last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.103030303030303,
  "eval_steps": 25,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19393939393939394,
      "grad_norm": 0.19390009343624115,
      "learning_rate": 9.913533761814537e-05,
      "loss": 10.3856,
      "step": 1
    },
    {
      "epoch": 0.19393939393939394,
      "eval_loss": 10.385096549987793,
      "eval_runtime": 0.1722,
      "eval_samples_per_second": 290.375,
      "eval_steps_per_second": 75.497,
      "step": 1
    },
    {
      "epoch": 0.3878787878787879,
      "grad_norm": 0.20893342792987823,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3836,
      "step": 2
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.20478656888008118,
      "learning_rate": 9.241613255361455e-05,
      "loss": 10.3844,
      "step": 3
    },
    {
      "epoch": 0.7757575757575758,
      "grad_norm": 0.18872524797916412,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3818,
      "step": 4
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.2039109617471695,
      "learning_rate": 8.000066048588211e-05,
      "loss": 10.3821,
      "step": 5
    },
    {
      "epoch": 1.1636363636363636,
      "grad_norm": 0.32059603929519653,
      "learning_rate": 7.222075445642904e-05,
      "loss": 19.0569,
      "step": 6
    },
    {
      "epoch": 1.3575757575757577,
      "grad_norm": 0.20104046165943146,
      "learning_rate": 6.377906449072578e-05,
      "loss": 10.1499,
      "step": 7
    },
    {
      "epoch": 1.5515151515151515,
      "grad_norm": 0.2074582725763321,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.337,
      "step": 8
    },
    {
      "epoch": 1.7454545454545456,
      "grad_norm": 0.20364588499069214,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 10.2317,
      "step": 9
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": 0.22322978079319,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.3208,
      "step": 10
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.3697808086872101,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 18.9844,
      "step": 11
    },
    {
      "epoch": 2.327272727272727,
      "grad_norm": 0.20842325687408447,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.0307,
      "step": 12
    },
    {
      "epoch": 2.5212121212121215,
      "grad_norm": 0.2196199744939804,
      "learning_rate": 1.758386744638546e-05,
      "loss": 10.6077,
      "step": 13
    },
    {
      "epoch": 2.7151515151515153,
      "grad_norm": 0.19635999202728271,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 9.9391,
      "step": 14
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.2330584079027176,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.1949,
      "step": 15
    },
    {
      "epoch": 3.103030303030303,
      "grad_norm": 0.3534669280052185,
      "learning_rate": 1e-05,
      "loss": 19.0088,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "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": 13685779070976.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}