last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.38095238095238093,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0380952380952381,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0380952380952381,
      "eval_loss": NaN,
      "eval_runtime": 1.2364,
      "eval_samples_per_second": 9.706,
      "eval_steps_per_second": 4.853,
      "step": 1
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.11428571428571428,
      "eval_loss": NaN,
      "eval_runtime": 0.6721,
      "eval_samples_per_second": 17.856,
      "eval_steps_per_second": 8.928,
      "step": 3
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.22857142857142856,
      "eval_loss": NaN,
      "eval_runtime": 0.6698,
      "eval_samples_per_second": 17.916,
      "eval_steps_per_second": 8.958,
      "step": 6
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.34285714285714286,
      "eval_loss": NaN,
      "eval_runtime": 0.6704,
      "eval_samples_per_second": 17.901,
      "eval_steps_per_second": 8.95,
      "step": 9
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 3446998397091840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}