checkpoint-300/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2800793558174816,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09335978527249388,
      "grad_norm": 5.347364902496338,
      "learning_rate": 9.897551417342852e-05,
      "loss": 4.6888,
      "step": 100
    },
    {
      "epoch": 0.09335978527249388,
      "eval_loss": 0.3825870752334595,
      "eval_runtime": 23.2535,
      "eval_samples_per_second": 3.741,
      "eval_steps_per_second": 3.741,
      "step": 100
    },
    {
      "epoch": 0.18671957054498775,
      "grad_norm": 5.412732124328613,
      "learning_rate": 9.374809314115647e-05,
      "loss": 2.3316,
      "step": 200
    },
    {
      "epoch": 0.18671957054498775,
      "eval_loss": 0.25006037950515747,
      "eval_runtime": 23.4002,
      "eval_samples_per_second": 3.718,
      "eval_steps_per_second": 3.718,
      "step": 200
    },
    {
      "epoch": 0.2800793558174816,
      "grad_norm": 2.9451260566711426,
      "learning_rate": 8.454375586546417e-05,
      "loss": 1.5881,
      "step": 300
    },
    {
      "epoch": 0.2800793558174816,
      "eval_loss": 0.1890459656715393,
      "eval_runtime": 23.2549,
      "eval_samples_per_second": 3.741,
      "eval_steps_per_second": 3.741,
      "step": 300
    }
  ],
  "logging_steps": 100,
  "max_steps": 1071,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.383029974375424e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}