last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.33613445378151263,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03361344537815126,
      "eval_loss": NaN,
      "eval_runtime": 1.9986,
      "eval_samples_per_second": 6.505,
      "eval_steps_per_second": 3.502,
      "step": 1
    },
    {
      "epoch": 0.10084033613445378,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.16806722689075632,
      "eval_loss": NaN,
      "eval_runtime": 1.5284,
      "eval_samples_per_second": 8.506,
      "eval_steps_per_second": 4.58,
      "step": 5
    },
    {
      "epoch": 0.20168067226890757,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.3025210084033613,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.33613445378151263,
      "eval_loss": NaN,
      "eval_runtime": 1.5332,
      "eval_samples_per_second": 8.479,
      "eval_steps_per_second": 4.566,
      "step": 10
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3547400723496960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}