last-checkpoint/trainer_state.json

{
  "best_metric": 11.919669151306152,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0050729232720355105,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001690974424011837,
      "eval_loss": 11.938138961791992,
      "eval_runtime": 63.3507,
      "eval_samples_per_second": 39.305,
      "eval_steps_per_second": 19.653,
      "step": 1
    },
    {
      "epoch": 0.000507292327203551,
      "grad_norm": 0.1530068963766098,
      "learning_rate": 0.00012,
      "loss": 11.9354,
      "step": 3
    },
    {
      "epoch": 0.0008454872120059184,
      "eval_loss": 11.936454772949219,
      "eval_runtime": 63.4003,
      "eval_samples_per_second": 39.274,
      "eval_steps_per_second": 19.637,
      "step": 5
    },
    {
      "epoch": 0.001014584654407102,
      "grad_norm": 0.2502671182155609,
      "learning_rate": 0.0001992114701314478,
      "loss": 11.9346,
      "step": 6
    },
    {
      "epoch": 0.0015218769816106531,
      "grad_norm": 0.17158111929893494,
      "learning_rate": 0.00018763066800438636,
      "loss": 11.9326,
      "step": 9
    },
    {
      "epoch": 0.0016909744240118367,
      "eval_loss": 11.931650161743164,
      "eval_runtime": 63.4677,
      "eval_samples_per_second": 39.233,
      "eval_steps_per_second": 19.616,
      "step": 10
    },
    {
      "epoch": 0.002029169308814204,
      "grad_norm": 0.16513514518737793,
      "learning_rate": 0.000163742398974869,
      "loss": 11.9352,
      "step": 12
    },
    {
      "epoch": 0.0025364616360177552,
      "grad_norm": 0.19673532247543335,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.9258,
      "step": 15
    },
    {
      "epoch": 0.0025364616360177552,
      "eval_loss": 11.926512718200684,
      "eval_runtime": 63.4061,
      "eval_samples_per_second": 39.271,
      "eval_steps_per_second": 19.635,
      "step": 15
    },
    {
      "epoch": 0.0030437539632213063,
      "grad_norm": 0.20807549357414246,
      "learning_rate": 9.372094804706867e-05,
      "loss": 11.9276,
      "step": 18
    },
    {
      "epoch": 0.0033819488480236735,
      "eval_loss": 11.922327995300293,
      "eval_runtime": 63.5327,
      "eval_samples_per_second": 39.192,
      "eval_steps_per_second": 19.596,
      "step": 20
    },
    {
      "epoch": 0.0035510462904248573,
      "grad_norm": 0.2239098697900772,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 11.9274,
      "step": 21
    },
    {
      "epoch": 0.004058338617628408,
      "grad_norm": 0.2766207754611969,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 11.9269,
      "step": 24
    },
    {
      "epoch": 0.004227436060029592,
      "eval_loss": 11.920109748840332,
      "eval_runtime": 63.4878,
      "eval_samples_per_second": 39.22,
      "eval_steps_per_second": 19.61,
      "step": 25
    },
    {
      "epoch": 0.004565630944831959,
      "grad_norm": 0.28358063101768494,
      "learning_rate": 7.022351411174866e-06,
      "loss": 11.9232,
      "step": 27
    },
    {
      "epoch": 0.0050729232720355105,
      "grad_norm": 0.2541441321372986,
      "learning_rate": 0.0,
      "loss": 11.9231,
      "step": 30
    },
    {
      "epoch": 0.0050729232720355105,
      "eval_loss": 11.919669151306152,
      "eval_runtime": 63.5352,
      "eval_samples_per_second": 39.191,
      "eval_steps_per_second": 19.595,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9648303243264.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}