checkpoint-250/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.6744054555892944,
      "learning_rate": 0.000495,
      "loss": 8.731851196289062,
      "step": 100
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.6788963079452515,
      "learning_rate": 0.00017,
      "loss": 7.8947900390625,
      "step": 200
    }
  ],
  "logging_steps": 100,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 65323008000000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}