checkpoint-450/trainer_state.json

{
  "best_metric": 0.03989905118942261,
  "best_model_checkpoint": "klimacoder-v0-2-1/checkpoint-450",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 1.1921207904815674,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.6855,
      "step": 25
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.5017459392547607,
      "learning_rate": 4.938271604938271e-05,
      "loss": 0.54,
      "step": 50
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.509257435798645,
      "learning_rate": 4.654320987654321e-05,
      "loss": 0.2217,
      "step": 75
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.20545396208763123,
      "learning_rate": 4.345679012345679e-05,
      "loss": 0.1143,
      "step": 100
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": Infinity,
      "learning_rate": 4.049382716049383e-05,
      "loss": 0.0751,
      "step": 125
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.169285848736763,
      "learning_rate": 3.740740740740741e-05,
      "loss": 0.0866,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9808013355592654,
      "eval_auc": 0.9981018215266262,
      "eval_f1": 0.9805249788314987,
      "eval_loss": 0.0736752524971962,
      "eval_precision": 0.9846938775510204,
      "eval_recall": 0.9763912310286678,
      "eval_runtime": 0.5963,
      "eval_samples_per_second": 2009.125,
      "eval_steps_per_second": 31.864,
      "step": 150
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 0.08550403267145157,
      "learning_rate": 3.432098765432099e-05,
      "loss": 0.0503,
      "step": 175
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.06706776469945908,
      "learning_rate": 3.123456790123457e-05,
      "loss": 0.0723,
      "step": 200
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.05572424456477165,
      "learning_rate": 2.814814814814815e-05,
      "loss": 0.0235,
      "step": 225
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.062113117426633835,
      "learning_rate": 2.5061728395061727e-05,
      "loss": 0.0877,
      "step": 250
    },
    {
      "epoch": 1.8333333333333335,
      "grad_norm": 0.0703682079911232,
      "learning_rate": 2.1975308641975308e-05,
      "loss": 0.0646,
      "step": 275
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.333071708679199,
      "learning_rate": 1.888888888888889e-05,
      "loss": 0.0631,
      "step": 300
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9874791318864775,
      "eval_auc": 0.9970370576839993,
      "eval_f1": 0.9872988992379339,
      "eval_loss": 0.05900123342871666,
      "eval_precision": 0.9914965986394558,
      "eval_recall": 0.9831365935919055,
      "eval_runtime": 0.5975,
      "eval_samples_per_second": 2005.175,
      "eval_steps_per_second": 31.802,
      "step": 300
    },
    {
      "epoch": 2.1666666666666665,
      "grad_norm": 0.05191728472709656,
      "learning_rate": 1.580246913580247e-05,
      "loss": 0.0645,
      "step": 325
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.05018889531493187,
      "learning_rate": 1.2716049382716049e-05,
      "loss": 0.068,
      "step": 350
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.04393320530653,
      "learning_rate": 9.62962962962963e-06,
      "loss": 0.0364,
      "step": 375
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.044134195894002914,
      "learning_rate": 6.54320987654321e-06,
      "loss": 0.0387,
      "step": 400
    },
    {
      "epoch": 2.8333333333333335,
      "grad_norm": 1.5181336402893066,
      "learning_rate": 3.45679012345679e-06,
      "loss": 0.0128,
      "step": 425
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.045596569776535034,
      "learning_rate": 3.703703703703704e-07,
      "loss": 0.0285,
      "step": 450
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9908180300500835,
      "eval_auc": 0.9993268574136274,
      "eval_f1": 0.9907016060862215,
      "eval_loss": 0.03989905118942261,
      "eval_precision": 0.9932203389830508,
      "eval_recall": 0.9881956155143339,
      "eval_runtime": 0.6094,
      "eval_samples_per_second": 1965.953,
      "eval_steps_per_second": 31.18,
      "step": 450
    }
  ],
  "logging_steps": 25,
  "max_steps": 450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "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": 947199814926336.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}