checkpoint-204/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.978102189781022,
  "eval_steps": 500,
  "global_step": 204,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.36,
      "grad_norm": 1.607978105545044,
      "learning_rate": 0.00019672131147540985,
      "loss": 1.9632,
      "step": 25
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.4215347468852997,
      "learning_rate": 0.00016939890710382515,
      "loss": 1.2822,
      "step": 50
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.6183569431304932,
      "learning_rate": 0.00014316939890710384,
      "loss": 1.2407,
      "step": 75
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.49381059408187866,
      "learning_rate": 0.00011584699453551913,
      "loss": 1.1787,
      "step": 100
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.47651711106300354,
      "learning_rate": 8.852459016393443e-05,
      "loss": 1.1866,
      "step": 125
    },
    {
      "epoch": 2.19,
      "grad_norm": 0.5027020573616028,
      "learning_rate": 6.120218579234973e-05,
      "loss": 1.1836,
      "step": 150
    },
    {
      "epoch": 2.55,
      "grad_norm": 0.5709903240203857,
      "learning_rate": 3.387978142076503e-05,
      "loss": 1.1499,
      "step": 175
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.6197895407676697,
      "learning_rate": 6.557377049180328e-06,
      "loss": 1.1439,
      "step": 200
    }
  ],
  "logging_steps": 25,
  "max_steps": 204,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3.568349359374336e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}