checkpoint-345/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 345,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0001927536231884058,
      "loss": 2.497,
      "step": 25
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001855072463768116,
      "loss": 1.0576,
      "step": 50
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001782608695652174,
      "loss": 1.063,
      "step": 75
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001710144927536232,
      "loss": 1.5434,
      "step": 100
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000163768115942029,
      "loss": 1.1751,
      "step": 125
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001565217391304348,
      "loss": 0.9868,
      "step": 150
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00014927536231884058,
      "loss": 1.0466,
      "step": 175
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00014202898550724638,
      "loss": 0.7962,
      "step": 200
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001347826086956522,
      "loss": 1.0158,
      "step": 225
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00012753623188405797,
      "loss": 0.8366,
      "step": 250
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00012028985507246378,
      "loss": 1.2794,
      "step": 275
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00011304347826086956,
      "loss": 1.6535,
      "step": 300
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010579710144927538,
      "loss": 0.878,
      "step": 325
    }
  ],
  "max_steps": 690,
  "num_train_epochs": 2,
  "start_time": 1678594586.128044,
  "total_flos": 1.5748493096591032e+19,
  "trial_name": null,
  "trial_params": null
}