results/checkpoint-77/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9935483870967742,
  "eval_steps": 500,
  "global_step": 77,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14,
      "grad_norm": 0.6195777654647827,
      "learning_rate": 0.00019549667548552556,
      "loss": 3.2597,
      "step": 11
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.6481589674949646,
      "learning_rate": 0.00017146733860429612,
      "loss": 2.9913,
      "step": 22
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.88404381275177,
      "learning_rate": 0.00013171912885891063,
      "loss": 2.9169,
      "step": 33
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.6059058904647827,
      "learning_rate": 8.499446016553474e-05,
      "loss": 2.8932,
      "step": 44
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.6640863418579102,
      "learning_rate": 4.1570182637163155e-05,
      "loss": 2.9104,
      "step": 55
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.660681426525116,
      "learning_rate": 1.0997242356532334e-05,
      "loss": 2.8961,
      "step": 66
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.8390025496482849,
      "learning_rate": 0.0,
      "loss": 2.9082,
      "step": 77
    }
  ],
  "logging_steps": 11,
  "max_steps": 77,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 8847141698304000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}