checkpoint-26/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "/tmp/model/checkpoint-26",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.09803921568627451,
      "eval_f1_macro": 0.029761904761904757,
      "eval_f1_micro": 0.09803921568627451,
      "eval_f1_weighted": 0.01750700280112045,
      "eval_loss": NaN,
      "eval_precision_macro": 0.016339869281045753,
      "eval_precision_micro": 0.09803921568627451,
      "eval_precision_weighted": 0.009611687812379853,
      "eval_recall_macro": 0.16666666666666666,
      "eval_recall_micro": 0.09803921568627451,
      "eval_recall_weighted": 0.09803921568627451,
      "eval_runtime": 0.3417,
      "eval_samples_per_second": 149.24,
      "eval_steps_per_second": 11.705,
      "step": 26
    }
  ],
  "logging_steps": 1,
  "max_steps": 260,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.557644831963136e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}