trainer_state.json

{
  "best_metric": 2.451780080795288,
  "best_model_checkpoint": "/content/Model/checkpoint-8",
  "epoch": 0.12,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.7323,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.7914,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.7974,
      "step": 3
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.7408,
      "step": 4
    },
    {
      "epoch": 0.06,
      "eval_loss": 2.6886792182922363,
      "eval_runtime": 275.0654,
      "eval_samples_per_second": 3.912,
      "eval_steps_per_second": 0.491,
      "step": 4
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00015,
      "loss": 2.6641,
      "step": 5
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.604,
      "step": 6
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00020999999999999998,
      "loss": 2.5921,
      "step": 7
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00023999999999999998,
      "loss": 2.5239,
      "step": 8
    },
    {
      "epoch": 0.12,
      "eval_loss": 2.451780080795288,
      "eval_runtime": 274.9467,
      "eval_samples_per_second": 3.913,
      "eval_steps_per_second": 0.491,
      "step": 8
    }
  ],
  "max_steps": 10,
  "num_train_epochs": 1,
  "total_flos": 1.0631008082460672e+16,
  "trial_name": null,
  "trial_params": null
}