trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02627726266000976,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.5676,
      "step": 25
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.2721,
      "step": 50
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.181,
      "step": 75
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.1398,
      "step": 100
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.1887,
      "step": 125
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1021,
      "step": 150
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1441,
      "step": 175
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1414,
      "step": 200
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.2161,
      "step": 225
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.0418,
      "step": 250
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1488,
      "step": 275
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.0276,
      "step": 300
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1425,
      "step": 325
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.0713,
      "step": 350
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1438,
      "step": 375
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0475,
      "step": 400
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.1166,
      "step": 425
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0796,
      "step": 450
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.1399,
      "step": 475
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0803,
      "step": 500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.1041,
      "step": 525
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0854,
      "step": 550
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0958,
      "step": 575
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0094,
      "step": 600
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0519,
      "step": 625
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0341,
      "step": 650
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1016,
      "step": 675
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.0138,
      "step": 700
    }
  ],
  "max_steps": 26639,
  "num_train_epochs": 1,
  "total_flos": 1.749425782259712e+16,
  "trial_name": null,
  "trial_params": null
}