checkpoint-60/trainer_state.json

{
  "best_metric": 0.039548490196466446,
  "best_model_checkpoint": "autotrain-oaqu7-o86bm/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,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.071,
      "step": 3
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.7486,
      "step": 6
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.5e-05,
      "loss": 0.6061,
      "step": 9
    },
    {
      "epoch": 0.2,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4679,
      "step": 12
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.6043,
      "step": 15
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 0.3619,
      "step": 18
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.9074074074074075e-05,
      "loss": 0.2092,
      "step": 21
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.814814814814815e-05,
      "loss": 0.2621,
      "step": 24
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.1716,
      "step": 27
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.62962962962963e-05,
      "loss": 0.2724,
      "step": 30
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.5370370370370374e-05,
      "loss": 0.2802,
      "step": 33
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.2865,
      "step": 36
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.351851851851852e-05,
      "loss": 0.2598,
      "step": 39
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.259259259259259e-05,
      "loss": 0.0421,
      "step": 42
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.2537,
      "step": 45
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.6034,
      "step": 48
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.981481481481482e-05,
      "loss": 0.0151,
      "step": 51
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.0803,
      "step": 54
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.7962962962962964e-05,
      "loss": 0.4133,
      "step": 57
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.2113,
      "step": 60
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9916666666666667,
      "eval_auc": 0.9991376832423111,
      "eval_f1": 0.9896907216494846,
      "eval_loss": 0.039548490196466446,
      "eval_precision": 1.0,
      "eval_recall": 0.9795918367346939,
      "eval_runtime": 67.072,
      "eval_samples_per_second": 1.789,
      "eval_steps_per_second": 0.119,
      "step": 60
    }
  ],
  "logging_steps": 3,
  "max_steps": 180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3.74491755901993e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}