trainer_state.json

{
  "best_metric": 0.03221152722835541,
  "best_model_checkpoint": "/mounts/work/akoksal/earthquake_anon_models/checkpoint-96",
  "epoch": 5.0,
  "global_step": 240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.301,
      "step": 48
    },
    {
      "epoch": 1.0,
      "eval_ad_f1": 0.8044280442804429,
      "eval_ad_precision": 0.7315436241610739,
      "eval_ad_recall": 0.8934426229508197,
      "eval_ad_support": 122,
      "eval_loss": 0.03607584163546562,
      "eval_overall_accuracy": 0.9892580067634772,
      "eval_overall_f1": 0.8044280442804429,
      "eval_overall_precision": 0.7315436241610739,
      "eval_overall_recall": 0.8934426229508197,
      "eval_runtime": 0.7431,
      "eval_samples_per_second": 258.387,
      "eval_steps_per_second": 8.075,
      "step": 48
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0274,
      "step": 96
    },
    {
      "epoch": 2.0,
      "eval_ad_f1": 0.8286852589641434,
      "eval_ad_precision": 0.8062015503875969,
      "eval_ad_recall": 0.8524590163934426,
      "eval_ad_support": 122,
      "eval_loss": 0.03221152722835541,
      "eval_overall_accuracy": 0.9910483389695643,
      "eval_overall_f1": 0.8286852589641434,
      "eval_overall_precision": 0.8062015503875969,
      "eval_overall_recall": 0.8524590163934426,
      "eval_runtime": 0.7362,
      "eval_samples_per_second": 260.794,
      "eval_steps_per_second": 8.15,
      "step": 96
    },
    {
      "epoch": 3.0,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0145,
      "step": 144
    },
    {
      "epoch": 3.0,
      "eval_ad_f1": 0.8537549407114624,
      "eval_ad_precision": 0.8244274809160306,
      "eval_ad_recall": 0.8852459016393442,
      "eval_ad_support": 122,
      "eval_loss": 0.03574167191982269,
      "eval_overall_accuracy": 0.9916451163715934,
      "eval_overall_f1": 0.8537549407114624,
      "eval_overall_precision": 0.8244274809160306,
      "eval_overall_recall": 0.8852459016393442,
      "eval_runtime": 0.7344,
      "eval_samples_per_second": 261.428,
      "eval_steps_per_second": 8.17,
      "step": 144
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0101,
      "step": 192
    },
    {
      "epoch": 4.0,
      "eval_ad_f1": 0.8582677165354332,
      "eval_ad_precision": 0.8257575757575758,
      "eval_ad_recall": 0.8934426229508197,
      "eval_ad_support": 122,
      "eval_loss": 0.03515293449163437,
      "eval_overall_accuracy": 0.9920429679729461,
      "eval_overall_f1": 0.8582677165354332,
      "eval_overall_precision": 0.8257575757575758,
      "eval_overall_recall": 0.8934426229508197,
      "eval_runtime": 0.7354,
      "eval_samples_per_second": 261.069,
      "eval_steps_per_second": 8.158,
      "step": 192
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.0065,
      "step": 240
    },
    {
      "epoch": 5.0,
      "eval_ad_f1": 0.8582677165354332,
      "eval_ad_precision": 0.8257575757575758,
      "eval_ad_recall": 0.8934426229508197,
      "eval_ad_support": 122,
      "eval_loss": 0.03596705570816994,
      "eval_overall_accuracy": 0.9922418937736225,
      "eval_overall_f1": 0.8582677165354332,
      "eval_overall_precision": 0.8257575757575758,
      "eval_overall_recall": 0.8934426229508197,
      "eval_runtime": 0.7358,
      "eval_samples_per_second": 260.929,
      "eval_steps_per_second": 8.154,
      "step": 240
    }
  ],
  "max_steps": 240,
  "num_train_epochs": 5,
  "total_flos": 178090660164636.0,
  "trial_name": null,
  "trial_params": null
}