": 0.5737508964857757,
      "grad_norm": 22.670669555664062,
      "learning_rate": 0.0001015,
      "loss": 3.9898,
      "step": 300
    },
    {
      "epoch": 0.6693760459000717,
      "grad_norm": 15.043886184692383,
      "learning_rate": 6.265763161494339e-05,
      "loss": 3.9196,
      "step": 350
    },
    {
      "epoch": 0.7650011953143677,
      "grad_norm": 14.02161693572998,
      "learning_rate": 2.972866170956543e-05,
      "loss": 3.8365,
      "step": 400
    },
    {
      "epoch": 0.8606263447286636,
      "grad_norm": 18.380149841308594,
      "learning_rate": 7.726227450104397e-06,
      "loss": 3.9378,
      "step": 450
    },
    {
      "epoch": 0.9562514941429596,
      "grad_norm": 18.12775421142578,
      "learning_rate": 0.0,
      "loss": 4.0012,
      "step": 500
    },
    {
      "epoch": 0.9562514941429596,
      "eval_loss": 0.4316163659095764,
      "eval_runtime": 49.3355,
      "eval_samples_per_second": 17.857,
      "eval_steps_per_second": 4.48,
      "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": 2.972530438821642e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}