checkpoint-60/trainer_state.json

{
  "best_metric": 0.4916948974132538,
  "best_model_checkpoint": "autotrain-57208-4mv8z/checkpoint-60",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 0.9702,
      "step": 3
    },
    {
      "epoch": 0.1,
      "grad_norm": 25.49532699584961,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.7682,
      "step": 6
    },
    {
      "epoch": 0.15,
      "grad_norm": 36.088096618652344,
      "learning_rate": 1.388888888888889e-05,
      "loss": 1.1279,
      "step": 9
    },
    {
      "epoch": 0.2,
      "grad_norm": 42.65789031982422,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 1.2649,
      "step": 12
    },
    {
      "epoch": 0.25,
      "grad_norm": 13.15088176727295,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.7979,
      "step": 15
    },
    {
      "epoch": 0.3,
      "grad_norm": 26.759204864501953,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.6888,
      "step": 18
    },
    {
      "epoch": 0.35,
      "grad_norm": 23.444761276245117,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.7643,
      "step": 21
    },
    {
      "epoch": 0.4,
      "grad_norm": 46.247528076171875,
      "learning_rate": 4.938271604938271e-05,
      "loss": 0.6103,
      "step": 24
    },
    {
      "epoch": 0.45,
      "grad_norm": 18.17511749267578,
      "learning_rate": 4.845679012345679e-05,
      "loss": 1.2048,
      "step": 27
    },
    {
      "epoch": 0.5,
      "grad_norm": 12.499485969543457,
      "learning_rate": 4.7530864197530866e-05,
      "loss": 0.5038,
      "step": 30
    },
    {
      "epoch": 0.55,
      "grad_norm": 14.672439575195312,
      "learning_rate": 4.6604938271604945e-05,
      "loss": 0.7822,
      "step": 33
    },
    {
      "epoch": 0.6,
      "grad_norm": 13.163423538208008,
      "learning_rate": 4.567901234567901e-05,
      "loss": 0.5031,
      "step": 36
    },
    {
      "epoch": 0.65,
      "grad_norm": 21.604719161987305,
      "learning_rate": 4.4753086419753084e-05,
      "loss": 0.5332,
      "step": 39
    },
    {
      "epoch": 0.7,
      "grad_norm": 26.531099319458008,
      "learning_rate": 4.3827160493827164e-05,
      "loss": 0.5944,
      "step": 42
    },
    {
      "epoch": 0.75,
      "grad_norm": 7.5323615074157715,
      "learning_rate": 4.290123456790124e-05,
      "loss": 0.6344,
      "step": 45
    },
    {
      "epoch": 0.8,
      "grad_norm": 7.045075416564941,
      "learning_rate": 4.197530864197531e-05,
      "loss": 0.5561,
      "step": 48
    },
    {
      "epoch": 0.85,
      "grad_norm": 19.56390953063965,
      "learning_rate": 4.104938271604938e-05,
      "loss": 0.7812,
      "step": 51
    },
    {
      "epoch": 0.9,
      "grad_norm": 9.734304428100586,
      "learning_rate": 4.012345679012346e-05,
      "loss": 0.7483,
      "step": 54
    },
    {
      "epoch": 0.95,
      "grad_norm": 13.189071655273438,
      "learning_rate": 3.9197530864197535e-05,
      "loss": 0.6367,
      "step": 57
    },
    {
      "epoch": 1.0,
      "grad_norm": 4.375649929046631,
      "learning_rate": 3.82716049382716e-05,
      "loss": 0.5642,
      "step": 60
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7833333333333333,
      "eval_auc": 0.8416783216783217,
      "eval_f1": 0.8059701492537313,
      "eval_loss": 0.4916948974132538,
      "eval_precision": 0.782608695652174,
      "eval_recall": 0.8307692307692308,
      "eval_runtime": 0.2902,
      "eval_samples_per_second": 413.471,
      "eval_steps_per_second": 27.565,
      "step": 60
    }
  ],
  "logging_steps": 3,
  "max_steps": 180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 31310215587840.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}