checkpoint-500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4667989263624694,
  "eval_steps": 250,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2333994631812347,
      "grad_norm": 6.351889133453369,
      "learning_rate": 8.987402315498223e-05,
      "loss": 0.3368,
      "step": 250
    },
    {
      "epoch": 0.2333994631812347,
      "eval_loss": 0.18190699815750122,
      "eval_runtime": 40.5235,
      "eval_samples_per_second": 2.147,
      "eval_steps_per_second": 2.147,
      "step": 250
    },
    {
      "epoch": 0.4667989263624694,
      "grad_norm": 3.1040618419647217,
      "learning_rate": 5.828471682626175e-05,
      "loss": 0.1395,
      "step": 500
    },
    {
      "epoch": 0.4667989263624694,
      "eval_loss": 0.12028516829013824,
      "eval_runtime": 40.8355,
      "eval_samples_per_second": 2.13,
      "eval_steps_per_second": 2.13,
      "step": 500
    }
  ],
  "logging_steps": 250,
  "max_steps": 1071,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.780342084773376e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}