last-checkpoint/trainer_state.json

{
  "best_metric": 0.9219593405723572,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.00020726355115005364,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0726355115005362e-05,
      "grad_norm": 4.606229305267334,
      "learning_rate": 2e-05,
      "loss": 6.4285,
      "step": 1
    },
    {
      "epoch": 2.0726355115005362e-05,
      "eval_loss": 1.386435627937317,
      "eval_runtime": 3680.0393,
      "eval_samples_per_second": 5.52,
      "eval_steps_per_second": 2.76,
      "step": 1
    },
    {
      "epoch": 4.1452710230010724e-05,
      "grad_norm": 3.1252923011779785,
      "learning_rate": 4e-05,
      "loss": 3.6875,
      "step": 2
    },
    {
      "epoch": 6.217906534501609e-05,
      "grad_norm": 5.3452863693237305,
      "learning_rate": 6e-05,
      "loss": 9.747,
      "step": 3
    },
    {
      "epoch": 8.290542046002145e-05,
      "grad_norm": 3.473754644393921,
      "learning_rate": 8e-05,
      "loss": 4.0488,
      "step": 4
    },
    {
      "epoch": 0.00010363177557502682,
      "grad_norm": 5.435574531555176,
      "learning_rate": 0.0001,
      "loss": 6.2278,
      "step": 5
    },
    {
      "epoch": 0.00010363177557502682,
      "eval_loss": 1.3445682525634766,
      "eval_runtime": 3632.6364,
      "eval_samples_per_second": 5.592,
      "eval_steps_per_second": 2.796,
      "step": 5
    },
    {
      "epoch": 0.00012435813069003218,
      "grad_norm": 3.7246408462524414,
      "learning_rate": 0.00012,
      "loss": 3.9211,
      "step": 6
    },
    {
      "epoch": 0.00014508448580503755,
      "grad_norm": 7.678606986999512,
      "learning_rate": 0.00014,
      "loss": 8.467,
      "step": 7
    },
    {
      "epoch": 0.0001658108409200429,
      "grad_norm": 5.895946979522705,
      "learning_rate": 0.00016,
      "loss": 5.3675,
      "step": 8
    },
    {
      "epoch": 0.00018653719603504827,
      "grad_norm": 3.4130988121032715,
      "learning_rate": 0.00018,
      "loss": 2.225,
      "step": 9
    },
    {
      "epoch": 0.00020726355115005364,
      "grad_norm": 2.9022064208984375,
      "learning_rate": 0.0002,
      "loss": 1.891,
      "step": 10
    },
    {
      "epoch": 0.00020726355115005364,
      "eval_loss": 0.9219593405723572,
      "eval_runtime": 3715.7051,
      "eval_samples_per_second": 5.467,
      "eval_steps_per_second": 2.734,
      "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": 1628749242040320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}