checkpoint-4000/trainer_state.json

{
  "best_metric": 5.885306358337402,
  "best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained_recent/fr/wikipedia_clm_13_full/checkpoint-4000",
  "epoch": 1.9398642095053347,
  "eval_steps": 4000,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9398642095053347,
      "grad_norm": 1.9506170749664307,
      "learning_rate": 4e-05,
      "loss": 6.8417,
      "step": 4000
    },
    {
      "epoch": 1.9398642095053347,
      "eval_loss": 5.885306358337402,
      "eval_runtime": 1.7357,
      "eval_samples_per_second": 984.627,
      "eval_steps_per_second": 61.647,
      "step": 4000
    }
  ],
  "logging_steps": 4000,
  "max_steps": 400000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 194,
  "save_steps": 4000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 310508349161472.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}