checkpoint-127/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "/tmp/model/checkpoint-127",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 127,
  "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": 6
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 114
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.20078740157480315,
      "eval_f1_macro": 0.05573770491803279,
      "eval_f1_micro": 0.20078740157480315,
      "eval_f1_weighted": 0.06714857364140958,
      "eval_loss": NaN,
      "eval_precision_macro": 0.03346456692913386,
      "eval_precision_micro": 0.20078740157480315,
      "eval_precision_weighted": 0.040315580631161266,
      "eval_recall_macro": 0.16666666666666666,
      "eval_recall_micro": 0.20078740157480315,
      "eval_recall_weighted": 0.20078740157480315,
      "eval_runtime": 4.7306,
      "eval_samples_per_second": 53.694,
      "eval_steps_per_second": 3.382,
      "step": 127
    }
  ],
  "logging_steps": 6,
  "max_steps": 381,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2.156144787965952e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}