last-checkpoint/trainer_state.json

{
  "best_metric": 1.6954796314239502,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0006599571027883187,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.299785513941594e-05,
      "eval_loss": 2.1430368423461914,
      "eval_runtime": 4869.9022,
      "eval_samples_per_second": 5.24,
      "eval_steps_per_second": 1.31,
      "step": 1
    },
    {
      "epoch": 9.899356541824782e-05,
      "grad_norm": 0.883987307548523,
      "learning_rate": 0.00012,
      "loss": 7.0041,
      "step": 3
    },
    {
      "epoch": 0.00016498927569707968,
      "eval_loss": 2.0103447437286377,
      "eval_runtime": 4901.016,
      "eval_samples_per_second": 5.207,
      "eval_steps_per_second": 1.302,
      "step": 5
    },
    {
      "epoch": 0.00019798713083649564,
      "grad_norm": 1.0903679132461548,
      "learning_rate": 0.0001992114701314478,
      "loss": 6.6501,
      "step": 6
    },
    {
      "epoch": 0.00029698069625474344,
      "grad_norm": 1.8503755331039429,
      "learning_rate": 0.00018763066800438636,
      "loss": 6.7415,
      "step": 9
    },
    {
      "epoch": 0.00032997855139415937,
      "eval_loss": 1.7760616540908813,
      "eval_runtime": 4901.0887,
      "eval_samples_per_second": 5.207,
      "eval_steps_per_second": 1.302,
      "step": 10
    },
    {
      "epoch": 0.00039597426167299127,
      "grad_norm": 1.2617883682250977,
      "learning_rate": 0.000163742398974869,
      "loss": 6.3922,
      "step": 12
    },
    {
      "epoch": 0.000494967827091239,
      "grad_norm": 1.170369029045105,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.6538,
      "step": 15
    },
    {
      "epoch": 0.000494967827091239,
      "eval_loss": 1.716353178024292,
      "eval_runtime": 4910.0447,
      "eval_samples_per_second": 5.198,
      "eval_steps_per_second": 1.299,
      "step": 15
    },
    {
      "epoch": 0.0005939613925094869,
      "grad_norm": 1.3879562616348267,
      "learning_rate": 9.372094804706867e-05,
      "loss": 6.4795,
      "step": 18
    },
    {
      "epoch": 0.0006599571027883187,
      "eval_loss": 1.6954796314239502,
      "eval_runtime": 4905.6933,
      "eval_samples_per_second": 5.202,
      "eval_steps_per_second": 1.301,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.95172220911616e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}