last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15600624024961,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0031201248049922,
      "eval_loss": NaN,
      "eval_runtime": 15.2229,
      "eval_samples_per_second": 8.868,
      "eval_steps_per_second": 4.467,
      "step": 1
    },
    {
      "epoch": 0.015600624024960999,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.031201248049921998,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.031201248049921998,
      "eval_loss": NaN,
      "eval_runtime": 14.3002,
      "eval_samples_per_second": 9.44,
      "eval_steps_per_second": 4.755,
      "step": 10
    },
    {
      "epoch": 0.046801872074883,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.062402496099843996,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.062402496099843996,
      "eval_loss": NaN,
      "eval_runtime": 14.3506,
      "eval_samples_per_second": 9.407,
      "eval_steps_per_second": 4.738,
      "step": 20
    },
    {
      "epoch": 0.078003120124805,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.093603744149766,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.093603744149766,
      "eval_loss": NaN,
      "eval_runtime": 14.3675,
      "eval_samples_per_second": 9.396,
      "eval_steps_per_second": 4.733,
      "step": 30
    },
    {
      "epoch": 0.10920436817472699,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.12480499219968799,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.12480499219968799,
      "eval_loss": NaN,
      "eval_runtime": 14.3931,
      "eval_samples_per_second": 9.379,
      "eval_steps_per_second": 4.724,
      "step": 40
    },
    {
      "epoch": 0.14040561622464898,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.15600624024961,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.15600624024961,
      "eval_loss": NaN,
      "eval_runtime": 14.4202,
      "eval_samples_per_second": 9.362,
      "eval_steps_per_second": 4.716,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.72349919854592e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}