checkpoint-549/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "/tmp/model/checkpoint-549",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 549,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 162
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 189
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 216
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 243
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 270
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 297
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 324
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 351
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 378
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 405
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 432
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 459
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 486
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 513
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 540
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1690909090909091,
      "eval_f1_macro": 0.09132538710036761,
      "eval_f1_micro": 0.1690909090909091,
      "eval_f1_weighted": 0.08854425957244272,
      "eval_loss": NaN,
      "eval_precision_macro": 0.07907624633431085,
      "eval_precision_micro": 0.1690909090909091,
      "eval_precision_weighted": 0.08039189549453478,
      "eval_recall_macro": 0.18150387596899226,
      "eval_recall_micro": 0.1690909090909091,
      "eval_recall_weighted": 0.1690909090909091,
      "eval_runtime": 2.6849,
      "eval_samples_per_second": 204.847,
      "eval_steps_per_second": 25.699,
      "step": 549
    }
  ],
  "logging_steps": 27,
  "max_steps": 1647,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.7017698479807693e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}