trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00400026668444563,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 2.5444,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.9186,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018461538461538463,
      "loss": 1.638,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016923076923076923,
      "loss": 1.5763,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00015384615384615385,
      "loss": 1.5843,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00013846153846153847,
      "loss": 1.2616,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001230769230769231,
      "loss": 1.3111,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001076923076923077,
      "loss": 1.3044,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001076923076923077,
      "loss": 1.299,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.230769230769232e-05,
      "loss": 1.2492,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.692307692307693e-05,
      "loss": 1.1069,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.7699,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.615384615384616e-05,
      "loss": 1.1393,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.4198,
      "step": 14
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.2558,
      "step": 15
    },
    {
      "epoch": 0.0,
      "step": 15,
      "total_flos": 232910960836608.0,
      "train_loss": 1.4252451022466024,
      "train_runtime": 116.0587,
      "train_samples_per_second": 0.517,
      "train_steps_per_second": 0.129
    }
  ],
  "max_steps": 15,
  "num_train_epochs": 1,
  "total_flos": 232910960836608.0,
  "trial_name": null,
  "trial_params": null
}