last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.00027038719446247024,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7038719446247027e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 2.7038719446247027e-05,
      "eval_loss": NaN,
      "eval_runtime": 1251.5377,
      "eval_samples_per_second": 12.443,
      "eval_steps_per_second": 6.222,
      "step": 1
    },
    {
      "epoch": 5.4077438892494055e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 8.111615833874107e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00010815487778498811,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00013519359723123512,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00013519359723123512,
      "eval_loss": NaN,
      "eval_runtime": 1250.0463,
      "eval_samples_per_second": 12.458,
      "eval_steps_per_second": 6.229,
      "step": 5
    },
    {
      "epoch": 0.00016223231667748214,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00018927103612372917,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00021630975556997622,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.9387,
      "step": 8
    },
    {
      "epoch": 0.00024334847501622324,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00027038719446247024,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00027038719446247024,
      "eval_loss": NaN,
      "eval_runtime": 1245.3497,
      "eval_samples_per_second": 12.505,
      "eval_steps_per_second": 6.253,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 766287626108928.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}