last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1153846153846154,
  "eval_steps": 5,
  "global_step": 7,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15384615384615385,
      "eval_loss": 1.4272022247314453,
      "eval_runtime": 0.3995,
      "eval_samples_per_second": 15.019,
      "eval_steps_per_second": 5.006,
      "step": 1
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 7.9876298904418945,
      "learning_rate": 0.00012,
      "loss": 5.6171,
      "step": 3
    },
    {
      "epoch": 0.7692307692307693,
      "eval_loss": 0.9438693523406982,
      "eval_runtime": 0.3983,
      "eval_samples_per_second": 15.062,
      "eval_steps_per_second": 5.021,
      "step": 5
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 7.793228626251221,
      "learning_rate": 0.0001,
      "loss": 4.2374,
      "step": 6
    }
  ],
  "logging_steps": 3,
  "max_steps": 7,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4921906490769408.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}