last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0018793459875963165,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018793459875963165,
      "grad_norm": 0.40805867314338684,
      "learning_rate": 2e-05,
      "loss": 2.0097,
      "step": 1
    },
    {
      "epoch": 0.00018793459875963165,
      "eval_loss": 2.225860595703125,
      "eval_runtime": 104.7616,
      "eval_samples_per_second": 10.7,
      "eval_steps_per_second": 10.7,
      "step": 1
    },
    {
      "epoch": 0.0003758691975192633,
      "grad_norm": 0.3363264501094818,
      "learning_rate": 4e-05,
      "loss": 2.0424,
      "step": 2
    },
    {
      "epoch": 0.0005638037962788949,
      "grad_norm": 0.4387308359146118,
      "learning_rate": 6e-05,
      "loss": 2.2437,
      "step": 3
    },
    {
      "epoch": 0.0005638037962788949,
      "eval_loss": 2.223356246948242,
      "eval_runtime": 105.324,
      "eval_samples_per_second": 10.643,
      "eval_steps_per_second": 10.643,
      "step": 3
    },
    {
      "epoch": 0.0007517383950385266,
      "grad_norm": 0.30487483739852905,
      "learning_rate": 8e-05,
      "loss": 2.1183,
      "step": 4
    },
    {
      "epoch": 0.0009396729937981583,
      "grad_norm": 0.44409823417663574,
      "learning_rate": 0.0001,
      "loss": 2.2092,
      "step": 5
    },
    {
      "epoch": 0.0011276075925577898,
      "grad_norm": 0.31591424345970154,
      "learning_rate": 0.00012,
      "loss": 2.223,
      "step": 6
    },
    {
      "epoch": 0.0011276075925577898,
      "eval_loss": 2.2032065391540527,
      "eval_runtime": 104.9365,
      "eval_samples_per_second": 10.683,
      "eval_steps_per_second": 10.683,
      "step": 6
    },
    {
      "epoch": 0.0013155421913174216,
      "grad_norm": 0.49352651834487915,
      "learning_rate": 0.00014,
      "loss": 2.1991,
      "step": 7
    },
    {
      "epoch": 0.0015034767900770532,
      "grad_norm": 0.3866937458515167,
      "learning_rate": 0.00016,
      "loss": 2.1441,
      "step": 8
    },
    {
      "epoch": 0.001691411388836685,
      "grad_norm": 0.3655875623226166,
      "learning_rate": 0.00018,
      "loss": 2.0592,
      "step": 9
    },
    {
      "epoch": 0.001691411388836685,
      "eval_loss": 2.1501598358154297,
      "eval_runtime": 105.4766,
      "eval_samples_per_second": 10.628,
      "eval_steps_per_second": 10.628,
      "step": 9
    },
    {
      "epoch": 0.0018793459875963165,
      "grad_norm": 0.36404484510421753,
      "learning_rate": 0.0002,
      "loss": 2.0794,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 695723045683200.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}