last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007919223916056227,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002639741305352075,
      "eval_loss": NaN,
      "eval_runtime": 120.7603,
      "eval_samples_per_second": 13.208,
      "eval_steps_per_second": 6.608,
      "step": 1
    },
    {
      "epoch": 0.0007919223916056226,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0013198706526760377,
      "eval_loss": NaN,
      "eval_runtime": 120.895,
      "eval_samples_per_second": 13.193,
      "eval_steps_per_second": 6.601,
      "step": 5
    },
    {
      "epoch": 0.0015838447832112453,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.002375767174816868,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0026397413053520754,
      "eval_loss": NaN,
      "eval_runtime": 120.9255,
      "eval_samples_per_second": 13.19,
      "eval_steps_per_second": 6.599,
      "step": 10
    },
    {
      "epoch": 0.0031676895664224905,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0039596119580281135,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0039596119580281135,
      "eval_loss": NaN,
      "eval_runtime": 120.9544,
      "eval_samples_per_second": 13.187,
      "eval_steps_per_second": 6.598,
      "step": 15
    },
    {
      "epoch": 0.004751534349633736,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.005279482610704151,
      "eval_loss": NaN,
      "eval_runtime": 120.9532,
      "eval_samples_per_second": 13.187,
      "eval_steps_per_second": 6.598,
      "step": 20
    },
    {
      "epoch": 0.0055434567412393585,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.006335379132844981,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.006599353263380189,
      "eval_loss": NaN,
      "eval_runtime": 120.9571,
      "eval_samples_per_second": 13.186,
      "eval_steps_per_second": 6.597,
      "step": 25
    },
    {
      "epoch": 0.0071273015244506036,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.007919223916056227,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.007919223916056227,
      "eval_loss": NaN,
      "eval_runtime": 120.9635,
      "eval_samples_per_second": 13.186,
      "eval_steps_per_second": 6.597,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.054694248022016e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}