trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.22522522522522523,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.5366,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2614,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.248,
      "step": 75
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.2142,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.1638,
      "step": 125
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.1349,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.2323,
      "step": 175
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.1278,
      "step": 200
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.1992,
      "step": 225
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.0986,
      "step": 250
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.2049,
      "step": 275
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 2.1108,
      "step": 300
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.1739,
      "step": 325
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 2.0718,
      "step": 350
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.1104,
      "step": 375
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.1098,
      "step": 400
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 2.1431,
      "step": 425
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 2.0492,
      "step": 450
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.1305,
      "step": 475
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 2.0664,
      "step": 500
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 2.117,
      "step": 525
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 2.0769,
      "step": 550
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.1066,
      "step": 575
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.9691,
      "step": 600
    }
  ],
  "max_steps": 2664,
  "num_train_epochs": 1,
  "total_flos": 1.51942000140288e+16,
  "trial_name": null,
  "trial_params": null
}