trainer_state.json

{
  "best_metric": 0.2658565044403076,
  "best_model_checkpoint": "./results/checkpoint-300",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.3161751329898834,
      "eval_runtime": 9.883,
      "eval_samples_per_second": 121.42,
      "eval_steps_per_second": 15.178,
      "step": 150
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.2658565044403076,
      "eval_runtime": 9.8592,
      "eval_samples_per_second": 121.714,
      "eval_steps_per_second": 15.214,
      "step": 300
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.26993614435195923,
      "eval_runtime": 9.8656,
      "eval_samples_per_second": 121.634,
      "eval_steps_per_second": 15.204,
      "step": 450
    },
    {
      "epoch": 3.33,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.281,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.2938203513622284,
      "eval_runtime": 9.8632,
      "eval_samples_per_second": 121.664,
      "eval_steps_per_second": 15.208,
      "step": 600
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.31206923723220825,
      "eval_runtime": 9.8546,
      "eval_samples_per_second": 121.771,
      "eval_steps_per_second": 15.221,
      "step": 750
    }
  ],
  "logging_steps": 500,
  "max_steps": 900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "total_flos": 6314665328640000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}