last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.2903225806451615,
  "eval_steps": 25,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 2.504321813583374,
      "learning_rate": 9.846666218300807e-05,
      "loss": 4.2511,
      "step": 1
    },
    {
      "epoch": 0.25806451612903225,
      "eval_loss": 4.585047721862793,
      "eval_runtime": 3.5897,
      "eval_samples_per_second": 13.929,
      "eval_steps_per_second": 3.622,
      "step": 1
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 2.647432565689087,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.218,
      "step": 2
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 3.1867308616638184,
      "learning_rate": 8.681980515339464e-05,
      "loss": 3.7796,
      "step": 3
    },
    {
      "epoch": 1.096774193548387,
      "grad_norm": 3.8406894207000732,
      "learning_rate": 7.75e-05,
      "loss": 4.349,
      "step": 4
    },
    {
      "epoch": 1.3548387096774195,
      "grad_norm": 2.370175838470459,
      "learning_rate": 6.664685702961344e-05,
      "loss": 2.6897,
      "step": 5
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 1.7631345987319946,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.6366,
      "step": 6
    },
    {
      "epoch": 1.870967741935484,
      "grad_norm": 2.5610830783843994,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 3.2329,
      "step": 7
    },
    {
      "epoch": 2.193548387096774,
      "grad_norm": 1.9402637481689453,
      "learning_rate": 3.250000000000001e-05,
      "loss": 2.8209,
      "step": 8
    },
    {
      "epoch": 2.4516129032258065,
      "grad_norm": 1.3551928997039795,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 2.3604,
      "step": 9
    },
    {
      "epoch": 2.709677419354839,
      "grad_norm": 1.3063544034957886,
      "learning_rate": 1.602885682970026e-05,
      "loss": 2.5761,
      "step": 10
    },
    {
      "epoch": 3.032258064516129,
      "grad_norm": 1.7029117345809937,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 3.0796,
      "step": 11
    },
    {
      "epoch": 3.2903225806451615,
      "grad_norm": 1.230550765991211,
      "learning_rate": 1e-05,
      "loss": 2.1148,
      "step": 12
    }
  ],
  "logging_steps": 1,
  "max_steps": 12,
  "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": 1.3497738745557811e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}