tmp-checkpoint-500/trainer_state.json

{
  "best_metric": 0.0355601739229453,
  "best_model_checkpoint": "fydhfzh/sewd_classifier\\checkpoint-500",
  "epoch": 1.9398642095053347,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "eval_accuracy": 0.015776699029126214,
      "eval_binary": 0.12427184466019374,
      "eval_f1": 0.0021836259473444657,
      "eval_loss": 4.4300618171691895,
      "eval_precision": 0.0012509378194052938,
      "eval_recall": 0.015776699029126214,
      "eval_runtime": 1.5569,
      "eval_samples_per_second": 529.245,
      "eval_steps_per_second": 16.699,
      "step": 50
    },
    {
      "epoch": 0.39,
      "eval_accuracy": 0.014563106796116505,
      "eval_binary": 0.17548543689320378,
      "eval_f1": 0.0013947717644465854,
      "eval_loss": 4.409471035003662,
      "eval_precision": 0.0009291296564070783,
      "eval_recall": 0.014563106796116505,
      "eval_runtime": 1.3313,
      "eval_samples_per_second": 618.964,
      "eval_steps_per_second": 19.53,
      "step": 100
    },
    {
      "epoch": 0.58,
      "eval_accuracy": 0.025485436893203883,
      "eval_binary": 0.22245145631068086,
      "eval_f1": 0.008549061468070154,
      "eval_loss": 4.337551593780518,
      "eval_precision": 0.011859165691412587,
      "eval_recall": 0.025485436893203883,
      "eval_runtime": 1.4169,
      "eval_samples_per_second": 581.534,
      "eval_steps_per_second": 18.349,
      "step": 150
    },
    {
      "epoch": 0.78,
      "eval_accuracy": 0.03640776699029126,
      "eval_binary": 0.2802184466019448,
      "eval_f1": 0.014380764940975713,
      "eval_loss": 4.227560520172119,
      "eval_precision": 0.032203883955239945,
      "eval_recall": 0.03640776699029126,
      "eval_runtime": 1.5427,
      "eval_samples_per_second": 534.121,
      "eval_steps_per_second": 16.853,
      "step": 200
    },
    {
      "epoch": 0.97,
      "eval_accuracy": 0.05339805825242718,
      "eval_binary": 0.3122572815534021,
      "eval_f1": 0.02055877629770541,
      "eval_loss": 4.134052276611328,
      "eval_precision": 0.021501409455781946,
      "eval_recall": 0.05339805825242718,
      "eval_runtime": 1.6496,
      "eval_samples_per_second": 499.507,
      "eval_steps_per_second": 15.761,
      "step": 250
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.8999079465866089,
      "learning_rate": 9e-06,
      "loss": 4.3244,
      "step": 257
    },
    {
      "epoch": 1.16,
      "eval_accuracy": 0.050970873786407765,
      "eval_binary": 0.3190533980582566,
      "eval_f1": 0.017415580929307544,
      "eval_loss": 4.047242164611816,
      "eval_precision": 0.013874415351638724,
      "eval_recall": 0.050970873786407765,
      "eval_runtime": 1.6726,
      "eval_samples_per_second": 492.646,
      "eval_steps_per_second": 15.545,
      "step": 300
    },
    {
      "epoch": 1.36,
      "eval_accuracy": 0.06674757281553398,
      "eval_binary": 0.33737864077670343,
      "eval_f1": 0.021109602049388235,
      "eval_loss": 3.9619970321655273,
      "eval_precision": 0.015144910708081936,
      "eval_recall": 0.06674757281553398,
      "eval_runtime": 1.544,
      "eval_samples_per_second": 533.67,
      "eval_steps_per_second": 16.839,
      "step": 350
    },
    {
      "epoch": 1.55,
      "eval_accuracy": 0.08495145631067962,
      "eval_binary": 0.3495145631068007,
      "eval_f1": 0.0362232684065308,
      "eval_loss": 3.8773157596588135,
      "eval_precision": 0.043156601029494375,
      "eval_recall": 0.08495145631067962,
      "eval_runtime": 1.6284,
      "eval_samples_per_second": 506.031,
      "eval_steps_per_second": 15.967,
      "step": 400
    },
    {
      "epoch": 1.75,
      "eval_accuracy": 0.08859223300970874,
      "eval_binary": 0.35618932038835416,
      "eval_f1": 0.032488157810960344,
      "eval_loss": 3.807878017425537,
      "eval_precision": 0.027817262527314878,
      "eval_recall": 0.08859223300970874,
      "eval_runtime": 1.5357,
      "eval_samples_per_second": 536.564,
      "eval_steps_per_second": 16.93,
      "step": 450
    },
    {
      "epoch": 1.94,
      "eval_accuracy": 0.08859223300970874,
      "eval_binary": 0.3560679611650534,
      "eval_f1": 0.0355601739229453,
      "eval_loss": 3.7442734241485596,
      "eval_precision": 0.03374590733472966,
      "eval_recall": 0.08859223300970874,
      "eval_runtime": 1.5994,
      "eval_samples_per_second": 515.209,
      "eval_steps_per_second": 16.257,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2570,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 2.1424965481558547e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}