trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.42914979757085,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.579,
      "step": 5
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.275,
      "step": 10
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.1907,
      "step": 15
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.1357,
      "step": 20
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.0673,
      "step": 25
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 1.019,
      "step": 30
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.0114,
      "step": 35
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.9641,
      "step": 40
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 0.9895,
      "step": 45
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 0.9548,
      "step": 50
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 0.943,
      "step": 55
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 0.9927,
      "step": 60
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0002,
      "loss": 1.0159,
      "step": 65
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0002,
      "loss": 0.9183,
      "step": 70
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0002,
      "loss": 0.8964,
      "step": 75
    }
  ],
  "max_steps": 120,
  "num_train_epochs": 4,
  "total_flos": 8.24205694844928e+17,
  "trial_name": null,
  "trial_params": null
}