checkpoint-29/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 2108.397216796875,
      "learning_rate": 2.5454545454545454e-08,
      "loss": 1035.4573,
      "step": 5
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 2107.33642578125,
      "learning_rate": 5.727272727272728e-08,
      "loss": 1065.6187,
      "step": 10
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 2219.214111328125,
      "learning_rate": 8.90909090909091e-08,
      "loss": 1036.3791,
      "step": 15
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 1936.712890625,
      "learning_rate": 1.2090909090909092e-07,
      "loss": 1035.5998,
      "step": 20
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 2196.76318359375,
      "learning_rate": 1.5272727272727273e-07,
      "loss": 1064.9285,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 58,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3605990243426e+17,
  "train_batch_size": 14,
  "trial_name": null,
  "trial_params": null
}