last-checkpoint/trainer_state.json

{
  "best_metric": 2.5102765560150146,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.007979253939756632,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007979253939756633,
      "grad_norm": 2.8758528232574463,
      "learning_rate": 2e-05,
      "loss": 3.5275,
      "step": 1
    },
    {
      "epoch": 0.0007979253939756633,
      "eval_loss": 3.5597481727600098,
      "eval_runtime": 112.8506,
      "eval_samples_per_second": 4.679,
      "eval_steps_per_second": 2.339,
      "step": 1
    },
    {
      "epoch": 0.0015958507879513266,
      "grad_norm": 2.3059797286987305,
      "learning_rate": 4e-05,
      "loss": 3.7981,
      "step": 2
    },
    {
      "epoch": 0.0023937761819269898,
      "grad_norm": 2.3253207206726074,
      "learning_rate": 6e-05,
      "loss": 3.4762,
      "step": 3
    },
    {
      "epoch": 0.003191701575902653,
      "grad_norm": 3.0633058547973633,
      "learning_rate": 8e-05,
      "loss": 4.314,
      "step": 4
    },
    {
      "epoch": 0.003989626969878316,
      "grad_norm": 2.5281550884246826,
      "learning_rate": 0.0001,
      "loss": 3.6369,
      "step": 5
    },
    {
      "epoch": 0.003989626969878316,
      "eval_loss": 3.4488863945007324,
      "eval_runtime": 113.3494,
      "eval_samples_per_second": 4.658,
      "eval_steps_per_second": 2.329,
      "step": 5
    },
    {
      "epoch": 0.0047875523638539795,
      "grad_norm": 2.609208822250366,
      "learning_rate": 0.00012,
      "loss": 3.4644,
      "step": 6
    },
    {
      "epoch": 0.005585477757829643,
      "grad_norm": 3.4844303131103516,
      "learning_rate": 0.00014,
      "loss": 3.608,
      "step": 7
    },
    {
      "epoch": 0.006383403151805306,
      "grad_norm": 4.003000736236572,
      "learning_rate": 0.00016,
      "loss": 3.1775,
      "step": 8
    },
    {
      "epoch": 0.00718132854578097,
      "grad_norm": 2.684307813644409,
      "learning_rate": 0.00018,
      "loss": 2.7451,
      "step": 9
    },
    {
      "epoch": 0.007979253939756632,
      "grad_norm": 3.117142677307129,
      "learning_rate": 0.0002,
      "loss": 2.7653,
      "step": 10
    },
    {
      "epoch": 0.007979253939756632,
      "eval_loss": 2.5102765560150146,
      "eval_runtime": 112.4497,
      "eval_samples_per_second": 4.695,
      "eval_steps_per_second": 2.348,
      "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": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}