last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007545746085644218,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025152486952147396,
      "eval_loss": NaN,
      "eval_runtime": 221.5767,
      "eval_samples_per_second": 7.559,
      "eval_steps_per_second": 3.782,
      "step": 1
    },
    {
      "epoch": 0.0007545746085644218,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0015091492171288435,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0020121989561717917,
      "eval_loss": NaN,
      "eval_runtime": 221.6389,
      "eval_samples_per_second": 7.557,
      "eval_steps_per_second": 3.781,
      "step": 8
    },
    {
      "epoch": 0.0022637238256932655,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.003018298434257687,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.003772873042822109,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.004024397912343583,
      "eval_loss": NaN,
      "eval_runtime": 221.6255,
      "eval_samples_per_second": 7.558,
      "eval_steps_per_second": 3.781,
      "step": 16
    },
    {
      "epoch": 0.004527447651386531,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.005282022259950953,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.006036596868515374,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.006036596868515374,
      "eval_loss": NaN,
      "eval_runtime": 221.627,
      "eval_samples_per_second": 7.558,
      "eval_steps_per_second": 3.781,
      "step": 24
    },
    {
      "epoch": 0.006791171477079796,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.007545746085644218,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "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": 8384528787701760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}