trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 23061,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 0.003427580225498699,
      "loss": 5.0966,
      "step": 1000
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.006896790980052038,
      "loss": 9.0282,
      "step": 2000
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.01020294882914137,
      "loss": 9.2789,
      "step": 3000
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.010206418039895923,
      "loss": 812422.208,
      "step": 4000
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 5000
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 6000
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 7000
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 8000
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 9000
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 10000
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 11000
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 12000
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 13000
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 14000
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 15000
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 16000
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 17000
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 18000
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 19000
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 20000
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 21000
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 22000
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 23000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 57650,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 5.243846810778206e+19,
  "trial_name": null,
  "trial_params": null
}