trainer_state.json

{
  "best_metric": 1.114396333694458,
  "best_model_checkpoint": "./beans_outputs/checkpoint-10",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4375,
      "eval_loss": 1.1243417263031006,
      "eval_runtime": 0.3336,
      "eval_samples_per_second": 47.962,
      "eval_steps_per_second": 5.995,
      "step": 2
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.375,
      "eval_loss": 1.1203868389129639,
      "eval_runtime": 0.2032,
      "eval_samples_per_second": 78.744,
      "eval_steps_per_second": 9.843,
      "step": 4
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.375,
      "eval_loss": 1.1172332763671875,
      "eval_runtime": 0.1981,
      "eval_samples_per_second": 80.755,
      "eval_steps_per_second": 10.094,
      "step": 6
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.375,
      "eval_loss": 1.1152395009994507,
      "eval_runtime": 0.1941,
      "eval_samples_per_second": 82.414,
      "eval_steps_per_second": 10.302,
      "step": 8
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.9751,
      "step": 10
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.375,
      "eval_loss": 1.114396333694458,
      "eval_runtime": 0.189,
      "eval_samples_per_second": 84.659,
      "eval_steps_per_second": 10.582,
      "step": 10
    },
    {
      "epoch": 5.0,
      "step": 10,
      "total_flos": 6199414732062720.0,
      "train_loss": 0.9750574111938477,
      "train_runtime": 26.3663,
      "train_samples_per_second": 3.034,
      "train_steps_per_second": 0.379
    }
  ],
  "logging_steps": 10,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 6199414732062720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}