last-checkpoint/trainer_state.json

{
  "best_metric": 1.8473726511001587,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0713436385255648,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023781212841854932,
      "eval_loss": 2.905052661895752,
      "eval_runtime": 4.7108,
      "eval_samples_per_second": 37.786,
      "eval_steps_per_second": 18.893,
      "step": 1
    },
    {
      "epoch": 0.007134363852556481,
      "grad_norm": 3.7379939556121826,
      "learning_rate": 0.00012,
      "loss": 2.9411,
      "step": 3
    },
    {
      "epoch": 0.011890606420927468,
      "eval_loss": 2.6086349487304688,
      "eval_runtime": 4.8398,
      "eval_samples_per_second": 36.779,
      "eval_steps_per_second": 18.389,
      "step": 5
    },
    {
      "epoch": 0.014268727705112961,
      "grad_norm": 2.683621644973755,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.6841,
      "step": 6
    },
    {
      "epoch": 0.02140309155766944,
      "grad_norm": 3.3652477264404297,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.3553,
      "step": 9
    },
    {
      "epoch": 0.023781212841854936,
      "eval_loss": 2.244985580444336,
      "eval_runtime": 4.7104,
      "eval_samples_per_second": 37.789,
      "eval_steps_per_second": 18.894,
      "step": 10
    },
    {
      "epoch": 0.028537455410225922,
      "grad_norm": 3.0050437450408936,
      "learning_rate": 0.000163742398974869,
      "loss": 2.2602,
      "step": 12
    },
    {
      "epoch": 0.0356718192627824,
      "grad_norm": 2.746276617050171,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.1064,
      "step": 15
    },
    {
      "epoch": 0.0356718192627824,
      "eval_loss": 2.0495896339416504,
      "eval_runtime": 4.977,
      "eval_samples_per_second": 35.764,
      "eval_steps_per_second": 17.882,
      "step": 15
    },
    {
      "epoch": 0.04280618311533888,
      "grad_norm": 2.704167127609253,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.1799,
      "step": 18
    },
    {
      "epoch": 0.04756242568370987,
      "eval_loss": 1.9199856519699097,
      "eval_runtime": 4.7375,
      "eval_samples_per_second": 37.573,
      "eval_steps_per_second": 18.786,
      "step": 20
    },
    {
      "epoch": 0.04994054696789536,
      "grad_norm": 2.961555242538452,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.9746,
      "step": 21
    },
    {
      "epoch": 0.057074910820451845,
      "grad_norm": 2.0701985359191895,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.9017,
      "step": 24
    },
    {
      "epoch": 0.059453032104637336,
      "eval_loss": 1.8603113889694214,
      "eval_runtime": 4.8901,
      "eval_samples_per_second": 36.4,
      "eval_steps_per_second": 18.2,
      "step": 25
    },
    {
      "epoch": 0.06420927467300833,
      "grad_norm": 2.001005172729492,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.8412,
      "step": 27
    },
    {
      "epoch": 0.0713436385255648,
      "grad_norm": 2.62384033203125,
      "learning_rate": 0.0,
      "loss": 1.7613,
      "step": 30
    },
    {
      "epoch": 0.0713436385255648,
      "eval_loss": 1.8473726511001587,
      "eval_runtime": 4.7303,
      "eval_samples_per_second": 37.629,
      "eval_steps_per_second": 18.815,
      "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": 540715725619200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}