checkpoint-275/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "/tmp/model/checkpoint-275",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 275,
  "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": 13
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 104
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 117
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 143
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 156
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 169
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 182
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 208
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 221
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 234
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 247
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 260
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 273
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.18181818181818182,
      "eval_f1_macro": 0.06153846153846154,
      "eval_f1_micro": 0.18181818181818182,
      "eval_f1_weighted": 0.055944055944055944,
      "eval_loss": NaN,
      "eval_precision_macro": 0.03636363636363636,
      "eval_precision_micro": 0.18181818181818182,
      "eval_precision_weighted": 0.03305785123966942,
      "eval_recall_macro": 0.2,
      "eval_recall_micro": 0.18181818181818182,
      "eval_recall_weighted": 0.18181818181818182,
      "eval_runtime": 2.5061,
      "eval_samples_per_second": 219.463,
      "eval_steps_per_second": 13.966,
      "step": 275
    }
  ],
  "logging_steps": 13,
  "max_steps": 825,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.7017698479807693e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}