last-checkpoint/trainer_state.json

{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.1529110440001529,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003058220880003058,
      "eval_loss": 11.5,
      "eval_runtime": 36.9905,
      "eval_samples_per_second": 148.903,
      "eval_steps_per_second": 37.226,
      "step": 1
    },
    {
      "epoch": 0.015291104400015292,
      "grad_norm": 0.0004992752219550312,
      "learning_rate": 0.000107,
      "loss": 92.0,
      "step": 50
    },
    {
      "epoch": 0.030582208800030583,
      "grad_norm": 0.0018408223986625671,
      "learning_rate": 0.000214,
      "loss": 92.0,
      "step": 100
    },
    {
      "epoch": 0.045873313200045875,
      "grad_norm": 0.002780839102342725,
      "learning_rate": 0.0002058551099787077,
      "loss": 92.0,
      "step": 150
    },
    {
      "epoch": 0.061164417600061166,
      "grad_norm": 0.006299033761024475,
      "learning_rate": 0.00018266042558696057,
      "loss": 92.0,
      "step": 200
    },
    {
      "epoch": 0.07645552200007645,
      "grad_norm": 0.009835680015385151,
      "learning_rate": 0.00014794712726306461,
      "loss": 92.0,
      "step": 250
    },
    {
      "epoch": 0.09174662640009175,
      "grad_norm": 0.010252038948237896,
      "learning_rate": 0.000107,
      "loss": 92.0,
      "step": 300
    },
    {
      "epoch": 0.10703773080010703,
      "grad_norm": 0.007084604352712631,
      "learning_rate": 6.60528727369354e-05,
      "loss": 92.0,
      "step": 350
    },
    {
      "epoch": 0.12232883520012233,
      "grad_norm": 0.0059821694158017635,
      "learning_rate": 3.1339574413039424e-05,
      "loss": 92.0,
      "step": 400
    },
    {
      "epoch": 0.13761993960013763,
      "grad_norm": 0.007614255882799625,
      "learning_rate": 8.14489002129232e-06,
      "loss": 92.0,
      "step": 450
    },
    {
      "epoch": 0.1529110440001529,
      "grad_norm": 0.011491325683891773,
      "learning_rate": 0.0,
      "loss": 92.0,
      "step": 500
    },
    {
      "epoch": 0.1529110440001529,
      "eval_loss": 11.5,
      "eval_runtime": 38.4491,
      "eval_samples_per_second": 143.254,
      "eval_steps_per_second": 35.814,
      "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": 80416255967232.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}