last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.076923076923077,
  "eval_steps": 50,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 30.686565399169922,
      "learning_rate": 1e-05,
      "loss": 1.5426,
      "step": 1
    },
    {
      "epoch": 0.3076923076923077,
      "eval_loss": 1.6406216621398926,
      "eval_runtime": 0.1225,
      "eval_samples_per_second": 48.974,
      "eval_steps_per_second": 16.325,
      "step": 1
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 28.873037338256836,
      "learning_rate": 2e-05,
      "loss": 1.7179,
      "step": 2
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 27.685832977294922,
      "learning_rate": 3e-05,
      "loss": 1.2476,
      "step": 3
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 29.89850616455078,
      "learning_rate": 4e-05,
      "loss": 1.3934,
      "step": 4
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 13.405213356018066,
      "learning_rate": 5e-05,
      "loss": 0.5349,
      "step": 5
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 4.893474102020264,
      "learning_rate": 6e-05,
      "loss": 0.3112,
      "step": 6
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 5.524457931518555,
      "learning_rate": 7e-05,
      "loss": 0.3404,
      "step": 7
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 2.286975860595703,
      "learning_rate": 8e-05,
      "loss": 0.2092,
      "step": 8
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 2.909632921218872,
      "learning_rate": 9e-05,
      "loss": 0.188,
      "step": 9
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 5.125063896179199,
      "learning_rate": 0.0001,
      "loss": 0.2177,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 751111886340096.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}