last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06917423259835712,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023058077532785706,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0023058077532785706,
      "eval_loss": NaN,
      "eval_runtime": 132.6571,
      "eval_samples_per_second": 5.51,
      "eval_steps_per_second": 2.759,
      "step": 1
    },
    {
      "epoch": 0.004611615506557141,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.006917423259835711,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.009223231013114282,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.011529038766392852,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.013834846519671422,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.016140654272949993,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.018446462026228565,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.018446462026228565,
      "eval_loss": NaN,
      "eval_runtime": 44.1532,
      "eval_samples_per_second": 16.556,
      "eval_steps_per_second": 8.289,
      "step": 8
    },
    {
      "epoch": 0.020752269779507133,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.023058077532785704,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.025363885286064276,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.027669693039342844,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.029975500792621415,
      "grad_norm": NaN,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.03228130854589999,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.03458711629917856,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.03689292405245713,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.03689292405245713,
      "eval_loss": NaN,
      "eval_runtime": 44.1216,
      "eval_samples_per_second": 16.568,
      "eval_steps_per_second": 8.295,
      "step": 16
    },
    {
      "epoch": 0.039198731805735694,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.041504539559014265,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.04381034731229284,
      "grad_norm": NaN,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.04611615506557141,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.04842196281884998,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.05072777057212855,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.053033578325407116,
      "grad_norm": NaN,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.05533938607868569,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.05533938607868569,
      "eval_loss": NaN,
      "eval_runtime": 44.1472,
      "eval_samples_per_second": 16.558,
      "eval_steps_per_second": 8.29,
      "step": 24
    },
    {
      "epoch": 0.05764519383196426,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.05995100158524283,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.0622568093385214,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.06456261709179997,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.06686842484507854,
      "grad_norm": NaN,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.06917423259835712,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 8,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.135045208375296e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}